JP7056866B2 - Failure sign detection system, failure sign detection method and failure sign detection program - Google Patents

Description

The present invention relates to a failure sign detection system, a failure sign detection method and a failure sign detection program, and more particularly to a failure sign detection system for detecting a failure sign of a monitored device, a failure sign detection method and a failure sign detection program.

Patent Document 1 discloses a technique relating to an inspection device for inspecting an image forming device that forms an image according to a print job on a recording medium such as roll paper. The inspection device compares the scanned image read from the recording medium on which the image is formed with the formed image data which is image data such as bitmap data based on the print job data, and the difference exceeds a predetermined threshold value. Judge whether or not. At this time, the inspection device uses a second threshold value, which is set lower than the first threshold value for determining the presence or absence of a defect in image formation, as a predetermined threshold value, and is used as a precursor of a defect in the image forming device. Determine the presence or absence. Then, when it is determined that the difference exceeds the first or second threshold value, the inspection device stores the corresponding scanned image in the storage device.

Japanese Unexamined Patent Publication No. 2014-182551

However, in the above-mentioned Patent Document 1, when it is determined that the difference between the images exceeds a predetermined threshold value, it is always detected as a defect or a sign of the defect, and a case where the failure is not originally caused by a sudden cause is also included. Therefore, there is a problem that the detection accuracy is insufficient.

The present invention has been made to solve such a problem, and provides a failure sign detection system, a failure sign detection method, and a failure sign detection program for accurately detecting a failure sign of a monitored device. The purpose is to do.

The failure sign detection system according to the first aspect of the present invention is
A storage unit that stores normal image data, which is an image of normal measurement data in the monitored device,
A primary determination unit for determining whether or not the difference between the monitoring image data obtained by imaging the measurement data measured from the monitoring target device at a predetermined monitoring interval and the normal image data is outside the first range. ,
A secondary determination unit that determines whether or not there is a sign of failure of the monitored device based on the determination that the difference is out of the first range a plurality of times by the primary determination unit.
To prepare for.

The failure sign detection method according to the second aspect of the present invention is
The difference between the monitored image data obtained by imaging the measurement data measured from the monitored device at a predetermined monitoring interval and the normal image data obtained by imaging the normal measurement data of the monitored device is out of the first range. The primary judgment step to judge whether or not it is
A secondary determination step for determining whether or not there is a sign of failure of the monitored device based on the determination that the difference is out of the first range a plurality of times by the primary determination step.
including.

The failure sign detection program according to the third aspect of the present invention is
The difference between the monitored image data obtained by imaging the measurement data measured from the monitored device at a predetermined monitoring interval and the normal image data obtained by imaging the normal measurement data of the monitored device is out of the first range. The primary judgment process to judge whether or not it is
A secondary determination process for determining whether or not there is a sign of failure of the monitored device based on the determination that the difference is out of the first range a plurality of times by the primary determination process.
Let the computer run.

INDUSTRIAL APPLICABILITY According to the present invention, it is possible to provide a failure sign detection system, a failure sign detection method, and a failure sign detection program for accurately detecting a failure sign of a monitored device.

It is a block diagram which shows the structure of the failure sign detection system which concerns on Embodiment 1 of this invention. It is a flowchart which shows the flow of the failure sign detection method which concerns on Embodiment 1 of this invention. It is a block diagram which shows the structure of the failure sign detection system which concerns on Embodiment 2 of this invention. It is a flowchart which shows the flow of the failure sign detection method which concerns on Embodiment 2 of this invention. It is a block diagram which shows the structure of the failure sign detection system which concerns on Embodiment 3 of this invention. It is a flowchart which shows the flow of the white list registration process which concerns on Embodiment 3 of this invention. It is a block diagram which shows the structure of the failure sign detection system which concerns on Embodiment 4 of this invention. It is a flowchart which shows the flow of the feedback processing which concerns on Embodiment 4 of this invention. It is a block diagram which shows the structure of the failure sign detection system which concerns on Embodiment 5 of this invention. It is a flowchart which shows the flow of the whitelist registration process which concerns on Embodiment 5 of this invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and duplicate explanations are omitted as necessary for the sake of clarity of explanation.

<Embodiment 1>
FIG. 1 is a block diagram showing a configuration of a failure sign detection system 20 according to the first embodiment of the present invention. The failure sign detection system 20 is an information system for monitoring the monitored device 10 and detecting a failure sign of the monitored device 10. Here, the monitored device 10 is, for example, equipment in a factory, and the failure sign detection system 20 periodically monitors the operating sound, vibration, and the like of the monitored device 10. The failure sign detection system 20 includes a storage unit 21, a primary determination unit 22, and a secondary determination unit 23.

The storage unit 21 stores the normal image data 211 and the monitoring image data 212. For example, the storage unit 21 is a non-volatile storage device. The normal image data 211 is information obtained by imaging normal measurement data in the monitored device 10 as a waveform. Further, since the normal image data 211 is information indicating a state in which the monitored device 10 has not failed, it can also be called a white list in detecting a sign of failure. The monitoring image data 212 is information obtained by imaging measurement data measured from the monitoring target device 10 at a predetermined monitoring interval as a waveform. Here, the measurement data is, for example, time-series data in which the measurement time and the measured value are associated with each other, voice data at the time of measurement, vibration data, and the like. Further, the information obtained by imaging the measured data as a waveform is, for example, image data of a waveform obtained by graphing time-series data in a two-dimensional graph, image data of a waveform showing a frequency distribution of measured values, and the like. The image data is not limited to the waveform, and may be, for example, image data in which the horizontal axis is the time axis and the vertical axis is the frequency and the level of sound or the like for each frequency is represented by the color density or the like.

The primary determination unit 22 determines whether or not the difference between the monitoring image data 212 and the normal image data 211 is outside the first range. That is, the primary determination unit 22 compares the monitored image data 212 and the normal image data 211 as an image, calculates the difference information as an image, and determines whether or not the difference information exceeds a predetermined threshold value. Then, when the primary determination unit 22 determines that the difference information exceeds a predetermined threshold value, it is determined that the difference is out of the first range.

The secondary determination unit 23 determines whether or not there is a sign of failure of the monitored device 10 based on the determination that the difference is out of the first range a plurality of times by the primary determination unit 22. That is, even if the primary determination unit 22 determines that the difference is out of the first range only once within a certain period, the secondary determination unit 23 does not determine that it is a sign of failure. Then, the secondary determination unit 23 determines that the difference is out of the first range by the primary determination unit 22 more than a predetermined number of times within a certain period, or continuously within a certain period. If so, it is determined that the monitored device 10 has a sign of failure.

The storage unit 21, the primary determination unit 22, and the secondary determination unit 23 may be realized in the same computer device. In that case, for example, the control unit of the computer device reads and executes the failure sign detection program in which the processes of the primary determination unit 22 and the secondary determination unit 23 are implemented, so that the primary determination unit 22 and the secondary determination unit 23 are executed. Realize the processing. Further, the storage unit 21 may be an external storage device. Further, the primary determination unit 22 and the secondary determination unit 23 may be distributed and realized by two or more computer devices.

FIG. 2 is a flowchart showing the flow of the failure sign detection method according to the first embodiment of the present invention. As a premise, the storage unit 21 contains normal image data 211, which is waveform data based on data measured from the monitored device 10 during normal operation, and monitoring, which is waveform data based on data measured from the monitored device 10 during monitoring. It is assumed that the image data 212 and the image data 212 are stored in advance.

First, the primary determination unit 22 compares the normal image data 211 with the monitoring image data 212 and makes a primary determination (S11). Specifically, the primary determination unit 22 reads the normal image data 211 and the monitoring image data 212 from the storage unit 21, compares the results of image recognition of each of the read normal image data 211 and the monitoring image data 212, and makes a difference. Is calculated as numerical information. Then, the primary determination unit 22 determines whether or not the difference is outside the first range (S12). If the difference is within the first range, the process returns to step S11, and then step S11 is performed on the measured data.

On the other hand, when the difference is determined to be out of the first range, the primary determination unit 22 determines whether or not the difference is determined to be out of the first range a plurality of times (S13). If it is the first time, the process returns to step S11, and then step S11 is performed for the measured data.

On the other hand, if it is a plurality of times, the secondary determination unit 23 makes a secondary determination (S14). Specifically, the secondary determination unit 23 determines that the difference is out of the first range by the primary determination unit 22 more than a predetermined number of times within a certain period, or continuously within a certain period. If it has occurred, it is determined that the monitored device 10 has a sign of failure. If it is determined that there is no sign of failure, the process returns to step S11, and then step S11 is performed for the measured data. On the other hand, if it is determined that there is a sign of failure, the process is terminated. After that, it is possible to notify the user of a sign of failure.

For example, a predetermined machine operating in a factory is a monitored device, and a sign of failure of the machine is detected by measuring the machine sound. In this case, the voice of a worker, the sound of a speaker in a factory, or the like may be mixed with the measurement sound during monitoring. Since the waveform of such measurement data is different from the waveform of the mechanical sound in the normal state, it is detected as a sign of failure if only the primary determination is made. However, the voices of workers and the like are irrelevant to machine failures and are often temporary. Therefore, for example, if the monitoring interval is about 5 minutes, it is rare that the voice of the worker is confused and measured every time the monitoring is performed. Therefore, in the first embodiment, the secondary determination is performed for the case where the waveform of the measurement data measured at a predetermined monitoring interval is detected a plurality of times in the primary determination. As a result, even if an abnormal waveform is detected temporarily, if it continues or is not detected frequently, it can be suppressed from excessive detection by not considering it as a sign of failure. ..

As described above, in the first embodiment, it is not detected as a sign of failure simply because it does not correspond to the whitelist only once, but it is detected as a sign of failure only for an event that occurs a plurality of times. As a result, cases that are not originally a failure due to a sudden cause are excluded, and false detection is reduced, so that the accuracy of detecting a failure sign can be improved.

Further, by using the whitelist for detecting the sign of failure, it is not necessary to cover the abnormal cases in advance, and unknown abnormal cases can be detected. Further, since it is not necessary to confirm the operation for detecting an abnormal case in advance, the cost at the time of introduction can be reduced.

<Embodiment 2>
The second embodiment is an improved example of the first embodiment described above. That is, the storage unit stores a plurality of types of the normal image data, and the primary determination unit stores all the differences between the monitoring image data and the plurality of types of the normal image data. When it is out of the range, it is determined that the difference is out of the first range. In this way, by registering a plurality of types of normal cases in the white list, false positives can be reduced.

Further, when the primary determination unit determines that the difference is out of the first range, the primary determination unit notifies the secondary determination unit to that effect, and the secondary determination unit notifies the secondary determination unit to that effect. It is desirable to determine that there is a sign of the failure when the reception frequency of the above or the continuity of the notification exceeds a predetermined condition. As a result, sudden cases that are not actually abnormal can be excluded with a certain degree of validity, and the detection accuracy can be improved.

Further, it is desirable to further include a display unit for displaying the monitoring image data when the secondary determination unit determines that there is a sign of the failure. As a result, the user can visually check the waveform data detected as an abnormality, so that the validity of the detection can be easily determined.

FIG. 3 is a block diagram showing the configuration of the failure sign detection system 200 according to the second embodiment of the present invention. The failure sign detection system 200 embodies the failure sign detection system 20 described above, and is an information system for monitoring the monitored device 10 and detecting a failure sign of the monitored device 10. The failure sign detection system 200 includes a measurement unit 210, an image conversion unit 220, a primary determination unit 230, a secondary determination unit 240, a notification unit 250, and a storage unit 260.

The storage unit 260 is an example of the storage unit 21 described above, and stores measurement data 261, monitoring image data 262, whitelist 263, difference threshold value 264, notification frequency 265, and notification duration 266. The measurement data 261 is time-series data or the like of a combination of physical quantities such as sound, vibration, or odor measured from the monitored device 10 and the measurement time. The surveillance image data 262 is equivalent to the above-mentioned surveillance image data 212. The white list 263 is an information group including a plurality of types of normal image data. For example, when the measurement data 261 is audio data, the whitelist 263 shows the normal operating sound of a pure machine (monitoring target device 10) (one that is not mixed with other sounds), and the room in which the monitoring target device 10 is installed. Examples thereof include a sound in which the sound of the air conditioning and the normal operation sound of the machine are mixed, and the sound of the air conditioning when the operation of the monitored device 10 is stopped, that is, in the state where there is no machine sound. Further, as the sound of the air conditioner, the cooling sound when the air conditioner is weakly cooled and the normal operating sound of the machine are mixed, and the cooling sound when the air conditioner is strongly cooled and the normal operating sound of the machine are used. Sounds in which and are mixed may be included. This makes it possible to use a sound close to the actual measured sound, which differs depending on the season or time zone, as a whitelist. Therefore, cases that are not failures can be accurately excluded by the primary determination.

The difference threshold value 264 is a threshold value for detecting that the difference between the monitoring image data 262 and each normal image data in the whitelist 263 is different from the normal one by the primary determination. The difference threshold value 264 may be a different value in each of the plurality of types of normal image data.

The notification frequency 265 is the number of times the primary determination unit 230 notifies the secondary determination unit 240 within a certain period of time. In other words, the notification frequency 265 is the number of times that the primary determination unit 230 determines that the difference exceeds the difference threshold 264 within a certain period of time. The notification duration 266 is the number or time of consecutive notifications from the primary determination unit 230 with respect to the measurement interval (monitoring interval) in the measurement unit 210.

The measurement unit 210 acquires a predetermined physical quantity in the monitored device 10 at a predetermined monitoring interval and stores it in the storage unit 260 as measurement data 261. The image conversion unit 220 reads the measurement data 261 from the storage unit 260, converts the read measurement data 261 into image data when displayed as a waveform by a two-dimensional graph or the like, and stores it in the storage unit 260 as the monitoring image data 262. ..

The primary determination unit 230 is an example of the above-mentioned primary determination unit 22, and compares the monitoring image data 262 with each normal image data in the whitelist 263 and calculates the difference between them. Then, the primary determination unit 230 determines whether or not each of the calculated differences exceeds the difference threshold value 264. Then, when the primary determination unit 230 determines that all of the differences exceed the difference threshold value 264, the primary determination unit 230 notifies the secondary determination unit 240 to that effect.

The secondary determination unit 240 is an example of the above-mentioned secondary determination unit 23, and when the frequency of receiving notifications from the primary determination unit 230 or the continuity of the notifications exceeds a predetermined condition, the monitored device 10 fails. Judge that there is a sign. Then, when the secondary determination unit 240 determines that the monitored device 10 has a failure sign, the secondary determination unit 240 outputs a failure sign notification to the reporting unit 250. That is, the secondary determination unit 240 adds the notification frequency 265 each time the notification from the primary determination unit 230 is received within a certain period. Then, the secondary determination unit 240 outputs a failure sign notification to the notification unit 250 when the notification frequency 265 exceeds a predetermined number of times, and the secondary determination unit 240 is from the primary determination unit 230 within a certain period of time. Every time a notification is received, the measurement of the notification duration 266 is continued when the notification is continuously received at the monitoring interval of the measurement unit 210. Alternatively, the secondary determination unit 240 adds the number of continuations of the notification duration 266. Then, when the notification duration 266 exceeds a predetermined time or a predetermined number of times, the secondary determination unit 240 outputs a failure sign notification to the notification unit 250. The secondary determination unit 240 may perform the secondary determination using either or both of the notification frequency 265 and the notification duration 266.

The reporting unit 250 makes various notifications according to the failure sign detection from the secondary determination unit 240. For example, the reporting unit 250 includes a display unit 251, an alarm unit 252, and a mail transmitting unit 253. The display unit 251 is a display device such as a screen, and when a failure sign notification is received from the secondary determination unit 240, the corresponding monitoring image data 262 is read from the storage unit 260, and the read monitoring image data 262 is displayed on the screen. indicate. As a result, the user who monitors the failure of the monitored device 10 can easily grasp the sign of the failure and the process of detection, and can promptly take a subsequent action.

When the alarm unit 252 receives the failure sign notification from the secondary determination unit 240, the alarm unit 252 outputs an alarm to the user by sound or the like. When the mail transmission unit 253 receives the failure sign notification from the secondary determination unit 240, the mail transmission unit 253 sends an e-mail indicating that the failure sign has been detected in the monitored device 10 for the preset user's e-mail address. Send. The mail transmission unit 253 may include the monitoring image data 262 in the e-mail to be transmitted.

FIG. 4 is a flowchart showing the flow of the failure sign detection method according to the second embodiment of the present invention. As a premise, it is assumed that the white list 263 including a plurality of types of normal image data and the difference threshold value 264 are stored in the storage unit 260 at least in advance.

First, the measuring unit 210 measures the monitored device 10 at predetermined monitoring intervals (S21). Then, the measuring unit 210 stores the data measured from the monitored device 10 as the measurement data 261 in the storage unit 260. Next, the image conversion unit 220 images the measurement data 261 read from the storage unit 260 as a waveform and stores it in the storage unit 260 as the monitoring image data 262 (S22).

Subsequently, the primary determination unit 230 compares the monitoring image data 262 with each normal image data in the whitelist 263, and calculates the difference between them (S23). Then, the primary determination unit 230 determines whether or not all of the calculated differences exceed the difference threshold value 264 (S24).

If it is determined in step S24 that even a part of the difference does not exceed the difference threshold value 264, the process returns to step S21. On the other hand, when it is determined in step S24 that all of the differences exceed the difference threshold value 264, the primary determination unit 230 notifies the secondary determination unit 240 to that effect (S25).

After that, the secondary determination unit 240 calculates the notification frequency 265 and the notification duration 266 in response to the notification from the primary determination unit 230 (S26). Then, the secondary determination unit 240 determines whether the notification frequency 265 exceeds the predetermined number of times, or the notification continuation time 266 exceeds the predetermined time (S27). If it is determined in step S27 that none of the conditions is exceeded, the process returns to step S21. On the other hand, if it is determined in step S27 that any of the conditions is exceeded, the secondary determination unit 240 notifies the notification unit 250 of the failure sign (S28).

The reporting unit 250 displays, alerts, and sends an e-mail in response to a failure sign notification from the secondary determination unit 240 (S29). That is, the display unit 251 reads the corresponding monitoring image data 262 from the storage unit 260 and displays it on the screen. The alarm unit 252 outputs an alarm. The mail transmission unit 253 sends an e-mail indicating that a sign of failure has been detected to a preset user's e-mail address.

As described above, by registering a plurality of types of normal cases in the white list according to the second embodiment, for example, various environmental sounds (air conditioning, etc.) other than the mechanical sound to be monitored can be added to perform the primary determination. .. Therefore, it is possible to reduce erroneous detection due to the primary determination.

Further, by performing the secondary determination using the statistical information notified by the primary determination, it is possible to perform accurate detection so that the expert can identify the sign of failure based on the tendency of the notification. Further, since the waveform data detected as an abnormality can be visually checked by the user, it becomes easy to determine the validity of the detection.

<Embodiment 3>
The third embodiment is an improved example of the second embodiment described above. That is, it further includes a registration unit for additionally registering the first image data, which is an image of the measurement data measured from the monitoring target device as a waveform, in the storage unit as the normal image data. This facilitates whitelisting. In addition, it is not necessary to prepare abnormal data in advance, and normal data in various situations can be easily registered.

Further, the registration unit compares the first image data with the second image data which is the normal image data registered in the storage unit before the additional registration, and the first image data and the first image data. When the difference from the two image data is within the second range, it is desirable to delete one of the first image data and the second image data and register the other in the storage unit. As a result, duplicate registration can be prevented and the amount of whitelist data can be suppressed.

FIG. 5 is a block diagram showing the configuration of the failure sign detection system 200a according to the third embodiment of the present invention. In FIG. 5, the description of the same configuration as that of FIG. 3 will be omitted as appropriate, and the description will also be omitted.

The failure sign detection system 200a includes a registration unit 270 in addition to the configuration of the failure sign detection system 200 described above. The registration unit 270 additionally registers the measurement image data 267 (first image data), which is an image of the measurement data 261 measured from the monitoring target device 10 as a waveform, in the storage unit 260 as normal image data of the whitelist 263. Here, the registration unit 270 compares the first image data with the second image data (in the white list 263) registered in the storage unit 260 before additional registration, and the first image. When the difference between the data and the second image data is within the duplication determination threshold 268 (second range), one of the first image data and the second image data is deleted, and the other is registered in the storage unit 260.

FIG. 6 is a flowchart showing the flow of the whitelist registration process according to the third embodiment of the present invention. As a premise, it is assumed that at least the white list 263 including one or more normal image data and the duplication determination threshold value 268 are stored in the storage unit 260 in advance. Further, the whitelist registration process according to the third embodiment can be carried out as a preliminary preparation for the failure sign detection method according to the second embodiment described above. Further, the whitelist registration process may be performed during the monitoring interval of step S21 in FIG.

First, the measuring unit 210 makes a measurement during normal operation of the monitored device 10 (S31). Then, the measuring unit 210 stores the data measured from the monitored device 10 as the measurement data 261 in the storage unit 260. Next, the image conversion unit 220 images the measurement data 261 read from the storage unit 260 as a waveform and stores it in the storage unit 260 as the measurement image data 267 (S32).

Subsequently, the registration unit 270 compares the measured image data 267 with each normal image data in the whitelist 263, and calculates the difference between them (S33). Then, the registration unit 270 determines whether or not all of the calculated differences exceed the duplication determination threshold value 268 (S34).

When it is determined in step S34 that all of the differences exceed the overlap determination threshold value 268, the registration unit 270 adds the measurement image data 267 to the whitelist 263 and registers it (S35). On the other hand, when it is determined in step S34 that even a part of the difference is within the range of the duplication determination threshold value 268, the registration unit 270 deletes the measurement image data 267 (S36) and does not register it in the white list 263. In step S36, the registration unit 270 does not delete the measurement image data 267, deletes the normal image data determined to overlap with the measurement image data 267, and additionally registers the measurement image data 267 in the whitelist 263. May be good.

As described above, according to the third embodiment, it is possible to prevent duplicate registration of normal image data in the whitelist and suppress the amount of data in the whitelist. Further, the data measured during the normal operation of the monitored device 10 can be easily registered in the white list without preparing the abnormal data in advance. Therefore, it becomes easy to cover various situations at normal times.

<Embodiment 4>
The fourth embodiment is an improved example of the second or third embodiment described above. That is, when the response to the embodiment 2 that the monitoring image data displayed on the display unit is normal is received, the monitoring image data is added to the storage unit as the normal image data. It also has a registration unit for registration. Alternatively, when the registration unit receives a response to the third embodiment that the monitoring image data displayed on the display unit is normal, the monitoring image data is used as the first image data. The first image data is additionally registered in the storage unit as the normal image data. As a result, the detection accuracy can be improved by the feedback of the determination result by the user with respect to the detection result of the failure sign.

FIG. 7 is a block diagram showing the configuration of the failure sign detection system 200b according to the fourth embodiment of the present invention. In FIG. 7, the description of the same configuration as that of FIG. 3 will be omitted as appropriate, and the description will also be omitted.

The failure sign detection system 200b includes a reception unit 281 and a registration unit 282 in addition to the configuration of the failure sign detection system 200 described above. The registration unit 282 may be shared with the registration unit 270 of FIG. The reception unit 281 receives a reply from the user U that the monitoring image data 262 displayed on the display unit 251 is normal (no sign of failure) or abnormal (presence of failure). When the reception unit 281 receives a reply indicating that it is normal, the registration unit 282 additionally registers the monitoring image data 262 as normal image data in the whitelist 263 in the storage unit 260.

FIG. 8 is a flowchart showing the flow of feedback processing according to the fourth embodiment of the present invention. As a premise, it is assumed that the monitoring image data 262 detected by step S29 in FIG. 4 as having a sign of failure is displayed on the display unit 251.

First, the user U who monitors the failure of the monitored device 10 visually checks the monitoring image data 262 displayed on the display unit 251 and determines whether or not the monitoring image data 262 shows a sign of failure. Then, the reception unit 281 receives a response (feedback) from the user U to the effect that the monitoring image data 262 is normal or abnormal (S41).

Here, when the answer indicates that the monitored image data 262 is normal data, that is, false detection, the registration unit 282 additionally registers the monitored image data 262 as normal image data in the whitelist 263 in the storage unit 260. (S43). On the other hand, when the answer indicates that the monitoring image data 262 is abnormal data, that is, the detection is correct and there is a possibility of a failure sign, the registration unit 282 does not additionally register the monitoring image data 262. For example, the registration unit 282 deletes the monitoring image data 262.

As described above, according to the fourth embodiment, the detection accuracy can be improved by the feedback of the determination result by the user with respect to the detection result of the failure sign.

<Embodiment 5>
The fifth embodiment is a modification of the third or fourth embodiment described above. That is, before the additional registration, the registration unit compares the first image data with the second image data which is the normal image data registered in the storage unit, and the first image data and the first image data. 2 When the difference from the image data is within the second range, the first image data and the second image data are integrated to generate integrated image data, and the integrated image data is used as the normal image data. It is additionally registered in the storage unit and the width of the first range is adjusted. The first image data may be the monitoring image data displayed on the display unit, which has received the reply that it is normal in the fourth embodiment. As a result, the detection accuracy can be improved while suppressing the amount of data in the whitelist by collecting similar cases and determining the surroundings as normal cases.

FIG. 9 is a block diagram showing the configuration of the failure sign detection system 200c according to the fifth embodiment of the present invention. In FIG. 9, the description of the same configuration as that of FIG. 5 is omitted as appropriate, and the description is also omitted. Similar to the registration unit 270 described above, the registration unit 270a is the measurement image data 267 (first image data) and the normal image data (in the whitelist 263) registered in the storage unit 260 before the additional registration. Compare with the second image data. Then, when the difference between the first image data and the second image data is within the overlap determination threshold 268 (second range), the registration unit 270a integrates and integrates the first image data and the second image data. Image data is generated, and the integrated image data is additionally registered in the storage unit 260 as normal image data in the white list 263. Further, the registration unit 270a adjusts the value of the difference threshold value 264, that is, the width of the first range.

FIG. 10 is a flowchart showing the flow of the whitelist registration process according to the fifth embodiment of the present invention. Since steps S31 to S35 are the same as those in FIG. 6 described above, the description thereof will be omitted.

Here, when it is determined in step S34 that even a part of the difference is within the range of the duplication determination threshold value 268, the registration unit 270a determines that the measurement image data 267 and the duplication determination threshold value 268 are within the range before additional registration. The determined normal image data is integrated to generate integrated image data (S37). Then, the registration unit 270a additionally registers the integrated image data in the white list 263 (S38). Further, the registration unit 270a deletes the measurement image data 267 and the normal image data determined to be within the range of the duplication determination threshold value 268 from the storage unit 260 (S39). After that, the registration unit 270a adjusts the difference threshold value 264 (S40). Specifically, the registration unit 270a separates the original difference threshold value 264 from the measurement image data 267 and the original difference threshold value 264 from the normal image data determined to be within the range of the overlap determination threshold value 268. The difference threshold 264 is increased so that both of the above are included. That is, the first range is expanded.

As described above, according to the fifth embodiment, by collecting similar waveform data and determining the periphery thereof as a normal case, it is possible to improve the detection accuracy while suppressing the amount of data in the white list.

<Embodiment 6>
The sixth embodiment is an improved example of the above-mentioned embodiments 2 to 5. That is, the attribute information is associated with each of the normal image data registered as the white list. For example, each normal image data is associated with text information indicating its characteristics. The text information is, for example, the normal operating sound of the monitored device 10 when the air conditioner is weakly cooled. Further, when the reception unit 281 of the fourth embodiment receives text information as a reply from the user U and the registration unit 282 additionally registers the monitoring image data 262 to the whitelist 263, the received text information is associated with the reception unit 281. It is good.

As described above, according to the sixth embodiment, the user U can easily grasp the attributes of each normal image data registered in the whitelist 263, so that the maintainability of the whitelist 263 by the user U can be improved.

<Other embodiments>
The present invention is not limited to the above embodiment, and can be appropriately modified without departing from the spirit.

Further, in the above-described embodiment, the present invention has been described as a hardware configuration, but the present invention is not limited thereto. The present invention can also realize arbitrary processing by causing a CPU (Central Processing Unit) to execute a computer program.

In the above example, the program can be stored and supplied to the computer using various types of non-transitory computer readable medium. Non-temporary computer-readable media include various types of tangible storage media. Examples of non-temporary computer readable media include magnetic recording media (eg, flexible disks, magnetic tapes, hard disk drives), optomagnetic recording media (eg, optomagnetic disks), CD-ROMs (Read Only Memory), CD-Rs. Includes CD-R / W, DVD (Digital Versatile Disc), semiconductor memory (eg, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)). The program may also be supplied to the computer by various types of transient computer readable medium. Examples of temporary computer readable media include electrical, optical, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.

10 Monitored device 20 Failure sign detection system 21 Storage unit 211 Normal image data 212 Monitoring image data 22 Primary judgment unit 23 Secondary judgment unit 200 Failure sign detection system 210 Measuring unit 220 Image conversion unit 230 Primary judgment unit 240 Secondary judgment unit 250 Notification unit 251 Display unit 252 Alarm unit 253 Mail transmission unit 260 Storage unit 261 Measurement data 262 Monitoring image data 263 White list 264 Difference threshold 265 Notification frequency 266 Notification duration 200a Failure sign detection system 270 Registration unit 267 Measurement image data 268 Duplicate Judgment threshold 200b Failure sign detection system 281 Reception section 282 Registration section 200c Failure sign detection system 270a Registration section U User

Claims (10)

An image conversion unit that converts measurement data, which is time-series data measured from a monitored device at a predetermined monitoring interval, into image data when displayed on the display unit, and an image conversion unit.
A storage unit that stores normal image data in which normal measurement data in the monitored device is converted by the image conversion unit, and a storage unit.
A primary determination unit for determining whether or not the difference between the monitoring image data whose measurement data is converted by the image conversion unit and the normal image data is outside the first range.
A secondary determination unit that determines whether or not there is a sign of failure of the monitored device based on the determination that the difference is out of the first range a plurality of times by the primary determination unit.
A failure sign detection system equipped with. The storage unit stores a plurality of types of the normal image data, and stores the normal image data.
When the difference between the monitoring image data and the normal image data of each of the plurality of types is outside the first range, the primary determination unit determines that the difference is outside the first range. The failure sign detection system according to claim 1. The primary determination unit is
When it is determined that the difference is out of the first range, the secondary determination unit is notified to that effect.
The secondary determination unit is
The failure sign detection system according to claim 1 or 2, wherein it is determined that there is a sign of failure when the frequency of receiving notifications from the primary determination unit or the continuity of the notification exceeds a predetermined condition. Claims 1 to 3 further include a registration unit for additionally registering the first image data obtained by converting the measurement data measured in a normal state from the monitored device to the image conversion unit as the normal image data in the storage unit. The failure sign detection system according to any one of the above items. The registration unit
Before the additional registration, the first image data and the second image data, which is the normal image data registered in the storage unit, are compared.
When the difference between the first image data and the second image data is within the second range, one of the first image data and the second image data is deleted, and the other is registered in the storage unit. The failure sign detection system according to claim 4. The registration unit
Before the additional registration, the first image data and the second image data, which is the normal image data registered in the storage unit, are compared.
When the difference between the first image data and the second image data is within the second range, the first image data and the second image data are integrated to generate integrated image data, and the integration is performed. The failure sign detection system according to claim 4, wherein the image data is additionally registered in the storage unit as the normal image data, and the width of the first range is adjusted. When the secondary determination unit determines that there is a sign of the failure, the display unit displays the monitoring image data.
The failure sign detection system according to any one of claims 1 to 6. The registration unit
When a reply to the effect that the monitored image data displayed on the display unit is normal is received, the monitored image data is used as the first image data, and the first image data is used as the normal image data. The failure sign detection system according to claim 7, which is subordinate to any one of claims 4 to 6 to be additionally registered in the storage unit. An image conversion step for converting measurement data, which is time-series data measured from a monitored device at a predetermined monitoring interval, into monitoring image data when displayed on the display unit, and an image conversion step.
A primary determination step for determining whether or not the difference between the monitored image data and the normal image data obtained by converting the normal measurement data in the monitored device by the image conversion step is outside the first range. ,
A secondary determination step for determining whether or not there is a sign of failure of the monitored device based on the determination that the difference is out of the first range a plurality of times by the primary determination step.
Failure sign detection method including. Image conversion processing that converts measurement data, which is time-series data measured from the monitored device at a predetermined monitoring interval, into monitoring image data when displayed on the display unit, and image conversion processing.
A primary determination process for determining whether or not the difference between the monitored image data and the normal image data obtained by converting the measurement data in the normal state of the monitored device by the image conversion process is out of the first range. ,
A secondary determination process for determining whether or not there is a sign of failure of the monitored device based on the determination that the difference is out of the first range a plurality of times by the primary determination process.
A failure sign detection program that causes the computer to execute.

Images