Abnormality diagnosis device, abnormality diagnosis method, and storage medium

Abstract

The purpose of the present invention is to enable an analyst to identify a combination of sensors showing the cause of an abnormality occurring in a monitored object with less labor and in a short time. When an abnormality is detected, a combination of two sensors is selected, and the combination includes, as one sensor, a sensor corresponding to an SN ratio from the uppermost position to a predetermined first predetermined order when the SN ratios are arranged in the order from large to small, and a sensor corresponding to the SN ratio from the uppermost position to the predetermined first predetermined order from the uppermost position. A sensor that includes sensors other than the one sensor and that satisfies a predetermined selection condition is used as the other sensor. An index indicating the state quantity of one sensor included in each combination is selected as a first index, and an index indicating the state quantity of the other sensor included in each combination is selected as a second index. The scale of the first index, the scale of the second index, and the position of each of the state quantities specified by the scales of the first index and the second index are displayed on a display screen.

Description

Technical Field

[0001] The present disclosure relates to an abnormality diagnosis device, an abnormality diagnosis method and a storage medium. Background Art

[0002] As a remote monitoring method for mechanical equipment such as gas turbines, for example, the Mahalanobis-Taguchi method (hereinafter referred to as the MT (Mahalanobis-Taguchi) method) is used. In the MT method, when the mechanical equipment as the monitored object is operating in a normal state, multiple state quantities detected by various sensors installed on the monitored object are obtained, and the obtained multiple state quantities are used as a reference. Thereafter, the state quantities detected by various sensors are successively obtained as time passes, and the signal space is determined using the obtained state quantities. Whenever the signal space is obtained, the difference between the signal space and the unit space determined using the state quantity used as the reference is calculated as the Mahalanobis distance. When the calculated Mahalanobis distance exceeds a predetermined threshold, for example, it is determined that an abnormality has occurred in the monitored object.

[0003] In the MT method, the SN (Signal-to-Noise) ratio is further calculated as an index indicating the influence of each state quantity, that is, each sensor, on the Mahalanobis distance. By using this SN ratio, it is possible to determine which state quantity detected by which sensor has an abnormality, in other words, it is possible to determine which part of the monitoring object that is the detection object of each sensor has an abnormality (for example, refer to Patent Documents 1 and 2).

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2011-238148

[0007] Patent Document 2: Japanese Patent Application Publication No. 2021-140540 Summary of the invention

[0008] Problem that the invention aims to solve

[0009] The state quantity detected by the sensor with the largest SN ratio is one of the factors that increase the Mahalanobis distance. However, the abnormality that occurs in the monitored object occurs due to various factors. For example, sometimes there is no cause of abnormality in the part of the detection object of the sensor with the largest SN ratio, and the change of the state of the part that becomes the cause of the abnormality causes the state quantity of the part of the detection object of the sensor with the largest SN ratio to change.

[0010] In this case, the analyst who analyzes the abnormality needs to refer to the relationship between the state quantities of multiple sensors while performing the analysis operation to determine the cause of the abnormality. However, since the number of sensors installed in the monitored object is very large, the number of sensor combinations is huge. Therefore, there is a problem that in the analysis operation to determine the cause of the abnormality, it takes a lot of labor and time for the analyst to determine which sensor combination to refer to.

[0011] The present invention is completed to solve the above-mentioned problems, and its purpose is to provide an abnormality diagnosis device, an abnormality diagnosis method and a storage medium that enable an analyst to determine the combination of sensors that indicate the cause of an abnormality occurring in a monitored object with less labor and in a shorter time.

[0012] Technical Solution

[0013] In order to solve the above-mentioned problem, the abnormality diagnosis device of the present disclosure includes: an abnormality detection unit that applies the Mahalanobis-Taguchi method to a state quantity detected by each of a plurality of sensors provided to a monitoring object to perform abnormality detection and calculate an SN ratio corresponding to each of the sensors; a sensor selection unit that selects a combination of two sensors selected from the plurality of sensors when the abnormality detection unit detects an abnormality, the combination including as one sensor a sensor corresponding to an SN ratio that is counted from the highest to a predetermined first predetermined rank when the SN ratios are arranged in descending order, and including as the other sensor a sensor other than the one sensor and that satisfies a predetermined predetermined selection condition; and a display processing unit that selects as a first index an index representing the state quantity of one sensor included in each of the combinations of the two sensors selected by the sensor selection unit, and selects as a second index an index representing the state quantity of the other sensor, and displays on a display screen a scale of the first index, a scale of the second index, and a position of each of the state quantities determined by the scales of the first index and the second index for each selected combination of the first index and the second index.

[0014] The abnormality diagnosis method disclosed in the present invention includes: an abnormality detection step of applying the Mahalanobis-Taguchi method to a state quantity detected by each of a plurality of sensors provided in a monitoring object to perform abnormality detection, and calculating an SN ratio corresponding to each of the sensors; a sensor selection step of selecting, when an abnormality is detected in the abnormality detection step, a combination of two sensors selected from the plurality of sensors, the combination including, as one sensor, a sensor corresponding to an SN ratio counted from the highest to a predetermined first predetermined rank when the SN ratios are arranged in descending order, and including, as the other sensor, a sensor other than the one sensor and satisfying a predetermined predetermined selection condition; and a display processing step of selecting, as a first index, an index representing the state quantity of one sensor included in each of the combinations of the two sensors selected in the sensor selection step, and selecting, as a second index, an index representing the state quantity of the other sensor, and displaying, on a display screen, for each selected combination of the first index and the second index, a scale of the first index, a scale of the second index, and a position of each of the state quantities determined by the scales of the first index and the second index.

[0015] A storage medium of the present disclosure stores a program that causes a computer to function as the following units: an abnormality detection unit that applies the Mahalanobis-Taguchi method to a state quantity detected by each of a plurality of sensors provided to a monitoring object, and performs abnormality detection, and calculates an SN ratio corresponding to each of the sensors; a sensor selection unit that selects a combination of two sensors selected from the plurality of sensors when the abnormality detection unit detects an abnormality, the combination including as one sensor a sensor corresponding to an SN ratio that is counted from the highest to a predetermined first predetermined rank when the SN ratios are arranged in descending order, and including as the other sensor a sensor other than the one sensor and that satisfies a predetermined predetermined selection condition; and a display processing unit that selects as a first index an index representing the state quantity of one sensor included in each of the combinations of the two sensors selected by the sensor selection unit, and selects as a second index an index representing the state quantity of the other sensor, and displays, on a display screen, for each selected combination of the first and second indicators, a scale of the first indicator, a scale of the second indicator, and a position of each of the state quantities determined by the scales of the first and second indicators.

[0016] Effects of the Invention

[0017] According to the abnormality diagnosis device, the abnormality diagnosis method, and the storage medium of the present disclosure, an analyst can determine a combination of sensors that indicates the cause of an abnormality occurring in a monitoring object with less labor and in a shorter time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a block diagram showing the configuration of an abnormality diagnosis device according to an embodiment of the present disclosure, a machine device to be monitored by the abnormality diagnosis device, and a sensor and a display device connected to the abnormality diagnosis device.

[0019] Figure 2 It is a diagram showing the data format of a table stored in the state quantity storage unit of the abnormality diagnosis device according to the embodiment of the present disclosure.

[0020] Figure 3 It is a diagram showing the data format of a table stored in the SN ratio storage unit of the abnormality diagnosis device according to the embodiment of the present disclosure.

[0021] Figure 4 : is a flowchart showing the flow of processing performed by the abnormality diagnosis device according to the embodiment of the present disclosure.

[0022] Figure 5 It is a diagram showing an example of a graph displayed on a display screen of a display device connected to the abnormality diagnosis device of the present disclosure.

[0023] Figure 6 This is a schematic block diagram showing the configuration of a computer according to at least one embodiment.

[0024] Description of Reference Numerals

[0025] 1: Abnormal diagnosis device;

[0026] 2: Display device;

[0027] 11: state quantity collection unit;

[0028] 12: state quantity storage unit;

[0029] 13: Abnormal detection unit;

[0030] 14: SN ratio storage unit;

[0031] 15: sensor selection unit;

[0032] 15-1: sensor combination generation unit;

[0033] 15-2: 2D MD calculation unit;

[0034] 16: display processing unit;

[0035] 20-1~20-N: sensor;

[0036] 30: Mechanical equipment. DETAILED DESCRIPTION

[0037] Below, refer to Figure 1 to Figure 5 An abnormality diagnosis device, an abnormality diagnosis method, and a program according to an embodiment of the present disclosure will be described. Figure 1 This is a block diagram showing the configuration of the abnormality diagnosis device 1 according to the embodiment of the present disclosure, the machinery 30 to be monitored by the abnormality diagnosis device 1 , and the sensors 20 - 1 to 20 -N and the display device 2 connected to the abnormality diagnosis device 1 . Figure 2 , Figure 3 Each of the diagrams shows the data format of the table stored in the state quantity storage unit 12 and the SN ratio storage unit 14 of the abnormality diagnosis device 1 according to the embodiment of the present disclosure. Figure 4 : is a flowchart showing the flow of processing performed by the abnormality diagnosis device 1 according to the embodiment of the present disclosure. Figure 5 The diagram shows an example of a graph displayed on the display screen of the display device 2 connected to the abnormality diagnosis device 1 of the present disclosure. In the drawings, the same or corresponding components are denoted by the same reference numerals, and description thereof is appropriately omitted.

[0038] (Configuration Example of Abnormality Diagnosis Device)

[0039] like Figure 1 As shown, the abnormality diagnosis device 1 is connected to the display device 2 and sensors 20-1 to 20-N, and the sensors 20-1 to 20-N monitor the state of the mechanical equipment 30 as the monitoring object of the abnormality diagnosis device 1. The mechanical equipment 30 is, for example, a gas turbine, etc. The display device 2 is, for example, a liquid crystal display having a display screen.

[0040] Sensors 20.1 to 20-N are various sensors such as temperature sensors, pressure sensors, and voltage sensors, and are provided at locations that need to be monitored in the mechanical equipment 30. N is an integer greater than or equal to 2. Each of the sensors 20-1 to 20-N has a timing unit such as a clock inside, and detects the state of the monitored location in the mechanical equipment 30 where each of the sensors 20-1 to 20-N is provided at a certain time interval, and obtains the time when the detection is performed (hereinafter referred to as the detection time) from the timing unit. Each of the sensors 20-1 to 20-N outputs state data, and the state data includes a state quantity indicating the amount of the detected state, information indicating the detection time of the state quantity, and sensor identification information of each of the sensors 20-1 to 20-N. The sensor identification information is information pre-assigned to each of the sensors 20-1 to 20-N in a manner that allows each of the sensors 20-1 to 20-N to be identified. Here, the state quantity detected by the sensors 20-1 to 20-N is, for example, a temperature value in the case of a temperature sensor, a pressure value in the case of a pressure sensor, and a voltage value in the case of a voltage sensor. The information indicating the time obtained from the timing unit provided inside each of the sensors 20-1 to 20-N is, for example, information expressed in the form of year, month, day, hour, minute, and second.

[0041] The abnormality diagnosis device 1 includes a state quantity collecting unit 11 , a state quantity storing unit 12 , an abnormality detecting unit 13 , an SN ratio storing unit 14 , a sensor selecting unit 15 , and a display processing unit 16 .

[0042] The state quantity collection unit 11 is connected to the sensors 20-1 to 20-N via an electrical line or a communication line, for example, and takes in the state data output by each of the sensors 20-1 to 20-N. The state quantity collection unit 11 corrects the deviation of the detection time of each of the taken-in state data, and associates the detection time with the state data in such a way that there are N state data at one detection time. The state quantity collection unit 11 records the N state quantities included in the N state data, the sensor identification information corresponding to each of the N state quantities, and the information indicating a detection time corresponding to the N state quantities as one record in the state quantity storage unit 12.

[0043] like Figure 2As shown, the state quantity storage unit 12 stores a table in the data format having items such as "detection time", each of N "sensor identification information", and "type". In the item of "detection time", the information indicating the detection time is recorded by the state quantity collection unit 11. In each of the N items of "sensor identification information", the state quantity corresponding to the sensor identification information of each item is recorded by the state quantity collection unit 11. In the item of "type", any one of "unit space", "signal space" and "abnormality" is recorded. It should be noted that when the state quantity collection unit 11 records the record in the state quantity storage unit 12, it records "signal space" in the item of "type".

[0044] The user of the abnormality diagnosis device 1, that is, the analyst who analyzes the abnormality, operates the operation unit (not shown) provided in the abnormality diagnosis device 1, selects several records during the normal operation of the mechanical device 30 from the records in the state quantity storage unit 12, and rewrites the "type" item of the selected records from "signal space" to "unit space". It should be noted that the following state is ideal: the rewriting from "signal space" to "unit space" is performed regularly by the analyst, for example, and the continuous records during the recent 2 to 3 months of normal operation of the mechanical device 30 are rewritten from "signal space" to "unit space" and recorded in the state quantity storage unit 12.

[0045] The abnormality detection unit 13 specifies the unit space using the state quantity of the record whose “type” item is “unit space” in the record recorded in the state quantity storage unit 12. The abnormality detection unit 13 continues to monitor the process of recording a new record in the state quantity storage unit 12 by the state quantity collection unit 11, and when a new record is recorded in the state quantity storage unit 12, the abnormality detection unit 13 specifies the signal space using the state quantity of the recorded new record.

[0046] The abnormality detection unit 13 applies the MT method to the state quantity of the signal space and the state quantity of the unit space, and calculates the Mahalanobis distance of the signal space. When the calculated Mahalanobis distance exceeds a predetermined threshold, the abnormality detection unit 13 determines that an abnormality has occurred in the mechanical device 30. When the abnormality detection unit 13 determines that an abnormality has occurred in the mechanical device 30, the item of "type" recorded corresponding to the signal space at the time of determination is rewritten from "signal space" to "abnormality".

[0047] The abnormality detection unit 13 calculates the SN ratio, which is an index indicating the influence of each sensor 20-1 to 20-N on the Mahalanobis distance, based on each of the state quantities recorded in the state quantity storage unit 12 of the determination object when it is determined that an abnormality has occurred and the state quantity of the unit space. The abnormality detection unit 13 records the information indicating the detection time recorded in the state quantity storage unit 12 of the determination object when it is determined that an abnormality has occurred and the calculated SN ratio of each sensor 20-1 to 20-N in the SN ratio storage unit 14. When the recording to the SN ratio storage unit 14 is completed, the abnormality detection unit 13 outputs an abnormality occurrence notification signal including the information indicating the detection time recorded in the SN ratio storage unit 14.

[0048] like Figure 3 As shown in FIG. 1 , the SN ratio storage unit 14 stores a table in a data format having items such as “detection time” and each of N “sensor identification information”. In the item of “detection time”, information indicating the detection time is recorded by the abnormality detection unit 13. In each of the items of N “sensor identification information”, the SN ratio corresponding to the sensor identification information of each item is recorded by the abnormality detection unit 13.

[0049] The sensor selection unit 15 selects a combination of two sensors from a plurality of sensors 20-1 to 20-N. The sensor selection unit 15 includes a sensor combination generation unit 15-1 and a two-dimensional MD (Mahalanobis-Distance) calculation unit 15-2. When the sensor combination generation unit 15-1 receives the abnormality occurrence notification signal output by the abnormality detection unit 13, it detects a record corresponding to the information indicating the detection time included in the received abnormality occurrence notification signal from the SN ratio storage unit 14. The sensor combination generation unit 15-1 arranges the sensor identification information in descending order of the N SN ratios included in the detected record. The sensor combination generation unit 15-1 selects the sensor identification information from the highest rank to the predetermined rank (hereinafter referred to as the first predetermined rank).

[0050] The sensor combination generation unit 15-1 generates combination data, which includes the selected sensor identification information as the sensor identification information of one party, and includes sensor identification information other than the sensor identification information of the one party and sensor identification information corresponding to the sensors 20-1~20-N that meet the predetermined specified selection conditions as the sensor identification information of the other party.

[0051] The two-dimensional MD calculation unit 15-2 reads out the state quantities corresponding to the two sensor identification information included in the combination data generated by the sensor combination generation unit 15-1 from the state quantity storage unit 12, and uses the read state quantities to determine the unit space and the signal space. The two-dimensional MD calculation unit 15-2 calculates the two-dimensional Mahalanobis distance of the signal space based on the determined unit space and signal space.

[0052] When calculating the two-dimensional Mahalanobis distance corresponding to each of the combination data generated by the sensor combination generating unit 15-1, the two-dimensional MD calculating unit 15-2 arranges the combination data in descending order of the two-dimensional Mahalanobis distance. The two-dimensional MD calculating unit 15-2 selects the combination data from the highest position to the predetermined position (hereinafter referred to as the second predetermined position).

[0053] The display processing unit 16 is connected to the display device 2 via an electrical line, for example. The display processing unit 16 reads out the state quantity corresponding to each of the two sensor identification information included in the combination data selected by the two-dimensional MD calculation unit 15-2 from the state quantity storage unit 12. The display processing unit 16 selects the index representing the state quantity of one sensor of the two sensor identification information included in the combination data selected by the two-dimensional MD calculation unit 15-2 as the first index, and selects the index representing the state quantity of the other sensor as the second index. The display processing unit 16 generates the image data of a chart according to each combination of the selected first index and the second index, and the chart is a chart represented by the scale of the first index and the scale of the second index, and is a chart in which the position of each read state quantity is represented by the scale of the first index and the second index. When generating the image data of the chart, the display processing unit 16 generates the image data of the chart in a manner that shows the position of the state quantity in different forms according to the type of each read state quantity, that is, the type of "unit space", "signal space", and "abnormality". The display processing unit 16 outputs the image data of the generated chart to the display device 2. The display device 2 uses the image data of the chart output by the display processing unit 16 to display the image of the chart on the display screen.

[0054] (Processing by abnormality diagnosis device)

[0055] Figure 4 The flowchart shows the processing flow performed by the sensor selection unit 15 and the display processing unit 16 after the abnormality detection unit 13 outputs the abnormality occurrence notification signal in the abnormality diagnosis device 1. It should be noted that, below, the processing of the case where the above-mentioned predetermined selection condition is set to the condition that all sensors 20-1 to 20-N except the sensor 20-1 to 20-N corresponding to the sensor identification information of one party, the above-mentioned first predetermined rank is the highest rank, and the above-mentioned second predetermined rank is the third rank is described.

[0056] The sensor combination generation unit 15-1 takes in and acquires the abnormality occurrence notification signal output by the abnormality detection unit 13 (S1). The sensor combination generation unit 15-1 reads out the record corresponding to the information indicating the detection time included in the acquired abnormality occurrence notification signal from the SN ratio storage unit 14. The sensor combination generation unit 15-1 arranges the sensor identification information in descending order of the N SN ratios included in the read record. The sensor combination generation unit 15-1 selects the sensor identification information at the top of the order, that is, the sensor identification information with the largest SN ratio (S2).

[0057] The sensor combination generation unit 15-1 sets the selected sensor identification information with the largest SN ratio as the main sensor identification information (hereinafter referred to as the main sensor identification information) when generating the combination. The sensor combination generation unit 15-1 generates N-1 combination data according to the specified selection conditions, and the N-1 combination data includes the main sensor identification information as one of the sensor identification information and includes each of all the sensor identification information other than the main sensor identification information as the other sensor identification information. It should be noted that when generating the combination data, the sensor combination generation unit 15-1 assigns an identification tag indicating that it is the main sensor identification information to the main sensor identification information, and generates the combination data.

[0058] The sensor combination generating unit 15-1 associates each of the N-1 combination data generated with the information indicating the detection time of the item "detection time" recorded and read from the SN ratio storage unit 14 when generating the N-1 combination data. The sensor combination generating unit 15-1 outputs the N-1 combination data associated with the information indicating the detection time to the two-dimensional MD calculating unit 15-2 (S3).

[0059] The two-dimensional MD calculation unit 15-2 takes in N-1 pieces of combination data each associated with information indicating the detection time output by the sensor combination generation unit 15-1. The two-dimensional MD calculation unit 15-2 selects any one piece of combination data from the taken-in N-1 pieces of combination data.

[0060] The two-dimensional MD calculation unit 15-2 reads out the state quantities corresponding to the two sensor identification information included in the selected combination data, that is, all the state quantities whose "type" item is "unit space" from the state quantity storage unit 12. The two-dimensional MD calculation unit 15-2 uses the read state quantities whose "type" item is "unit space" to determine the unit space corresponding to the selected combination data.

[0061] The two-dimensional MD calculation unit 15-2 detects a record corresponding to the information indicating the detection time associated with the selected combination data from the state quantity storage unit 12. The two-dimensional MD calculation unit 15-2 reads out two state quantities corresponding to each of the two sensor identification information included in the selected combination data from the detected record. The two-dimensional MD calculation unit 15-2 uses the two read state quantities to determine the signal space corresponding to the selected combination data. The two-dimensional MD calculation unit 15-2 calculates the two-dimensional Mahalanobis distance of the signal space using the signal space and the unit space determined corresponding to the selected combination data. The two-dimensional MD calculation unit 15-2 further associates the calculated two-dimensional Mahalanobis distance with the selected combination data. The two-dimensional MD calculation unit 15-2 records the combination data in which the information indicating the detection time is associated with the two-dimensional Mahalanobis distance in the internal storage area (S4).

[0062] The two-dimensional MD calculation unit 15-2 selects any combination of data that is not to be processed in S4, and repeatedly performs S4 processing on the selected combination of data until there is no combination of data to be processed in S4 (loops L1s to L1e). Figure 4 The processing of the flowchart is the processing performed by the abnormality detection unit 13 each time the abnormality occurrence notification signal is output. Therefore, in the processing of S4 for the first time in the processing of the loop L1s to L1e, the two-dimensional MD calculation unit 15-2 initializes the internal storage area before recording the combination data associated with the information indicating the detection time and the two-dimensional Mahalanobis distance in the internal storage area. As a result, the combination data at the time of the last abnormality occurrence notification signal is erased.

[0063] The two-dimensional MD calculation unit 15-2 reads out N-1 combination data of the two-dimensional Mahalanobis distance and the information indicating the detection time from the internal storage area. The two-dimensional MD calculation unit 15-2 arranges the read N-1 combination data of the two-dimensional Mahalanobis distance and the information indicating the detection time in the order of the two-dimensional Mahalanobis distance from large to small. The two-dimensional MD calculation unit 15-2 selects three combination data from the highest to the third. The two-dimensional MD calculation unit 15-2 further associates the information indicating the rank with the selected three combination data, i.e., the combination data associated with the information indicating the detection time, and outputs it to the display processing unit 16 (S5).

[0064] The display processing unit 16 takes in the three combination data output by the two-dimensional MD calculation unit 15-2, that is, the combination data in which the information indicating the rank is associated with the information indicating the detection time. The display processing unit 16 processes the image data of the generated chart, for example, from each of the combination data according to the rank according to the process shown below. That is, the display processing unit 16 initially selects the combination data of the first position, and reads out the sensor identification information that is assigned an identification tag indicating that it is the main sensor identification information and the sensor identification information that is not assigned an identification tag, which are included in the selected combination data. Here, the sensor corresponding to the sensor identification information assigned an identification tag is set to be sensor 20-A (where A is an integer greater than 1 and less than N), and the sensor corresponding to the sensor identification information that is not assigned an identification tag is set to be sensor 20-P (where P is an integer greater than 1 and less than N and is an integer different from A).

[0065] The display processing unit 16 sets the index representing the state quantity of the sensor 20-A as the first index, and sets the index representing the state quantity of the sensor 20-P as the second index. The display processing unit 16 reads the state quantity corresponding to each of the sensor identification information of the sensors 20-A and 20-P from the state quantity storage unit 12, and the state quantity whose "type" item is "unit space" is assigned a label representing "unit space" to the read state quantity.

[0066] The display processing unit 16 reads out from the state quantity storage unit 12 the state quantity corresponding to each of the sensor identification information of the sensors 20-A and 20-P, and the state quantity whose year, month and day of the detection time of the item "detection time" is consistent with the year, month and day indicated by the information indicating the detection time associated with the first combination data, and the state quantity whose item "type" is "signal space" or "abnormal". In other words, the display processing unit 16 reads out from the state quantity storage unit 12 the state quantity corresponding to each of the sensor identification information of the sensors 20-A and 20-P, and the state quantity of "signal space" or "abnormal" detected on the same date as the date on which the abnormality occurred.

[0067] When the display processing unit 16 reads the state quantity of "signal space" or "abnormality" detected on the date when the abnormality occurred corresponding to each of the sensor identification information of the sensors 20-A and 20-P from the state quantity storage unit 12, it also reads the information of the item of "type" corresponding to the read state quantity, that is, the information of "signal space" or "abnormality". The display processing unit 16 gives the information of the item of "type" read corresponding to the state quantity to the read state quantity.

[0068] Thus, the display processing unit 16 obtains a state quantity corresponding to the first-digit combination data and each of the sensor identification information of the sensors 20-A and 20-P, and assigns a state quantity of any one of the information of "unit space", "signal space" and "abnormality" to each of the state quantities.

[0069] The display processing unit 16 sets the indicator representing the state quantity of the sensor 20-A as the first indicator, and sets the indicator representing the state quantity of the sensor 20-P as the second indicator. The display processing unit 16 sets the scale of the first indicator as the vertical axis, and the scale of the second indicator as the horizontal axis, and generates image data of a chart that is a scatter diagram representing the position of each state quantity determined by the scales of the first indicator and the second indicator and the type of each state quantity. The display processing unit 16 displays the position and type of the state quantity, and thus, for example, generates image data of the chart in a manner such that a circular mark is displayed at the position of the state quantity assigned to the "unit space", a diamond mark is displayed at the position of the state quantity assigned to the "signal space", and a star mark is displayed at the position of the state quantity assigned to the "abnormal". The display processing unit 16 outputs the image data of the generated chart to the display device 2. The display device 2 takes in the image data of the chart output by the display processing unit 16, and uses the taken-in image data of the chart to display the image of the chart on the display screen (S6). Thus, for example, Figure 5 The graph shown in (a) is displayed on the display screen of the display device 2.

[0070] Next, the display processing unit 16 selects the second-digit combination data and performs processing of S6. The sensor corresponding to the main sensor identification information included in the second-digit combination data becomes sensor 20-A. Here, the other sensor included in the second-digit combination data is set to sensor 20-Q (where Q is an integer greater than 1 and less than N and is an integer different from A and P). In this case, the display processing unit 16 generates image data of a chart of a scatter diagram with the first indicator corresponding to sensor 20-A as the vertical axis and the second indicator corresponding to sensor 20-Q as the horizontal axis by processing S6 for the second-digit combination data. As a result, for example, a display screen of the display device 2 displays Figure 5 The graph shown in (b) .

[0071] Finally, the display processing unit 16 selects the third-digit combination data and performs processing of S6. The sensor corresponding to the main sensor identification information included in the third-digit combination data becomes sensor 20-A. Here, the other sensor included in the third-digit combination data is set to sensor 20-R (where R is an integer greater than 1 and less than N and is an integer different from A, P, and Q). In this case, the display processing unit 16 generates image data of a chart of a scatter diagram with the first indicator corresponding to sensor 20-A as the vertical axis and the second indicator corresponding to sensor 20-R as the horizontal axis by processing S6 for the third-digit combination data. As a result, for example, a scatter diagram is displayed on the display screen of the display device 2. Figure 5 The diagram shown in (c) (cycle L2s to L2e). By the end of the processing of the cycle L2s to L2e, Figure 4 The processing of the shown flowchart ends.

[0072] (Function / Effect of Abnormality Diagnosis Device)

[0073] exist Figure 4 When the processing is finished, the display screen of the display device 2 displays Figure 5 The three graphs (a), (b), and (c) are shown in Figure 1. Figure 5 The graph shown in (a) is a graph showing the relationship between the state quantity of the sensor 20-P having the largest two-dimensional Mahalanobis distance with the state quantity of the sensor 20-A and the state quantity of the sensor 20-A. Figure 5 The graph shown in (b) is a graph showing the relationship between the state quantity of the sensor 20-Q having the second largest two-dimensional Mahalanobis distance with the state quantity of the sensor 20-A and the state quantity of the sensor 20-A. Figure 5 The graph shown in (c) is a graph showing the relationship between the state quantity of sensor 20-R having the third largest two-dimensional Mahalanobis distance with the state quantity of sensor 20-A and the state quantity of sensor 20-A. Figure 5 In the graphs (a), (b), and (c), there are five star-shaped marks indicating the types of "abnormality", and therefore, these are the graphs displayed on the display screen of the display device 2 when the abnormality detection unit 13 outputs the abnormality occurrence notification signal for the fifth time. The analyst refers to these three graphs and analyzes how much the state quantity indicating the abnormality has left the unit space, and thereby the analyst can determine the location of the abnormality in the mechanical equipment 30.

[0074] The number of combinations of two sensors 20-1 and 20-N selected from the N sensors 20-1 to 20-N is NC2, that is, N×(N-1) / 2. The larger the number of N, the larger the number of combinations. In response to this, the sensor selection unit 15 of the abnormality diagnosis device 1 narrows down the combinations set as display objects from the N×(N-1) / 2 combinations based on the two indicators of the size of the SN ratio and the size of the two-dimensional Mahalanobis distance. The two indicators of the size of the SN ratio and the two-dimensional Mahalanobis distance can be called indicators indicating the degree of relevance to the abnormality. Therefore, the combinations narrowed down by the sensor selection unit 15 are combinations with high relevance to the abnormality, and the graph displayed on the display screen of the display device 2 becomes a graph indicating the relationship between the combinations with high relevance to the abnormality. In other words, by narrowing down the combinations based on the two indicators of the size of the SN ratio and the size of the two-dimensional Mahalanobis distance, it is possible to increase the possibility that the graph displayed on the display screen of the display device 2 includes a graph indicating the characteristics of the state quantities of the sensors 20-1 to 20-N indicating the cause of the abnormality that has occurred. Therefore, by using the abnormality diagnosis device 1 , the analyst can determine the combination of sensors that indicates the cause of the abnormality occurring in the machine equipment 30 that is the monitoring target, with less labor and in a shorter time.

[0075] <Other Configuration Examples of Embodiments>

[0076] (Other examples of structures for prescribing the order of rank)

[0077] As Figure 4 The first predetermined rank and the second predetermined rank are examples of the premise of the processing, and the first predetermined rank and the second predetermined rank may be set to any rank. For example, when the second predetermined rank is set to the highest rank, the two-dimensional MD calculation unit 15-2 only outputs the combination data with the largest two-dimensional Mahalanobis distance to the display processing unit 16, so in the above Figure 4 In the case of the example of Figure 5 The graph of (a) is displayed on the display screen of the display device 2.

[0078] Since the rank indicated by the first predetermined rank is lowered, the number of combination data generated by the sensor combination generation unit 15-1 increases, and thus the processing load generated by the two-dimensional MD calculation unit 15-2 increases, but on the other hand, combinations with a high correlation with the abnormality that has occurred can be extracted in a wider range. Therefore, the first predetermined rank is determined in consideration of the analysis range and the degree of processing load generated by the two-dimensional MD calculation unit 15-2. It should be noted that, when the first predetermined rank is set to the second rank or lower, the sensor combination generation unit 15-1 may select sensor identification information of any one or more ranks from the highest rank to the first predetermined rank.

[0079] The second specified rank is associated with the number of graphs displayed by the display processing unit 16 on the display screen of the display device 2. Therefore, by lowering the order shown in the second specified rank, the display processing unit 16 displays more graphs on the display screen of the display device 2. Therefore, the analyst refers to more graphs for analysis, thereby increasing the labor and time required for the analyst's analysis, but on the other hand, the analyst's analysis objects increase, so the possibility of more accurately determining the cause of the abnormality that occurred can be increased. Therefore, the second specified rank is determined in view of the labor and time required for the analyst's analysis and the required accuracy. It should be noted that, when the second specified rank is set to less than the second rank, the two-dimensional MD calculation unit 15-2 may select any one or more combination data of ranks from the highest rank to the second specified rank.

[0080] (Other configuration examples of the predetermined selection condition (Part 1))

[0081] As Figure 4 The predetermined selection condition as a prerequisite for the processing of is an example, and the following predetermined selection condition may also be applied. For example, as the predetermined selection condition, the condition that two or more predetermined number of arbitrary sensors 20-1 to 20-N other than the sensor 20-A corresponding to the main sensor identification information may also be applied. By setting this condition, the number of combination data generated by the sensor combination generation unit 15-1 can be reduced, and thus the processing load generated by the two-dimensional MD calculation unit 15-2 can be reduced.

[0082] (Other configuration examples of the specified selection conditions (Part 2))

[0083] As the specified selection condition, the following condition may also be applied: the sensors 20-1 to 20-N other than the sensor 20-A corresponding to the main sensor identification information and the sensors 20-1 to 20-N whose state quantity of the sensor 20-A and the state quantity of the sensors 20-1 to 20-N other than the sensor 20-A show a high degree of correlation in relation to a predetermined threshold value. The specific processing of the case where this condition is applied is described below. For example, the sensor combination generation unit 15-1 Figure 4In the process of S3, after the main sensor identification information is determined, the state quantity of the main sensor identification information is read from the state quantity storage unit 12, and the item of "Type" is the state quantity of "unit space". The sensor combination generation unit 15-1 selects any sensor identification information other than the main sensor identification information, and reads the state quantity of the selected sensor identification information from the state quantity storage unit 12, and the item of "Type" is the state quantity of "unit space". The sensor combination generation unit 15-1 calculates the correlation coefficient based on the state quantity of the unit space of the main sensor identification information and the state quantity of the unit space of the selected sensor identification information.

[0084] The sensor combination generation unit 15-1 calculates the correlation coefficient corresponding to each of the sensor identification information other than the main sensor identification information through the above process. The sensor combination generation unit 15-1 selects the sensor identification information whose absolute value of the correlation coefficient exceeds the predetermined threshold value. The sensor combination generation unit 15-1 generates combination data including the main sensor identification information on one side and each of the sensor identification information whose absolute value of the correlation coefficient exceeds the predetermined threshold value on the other side. The sensor combination generation unit 15-1 associates each of the generated combination data with the information indicating the detection time recorded in the "detection time" item of the SN ratio storage unit 14 referenced when generating the combination data. The sensor combination generation unit 15-1 outputs the combination data associated with the information indicating the detection time to the two-dimensional MD calculation unit 15-2. Thereafter, the processing of loop L1s to L1e is performed.

[0085] Thus, the sensor combination generation unit 15-1 can generate combination data, which sets the sensor identification information of one side to the main sensor identification information with a high correlation with the occurred abnormality selected based on the size of the SN ratio, and sets the sensor identification information of the other side to the sensor identification information of sensors 20-1~20-N that detect a state quantity indicating a high degree of correlation with the state quantity corresponding to the main sensor identification information.

[0086] In this case, the sensor combination generation unit 15-1 reduces the number of sensor identification information selected as the other party, compared with the case where the sensor identification information of the other party is set to all sensor identification information except the main sensor identification information, so the number of generated combination data can be reduced. Therefore, the processing load generated by the two-dimensional MD calculation unit 15-2 can be reduced. In addition, the sensor combination generation unit 15-1 does not randomly reduce the number of sensor identification information selected as the other party, but reduces it to the sensor identification information of sensors 20-1 to 20-N with a high degree of correlation with the state quantity detection of the sensor 20-1. Therefore, in the process of S6, the display processing unit 16 can make it more likely that the chart displayed on the display screen of the display device 2 includes a chart showing the characteristics of the state quantities of sensors 20-1 to 20-N that show the cause of the abnormality that has occurred.

[0087] It should be noted that the sensor combination generation unit 15-1 may calculate a determination coefficient instead of calculating a correlation coefficient. The determination coefficient is represented by a numerical value between 0 and 1, so it is not necessary to compare the absolute value with the threshold value as in the case of a correlation coefficient represented by a numerical value between -1 and 1, but only the determination coefficient and the threshold value need to be compared.

[0088] (Other configuration examples of the specified selection conditions (Part 3))

[0089] As the predetermined selection condition, a condition that the sensors 20-1 to 20-N other than the sensor 20-A corresponding to the main sensor identification information and the sensors 20-1 to 20-N predetermined for the sensor 20-A corresponding to the main sensor identification information may be applied. For example, other sensors 20-1 to 20-N with a large two-dimensional Mahalanobis distance and other sensors 20-1 to 20-N estimated to be useful for determining the cause of the abnormality can be predetermined for each sensor 20-1 to 20-N based on experience of abnormalities that occurred in the past, and other sensors 20-1 to 20-N with high correlation, such as other sensors 20-1 to 20-N, can be predetermined. List data is generated in advance, and the list data shows the correspondence relationship between each of the sensors 20-1 to 20-N determined in this way and each of the corresponding other sensors 20-1 to 20-N through the sensor identification information. The generated list data is stored in advance in the storage area inside the sensor combination generation unit 15-1.

[0090] The sensor combination generation unit 15-1 Figure 4In the processing of S3, after the main sensor identification information is determined, the list data stored in the internal storage area is referred to, and the sensor identification information corresponding to the main sensor identification information is read out from the list data. The sensor combination generation unit 15-1 generates combination data, which includes the main sensor identification information on one side and each of the sensor identification information read out from the list data on the other side. The sensor combination generation unit 15-1 associates each of the generated combination data with the information indicating the detection time of the item "detection time" recorded in the SN ratio storage unit 14 referred to when generating the combination data. The sensor combination generation unit 15-1 outputs the combination data associated with the information indicating the detection time to the two-dimensional MD calculation unit 15-2. Thereafter, the processing of loop L1s to L1e is performed.

[0091] Thus, the sensor combination generation unit 15-1 can generate combination data, which sets the sensor identification information of one party to the main sensor identification information that is selected based on the size of the SN ratio and has a high correlation with the occurred abnormality, and sets the sensor identification information of the other party to the sensor identification information of sensors 20-1 to 20-N that are estimated to have a high correlation with the sensor 20-A corresponding to the main sensor identification information.

[0092] In this case, the sensor combination generation unit 15-1 reduces the number of sensor identification information selected as the other party compared to the case where the sensor identification information of the other party is set to all sensor identification information except the main sensor identification information, so the number of generated combination data can be reduced. Therefore, the processing load generated by the two-dimensional MD calculation unit 15-2 can be reduced. In addition, the sensor combination generation unit 15-1 does not randomly reduce the number of sensor identification information selected as the other party, but reduces it to the sensor identification information of sensors 20-1 to 20-N that are estimated to have a high correlation with the sensor 20-A of the main sensor identification information. Therefore, in the process of S6, the display processing unit 16 can make it more likely that the chart displayed on the display screen of the display device 2 includes a chart showing the characteristics of the state quantity of sensors 20-1 to 20-N that shows the cause of the abnormality that has occurred.

[0093] It should be noted that, when the sensor combination generating unit 15-1 applies any one of the specified selection conditions of the other configuration example (two) of the specified selection conditions and the specified selection conditions of the other configuration example (three) of the specified selection conditions as the specified selection conditions, instead of using the sensor identification information corresponding to all sensors 20-1 to 20-N that meet the specified selection conditions as described above, the combination data is generated using the sensor identification information corresponding to any sensor 20-1 to 20-N selected from the sensors 20-1 to 20-N that meet the specified selection conditions.

[0094] In addition, the sensor combination generating unit 15-1 may apply both the specified selection condition of the other configuration example (one of the two) of the specified selection condition and the specified selection condition of the other configuration example (one of the three) of the specified selection condition as the specified selection condition, and use the sensor identification information corresponding to all sensors 20-1 to 20-N that meet the specified selection condition to generate the combination data, or use the sensor identification information corresponding to the sensor 20-1 to 20-N arbitrarily selected from the sensors 20-1 to 20-N that meet the specified selection condition to generate the combination data.

[0095] (About chart types)

[0096] In the above-mentioned embodiment, the display processing unit 16 indicates the types of the state quantities of "unit space", "signal space", and "abnormality" by using marks of different shapes. In this regard, the display processing unit 16 may display the graph in any form as long as the types of the state quantities of "unit space", "signal space", and "abnormality" are indicated by marks of different colors, etc., so that the different forms of the types of the state quantities of "unit space", "signal space", and "abnormality" can be known. In this case, the display processing unit 16 is not necessarily set to be able to know the different forms of the three types of "unit space", "signal space", and "abnormality". For example, the state quantity of "abnormality" may be regarded as a part of the state quantity of "signal space" and displayed in a form that the state quantity of "unit space" and the state quantity of "signal space" are different, or the types of "unit space", "signal space", and "abnormality" may not be considered, and only the position of the state quantity may be displayed.

[0097] In the above embodiment, if Figure 5As shown, the display processing unit 16 displays a graph of a scatter diagram in which the index representing the state quantity of the sensor 20-A corresponding to the main sensor identification information assigned with the identification tag is set as the first index, the first index is represented on the vertical axis, and the second index is represented on the horizontal axis. In contrast, a graph of a scatter diagram in which the first index is represented on the horizontal axis and the second index is represented on the vertical axis may be used. In addition, the sensor combination generation unit 15-1 may generate combination data without assigning identification tags, and the display processing unit 16 may set the index representing the state quantity of the sensors 20-1 to 20-N corresponding to one of the sensor identification information randomly selected from the two sensor identification information included in the combination data as the first index, and the index representing the state quantity of the sensors 20-1 to 20-N corresponding to the remaining other sensor identification information as the second index. In addition, the display processing unit 16 may generate image data of a graph other than a scatter diagram as long as it is a graph that represents the scales of the first index and the second index, the position of each state quantity determined by the scales of the first index and the second index, and the type of each state quantity.

[0098] (About the display of charts)

[0099] In the above embodiment, the abnormality detection unit 13 outputs an abnormality occurrence notification signal. Figure 4 In this case, when the abnormality detection unit 13 outputs a plurality of abnormality occurrence notification signals in a short period of time, three additional graphs are displayed on the display screen of the display device 2 for each abnormality occurrence notification signal. In this way, in order to prevent a plurality of graphs from being displayed on the display screen of the display device 2, for example, the display processing unit 16 may selectively display the graphs on the display screen of the display device 2 as follows.

[0100] When the display processing unit 16 takes in the combination data output by the two-dimensional MD calculation unit 15-2, that is, the combination data in which the information indicating the rank is associated with the information indicating the detection time, the taken-in combination data is recorded in the internal storage area. The analyst performs an operation to specify the detection time on the display processing unit 16 via the operation unit (not shown) provided by the abnormality diagnosis device 1. The display processing unit 16 reads out the three combination data corresponding to the detection time received from the operation unit from the internal storage area, and performs the processing of the loop L2s to L2e. Thus, only the images of the three charts corresponding to the detection time specified by the analyst can be displayed on the display screen of the display device 2.

[0101] The analyst may also specify the detection time and the rank to the display processing unit 16 via an operation unit (not shown). In this case, the display processing unit 16 reads a combination of data corresponding to the detection time and rank received from the operation unit from the internal storage area, and performs the process of S6. Thus, only an image of a chart corresponding to the detection time and rank specified by the analyst can be displayed on the display screen of the display device 2.

[0102] (About 2D MD calculation section)

[0103] In the abnormality diagnosis device 1 of the above-mentioned embodiment, the sensor selection unit 15 may be a sensor selection unit 15 that includes only the sensor combination generation unit 15-1 and does not include the two-dimensional MD calculation unit 15-2. In this case, the display processing unit 16 displays a graph on the display screen of the display device 2 based on the combination data generated by the sensor combination generation unit 15-1. Therefore, although the abnormality diagnosis device 1 cannot obtain the reduction effect using the two-dimensional Mahalanobis distance, it can eliminate the processing load generated by the two-dimensional MD calculation unit 15-2. In this case, the prescribed selection condition applied in the sensor combination generation unit 15-1 may also apply any of the above-mentioned prescribed selection conditions.

[0104] <Other Implementation Methods>

[0105] As mentioned above, although the embodiment of this disclosure is described in detail with reference to drawings, the specific structure is not limited to this embodiment, and design changes etc. which do not deviate from the gist of this disclosure are also included.

[0106] <Computer Configuration>

[0107] Figure 6 A schematic block diagram showing the configuration of a computer according to at least one embodiment. The computer 90 includes a processor 91, a main memory 92, a memory 93, and an interface 94. Sensors 20-1 to 20-N and a display device 2 are connected to the interface 94. The abnormality diagnosis device 1 is installed in the computer 90. In addition, the operation of the state quantity collection unit 11, the abnormality detection unit 13, the sensor selection unit 15, and the display processing unit 16 of the abnormality diagnosis device 1 is stored in the memory 93 in the form of a program. The processor 91 reads the program from the memory 93 and expands it in the main memory 92, and executes the above-mentioned processing according to the program. In addition, the processor 91 ensures the internal storage area of ​​the sensor combination generation unit 15-1 and the two-dimensional MD calculation unit 15-2, and the storage area corresponding to the state quantity storage unit 12 and the SN ratio storage unit 14 in the main memory 92 according to the program. It should be noted that the storage area of ​​the state quantity storage unit 12 and the SN ratio storage unit 14 can also be ensured in the memory 93.

[0108] The program may also be a program for realizing a part of the functions performed by the computer 90. For example, the program may also perform functions by combining with other programs already stored in the memory 93, or by combining with other programs installed in other devices. It should be noted that in other embodiments, the computer may also have a random LSI (Large Scale Integrated Circuit) such as PLD (Programmable Logic Device) in addition to or instead of the above-mentioned structure. Examples of PLD include PAL (Programmable Array Logic), GAL (Generic Array Logic), CPLD (Complex Programmable Logic Device), FPGA (Field Programmable Gate Array), etc. In this case, it is better to implement part or all of the functions implemented by the processor through the integrated circuit.

[0109] Examples of the memory 93 include a HDD (Hard Disk Drive), an SSD (Solid State Drive), a magnetic disk, an optical magnetic disk, a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), and a semiconductor memory. The memory 93 may be an internal medium directly connected to the bus of the computer 90, or an external medium connected to the computer 90 via an interface 94 or a communication line. In addition, when the program is distributed to the computer 90 via a communication line, the distributed computer 90 may expand the program in the main memory 92 and execute the above-mentioned processing. In at least one embodiment, the memory 93 is a non-temporary tangible storage medium.

[0110] <Notes>

[0111] The abnormality diagnosis device 1 described in the above embodiment can be understood, for example, as follows.

[0112] (1) The abnormality diagnosis device 1 of the first scheme comprises: an abnormality detection unit 13, which applies the Mahalanobis-Taguchi method to the state quantity detected by each of the plurality of sensors 20-1 to 20-N of the monitored object to perform abnormality detection, and calculates the SN ratio corresponding to each of the sensors 20-1 to 20-N; a sensor selection unit 15, which selects a combination of two sensors selected from the plurality of sensors 20-1 to 20N when the abnormality detection unit 13 detects an abnormality, the combination including the sensors 20-1 to 20-N corresponding to the SN ratios from the highest to the first predetermined rank as one of the sensors when the SN ratios are arranged in descending order, and including the sensors other than the one of the sensors The display processing unit 16 selects a sensor 20-1 to 20-N other than the sensor and satisfying a predetermined selection condition as the other sensor; and the display processing unit 16 selects an index representing the state quantity of the sensors 20-1 to 20-N on one side included in each combination of the two sensors selected by the sensor selection unit 15 as a first index, selects an index representing the state quantity of the other sensor 20-1 to 20-N as a second index, and displays the scale of the first index, the scale of the second index, and the position of each of the state quantities determined by the scales of the first index and the second index on the display screen for each selected combination of the first index and the second index. According to this scheme and the following schemes, the analyst can determine the combination of sensors that indicates the cause of an abnormality occurring in the monitored object with less labor and in a shorter time.

[0113] (2) The abnormality diagnosis device 1 of the second scheme is the abnormality diagnosis device 1 of (1), wherein the sensor selection unit 15 calculates the two-dimensional Mahalanobis distance according to the state quantities of the two sensors included in each selected combination of the two sensors, and reselects the combination of the two sensors from the combinations corresponding to the two-dimensional Mahalanobis distances from the highest position to the second predetermined position, when the two-dimensional Mahalanobis distances are arranged in descending order. According to this scheme, the combination of the two sensors can be narrowed down based on the size of the two-dimensional Mahalanobis distance.

[0114] (3) The abnormality diagnosis device 1 of the third aspect is the abnormality diagnosis device 1 described in (1) or (2), wherein the predetermined selection condition is the following condition: all sensors 20-1 to 20N except the one sensor. According to this aspect, all sensors that can be combined with the one sensor selected based on the SN ratio can be selected and a combination of two sensors can be generated.

[0115] (4) The abnormality diagnosis device 1 of the fourth aspect is the abnormality diagnosis device 1 described in (1) or (2), wherein the predetermined selection condition is the following condition: the sensor is any sensor 20-1 to 20N other than the sensor of the one side, and is a predetermined number of two or more. According to this aspect, the sensor of the other side of the combination of two sensors can be reduced to a predetermined plurality of sensors 20-1 to 20-N.

[0116] (5) The abnormality diagnosis device 1 of the fifth aspect is the abnormality diagnosis device 1 described in (1) or (2), wherein the predetermined selection condition is the following condition: the sensors 20-1 to 20-N are sensors other than the one sensor, and the correlation between the state quantity of the one sensor and the state quantity of the sensors other than the one sensor shows a high correlation with a predetermined threshold value. According to this aspect, the combination of two sensors can be narrowed down based on the correlation.

[0117] (6) The abnormality diagnosis device 1 of the sixth aspect is the abnormality diagnosis device 1 described in any one of (1), (2), and (5), wherein the predetermined selection condition is the following condition: the sensor is a sensor other than the one sensor, and the sensors 20-1 to 20-N are predetermined for the one sensor. According to this aspect, the other sensor of the combination of two sensors can be narrowed down to the predetermined sensors 20-1 to 20-N.

[0118] (7) The abnormality diagnosis device 1 of the seventh aspect is the abnormality diagnosis device 1 described in any one of (1) to (6), wherein the display processing unit 16 displays the position of each of the state quantities in a different form according to the type of each state quantity when displaying the position of the state quantity determined by the scale of the first indicator and the second indicator. According to this aspect, the position of the state quantity is displayed in a different form according to the type of each state quantity in the display screen, so that, for example, each state quantity can be distinguished in the display screen as a unit space, a signal space, or a state quantity when an abnormality occurs.

[0119] (8) The abnormality diagnosis device 1 of an eighth aspect is the abnormality diagnosis device 1 described in any one of (1) to (7), wherein the first predetermined rank is the highest rank. According to this aspect, the sensor selected based on the SN ratio can be set as the sensor with the largest SN ratio.

[0120] (9) The abnormality diagnosis device 1 of a ninth aspect is the abnormality diagnosis device 1 described in any one of (1) to (8), wherein the second predetermined rank is the highest rank. According to this aspect, the combination of two sensors displayed on the display screen can be set to the combination with the largest two-dimensional Mahalanobis distance.

Claims

1. An abnormality diagnosis device, comprising: an abnormality detection unit that performs abnormality detection by applying the Mahalanobis-Taguchi method to a state quantity detected by each of a plurality of sensors provided to a monitoring object, and calculates an SN ratio corresponding to each of the sensors; a sensor selection unit, when the abnormality detection unit detects an abnormality, selecting a combination of two sensors selected from the plurality of sensors, the combination including as one sensor a sensor corresponding to an SN ratio from the highest to a predetermined first specified rank when the SN ratios are arranged in descending order, and including as the other sensor a sensor other than the sensor on the one side and satisfying a predetermined specified selection condition; as well as The display processing unit selects an indicator representing the state quantity of one sensor included in each combination of the two sensors selected by the sensor selection unit as a first indicator, selects an indicator representing the state quantity of the other sensor as a second indicator, and displays the scale of the first indicator, the scale of the second indicator, and the position of each of the state quantities determined by the scales of the first indicator and the second indicator on a display screen according to each selected combination of the first indicator and the second indicator.

2. The abnormality diagnosis device according to claim 1, wherein: The sensor selection unit calculates the two-dimensional Mahalanobis distance according to the state quantities of the two sensors included in each selected combination of the two sensors, and reselects the combination of the two sensors from the combinations corresponding to the two-dimensional Mahalanobis distances counted from the highest position to a predetermined second specified position while arranging the two-dimensional Mahalanobis distances in descending order.

3. The abnormality diagnosis device according to claim 1 or 2, wherein: The predetermined selection condition is a condition that all sensors except the one sensor are selected.

4. The abnormality diagnosis device according to claim 1 or 2, wherein: The predetermined selection condition is a condition that the sensors are other than the one sensor and are any sensors of a predetermined number of two or more.

5. The abnormality diagnosis device according to claim 1 or 2, wherein: The prescribed selection condition is the following condition: it is a sensor other than the sensor of the one party, and the state quantity of the sensor of the one party and the state quantity of the sensor other than the sensor of the one party show a high correlation in the relationship with a predetermined threshold.

6. The abnormality diagnosis device according to claim 1 or 2, wherein: The predetermined selection condition is a condition that the sensor is other than the one sensor and is a sensor predetermined for the one sensor.

7. The abnormality diagnosis device according to claim 1 or 2, wherein: When displaying the position of each of the state quantities specified by the scales of the first indicator and the second indicator, the display processing unit displays the position of the state quantity in a different form for each type of the state quantity.

8. The abnormality diagnosis device according to claim 1 or 2, wherein: The first predetermined rank is the highest rank.

9. The abnormality diagnosis device according to claim 2, wherein: The second predetermined rank is the highest rank.

10. A method for abnormality diagnosis, comprising: an abnormality detection step, applying the Mahalanobis-Taguchi method to each state quantity detected by a plurality of sensors of the monitored object to perform abnormality detection, and calculating the SN ratio corresponding to each of the sensors; a sensor selection step of selecting, when an abnormality is detected by the abnormality detection step, a combination of two sensors selected from the plurality of sensors, the combination including, as one sensor, a sensor corresponding to an SN ratio from the highest digit to a predetermined first digit when the SN ratios are arranged in descending order, and including, as the other sensor, a sensor other than the sensor on the one side and satisfying a predetermined specified selection condition; as well as In a display processing step, an indicator representing the state quantity of one sensor included in each combination of the two sensors selected by the sensor selection step is selected as a first indicator, and an indicator representing the state quantity of the other sensor is selected as a second indicator, and according to each selected combination of the first indicator and the second indicator, the scale of the first indicator, the scale of the second indicator, and the position of each of the state quantities determined by the scales of the first indicator and the second indicator are displayed on a display screen.

11. A storage medium storing a program for causing a computer to function as the following means: an abnormality detection unit that applies the Mahalanobis-Taguchi method to a state quantity detected by each of a plurality of sensors provided to the monitoring object, and calculates an SN ratio corresponding to each of the sensors; a sensor selection unit, which selects a combination of two sensors selected from the plurality of sensors when the abnormality detection unit detects an abnormality, the combination including as one sensor a sensor corresponding to an SN ratio from the highest digit to a predetermined first digit when the SN ratios are arranged in descending order, and including as the other sensor a sensor other than the sensor on the one digit and satisfying a predetermined specified selection condition; as well as The display processing unit selects an indicator representing the state quantity of one sensor included in each combination of the two sensors selected by the sensor selection unit as a first indicator, selects an indicator representing the state quantity of the other sensor as a second indicator, and displays the scale of the first indicator, the scale of the second indicator, and the position of each of the state quantities determined by the scales of the first indicator and the second indicator on a display screen according to each selected combination of the first indicator and the second indicator.

Images