WO2022085350A1 - 異常診断モデルの構築方法、異常診断方法、異常診断モデルの構築装置および異常診断装置 - Google Patents
異常診断モデルの構築方法、異常診断方法、異常診断モデルの構築装置および異常診断装置 Download PDFInfo
- Publication number
- WO2022085350A1 WO2022085350A1 PCT/JP2021/034601 JP2021034601W WO2022085350A1 WO 2022085350 A1 WO2022085350 A1 WO 2022085350A1 JP 2021034601 W JP2021034601 W JP 2021034601W WO 2022085350 A1 WO2022085350 A1 WO 2022085350A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- abnormality
- abnormality diagnosis
- diagnosis
- model
- relationship
- Prior art date
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 257
- 238000003745 diagnosis Methods 0.000 title claims abstract description 227
- 238000000034 method Methods 0.000 title claims abstract description 72
- 230000008569 process Effects 0.000 claims abstract description 21
- 239000007769 metal material Substances 0.000 claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000005096 rolling process Methods 0.000 claims description 56
- 239000000463 material Substances 0.000 claims description 39
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 description 19
- 238000013459 approach Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 229910000831 Steel Inorganic materials 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 239000010959 steel Substances 0.000 description 6
- 238000002405 diagnostic procedure Methods 0.000 description 5
- 239000000047 product Substances 0.000 description 5
- 238000005520 cutting process Methods 0.000 description 3
- 239000012467 final product Substances 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000005445 natural material Substances 0.000 description 1
- 238000010238 partial least squares regression Methods 0.000 description 1
- 238000012628 principal component regression Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/20—Metals
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B38/00—Methods or devices for measuring, detecting or monitoring specially adapted for metal-rolling mills, e.g. position detection, inspection of the product
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
- B21B37/70—Length control
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- 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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
-
- 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32356—For diagnostics
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/33—Director till display
- G05B2219/33295—Fuzzy expert system for diagnostic, monitoring
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/33—Director till display
- G05B2219/33296—ANN for diagnostic, monitoring
Definitions
- the present invention relates to an abnormality diagnosis model construction method, an abnormality diagnosis method, an abnormality diagnosis model construction device, and an abnormality diagnosis device.
- the model-based approach is an approach in which a model expressing a physical or chemical phenomenon in a manufacturing process is constructed by a mathematical formula, and the manufacturing state of the manufacturing process is diagnosed using the constructed model.
- the database approach is an approach in which a statistical analysis model is constructed from the operation data obtained in the manufacturing process, and the manufacturing state of the manufacturing process is diagnosed using the constructed model.
- Patent Documents 1 to 4 describe a method of predicting or detecting an abnormal state of a manufacturing process based on a prediction by a model created using normal operation data. Further, in Patent Documents 3 and 4, patterns are extracted from normal operation data and made into a library, and the difference between the acquired operation data and the library pattern is determined to detect a situation different from usual at an early stage. How to do it is described.
- the present invention has been made in view of the above, and by detecting an abnormal state from a large amount of measured values acquired in a manufacturing process and classifying and selecting a large number of candidates for causes of abnormalities that do not have a one-to-one correspondence. It is an object of the present invention to provide a method for constructing an abnormality diagnosis model, an abnormality diagnosis method, a device for constructing an abnormality diagnosis model, and an abnormality diagnosis device capable of investigating the cause of an abnormality at an early stage.
- the method for constructing an abnormality diagnosis model is a method for constructing an abnormality diagnosis model for a process of sequentially processing a metal material in a plurality of facilities.
- the model creation step of the above and the measured values measured for the plurality of facilities are edited for each position of the metal material, and the measured values for the same position of the metal material are used to obtain the measured values and abnormalities at the same position.
- a second model creation step which creates a second anomaly diagnostic model trained in relation to.
- the metal material is a rolled material and the equipment is a rolling mill.
- the measured values at the same position are the total length of the rolled material on the exit side of the final rolling mill and the exit side of the rolling mill other than the final. It is calculated by converting the position of the rolled material on the exit side of the rolling mill other than the final one based on the ratio with the total length of the rolled material.
- the total length of the rolled material on the outlet side of the rolling mill is based on the roll speed and the advanced rate of the rolling mill and the passing speed of the rolled material. Is calculated, and the plate passing speed is calculated by time integration.
- the abnormality diagnosis method is an abnormality diagnosis method using the abnormality diagnosis model constructed by the above-mentioned abnormality diagnosis model construction method.
- the first abnormality diagnosis step for performing abnormality diagnosis and the second abnormality diagnosis model at the same position.
- the second abnormality diagnosis step for performing an abnormality diagnosis the diagnosis result in the first abnormality diagnosis step, and the diagnosis result in the second abnormality diagnosis step
- an anomaly determination step to determine the cause of the anomaly based on.
- the abnormality determination step is based on the abnormality diagnosis table showing the cause of the abnormality by associating the first diagnosis result with the second diagnosis result. Determine the cause of the abnormality.
- the abnormality diagnosis model construction device is a plurality of abnormality diagnosis model construction devices for a process of sequentially processing a metal material with a plurality of facilities.
- the model creation means of the above and the measured values measured for the plurality of facilities are edited for each position of the metal material, and the measured values for the same position of the metal material are used to obtain the measured values and abnormalities at the same position. It is provided with a second model creation means for creating a second abnormality diagnosis model trained in the relationship with.
- the abnormality diagnosis device is an abnormality diagnosis device using the abnormality diagnosis model constructed by the above-mentioned abnormality diagnosis model construction device.
- the first abnormality diagnosis means for performing abnormality diagnosis and the second abnormality diagnosis model at the same position.
- the second abnormality diagnosis means for performing an abnormality diagnosis the diagnosis result in the first abnormality diagnosis means, and the diagnosis result in the second abnormality diagnosis means Based on this, an abnormality determining means for determining the cause of the abnormality is provided.
- the method for constructing an abnormality diagnosis model, the method for diagnosing an abnormality, the device for constructing an abnormality diagnosis model, and the abnormality diagnosis device according to the present invention can be used for abnormalities in the machine / control system of equipment and products by constructing two types of abnormality diagnosis models. It is possible to distinguish between abnormalities caused by the quality and shape of the product. Therefore, the cause of the abnormality can be investigated at an early stage, the downtime of the equipment can be reduced, and efficient and effective countermeasures against the abnormality can be achieved.
- FIG. 1 is a diagram showing a schematic configuration of an abnormality diagnosis device and a model building device according to an embodiment of the present invention.
- FIG. 2 is a flowchart showing a procedure for creating time-related data in the abnormality diagnosis device and the model building device according to the embodiment of the present invention.
- FIG. 3 is a flowchart showing a procedure for creating the same positional relationship data in the abnormality diagnosis device and the model building device according to the embodiment of the present invention.
- FIG. 4 is a flowchart showing a procedure of an abnormality diagnosis method executed by the abnormality diagnosis apparatus according to the embodiment of the present invention.
- model construction device the configuration of the abnormality diagnosis device and the abnormality diagnosis model construction device (hereinafter referred to as “model construction device”) according to the embodiment of the present invention will be described with reference to FIG.
- Abnormality diagnostic equipment and model building equipment are applied to the process of sequentially processing metallic materials in multiple facilities.
- an example applied to a rolling process in which rolled materials such as steel plates are sequentially rolled by a plurality of rolling mills will be described.
- the rolling mill is also referred to as a "stand”.
- the abnormality diagnosis device 1 includes an input unit 10, a storage unit 20, a calculation unit 30, and a display unit 40.
- the "model construction device” is realized by the components excluding the abnormality determination table 25, the same time relationship diagnosis unit 34, the same position relationship diagnosis unit 35, and the abnormality determination unit 36 among the components of the abnormality diagnosis device 1. To.
- the input unit 10 is an input means for the calculation unit 30, receives actual operation data (time series data) of the equipment to be diagnosed via the information / control system network, and inputs the data to the calculation unit 30 in a predetermined format.
- the storage unit 20 is composed of a recording medium such as an EPROM (Erasable Programmable ROM), a hard disk drive (Hard Disk Drive: HDD), and a removable medium.
- a recording medium such as an EPROM (Erasable Programmable ROM), a hard disk drive (Hard Disk Drive: HDD), and a removable medium.
- the removable medium include a disc recording medium such as a USB (Universal Serial Bus) memory, a CD (Compact Disc), a DVD (Digital Versatile Disc), and a BD (Blu-ray (registered trademark) Disc).
- the storage unit 20 can store an operating system (Operating System: OS), various programs, various tables, various databases, and the like.
- OS Operating System
- the same time relationship data definition table 21 the same position relationship data definition table 22, the same time relationship diagnosis model (first abnormality diagnosis model) 23, and the same position relationship diagnosis model (second abnormality diagnosis model) 24 and the abnormality determination table 25 are stored.
- the same time relationship data definition table 21 is a table in which settings necessary for creating the same time relationship data by the same time relationship data creation unit 31 are described.
- the same time relationship data definition table 21 is, for example, a table as shown in Table 1 below.
- the same positional relationship data definition table 22 is a table in which the settings necessary for creating the same positional relationship data by the same positional relationship data creation unit 32 are described.
- the co-positional relationship data definition table 22 is, for example, a table as shown in Table 2 below.
- the same time relationship diagnosis model 23 is a model referred to in the abnormality diagnosis process of the same time relationship data by the same time relationship diagnosis unit 34.
- the same-time relationship diagnosis model 23 is a trained model in which the relationship between the measured value at the same time and the abnormality is learned, and is created by the model creation unit 33 described later.
- the same positional relationship diagnosis model 24 is a model referred to in the abnormality diagnosis process of the same positional relationship data by the same positional relationship diagnosis unit 35.
- the same-position relationship diagnosis model 24 is a trained model in which the relationship between the measured value at the same position and the abnormality is learned, and is created by the model creation unit 33 described later.
- the abnormality determination table 25 is a table referred to in the abnormality determination process by the abnormality determination unit 36.
- the abnormality determination table 25 is created based on examples of past operations, and is composed of a classification table of causes of abnormalities, for example, as shown in Table 3 below.
- the abnormality determination table 25 shown in Table 3 has information regarding the following in order from the left column. (1) Items observed as abnormalities, causes of abnormalities when abnormalities are determined from the same time-related data (2) Causes of abnormalities when abnormalities are determined from the same positional relationship data (3) Same time-related data and the same Cause of abnormality when abnormality is judged from positional relationship data
- the abnormality determination unit 36 performs differential load and rolling. It is determined that the causes of the abnormal load and tension between stands are as follows.
- the abnormality diagnosis device 1 there are concerns about cases where an abnormality is detected from the same time relationship data, an abnormality is detected from the same positional relationship data, and an abnormality is detected from both data.
- the cause of the abnormality is prepared in advance as the abnormality determination table 25. Then, in the abnormality determination process, the cause of the abnormality is classified by referring to the abnormality determination table 25.
- the arithmetic unit 30 is realized by, for example, a processor composed of a CPU (Central Processing Unit) or the like, and a memory (main storage unit) composed of a RAM (Random Access Memory), a ROM (Read Only Memory), or the like.
- a processor composed of a CPU (Central Processing Unit) or the like
- a memory main storage unit
- RAM Random Access Memory
- ROM Read Only Memory
- the arithmetic unit 30 loads the program into the work area of the main storage unit and executes it, and controls each component unit or the like through the execution of the program to realize a function that meets a predetermined purpose.
- the calculation unit 30 functions as the same time relationship data creation unit 31, the same positional relationship data creation unit 32, and the model creation unit (first and second model creation means) 33 through the execution of the above-mentioned program. Further, the calculation unit 30 has the same time relationship diagnosis unit (first abnormality diagnosis means) 34, the same position relationship diagnosis unit (second abnormality diagnosis means) 35, and the abnormality determination unit (abnormality determination) through the execution of the above-mentioned program.
- Means Functions as 36. Note that FIG. 1 shows an example in which the functions of each part are realized by, for example, one computer, but the means for realizing the functions of each part is not particularly limited, and even if the functions of each part are realized by a plurality of computers, for example. good.
- the same time relationship data creation unit 31 processes the time series data input from the input unit 10 and creates the same time relationship data showing the relationship between the measured values at the same time. Specifically, the same-time-related data creation unit 31 creates the same-time-related data with reference to the same-time-related data definition table 21. In addition, the same time relationship data creation unit 31 has two situations, one is when the same time relationship diagnosis model 23 is created offline and the other is when the same time relationship diagnosis model 23 is used to perform an abnormality diagnosis online (during operation). Create time-related data.
- an example of a method of creating the same time-related data will be described with reference to FIG.
- the same time-related data creation unit 31 searches for the rolling start time of the start stand that determines the start of the abnormality diagnosis and the rolling end time of the final stand that determines the end of the abnormality diagnosis from the time-series data related to the actual operation (Stes S1 and S2).
- steps S1 and S2 for example, in the case of a finishing continuous rolling mill composed of 7 stands, the F7 stand is defined as a start stand and the F1 stand is defined as an end stand, so that the rolling material (coil) being rolled in all stands is steady. It is possible to extract the same time-related data for the parts.
- the same time relation data creation unit 31 creates the same time relation data by cutting out the rolling data (sensor data) of each stand between the searched start time and the end time (step S3) (step S3). Step S4).
- the same position relationship data creation unit 32 processes the time series data input from the input unit 10 and creates the same position relationship data showing the relationship between the measured values at the same position. Specifically, the same positional relationship data creation unit 32 creates the same positional relationship data with reference to the same positional relationship data definition table 22. Further, the same positional relationship data creation unit 321 can be used in two situations: when the same positional relationship diagnosis model 24 is created offline and when the same positional relationship diagnosis model 24 is used to perform an abnormality diagnosis online (during operation). Create co-positional data.
- an example of a method of creating the same positional relationship data will be described with reference to FIG.
- the same positional relationship data creation unit 32 searches for the rolling start time and the rolling end time of each stand to be diagnosed from the time-series data related to the actual operation (steps S11 and S12). Subsequently, the same positional relationship data creation unit 32 cuts out the rolling data (sensor data), rolling speed (mill speed), and advanced rate data of the target stand between the searched start time and the end time (step). S13, S14).
- the same positional relationship data creation unit 32 calculates the total length of the rolled material at each stand (the total length of the rolled material on the output side of each rolling mill) from the cut out data (step S15). For example, if the rolling start time of the i -th stand is ti0 , the advanced rate at time t is fi (t), and the rolling speed of the rolled material (hereinafter referred to as "rolling speed") is vi (t).
- the position Li (t) of the data acquired in t from the tip of the rolled material can be expressed by the following equation (1).
- the plate passing speed of the rolled material can be calculated from the roll speed of the rolling mill and the advanced rate.
- the same positional relationship data creation unit 32 sets the standard of the length of the rolled material to the final product, that is, the final coil length. Then, based on the ratio of the total length of the rolled material on the output side of the final stand to the total length of the rolled material on the output side of the target stand (stand other than the final stand), the rolled material on the output side of the target rolling mill Convert the position (step S16). As a result, the same positional relationship data is created (step S17).
- the obtained data is not evenly spaced data when viewed in terms of the total length of the rolled material. Therefore, in this case, it is necessary to obtain equidistant equidistant data by performing interpolation processing.
- interpolation method at that time for example, linear interpolation can be used when focusing on two adjacent points, and spline interpolation or the like can be used when focusing on three or more points.
- the total length of the rolled material is integrated by time-integrating the rolling speed of the rolled material calculated from the roll speed of the rolling mill and the advanced rate. Is calculated. Then, based on the ratio of the total length of the rolled material similarly calculated from the final stand to the total length of the rolled material at the target stand, data regarding the position of the target stand in the rolling direction corresponding to the exit side of the final stand. To create. This makes it possible to edit the data measured at different stands into data related to the position in the rolling direction from the tip of the final product.
- the model creation unit 33 uses the measured values measured at the same time in a predetermined measurement cycle for a plurality of rolling mills to learn the relationship between the measured values at the same time and the abnormality.
- the diagnostic model 23 is created.
- the above-mentioned "measured value” indicates the same time-related data created by the same-time-related data creation unit 31.
- model creation unit 33 uses the measured values for each position of the rolled material, in which the measured values measured for the plurality of rolling mills are edited for each position of the rolled material, and is abnormal with the measured values at the same position.
- the same positional relationship diagnostic model 24 is created so that the relationship with the rolling mill is learned.
- the above "measured value” indicates the same positional relationship data created by the same time relationship data creation unit 31.
- the model creation method in the model creation unit 33 is not particularly limited. As a model creation method, it is possible to use a method of detecting anomalies from the magnitude of the discrepancy between the estimated amount derived by the regression model and the actual amount, a method of detecting anomalies from the restoration error by a generative model such as an autoencoder, and the like. .. Examples of the former method include linear regression, local regression, Lasso regression, Ridge regression, principal component regression, PLS regression, neural network, regression tree, random forest, XGBoost, and the like. Further, the model creation unit 33 stores the created same-time relationship diagnosis model 23 and the same position relationship diagnosis model 24 in the storage unit 20, respectively.
- the same time relationship diagnosis unit 34 performs abnormality diagnosis using the same time relationship diagnosis model 23.
- the same time relationship diagnosis unit 34 performs an abnormality diagnosis by inputting the same time relationship data created by the same time relationship data creation unit 31 into the same time relationship diagnosis model 23.
- the abnormality diagnosis result by the same time relationship diagnosis unit 34 is an item observed as an abnormality, for example, "differential load: abnormal / none, rolling load: abnormal / none, tension between stands: abnormal / none" ( The information is a combination of (see the left column of Table 3) and the presence or absence of an abnormality in the item. Further, in the abnormality diagnosis by the time-related diagnosis unit 34, it is possible to mainly detect an abnormality in the machine / control system of the equipment.
- the same positional relationship diagnosis unit 35 performs abnormality diagnosis using the same positional relationship diagnosis model 24.
- the same positional relationship diagnosis unit 35 performs an abnormality diagnosis by inputting the same positional relationship data created by the same positional relationship data creation unit 32 into the same positional relationship diagnosis model 24.
- the abnormality diagnosis result by the same positional relationship diagnosis unit 35 is an item observed as an abnormality, for example, "differential load: abnormal / none, rolling load: abnormal / none, tension between stands: abnormal / none" ( The information is a combination of (see Table 3) and the presence or absence of abnormality in the item. Further, in the abnormality diagnosis by the same positional relationship diagnosis unit 35, it is possible to detect an abnormality mainly caused by the quality and shape of the product.
- the abnormality determination unit 36 determines the cause of the abnormality based on the diagnosis result (first diagnosis result) in the same time relationship diagnosis unit 34 and the diagnosis result (second diagnosis result) in the same position relationship diagnosis unit 35. do.
- the abnormality determination unit 36 determines the cause of the abnormality based on the abnormality determination table 25 indicating the cause of the abnormality by associating the diagnosis result of the same time relationship diagnosis unit 34 with the diagnosis result of the same positional relationship diagnosis unit 35.
- the abnormality determination unit 36 determines the presence or absence of an abnormality based on the diagnosis results of the same time relationship diagnosis unit 34 and the same position relationship diagnosis unit 35. Subsequently, the abnormality determination unit 36 classifies the cause of the abnormality by comparing the diagnosis results of the same time relationship diagnosis unit 34 and the same position relationship diagnosis unit 35 with the abnormality determination table 25 (see Table 3). Then, the abnormality determination unit 36 outputs these determination results to the display unit 40.
- the display unit 40 is realized by a display device such as an LCD display or a CRT display. Based on the display signal input from the calculation unit 30, the display unit 40 displays, for example, a diagnosis result in the same time relationship diagnosis unit 34, a diagnosis result in the same position relationship diagnosis unit 35, a determination result in the abnormality determination unit 36, and the like. Guidance is given to the operator by displaying.
- abnormality diagnosis method The abnormality diagnosis method by the abnormality diagnosis device 1 according to the embodiment of the present invention will be described with reference to FIG.
- the abnormality diagnosis method is carried out every time the rolling of one rolled material is completed in the rolling process.
- step S21 determines whether or not the rolling of the rolled material has been completed.
- step S21 whether or not the rolling of the rolled material is completed can be determined based on, for example, a winding completion signal of the equipment for winding the rolled material.
- the same time relationship data creation unit 31 and the same position relationship data creation unit 32 return to step S1.
- step S21 when it is determined that the rolling of the rolled material is completed (Yes in step S21), the same time relationship data creation unit 31 and the same position relationship data creation unit 32 transition from the event waiting state to the diagnostic process, and actually Collect time-series data related to the operation (step S22).
- the same time relation data creation unit 31 creates the same time relation data with reference to the same time relation data definition table 21 (step S23).
- the procedure for creating the same time-related data in step S23 is the same as in FIG.
- the same positional relationship data creation unit 32 creates the same positional relationship data with reference to the same positional relationship data definition table 22 (step S24).
- the procedure for creating the same positional relationship data in step S24 is the same as in FIG. In steps S23 and S24, either may be performed first, or both may be performed at the same time.
- step S25 diagnosis is performed using the abnormality diagnosis model.
- the same time relationship diagnosis unit 34 performs an abnormality diagnosis process of the same time relationship data
- the same position relationship diagnosis unit 35 performs an abnormality diagnosis process of the same position relationship data.
- the abnormality determination unit 36 determines the presence or absence of an abnormality based on the two diagnosis results in step S25 (step S26). In step S26, the abnormality determination unit 36 determines that there is an abnormality, for example, when any of the two diagnosis results in step S25 includes the item “abnormal”.
- the abnormality determination unit 36 classifies the cause of the abnormality with reference to the abnormality determination table 25 (see Table 3) (step S27). Subsequently, the abnormality determination unit 36 provides guidance to the operator by displaying the abnormality classification result, that is, the candidate of the cause of the abnormality on the display unit 40 (step S28). Then, the abnormality determination unit 36 ends this process and transitions to the initial state of waiting for an event. If it is determined in step S26 that there is no abnormality (No in step S26), the abnormality determination unit 36 ends this process and transitions to the initial state of waiting for an event.
- abnormality diagnosis model construction method abnormality diagnosis method, abnormality diagnosis model construction device, and abnormality diagnosis device 1 according to the embodiment, the following processing is performed in the steel rolling process.
- information on the position in the rolling direction from the tip of the rolled material is added to the time-series data measured by a sensor or the like from the rolling mill in operation.
- two types of data groups are created, one is data showing the relationship between the measured values at the same position and the other is the data showing the relationship between the measured values at the same time, and two types of abnormality diagnosis models are constructed.
- the method for constructing the abnormality diagnosis model, the method for diagnosing the abnormality, the apparatus for constructing the abnormality diagnosis model, and the abnormality diagnosis apparatus 1 according to the present invention have been specifically described with reference to the embodiments and examples for carrying out the invention.
- the gist of the present invention is not limited to these statements, and must be broadly interpreted based on the statements of the claims. Needless to say, various changes, modifications, etc. based on these descriptions are also included in the gist of the present invention.
- abnormality diagnosis is performed using two types of abnormality diagnosis models (same time relationship diagnosis model 23 and same position relationship diagnosis model 24), but one of them is diagnosed.
- the anomaly diagnosis may be made first using only the model. Then, if necessary, the abnormality diagnosis by the other abnormality diagnosis model may be performed.
- abnormality diagnosis device 1 an example applied to the rolling process has been described, but it can be applied not only to the rolling process but also to, for example, a surface treatment process.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Control Of Metal Rolling (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Description
まず、本発明の実施形態に係る異常診断装置および異常診断モデルの構築装置(以下、「モデル構築装置」という)の構成について、図1を参照しながら説明する。異常診断装置およびモデル構築装置は、金属材料を複数の設備で順次処理するプロセスに適用される。本実施形態では、鋼板等の圧延材を複数の圧延機によって順次圧延する圧延プロセスに適用した例について説明する。なお、以下の説明では、圧延機のことを「スタンド」とも表記する。
(1)切り出しの開始および終了のタイミングを指示する信号
(2)信号が属するミル(圧延機)のロール速度を指示する信号
(3)信号が属するミルの先進率を指示する信号
(1)異常として観測される項目、同時刻関係データから異常判定される場合の異常の原因
(2)同位置関係データから異常判定される場合の異常の原因
(3)同時刻関係データおよび同位置関係データから異常判定される場合の異常の原因
同時刻関係データの異常診断処理の結果:「差荷重:異常あり、圧延荷重:異常あり、スタンド間張力:異常なし」
同位置関係データの異常診断処理の結果:「差荷重:異常あり、圧延荷重:異常なし、スタンド間張力:異常あり」
差荷重の異常の原因:「圧力計不良」
圧延荷重の異常の原因:「圧下保障制御過不足」
スタンド間張力の異常の原因:「板厚過変動」
本発明の実施形態に係る異常診断装置1による異常診断方法について、図4を参照しながら説明する。なお、異常診断方法は、圧延プロセスにおいて、一本の圧延材の圧延が終了するごとに実施される。
10 入力部
20 記憶部
21 同時刻関係データ定義テーブル
22 同位置関係データ定義テーブル
23 同時刻関係診断モデル
24 同位置関係診断モデル
30 演算部
31 同時刻関係データ作成部
32 同位置関係データ作成部
33 モデル作成部
34 同時刻関係診断部
35 同位置関係診断部
36 異常判定部
40 表示部
Claims (8)
- 金属材料を複数の設備で順次処理するプロセスの異常診断モデルの構築方法であって、
前記複数の設備について、予め定めた所定の計測周期で同時刻に計測された計測値を利用して、同時刻の計測値と異常との関係を学習させた第一の異常診断モデルを作成する第一のモデル作成ステップと、
前記複数の設備について計測された計測値が前記金属材料の位置ごとに編集された、前記金属材料の同じ位置ごとの計測値を利用して、同位置の計測値と異常との関係を学習させた第二の異常診断モデルを作成する第二のモデル作成ステップと、
を含む異常診断モデルの構築方法。 - 前記金属材料は、圧延材であり、
前記設備は、圧延機である、
請求項1に記載の異常診断モデルの構築方法。 - 前記同位置の計測値は、最終の圧延機の出側における前記圧延材の全長と、最終以外の圧延機の出側における前記圧延材の全長との比に基づいて、前記最終以外の圧延機の出側における前記圧延材の位置を換算することにより算出される、
請求項2に記載の異常診断モデルの構築方法。 - 前記圧延機の出側における前記圧延材の全長は、前記圧延機のロール速度と先進率とから前記圧延材の通板速度を算出し、前記通板速度を時間積分することにより算出される、
請求項3に記載の異常診断モデルの構築方法。 - 請求項1から請求項4のいずれか一項に記載の異常診断モデルの構築方法によって構築された異常診断モデルを用いた異常診断方法であって、
第一の異常診断モデルに対して、同時刻の計測値間の関係を示すデータを入力することにより、異常診断を行う第一の異常診断ステップと、
第二の異常診断モデルに対して、同位置の計測値間の関係を示すデータを入力することにより、異常診断を行う第二の異常診断ステップと、
前記第一の異常診断ステップにおける第一の診断結果と、前記第二の異常診断ステップにおける第二の診断結果とに基づいて、異常の原因を判定する異常判定ステップと、
を含む異常診断方法。 - 前記異常判定ステップは、前記第一の診断結果と前記第二の診断結果とを関連づけて異常の原因を示す異常診断テーブルに基づいて、異常の原因を判定する請求項5に記載の異常診断方法。
- 金属材料を複数の設備で順次処理するプロセスの異常診断モデルの構築装置であって、
前記複数の設備について、予め定めた所定の計測周期で同時刻に計測された計測値を利用して、同時刻の計測値と異常との関係を学習させた第一の異常診断モデルを作成する第一のモデル作成手段と、
前記複数の設備について計測された計測値が前記金属材料の位置ごとに編集された、前記金属材料の同じ位置ごとの計測値を利用して、同位置の計測値と異常との関係を学習させた第二の異常診断モデルを作成する第二のモデル作成手段と、
を備える異常診断モデルの構築装置。 - 請求項7に記載の異常診断モデルの構築装置によって構築された異常診断モデルを用いた異常診断装置であって、
第一の異常診断モデルに対して、同時刻の計測値間の関係を示すデータを入力することにより、異常診断を行う第一の異常診断手段と、
第二の異常診断モデルに対して、同位置の計測値間の関係を示すデータを入力することにより、異常診断を行う第二の異常診断手段と、
前記第一の異常診断手段における診断結果と、前記第二の異常診断手段における診断結果とに基づいて、異常の原因を判定する異常判定手段と、
を備える異常診断装置。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180070375.3A CN116367936A (zh) | 2020-10-22 | 2021-09-21 | 异常诊断模型的构建方法、异常诊断方法、异常诊断模型的构建装置以及异常诊断装置 |
EP21882491.0A EP4235140A4 (en) | 2020-10-22 | 2021-09-21 | METHOD FOR BUILDING FAULT DIAGNOSIS MODEL, ANOMALY DIAGNOSIS METHOD, DEVICE FOR BUILDING FAULT DIAGNOSIS MODEL AND ANOMALY DIAGNOSIS DEVICE |
KR1020237015884A KR20230085924A (ko) | 2020-10-22 | 2021-09-21 | 이상 진단 모델의 구축 방법, 이상 진단 방법, 이상 진단 모델의 구축 장치 및 이상 진단 장치 |
US18/032,239 US20230393113A1 (en) | 2020-10-22 | 2021-09-21 | Construction method of abnormality diagnosis model, abnormality diagnosis method, construction device of abnormality diagnosis model, and abnormality diagnosis device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020-177364 | 2020-10-22 | ||
JP2020177364A JP7031713B1 (ja) | 2020-10-22 | 2020-10-22 | 異常診断モデルの構築方法、異常診断方法、異常診断モデルの構築装置および異常診断装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022085350A1 true WO2022085350A1 (ja) | 2022-04-28 |
Family
ID=81212867
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/034601 WO2022085350A1 (ja) | 2020-10-22 | 2021-09-21 | 異常診断モデルの構築方法、異常診断方法、異常診断モデルの構築装置および異常診断装置 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20230393113A1 (ja) |
EP (1) | EP4235140A4 (ja) |
JP (1) | JP7031713B1 (ja) |
KR (1) | KR20230085924A (ja) |
CN (1) | CN116367936A (ja) |
WO (1) | WO2022085350A1 (ja) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10122917A (ja) * | 1996-10-23 | 1998-05-15 | Nippon Steel Corp | 設備及び製品プロセス異常状態の診断方法及び診断装置 |
JP2011258113A (ja) * | 2010-06-11 | 2011-12-22 | Kobe Steel Ltd | 金属帯材料の製造条件決定システム |
JP4922265B2 (ja) | 2008-08-19 | 2012-04-25 | 株式会社東芝 | プラント監視装置およびプラント監視方法 |
WO2013011745A1 (ja) | 2011-07-15 | 2013-01-24 | 株式会社日立製作所 | 設備状態監視方法およびその装置 |
JP5499900B2 (ja) | 2010-05-25 | 2014-05-21 | Jfeスチール株式会社 | パターン自動抽出方法およびパターン自動抽出システム |
JP5651998B2 (ja) | 2010-05-25 | 2015-01-14 | Jfeスチール株式会社 | パターンライブラリを用いた異常診断方法および異常診断システム |
WO2018096682A1 (ja) * | 2016-11-28 | 2018-05-31 | 東芝三菱電機産業システム株式会社 | 圧延設備の異常診断の方法及び装置 |
JP2019074969A (ja) * | 2017-10-17 | 2019-05-16 | 新日鐵住金株式会社 | 品質予測装置及び品質予測方法 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS4922265B1 (ja) | 1969-08-08 | 1974-06-07 | ||
JPS6012880Y2 (ja) | 1979-09-29 | 1985-04-24 | 松下電工株式会社 | 門扉 |
WO2020049338A1 (en) * | 2018-09-06 | 2020-03-12 | Arcelormittal | Method and electronic device for monitoring a manufacturing of a metal product, related computer program and installation |
-
2020
- 2020-10-22 JP JP2020177364A patent/JP7031713B1/ja active Active
-
2021
- 2021-09-21 CN CN202180070375.3A patent/CN116367936A/zh active Pending
- 2021-09-21 US US18/032,239 patent/US20230393113A1/en active Pending
- 2021-09-21 KR KR1020237015884A patent/KR20230085924A/ko unknown
- 2021-09-21 EP EP21882491.0A patent/EP4235140A4/en active Pending
- 2021-09-21 WO PCT/JP2021/034601 patent/WO2022085350A1/ja active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10122917A (ja) * | 1996-10-23 | 1998-05-15 | Nippon Steel Corp | 設備及び製品プロセス異常状態の診断方法及び診断装置 |
JP4922265B2 (ja) | 2008-08-19 | 2012-04-25 | 株式会社東芝 | プラント監視装置およびプラント監視方法 |
JP5499900B2 (ja) | 2010-05-25 | 2014-05-21 | Jfeスチール株式会社 | パターン自動抽出方法およびパターン自動抽出システム |
JP5651998B2 (ja) | 2010-05-25 | 2015-01-14 | Jfeスチール株式会社 | パターンライブラリを用いた異常診断方法および異常診断システム |
JP2011258113A (ja) * | 2010-06-11 | 2011-12-22 | Kobe Steel Ltd | 金属帯材料の製造条件決定システム |
WO2013011745A1 (ja) | 2011-07-15 | 2013-01-24 | 株式会社日立製作所 | 設備状態監視方法およびその装置 |
WO2018096682A1 (ja) * | 2016-11-28 | 2018-05-31 | 東芝三菱電機産業システム株式会社 | 圧延設備の異常診断の方法及び装置 |
JP2019074969A (ja) * | 2017-10-17 | 2019-05-16 | 新日鐵住金株式会社 | 品質予測装置及び品質予測方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4235140A4 |
Also Published As
Publication number | Publication date |
---|---|
CN116367936A (zh) | 2023-06-30 |
US20230393113A1 (en) | 2023-12-07 |
EP4235140A4 (en) | 2024-04-10 |
JP2022068595A (ja) | 2022-05-10 |
EP4235140A1 (en) | 2023-08-30 |
KR20230085924A (ko) | 2023-06-14 |
JP7031713B1 (ja) | 2022-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107949813B (zh) | 制造设备诊断辅助装置及制造设备诊断辅助方法 | |
JP6116445B2 (ja) | 品質異常の原因推定支援システム | |
US11740592B2 (en) | Control method, control apparatus, mechanical equipment, and recording medium | |
US20110209083A1 (en) | Process analysis system | |
WO2022085350A1 (ja) | 異常診断モデルの構築方法、異常診断方法、異常診断モデルの構築装置および異常診断装置 | |
JP4500876B1 (ja) | 生産管理システム | |
WO2022091639A1 (ja) | 異常診断モデルの構築方法、異常診断方法、異常診断モデルの構築装置および異常診断装置 | |
CN112987682A (zh) | 控制方法、控制装置和机械设备 | |
JPWO2019016892A1 (ja) | 品質分析装置及び品質分析方法 | |
Gamero et al. | Predicting aerodynamic instabilities in a blast furnace | |
JP2755782B2 (ja) | 圧延ラインの総合診断システム | |
JPH05253797A (ja) | ライン異常判定方式 | |
JP3892614B2 (ja) | 設備及び製品プロセス異常状態の診断方法及び装置 | |
CN112783935A (zh) | 分析装置 | |
JP2018005715A (ja) | 製造プロセスの異常状態診断方法及び異常状態診断装置 | |
Herrera-Granados et al. | An experimental study of multi-sensor tool wear monitoring and its application to predictive maintenance | |
WO2023176464A1 (ja) | 要因推論装置、要因推論方法、要因推論システムおよび端末装置 | |
JP3625744B2 (ja) | 情報解析方法、情報解析装置及び情報解析プログラムを記録した記録媒体 | |
JP7180676B2 (ja) | プロセス状態監視装置及びプロセス状態監視方法 | |
WO2023176467A1 (ja) | 要因推論装置、要因推論方法、要因推論システムおよび端末装置 | |
WO2022123877A1 (ja) | 異常判定装置、異常判定モデル生成方法および異常判定方法 | |
WO2021166232A1 (ja) | プログラマブル表示器、制御システムおよび解析方法 | |
Peters et al. | Optimisation of flat product quality by intelligent data exploitation | |
CN117581170A (zh) | 分析装置 |
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: 21882491 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18032239 Country of ref document: US |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112023007064 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 20237015884 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021882491 Country of ref document: EP Effective date: 20230522 |
|
ENP | Entry into the national phase |
Ref document number: 112023007064 Country of ref document: BR Kind code of ref document: A2 Effective date: 20230414 |