WO2019207855A1 - 故障予兆診断システム及び故障予兆診断方法 - Google Patents

故障予兆診断システム及び故障予兆診断方法 Download PDF

Info

Publication number
WO2019207855A1
WO2019207855A1 PCT/JP2019/001441 JP2019001441W WO2019207855A1 WO 2019207855 A1 WO2019207855 A1 WO 2019207855A1 JP 2019001441 W JP2019001441 W JP 2019001441W WO 2019207855 A1 WO2019207855 A1 WO 2019207855A1
Authority
WO
WIPO (PCT)
Prior art keywords
operation mode
sensor data
data table
sensor
diagnosis
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2019/001441
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
祥平 藤本
俊之 小高
野口　純司
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Priority to US17/046,317 priority Critical patent/US20210149875A1/en
Priority to EP19791478.1A priority patent/EP3786748A4/en
Priority to CN201980022894.5A priority patent/CN111989629A/zh
Publication of WO2019207855A1 publication Critical patent/WO2019207855A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G06F16/2365—Ensuring data consistency and integrity
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
    • G05B23/0254—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0297—Reconfiguration of monitoring system, e.g. use of virtual sensors; change monitoring method as a response to monitoring results
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
    • G06F11/2252—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using fault dictionaries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
    • G06F11/2257—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using expert systems
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
    • G06F11/2263—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
    • G06F11/2268—Logging of test results
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2282—Tablespace storage structures; Management thereof
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/242—Query formulation
    • G06F16/2433—Query languages
    • G06F16/244—Grouping and aggregation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the present invention relates to a failure sign diagnosis system and a failure sign diagnosis method, and more particularly, to a failure sign diagnosis system and a failure sign diagnosis method capable of diagnosing a machine failure sign in accordance with an operation mode.
  • the failure sign diagnosis in the present invention can also be referred to as failure sign detection or failure prediction.
  • Patent Document 1 describes that a failure prediction system including a machine learning device enables accurate failure prediction according to the situation.
  • Japanese Patent Application Laid-Open No. H10-260260 describes that an abnormality sign diagnosis apparatus diagnoses the presence or absence of an abnormality sign of a mechanical facility with high accuracy.
  • JP 2017-33526 A Japanese Unexamined Patent Publication No. 2016-33778
  • Patent Document 1 there is a description of a system that predicts failure based on sensor data and control software, but multiple models are not explicitly distinguished for each operation mode, and what model was used for diagnosis? Is unclear.
  • patent document 2 has the description about the system which performs a failure sign regarding the mechanical installation in which a predetermined
  • an object of the present invention is to provide a failure sign diagnosis system and a failure sign diagnosis method capable of more accurately diagnosing a machine failure sign.
  • one of the typical failure sign diagnosis systems of the present invention includes an operation sensor data table indicating correspondence between sensor data and the sensor data acquisition time, an operation mode, and an operation time in the operation mode.
  • An operation mode data table indicating the correspondence between the operation sensor data table and the operation data table created by merging the operation mode data table and having sensor data for the operation mode at the same time.
  • the threshold value determined based on the learned and created diagnostic model and the value calculated based on the diagnostic model from the sensor data to be diagnosed are compared in the same operation mode to determine whether or not there is an abnormality.
  • a failure sign of a machine can be diagnosed more accurately in a failure sign diagnosis system and a failure sign diagnosis method. Problems, configurations, and effects other than those described above will be clarified by the following description of embodiments.
  • FIG. 1 is a block diagram showing an embodiment of the failure sign diagnosis system of the present invention.
  • FIG. 2 is a diagram showing an example of processing of the learning / diagnosis system in the failure sign diagnosis system of the present invention.
  • FIG. 3 is a diagram showing an example of an operation mode data output processing flow in the failure sign diagnosis system of the present invention.
  • FIG. 4 is a diagram showing an example of operation sensor data output processing flow in the failure sign diagnosis system of the present invention.
  • FIG. 5 is a diagram showing an example of a data merge processing flow in the failure sign diagnosis system of the present invention.
  • FIG. 6 is a diagram showing an example of an operation mode determination processing flow in the failure sign diagnosis system of the present invention.
  • FIG. 7 is a diagram showing an example of a learning process flow in the failure sign diagnosis system of the present invention.
  • FIG. 8 is a diagram showing an example of a diagnosis process flow in the failure sign diagnosis system of the present invention.
  • FIG. 9 is a diagram showing an example of an abnormality notification processing flow in the failure sign diagnosis system of the present invention.
  • FIG. 10 is a diagram showing an example of an operation mode data table in the failure sign diagnosis system of the present invention.
  • FIG. 11 is a diagram showing an example of an operation sensor data table in the failure sign diagnosis system of the present invention.
  • FIG. 12 is a diagram showing an example of an operation data table in the failure sign diagnosis system of the present invention.
  • FIG. 13 is a diagram showing an example of a diagnosis model table in the failure sign diagnosis system of the present invention.
  • FIG. 14 is a diagram showing an example of a diagnosis result storage table in the failure sign diagnosis system of the present invention.
  • FIG. 15 is a diagram showing an example of an abnormal data table in the failure sign diagnosis system of the present invention.
  • FIG. 1 is a block diagram showing an embodiment of the failure sign diagnosis system of the present invention.
  • the failure sign diagnosis system is a system for diagnosing a failure sign of the industrial machine 1 and includes an operation mode data acquisition unit 4, an operation sensor data acquisition unit 7, a data combination system 10, and a learning / diagnosis system 13. These may be configured independently of each other, or may be configured as a single unit, for example.
  • the industrial machine 1 includes various machines such as a machine tool, a robot, and a machine for welding. There may be a plurality of industrial machines 1. In this case, a failure sign can be diagnosed for each industrial machine.
  • the industrial machine 1 is configured to drive the drive unit 3 under the control of the control unit 2, and for example, a motor, an electromagnetic solenoid, a cylinder (such as hydraulic or pneumatic pressure), an engine, or the like can be applied to the drive unit 3. .
  • the industrial machine 1 includes a sensor that acquires information related to driving of the driving unit 3.
  • Various sensors can be used as the sensor, and examples thereof include a current sensor, a voltage sensor, a vibration sensor, a temperature sensor, a pressure sensor, and a torque sensor.
  • the industrial machine 1 is provided with a device for outputting operation mode information. This may be provided in the control unit 2.
  • the operation mode data acquisition unit 4 includes a control unit 5 and a storage unit 6.
  • the control unit 5 of the operation mode data acquisition unit 4 acquires data (operation mode data) related to the operation mode from the industrial machine 1 (control unit 2 or the like), creates an operation mode data table, and records it in the storage unit 6. At the same time, the information is output to the data combination system 10.
  • the operation mode indicates what kind of operation state the drive unit 3 of the industrial machine 1 is currently driving. For example, in the case of a machine tool, it can be divided into a state in which a work such as cutting is actually performed, a state in which a machining operation is not performed, or a state in which a blade is moving. In addition, for cutting, it is also possible to divide the operation mode for each material, for each shape of a workpiece (for example, a straight line and a curve), for each cutting method, and the like.
  • the operation mode can be divided into various states.
  • it is effective to divide the driving unit 3 according to different modes (operation states). For example, during operation, the state in which the load is applied to the object and the object is not in contact with the object. It is also possible to divide the state into The operation mode is information for distinguishing these types by numbers, letters, symbols, and the like.
  • the operation sensor data acquisition unit 7 includes a control unit 8 and a storage unit 9.
  • the control unit 8 acquires data (operation sensor data) from the above-described sensor of the industrial machine 1, creates an operation sensor data table and records it in the storage unit 9, and outputs the information to the data combination system 10. To do.
  • data from the sensor sensor value
  • the data combination system 10 includes a control unit 11 and a storage unit 12.
  • the control unit 11 combines the operation mode data table from the operation mode data acquisition unit 4 and the operation sensor data table from the operation sensor data acquisition unit 7, performs data merge processing, and creates an operation data table.
  • the operation data table is recorded in the storage unit 12 and the information is output to the learning / diagnosis system 13.
  • the learning / diagnosis system 13 includes a control unit 14 and a storage unit 15.
  • the control unit 14 acquires an operation data table from the data combination system 10 and performs an operation mode determination process, a learning process, a diagnosis process, and an abnormality notification process. Then, the storage unit 15 is recorded with an operation data table, a diagnosis result storage table, a diagnosis model table, an abnormality data table, and diagnosis time data (file).
  • FIG. 2 is a diagram showing an example of processing of the learning / diagnosis system 13 in the failure sign diagnosis system of the present invention. As shown in FIG. 2, the operation mode determination process is performed based on an operation data table. Then, learning processing and diagnosis processing are performed for each operation mode. In this way, it is possible to diagnose a failure sign for each operation mode.
  • FIG. 3 is a diagram showing an example of an operation mode data output processing flow in the failure sign diagnosis system of the present invention.
  • the processing by the control unit 5 (see FIG. 1) of the operation mode data acquisition unit 4 is shown.
  • operation mode data is acquired from each industrial machine 1 (S101).
  • the acquired data is stored in the operation mode data table of each industrial machine 1 (S102).
  • the operation mode data table stores an operation mode for each time (time stamp).
  • the time can be acquired at regular intervals, for example, every second. In this way, an operation mode data table is created for each industrial machine 1.
  • FIG. 4 is a diagram showing an example of an operation sensor data output processing flow in the failure sign diagnosis system of the present invention.
  • the processing here is the processing by the control unit 8 (see FIG. 1) of the operation sensor data acquisition unit 7.
  • operation sensor data is acquired from each industrial machine 1 (S201).
  • the acquired data is stored in the operation sensor data table (S202).
  • sensor values are stored for each time (time stamp).
  • the time can be acquired at the same fixed interval as in FIG. 3, for example, every second. In this way, an operation sensor data table is created for each industrial machine 1.
  • FIG. 5 is a diagram showing an example of a data merge processing flow in the failure sign diagnosis system of the present invention. Here, the processing by the control unit 11 (see FIG. 1) of the data combination system 10 is shown.
  • a process is repeated for the records output by the operation sensor data (S301).
  • the operation sensor data is included in the operation sensor data table output by the operation sensor data acquisition unit 7 and is stored for each time (time stamp).
  • time stamp it is determined whether the time stamps of the operation sensor data and the operation mode data are the same (S302). If it is determined in S302 that the time stamp is the same, the operation sensor data and the operation mode data are merged with the time stamp and stored in the operation data table (S303).
  • the operation data table stores the sensor value, the operation mode, the machine number of the industrial machine 1 and the like for each time stamp. This associates the sensor value with the operation mode.
  • time stamp indicates the time at that time, and can include year, month, date, hour, minute, and second as a specific example.
  • FIG. 6 is a diagram showing an example of an operation mode determination processing flow in the failure sign diagnosis system of the present invention.
  • the processing here is the processing by the control unit 14 (see FIG. 1) of the learning / diagnosis system 13.
  • the machine and period for which the operation mode is to be determined are selected (S401).
  • the number machine is a number machine for each industrial machine 1.
  • As the period all periods may be automatically selected, or a specific period may be manually designated.
  • the operation mode is determined from the value of the operation data table (S402). Since the operation data table includes information on the operation mode, the operation mode for the selected period can be determined.
  • FIG. 7 is a diagram showing an example of a learning process flow in the failure sign diagnosis system of the present invention.
  • the processing here is the processing by the control unit 14 (see FIG. 1) of the learning / diagnosis system 13.
  • an industrial machine number to be learned is selected (S501).
  • all the units may be automatically selected, or any number of units may be selected by the user.
  • the industrial machine 1 in FIG. 1 corresponds to the industrial equipment.
  • a learning target period is selected (S502).
  • the selection here selects a period in which the machine selected in S501 by the user is operating normally.
  • the operation mode to be learned is selected (S503).
  • all the operation modes recorded in the operation data table may be automatically selected for the machine selected in S501.
  • a specific operation mode may be manually selected for the machine selected in S501 by the user.
  • the sensor value is acquired from the operation data table using the machine / period / operation mode to be learned as a key (S504).
  • the learning target machine is selected in S501
  • the learning target period is selected in S502
  • the learning target operation mode is the content selected in S503.
  • the sensor value is sensor data included in the operation data table.
  • the selected sensor value is a sensor value based on the machine, the period, and the operation mode that are operating normally.
  • the diagnosis model is created as a model indicating the range of sensor values that are operating normally for each operation mode in which the target machine is selected.
  • a threshold value is determined based on the learning result (S506).
  • a threshold value for determining an abnormality of processing to be described later is determined for the diagnostic model.
  • the threshold value can be determined by a diagnostic model. That is, the threshold value can specify the boundary between normal and abnormal based on the normal value range specified in the diagnostic model by a suitable method. Moreover, since the diagnostic model is created for each operation mode, an appropriate threshold value corresponding to the operation mode can be determined.
  • a threshold and a diagnostic model storage destination are added to the diagnostic model table using the learned operation mode and machine number as keys (S507).
  • the diagnostic model storage destination can be added to the diagnostic model table. At this time, it is recorded in the diagnostic model table together with the operation mode, machine number, threshold value and the like.
  • FIG. 8 is a diagram showing an example of a diagnosis processing flow in the failure sign diagnosis system of the present invention.
  • the processing here is the processing by the control unit 14 (see FIG. 1) of the learning / diagnosis system 13.
  • an industrial machine number to be diagnosed is selected (S601).
  • the industrial equipment number is selected automatically.
  • the industrial machine 1 in FIG. 1 corresponds to the industrial equipment.
  • the diagnosis time file is a file containing data of the last diagnosis time (date and time) of the target unit.
  • the last diagnosis time acquired here is the last diagnosis time of the target vehicle.
  • the diagnosis time file may not be a file but may be handled as data.
  • the time stamp record after the previous diagnosis time is acquired from the operation data table (S603). Since the last diagnosis time of the previous time is known from the data acquired in S602, data (record) recorded for each subsequent time stamp is acquired.
  • the process of repeating S605 to S611 is performed for the number of acquired records (S604).
  • the number of records is equal to the number of time stamps recorded.
  • the record here is a record of the operation data table.
  • the diagnostic model table is created by the processing of FIG. 7, and is created for each operation mode. Therefore, it is determined whether or not the diagnosis model table includes data in the same operation mode as the operation mode of the record acquired in S603.
  • diagnosis model table has the operation mode data value acquired in S603
  • diagnosis model is acquired from the diagnosis model table using the operation mode data value as a key (S607). That is, if there is a diagnosis model having the same operation mode as the operation mode in the record acquired in S603, the diagnosis model is acquired.
  • the abnormality level threshold here is the threshold determined in S506 of FIG. This threshold is compared with the target sensor data, and diagnosis is performed based on whether the target sensor data is in a normal range or an abnormal range.
  • the comparison here can be performed by comparing the threshold value and a value calculated based on a diagnosis model from sensor data to be diagnosed in the same operation mode.
  • diagnosis result is stored in the diagnosis result table (normal: 0, abnormal: 1) (S609).
  • diagnosis result table information such as time (time stamp), sensor value, operation mode, and machine number is stored together with the diagnosis result.
  • FIG. 9 is a diagram showing an example of an abnormality notification processing flow in the failure sign diagnosis system of the present invention.
  • an email notification is sent to the person in charge at the site (S701), and the data is stored in the abnormality data table (S702).
  • the mail notification to the person in charge may be automatically performed to a mail address registered in advance.
  • the abnormal data table is a table to which only data determined to be abnormal is added, and records the time, operation mode, machine number, and the like. Further, the degree of abnormality may be recorded as necessary.
  • FIG. 10 is a diagram showing an example of an operation mode data table in the failure sign diagnosis system of the present invention.
  • the operation mode data table is a table created by the operation mode data acquisition unit 4 (see FIG. 1). An example of the processing is shown in FIG.
  • the operation mode data table shown in FIG. 10 the number (#), time (time stamp), and operation mode are recorded.
  • the operation modes are indicated by numerals, and are “30” and “45” in the example of the figure. This shows an example in which information on the type of operation mode is represented by numbers. If the numbers are the same, it means the same operation mode. In addition, it is also possible to represent an operation mode with symbols and characters other than numbers.
  • the operation mode data table is created for each industrial machine.
  • FIG. 11 is a diagram showing an example of an operation sensor data table in the failure sign diagnosis system of the present invention.
  • the operation sensor data table is a table created by the operation sensor data acquisition unit 7 (see FIG. 1). An example of the processing is shown in FIG.
  • the operation sensor data table shown in FIG. 11 records the number (#), time (time stamp), sensor A value, sensor B value, and sensor C value.
  • the sensor here shows an example using three sensors, and these numerical values show examples assuming values such as current and voltage. For example, it is possible to diagnose a failure sign from these values by measuring the current and voltage of the motor of the drive unit.
  • the operation sensor data table is created for each industrial machine.
  • FIG. 12 is a diagram showing an example of an operation data table in the failure sign diagnosis system of the present invention.
  • the operation data table is a table created by the data combination system 10 (see FIG. 1). An example of the process is shown in FIG.
  • the operation data table shown in FIG. 12 records number (#), time (time stamp), sensor A value, sensor B value, sensor C value, operation mode, and machine number. These show an example in which the operation mode data table of FIG. 10 and the operation sensor data table of FIG. 11 are combined at the same time (time stamp) of the same machine number. This makes it possible to associate the operation mode with the value of each sensor.
  • the machine number is a number that identifies the industrial machine.
  • FIG. 13 is a diagram showing an example of a diagnosis model table in the failure sign diagnosis system of the present invention.
  • the diagnosis model table is a table created by the learning / diagnosis system 13 (see FIG. 1). An example of the process is shown in FIG.
  • the diagnostic model table of FIG. 13 a number (#), an operation mode, an abnormality threshold, a diagnostic model storage destination, and a machine number are recorded.
  • the diagnostic model is the diagnostic model created in S505.
  • the table of FIG. 13 shows the storage location of the file.
  • the abnormality degree threshold is a threshold determined in S506 in FIG.
  • the diagnostic model table is recorded corresponding to the operation mode.
  • the operation mode distinguishes the state of operation of the industrial machine 1 such that the operation mode “30” is preparation for machining operation and the operation mode “31” is during machining.
  • FIG. 14 is a diagram showing an example of a diagnosis result storage table in the failure sign diagnosis system of the present invention.
  • the diagnosis result storage table is a table created by the learning / diagnosis system 13 (see FIG. 1). An example of the process is shown in FIG.
  • diagnosis result storage table shown in FIG. 14 the number (#), time (time stamp), sensor A value, sensor B value, sensor C value, operation mode, diagnosis result, and unit number are recorded. That is, the diagnosis result storage table of FIG. 14 has a configuration in which diagnosis results are added to the operation mode data table of FIG.
  • the diagnosis result shows an example in which “0” is normal and “1” indicates abnormality.
  • this information is stored in S609.
  • FIG. 15 is a diagram showing an example of an abnormal data table in the failure sign diagnosis system of the present invention.
  • the abnormal data table is a table created by the learning / diagnosis system 13 (see FIG. 1). An example of the processing is shown in FIG.
  • the abnormal data table in FIG. 15 is a table obtained by extracting only values of the diagnostic result “1” (abnormal) from the diagnostic result storage table in FIG.
  • the degree of abnormality indicates the degree of the abnormality value threshold of the diagnostic model table of FIG. 13 with respect to the sensor value of the diagnostic result storage table of FIG. 14, and the degree of abnormality is higher as the value is higher (sensor The value is on the abnormal side of the threshold).
  • the present embodiment it is possible to perform a failure sign diagnosis that matches the operation mode by determining the operation mode of the industrial machine and performing learning processing for each operation mode. Then, by determining that the value of the sensor is abnormal for each operation mode, it is possible to make a diagnosis that predicts a failure of the industrial machine more accurately. Moreover, since a normal state is learned for each operation mode and a diagnosis is performed based on the learned normal state, a more accurate failure sign diagnosis can be performed. In addition, since it becomes clear what diagnostic model is used for each operation mode, it can be applied to the same industrial machine using the same usage method, and it is easy to deploy horizontally. It will be a thing.
  • the present invention is not limited to the above-described embodiment, and includes various modifications.
  • the above-described embodiment has been described in detail for easy understanding of the present invention, and is not necessarily limited to one having all the configurations described.
  • a part of the configuration of an embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of an embodiment.
  • the present invention can be applied not only to industrial machines but also to machines that require failure sign diagnosis.
  • SYMBOLS 1 ... Industrial machine, 2 ... Control part, 3 ... Drive part, 4 ... Operation mode data acquisition part, 5 ... Control part, 6 ... Storage part, 7 ... Operation sensor data acquisition part, 8 ... Control part, 9 ... Storage part DESCRIPTION OF SYMBOLS 10 ... Data connection system, 11 ... Control part, 12 ... Memory

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Automation & Control Theory (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Testing And Monitoring For Control Systems (AREA)
PCT/JP2019/001441 2018-04-23 2019-01-18 故障予兆診断システム及び故障予兆診断方法 Ceased WO2019207855A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/046,317 US20210149875A1 (en) 2018-04-23 2019-01-18 Fault indicator diagnostic system and fault indicator diagnostic method
EP19791478.1A EP3786748A4 (en) 2019-01-18 Fault indicator diagnostic system and fault indicator diagnostic method
CN201980022894.5A CN111989629A (zh) 2018-04-23 2019-01-18 故障预兆诊断系统以及故障预兆诊断方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2018082178A JP2019191799A (ja) 2018-04-23 2018-04-23 故障予兆診断システム及び故障予兆診断方法
JP2018-082178 2018-04-23

Publications (1)

Publication Number Publication Date
WO2019207855A1 true WO2019207855A1 (ja) 2019-10-31

Family

ID=68294461

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/001441 Ceased WO2019207855A1 (ja) 2018-04-23 2019-01-18 故障予兆診断システム及び故障予兆診断方法

Country Status (4)

Country Link
US (1) US20210149875A1 (enExample)
JP (1) JP2019191799A (enExample)
CN (1) CN111989629A (enExample)
WO (1) WO2019207855A1 (enExample)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7660292B2 (ja) * 2021-06-14 2025-04-11 パナソニックＩｐマネジメント株式会社 劣化判定方法及び装置
DE112021007486T5 (de) * 2021-06-21 2024-02-01 Fanuc Corporation Vorrichtung zur verarbeitung von auffälligkeiten, netzwerksystem und verfahren zur bereitstellung einer methode in bezug auf aufgetretene auffälligkeiten in einem robotersystem
JP2024034459A (ja) * 2022-08-31 2024-03-13 株式会社日立産機システム 予兆検知システム及び予兆検知方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001217169A (ja) * 1999-11-26 2001-08-10 Matsushita Electric Ind Co Ltd データ変動監視方法と監視装置
JP2001306140A (ja) * 2000-04-26 2001-11-02 Howa Mach Ltd 異常検出システム
JP2007165721A (ja) * 2005-12-15 2007-06-28 Omron Corp プロセス異常分析装置及びプログラム
JP2016033778A (ja) 2014-07-31 2016-03-10 株式会社日立パワーソリューションズ 異常予兆診断装置及び異常予兆診断方法
JP2017033526A (ja) 2015-07-31 2017-02-09 ファナック株式会社 故障条件を学習する機械学習方法及び機械学習装置、並びに該機械学習装置を備えた故障予知装置及び故障予知システム
JP2017120622A (ja) * 2015-12-25 2017-07-06 株式会社リコー 診断装置、診断方法、プログラムおよび診断システム
JP2018018507A (ja) * 2016-07-15 2018-02-01 株式会社リコー 診断装置、プログラムおよび診断システム

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6917839B2 (en) * 2000-06-09 2005-07-12 Intellectual Assets Llc Surveillance system and method having an operating mode partitioned fault classification model
US7233886B2 (en) * 2001-01-19 2007-06-19 Smartsignal Corporation Adaptive modeling of changed states in predictive condition monitoring
IN2013DE02965A (enExample) * 2013-10-04 2015-04-10 Samsung India Electronics Pvt Ltd
JP6234359B2 (ja) * 2014-12-15 2017-11-22 日立建機株式会社 作業機械のオイル性状の診断システム
JP6154523B1 (ja) * 2016-07-05 2017-06-28 山本 隆義 対象物の状態変化の原因探索方法
US10739764B2 (en) * 2016-07-15 2020-08-11 Ricoh Company, Ltd. Diagnostic apparatus, diagnostic system, diagnostic method, and recording medium
JP6862130B2 (ja) * 2016-09-08 2021-04-21 株式会社東芝 異常検知装置、異常検知方法、およびプログラム

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001217169A (ja) * 1999-11-26 2001-08-10 Matsushita Electric Ind Co Ltd データ変動監視方法と監視装置
JP2001306140A (ja) * 2000-04-26 2001-11-02 Howa Mach Ltd 異常検出システム
JP2007165721A (ja) * 2005-12-15 2007-06-28 Omron Corp プロセス異常分析装置及びプログラム
JP2016033778A (ja) 2014-07-31 2016-03-10 株式会社日立パワーソリューションズ 異常予兆診断装置及び異常予兆診断方法
JP2017033526A (ja) 2015-07-31 2017-02-09 ファナック株式会社 故障条件を学習する機械学習方法及び機械学習装置、並びに該機械学習装置を備えた故障予知装置及び故障予知システム
JP2017120622A (ja) * 2015-12-25 2017-07-06 株式会社リコー 診断装置、診断方法、プログラムおよび診断システム
JP2018018507A (ja) * 2016-07-15 2018-02-01 株式会社リコー 診断装置、プログラムおよび診断システム

Also Published As

Publication number Publication date
EP3786748A1 (en) 2021-03-03
US20210149875A1 (en) 2021-05-20
CN111989629A (zh) 2020-11-24
JP2019191799A (ja) 2019-10-31

Similar Documents

Publication Publication Date Title
JP6426667B2 (ja) 工作機械の工具の異常検知装置及び方法
KR102407484B1 (ko) 정보 처리 방법, 정보 처리 시스템, 및 정보 처리 장치
JP6140331B1 (ja) 主軸または主軸を駆動するモータの故障予知を学習する機械学習装置および機械学習方法、並びに、機械学習装置を備えた故障予知装置および故障予知システム
JP6340236B2 (ja) 工作機械の診断方法及びシステム
EP3349949B1 (en) Actuator diagnostics and prognostics
US20200198128A1 (en) Learning data confirmation support device, machine learning device, and failure predicting device
JP2018103284A (ja) 工具寿命推定装置
WO2019207855A1 (ja) 故障予兆診断システム及び故障予兆診断方法
JP7079420B2 (ja) 異常診断装置及び異常診断方法
CN102441817A (zh) 工作历史管理方法以及工作历史管理装置
JP2005221258A (ja) エンコーダ
JP7185247B2 (ja) 機械の診断システム及び診断プログラム
DE102019104244A1 (de) Abnormalitätsfaktoridentifizierungsgerät
JP7154100B2 (ja) 工作機械の加工異常検出装置
CN105320064A (zh) 具有设备异常履历的解析支援功能的数值控制装置
JP5268637B2 (ja) 生産機械のための評価装置の動作方法
CN111857050B (zh) 机床的数值控制系统
JP5243695B2 (ja) 加工器具用の装置の検査方法
US10955837B2 (en) Method and system for error detection and monitoring for an electronically closed-loop or open-loop controlled machine part
CN104111626B (zh) 用于监控至少一个机床的方法
JP2005148873A (ja) ロボット劣化診断装置
JP2024062242A (ja) 加工異常診断のための情報更新装置及び情報更新方法
CN110165969B (zh) 机床的控制装置
US20250068140A1 (en) Diagnostic device
WO2024176390A1 (ja) データ分割装置、及びコンピュータ読み取り可能な記録媒体

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19791478

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019791478

Country of ref document: EP

Effective date: 20201123