JP4127214B2 - Sound source discrimination device and its discrimination method - Google Patents

Description

  The present invention relates to a sound source discriminating apparatus and a discriminating method for discriminating the cause of occurrence of a sound source whose occurrence cause is unknown, and in particular, the cause of occurrence is covered with an exterior cover partly formed with an opening. The present invention relates to a sound source discriminating apparatus and a discriminating method effective for estimating and discriminating the cause of occurrence of plural kinds of sounds included in noise emitted from a mechanical device having an unknown plural kinds of sound sources.

  In recent years, there has been a demand for improvement in the office environment in order to support improvement in comfort and intellectual productivity in the office. In response to such a movement, for example, an image forming apparatus such as a copying machine or a printer used in an office is required to reduce noise generated from the apparatus.

  FIG. 4 shows a time waveform of noise generated during operation of a printer using a general electrophotographic system. As shown in this figure, it can be seen that the sound pressure of the noise varies with time. A waveform portion indicated by an arrow in the drawing indicates a portion where a sound having a high sound pressure for a short time of about several tens to several hundred milliseconds, that is, a so-called impact sound is generated. Such a sound called an impact sound is generated by a collision between parts, a collision between a sheet and a part, or the like. Specifically, when the moving parts represented by solenoids, electromagnetic clutches, motors, etc. operate, or when the paper leading edge and the alignment member collide with each other in the paper alignment section, the paper trailing edge is caused by the conveyance guide member, etc. Occurs when the passage is released from the holding state.

  Such a sound such as an impact sound generally shows a large fluctuation in sound pressure in a short time, and therefore, it is easily recognized by humans and is likely to cause discomfort among noises.

  For this reason, at the time of product development that requires noise countermeasures, product development that focuses on the reduction of sound such as impact noise is often performed. However, in the case of the above-described image forming apparatus, it is very difficult to specify the cause of the occurrence of the impact sound.

  This is because image forming apparatuses such as copying machines and printers have orders of magnitude of moving parts and related parts compared to general household electrical appliances and mechanical structures, and the moving parts have various timings. This is because sound is generated from various sound sources at various timings, and a plurality of types of impact sounds are mixed. Further, in such an image forming apparatus, as the size and functionality thereof increase, the components are arranged in a very close positional relationship, and the components themselves become smaller and new components become smaller. This is due to the feature that is added.

  Therefore, the present applicant has made a proposal regarding a signal determination device for accurately determining the cause of the generation of sounds (mainly impact sounds) randomly generated from such many sound sources (patents). References 1, 2).

  For example, the signal determination device prepares a waveform vector related to an acoustic signal obtained by collecting a plurality of types of sound from a sound source whose cause of occurrence is clear as a known waveform vector (reference space), and becomes a determination target. A waveform vector related to an acoustic signal obtained by collecting sound of a sound source whose occurrence is unknown with a microphone is taken as a judgment target waveform vector, and a distance measure (for example, Mahalanobis distance) between the waveform vector and the known waveform vector is calculated. . Then, by comparing the distance measure of the judgment target waveform vector with a discrimination threshold set based on the distance measure data for each cause of the known waveform vector, the sound source group of which known waveform vector is the judgment target waveform vector It is determined by estimating whether it is included in.

JP 2002-323370 A JP 2002-318155 A

  However, such a determination device has the following problems.

  That is, the sound source to be determined is covered by the exterior cover 02 in which an opening (a paper discharge port, an exhaust port, etc.) 03 is partially formed as illustrated in FIG. In the case of a mechanical device 01 such as an image forming apparatus having a plurality of types of sound sources, the microphone 05 is placed in the cover portion 02A where the opening 03 exists and the sound is collected, and the cause of the sound generation is determined. Can be determined relatively accurately when performing the measurement, but when determining the cause of the sound after the microphone 05 is placed on the cover portion 02B where the opening 03 does not exist and the sound is collected, the determination accuracy is determined. There is a problem that will be reduced.

  As described above, the discrimination accuracy is lowered when sound is picked up by facing the cover portion 02B where the opening 03 does not exist, and the sound generated inside the mechanical device 01 reaches the microphone 05. Until the sound is picked up, an exterior cover (opening is formed in addition to other components (peripheral structures) 04 installed near the periphery of the element (movable part, etc.) that causes the sound. Cover part) 02 also passes, and when it passes, phenomena such as reflection, sound absorption, and reverberation occur, which are added to the sound characteristics as transmission characteristics. It is considered that the main cause is that the characteristics (for example, time waveform, frequency waveform) change.

  In addition, the change in the sound characteristics shows different results corresponding to changes in the peripheral structure (including the support frame) 04 and the type of the exterior cover 02. In particular, in an image forming apparatus or the like that takes measures against low noise by using a sound absorbing material or the like, the result shows that the high frequency component portion of the sound is reduced by several dB to several tens dB due to the influence of the sound absorbing material. become.

  Then, the sound collected by the microphone with the sound characteristics changed through the exterior cover or the like in this way is obtained a distance measure based on the acoustic signal as a result of the sound collection, and the distance measure is determined to be the same. When compared with the threshold value, the distance measure also changes due to the influence of such characteristic change, so it may not be accurately determined by the threshold value, and may be erroneously determined to be a sound source of a different cause. . In this regard, the sound picked up facing the cover portion 02A side where the opening of the exterior cover is present has little change in sound characteristics caused by phenomena such as reflection, sound absorption, and reverberation caused by the presence of the exterior cover. Therefore, it is accurately discriminated by at least the same threshold value.

  FIG. 15 conceptually shows the relationship between the collection location of plural types of pseudo sounds (X sound, Y sound, Z sound) and the average distance measure of each sound. The sound collection location is where a sound generator (speaker, etc.) that generates the above sounds is installed outside the machine (outer cover: outside) and the microphone is directly picked up by the sound generator. When the sound generator is installed inside a mechanical device and the sound is collected toward the cover part where the opening is present in the exterior cover, either when the sound is collected toward the cover part where the opening is not present. It is. The average distance measure is obtained by averaging the data of an acoustic signal obtained when a plurality of collected sounds are generated outside the mechanical device as a reference space.

  As shown in FIG. 15, when the Y sound and the Z sound among the above sounds are collected through a cover portion where no opening is present, the distance measure is that the sound is collected through the cover portion where the opening is present. If you look at the distance measure as a reference, you can see that it has changed significantly. In the figure, reference numeral TH01 is a threshold value for determining that it is a Y sound, and TH02 is a threshold value for determining that it is a Z sound. The sound source is determined based on such threshold values TH01 and TH02. In some cases, the Y sound and Z sound, which are sounds generated near the center inside the machine, may not be accurately identified. That is, as illustrated in FIG. 15, it may not be possible to determine that the Y sound is a “Y sound” by the threshold value TH01 (cannot be distinguished from the X sound). In addition, the Z sound may not be accurately determined as the “Z sound” by the threshold value TH02 (that is, a value close to the threshold value may be erroneously determined).

  As a countermeasure against the above-described decrease in discrimination accuracy, for example, a method can be considered in which the discrimination threshold is empirically changed.

  However, in this countermeasure, not only there are individual differences in the judgment criteria, but the conditions of the exterior cover, including the surrounding structures that affect the sound characteristics, differ depending on the type of mechanical device, etc. It is difficult to select an appropriate threshold and appropriate measures cannot be stably performed.

  For example, taking an exterior cover as an example, the exterior cover in an image forming apparatus generally called a low-speed machine has a relatively thin thickness, and there is almost no change in sound due to sound insulation or sound absorption. There is a difference that the exterior cover of an image forming apparatus called a medium / high-speed machine is relatively thick, and there is a large change in sound due to sound insulation and sound absorption. Because it is difficult, it is impossible to correctly select an appropriate threshold value based on experience based on experience alone. In addition, when the threshold value is empirically changed to a value suitable for sound source discrimination when the sound is picked up on the cover part side without the opening, sound is picked up on the cover part side with the opening at the changed threshold value. When the sound source is discriminated, there is a possibility that the threshold value is not always appropriate, and the discrimination may be erroneous.

  The present invention has been made in view of such circumstances, and the main purpose thereof is a plurality of types that are covered with an exterior cover partially formed with openings and whose cause of occurrence is unknown. The sound source for a mechanical device that emits a certain sound may differ in the conditions of its exterior cover (existence of openings, thickness, structure that affects sound characteristics, differences in elements such as sound absorption processing, etc.), etc. An object is to provide a sound source discriminating apparatus and a sound source discriminating method that can be accurately and simply performed.

  The sound source discriminating device of the present invention collects sound from a mechanical device having a plurality of types of sound sources that are covered with an exterior cover partly formed with an opening and whose cause of occurrence is unknown, by means of a microphone. A sound collection unit to be captured as a signal, a sound cutout unit that cuts out an acoustic signal of a sound part to be discriminated from the captured acoustic signal, and a plurality of types of sounds whose cause of occurrence is known in advance for the cut out acoustic signal A distance measure calculation unit that calculates a distance measure from a reference space that includes sound signal data obtained by capturing sound from a sound source into the sound collection unit, and the calculated distance measure from the sound source in which the cause of occurrence is clear A sound source determination device having a determination unit that determines a cause of sound generation in comparison with a threshold value for sound source determination set based on a distance measure for a plurality of types of sounds, A plate-like member installed so as to be interposed between the cover portion where the opening exists and the microphone when the microphone is arranged toward the cover portion where the opening is present and picks up sound. It is characterized by this.

  Here, the sound collecting unit is basically composed of a microphone that can pick up sound emitted from a predetermined sound source and capture it as an acoustic signal composed of an electric signal. It may be configured in combination with a data storage unit capable of storing / storing the acoustic signal captured in step (b). When this data storage unit is included, only sound recording is performed first, and then analysis and calculation of the recorded acoustic waveforms can be collectively processed offline. As a data storage unit, a DAT (Digital Audio Tape recorder), HD (Hard Disc) recorder, etc. that can convert an acoustic signal by an analog / digital (A / D) converter and store it as a digital signal Adopt it.

  The sound collected by the microphone is a sound emitted from a sound source whose cause of determination is unknown or a sound source whose cause is clear. In addition, when the sound picked up by the microphone is directly stored in a PC (personal computer) constituting a sound extraction unit, a distance measure calculation unit, a determination unit, etc., which will be described later, without temporarily storing the sound in the data storage unit, An analog / digital converter may be installed in the PC. The microphone is installed at an approximate location in a part of the mechanical device that is thought to be generating at least a sound (noise) for which sound source discrimination is desired. In addition, as the microphone, a microphone that exhibits unidirectionality can be used. The microphone installation conditions (sound collection position, height, etc.) are set as appropriate based on conditions for obtaining an acoustic signal having a level sufficient for sound source discrimination (for example, a sufficiently high SN ratio).

  The sound cutout unit cuts out the sound signal of the sound part to be discriminated from the sound signal taken in by the sound pickup unit, and the cutout is a feature on the time axis that becomes the rising part of the waveform or the maximum amplitude part of the sound signal. For a predetermined range set with reference to a typical waveform portion. The sound cut-out unit that performs such cut-out can be configured by, for example, acoustic analysis software imported into a PC, a data logger having a trigger function, or the like. The sound part to be determined is not limited as long as the cause of occurrence can be determined by the determination method according to the present invention, and is mainly an impact sound. The impact sound is a sound whose acoustic duration is 1 second (sec) or less, preferably 100 milliseconds or less.

  In addition, the sound clipping unit may include an auditory correction unit that corrects the auditory sense of the acquired acoustic signal or the extracted acoustic signal using a predetermined correction filter. As a correction filter, a high-pass filter for removing low-frequency background noise components and other characteristic filters that are uniquely defined can be used, but they are used in general sound level meters and are close to human hearing. It is preferable to use an A-characteristic filter said to be used. Further, the cut-out acoustic signal may be configured such that the amplitude is standardized so that the maximum value or the minimum value of the amplitude of the time waveform or the frequency waveform has a predetermined magnitude. When such a standardization is performed, the difference in sound caused by the difference in the separation distance between the microphone of the sound pickup unit and the sound source is included as a determination factor of the cause of the sound source, and an erroneous determination is made. It is possible to avoid the occurrence of a problem of performing the process.

  The distance measure calculation unit calculates a distance measure (spatial distance) with respect to the reference space of the acoustic signal cut out by the sound cutout unit, and the distance measure is a general measure used in statistical discriminant analysis and cluster analysis. Distance measures, such as Euclidean distance, standardized Euclidean distance, Minkowski distance, Mahalanobis distance, etc. can be used. When the Mahalanobis distance is adopted, it is possible to comprehensively determine the cause of the sound source including the correlation state between the variables. Further, when the Mahalanobis distance is adopted, in order to calculate the distance measure, an average, variance, covariance, standard deviation, etc. are obtained in advance for each acoustic signal data obtained by collecting the sound.

  As a sound source whose cause for obtaining the reference space of this distance measure is obvious, for example, a member (for example, a plastic ball and a metal plate) that generates a substantially constant sound by forcibly colliding or hitting, One of the components that make up the sound generator that can reproduce and generate sound (pseudo sound) similar to the sound emitted from the target sound source, and the sound source that is the object of discrimination (the sound source whose generation cause is unknown) Parts that can be operated independently and related parts. The sound of such a sound source is different from the generation space where there is a surrounding structure or exterior cover that affects the sound characteristics, such as a sound source whose cause of occurrence is unknown, preferably the surrounding structure or exterior Sound is collected in a space condition (free sound field space such as a semi-anechoic sound room) without a cover. Data of an acoustic signal obtained from a sound source in which the cause of occurrence is clear is defined as a reference space.

The predetermination unit obtains distance measures (average values) for a plurality of types of sound from a sound source whose cause of occurrence is known in advance as pre-processing for determining the cause of the sound emitted from the sound source to be determined, and determines each distance. Based on the measure, a threshold value for estimating and discriminating in which cause group the occurrence cause is included and accumulation (memory retention) of the threshold value is performed. The threshold is set by, for example, a predetermined coefficient k (0 <k <1, preferably k) in a difference between adjacent average values of distance measures obtained from a plurality of types of sounds whose cause of occurrence is clear. = the value obtained by multiplying the 0.5 to 0.7 is a), can be a value obtained by adding the average value of the smaller average value thereof adjacent to the threshold.

  As the above-described mechanical device, any device may be used as long as it has a plurality of types of sound sources that are covered with the exterior cover in which the opening is formed as described above and the cause of occurrence is unknown. Image forming apparatus.

  A plurality of types of sound sources in a mechanical device usually include sound sources that are difficult to determine the cause of the occurrence, but are not limited to components that generate the operating sound of the mechanical device, but are related to things used for the mechanical operation. Including those that emit sound. An exterior cover in a mechanical device is usually configured by appropriately combining a cover part (surface part) having an opening and a cover part (surface part) having no opening, but is not necessarily limited to this configuration. Not. The exterior cover has a structure in which at least a part can be removed from the machine body. The opening formed in the exterior cover is in an open state when the machine device is used, and has a size having an opening area to the extent of causing sound leakage. When the mechanical device is an image forming apparatus, examples of the opening formed in the exterior cover of the image forming apparatus include a paper discharge port, an exhaust port, and a paper feed port for a manual tray.

  The said plate-shaped member should just consist of a plate-shaped form which has a curved surface part, a level | step-difference part, a projection part etc. including a flat plate, About the whole form, it does not specifically limit.

  The size of the plate member (the size of the outer shape) is appropriately selected. For example, when collecting sound generated from a mechanical device without removing the exterior cover and performing sound source discrimination, when collecting sound toward the cover portion of the exterior cover where the opening exists, The size may be a little larger than the opening area of the opening, or may be approximately the same as or slightly larger than the outer area of the cover portion where the opening exists. The material and thickness of the plate-like member are not particularly limited, but can be set to a material or thickness that is the same as or similar to, for example, the material or thickness of the exterior cover used in the mechanical device. . Of these, the thickness is preferably about 1 mm as in the case of an outer cover used in a low-speed machine, but not as thin as an outer cover used in a low-speed machine. It is good to make it thick (for example, about 1 to 3 mm).

  In addition, the position where the plate-like member is installed (position between the exterior cover and the microphone) can collect sound emitted from the mechanical device, and the effect of installing the plate-like member can be obtained. Although not particularly limited, it is preferably a position close to the cover portion where the opening exists, and more preferably a position that at least closes the opening. In addition, the size of the plate-like member when the opening of the exterior cover is installed in a state in which the opening is not blocked is that the sound leaked from the opening is the plate-like member from the viewpoint of enabling accurate discrimination. It is desirable that the size be such that the sound is not picked up by the microphone and is not collected by the microphone (sound insulation or sound absorption is generated by the plate-like member). When a microphone is placed on a cover portion of the exterior cover that does not have an opening to collect sound, a plate-like member does not have to be installed between the cover portion and the microphone.

In the sound source discrimination device, the plate-like member is interposed between the mounting portion of the cover part and the microphone in the mechanical device , instead of the cover part having at least an opening in the exterior cover. It is good to install in.

  In this case, the plate-like member installed between the mounting part of the cover part where the opening is present and the microphone has the same size as the outer area of the cover part or a slightly larger size. It is preferable. Moreover, about the whole form regarding this plate-shaped member, an installation position, etc., it is the same as that of the case of the plate-shaped member mentioned above. After all, the plate-like member at this time is installed between the mounting portion and the microphone instead of the cover portion to be removed.

  When sound is collected by removing the cover portion where the opening is present, the cover portion (all or part of the cover) where the opening is not present is also removed from the mechanical device, and the removed opening is removed. It is preferable that the microphone is placed on the mounting portion of the cover portion that is not present and the plate-like member is interposed between the mounting portion and the microphone to collect sound.

In this case, the plate-like member installed between the mounting part of the cover part where the opening does not exist and the microphone is a plate-like member installed between the mounting part of the cover part where the opening exists and the microphone. It is preferable to use them in common. As a result, the sound picked up by each microphone is affected by the difference in the exterior cover (such as the presence or absence of an opening or the shape of the cover), and the degree to which the sound characteristics change due to the change in transfer characteristics is also reduced. Therefore, more accurate sound source discrimination can be performed.

  Further, as the commonly used plate-like member, for example, one of the removed cover portions without the opening may be reused. This eliminates the need to prepare a separate plate-like member, which is economical and convenient because it does not require storage of the plate-like member.

  On the other hand, the sound source discrimination method of the present invention collects sound from a mechanical device having a plurality of types of sound sources that are covered with an exterior cover partially formed with an opening and whose cause of occurrence is unknown, using a microphone. A sound collecting process for capturing as an acoustic signal, a sound extracting process for extracting an acoustic signal of a sound part to be discriminated from the acquired acoustic signal, and a plurality of types of sounds for which the cause of occurrence is known in advance for the extracted acoustic signal. A distance measure calculation step for calculating a distance measure with respect to a reference space composed of data of an acoustic signal in which sound from the generated sound source is taken into the sound pickup unit, and the calculated distance measure is a sound source whose cause is obvious A sound source determination method comprising: a determination step of determining a cause of sound generation by comparing with a threshold value for sound source determination set based on a distance measure for a plurality of types of sounds from When the microphone is installed toward the side of the exterior cover where at least the opening is present and picks up sound, it is installed so that a plate-like member is interposed between the cover portion where the opening is present and the microphone. And collecting the sound.

  Each step in this discrimination method is realized by the operation of each functional part (sound collection unit, sound cutout unit, distance measure calculation unit, discrimination unit) in the sound source discrimination device.

  Also in this discrimination method, as in the case of the sound source discrimination device described above, the cover portion where at least the opening is present is removed from the exterior cover, and the microphone is directed toward the attachment portion of the removed cover portion on the mechanical sound source. When the sound is collected by installing the cover, the sound may be collected by installing the plate-like member between the mounting portion of the removed cover portion and the microphone. The configuration relating to the plate-like member, the removed exterior cover portion, etc. in this case is the same as the configuration in the case of the above-described discrimination device.

  According to the sound source discriminating apparatus and the sound source discriminating method of the present invention, sound (noise) that is emitted from a mechanical device (such as an image forming apparatus) that is covered with the exterior cover as described above and emits a plurality of types of sounds whose cause of occurrence is unknown When a sound source is determined in (), a plate-like member is interposed between the cover portion and the microphone when a microphone is installed and picks up sound toward the cover portion of the exterior cover where at least the opening exists. The sound is collected and the sound is collected, so even if the conditions of the exterior cover may be different, the characteristics of the collected sound will not change significantly and will be almost aligned. As a result, the cause of the sound source can be determined accurately. Such an accurate determination can be realized by simply installing the plate-like member as described above and collecting sound, and can be performed very simply.

For example, the average distance measure sound when picked up by the cover portion side having an opening portion (Y tones, Z sound) is the installation of the plate-like member, indicated by circles and triangles in the previous drawings 15 two-dot line It is obtained as such a value. This value approximates the average distance measure of the sound (Y sound, Z sound) when the sound is picked up on the cover part side without the opening. As a result, the Y sound and the Z sound are the same in both cases where sound is collected on the cover part side having the opening of the outer cover and on the cover part side having no opening. The thresholds TH01 and TH02 are accurately discriminated.

[Embodiment 1]
FIG. 1 illustrates the configuration of a sound source discrimination system 100 according to Embodiment 1 of the present invention. The sound source to be identified by the sound source determination system 100 is noise radiated from the copying machine 200. In the discrimination system 100, the cause of the noise is the cause (1): the impact sound of the metal member, the cause (2): the collision sound at the front end of the recording paper conveyance direction, and the cause (3): the conveyance direction of the recording paper. It is determined whether the sound is a jumping sound at the rear end.

<Basic configuration of discrimination system>
The entire sound source determination system 100 includes a unidirectional macrophone 1 that picks up noise from the copying machine 200, DAT2 connected to the microphone 1, a personal computer system C connected to DAT2, and its noise. It is comprised from the board | plate material 7 installed and used at the time of sound collection. The personal computer system C includes a computer main body 3, a keyboard 4a as an input means, a mouse 4b, a display device 5 as an output means, and the like.

  The hardware resources in the computer main body 3 include a CPU as a calculation control means, a RAM as a main storage means, a hard disk as an auxiliary storage means, an input / output control device (all not shown), and the like. Software resources in the main body 3 include an operating system, acoustic waveform analysis software, numerical analysis software, and the like (all not shown). The functions of the waveform cutout unit 30, the distance measure calculation unit 40, and the determination unit 50 shown in FIG. 2 are realized by the joint work of the hardware resource and the software resource.

  FIG. 2 is a basic functional block diagram of the discrimination system 100. The basic functions of the discrimination system 100 are, in order along the processing flow, a sound collection unit 10 composed of the microphone 1 and the DAT recorder 2, a data storage unit 20 composed of the DAT recorder 2, and the computer main body. 3, a waveform cutout unit 30, a distance measure calculation unit 40 and a determination unit 50, and a display unit 60 including the display device 5. Signals input / output between these functional blocks are an analog electric signal AS, a digital signal DS, and a determination result R.

  Among them, the waveform cutout unit 30 includes an auditory correction processing unit 31 that performs auditory correction of the collected sound signal, a cutout unit 32 that cuts out a sound portion to be determined from the corrected acoustic signal, and the cutout thereof. And a waveform converter 33 for converting the sound into waveform data (time waveform data, frequency waveform data, etc.) indicating the sound characteristics necessary for the arithmetic processing.

  The distance measure calculation unit 40 calculates the Mahalanobis distance as a distance measure (spatial distance) with respect to the reference space of the acoustic signal cut out by the waveform cutout unit 30. In addition, the calculation unit 40 obtains in advance an average, variance, covariance, standard deviation, etc., for each collected sound signal data before the calculation.

  The determination unit 50 compares the distance measure calculated by the calculation unit 40 with respect to the sound to be determined and a determination threshold value that is prepared and stored in advance, and determines which sound source is the cause of occurrence. To do. The threshold value is obtained by calculating the distance measure (average value) of each acoustic signal collected for each cause from a sound source in which the cause is clear in advance, and the average value of the adjacent distance measures (average distance measure). Are appropriately set as threshold values for determination, and are stored and held in the determination unit 50 (storage unit thereof).

<Setting threshold for discrimination>
In the discrimination system 100, as a sound source whose cause is clearly used in the acoustic signal constituting the reference space in the distance measure calculation unit 40, a metal piece hitting sound by a plastic ball, a sound colliding with a plastic plate at the front end of the paper (paper) The leading edge collision sound) and the sound of the trailing edge of the paper (the trailing edge of the paper) were adopted.

  As plastic spheres, two types of spheres made of polypropylene having a diameter of 16 mm and 26 mm were prepared. On the other hand, as the metal pieces, two types of metal plates having a plate size of 20 × 30 × 1 mm and 30 × 40 × 1 mm made of stainless steel (SUS) were prepared. As the plastic plate, two types of plastic plates having a size of 20 × 30 × 1 mm and 30 × 40 × 1 mm made of ABS resin were prepared. In addition, this metal plate and plastic plate are supported and fixed by affixing to a stone surface plate with double-sided tape, or with a single rubber plate of 30 x 40 x 1 mm sandwiched between them. Each was installed in two types of support states. The viewpoint that each material of the plastic sphere or plate or metal plate is substantially the same as the material generally used as a material constituting each component in the image forming apparatus such as a copying machine. Is selected.

  Sampling sound of metal pieces is a total of four types of impact sounds generated when the above two types of plastic balls are naturally dropped from above 5 cm height on two types of metal pieces with different support states. The sound was collected by the microphone 1. The sound collection at this time is a stone surface plate with the metal piece attached to it in a semi-anechoic sound room (free field space), and a distance of 0.6 m from the center of the metal piece on the surface plate. The microphone 1 was installed at a remote position. In addition, sound collection at this time is performed so that a necessary number of data samples (i) can be obtained.

  In addition, the leading edge impact sound is collected by causing the long side and the short side of the A4 size copy paper to collide with the plastic plate and collecting the impact sound generated at that time by the microphone 1 in the same manner. I went there. Further, the trailing edge of the sheet was collected by moving the rear part of the sheet so as to get over the step and picking up the jumping sound generated by the microphone 1 in the same manner.

The acoustic signal picked up by the microphone 1 in this way is calculated as reference space data through the same operation process of the waveform cutout unit 30 described later. Specifically, an acoustic signal picked up by the microphone 1 is obtained as, for example, 48,000 sampling data (digital signal) per second by an A / D conversion circuit built in the DAT 2, and out of the digital signal 64 points around the maximum amplitude value are cut out as acoustic signals (time waveform data). Subsequently, the cut-out acoustic signal is subjected to frequency analysis by fast Fourier transform to obtain 32 points of frequency waveform data. 100 sounds are obtained for each sound, which is the necessary number of data (i), for a total of 300 sounds. Such reference space data is obtained as vectors y for 100 cases (i = 1 to 100) consisting of frequency waveforms of 32 points as shown below.
y = (y _i1 , y _i2 ,..., y _i32 )

  Next, in order to calculate the threshold value, a plurality of types of sounds of a sound source whose cause of occurrence is known in advance are collected, and a distance measure of each acoustic signal with respect to the reference space is obtained.

_First , similarly to the waveform data y (= y _i1 , y _i2 ,..., Y _i32 ) (i = 1 to 100) in the reference space, the waveform data y ′ (= y _i1 ′, y _i2 ′,..., y _i32 ) (i = 101 to) is normalized. Normalization is performed based on Equation 1 below. In the formula, an integer of j = 1 to 32, and σ represents a standard deviation.

Subsequently, the correlation coefficient matrix A and the inverse matrix R ⁻¹ of the correlation coefficient matrix A are calculated. In order to obtain a correlation coefficient matrix, a correlation coefficient r is calculated. The correlation coefficient r was calculated by the following formula 2. In the formula, y displayed as a superscript bar represents an average value of y, and p and q both represent integers of 1 to 32.

  The correlation coefficient matrix A was obtained by the following formula 3. In the formula, a represents an element obtained by calculation of an inverse matrix, and k represents an integer of 1 to 32.

The Mahalanobis distance D ² was calculated based on Equation 4 below.

  The distance measure (Mahalanobis distance) calculated in this way is obtained as a distance measure of 100 sounds for each sound source, and an average value (average distance measure) for each sound source is calculated.

  A value obtained by multiplying the difference between the average distance measures of sound sources adjacent to each other (in a magnitude relationship) by 0.7 times among the average distance measures of the respective sound sources whose cause of occurrence is apparent. Was added to the average distance measure of the smaller sound source, and the value obtained was defined as the threshold value TH. In this example, since three types (causes (1) to (3)) of sound sources with obvious causes of occurrence are used, when the average distance measure is divided by magnitude relationship, two types of differences are generated, so that Thus, two threshold values (for example, the relatively small threshold value is the first threshold value THa and the relatively large threshold value is the second threshold value THb) are obtained. This threshold value is stored in a predetermined storage unit so as to be used by the determination unit 50.

  In the determination unit 50 using the thresholds THa and THb set in this way, when the distance measure related to the sound to be determined becomes a value smaller than the first threshold THa, the smallest average distance measure among the three types of sound sources. And when it is determined that the distance measure of the determination target is larger than the second threshold value THb, it is determined that the sound source indicates the largest average distance measure among the three types of sound sources. When the distance measure to be discriminated becomes a value between the first threshold value THa and the second threshold value THb, it is determined that the sound source indicates an intermediate average distance measure among the three types of sound sources.

<Basic sound source discrimination operation>
Basic sound source discrimination by the sound source discrimination system 100 is performed as follows.

  First, in the sound source discrimination system 100, as shown in FIG. 3, pre-processing is performed in advance before the actual discrimination is performed (step S1). In this preprocessing, as described above, the threshold used by the determination unit 50 is set.

  On the other hand, after the setting of the threshold value is completed, the microphone 1 collects noise emitted from the copying machine 200 having a plurality of sound sources to be determined (unknown cause) (step S2). This sound collection may be performed in a state where a plate material 7 is installed between the copying machine 200 and the microphone 1 as necessary, as will be described later. Further, such sound collection is performed so as to collect sound generated when at least one copy operation of the copying machine 200 is performed once. The sound picked up by the microphone 1 is converted into an electric signal and taken into the DAT 2 as an analog sound signal.

  The analog signal is converted into a digital signal by an A / D conversion circuit built in DAT2 (step S3). The digital signal at this time is once recorded on the cassette type magnetic tape of DAT2. FIG. 4 is a graph showing a digital signal recorded in the DAT2. In this example, since the resolution (sampling frequency) of the A / D conversion circuit of DAT2 is 48 kHz, the obtained digital signal is obtained as sampling data of 48000 points per second. Here, when picking up an image forming apparatus such as a copying machine, it is desirable to apply a sampling frequency of at least 10 kHz or more, preferably 20 kHz or more.

  Next, after the digital signal recorded in the DAT 2 is taken into the main body 3 (hard disk) of the personal computer C, the waveform cutout unit 30 cuts out the sound part (impact sound) to be determined (see FIG. Step S4).

  First, the audibility correction unit 31 in the sound cutout unit 30 corrects the audibility of the captured digital signal. In this example, correction was performed using an A-characteristic filter close to human hearing in order to cut a signal having a low frequency component of several tens of Hz or less, which is often included in background noise. The digital signal that is not subjected to the auditory sensation correction is directly output to the clipping unit 32.

  Subsequently, the time waveform data of the impact sound to be discriminated is cut out by the cutout unit 32 from the new digital signal whose auditory sense is corrected. In this example, a signal portion including a shock wave is cut out from the digital signal for about 0.2 seconds, and then a total of 64 time waveform data around 64 points around the maximum amplitude (sound pressure) value is taken as 100 samples. Cut out in minutes. FIG. 5 is a graph showing a digital signal composed of the extracted time waveform data.

  Subsequently, the extracted 64-point time waveform data is converted into predetermined waveform data by the waveform conversion unit 33 (step S4). In this example, a predetermined Hanning window function process is performed on the cut-out waveform data, and then frequency analysis is performed using fast Fourier transform to obtain frequency waveform data as shown in FIG. Here, a total of 32 power spectra for each frequency band having a frequency resolution of, for example, 750 Hz (= 48000/64) is obtained.

  Next, the digital signal cut out in this way is output to the distance measure calculation unit 40 (FIG. 2), and the calculation unit 40 calculates the Mahalanobis distance, which is a distance measure with respect to the reference space (step S5). . The Mahalanobis distance is calculated in the same manner as the calculation of the reference space data. Further, the calculated distance measure (Mahalanobis distance) is output to the determination unit 50 as an average value (average distance measure) of the distance measure.

  In the determination unit 50, a process of comparing the average distance measure regarding the sound source to be discriminated output from the distance measure calculation unit 40 with the threshold value THa and the second threshold value THb set in advance as described above. Based on this comparison result, it is determined which of the above three causes (1) to (3) the sound source to be determined corresponds to. The determined result is obtained as a determination result R relating to the cause of the generation of the sound source to be determined (step S6).

  The cause determination result R obtained in this way is finally displayed on the display device 5 (step S7 in FIG. 3). For example, when the sound source to be determined is the “metal piece impact sound” of the cause (1), the content of the determination result is displayed on the screen of the display device 5 (see FIG. 2). Thereafter, if the next sound source discrimination is necessary, the above steps (S2 to S7) are similarly repeated, but if there is no subsequent sound source discrimination, the process is ended (step S8).

<Configuration related to sound collection>
In the sound source discrimination system 100, taking into account the characteristics of a machine device to be discriminated, such as the copying machine 200, sound collection using the plate material 7 as described below is performed as necessary.

  First, as shown in FIGS. 1 and 7, the copying machine 200 that is a discrimination target basically sends a document to be copied from the automatic document feeder 215 to the image input unit (document reading unit) 210 and sends the document. The image output unit (image forming unit) 220 forms a toner image based on the document information, and finally transfers the toner image to a recording sheet conveyed from the paper supply unit 230. It is provided with a function of copying a document by fixing.

  The copying machine 200 is configured such that the image input unit 210, the image output unit 220, and the paper feeding unit 230 are all arranged in a state in which a large number of components are densely arranged with respect to the support frame. At the time of copying, there is a characteristic that noise is generated by intricately mixing sounds generated from a plurality of operating component parts (for example, metal movable parts), etc., and sounds generated by the conveyance movement of recording paper. Yes. In the figure, reference numeral 216 denotes a document tray on which a document is placed, 225 denotes a paper discharge tray that stores recording paper discharged after copying, and 235 stores recording paper according to the size and transport direction of the copying machine. This is a paper feed cassette (tray) attached to the front side so as to be drawable.

  Further, as shown in FIGS. 7 and 8, the copying machine 200 is partially included except for the upper surface portion where the automatic document feeder 215 is located, the bottom surface portion of the paper feeding portion 230, and the attachment portion of the paper feeding cassette 235. It is covered with an exterior cover 250 having an opening formed therein, and has a structure in which the overall appearance has a three-dimensional shape similar to a rectangular body. The exterior cover 250 is fixed to the front cover 250A attached to the front side of the image output unit 220 so as to be opened and closed, and fixed to the left and right side parts of the image output unit 220 and the paper feed unit 230, or can be opened and closed. The left and right side covers (250B) 250C attached to the main body and the back cover (250D) fixed to and attached to the rear side of the image output unit 220 and the paper feed unit 230 are mainly configured. The exterior cover 250 is formed in a substantially flat plate shape having an average thickness of about 1 to 2 mm mainly using plastics such as ABS resin. Further, the exterior cover 250 can be removed from any surface of the copying machine (main body frame).

  Further, the right side cover 250C of the outer cover is formed with a discharge port 260 that is a rectangular shape that is elongated in the horizontal direction and is discharged when the recording sheet after copying is stored in the discharge tray 225. Further, an exhaust port (265) is formed in the back cover 250D. In addition, the right side cover 250C is formed with a jam processing door for performing a jam processing operation for removing a jammed recording paper, and the left side cover 250B is a manual feed for supplying the recording paper to the image output unit. The tray is formed to be openable and closable. Reference numeral 290 conceptually shows the components of the copying machine arranged in a dense state on the inner side of the exterior cover 250.

  As shown in FIG. 7, for example, as shown in FIG. 7, the sound collection with respect to the copying machine 200 equipped with the exterior cover portion in which the opening such as the paper discharge port 260 is formed is recorded on the four side surfaces. Each of the side covers and the back covers is attached to the microphones 1). In this case, it is possible to collect sound with the exterior cover 250 attached, but in particular, the sound is collected toward the microphone 1 on the right side cover 250C and the back cover 250D where openings such as the exhaust port 260 exist. 1 and 7, for example, the sound is collected by installing the plate member 7 between the discharge port 260 of the right side cover 250C and the microphone 1, for example. On the other hand, when the microphone 1 is accommodated in the front cover 250A or the left side cover 250B where no opening is present, sound is collected without installing the plate 7.

  As the plate member 7, a plastic plate (thickness 2 mm) 71 made of an ABS resin having a flat area larger than the opening area of the paper discharge outlet 260 is used, and this is used as the paper discharge of the right side cover 250C. It was made to install with the mouth 260 closed. The plastic plate 71 is installed so as to be directly attached to the right side cover 250C. However, when sound is collected by performing a copying operation, it is necessary to actually take out the recording paper discharged after copying from the paper discharge port 260 to the outside. Therefore, the predetermined plate 7 is installed in a state slightly separated from the side cover 250C. As a result, the copied recording paper is discharged to the outside through the space (gap) between the side cover 250C and the plate material 7. As the plate member 7 when installed in such a separated state, a plate having the same area as the right side cover 250C is used.

For microphone 1 serves to place toward the right side cover 250C formed by installing a state that closed by plate 7 and discharge outlet 260, a sound pressure necessary for discrimination with the sound pickup performance (characteristic) and the reference Find the installation position that can pick up sound by level and install it. Further, when the microphone 1 is accommodated in a cover portion (250A, 250B) having no opening such as the paper discharge port 260, sound is collected without installing the plate member 7.

<Difference in effect due to sound collection configuration>
Next, the following test was performed in order to confirm the effect of performing sound collection with the plate material 7 installed.

  Speakers 6 serving as sound generators are respectively installed at four positions of the copying machine 200 (see FIG. 8), and three sounds collected from the respective speakers 6 when the threshold value is set (metal piece hitting sound, leading edge of paper) The collision sound and the trailing edge jumping sound) were reproduced 20 times for each sound. The four positions are the internal position (p1) near the discharge outlet 260, the internal position (p2) near the exhaust outlet 265, the internal position (p3) near the left side, and the internal position (p4) near the front. . Each of the internal positions is an empty space of the corresponding part, and the speaker 6 is installed in a state facing the exterior cover portion in the vicinity of the empty space. The speaker 6 is connected to the computer main body 3 and reproduces the three sounds recorded in advance on the DAT 2 or the hard disk via a sound generation circuit mechanism in the computer main body 3.

  On the other hand, the microphones 1 were respectively installed under the same conditions toward the exterior cover portions (250A to 250D) corresponding to the above four positions. Further, when collecting sound to the right side cover 260C having the paper discharge port 260 and the back cover 250D having the exhaust port 265, the plastic plate 71 as the plate material 7 is disposed in a state in which the exhaust port 260 and the exhaust port 265 are closed. I picked up the sound.

  For comparison, as illustrated in FIG. 9, the speaker 6 is installed outside the outer cover 250 (the upper surface portion of the copying machine: outer), and the three sounds are similarly reproduced from the speaker 6 to obtain a microphone. 1 was picked up. Further, when collecting sound from the right side cover 260C having the discharge port 260 and the back cover 250D having the exhaust port 265, sound was collected without the plastic plate 71 being installed.

  Then, the sound source discrimination process as described above is executed based on each collected sound data, and finally the distance measure calculation unit 40 measures the distance to the reference space for each sound (for 20 sounds). (Mahalanobis distance) was determined, and the average value of each distance measure (average distance measure) was determined. The result at this time is shown in FIG.

  From the results shown in FIG. 10, even when the microphone 1 is picked up by the right side cover 250C or the back cover 250D having the paper discharge port 260 and the exhaust port 265 (P1, P2), the plastic plate 71 is installed and stored. By making sound, an average distance measure close to the average distance speed in the case where the microphone 1 is picked up by the cover part (250B, 250A) having no opening such as the paper discharge opening (P3, P4) can be obtained. I understand.

  On the other hand, even when the microphone 1 is picked up by the same right side cover 250C and back cover 250D (P1, P2), when the sound is picked up without the plastic plate 71 installed, the average distance measure is as shown in FIG. The result (value smaller than the values at P3 and P4) is indicated by dotted circles and triangular symbols inside. Further, even when sound is collected (P3, P4) by a cover part (250B, 250A) having no opening such as a paper discharge port, the configuration (type, thickness, structure, etc.) of the cover part 250B, 250A Or different arrangement states of component parts (types of component parts, arrangement conditions thereof, etc.) may cause the average distance measures to differ (vari).

  Further, by obtaining the result shown in FIG. 10, sound source discrimination based on the following threshold (different from the preset threshold) can be performed.

  First, since the average distance measure between the metal striking sound and the paper tip collision sound is adjacent to the threshold in this case, the difference between the two (here, the difference between the average distance speeds at the position of P4) is 0. The value obtained by adding the value multiplied by 7 times to the average distance measure of the metal striking sound was taken as the first threshold value THa (specifically, 1600). Further, since the average distance measure between the leading edge collision sound and the trailing edge splash sound is adjacent, the difference between the two (here, the difference between the average distance speeds at the position of P4) is multiplied by 0.7 times. The value obtained by adding the obtained value to the average distance measure of the paper tip impact sound was taken as the second threshold value THb (specifically 3000).

  When the average distance measure is determined at each of the above positions (the positions of P1 to P3; the P4 position is used for calculating the threshold value and excluded from the target of the effect verification) based on the threshold values THa and THb. When the average distance measure of the sound becomes a value smaller than the first threshold value THa, it is determined that the sound is a metal hitting sound, and the average distance measure of the discrimination target becomes a value larger than the second threshold value THb. Is determined to be “paper trailing edge bounce sound”, and when the average distance measure to be determined becomes a value between the first threshold value THa and the second threshold value THb, “paper edge collision sound”. It is judged.

  From the above, the average distance measure obtained by collecting the sounds generated at the respective positions (P1 to P4) is accurately determined based on the two threshold values THa and THb regardless of the difference in the positions. be able to. On the other hand, particularly when the sound is collected without installing the plastic plate 71 at the two positions (P1, P2), if the discrimination is made based on the threshold values THa and THb, the sound is correctly the leading edge collision. However, it is erroneously determined that the sound is a metal hitting sound.

  The sound source discrimination system 100 and its discrimination method collect sound sources as described above for the noise actually generated when the copying operation is performed by the copying machine 200, and determine the sound source as described above. Even if there is a difference in the presence or absence of openings, etc., the average distance measure, which is the characteristic of the sound to be picked up, is almost the same value. As a result, the cause of the occurrence of the sound sources included in the noise is obvious Thus, it is possible to accurately determine whether the sound is one of the three sounds.

At this time, the plastic plate 71 installed on the right side cover 250 </ b> C where the paper discharge port 260 is provided is set a little away from the paper discharge port 260 in order to allow the recording paper to be discharged from the paper discharge port 260. For this reason, a cover having approximately the same size as the entire right side cover 250C is used.
[Embodiment 2]

  11 and 12 show a sound source discrimination system and its discrimination method according to the second embodiment. The sound source discrimination system 100 and the discrimination method thereof are the same as those in Embodiment 1 except that the configuration related to sound collection is partially different as described below when a copying machine equipped with an exterior cover portion having an opening is targeted. The sound source discriminating system 100 and the discriminating method thereof have the same configuration.

  That is, when collecting the sound, all or part of the outer cover 250 of the copying machine 200 is removed, and the plate member 7 is interposed between the microphone 1 and the mounting portion of the removed cover part. Like to do. For example, when all of the exterior cover 250 (front cover 250A, left and right side covers 250B, C, and back cover 250D) is removed, each mounting portion (250Ap, 250Bp, 250Cp, 250Dp) of each cover and its respective parts. Sound is collected in a state in which the plate member 7 is installed between the microphone 1 and the microphone 1 arranged toward the site.

  As the plate material 7 at this time, plastic plates made of ABS resin (thickness 2 mm) 72 and 73 having a plate shape having a slightly larger area than the entire appearance of each cover portion (250A to D) are used. Is installed in the vicinity of the device part (250 Ap, 250 Bp, 250 Cp, 250 Dp) of each cover part.

  In the sound source discrimination system 100 according to the second embodiment, after the sound is collected as described above, the sound source discrimination process in the case of the first embodiment is executed in the same manner, and the sound source for the noise emitted from the copying machine 200 is executed. A determination can be made.

In this discrimination system 100 and its discrimination method, it is also possible to use a cover portion in which no opening is formed as the plate material 7 and install the cover portion at each mounting position for reuse. is there. In addition, only a part of the outer cover to be removed (for example, the covers 250C and 250D having an opening such as a paper discharge port) may be used. It is not necessary to install the plate material 7 when collecting sound. In addition, in this case, it is preferable to use the same material as the plate member 7 installed between the mounting portion of the removed cover portion (250C, 250D) and the microphone 1 from the viewpoint of arranging the change in sound characteristics as much as possible. .

  Next, in order to confirm the effect of performing the sound collection by removing the outer cover and installing the plate member 7, the same test as in the case of the first embodiment was performed.

  As in the case of the first embodiment, the speakers 6 are respectively installed at the four positions (P1 to P4) of the copying machine 200 (see FIG. 12), and the three sounds (metal strike sound, The paper leading edge collision sound and the paper trailing edge jump sound) were reproduced 20 times for each sound. All of the exterior cover 250 was removed.

On the other hand, the microphones 1 were respectively installed under the same conditions toward the mounting positions (250 Ap, 250 Bp, 250 Cp, 250 Dp) of the removed cover portions. In addition, plastic plates 7 2 and 7 3 were arranged in the vicinity of the mounting portions of the removed cover parts, respectively. In this embodiment, a left side cover 250B (average thickness of about 2 mm) in which no opening is formed is used as the plate member 7, and this one left side cover 250B is installed and used at each of the above mounting positions. I did it.

  Then, the sound source discrimination process as described above is executed based on each collected sound data, and finally the distance measure calculation unit 40 measures the distance to the reference space for each sound (for 20 sounds). (Mahalanobis distance) was determined, and the average value of each distance measure (average distance measure) was determined. The result at this time is shown in FIG.

  From the result of FIG. 13, in particular, the entire outer cover 250 including the right side cover 250C and the rear cover 250D having the paper discharge port 260 and the exhaust port 265 is removed, and the microphone 1 is directed to the mounting portion of each removed cover portion. When collecting sound, the left side cover 250B is installed as a common plate member 7 in place of each removed cover portion to collect sound, so that each of the four positions (P1 to P4) can be collected regardless of the difference between the four positions (P1 to P4). It can be seen that the average distance measure for each sound is obtained as a value of almost the same level (in a nearly uniform state).

  Further, in this case, unlike the test result of the first embodiment (FIG. 10), sound is picked up at the mounting portion of the cover portion (250B, 250A) having no opening such as a paper discharge port (P3, P4). ) Average distance measures are also obtained as values approximately approximate to each other. This is because the configuration (type, thickness, structure, etc.) of the cover portions 250B and 250A is different because the sound is collected by installing the same left side cover 250B instead of the cover portions 250B and 250A. This is considered to be because the occurrence of the characteristic change of the collected sound was eliminated. Therefore, the second embodiment is advantageous in that it is possible to perform more accurate sound source discrimination than in the first embodiment.

  Further, by obtaining the result shown in FIG. 13, sound source discrimination based on the following threshold can be performed.

  In this case, since the average distance measure between the metal striking sound and the paper tip collision sound is adjacent, the threshold value in this case is 0.7 times the difference between them (here, the difference between the average distance speeds at the position of P4). The value obtained by adding the value to the average distance measure of the metal striking sound was taken as the first threshold THa (specifically, 1100). Further, since the average distance measure between the leading edge collision sound and the trailing edge splash sound is adjacent, the difference between the two (here, the difference between the average distance speeds at the position of P4) is multiplied by 0.7 times. The value obtained by adding the calculated value to the average distance measure of the paper tip impact sound was taken as the second threshold value THb (specifically 2700).

  When the average distance measure at each of the positions (P1 to P3) is determined based on the threshold values THa and THb, the average distance measure of the sound to be determined becomes a value smaller than the first threshold value THa. Sometimes it is determined that the sound is a metal hitting sound, and when the average distance measure of the determination target is greater than the second threshold value THb, it is determined that it is a paper trailing edge bounce sound. When the average distance measure becomes a value between the first threshold value THa and the second threshold value THb, it is determined that it is “paper tip collision sound”.

  From the above, the average distance measure obtained by collecting the sounds generated at the respective positions (P1 to P4) is accurately determined based on the two threshold values THa and THb regardless of the difference in the positions. be able to.

  The sound source discrimination system 100 and its discrimination method collect sound sources as described above for the noise actually generated when the copying operation is performed by the copying machine 200 and perform the sound source discrimination. Even if there is a difference in the presence or absence of openings, etc., the average distance measure that is the characteristic of the sound to be picked up is almost the same value. As a result, the cause of occurrence of the sound source included in the noise is It becomes possible to accurately determine whether the sound is one of the three obvious sounds. In particular, in this case, as described above, the average distance measure when the sound is picked up at the mounting portion (P3, P4) of the cover portion (250B, 250A) having no opening such as the paper discharge port is the case of the first embodiment. Therefore, the sound source discrimination can be performed more accurately at any of the above positions.

It is a conceptual diagram which shows the structure of the sound source discrimination | determination system which concerns on Embodiment 1. FIG. It is a functional block diagram which shows the basic function of the discrimination | determination system of FIG. 1 (including FIG. 11). It is a flowchart which shows the operation | movement of the sound source discrimination | determination by the sound source discrimination | determination system of FIG. 1 (including FIG. 11). It is a graph which shows the time-sound pressure waveform of the noise from a copying machine. It is a graph which shows the waveform which cut out a part of FIG. It is a wave form diagram which shows a frequency spectrum waveform. 1 is a perspective view of a copying machine that is a discrimination target. FIG. 3 is an explanatory diagram illustrating each part of the exterior cover and a configuration related to sound collection in the first embodiment. It is a schematic perspective view which shows the one aspect | mode when sound-collecting in the state which attached the exterior cover. 4 is a graph showing measurement results of sound generation positions and average distance measures of each sound in the first embodiment. It is a conceptual diagram which shows the structure of the sound source discrimination | determination system which concerns on Embodiment 2. FIG. FIG. 10 is an explanatory diagram illustrating a configuration related to each mounting site and sound collection of an exterior cover in the second embodiment. It is a graph which shows the measurement result of the average distance measure of a sound generation position and each sound in Embodiment 2. It is a perspective view which shows notionally the state of sound collection of the mechanical apparatus (copier etc.) equipped with the exterior cover part with an opening part, and the exterior cover part without an opening part. Average distance measurement results obtained when sound is collected on the side of the exterior cover part with the opening and on the side of the exterior cover part without the opening (when the sound is collected with a plate-like member installed) It is explanatory drawing which shows notion of this.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Microphone, 7 ... Board | plate material (plate-shaped member), 10 ... Sound collection part, 30 ... Sound extraction part, 40 ... Distance measure calculation part, 50 ... Judgment part, 71-73 ... Plastic plate (plate-like member), 100 ... Sound source discrimination system (sound source discrimination device), 200 ... copier (mechanical device), 250 ... exterior cover, 250C ... right side cover (cover portion where an opening exists), 250D ... back cover (cover where an opening exists) Part), 260... Discharge port (opening), 265... Exhaust port (opening).

Claims (4)

A sound collection unit that is covered with an exterior cover partly formed with an opening and has a sound source from a mechanical device having a plurality of types of sound sources whose occurrence is unknown, and picks up the sound as a sound signal by a microphone;
A sound extraction unit for converting the frequency waveform data showing the sound characteristics required for arithmetic processing by cut out the acoustic signal of the sound portion to be the determination target from the fetched audio signal,
For the cut determination target frequency waveform data obtained by converting the acoustic signal was cut out reference sound from the sound source in advance cause generates a clear plurality of types of sound Write-the sound cutout portion taken up in the sound pickup section A distance measure calculation unit for calculating a distance measure with frequency waveform data of a reference sound obtained by converting an acoustic signal ;
A judgment unit for judging the cause of sound generation by comparing the calculated distance measure with a threshold for sound source discrimination set based on a distance measure for a plurality of types of sounds from the sound source whose cause is obvious; A sound source discrimination device having
When the microphone is arranged toward the cover portion where at least the opening exists in the exterior cover and picks up sound, the plate is installed so as to be interposed between the cover portion where the opening exists and the microphone. A sound source discrimination device comprising a member. The discrimination device according to claim 1,
A sound source discriminating device that is installed so that the plate-like member is interposed between a mounting portion of the cover portion and a microphone in the mechanical device instead of a cover portion having at least an opening in the exterior cover. A sound collecting step of collecting sound from a mechanical device having a plurality of types of sound sources that are covered with an exterior cover partially formed with an opening and capturing the sound as a sound signal by a microphone,
Sound-cutting process step of converting the frequency waveform data showing the sound characteristics required for arithmetic processing by cut out the acoustic signal of the sound portion to be the determination target from the fetched audio signal,
For the cut determination target frequency waveform data obtained by converting the acoustic signal, in Write-the sound cut step takes reference sound from the sound source in advance cause generates a clear plurality of types of sound picked up by the microphone A distance measure calculation step for calculating a distance measure with the frequency waveform data of the reference sound obtained by converting the cut-out acoustic signal ;
A judgment step for judging the cause of the sound by comparing the calculated distance measure with a threshold for sound source discrimination set based on the distance measure for a plurality of types of sounds from the sound source in which the cause of occurrence is obvious; A sound source discrimination method comprising:
When the microphone is installed and picks up sound toward at least a cover portion where an opening exists in the exterior cover, a plate-like member is interposed between the cover portion where the opening exists and the microphone. A sound source discrimination method characterized by being installed and collecting the sound. In the discrimination method according to claim 3,
When removing a cover part having at least an opening from the exterior cover and installing a microphone toward the attachment part in the mechanical device of the removed cover part, the attachment part of the removed cover part is collected. A sound source discriminating method for picking up sound by installing the plate-like member between a microphone and a microphone.

Images