Failure diagnosis device, failure diagnosis method, failure diagnosis program, and failure diagnosis system

Abstract

An abnormality data reception unit (110) receives abnormality data. A failure case selection unit (121) selects a failure case associated with abnormality information included in the abnormality data from a failure case database (191). A failure condition acquisition unit (122) acquires a failure condition associated with the selected failure case from a failure condition database (192). An environment information acquisition unit (130) acquires environment information. A failure condition determination unit (123) determines whether the failure condition is satisfied on the basis of the environment information or sensor data included in the abnormality data. A diagnostic result output unit (140) outputs a diagnostic result.

Description

Fault diagnosis device, fault diagnosis method, fault diagnosis program, and fault diagnosis system

[0001] The present disclosure relates to fault diagnosis for a device in which an abnormality has occurred.

[0002] Patent Document 1 proposes the following fault diagnosis system: The fault diagnosis system predicts equipment failures through machine learning using sensor data obtained from equipment and repair history indicating past repairs.

[0003] Japanese Patent Application Laid-Open No. 2022-008107

[0004] Conventional fault diagnosis cannot diagnose faults caused by environmental factors because it cannot grasp the environment that cannot be determined by the device's sensors.

[0005] The present disclosure aims to enable diagnosis of environmentally-related faults.

[0006] a failure condition acquisition unit that acquires, from a failure condition database that indicates the relationship between failure cases and abnormality information of abnormalities that may occur in the target device, a failure case associated with the same abnormality information as the abnormality information included in the abnormality data; a failure condition acquisition unit that acquires, from a failure condition database that indicates the relationship between failure cases and abnormality conditions, a failure condition associated with the same failure case as the selected failure case; an environmental information acquisition unit that acquires environmental information of an environment external to the target device; a failure condition determination unit that determines, based on the acquired environmental information, whether the acquired failure condition is established if the selected failure case is an environmental cause case that is a failure case caused by the environment external to the target device, and determines, based on the sensor data included in the abnormality data, whether the acquired failure condition is established if the selected failure case is not the environmental cause case; and a diagnosis result output unit that outputs a diagnosis result that indicates information related to the determination result.

[0007] The present disclosure aims to enable diagnosis of failures caused by environmental factors.

[0008] FIG. 1 is a configuration diagram of a fault diagnosis device 100 according to a first embodiment. FIG. 2 is a configuration diagram of a fault diagnosis system 200 according to the first embodiment. FIG. 3 is a flowchart of a fault diagnosis method according to the first embodiment. FIG. 4 is a diagram showing an example of a fault case database 191 according to the first embodiment. FIG. 5 is a diagram showing an example of a diagnosis result according to the first embodiment. FIG. 6 is a configuration diagram of a fault diagnosis system 200 according to the second embodiment. FIG. 7 is a flowchart of a fault diagnosis method according to the third embodiment. FIG. 8 is a flowchart of a verification method according to the fourth embodiment. FIG. 9 is a diagram showing an example of a fault case database 191 according to the fourth embodiment. FIG. 10 is a diagram showing an example of a fault condition database 192 according to the fourth embodiment. FIG. 11 is a configuration diagram of a fault diagnosis system 200 according to a fifth embodiment. FIG. 12 is a flowchart of a fault diagnosis method according to the fifth embodiment. FIG. 13 is a hardware configuration diagram of a fault diagnosis device 100 according to an embodiment.

[0009] In the embodiments and drawings, the same or corresponding elements are denoted by the same reference numerals. The description of elements denoted by the same reference numerals as those already described will be omitted or simplified as appropriate. Arrows in the drawings primarily indicate the flow of data or the flow of processing.

[0010] First Embodiment A fault diagnosis device 100 will be described with reference to FIGS.

[0011] ***Configuration Description***

[0012] The configuration of the fault diagnosis device 100 will be described with reference to Fig. 1. The fault diagnosis device 100 is a computer including hardware such as an abnormality data receiving unit 110, a fault diagnosis unit 120, an environmental information acquiring unit 130, a diagnosis result output unit 140, and a basic information receiving unit 150. These pieces of hardware are connected to each other via signal lines.

[0013] The processor 101 is an IC that performs arithmetic processing and controls other hardware. For example, the processor 101 is a CPU. IC is an abbreviation for Integrated Circuit. CPU is an abbreviation for Central Processing Unit.

[0014] The memory 102 is a volatile or non-volatile storage device. The memory 102 is also called a primary storage device or a main memory. For example, the memory 102 is a RAM. Data stored in the memory 102 is saved in the secondary storage device 103 as needed. RAM is an abbreviation for Random Access Memory.

[0015] The auxiliary storage device 103 is a non-volatile storage device. For example, the auxiliary storage device 103 is a ROM, a HDD, a flash memory, or a combination of these. Data stored in the auxiliary storage device 103 is loaded into the memory 102 as needed. ROM is an abbreviation for Read Only Memory. HDD is an abbreviation for Hard Disk Drive.

[0016] The communication device 104 is a receiver and a transmitter. For example, the communication device 104 is a communication chip or a NIC. Communication of the fault diagnosis device 100 is performed using the communication device 104. NIC is an abbreviation for Network Interface Card.

[0017] The input / output interface 105 is a port to which an input device and an output device are connected. For example, the input / output interface 105 is a USB terminal, the input devices are a keyboard and a mouse, and the output device is a display. Input and output of the fault diagnosis device 100 are performed using the input / output interface 105. USB is an abbreviation for Universal Serial Bus.

[0018] The fault diagnosis device 100 includes elements such as an abnormality data receiving unit 110, a fault diagnosis unit 120, an environmental information acquisition unit 130, a diagnosis result output unit 140, and a basic information receiving unit 150. These elements are realized by software.

[0019] The auxiliary storage device 103 stores a fault diagnosis program for causing the computer to function as an abnormality data receiving unit 110, a fault diagnosis unit 120, an environmental information acquiring unit 130, a diagnosis result output unit 140, and a basic information receiving unit 150. The fault diagnosis program is loaded into the memory 102 and executed by the processor 101. The auxiliary storage device 103 also stores an OS. At least a portion of the OS is loaded into the memory 102 and executed by the processor 101. The processor 101 executes the fault diagnosis program while running the OS. OS is an abbreviation for Operating System.

[0020] Input and output data of the fault diagnosis program are stored in the storage unit 190. The auxiliary storage device 103 functions as the storage unit 190. However, a storage device such as the memory 102, a register in the processor 101, or a cache memory in the processor 101 may function as the storage unit 190 instead of or together with the auxiliary storage device 103.

[0021] The fault diagnosis program can be recorded (stored) in a computer-readable manner on a non-volatile recording medium such as an optical disk or a flash memory.

[0022] The configuration of the fault diagnosis system 200 will be described with reference to Fig. 2. The fault diagnosis system 200 includes a fault diagnosis device 100, a target device 210, and an environmental information providing system 220. The fault diagnosis device 100 communicates with the target device 210 and the environmental information providing system 220 via a communication network 201.

[0023] In the fault diagnosis device 100 , the fault diagnosis unit 120 includes elements such as a fault case selection unit 121 , a fault condition acquisition unit 122 , and a fault condition determination unit 123 .

[0024] The target device 210 is a device that is the target of fault diagnosis. The target device 210 has a communication function and is equipped with one or more types of sensors 211. The target device 210 outputs abnormality data when an abnormality occurs. The abnormality data includes abnormality information and sensor data. The abnormality information is information related to an abnormality that has occurred in the target device 210. For example, the abnormality information indicates an error code or a symptom of the device. The sensor data is data obtained by one or more types of sensors 211.

[0025] An abnormality is a symptom that indicates an abnormal condition and is caused by a malfunction. Examples of abnormalities are poor performance, vibration, abnormal noise, and error code display. A malfunction is the cause of an abnormal symptom. Examples of malfunctions are component deterioration, frost buildup, and chemical embrittlement.

[0026] The environmental information providing system 220 is one or more computer systems that provide various types of environmental information. The environmental information is information about the external environment of the target device 210.

[0027] The fault case database 191 , the fault condition database 192 , the environmental information database 193 , and the basic information database 194 are stored in the storage unit 190 .

[0028] The fault case database 191 is a database in which one or more fault case data are registered. The fault case data indicates the relationship between abnormality information and fault cases. The fault case data is generated based on the designer's knowledge and other factors in accordance with the model and configuration of the target device 210. The abnormality information is information about abnormalities that may occur in the target device 210. The fault cases are information about failures that may occur in the target device 210. For example, the fault cases indicate the causes of abnormalities that may occur in the target device 210.

[0029] The fault condition database 192 is a database in which one or more fault condition data are registered. The fault condition data indicates the relationship between a fault case and a fault condition. The fault condition indicates a condition of sensor data or environmental information as a condition for the occurrence of a fault case. For example, the fault condition indicates a threshold value, a conditional expression, or a sensor data pattern.

[0030] The environmental information database 193 stores the environmental information acquired from the environmental information providing system 220 .

[0031] The basic information database 194 stores basic information about the target device 210 and basic information about the environmental information providing system 220. The user inputs the basic information about the target device 210 and the environmental information providing system 220 into the fault diagnosis device 100. The basic information receiving unit 150 receives the input basic information and stores it in the basic information database 194. The basic information about the target device 210 indicates location information about the target device 210. The basic information about the target device 210 also indicates the model and configuration of the target device 210. The location information about the target device 210 indicates the geographic location (installation position) where the target device 210 is installed. For example, the location information indicates latitude and longitude, an address, or a place name. The location information may also indicate regional information. The regional information indicates areas at risk of river flooding or areas at risk of landslides. The basic information about the environmental information providing system 220 indicates provider information. The provider information identifies the provider of various types of environmental information and indicates information necessary to access the provider.

[0032] ***Description of Operation*** The operational procedure of the fault diagnosis device 100 corresponds to a fault diagnosis method. Also, the operational procedure of the fault diagnosis device 100 corresponds to a processing procedure according to a fault diagnosis program.

[0033] The fault diagnosis method will be described with reference to Figures 3 and 4. In step S110, the abnormal data receiving unit 110 receives abnormal data. For example, when an abnormality occurs in the target device 210, the target device 210 transmits the abnormal data, and the abnormal data receiving unit 110 receives the abnormal data. For example, a user inputs abnormal data of the target device 210 into the fault diagnosis device 100, and the abnormal data receiving unit 110 receives the input abnormal data.

[0034] In step S121, the fault case selection unit 121 selects from the fault case database 191 one or more fault cases associated with the same anomaly information as the anomaly information included in the anomaly data.

[0035] In step S122, the fault condition acquisition unit 122 selects one unselected fault case from the one or more selected fault cases.

[0036] In step S123, the fault condition acquisition unit 122 acquires, from the fault condition database 192, fault conditions associated with the same fault case as the selected fault case.

[0037] In step S124, the failure condition determination unit 123 determines whether the selected failure case is an environmental cause case. An environmental cause case is a failure case caused by an environment external to the target device 210.

[0038] The determination is performed as follows. A classification is assigned to a failure case. The failure condition determination unit 123 determines whether the failure case is an environmental cause case based on the classification assigned to the failure case. For example, a classification such as "weather," "ambient environment," "accidental event," "man-made event," "equipment," or "software" is assigned to the failure case. "Weather," "ambient environment," "accidental event," and "man-made event" are classifications that belong to environmental factors. "Equipment" and "software" are classifications that do not belong to environmental factors. The failure condition determination unit 123 determines whether the classification assigned to the failure case is a classification that belongs to environmental factors. For example, a list of classifications that belong to environmental factors (environmental cause classification list) is stored in advance in the storage unit 190. Then, if the same classification assigned to the failure case is included in the environmental cause classification list, the failure condition determination unit 123 determines that the classification assigned to the failure case is a classification that belongs to environmental factors. If the classification assigned to the failure case is a classification that belongs to environmental factors, the failure condition determination unit 123 determines that the failure case is an environmental cause case.

[0039] If the selected failure case is an environmental cause case, the process proceeds to step S131. If the selected failure case is not an environmental cause case, the process proceeds to step S125.

[0040] In step S125, the fault condition determination unit 123 determines whether the acquired fault condition is established based on the sensor data included in the abnormality data. That is, the fault condition determination unit 123 determines whether the sensor data matches the fault condition. The fault condition determination unit 123 may make the determination using a trained model. The trained model is generated in advance by machine learning. After step S125, the process proceeds to step S126.

[0041] 4, the description will continue from step S131. In step S131, the environmental information acquisition unit 130 acquires basic information of the target device 210 and basic information of the environmental information providing system 220 from the basic information database 194. Then, the environmental information acquisition unit 130 acquires location information of the target device 210 from the basic information of the target device 210.

[0042] In step S132, the environmental information acquisition unit 130 accesses the environmental information providing system 220 using the basic information of the environmental information providing system 220. Then, the environmental information acquisition unit 130 uses the location information of the target device 210 to acquire environmental information at the installation location of the target device 210 from the environmental information providing system 220.

[0043] In step S133, the fault condition determination unit 123 determines whether the acquired fault condition is established based on the acquired environmental information. That is, the fault condition determination unit 123 determines whether the environmental information matches the fault condition. The fault condition determination unit 123 may make the determination using a trained model. After step S133, the process proceeds to step S126.

[0044] Returning to Fig. 3, the description will continue from step S126. In step S126, the fault condition determination unit 123 determines whether there is an unselected fault case among the one or more selected fault cases. If there is an unselected fault case among the one or more selected fault cases, the process proceeds to step S122. If there is no unselected fault case among the one or more selected fault cases, the process proceeds to step S140.

[0045] In step S140, the diagnostic result output unit 140 outputs the diagnostic result. The diagnostic result indicates information related to the result of the judgment made by the fault condition judgment unit 123. For example, the diagnostic result indicates a fault case in which the abnormality information and the fault condition are met. The fault case indicated in the diagnostic result is a fault case that is highly likely to have caused the occurrence of the abnormality. For example, the diagnostic result output unit 140 displays the diagnostic result on a display. After step S140, the processing ends.

[0046] ***Description of the Example*** When frost forms on the outdoor unit of an air conditioner, heating performance may be reduced. The occurrence of frost can be estimated using environmental information such as outdoor temperature, humidity, and wind speed. Therefore, environmental information is acquired from the environmental information providing system 220. FIG. 5 shows an example of the fault case database 191. Four fault case data are registered in the fault case database 191. The fault case data indicate the classification and events of the fault case. The first fault case data indicates a fault case in which frost occurs due to the weather (external environment), causing a decrease in heating performance due to the occurrence of fog. This fault case is referred to as a performance degradation fault case. The fault condition database 192 registers fault condition data indicating the fault conditions of the performance degradation fault case. This fault condition data indicates the conditions of environmental information regarding an environment in which frost may occur as a fault condition. For example, the fault condition is expressed using a mathematical formula. The fault conditions may be classified using a clustering method based on machine learning or the like. If the abnormality information indicates a decrease in heating performance, the fault case selection unit 121 selects a performance-degraded fault case from the fault case database 191. When a performance-degraded fault case is selected, the fault condition acquisition unit 122 acquires fault conditions associated with the performance-degraded fault case from the fault condition database 192. Because the selected fault case is a fault case caused by an environmental factor, the environmental information acquisition unit 130 acquires environmental information. Then, the fault condition determination unit 123 determines whether the fault conditions associated with the performance-degraded fault case are met based on the acquired environmental information. This makes it possible to estimate the possibility that an abnormality has occurred due to the formation of frost, even if there is no sensor data related to frost. In this way, it is possible to make an appropriate diagnosis by utilizing the knowledge of experts regarding the relationship between failure symptoms and environmental factors.

[0047] An example of the diagnosis result is shown in Fig. 6. The diagnosis result indicates the judgment result for each of one or more fault cases. The judgment result indicates the possibility (percentage, etc.) that the fault indicated in the fault case caused the occurrence of the abnormality.

[0048] ***Effects of First Embodiment*** The first embodiment relates to a fault diagnosis system that estimates the cause of a fault due to environmental factors. A cause is something that causes a certain thing, state, or change. A main factor is the main cause that causes something to occur. An environmental factor means that the environment is the main cause. Estimation is the act of guessing the possibility of a certain event based on data and conditions. Since it is not known whether a certain event has actually occurred, the occurrence of the event is estimated based on data and conditions. Diagnosis is the act of estimating and determining each of multiple causes of a fault. In other words, the most likely cause is diagnosed from among possible faults.

[0049] The fault diagnosis device 100 acquires external environmental information and estimates the environment that may lead to a fault in order to diagnose a fault due to an environmental factor that cannot be grasped from the sensor data of the target device 210. This makes it possible to estimate a fault due to an environmental factor. The diagnosis result output unit 140 outputs the diagnosis result. This enables a maintenance technician to determine the location of the fault due to the relevant environmental factor.

[0050] According to the first embodiment, it is possible to estimate the possibility of a failure due to an environmental factor without adding a new sensor required for grasping the environment.

[0051] Second Embodiment A mode for correcting a fault condition will be described below, focusing mainly on the differences from the first embodiment, with reference to FIGS.

[0052] ***Description of Configuration*** The configuration of the fault diagnosis device 100 will be described with reference to Fig. 7. The fault diagnosis device 100 further includes an element called an environment reproduction unit 160. The fault diagnosis program further causes a computer to function as the environment reproduction unit 160. The fault diagnosis unit 120 further includes an element called a fault condition correction unit 124.

[0053] ***Description of Operation*** The fault diagnosis method will be described with reference to Figures 3 and 8. In Figure 3, step S110, steps S121 to S126, and step S140 are the same as those described in the first embodiment.

[0054] In step S124, if the selected failure case is an environmental cause case, the process proceeds to step S201 (see FIG. 8).

[0055] In step S201, the environmental information acquisition unit 130 acquires basic information of the target device 210 and basic information of the environmental information providing system 220 from the basic information database 194. Then, the environmental information acquisition unit 130 acquires location information of the target device 210 from the basic information of the target device 210. Step S201 is the same as step S131 in the first embodiment.

[0056] In step S202, the environmental information acquisition unit 130 accesses the environmental information providing system 220 using the basic information of the environmental information providing system 220. Then, the environmental information acquisition unit 130 uses the location information of the target device 210 to acquire, from the environmental information providing system 220, environmental information for the abnormal time period at the installation location of the target device 210.

[0057] The abnormal time period is a time period during which an abnormality occurs in the target device 210. Specifically, the abnormal time period is a time period that includes the time when the abnormality occurs in the target device 210 (the abnormality occurrence time). For example, the abnormal time period is a time period up to the abnormality occurrence time, and has a predetermined length of time. For example, the abnormality occurrence time is the time when the abnormality data is received in step S110.

[0058] In step S203, the environment reproduction unit 160 reproduces the behavior of the target device 210 during the abnormal time period using the environment information acquired in step S202. At this time, the environment reproduction unit 160 simulates the operation of the target device 210 in the selected failure case.

[0059] The behavior of the target device 210 is reproduced using a physical formula or a calculation formula.

[0060] In step S203, sensor data during the abnormal time period is obtained.

[0061] In step S204, the fault condition corrector 124 corrects the fault condition acquired in step S123 using the sensor data obtained in step S203.

[0062] In step S205, the fault condition determination unit 123 determines whether the corrected fault condition is established based on the sensor data included in the abnormality data. The determination method is the same as the method used in step S125. After step S205, the process proceeds to step S126 (see FIG. 3).

[0063] ***Explanation of the Example*** An example will be described using an example of a failure affected by external temperature (heat). In conventional failure diagnosis, failure diagnosis is performed using sensor data from a device. However, if there is no sensor that captures the device's external environment, the behavior of the sensor data may be affected by the temperature of the external environment, and the sensor data may not meet the conditions for failure diagnosis. Therefore, in determining a failure that is affected by external temperature, external temperature information is acquired as environmental information. Then, the behavior of the device at the time of the failure is reproduced using environmental information from the time period when the failure occurred. This makes it possible to generate failure diagnosis conditions (sensor data behavior) that take environmental information into account when diagnosing the failure. When pattern matching is performed between the sensor data pattern obtained when the behavior of the device at the time of failure is reproduced and actual waveform data, the reproduced data can be used as the conditions for failure diagnosis.

[0064] ***Effects of Second Embodiment*** In the second embodiment, the judgment conditions are corrected when environmental factors affect the judgment conditions of the device's sensor data. According to the second embodiment, by reproducing the environment as needed for failure conditions for which environmental factors have not been taken into consideration in advance, it becomes possible to generate data that will become failure conditions according to the environment. Furthermore, even in cases where there is no sensor data for the device, it becomes possible to correct the conditions for failure diagnosis using environmental information. This makes it possible to improve the accuracy of diagnosis.

[0065] Third Embodiment A form for updating a fault condition will be described below, focusing mainly on the differences from the second embodiment, with reference to FIG.

[0066] ***Description of Configuration*** The configuration of the fault diagnosis device 100 is the same as that in the second embodiment.

[0067] ***Description of Operation*** The fault diagnosis method will be described with reference to Figures 3 and 9. In Figure 3, step S110, steps S121 to S126, and step S140 are the same as those described in the first embodiment.

[0068] In step S124, if the selected failure case is an environmental cause case, the process proceeds to step S201 (see FIG. 9).

[0069] 9, steps S201 to S205 are the same as those described in embodiment 2. After step S205, the process proceeds to step S301.

[0070] In step S301, the fault condition correcting unit 124 updates the fault condition acquired in step S123 to the corrected fault condition among the fault conditions shown in the fault condition database 192. After step S301, the process proceeds to step S126 (see FIG. 3).

[0071] ***Effects of Third Embodiment*** In the third embodiment, the results obtained by reproducing the behavior are registered in the fault condition database 192. This makes it possible to automatically update the fault condition database 192 with judgment conditions that take the environment into consideration. This reduces the burden of preparing models in advance.

[0072] Fourth Embodiment A form for verifying fault conditions will be described below, focusing mainly on the differences from the first to third embodiments, with reference to FIGS.

[0073] ***Description of Configuration*** The configuration of the fault diagnosis device 100 is the same as that in the second embodiment.

[0074] ***Description of Operation*** The verification method will be described with reference to Fig. 10. The verification method is part of the fault diagnosis method. In step S401, the environment reproduction unit 160 receives verification specification data. For example, a user inputs the verification specification data into the fault diagnosis device 100, and the environment reproduction unit 160 receives the input verification specification data.

[0075] The verification specification data specifies the environmental information to be verified and the fault conditions to be verified. The environmental information specified by the verification specification data is referred to as "specified environmental information." The fault conditions specified by the verification specification data are referred to as "specified fault conditions."

[0076] In step S402, the environment reproduction unit 160 uses the specified environment information to reproduce the behavior of the failure of the target device 210. The reproduction method is the same as the method in step S203 in embodiment 2. In step S402, sensor data at the time of the failure is obtained.

[0077] In step S403, the fault condition determination unit 123 determines whether the specified fault condition is satisfied based on the sensor data obtained in step S402. The specified fault condition is acquired from the fault condition database 192. The determination method is the same as the method in step S125 in the first embodiment.

[0078] If the specified fault condition is met, the process proceeds to step S404. If the specified fault condition is not met, the process proceeds to step S405.

[0079] In step S404, the fault condition corrector 124 changes the specified fault conditions using the specified environment information, thereby updating the specified fault conditions shown in the fault condition database 192.

[0080] In step S405, the fault condition corrector 124 adds the specified environment information to the specified fault conditions, thereby updating the specified fault conditions shown in the fault condition database 192.

[0081] ***Effects of the Fourth Embodiment*** In the fourth embodiment, the expected range of environments is automatically verified. This clarifies the behavior and range of sensor data that are affected by the environment, making it possible to determine conditions for fault diagnosis other than pattern matching. The fourth embodiment makes it possible to automatically update the fault condition database 192.

[0082] *** Supplementary Note to Fourth Embodiment *** Fig. 11 shows an example of the fault case database 191. The fault case database 191 holds data associated with possible fault cases from anomaly information. For example, assume that the anomaly information indicates a performance degradation. In this case, "Device: Deterioration of Component B" and "Weather: Weather Event A" are registered in the fault case database 191 as fault cases associated with the anomaly information. Multiple fault cases may be assigned to one piece of anomaly information, or one fault case may be associated with multiple pieces of anomaly information.

[0083] FIG. 12 shows an example of the fault condition database 192. The fault condition database 192 stores data types and judgment conditions used for fault diagnosis according to the fault case. The fault diagnosis data can be specified so that the data used for diagnosis can be changed depending on the fault case. When targeting sensor data of a device, sensor data is selected as the fault diagnosis data, and a list of sensors to be diagnosed in the event of a fault can be specified as the judgment conditions. The pattern of sensor data at the time of the fault is associated as a sensor pattern. This enables fault diagnosis based on the sensor data of the device. It is assumed that data other than the device's sensors will be used. For example, if a weather event A is the cause of the fault in a failure case, weather information is specified as the fault diagnosis data, and judgment conditions for judging the weather event A are registered. For example, conditions such as the temperature below a certain degree, the humidity above a certain percentage, and the wind speed in meters per second are registered. This makes it possible to determine whether the data obtained from the weather information meets these conditions. It is assumed that cases other than weather information will be used. For example, if a failure case is caused by a chemical substance that depends on the surrounding environment, it may be dependent on the region. Therefore, regional information is used as fault diagnosis data to determine whether the region is relevant. Furthermore, chemical substances cause chemical reactions, which are expected to lead to failures. Therefore, degradation estimation, which estimates the degree of impact from the relevant chemical substances, is specified as a judgment condition. This makes it possible to estimate such failures. It is possible to register not just one method, but multiple different methods as judgment conditions. This makes it possible to estimate the environment from multiple perspectives, using not only judgments based on conditional expressions, but also verification of judgment methods using machine learning and judgments based on environmental reproduction using simulations. This makes it possible to increase the reliability of the estimation results.

[0084] Fifth Embodiment A fifth embodiment of the present invention will be described with reference to Figs. 13 and 14, focusing on differences from the first to fourth embodiments in keeping a diagnostic history.

[0085] ***Description of Configuration*** The configuration of the fault diagnosis device 100 will be described with reference to Fig. 13. A diagnosis history database 195 is stored in the storage unit 190.

[0086] ***Description of Operation*** The fault diagnosis method will be described based on Fig. 14. Step S510 is the same as step S110 in the first embodiment. Steps S521 to S523 are the same as steps S121 to S123 in the first embodiment. Steps S531 to S533 are the same as steps S131 to S133 in the first embodiment. Step S534 is the same as step S125 in the first embodiment.

[0087] In step S535, the failure condition determination unit 123 registers the environmental information acquired in step S532, the determination results in step S533, and the determination results in step S534 in the diagnosis history database 195 in association with each other.

[0088] Step S536 is the same as step S126 in embodiment 1. Step S540 is the same as step S140 in embodiment 1.

[0089] ***Effects of Embodiment 5*** Assume that the fault case database 191 does not previously associate anomaly information with environmentally-related fault cases. In other words, assume that the relationship between the fault cases and environmental factors is unknown. In this case, regardless of the environmental information in the fault case database 191, all environmental information data is acquired during diagnosis and a history is saved, thereby estimating all environments that can be collected and assessed. Then, the estimation results and data related to the correlation between the anomaly data (sensor data and anomaly information) acquired from the target device 210 and the estimated environmental results are collected. By collecting such data in the diagnosis history database 195, it becomes possible to discover new relationships between anomaly information, device sensor data, environmental data, and environmental factors. This makes it possible to easily expand the fault case database 191 to include environmentally-related fault cases.

[0090] *** Supplementary Notes on the Embodiments *** The embodiments make it possible to estimate failures due to environmental factors even when the device does not have a sensor for detecting the environment.

[0091] The abnormality data receiving unit 110 receives sensor data from the target device 210. The basic information receiving unit 150 receives information related to the device, such as the installation location of the device. The fault case database 191 has a table that associates information indicating an abnormality in the device with fault cases related to that information. The fault condition database 192 records fault conditions that associate sensor patterns or fault conditions when a device failure occurs with fault cases, as well as conditions for estimating whether the environment surrounding the device is conducive to a failure. The fault case selection unit 121 selects a fault case for data evaluation by referring to the associated table in the fault case database 191 based on the abnormality information obtained from the abnormality data receiving unit 110. The basic information database 194 associates geographical location information where the device is installed with information on the acquisition source of environmental information services. The environmental information acquisition unit 130 acquires data that cannot be collected from the device from environmental information services, etc., and acquires information from the acquisition source associated in the basic information database 194. The fault condition determination unit 123 uses information for estimating the environment acquired from the fault condition database 192 and data from the collected environmental information service to estimate whether the environment is one that could lead to a fault. The fault diagnosis unit 120 is made up of a fault case selection unit 121, a fault condition acquisition unit 122, and a fault condition determination unit 123. The diagnosis result output unit 140 displays the cause of the device fault determined by the fault diagnosis unit 120.

[0092] The environment reproduction unit 160 generates a behavior model by reproducing the behavior of the device based on a formula or physical calculation using the data acquired by the environment information acquisition unit 130. The failure condition correction unit 124 estimates the cause of failure under the conditions of failure estimation of the behavior model due to environmental factors, taking into account the difference between the result obtained by the environment reproduction unit 160 and the behavior model of the device at the time of failure registered in the failure condition database 192 as an allowable error.

[0093] The fault condition correcting unit 124 updates the fault condition database 192 using the obtained results, thereby improving the accuracy of the determination conditions of the fault condition determining unit 123 .

[0094] The fault condition database 192 enables a data selection function for selecting fault diagnosis target data corresponding to a fault case, and allows one or more judgment conditions to be specified according to the fault diagnosis target data. Also, data other than the sensor data of the device can be specified as the fault diagnosis target data. This makes it possible to specify data related to the fault and a diagnosis method even when the device does not have sensor data.

[0095] The diagnosis history database 195 stores device anomalies related to failures, device sensor data, and estimated environmental factors. The relationship between device anomalies, data, and failures caused by environmental factors is accumulated, making it possible to easily update failure cases caused by environmental factors.

[0096] The hardware configuration of the fault diagnosis device 100 will be described with reference to Fig. 15. The fault diagnosis device 100 includes a processing circuit 109. The processing circuit 109 is hardware that implements an abnormality data receiving unit 110, a fault diagnosis unit 120, an environmental information acquisition unit 130, a diagnosis result output unit 140, a basic information receiving unit 150, and an environmental reproduction unit 160. The processing circuit 109 may be dedicated hardware, or may be a processor 101 that executes a program stored in a memory 102.

[0097] When the processing circuit 109 is dedicated hardware, the processing circuit 109 may be, for example, a single circuit, a multiple circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field Programmable Gate Array.

[0098] In the processing circuit 109, some functions may be realized by dedicated hardware, and the remaining functions may be realized by software or firmware.

[0099] In this way, the functions of the fault diagnosis device 100 can be realized by hardware, software, firmware, or a combination of these.

[0100] Each embodiment is an example of a preferred embodiment and is not intended to limit the technical scope of the present disclosure. Each embodiment may be implemented in part or in combination with other embodiments. Procedures described using flowcharts, etc. may be modified as appropriate.

[0101] The "part" of each element of the fault diagnosis device 100 may be read as a "process," a "step," a "circuit," or a "circuitry."

[0102] 100 Fault diagnosis device, 101 Processor, 102 Memory, 103 Auxiliary storage device, 104 Communication device, 105 Input / output interface, 109 Processing circuit, 110 Abnormal data reception unit, 120 Fault diagnosis unit, 121 Fault case selection unit, 122 Fault condition acquisition unit, 123 Fault condition determination unit, 124 Fault condition correction unit, 130 Environmental information acquisition unit, 140 Diagnosis result output unit, 150 Basic information reception unit, 160 Environmental reproduction unit, 190 Storage unit, 191 Fault case database, 192 Fault condition database, 193 Environmental information database, 194 Basic information database, 195 Diagnosis history database, 200 Fault diagnosis system, 201 Communication network, 210 Target device, 211 Sensor, 220 Environmental information providing system.

Claims

1. A fault diagnosis device comprising: an abnormality data receiving unit that receives abnormality data including abnormality information of an abnormality occurring in a target device and sensor data acquired by the target device; a fault case selection unit that selects a fault case associated with the same abnormality information as the abnormality information included in the abnormality data from a fault case database that indicates the relationship between abnormality information of an abnormality that may occur in the target device and fault cases; a fault condition acquisition unit that acquires a fault condition associated with the same fault case as the selected fault case from a fault condition database that indicates the relationship between fault cases and fault conditions; an environmental information acquisition unit that acquires environmental information of an environment outside the target device; a fault condition judgment unit that judges whether an acquired fault condition is established based on the acquired environmental information or the sensor data included in the abnormality data; and a diagnosis result output unit that outputs a diagnosis result indicating information regarding the judgment result.

2. The fault diagnosis device as described in claim 1, wherein the fault condition determination unit determines whether the acquired fault condition is established based on the acquired environmental information when the selected fault case is an environmental cause case, which is a fault case caused by the environment external to the target device, and determines whether the acquired fault condition is established based on sensor data included in the abnormality data when the selected fault case is not an environmental cause case.

3. The fault diagnosis device according to claim 1, comprising an environmental reproduction unit and a fault condition correction unit, wherein the environmental information acquisition unit acquires the environmental information for an abnormal time period when an abnormality occurs in the target device, the environmental reproduction unit uses the environmental information for the abnormal time period to reproduce the behavior of the target device during the abnormal time period to obtain sensor data for the abnormal time period, the fault condition correction unit corrects the acquired fault condition using the sensor data for the abnormal time period, and the fault condition determination unit determines whether the corrected acquired fault condition is established based on the sensor data included in the abnormal data.

4. The fault diagnosis device according to claim 3, wherein the fault condition correction unit updates the acquired fault condition among the fault conditions shown in the fault condition database to the corrected acquired fault condition.

5. The fault diagnosis device according to claim 1, comprising an environment reproduction unit and a fault condition correction unit, wherein the environment reproduction unit uses specified environment information to reproduce the fault behavior of the target device to obtain sensor data at the time of a fault, the fault condition determination unit determines whether a specified fault condition indicated in the fault condition database is satisfied based on the sensor data at the time of a fault, and the fault condition correction unit updates the specified fault condition indicated in the fault condition database based on the determination result for the specified fault condition and the specified environment information.

6. The fault diagnosis device according to claim 1, wherein the fault condition determination unit determines whether the acquired fault condition is satisfied based on the acquired environmental information, determines whether the acquired fault condition is satisfied based on sensor data included in the abnormality data, and registers the acquired environmental information and the determination result in a diagnosis history database.

7. A fault diagnosis method comprising: receiving fault data including fault information of an abnormality occurring in a target device and sensor data acquired by the target device; selecting a fault case associated with the same fault information as the fault information included in the fault data from a fault case database indicating the relationship between fault information of abnormalities that may occur in the target device and fault cases; acquiring a fault condition associated with the same fault case as the selected fault case from a fault condition database indicating the relationship between fault cases and fault conditions; acquiring environmental information of the external environment of the target device; determining whether the acquired fault condition is established based on the acquired environmental information or the sensor data included in the abnormality data; and outputting a diagnostic result indicating information regarding the determination result.

8. A fault diagnosis program for causing a computer to execute the following steps: an abnormality data receiving process for receiving abnormality data including abnormality information of an abnormality occurring in a target device and sensor data acquired by the target device; a fault case selection process for selecting a fault case associated with the same abnormality information as the abnormality information included in the abnormality data from a fault case database indicating the relationship between abnormality information of an abnormality that may occur in the target device and fault cases; a fault condition acquisition process for acquiring a fault condition associated with the same fault case as the selected fault case from a fault condition database indicating the relationship between fault cases and fault conditions; an environmental information acquisition process for acquiring environmental information of the external environment of the target device; a fault condition judgment process for judging whether the acquired fault condition is established based on the acquired environmental information or the sensor data included in the abnormality data; and a diagnostic result output process for outputting a diagnostic result indicating information regarding the judgment result.

9. A fault diagnosis system comprising: a fault case database indicating the relationship between fault cases and abnormality information of abnormalities that may occur in a target device; a fault condition database indicating the relationship between fault cases and fault conditions; an abnormality data receiving unit receiving abnormality data including abnormality information of abnormalities occurring in the target device and sensor data acquired by the target device; a fault case selection unit selecting a fault case associated with the same abnormality information as the abnormality information included in the abnormality data from the fault case database; a fault condition acquisition unit acquiring a fault condition associated with the same fault case as the selected fault case from the fault condition database; an environmental information acquisition unit acquiring environmental information of an environment outside the target device; a fault condition judgment unit judging whether the acquired fault condition is established based on the acquired environmental information or the sensor data included in the abnormality data; and a diagnosis result output unit outputting a diagnosis result indicating information regarding the judgment result.

Images