JP7783385B2 - Flame detector deterioration determination device, program, and flame detection system - Google Patents

Description

The present invention relates to technology for maintaining flame detectors.

Disaster prevention systems may stop working properly due to deterioration. Various technologies have been proposed to prevent such problems. For example, Patent Document 1 proposes a disaster prevention system that monitors the current value flowing in the signal line connecting the disaster prevention receiving panel to a terminal device that outputs a fire signal to the disaster prevention receiving panel when a fire is detected, and if the current value changes significantly, it determines that this is a sign of a malfunction caused by insulation deterioration in the signal line, etc., and outputs a warning.

Japanese Patent Application Laid-Open No. 2018-67032

Some flame detectors detect flames using a sensor that is sensitive to the light emitted by the flame. One cause of malfunction in such flame detectors is deterioration of the components that make up the flame detector. For example, if the light-sensitive sensor in a flame detector deteriorates, the amplitude of the signal output from the sensor may show irregular fluctuations regardless of the presence or absence of light. Furthermore, if the amplifier that amplifies the signal generated by the sensor deteriorates, the amplitude of the signal amplified by the amplifier from the sensor may show a steadily high value regardless of the presence or absence of light.

As parts deteriorate as described above, the accuracy of the flame detection judgment made by the flame detector decreases. Therefore, if the degree of deterioration of the flame detector can be determined, the required accuracy of flame detection judgment can be maintained by replacing parts, etc.

In light of these circumstances, the present invention aims to make it possible to determine the degree of deterioration of a flame detector.

In one aspect, the present invention provides a deterioration level determination device that includes an acquisition unit that acquires night vision noise data indicating the intensity of light measured by a flame detector that detects flames based on the intensity of light measured by a sensor during a period when light traveling from the outside to the sensor is blocked; a memory unit that stores the night vision noise data acquired by the acquisition unit; and a deterioration level determination unit that calculates an average value of the light intensity indicated by the night vision noise data stored in the memory unit and an index indicating the variation in the light intensity indicated by the night vision noise data stored in the memory unit, and, if the average value satisfies a predetermined condition, infers that a first type of part included in the flame detector is a part that needs to be replaced, and, if the index indicating the variation satisfies a predetermined condition, infers that a second type of part, different from the first type of part, included in the flame detector is a part that needs to be replaced.

In one aspect, the present invention provides a deterioration level determination device that includes an acquisition unit that acquires night vision noise data indicating the intensity of light measured by a flame detector that detects flames based on the intensity of light measured by a sensor during a period when light traveling from the outside to the sensor is blocked; and a deterioration level determination unit that inputs the night vision noise data acquired by the acquisition unit into a learning model generated by machine learning using training data for a flame detector of the same type as the flame detector, where the type of part replaced in past maintenance work and the degree of deterioration of the part are the objective variables and the night vision noise data before the part was replaced are the explanatory variables, and outputs from the learning model the type of part that needs to be replaced among the parts included in the flame detector and the degree of deterioration of the part.

In one aspect, the present invention provides a program for implementing the above-described deterioration level determination device on a computer.

In one aspect, the present invention provides a flame detection system comprising a flame detector and the above-described deterioration level determination device, wherein the flame detector comprises: a sensor that measures light intensity; a flame detection unit that detects a flame based on the light intensity measured by the sensor; a shielding member detection unit that detects that a shielding member that blocks light directed toward the sensor from the outside has been attached to the device; a shielding period determination unit that determines a period during which light directed toward the sensor from the outside is blocked based on the detection results of the shielding member detection unit; and an output unit that outputs night vision noise data indicating the light intensity measured by the sensor during the period determined by the shielding period determination unit, wherein the shielding member detection unit comprises one of a contact sensor that detects contact with the shielding member, a magnetic sensor that detects magnetic force emitted by the shielding member, and a proximity sensor that detects electromagnetic waves emitted by the shielding member in accordance with a short-range wireless communication standard; and the acquisition unit of the deterioration level determination device acquires the night vision noise data output by the output unit of the flame detector.

This invention makes it possible to determine the degree of deterioration of a flame detector.

1 is a diagram showing the overall configuration of a flame detection system according to an embodiment; FIG. 1 is a diagram schematically illustrating a hardware configuration of a flame detector according to an embodiment. FIG. 1 is a diagram illustrating an example of the appearance of a flame detector according to an embodiment. 1 is a diagram illustrating an example of the appearance of a shielding device according to an embodiment; FIG. 2 is a diagram schematically illustrating the functional configuration of a flame detector according to an embodiment. FIG. 10 is a diagram illustrating the configuration of a measurement value log table according to an embodiment. FIG. 4 is a diagram illustrating the configuration of a temperature correction constant table according to an embodiment. 10 is a graph illustrating a method for identifying an occlusion period by an occlusion period identifying unit according to an embodiment; FIG. 2 is a diagram illustrating a hardware configuration of a disaster prevention receiving panel according to an embodiment. FIG. 2 is a diagram illustrating a functional configuration of a disaster prevention receiving panel according to an embodiment. FIG. 4 is a diagram illustrating the configuration of a night vision noise table according to an embodiment. 6 is a graph illustrating a method in which a deterioration level determining device according to an embodiment determines a deterioration level and estimates deteriorated parts. 6 is a graph illustrating a method in which a deterioration level determining device according to an embodiment determines a deterioration level and estimates deteriorated parts. FIG. 10 is a diagram illustrating the configuration of a degradation diagnosis result table according to an embodiment. FIG. 10 is a diagram illustrating an example of a degradation diagnosis screen displayed by a terminal device according to an embodiment. FIG. 10 is a diagram schematically illustrating a hardware configuration of a flame detector according to a modified example. FIG. 10 is a diagram schematically illustrating the functional configuration of a flame detector according to a modified example.

[Embodiment]
Hereinafter, a flame detection system 1 according to one embodiment of the present invention will be described. Fig. 1 is a diagram showing the overall configuration of the flame detection system 1. The flame detection system 1 is a system that detects a flame occurring in a tunnel TN.

The flame detection system 1 comprises n flame detectors, namely, flame detectors 11(1), 11(2), 11(3), ..., 11(n), installed at approximately equal intervals along the direction of vehicle travel inside the tunnel TN. Hereinafter, these n flame detectors will be collectively referred to as flame detectors 11.

Each flame detector 11 essentially integrates two flame detectors. Specifically, the flame detector 11 integrates a flame detector whose monitoring area is a specified area on the right side of the flame detector 11 (hereinafter referred to as the "right flame detector"), and a flame detector whose monitoring area is a specified area on the left side of the flame detector 11 (hereinafter referred to as the "left flame detector").

Tunnel TN is divided into monitoring areas A(1), A(2), A(3), ..., A(n-1). Hereinafter, these (n-1) monitoring areas will be collectively referred to as monitoring area A. Each monitoring area A is monitored by two adjacent flame detectors 11 in an overlapping manner. For example, monitoring area A(1) is monitored by the left flame detector of flame detector 11(1) and the right flame detector of flame detector 11(2). Therefore, even if one of the two adjacent flame detectors 11 fails, monitoring of monitoring area A will not be interrupted unless the other fails at the same time.

In addition to flame detectors 11, the flame detection system 1 includes disaster prevention receiving panels 12 that are communicatively connected to each of the flame detectors 11, a server device 13 that is communicatively connected to the disaster prevention receiving panels 12, and a terminal device 14 that can communicate with the server device 13.

Figure 2 is a diagram showing a schematic diagram of the hardware configuration of the flame detector 11. The flame detector 11 includes a computer 101, four sensors connected to the computer 101, namely, sensor 111R, sensor 112R, sensor 111L, and sensor 112L, four amplifiers corresponding to each of the four sensors, namely, amplifier 113R, amplifier 114R, amplifier 113L, and amplifier 114L, and a thermometer 115 connected to the computer 101.

Sensors 111R and 112R are optical sensors for monitoring monitoring area A on the right side as viewed from flame detector 11. Sensors 111L and 112L are optical sensors for monitoring monitoring area A on the left side as viewed from flame detector 11.

Sensors 111R and 111L are long-wavelength optical sensors that respond with high sensitivity to the long-wavelength wavelength band emitted by flames (heat sources). For example, optical sensors using pyroelectric elements are used as sensors 111R and 111L. Hereinafter, sensors 111R and 111L are collectively referred to as sensors 111.

Sensors 112R and 112L are short wavelength optical sensors that respond with high sensitivity to the short wavelength band emitted by flames (heat sources). For example, optical sensors using photodiodes are used as sensors 112R and 112L. Hereinafter, sensors 112R and 112L are collectively referred to as sensors 112.

Amplifier 113R is connected between computer 101 and sensor 111R and amplifies the signal generated by sensor 111R in response to light. Amplifier 114R is connected between computer 101 and sensor 112R and amplifies the signal generated by sensor 112R in response to light. Amplifier 113L is connected between computer 101 and sensor 111L and amplifies the signal generated by sensor 111L in response to light. Amplifier 114L is connected between computer 101 and sensor 112L and amplifies the signal generated by sensor 112R in response to light.

In the following description, unless otherwise specified, the term "signal output from sensor 111 or sensor 112" refers to the signal output from sensor 111 or sensor 112 and amplified by amplifier 113 or amplifier 114.

The thermometer 115 measures the temperature inside the housing of the flame detector 11 and outputs temperature data indicating the measured temperature to the computer 101.

The computer 101 is equipped with a processor 1011 that processes data according to a program, a memory 1012 that stores various data including programs, an input/output interface 1013 that receives signal input from four sensors via four amplifiers and temperature data input from a thermometer 115, and a communication interface 1014 that communicates data with the disaster prevention receiving panel 12.

In addition to the components shown in Figure 2, the flame detector 11 also includes components such as an A/D converter that converts the analog signals output by the four sensors into digital signals. However, since these are unrelated to the features of the present invention, they are omitted from Figure 2 and will not be described further below.

Figure 3 is a diagram illustrating the external appearance of the flame detector 11. The flame detector 11 has a light-transmitting window W, through which light from the outside enters the housing of the flame detector 11. Sensors 111 and 112 are sensitive to light that passes through the window W and enters from the outside. Note that the housing of the flame detector 11 (parts other than the window W) does not transmit light.

A maintenance technician who performs maintenance on the flame detection system 1, for example, periodically visits the tunnel TN and continuously covers the window W of each flame detector 11 with a shielding device S for approximately a predetermined period of time (e.g., 30 seconds). This work is performed to measure noise (hereinafter referred to as "night vision noise"), which is a component not derived from light, contained in the signal output from the sensor 111 or sensor 112 of the flame detector 11.

Figure 4 is a diagram illustrating the appearance of the shielding device S. Figure 4(a) is a view of the shielding device S from the front, Figure 4(b) is a view of the shielding device S from the back, and Figure 4(c) is a view of the shielding device S from above. The shielding device S comprises a light-opaque shielding plate P, a handle H attached to the front side of the shielding plate P, and an oval ring-shaped elastic member C (which, together with the shielding plate P, constitutes an example of a shielding member) attached to the back side of the shielding plate P. A maintenance worker grasps the handle H and presses the shielding device S against the flame detector 11 at a position where the elastic member C roughly coincides with the outer periphery of the window W of the flame detector 11, thereby covering the window W.

Figure 5 is a diagram showing a schematic diagram of the functional configuration of the flame detector 11. That is, when the processor 1011 of the computer 101 executes processing according to the program of this embodiment, the flame detector 11 equipped with a determination device indicated by the reference numeral 116 in Figure 5 is realized. The functional configuration of the determination device 116 will be described below.

Determination device 116 comprises determination device 116R, which determines whether a flame has been detected using signals output from sensors 111R and 112R, and determination device 116L, which determines whether a flame has been detected using signals output from sensors 111L and 112L. Because determination device 116R and determination device 116L have a common configuration, the following description will be given of the configuration of determination device 116R as an example, and a description of the configuration of determination device 116L will be omitted.

The determination device 116R includes a memory unit 1161R, an acquisition unit 1162R, a correction unit 1163R, a shielding period determination unit 1164R, a flame detection unit 1165R, a transmission/reception unit 1166R, and a timing unit 1167R.

The memory unit 1161R is realized by the memory 1012, which operates under the control of the processor 1011. The memory unit 1161R stores various data. The data stored in the memory unit 1161R includes a measurement value log table, a temperature correction constant table, and steady-state correction constant data.

Figure 6 is a diagram illustrating the configuration of a measurement value log table. A measurement value log table is prepared for each of sensors 111R and 112R. The measurement value log table has a "Time" column, a "Temperature" column, a "Intensity (Actual Measurement)" column, a "Intensity (Temperature Corrected)" column, and a "Intensity (Steady State Correction)" column. The "Time" column stores the time measured by the timer unit 1167R when a signal is output from the sensor. The "Temperature" column stores the temperature measured by the thermometer 115 when a signal is output from the sensor. The "Intensity (Actual Measurement)" column stores the amplitude value of the signal output from the sensor. The "Intensity (Temperature Corrected)" column stores the value obtained by correcting the amplitude value stored in the "Intensity (Actual Measurement)" column using a temperature correction constant, which will be described later, by the correction unit 1163R. The "Intensity (Steady State Correction)" column stores the value obtained by correcting the amplitude value stored in the "Intensity (Temperature Correction)" column using a steady state correction constant, which will be described later, by the correction unit 1163R.

Figure 7 is a diagram illustrating the configuration of a temperature correction constant table. A temperature correction constant table is prepared for each of sensors 111R and 112R. The temperature correction constant table has columns for "Temperature" and "Temperature Correction Constant." Various temperatures are stored in the "Temperature" column. The "Temperature Correction Constant" column stores a temperature correction constant corresponding to the temperature stored in the "Temperature" column. The amplitude values of the signals generated by sensors 111R and 112R are biased by the influence of temperature. The temperature correction constant is a value that is subtracted from the amplitude value of the signal generated by sensor 111R or sensor 112R to cancel the bias due to the influence of temperature, and is a value measured in advance through experiments using sensor 111R or sensor 112R.

The steady-state correction constant data is data that indicates a steady-state correction constant. In addition to the bias due to the temperature influence described above, the amplitude values of the signals generated by sensors 111R and 112R are also subject to a bias unrelated to temperature. The steady-state correction constant is a value that is subtracted from the amplitude value of the signal generated by sensor 111R or sensor 112R to cancel the bias unrelated to temperature. In this embodiment, the average value of the amplitude values indicated by the night vision noise data described below is used as the steady-state correction constant.

Continuing with the explanation of the functional configuration of the flame detector 11 (Figure 5), the acquisition unit 1162R is implemented by the input/output interface 1013, which operates under the control of the processor 1011. The acquisition unit 1162R continuously acquires the signals output from the sensors 111R and 112R. The amplitude values of these signals acquired by the acquisition unit 1162R are stored in a measurement value log table together with the time and temperature at that time.

The correction unit 1163R is implemented by the processor 1011. When new data is stored in the "Time", "Temperature" and "Intensity (Actual Measurement)" columns of the measurement value log table, the correction unit 1163R refers to the temperature correction constant table to identify the temperature correction constant corresponding to the temperature stored in the "Temperature" column, and stores the value obtained by subtracting the temperature correction constant from the amplitude value stored in the "Intensity (Actual Measurement)" column in the "Intensity (After Temperature Correction)" column. Next, the correction unit 1163R subtracts the steady-state correction constant from the value stored in the "Intensity (After Temperature Correction)" column, and stores the value obtained by subtracting the steady-state correction constant from the value stored in the "Intensity (After Temperature Correction)" column in the "Intensity (After Steady-State Correction)" column.

The blocking period determination unit 1164R is realized by the processor 1011. For each of the sensors 111R and 112R, the blocking period determination unit 1164R determines the period during which light traveling from the outside world toward those sensors is blocked (hereinafter referred to as the "blocking period") based on the data stored in the measurement value log table corresponding to those sensors.

Figure 8 is a graph illustrating the method for identifying the occlusion period performed by the occlusion period identification unit 1164R. The graph in Figure 8 shows the change in light intensity over time, indicated by the amplitude values stored in the "Intensity (actual measurement)" column of the measurement value log table corresponding to the sensor 111, for example. Note that because the graph in Figure 8 is a graph relating to a short period of time, such as a few minutes, the values stored in the "Intensity (temperature corrected)" column or the "Intensity (steady-state corrected)" column may be used instead of the amplitude values stored in the "Intensity (actual measurement)" column.

Based on the data stored in the measurement value log table, for example, if the intensity drops sharply, and then the intensity fluctuations remain within a predetermined threshold for a predetermined period of time (e.g., 25 seconds to 35 seconds), and then the intensity rises sharply, the occlusion period identification unit 1164R identifies the period from when the intensity suddenly dropped to when the intensity suddenly rose as the occlusion period. In the example graph of Figure 8, the occlusion period identification unit 1164R identifies period Q1 as the occlusion period.

Continuing with the explanation of the functional configuration of the flame detector 11 (Figure 5), the flame detection unit 1165R is implemented by the processor 1011. The flame detection unit 1165R refers to the measurement value log table, and if it determines that the amplitude value of the signal output from sensor 111R (the value in the "Intensity (after steady-state correction)" column) and the amplitude value of the signal output from sensor 112R (the value in the "Intensity (after steady-state correction)" column) satisfy a predetermined condition, it stores data indicating that a flame has been detected in the memory unit 1161R. Furthermore, if the flame detection unit 1165R determines that the condition is not satisfied, it stores data indicating that a flame has not been detected in the memory unit 1161R.

Examples of conditions used by the flame detection unit 1165R to determine whether a flame has been detected are shown below.
(Condition 1) The amplitude value of the signal output from the sensor 111R is equal to or greater than the threshold value T1.
(Condition 2) The amplitude value of the signal output from the sensor 112R is equal to or greater than the threshold value T2.
(Condition 3) The ratio of the amplitude value of the signal output from sensor 111R to the amplitude value of the signal output from sensor 112R is equal to or greater than threshold T3 and equal to or less than threshold T4 (where T3<T4).

The flame detection unit 1165R determines that a flame has occurred if all of the above conditions 1 to 3 have been met a predetermined number of times or more within a predetermined period of time (e.g., 10 seconds) in the past.

The transmitter/receiver 1166R (an example of an output unit) is realized by the communication interface 1014, which operates under the control of the processor 1011. The transmitter/receiver 1166R continuously outputs a flame detection signal to the disaster prevention receiving panel 12 while data indicating that a flame has been detected is stored in the memory unit 1161R. The transmitter/receiver 1166R also outputs data stored in the measurement value log table that is for the occlusion period identified by the occlusion period identification unit 1164R to the disaster prevention receiving panel 12 as data indicating night vision noise (hereinafter referred to as "night vision noise data").

The transmitter/receiver 1166R also receives steady-state correction constant data transmitted from the disaster prevention receiving panel 12. The steady-state correction constant data received by the transmitter/receiver 1166R overwrites the steady-state correction constant data already stored in the memory unit 1161R.

The timekeeping unit 1167R is implemented by the processor 1011. The timekeeping unit 1167R continuously measures the elapsed time from a reference time, determines the current time, and generates a time signal indicating the determined current time.

The disaster prevention receiving panel 12 (Figure 1), which constitutes the flame detection system 1, is installed inside the tunnel TN. When it receives a flame detection signal from the flame detector 11, it warns people in the vicinity by displaying and sounding an alarm, and sends a notification that a flame has been detected to the server device 13. In addition to the functions of a general disaster prevention receiving panel, the disaster prevention receiving panel 12 also has the function of determining the degree of deterioration of the flame detector 11 based on the night vision noise data output from the flame detector 11.

Figure 9 is a diagram showing a schematic diagram of the hardware configuration of the disaster prevention receiving panel 12. The disaster prevention receiving panel 12 includes a computer 102, and a display 121 and operation unit 122 connected to the computer 102.

The computer 102 includes a processor 1021 that processes data according to a program, a memory 1022 that stores various data including the program, an input/output interface 1023 that inputs and outputs signals between the display 121 and the operation unit 122, and a communication interface 1024 that communicates data between the n flame detectors 11 and the server device 13.

Figure 10 is a diagram showing a schematic diagram of the functional configuration of the disaster prevention receiving panel 12. That is, when the processor 1021 of the computer 102 executes processing according to the program of this embodiment, the disaster prevention receiving panel 12 equipped with a deterioration level determination device indicated by the reference numeral 123 in Figure 10 is realized. The functional configuration of the deterioration level determination device 123 is described below.

The deterioration level determination device 123 includes a memory unit 1231, an acquisition unit 1232, a deterioration level determination unit 1233, a transmission unit 1234, a display control unit 1235, and an operation reception unit 1236.

The storage unit 1231 is realized by the memory 1022, which operates under the control of the processor 1021, and stores various data. For example, night vision noise data transmitted from the flame detector 11 and acquired by the acquisition unit 1232 is stored in the storage unit 1231. Figure 11 is a diagram illustrating the configuration of a table (hereinafter referred to as the "night vision noise table") stored in the storage unit 1231 for storing night vision noise data. The storage unit 1231 stores a night vision noise table corresponding to each of the four sensors for each of the multiple flame detectors 11.

The night vision noise table has the following columns: "Date and Time," "Night Vision Noise Data," "Average Value," "Standard Deviation," and "Data Abnormality." The "Date and Time" column stores, for example, the first date and time of the night vision period indicated by the night vision noise data. The "Night Vision Noise Data" column stores night vision noise data. Note that each piece of night vision noise data is a portion of the data extracted from the measurement value log table (Figure 6), and therefore contains multiple records. The "Average Value" column stores the average value of the values stored in the "Intensity (Temperature Corrected)" column of the night vision noise data. The "Standard Deviation" column stores the standard deviation of the values stored in the "Intensity (Temperature Corrected)" column of the night vision noise data. The "Data Abnormality" column stores data indicating whether the night vision noise data stored in the "Night Vision Noise Data" column is abnormal.

Returning to the explanation of the functional configuration of the disaster prevention receiving panel 12 (Figure 10), the acquisition unit 1232 is implemented by the communication interface 1024, which operates under the control of the processor 1021. The acquisition unit 1232 acquires flame detection signals and night vision noise data from each of the n flame detectors 11. The night vision noise data acquired by the acquisition unit 1162 is stored in a night vision noise table.

The deterioration level determination unit 1233 is implemented by the processor 1021. When new night vision noise data is stored in one of the night vision noise tables, the deterioration level determination unit 1233 calculates the average value and standard deviation of the values stored in the "Intensity (after temperature correction)" column of that night vision noise data and stores them in the corresponding columns of the night vision noise table. In addition, the deterioration level determination unit 1233 determines that any night vision noise data stored in the night vision noise table whose average value or standard deviation deviates from the average value or standard deviation of other night vision noise data before and after it by more than a predetermined threshold value is abnormal data, and stores data indicating the determination result in the "Data abnormality" column.

In addition, the deterioration level determination unit 1233 performs the following determinations and estimates for each of the four sensors of each of the multiple flame detectors 11 based on the data stored in the night vision noise table corresponding to that sensor (excluding data from records in which data indicating abnormality is stored in the "Data Abnormality" column).

(1) If the average intensity value indicated by the most recent night vision noise data is equal to or greater than a predetermined threshold A1, it is determined that a part needs to be replaced. In addition, the amplifier is estimated as the part that needs to be replaced.
(2) If the standard deviation of the intensity indicated by the most recent night vision noise data is equal to or greater than a predetermined threshold B1, it is determined that the part needs to be replaced. In addition, the sensor is estimated as the part that needs to be replaced.
(3) If the day on which the average intensity value indicated by the night vision noise data will reach a predetermined threshold A1, which is estimated based on the change over time of the average intensity value indicated by the night vision noise data for a predetermined period in the past, is within a predetermined number of days from the present, it is determined that the part will need to be replaced in the near future. In addition, the amplifier is estimated as the part that needs to be replaced.
(4) If the day on which the standard deviation of intensity, estimated based on the time-dependent change in the standard deviation of intensity indicated by the night vision noise data over a predetermined period in the past, reaches a predetermined threshold B1, is within a predetermined number of days from the present, it is determined that a part will need to be replaced in the near future. In addition, the sensor is estimated as the part that needs to be replaced.

Figures 12 and 13 are graphs that explain how the deterioration level determination device 123 performs the above-mentioned determinations and estimations. The graphs in Figures 12(a) and 13(a) are curves that approximate points corresponding to the values in the "Date and Time" and "Average Value" columns of the night vision noise table. Note that the solid line portion of the curve shows the progress of the average value up to the present, and the dashed dotted line portion shows the progress of the predicted average value in the future.

The graphs in Figures 12(b) and 13(b) are curves that approximate points corresponding to the values in the "Date and Time" and "Standard Deviation" columns of the night vision noise table. Note that the solid line portion of the curve shows the progress of standard deviation up to the present, while the dashed dotted line portion shows the predicted progress of standard deviation in the future.

The graph in Figure 12(a) shows that at the current date and time d1, the average intensity indicated by the night vision noise data does not reach threshold value A1. Furthermore, the graph in Figure 12(b) shows that at the current date and time d1, the standard deviation of the intensity indicated by the night vision noise data does not reach threshold value B1. Therefore, based on this data, the deterioration level determination unit 1233 determines that the sensor corresponding to this data or the amplifier connected to that sensor does not need to be replaced.

The graph in Figure 12(a) also shows that it is estimated that the average intensity indicated by the night vision noise data will reach threshold value A1 at date and time d2 within a predetermined number of days D1 from the current date and time d1. The graph in Figure 12(b) also shows that it is estimated that the standard deviation of the intensity indicated by the night vision noise data will not reach threshold value B1 within a predetermined number of days D1 from the current date and time d1. Therefore, based on this data, the deterioration level determination unit 1233 determines that the sensor corresponding to this data or the amplifier connected to that sensor will soon need to be replaced, and in this case, it estimates that the part to be replaced is the amplifier.

The graph in Figure 13(a) shows that at the current date and time d1, the average intensity indicated by the night vision noise data has not reached threshold value A1. Furthermore, the graph in Figure 13(b) shows that at the current date and time d1, the standard deviation of the intensity indicated by the night vision noise data has reached threshold value B1. Therefore, based on this data, the deterioration level determination unit 1233 determines that the sensor corresponding to this data or the amplifier connected to that sensor requires replacement, and estimates that the part to be replaced is the sensor.

The deterioration level determination unit 1233 stores data indicating the results of the determinations and estimations performed as described above in the memory unit 1231. Figure 14 is a diagram illustrating the configuration of a table (hereinafter referred to as the "deterioration diagnosis result table") for storing data indicating the results of the determinations and estimations performed by the deterioration level determination unit 1233. The deterioration diagnosis result table has a "Device ID" column, a "Right-side long wavelength" column, a "Right-side short wavelength" column, a "Left-side long wavelength" column, and a "Left-side short wavelength" column. The "Device ID" column stores identification information for the flame detector 11. The "Right-side long wavelength" column, the "Right-side short wavelength" column, the "Left-side long wavelength" column, and the "Left-side short wavelength" column correspond to sensor 111R, sensor 112R, sensor 111L, and sensor 112L, respectively, and stores data for these sensors in any of the following formats (a) to (c), for example:

(a) "Normal": indicates that the part does not need to be replaced at present and will not need to be replaced within a predetermined number of days D1 from now.
(b) "Replacement Required (##)": Indicates that a part currently needs to be replaced, and that it is estimated that the part indicated by "##" (either the sensor or the amplifier, or both) needs to be replaced.
(c) "Replacement required soon (##) (XX month XX day)": indicates that it is estimated that a part will need to be replaced around XX month XX day, and in that case, it is estimated that the part indicated by "##" (either the sensor or the amplifier, or both) will need to be replaced.

Returning to the explanation of the functional configuration of the disaster prevention receiving panel 12 (Figure 10), the transmitting unit 1234 is implemented by the communication interface 1024, which operates under the control of the processor 1021. The transmitting unit 1234 transmits the night vision noise table and the degradation diagnosis result table to the server device 13. In addition, the transmitting unit 1234, for example, periodically transmits data indicating the value in the "average value" column of the most recent record in the night vision noise table (excluding records in which data indicating abnormal data is stored in the "data abnormality" column) to the flame detector 11 as steady-state correction constant data.

The display control unit 1235 is realized by the processor 1021. The display control unit 1235 performs control to display various images on the display 121. For example, when a flame detection signal is received from any of the flame detectors 11, the display control unit 1235 generates image data representing the words "Flame Detection Area ##" and causes the display 121 to display the image represented by that image data. Here, "Area ##" is identification information for the monitoring area A corresponding to the right flame detector or left flame detector of the flame detector 11 that detected the flame.

The operation reception unit 1236 is realized by the input/output interface 1023, which operates under the control of the processor 1021. The operation reception unit 1236 receives operations performed by users, such as maintenance personnel, on the operation unit 122. Note that operations performed by users on the disaster prevention receiving panel 12 using the operation unit 122 include, for example, operations to instruct the start of operation of a fire extinguishing device controlled by the disaster prevention receiving panel 12 when a fire is detected.

The above is a description of the disaster prevention receiving panel 12. The server device 13 (see Figure 1) is a general server device equipped with web server functionality, so a description of its hardware configuration and functional configuration will be omitted.

Terminal device 14 (see Figure 1) is a terminal device used by maintenance personnel. Because terminal device 14 is a general terminal device equipped with web browser functionality, a description of its hardware configuration and functional configuration will be omitted.

The server device 13 receives the night vision noise table and the degradation diagnosis result table from the disaster prevention receiving panel 12 and stores the received data. In addition, in response to a request from the terminal device 14, the server device 13 generates display instruction data (e.g., HTML data) that instructs the display of a screen such as that shown in FIG. 15 (hereinafter referred to as the "degradation diagnosis screen") and transmits it to the terminal device 14. The terminal device 14 displays the degradation diagnosis screen in accordance with the display instruction data transmitted from the server device 13.

The degradation diagnosis screen includes a table that displays information about flame detectors 11 that currently require part replacement, and a table that displays information about flame detectors 11 that are estimated to require part replacement in the near future. Maintenance personnel can easily identify flame detectors 11 that require maintenance work by looking at the degradation diagnosis screen.

Furthermore, when a maintenance technician touches or clicks on any row in the table on the degradation diagnosis screen, the terminal device 14 sends a request to the server device 13 that includes the identification information of the sensor corresponding to that row. In response to the request from the terminal device 14, the server device 13 generates display instruction data instructing the display of a screen (hereinafter referred to as the "graph display screen") that includes a graph related to the sensor identified by the identification information included in the request, and sends this data to the terminal device 14. The graph included in the graph display screen is a graph such as that shown in FIG. 12 or FIG. 13. The terminal device 14 displays the graph display screen in accordance with the display instruction data sent from the server device 13. By looking at the graph display screen, the maintenance technician can confirm the state of deterioration of the flame detector 11, which parts require replacement now or in the near future.

[Modification]
The above-described embodiment is a specific example of the present invention, and various modifications are possible within the scope of the technical concept of the present invention. Examples of such modifications are shown below. Note that two or more of the following modifications may be combined as appropriate.

(1) The shielding period determination unit 1164 of the flame detector 11 included in the flame detection system 1 described above determines the shielding period based on the measurement results of the sensor 111 or the sensor 112. The method by which the shielding period determination unit 1164 determines the shielding period is not limited to this. For example, the flame detector 11 may include a shielding member detection unit that detects that a shielding member that blocks light from traveling toward the sensor from the outside has been attached to the device, and the shielding period determination unit 1164 may determine the shielding period based on the detection results from the shielding member detection unit.

Figure 16 is a diagram showing a schematic diagram of the hardware configuration of the flame detector 21 according to this modified example. In addition to the components of the flame detector 11 (see Figure 2) according to the embodiment described above, the flame detector 21 also includes a sensor 117 (an example of a shielding member detection unit) connected to the computer 101. The sensor 117 is a contact sensor that detects contact of the shielding device S when the shielding device S is pressed against the flame detector 21 and outputs a contact detection signal.

Figure 17 is a diagram showing a schematic diagram of the functional configuration of the flame detector 21. That is, the processor 1011 of the computer 101 included in the flame detector 21 executes processing according to the program of this modified example, thereby realizing the flame detector 21 equipped with a determination device indicated by reference numeral 116 in Figure 17. The acquisition unit 1162 of the determination device 116 included in the flame detector 21 acquires the contact detection signal output from the sensor 117.

When the acquisition unit 1162 acquires contact detection signals continuously for a predetermined period of time (e.g., 25 seconds or more and 35 seconds or less), the shielding period determination unit 1164 of the determination device 116 provided in the flame detector 21 determines the period during which the contact detection signals were acquired as the shielding period, excluding a predetermined period of time immediately after the start (e.g., 3 seconds) and a predetermined period of time immediately before the end (e.g., 3 seconds). In this way, part of the period during which the contact detection signals were acquired is excluded in order to exclude from the shielding period any period during which the window W may not be securely shielded by the shielding device S.

The flame detector 21 also extracts data from the measurement value log table for the shielding period as night vision noise data and outputs it to the disaster prevention receiving panel 12.

The type of sensor 117 provided in the flame detector 21 is not limited to a contact sensor. For example, a magnetic sensor may be used as the sensor 117. In this case, the shielding device S has a magnet positioned opposite the sensor 117 when pressed against the flame detector 21 to shield the window W. When the shielding device S is pressed against the flame detector 21, the sensor 117 detects the magnetic force emitted by the magnet provided in the shielding device S and outputs a contact detection signal.

A proximity sensor (NFC tag reader) that detects electromagnetic waves conforming to a short-range wireless communication standard may also be used as sensor 117. In this case, the shielding device S is equipped with an NFC tag that is positioned facing sensor 117 when pressed against flame detector 21 to shield window W. When the shielding device S is pressed against flame detector 21, sensor 117 detects the electromagnetic waves emitted by the NFC tag equipped on the shielding device S and outputs a contact detection signal.

Furthermore, the flame detector 21 may be equipped with an operator (e.g., a switch for switching ON and OFF) that is operated by a maintenance worker, and the sensor 117 may detect that the operator has been operated by the maintenance worker (e.g., the switch has been switched ON or OFF). In this case, the shielding period determination unit 1164 determines the shielding period based on the timing at which the sensor 117 detects the maintenance worker's operation of the operator.

(2) The flame detector 11 provided in the flame detection system 1 described above is a dual-wavelength flame detector, but the number of wavelength bands used by the flame detector provided in the flame detection system 1 to detect flames may be three or more.

(3) Some of the processing that is to be performed by the disaster prevention receiving panel 12 in the above-described flame detection system 1 may be performed by the flame detector 11, the server device 13, or the terminal device 14. For example, the flame detector 11 may be equipped with a deterioration level determination unit 1233. Furthermore, some of the processing that is to be performed by the flame detector 11 in the above-described flame detection system 1 may be performed by the disaster prevention receiving panel 12, the server device 13, or the terminal device 14.

(4) The flame detector 11 provided in the flame detection system 1 described above monitors the space within the tunnel TN, but the area monitored by the flame detection system 1 is not limited to the tunnel. For example, the flame detector 11 may also monitor spaces within a factory where there is a risk of a flame occurring.

(5) The flame detector 11 provided in the above-described flame detection system 1 includes a right flame detector and a left flame detector, but the flame detector 11 may also be a monocular flame detector that monitors only one area.

(6) In the above-described flame detection system 1, the flame detector 11 transmits night vision noise data to the disaster prevention receiving panel 12 without waiting for a request from the disaster prevention receiving panel 12. However, the flame detector 11 may transmit night vision noise data to the disaster prevention receiving panel 12 in response to a request from the disaster prevention receiving panel 12.

(7) In the flame detection system 1 described above, the method for determining the degree of deterioration of the flame detector 11 described using the graphs in Figures 12 and 13 is one example, and various other methods may be used. For example, instead of standard deviation, variance, coefficient of variation, or the difference between the maximum and minimum amplitude values may be used as an indicator of the variation in amplitude values contained in the night vision noise data. Furthermore, the degree of deterioration may be determined and the parts to be replaced may be estimated based on the shape of the graphs such as those shown in Figures 12 and 13. For example, a learning model may be generated by machine learning using a large amount of training data in which the type of part replaced in past maintenance work and the degree of deterioration of that part are used as the objective variables, and night vision noise data corresponding to that part immediately before replacement is used as the explanatory variable. Night vision noise data output from a flame detector 11 in operation may be input into the learning model, and the learning model may output the type of part to be replaced and the degree of deterioration of that part.

(8) In the flame detection system 1 described above, the degree of deterioration determined by the deterioration degree determination unit 1233 is one of three levels: (a) part replacement is currently required, (b) part replacement will be required in the near future, and (c) normal. The deterioration degree determination unit 1233 may determine the degree of deterioration in a different format. For example, the ratio of the average value of the amplitude values included in the night vision noise data to threshold value A1, or the ratio of the standard deviation of the amplitude values included in the night vision noise data to threshold value B1 may be used as the degree of deterioration of the flame detector 11.

(9) In the flame detection system 1 described above, the components of the flame detector 11 that may deteriorate are the sensor and amplifier, but components that may deteriorate are not limited to these. For example, deterioration of wiring, contacts, etc. may also be suspected.

1...Flame detection system, 11...Flame detector, 12...Disaster prevention receiving panel, 13...Server device, 14...Terminal device, 21...Flame detector, 101...Computer, 102...Computer, 111...Sensor, 112...Sensor, 113...Amplifier, 114...Amplifier, 115...Thermometer, 116...Determination device, 117...Sensor, 121...Display, 122...Operation unit, 123...Deterioration degree determination device, 1011...Processor, 1012...Memory, 1013...Input/output interface base, 1014...communication interface, 1021...processor, 1022...memory, 1023...input/output interface, 1024...communication interface, 1161...storage unit, 1162...acquisition unit, 1163...correction unit, 1164...shielding period determination unit, 1165...flame detection unit, 1166...transmission/reception unit, 1167...timekeeping unit, 1231...storage unit, 1232...acquisition unit, 1233...deterioration level determination unit, 1234...transmission unit, 1235...display control unit, 1236...operation reception unit.

Claims (6)

an acquisition unit that acquires night vision noise data indicating the intensity of light measured by a flame detector that detects a flame based on the intensity of light measured by a sensor during a period when light from the outside toward the sensor is blocked;
a storage unit that stores the night vision noise data acquired by the acquisition unit;
a deterioration level determination unit that calculates an average value of the light intensity indicated by the night vision noise data stored in the memory unit and an index indicating the variation in the light intensity indicated by the night vision noise data stored in the memory unit, and estimates a first type of part among the parts equipped in the flame detector as a part that needs to be replaced if the average value satisfies a predetermined condition, and estimates a second type of part, different from the first type of part, among the parts equipped in the flame detector as a part that needs to be replaced if the index indicating the variation satisfies a predetermined condition. the flame detector includes an amplifier that amplifies a signal indicative of the intensity of light measured by the sensor;
2. The deterioration level determination device according to claim 1, wherein the deterioration level determination unit estimates the amplifier as a part that needs to be replaced if an average value of the noise intensity indicated by the data stored in the memory unit satisfies a predetermined condition, and estimates the sensor as a part that needs to be replaced if an index indicating the variation in noise intensity indicated by the data stored in the memory unit satisfies a predetermined condition. an acquisition unit that acquires night vision noise data indicating the intensity of light measured by a flame detector that detects a flame based on the intensity of light measured by a sensor during a period when light from the outside toward the sensor is blocked;
a deterioration level determination unit that inputs the night vision noise data acquired by the acquisition unit into a learning model generated by machine learning using training data in which the type of part replaced in past maintenance work for a flame detector of the same type as the flame detector and the deterioration level of the part are used as objective variables, and night vision noise data before the part was replaced is used as an explanatory variable, and outputs from the learning model the type of part that should be replaced among the parts equipped on the flame detector and the deterioration level of the part. On the computer,
A process of acquiring night vision noise data indicating the intensity of light measured by a flame detector that detects a flame based on the intensity of light measured by a sensor during a period when light from the outside world toward the sensor is blocked;
A process of storing the acquired night vision noise data;
A program for executing a process of calculating an average value of the light intensity indicated by the stored night vision noise data and an index indicating the variation in the light intensity indicated by the stored night vision noise data, and estimating a first type of part among the parts equipped in the flame detector as a part that needs to be replaced if the average value satisfies a predetermined condition, and estimating a second type of part among the parts equipped in the flame detector that is different from the first type of part as a part that needs to be replaced if the index indicating the variation satisfies a predetermined condition. On the computer,
A process of acquiring night vision noise data indicating the intensity of light measured by a flame detector that detects a flame based on the intensity of light measured by a sensor during a period when light from the outside world toward the sensor is blocked;
A program for inputting the night vision noise data acquired in the acquisition process into a learning model generated by machine learning using training data in which the type of part replaced in past maintenance work for a flame detector of the same type as the flame detector and the degree of deterioration of the part are used as objective variables, and the night vision noise data before the part was replaced is used as an explanatory variable, and outputting from the learning model the type of part that needs to be replaced among the parts equipped on the flame detector and the degree of deterioration of the part. A flame detector;
a deterioration level determination device according to any one of claims 1 to 3;
The flame detector comprises:
a sensor for measuring light intensity;
a flame detection unit that detects a flame based on the intensity of light measured by the sensor;
a shielding member detection unit that detects that a shielding member that blocks light from the outside toward the sensor has been attached to the device;
a blocking period determination unit that determines a period during which light traveling from the outside to the sensor is blocked based on a detection result by the blocking member detection unit;
an output unit that outputs night vision noise data indicating the intensity of light measured by the sensor during the period specified by the occlusion period specifying unit;
the shielding member detection unit includes one of a contact sensor that detects contact with the shielding member, a magnetic sensor that detects a magnetic force emitted by the shielding member, and a proximity sensor that detects electromagnetic waves that comply with a short-range wireless communication standard emitted by the shielding member;
The acquisition unit of the deterioration level determination device acquires night vision noise data output by the output unit of the flame detector.