CN115454012A

CN115454012A - Diagnostic device, diagnostic method, and diagnostic program

Info

Publication number: CN115454012A
Application number: CN202210445527.XA
Authority: CN
Inventors: 山下智史; 岛村明夫
Original assignee: Fuji Electric Co Ltd
Current assignee: Fuji Electric Co Ltd
Priority date: 2021-06-09
Filing date: 2022-04-26
Publication date: 2022-12-09
Also published as: TWI831186B; JP2022188345A; KR20220166179A; TW202248779A

Abstract

The invention provides a diagnostic device, a diagnostic method and a diagnostic program, which can appropriately diagnose the abnormality of equipment according to the change of the normal range of the operation state of the equipment. A monitoring device (30) according to one embodiment of the present invention includes a model generation unit (3034) that generates a normal model indicating a normal operating state of a machine (10) on the basis of previously acquired operating data (batch data) indicating a time-series operating state of the machine (10) for each predetermined period; and a diagnosis unit (3054) for performing a diagnosis regarding an abnormality in the operating state of the machine (10) based on the normal model and subsequently acquired operating data (batch data) of the machine (10) for a predetermined period, wherein the model generation unit (3034) automatically updates the normal model used by the diagnosis unit (3054).

Description

Diagnostic device, diagnostic method, and diagnostic program

Technical Field

The present invention relates to a diagnostic apparatus and the like.

Background

For example, a technique is known in which a normal model indicating a normal operating state is generated from data of an operating state of a device or equipment corresponding to the normal state, and an abnormality diagnosis of the operating state is performed based on the generated normal model and the data of the operating state of the device or equipment (see patent document 1).

< Prior Art document >

< patent document >

Patent document 1 Japanese patent application laid-open No. 6733164

Disclosure of Invention

< problems to be solved by the invention >

However, the normal range of the operation state of the device or equipment may vary. For example, the normal range of the operation state of the equipment or facility may change according to a change in the environmental conditions of the equipment or facility such as air temperature and humidity. Therefore, if the normal range of the operating state of the equipment or facility changes, the existing normal model may deviate from the normal range of the operating state after the change, and appropriate abnormality diagnosis may not be performed.

In view of the above problems, an object of the present invention is to provide a technique capable of appropriately diagnosing an abnormality of an apparatus or a device in accordance with a change in a normal range of an operation state of the apparatus or the device.

< method for solving the problems >

In order to achieve the above object, one embodiment of the present invention provides a diagnostic apparatus comprising:

a generation unit that generates a normal model indicating a normal operating state of a machine or equipment based on previously acquired operating data indicating a time-series operating state of the machine or equipment for each predetermined period; and

a diagnosis unit that diagnoses an abnormality in the operating state of the equipment or facility based on the normal model and the operation data of the equipment or facility acquired later during the predetermined period,

the generation unit automatically updates the normal model used by the diagnosis unit.

In another embodiment of the present invention, there is provided a diagnostic method including:

a generation step of generating a normal model indicating a normal operation state of the equipment or facility based on operation data indicating a time-series operation state of the equipment or facility acquired in advance by a diagnosis device for each predetermined period; and

a diagnosis step of performing diagnosis relating to abnormality of the operation state of the equipment or facility based on the normal model and the operation data of the equipment or facility acquired later during the predetermined period,

in the generating step, the normal model used in the diagnosing step is automatically updated.

In another further embodiment of the present invention, there is provided a diagnostic program for causing a diagnostic apparatus to execute the steps of:

a generation step of generating a normal model indicating a normal operation state of a machine or equipment based on operation data acquired in advance and indicating a time-series operation state of the machine or equipment for each predetermined period; and

< effects of the invention >

According to the above embodiment, it is possible to appropriately diagnose the abnormality of the equipment or the device according to the change in the normal range of the operation state of the equipment or the device.

Drawings

Fig. 1 is a diagram showing an example of a monitoring system.

Fig. 2 is a block diagram showing an example of a hardware configuration of the monitoring apparatus.

Fig. 3 is a functional block diagram showing an example of a functional configuration of the monitoring apparatus.

Fig. 4 is a diagram showing an example of the operation data of each batch process.

Fig. 5 is a schematic diagram showing an example of the batch data.

Fig. 6 is a diagram illustrating an example of a method of data conversion.

Fig. 7 is a diagram showing a first example of a change in the normal state of the operation data of the machine during the batch process.

Fig. 8 is a diagram showing a second example of a change in the normal state of the operation data of the machine during the batch process.

Fig. 9 is a diagram showing a third example of a change in the normal state of the operation data of the machine during the batch process.

Fig. 10 is a diagram for explaining an example of the update condition of the normal model.

Fig. 11 is a flowchart schematically showing an example of the normal model generation process.

Fig. 12 is a flowchart schematically showing an example of the diagnosis process concerning the abnormality of the operation state of the machine.

Fig. 13 is a flowchart schematically showing an example of the storage processing of the batch data.

Fig. 14 is a flowchart schematically showing an example of the normal model changing process.

Description of the reference numerals

1. Monitoring system

10. Machine with a rotatable shaft

20. Control device

30. Monitoring device (diagnostic device)

31. External interface

31A storage medium

32. Auxiliary storage device

33. Memory device

34 CPU

35. Communication interface

36. Input device

37. Display device

40. Terminal device

301. Batch data storage unit

302. Data storage unit

303. Model generation processing unit

304. Normal model storage unit

305. Diagnosis processing unit

306. Model change processing unit

3031. Data acquisition unit

3032. Pretreatment unit

3033. Data conversion unit

3034. Model generation unit (generation unit)

3051. Data acquisition unit

3052. Pretreatment unit

3053. Index value calculation unit

3054. Diagnostic unit

3055. Notification part

3061. Change instruction unit

3061A change instruction unit

3061B change instruction unit

3062. Setting part

3062A setting unit (first setting unit)

3062B setting unit (second setting unit)

3062C setting part (third setting part)

Detailed Description

Hereinafter, embodiments will be described with reference to the drawings.

[ overview of monitoring System ]

An outline of the monitoring system 1 of the present embodiment will be described with reference to fig. 1.

Fig. 1 is a diagram showing an example of a monitoring system 1.

The monitoring system 1 performs monitoring related to the operation state of the machine 10. The monitoring system 1 includes a device 10, a control device 20, a monitoring device 30, and a terminal device 40.

The machine 10 processes through a batch process (batch processing). The machine 10 is a machine disposed in a factory or the like and used in a production process, for example. For example, the machine 10 includes a paper feeder installed in a paper manufacturing factory, a printing factory, or the like, a rotary cutter (shearing machine) installed in a metal press factory, or the like, a press machine, or the like.

One or more machines 10 may be included in the monitoring system 1.

In addition to the equipment 10, the monitoring system 1 may monitor the operation state of a plurality of pieces of equipment (production equipment group) installed in a production line of a factory or the like as a whole, which performs a batch process.

The control device 20 controls the operation of the apparatus 10. Specifically, the control device 20 may acquire various measurement data indicating the operation state of the device 10 from the device 10, and may control the operation of the device 10 so as to meet a predetermined operation condition (for example, a predetermined sequence) based on the acquired measurement data. The control device 20 is connected to the equipment 10 so as to be able to communicate with it via a one-to-one communication line, a field network in a plant, or the like. The control device 20 is, for example, a PLC (Programmable Logic Controller), an edge processor, or the like.

The control device 20 may be provided for each of the devices 10 to be controlled, or may be provided for a plurality of devices to be controlled. That is, the monitoring system 1 may include one control device 20, and when the monitoring system 1 includes a plurality of machines 10, the monitoring system may include a plurality of devices.

The monitoring device 30 (an example of a diagnostic device) performs monitoring related to the operation state of the machine 10. Specifically, monitoring device 30 can perform diagnosis regarding an abnormality in the operating state of machine 10.

The diagnosis regarding the abnormality of the operating state of the machine 10 includes, for example, a diagnosis of the presence or absence of the abnormality of the operating state of the machine 10. The diagnosis regarding the abnormality of the operating state of the machine 10 includes, for example, a diagnosis of the degree of abnormality (hereinafter, referred to as "abnormality degree") corresponding to the operating state of the machine.

The monitoring device 30 may be provided for each of the apparatuses 10 to be monitored, or may be provided for a plurality of apparatuses 10 to be monitored. That is, the monitoring system 1 may include one monitoring device 30, and when the monitoring system 1 includes a plurality of machines 10, the monitoring system may include a plurality of devices.

The monitoring device 30 acquires various data (hereinafter, referred to as "operation data") indicating the operation state of the equipment 10 from the control device 20 at predetermined sampling intervals via a predetermined communication line, and monitors the acquired operation data to diagnose an abnormality of the equipment 10. The sampling period is defined in a range of, for example, several hundred milliseconds to several tens of seconds.

The operation data includes various measurement data indicating the operation state of the device 10, which is acquired from the device 10 by the control device 20, for example. The operation data includes control data such as a control command generated by the control device 20 for controlling the machine 10. The operation data includes data indicating a plurality of types of state variables (hereinafter, referred to as "process variables") of the equipment 10, such as temperature, pressure, torque, and flow rate at a predetermined portion of the equipment 10. Therefore, the operation data is represented as vector data indicating a plurality of types of states (process variables), for example.

The predetermined communication line includes, for example, a one-to-one communication line. The predetermined communication line includes, for example, a Local Area Network (LAN) such as a field Network provided in a facility such as a plant in which the device 10 and the control device 20 are provided. The prescribed communication line includes, for example, a Wide Area Network (WAN). The wide area network includes, for example, a mobile communication network terminating in a base station, a satellite communication network using a communication satellite, the internet, and the like. The predetermined communication line includes, for example, a short-range communication line using a predetermined wireless communication method. The short-range communication line includes, for example, a wireless communication line of a communication system such as WiFi or bluetooth (registered trademark).

The monitoring device 30 is a terminal device installed in the same facility or site as the facility such as a factory in which the apparatus 10 and the control device 20 are installed. The terminal device is a stationary terminal device such as a PLC or a desktop PC (Personal Computer). In addition, the terminal device may be a portable terminal device (portable terminal) such as a smartphone, a tablet terminal, a laptop PC, or the like. The monitoring device 30 is, for example, a server device. The server device is, for example, a local deployment server or a cloud server provided outside the land of facilities such as a factory where the machine 10 and the control device 20 are provided. The server device may be, for example, the machine 10 and the control device 20 may be edge servers installed in the site of facilities such as an installed factory or in the vicinity thereof.

The monitoring device 30 may directly acquire the operation data from the machine 10.

The terminal device 40 is connected to the monitoring device 30 through a predetermined communication line so as to be able to communicate with each other, and is a user terminal that provides information on the monitoring result of the monitoring device 30 to a user.

The terminal device 40 may be a stationary terminal device such as a desktop PC, or may be a portable terminal such as a smartphone, a tablet terminal, or a laptop PC.

[ hardware configuration of monitoring device ]

Next, a hardware configuration of the monitoring device 30 according to the present embodiment will be described with reference to fig. 2.

Fig. 2 is a diagram showing an example of the hardware configuration of the monitoring apparatus 30.

The functions of the monitoring device 30 are implemented by arbitrary hardware, arbitrary combination of hardware and software, or the like. For example, as shown in fig. 2, the monitoring device 30 includes an external interface 31, an auxiliary storage device 32, a memory device 33, a CPU (Central Processing Unit) 34, a communication interface 35, an input device 36, and a display device 37, which are connected via a bus B.

The external interface 31 functions as an interface for reading data from the storage medium 31A and writing data to the storage medium 31A. The storage medium 31A includes, for example, a flexible disk, a CD (Compact Disc), a DVD (Digital Versatile Disc), a BD (Blu-ray (registered trademark) Disc), an SD memory card, a USB (Universal Serial Bus) memory, and the like. Thus, the monitoring device 30 reads various data used in the processing from the storage medium 31A and stores the data in the auxiliary storage device 32, thereby being able to install programs for realizing various functions.

The monitoring device 30 can acquire various data and programs from an external device through the communication interface 35.

The auxiliary storage device 32 is used to store various programs installed and to store files, data, and the like required for various processes. The auxiliary storage device 32 includes, for example, an HDD (Hard Disc Drive), an SSD (Solid State Drive), and the like.

When a start instruction of the program is issued, the memory device 33 reads the program from the auxiliary storage device 32 and stores the program. The Memory device 33 includes, for example, a DRAM (Dynamic Random Access Memory) and an SRAM (Static Random Access Memory).

The CPU34 executes various programs loaded from the auxiliary storage device 32 into the memory device 33, and realizes various functions related to the monitoring device 30 in accordance with the programs.

The communication interface 35 is used as an interface for connecting to an external device so as to enable communication. Thus, the monitoring device 30 is connected to external devices such as the control device 20 and the terminal device 40 through the communication interface 35 so as to be able to communicate. The communication interface 35 may have a plurality of types of communication interfaces according to a communication method with a connected device or the like.

The input device 36 accepts various inputs from a user.

The input device 36 includes, for example, an operation input device that accepts mechanical operation input from a user. The operation input device includes, for example, a button, a toggle switch, a lever, and the like. The operation input device includes, for example, a touch screen attached to the display device 37, a touch panel provided separately from the display device 37, and the like.

The input device 36 includes, for example, a voice input device capable of receiving voice input from a user. The sound input device includes, for example, a microphone capable of collecting a user's sound.

The input device 36 includes, for example, a gesture input device capable of accepting a gesture input from a user. The gesture input device includes, for example, a camera capable of capturing an image of a gesture of the user.

The input device 36 includes, for example, a living body input device capable of accepting a living body input from a user. The living body input device includes, for example, a camera capable of acquiring image data including information on a fingerprint or an iris of a user.

The display device 37 displays an information screen and an operation screen to the user under the control of the monitoring device 30. The display device 37 includes, for example, a liquid crystal display, an organic EL (Electroluminescence) display, and the like.

[ functional constitution of monitoring device ]

Next, the functional configuration of the monitoring device 30 according to the present embodiment will be described with reference to fig. 3 to 10.

Fig. 3 is a functional block diagram showing an example of the functional configuration of the monitoring device 30. Fig. 4 is a diagram showing an example of the operation data of each batch process. Fig. 5 is a schematic diagram showing an example of the batch data. Fig. 6 is a diagram illustrating an example of a method of data conversion. Fig. 7 to 9 are diagrams showing first to third examples of changes in the normal state of the operation data of the machine 10 during the batch process. Fig. 10 is a diagram for explaining an example of the update condition of the normal model.

As shown in fig. 3, the monitoring device 30 includes a batch data storage unit 301, a data storage unit 302, a model generation processing unit 303, a normal model storage unit 304, a diagnosis processing unit 305, and a model change processing unit 306. The functions of the batch data storage unit 301 and the normal model storage unit 304 are realized by, for example, a storage area defined in the auxiliary storage device 32. The functions of the data storage unit 302, the model generation processing unit 303, the diagnosis processing unit 305, and the model change processing unit 306 are realized by, for example, loading a program installed in the auxiliary storage device 32 into the memory device 33 and executing the program on the CPU 34.

The batch data storage unit 301 stores therein time-series operation data (hereinafter referred to as "batch data") for each batch process of the machine 10, which is received from the control device 20.

For example, as shown in fig. 4, the operation data includes, for example, state data for each process variable such as temperature, pressure, torque, flow rate, and the like, and for each sampling period. Also, in the batch process, the same kind (variable) of state data represents a similar waveform (graph) for each batch.

For example, as shown in fig. 5, the batch data is represented as three-dimensional data for each batch i, for the elapsed time k from the start of the batch in each batch i, and for each process variable j. The batch I represents an integer of 1 or more and the number of stored batches I or less, the time K represents an integer of 1 or more and the number of sampling times K within a batch, and the process variable J represents an integer of 1 or more and the number of types of process variables J or less. Hereinafter, the batch data may be represented as x (i, j, k) using the batch process i, time k, and process variable j.

Returning to fig. 3, the data storage unit 302 causes the batch data to be stored in the batch data storage unit 301. Specifically, the data storage unit 302 stores the batch data in the batch data storage unit 301 when the operation state of the machine 10 is within the normal range.

The model generation processing unit 303 performs processing for generating a normal model indicating a normal operating state of the machine 10. The model generation processing unit 303 includes a data acquisition unit 3031, a preprocessing unit 3032, a data conversion unit 3033, and a model generation unit 3034.

The data obtaining unit 3031 obtains batch data, as base data for generating the normal model, from the batch data storage unit 301, in which the operation state of the machine 10 corresponds to a normal state.

The preprocessing unit 3032 performs predetermined preprocessing on the batch data x (i, j, k) acquired by the data acquisition unit 3031, and outputs the preprocessed batch data x _s (i,j,k)。

The preprocessor 3032 performs, for example, a normalization process on the batch data acquired by the data acquisition unit 3031. Specifically, the preprocessing unit 3032 may perform the normalization process of the batch data x (i, j, k) by using the average μ j, k and the standard deviation σ j, k between the plurality of batches i of the batch data x (i, j, k) acquired by the data acquiring unit 3031.

The data conversion part 3033 converts the batch data x, which is completed by the preprocessing based on the preprocessing part 3032, of the three-dimensional form table _s (i, j, k) batch data X converted into two-dimensional form _s (j,k)。

For example, as shown in fig. 6, the data conversion part 3033 converts the batch data x _s (I, j, k) is decomposed into a batch data group x of the number of batches I for each batch I _s (1,j,k)、x _s (2,j,k)、…、x _s (I, j, k). The data conversion unit 3033 generates the batch data X corresponding to the matrix data of J rows I · K columns by combining the decomposed batch data groups in the time K axis direction _s (j,k)。

Returning to fig. 3, the model generation unit 3034 (an example of the generation unit) generates the batch data x indicating the normal state of the machine 10 based on the batch data x acquired by the data acquisition unit 3031 _s (i, j, k) performs machine learning to generate a normal model indicating a normal state of the machine 10.

The model generating unit 3034 generates, for example, a load Matrix (Loading Matrix) obtained by Principal Component Analysis (PCA) as a normal model.

In the case where the monitoring system 1 includes a plurality of machines 10, a normal model is generated for each of the plurality of machines 10. The model generation unit 3034 may generate the normal model by any method. For example, the model generator 3034 may generate the normal model using Independent Component Analysis (ICA) instead of principal Component Analysis. For example, model generation unit 3034 may generate a normal model using a Support Vector Machine (SVM), a Deep Neural Network (DNN), or the like.

The normal model storage unit 304 stores the normal model generated by the model generation unit 3034. As will be described later, when the normal model is updated by the model generator 3034, the updated normal model is stored in the normal model storage 304, and the normal model before the update is also stored. Specifically, the normal model storage unit 304 distinguishes a region (address) in which the normal model used for the diagnosis of the abnormality in the operating state of the device 10 by the diagnosis processor 305 is stored from a region (address) in which the normal model before update is stored.

The diagnosis processing unit 305 performs a process for diagnosing an abnormality in the operating state of the machine 10. The diagnosis processing unit 305 includes a data acquisition unit 3051, a preprocessing unit 3052, an index value calculation unit 3053, a diagnosis unit 3054, and a notification unit 3055.

The data acquisition unit 3051 acquires operation data of the apparatus 10 to be diagnosed, which is introduced from the control device 20.

The preprocessing unit 3052 performs the same preprocessing as the preprocessing unit 3032 on the operation data acquired by the data acquisition unit 3051.

The index value calculation unit 3053 calculates a predetermined index value for diagnosing an abnormality in the operating state of the machine 10 based on the operation data of the machine 10 on which the preprocessing performed by the preprocessing unit 3052 is completed and the latest normal model stored in the normal model storage unit 304.

The index value calculation unit 3053 calculates Q statistic and T as predetermined index values based on the operation data of the preprocessed equipment 10 and the load matrix as the normal model, for example ² Statistics are obtained. The index value calculation unit 3053 may calculate, for example, Q statistic and T of the entire batch process from the start of the current batch process by the machine 10 as a predetermined index value ² The respective function values of the statistics.

The diagnosis unit 3054 diagnoses an abnormality in the operating state of the machine 10 based on the index value calculated by the index value calculation unit 3053.

The diagnosis unit 3054 uses, for example, the Q statistic and T as index values ² When at least one of the statistics exceeds a predetermined criterion (hereinafter, "abnormal symptom criterion") IVth1, it is diagnosed that there is a symptom of an abnormality in the operating state of the machine 10. The diagnosis unit 3054 uses, for example, the Q statistic and T as index values ² When at least one of the statistical amounts exceeds a predetermined reference (hereinafter referred to as "abnormality occurrence reference") IVth2 larger than the abnormality sign reference IVth1, it is diagnosed that there is an abnormality in the operating state of the machine 10. In this case, the abnormality sign reference IVth1, the abnormality occurrence reference IVth2, the case of Q statistic, and T ² The statistics may be the same or different. The diagnosis unit 3054 may diagnose the degree of abnormality of the operating state of the machine 10, for example, by diagnosing the Q statistic and T as index values ² The larger the statistic amount is, the higher the degree of abnormality of the operating state of the machine 10 is.

In addition, the first and second substrates are,the diagnosis unit 3054 determines, for example, a value of a function based on the Q statistic and a value of a function based on the T statistic for the entire batch process at this time as an index value ² When at least one of the function values of the statistics exceeds the abnormality sign criterion IVth1, it is diagnosed that there is a sign that the operating state of the machine 10d falls into abnormality. The diagnostic unit 3054 may also determine, for example, a function value based on the Q statistic and a function value based on T of the entire lot process at this time as index values ² When at least one of the function values of the statistics exceeds the abnormality occurrence criterion IVth2, it is determined that there is an abnormality in the operating state of the machine 10. In this case, the abnormality indication reference IVth1 and the abnormality generation reference IVth2 may be based on the Q statistic function value and the T statistic function value in the whole batch process ² The function values of the statistics may be the same or different. The diagnosis unit 3054 may diagnose the degree of abnormality of the operation state of the machine 10, for example, by using the Q statistic, T, as an index value for the entire process of the lot at this time ² The larger the function value of the statistic is, the higher the degree of abnormality of the operating state of the machine 10 becomes.

The notification unit 3055 notifies the user of the diagnosis result based on the diagnosis unit 3054 to the user. The notification unit 3055 notifies the user of the diagnosis result, for example, via the display device 37. The notification unit 3055 may transmit the diagnosis result to the terminal device 40 through the communication interface 35, and display the diagnosis result on the display of the terminal device 40 to notify the user of the diagnosis result.

The model change processing unit 306 performs a process for changing a normal model used for diagnosis of an abnormality in the operating state of the machine 10 by the diagnosis processing unit 305. The model change processing unit 306 includes a change instruction unit 3061 and a setting unit 3062.

The change instruction unit 3061 generates and outputs an instruction for changing the normal model used by the diagnosis processing unit 305. The change instruction unit 3061 includes

change instruction units

3061A and 3061B.

The change instruction unit 3061A generates an instruction (hereinafter, referred to as a "model update instruction" for convenience) for automatically updating the normal model used by the diagnosis processing unit 305, and inputs the instruction to the model generation processing unit 303.

For example, as shown in fig. 7, in the case where the ambient temperature is low, the torque of the rotary shear as the machine 10 is relatively larger than that in the case where the ambient temperature is high. This is because the viscosity of the lubricating grease used varies according to the temperature. Therefore, when the ambient air temperature around the rotary shear changes with the passage of time, the normal range of the torque changes.

Further, for example, as shown in fig. 8, when the humidity around the paper feeding machine as the device 10 is high, the torque becomes relatively large as compared with the case where the humidity is low. This is because the degree of moisture absorption of the paper changes with changes in humidity, and as a result, the weight of the paper to be conveyed changes. Therefore, if the humidity around the paper feeding machine changes with the passage of time, the normal range of the torque changes.

For example, as shown in fig. 9, in a press machine as the machine 10, when the ambient air temperature is high, the torque is relatively larger than that in a case where the ambient air temperature is low. This is because the mold expands or contracts with a change in air temperature, and as a result, the sharpness of the mold changes. Therefore, as time passes, if the ambient air temperature around the press machine changes, the normal range of the torque changes.

Therefore, the change instruction unit 3061A can output a model update instruction to the model generation processing unit 303 in response to a change in the normal range of the operating state of the machine 10, and cause the model generation processing unit 303 to update the normal model.

Specifically, the change instruction unit 3061A may output the model update instruction if it can be determined that a predetermined condition (an example of a first condition) (hereinafter, referred to as a "model update condition") deviating from a predetermined reference from a normal model currently used is satisfied in a normal range of the operating state of the apparatus 10. When a plurality of model update conditions are defined, the change instruction unit 3061A may generate a model update instruction when any one of the plurality of model update conditions is satisfied, and output the generated model update instruction to the model generation processing unit 303.

The model update condition is, for example, "batch data of machine 10 acquired later relatively greatly deviates from the current normal model". The batch data of the machine 10 acquired after the fact is the batch data of the machine 10 acquired at a timing later than the batch data used for generating the normal model currently used by the diagnostic processing unit 305.

Specifically, the model update condition may be "index value is relatively large". More specifically, for example, as shown in fig. 10, the model update condition may be "index value exceeds a predetermined reference (hereinafter, referred to as" model update reference ") IVth3" (see a portion enclosed by a broken line in the figure). In addition, the model update condition may be "the moving average of index values exceeds the model update reference IVth3". The model update condition may be "the ratio RT of the index value exceeding the model update reference IVth3 exceeds a predetermined reference (hereinafter, referred to as" model update reference ") RTth during the batch. The model update condition may be, for example, "the number of consecutive times CN that the index value exceeds the state of the model update reference IVth3 exceeds a predetermined reference (hereinafter referred to as" model update reference ") CNth". The model update reference IVth3 may be defined as a range smaller than the abnormality sign reference IVth1 and the abnormality occurrence reference IVth2, or may be defined as a range between the abnormality sign reference IVth1 and the abnormality occurrence reference IVth2, for example. As shown in fig. 10, the model update reference IVth3 may be the same as the abnormality sign reference IVth 1.

The model update condition may be, for example, "the production quantity PN of articles produced by the machine 10 from a predetermined starting point exceeds a predetermined reference (hereinafter, referred to as" model update reference ") PNth". Information relating to the number of items produced PN based on the machine 10 may be retrieved from the control device 20. In this case, the starting point of the production number PN may be, for example, when the use of the normal model currently used is started, or when the acquisition of the lot data for generating the normal model currently used is completed.

The model update condition includes, for example, "the elapsed time Tm from a predetermined start point exceeds a predetermined reference (hereinafter, referred to as" model update reference ") Tm _ th". The starting point of the elapsed time Tm may be, for example, when the use of the normal model currently used is started, or when the acquisition of the batch data for the generation of the normal model currently used is completed.

The model update condition includes, for example, "a change in the environmental condition at the installation location of the device 10 exceeds a predetermined criterion (hereinafter, referred to as" model update criterion "). Specifically, the model update condition may include "the amount of change Δ Tp in the temperature Tp around the machine 10 exceeds a prescribed reference (hereinafter, referred to as" model update reference ") Δ Tp _ th. In addition, the model update condition may include "the amount of change Δ H in the humidity H around the machine 10 exceeds a predetermined reference (hereinafter, referred to as" model update reference ") Δ Hth. The environmental conditions of the installation location of the device 10, such as the temperature Tp and the humidity H around the device 10, are measured by, for example, sensors installed around the device 10 and the device 10, and information related to the environmental conditions of the installation location of the device 10 is introduced into the monitoring device 30 through the control device 20. The starting point of the change in the environmental condition at the installation site of the equipment 10, such as the change amount Δ Tp of the temperature Tp and the change amount Δ H of the humidity H around the equipment 10, may be, for example, the start of use of the normal model currently used, or the end of acquisition of the batch data used for generation of the normal model currently used.

In addition, the model updating instruction may include instruction contents related to the updating method of the normal model.

For example, a plurality of options are provided as a model update method, and a normal model may be updated by a set update method from among the plurality of options.

The update method of the model may include, for example, a method of updating a normal model using batch data of the latest specified number BN (for example, 20) of machines 10 in a normal state. The lot data in the normal state of the machine 10 is the lot data in which the operation state of the machine 10 is diagnosed as normal by the diagnostic unit 3054. Specifically, the model generation processing unit 303 generates a new normal model using the batch data in the normal state of the machines 10 traced back by the predetermined number BN closest to the time when the model update condition is satisfied, excluding the batch data in which the operation state of the machine 10 is diagnosed as abnormal.

On the premise that the state in which the operation state of the device 10 is normal continues, the model generation processing unit 303 may generate a new normal model using the latest predetermined number of batch data every time the batch process ends, and update the normal model used by the diagnosis processing unit 305. Specifically, the normal model may be updated by using the batch data of the new predetermined number of BN including the newest batch data instead of the oldest batch data among the batch data of the predetermined number of BN used for the generation of the normal model last time. The model update condition in this case is "batch process update of the machine 10".

The model updating method may include updating the normal model by replacing a certain number or a certain ratio of the batch data used for generation of the normal model currently used with the batch data acquired later and in a normal state of the machine 10, for example. The batch data acquired after the fact is the batch data acquired after the time point at which the batch data for generating the normal model used at present is acquired. Specifically, the model generation processing unit 303 generates a new normal model by using a predetermined number of pieces of batch data of the predetermined number of BN obtained later, in place of a predetermined number or a predetermined ratio of pieces of batch data of the predetermined number of BN used for generation of the normal model currently used. In this case, the newly added batch data (group) may be the latest batch data (group) selected by tracing back from the latest batch data, or may be selected according to some other condition.

The change instruction unit 3061B generates a command (hereinafter, referred to as an "old model reactivation command" for convenience) for discarding the normal model currently used by the diagnosis processing unit 305 and returning the normal model to the latest normal model before update, and outputs the command to the normal model storage unit 304. Specifically, the change instruction unit 3061B eliminates (discards) the latest normal model in the normal model storage unit 304 based on the old model reactivation instruction, and moves the normal model that has been updated most recently to the address of the normal model used by the diagnosis processing unit 305. Thus, the diagnosis processing unit 305 accesses the normal model before update, and uses the normal model before update to diagnose an abnormality in the operating state of the machine 10.

For example, when the deviation between the normal model currently used and the normal range of the actual operating state of the machine 10 exceeds a predetermined criterion (hereinafter referred to as "old model restoration criterion"), the change command unit 3061B outputs an old model restoration command to the normal model storage unit 304. Specifically, when it can be determined that a predetermined condition (hereinafter, referred to as "old-model reactivation condition") (an example of a second condition) that the deviation between the normal model currently used and the normal range of the actual operating state of the device 10 exceeds the old-model reactivation reference is satisfied, the change instruction unit 3061B may output the old-model reactivation command. When a plurality of old model reactivation conditions are defined, and when any one of the plurality of old model reactivation conditions is established, the change instruction unit 3061B may generate an old model reactivation instruction and output it to the normal model storage unit 304.

The old model reactivation condition is, for example, "the frequency Fq of the operation state of the machine 10 diagnosed as abnormal by the diagnosis unit 3054 before and after the latest update of the normal model exceeds a predetermined criterion (hereinafter, referred to as" old model reactivation criterion ") Fq _ th".

The old model reactivation condition may be, for example, "a change exceeding a predetermined criterion (hereinafter, referred to as" old model reactivation criterion ") in a direction deviating from a normal range of the operating state of the machine 10 based on the diagnostic result of the diagnostic unit 3054 before and after the latest update of the normal model". Specifically, the old model reactivation condition may be "the increase Δ IVm in the moving average value IVm of the index values exceeds a predetermined criterion (hereinafter referred to as" old model reactivation criterion ") Δ IVm _ th before and after the latest update of the normal model".

The setting unit 3062 performs setting related to changing (updating or reviving) the normal model based on an input from the user. Input from the user is accepted, for example, by input device 36. Further, the input from the user is performed, for example, by the terminal device 40, and the signal indicating the input from the user is received from the terminal device 40, and is received through the communication interface 35 (an example of the first input unit, the second input unit, and the third input unit). The setting unit 3062 includes setting units 3062A to 3062C.

The setting unit 3062A (an example of a first setting unit) performs setting relating to the model update condition based on a predetermined input from the user. For example, the User can input settings related to the model update conditions through a predetermined GUI (Graphical User Interface) displayed on the display of the display device 37 or the terminal device 40.

The setting unit 3062A sets the model update references IVth3, RTth, CNth, PNth, tm _ th, Δ Tp _ th, Δ Hth, and the like, for example, in accordance with a predetermined input from the user. The setting unit 3062A may allow the user to directly set the model update references IVth3, RTth, CNth, PNth, tm _ th, Δ Tp _ th, Δ Hth, and the like, or may allow indirect setting. The direct setting is a state in which the user can specify values corresponding to the model update references IVth3, RTth, CNth, PNth, tm _ th, Δ Tp _ th, Δ Hth, and the like by setting input. The indirect setting is a state in which the user can specify variables and the like in the relational expressions for determining values corresponding to the model update references IVth3, RTth, CNth, PNth, tm _ th, Δ Tp _ th, Δ Hth, and the like by setting input.

The setting unit 3062B (an example of a second setting unit) performs setting relating to a method of updating the normal model based on a predetermined input from the user. For example, the user can input settings related to the method of updating the normal model through a predetermined GUI displayed on the display devices of the display device 37 and the terminal device 40.

The setting unit 3062B may select and set an update method of one model from among a plurality of update methods of models, for example, in accordance with a predetermined input from the user. The setting unit 3062B may set the number of batch data (predetermined number BN) used for updating the normal model, for example, based on a predetermined input from the user. The setting unit 3062B may set the number, ratio, and the like of batch data acquired later, among the batch data used for updating the normal model.

The setting unit 3062C (an example of a third setting unit) performs setting relating to the old model reactivation condition based on a predetermined input from the user. For example, the user can input settings related to the old model reactivation condition through a predetermined GUI displayed on the display device 37 or the display of the terminal device 40.

The setting unit 3062C sets the old model reactivation references Fq _ th, Δ IVm _ th, and the like, based on a predetermined input from the user, for example. The user may directly set the old model reactivation references Fq _ th and Δ IVm _ th by the setting unit 3062C, or may indirectly set them.

[ Generation processing of Normal model ]

Next, a normal model generation process by the monitoring device 30 (model generation processing unit 303) will be described with reference to fig. 11.

Fig. 11 is a flowchart schematically showing an example of the normal model generation process by the model generation processing unit 303.

The present flowchart is executed, for example, in accordance with a prescribed input (request) from a user. The flowchart is executed after, for example, the model update command is output from the model change processing unit 306 (change command unit 3061A).

As shown in fig. 11, in step S102, the data obtaining unit 3031 obtains batch data (training data) corresponding to the normal state of the machine 10 for generating the normal model from the batch data storage unit 301.

After the process of step S102 is completed, the model generation processing unit 303 proceeds to step S104.

In step S104, the preprocessor 3032 performs predetermined preprocessing on the batch data acquired in step S102.

After the process of step S104 is completed, the model generation processing unit 303 proceeds to step S106.

Through step S106, the data conversion part 3033 converts the batch data whose preprocessing is completed in step S104 into batch data in a two-dimensional form.

After the process of step S106 is completed, the model generation processing unit 303 proceeds to step S108.

In step S108, the model generator 3034 generates a normal model based on the batch data converted into the two-dimensional format in step S106. As described above, the generated normal model is stored in the normal model storage unit 304.

After the process of step S108 is completed, the model generation processing unit 303 ends the process of this flowchart.

In this way, the monitoring device 30 can generate a normal model based on the batch data corresponding to the normal operating state of the machine 10. Further, the monitoring device 30 may update the normal model based on the model update command at a timing when the normal model used by the diagnosis processing section 305 needs to be updated.

[ diagnostic processing relating to abnormality in the operating state of the machine ]

Next, referring to fig. 12, a diagnosis process relating to an abnormality in the operating state of the machine 10 by the monitoring device 30 (diagnosis process unit 305) will be described.

Fig. 12 is a flowchart schematically showing an example of the diagnosis process related to the abnormality of the operation state of the machine 10 by the diagnosis processing unit 305.

The present flowchart is repeated for each prescribed processing cycle, for example, between the start and end of the batch process by the machine 10. The start and end of the batch process are grasped by a signal indicating the start and end of the batch process of the machine 10, which is transmitted from the control device 20 and received by the monitoring device 30, for example.

In this example, a flag F indicating the presence or absence of an abnormality in the operating state of the machine 10 is used. The flag F is initialized to "0" indicating a state where there is no abnormality at the start of the batch process of the machine 10.

As shown in fig. 12, in step S202, the data acquisition unit 3051 acquires the latest operation data of the device 10 introduced into the monitoring apparatus 30.

After the process of step S202 is completed, the diagnosis processing section 305 proceeds to step S204.

In step S204, the preprocessing unit 3052 performs predetermined preprocessing on the operation data acquired in step S202.

After the process of step S204 is completed, the diagnosis processing unit 305 proceeds to step S206.

In step S206, the index value calculation unit 3053 calculates an index value based on the latest operation data and the normal model for which the preprocessing is completed in step S204.

After the process of step S206 is completed, the diagnosis processing section 305 proceeds to step S208.

In step S208, the diagnosis unit 3054 performs a diagnosis regarding the operation state of the machine 10 based on the index value calculated in step S206.

After the process of step S208 is completed, the diagnosis processing unit 305 proceeds to step S210.

In step S210, the diagnosis unit 3054 determines whether or not there is an abnormality in the diagnosis result in step S208. The diagnosis unit 3054 proceeds to step S212 if there is an abnormality in the diagnosis result, and proceeds to step S216 if there is no abnormality.

In step S212, the notification unit 3055 notifies the user of the diagnosis result indicating that the operation state of the device 10 is abnormal.

The content of the notification relating to the diagnosis result may be, for example, only the fact that there is an abnormality in the operating state of the machine 10, or may include information that is the basis of the fact (diagnosis result) in addition to the fact. The information that is the basis of the diagnosis result includes, for example, information such as a graph indicating a time-series change of the index value. Hereinafter, the same applies to the content of the notification in step S216 described later.

After the process of step S212 is completed, the diagnosis processing unit 305 proceeds to step S214.

In step S214, the diagnosis processing unit 305 sets the flag F to "1" indicating that the operating state of the device 10 is abnormal (F = 1). Thus, the monitoring device 30 (the data storage unit 302 described later) can determine whether or not the lot data of the specific lot process indicates a normal state of the machine 10 by checking the flag F (see fig. 13).

After the process of step S214 is completed, the diagnosis processing unit 305 ends the process of this flowchart.

On the other hand, in step S216, the notification unit 3055 notifies the user of the result of diagnosis about the operation state of the device 10. Specifically, 3055 notifies the user of a diagnosis result indicating that there is no abnormality in the operating state of the machine 10 or that there is a sign of an abnormality.

After the process of step S216 is completed, the diagnosis processing unit 305 ends the process of this flowchart.

In this manner, monitoring device 30 can diagnose the operating state of machine 10 on-line using a normal model indicating the normal operating state of machine 10, and notify the user of the diagnosis result.

[ storage processing of batch data ]

Next, referring to fig. 13, a process of storing batch data indicating a normal operation state of the machine 10 by the monitoring device 30 (data storage unit 302) will be described.

Fig. 13 is a flowchart schematically showing an example of the storage processing of the batch data by the data storage unit 302.

The present flow chart is executed, for example, after the batch process of the machine 10 is completed.

As shown in fig. 13, the data storage unit 302 determines whether or not the flag F is "0" indicating that there is no abnormality in the operating state of the machine 10. If the flag F is "0", the data storage unit 302 proceeds to step S304, and if the flag F is not "0", that is, "1" indicating that there is an abnormality in the operation state of the device 10, the processing of this flowchart is ended.

In step S304, the data storage unit 302 stores (buffers) the time-series operation data of the start to the end of the current batch process, which is stored (buffered) in the memory device 33 or the like, in the batch data storage unit 301 as the batch data.

After the process of step S304 is completed, the data storage unit 302 ends the process of this flowchart.

In this way, the monitoring device 30 can store only the lot data of the machine 10, which is diagnosed by the diagnostic processing unit 305 that there is no abnormality in the operation state, among the lot data of the machines 10 introduced from the control device 20. Therefore, the monitoring device 30 can update the normal model by using the batch data stored after the acquisition of the batch data for the generation of the normal model used at present is completed.

[ Change processing of Normal model ]

Next, a normal model change process performed by the monitoring device 30 (model change processing unit 306) and used by the diagnosis processing unit 305 will be described with reference to fig. 14.

Fig. 14 is a flowchart schematically showing an example of normal model change processing performed by the model change processing unit 306 (change instruction unit 3061).

As shown in fig. 14, the change instruction unit 3061 acquires the latest data for determining whether or not the normal model currently used needs to be changed, that is, whether or not the model update condition and/or the old model reactivation condition are satisfied.

After the process of step S402 is completed, the change instruction unit 3061 proceeds to step S404.

In step S404, the change instruction unit 3061A determines whether the model update condition is satisfied. The change instruction unit 3061 proceeds to step S406 when the model update condition is satisfied, and proceeds to step S408 when the model update condition is not satisfied.

In step S406, the change instruction unit 3061A transmits a model update instruction to the model generation processing unit 303, and the model generation processing unit 303 updates the normal model used by the diagnosis processing unit 305.

After the process of step S406 is completed, the change instruction unit 3061 ends the process.

On the other hand, in step S408, the change instruction unit 3061B determines whether the old model reactivation condition is satisfied. When the old model reactivation condition is satisfied, the change instruction unit 3061B proceeds to step S410, and when the old model reactivation condition is not satisfied, the process of this flowchart is ended.

In step S410, the change instruction unit 3061B outputs an old model reactivation instruction to the normal model storage unit 304. Specifically, the change instruction unit 3061B discards (eliminates) the current normal model in the normal model storage unit 304, and returns the normal model before update to the address of the normal model used by the diagnosis processing unit 305.

After the process of step S410 is completed, the change instruction unit 3061 ends the process of this flowchart.

In this way, the monitoring device 30 can update the normal model using the batch data acquired after the establishment of the model update condition that can determine that the deviation between the normal model currently used and the normal operating state of the machine 10 exceeds the predetermined reference. Therefore, the monitoring device 30 can update the normal model in accordance with a change in the normal range of the machine 10. Therefore, monitoring device 30 can appropriately diagnose an abnormality in the operating state of machine 10 based on a change in the normal range of the operating state of machine 10.

Further, the monitoring device 30 may return the normal model used by the diagnosis processing unit 305 to the normal model before the update after determining that the model reactivation condition in which the deviation between the updated normal model and the normal operating state of the machine 10 exceeds the predetermined reference is satisfied. Therefore, monitoring device 30 may return the normal model used by diagnosis processing unit 305 to the normal model before the update in a situation where the updated normal model is not suitable for the normal operating state of machine 10 although the normal model is updated. Thus, monitoring device 30 can more appropriately perform diagnosis regarding an abnormality in the operating state of machine 10.

[ Effect ]

Next, the operation of the monitoring device 30 of the present embodiment will be explained.

In the present embodiment, the monitoring apparatus 30 includes a model generation unit 3034 and a diagnosis unit 3054. Specifically, the model generator 3034 generates a normal model indicating a normal operating state of the machine 10 or the like based on previously acquired operating data (for example, batch data for each batch process) indicating a time-series operating state of the machine 10 or equipment (hereinafter, referred to as "the machine 10 or the like") for each predetermined period. The diagnosis unit 3054 diagnoses an abnormality in the operating state of the device 10 and the like based on the normal model and the operation data of the device 10 and the like acquired later for a predetermined period. Then, the model generation unit 3034 automatically updates the normal model used by the diagnosis unit 3054.

Thus, for example, when the normal range of the operating state of the device 10 or the like changes, the monitoring device 30 can update the normal model in accordance with the change. Therefore, the monitoring device 30 can appropriately diagnose the abnormality of the device 10 or the like based on the change in the normal range of the operating state of the device 10 or the like.

In the present embodiment, the model generation unit 3034 may automatically update the normal model used by the diagnosis unit 3054 in accordance with a temporal change in the normal range of the operating state of the equipment 10 or the like.

Thus, the monitoring device 30 can appropriately diagnose an abnormality of the device 10 or the like based on a temporal change in the normal range of the operation state of the device 10 or the like.

In the present embodiment, the model generator 3034 may automatically update the normal model used by the diagnosis unit 3054 after the model update condition is satisfied.

Thus, the monitoring device 30 can update the normal model according to whether or not the model update condition indicating the change of the normal range of the operation state of the equipment 10 or the like is appropriately set.

In the present embodiment, the model update condition may be a condition in which the operation data of the machine 10 or the like during a predetermined period is relatively greatly deviated from the normal model within the range diagnosed as normal by the diagnosis unit 3054. The model update condition may be that the production quantity PN of the articles produced by the machine 10 or the like exceeds the model update criterion PNth, based on the start of use of the normal model used by the diagnosis unit 3054 or the end of acquisition of the operation data for each predetermined period used by the model generation unit 3034 for generation of the normal model. The model update condition may be that the elapsed time Tm exceeds the model update reference Tm _ th, based on the start of use of the normal model used by the diagnostic unit 3054 or the end of acquisition of the operation data for each predetermined period used by the model generation unit 3034 to generate the normal model. The model update condition may be a relatively large change in the environmental conditions around the machine 10 or the like, based on the start of use of the normal model used by the diagnosis unit 3054 or the end of acquisition of the operation data for each predetermined period used by the model generation unit 3034 for generation of the normal model.

Thus, the monitoring device 30 can define various model update conditions indicating the change in the normal range of the operating state of the equipment 10 and the like. Therefore, the monitoring device 30 can improve the degree of freedom of the timing of the automatic update of the normal model.

In the present embodiment, the monitoring device 30 may include a first input unit (for example, the input device 36 and the communication interface 35) and a setting unit 3062A. Specifically, the first input unit may accept input from a user. The setting unit 3062A may set the model update condition based on a predetermined input received by the first input unit.

Thus, the monitoring device 30 enables the user to determine (set) the timing of automatic update of the normal model.

In the present embodiment, the model generator 3034 may automatically update the normal model used by the diagnosis unit 3054 based on the operation data for each predetermined period for the diagnosis performed by the diagnosis unit 3054.

Thus, the monitoring device 30 can appropriately update the normal model by selecting and using the operation data for each predetermined period corresponding to the normal operation state based on the diagnosis result of the diagnosis unit 3054.

In the present embodiment, the model generator 3034 may automatically update the normal model used by the diagnostic unit 3054 based on the operation data for each of the plurality of predetermined periods, which is obtained by replacing a certain number or a certain ratio of the operation data for each of the plurality of predetermined periods used for generating the normal model before the update with the operation data for each of the plurality of predetermined periods used by the diagnostic unit 3054 for the diagnosis based on the normal model before the update.

In this way, monitoring device 30 can reflect the range of the recent normality of the operating state of machine 10 on the normal model.

In the present embodiment, the model generation unit 3034 may automatically update the normal model used by the diagnosis unit 3054 based on the operation data for each predetermined period of the latest predetermined number (for example, the predetermined number BN) used for the diagnosis based on the normal model before the update by the diagnosis unit 3054.

Thus, the monitoring device 30 can reflect the normal range of the operation state of the nearest equipment 10 to the normal model.

In the present embodiment, the monitoring device 30 may include a second input unit (for example, the input device 36 and the communication interface 35) and a setting unit 3062B. Specifically, the second input unit may accept input from a user. The setting unit 3062B also performs setting relating to the side in which the model generation unit 3034 automatically updates the normal model used by the diagnosis unit 3054 based on the operation data for each predetermined period used for the diagnosis performed by the diagnosis unit 3054, based on the predetermined input received by the second input unit.

Thus, the monitoring device 30 enables the user to determine (set) the updating method of the normal model.

In the present embodiment, the diagnosis unit 3054 may return the normal model used for diagnosis to the normal model before updating when the range of the normal model updated by the model generation unit 3034 with respect to the operating state of the equipment 10 or the like deviates from a predetermined reference.

Thus, even when the normal model after the update does not properly express the normal range of the operating state of the device 10 or the like, the monitoring device 30 can return to the normal model before the update to continue and properly perform diagnosis on the abnormality of the device 10 or the like.

In the present embodiment, the diagnosing unit 3054 may return the normal model used for the diagnosis to the normal model before the update when it is determined that the old model reactivation condition, which is out of the normal range of the operation state of the equipment 10 or the like updated by the model generating unit 3034, is satisfied, the old model reactivation condition exceeding a predetermined criterion. The old model reactivation condition may be that before and after the update of the normal model, the frequency of the abnormality in the operation state of the machine 10 or the like diagnosed by the diagnostic unit 3054 increases beyond a predetermined criterion. The old model reactivation condition may be a change exceeding a predetermined criterion in a direction deviating from a normal range of the operation state of the device 10 or the like based on the diagnosis result of the diagnosis unit 3054 before and after the update of the normal model.

Thus, when the updated normal model does not properly express the normal range of the operating state of the device 10 or the like, the monitoring device 30 can return to the normal model before the update.

In the present embodiment, the monitoring device 30 may include a third input unit (e.g., the input device 36, the communication interface 35, and the like) and a setting unit 3062C. Specifically, the third input unit may accept an input from the user. The setting unit 3062C may set the old model reactivation condition based on a predetermined input received by the third input unit.

Thus, the monitoring device 30 enables the user to determine (set) the timing for returning the normal model to the state before the update.

Although the embodiments have been described in detail above, the present invention is not limited to the specific embodiments, and various modifications and changes can be made within the scope of the gist of the present invention.

Claims

1. A diagnostic device comprising:

a diagnosis unit that diagnoses an abnormality in the operating state of the equipment or facility based on the normal model and the operating data of the equipment or facility acquired later for the predetermined period of time,

2. The diagnostic device of claim 1,

the generation unit automatically updates the normal model used by the diagnosis unit in accordance with a temporal change in a normal range of the operating state of the equipment or facility.

3. The diagnostic device of claim 1 or 2, wherein,

if the first condition is satisfied, the generation unit automatically updates the normal model used by the diagnosis unit.

4. The diagnostic apparatus according to claim 3, wherein the first condition is any one of the following conditions:

within a range diagnosed as normal by the diagnosing section, the operation data of the machine or equipment for the predetermined period is relatively largely deviated from the normal model;

a step of setting, as a reference, a production quantity of the article produced by the machine or the facility to exceed a predetermined reference when starting use of the normal model used by the diagnosis unit or when finishing acquisition of the operation data for each predetermined period used by the generation unit in generation of the normal model;

setting an elapsed time exceeding a predetermined reference, based on a start of use of the normal model used by the diagnostic unit or an end of acquisition of the operation data for each predetermined period used by the generating unit for generating the normal model; and

the environmental conditions around the equipment or facility are changed relatively largely with reference to the start of use of the normal model used by the diagnosis unit or the end of acquisition of the operation data for each of the predetermined periods used by the generation unit in generating the normal model.

5. The diagnostic device of claim 3 or 4, comprising:

a first input unit that accepts input from a user; and

and a first setting unit that performs setting relating to the first condition based on a predetermined input received by the first input unit.

6. The diagnostic device of any one of claims 1 to 5,

the generation unit automatically updates the normal model used by the diagnosis unit based on the operation data for each predetermined period used for the diagnosis by the diagnosis unit.

7. The diagnostic device of claim 6,

the generation unit automatically updates the normal model used by the diagnosis unit based on the operation data for each of a plurality of predetermined periods, in which a predetermined number or a predetermined ratio of the operation data for each of the plurality of predetermined periods used for generation of the normal model before updating is replaced with the operation data for each of the predetermined periods used by the diagnosis unit for diagnosis based on the normal model before updating.

8. The diagnostic device of claim 6,

the generation unit automatically updates the normal model used by the diagnosis unit based on the operation data for the predetermined period of a predetermined number of latest times used by the diagnosis unit for the diagnosis based on the normal model before the update.

9. The diagnostic device of any one of claims 6 to 8, comprising:

a second input unit that accepts input from a user; and

and a second setting unit that performs, based on a predetermined input received by the second input unit, a setting regarding a method in which the generating unit automatically updates the normal model used by the diagnosing unit based on the operation data for each predetermined period used for the diagnosis performed by the diagnosing unit.

10. The diagnostic device of any one of claims 1 to 9,

the diagnostic unit returns the normal model used for the diagnosis to the normal model before the update when the normal model updated by the generating unit deviates from a normal range of the operating state of the machine or equipment by more than a predetermined reference.

11. The diagnostic device of claim 10,

the diagnostic unit returns the normal model used for the diagnosis to the normal model before the update when a second condition that can determine that the normal model updated by the generation unit deviates from a normal range of the operating state of the machine or equipment by more than a predetermined reference is satisfied,

the second condition is that the frequency of the operation state of the equipment or device diagnosed as abnormal by the diagnosing unit increases and exceeds a predetermined reference before and after the update of the normal model, or that the diagnostic result of the diagnosing unit shows a change exceeding the predetermined reference in a direction deviating from a normal range of the operation state of the equipment or device before and after the update of the normal model.

12. The diagnostic apparatus of claim 11, comprising:

a third input unit that accepts input from a user; and

and a third setting unit that performs setting relating to the second condition based on a predetermined input received by the third input unit.

13. A diagnostic method comprising:

a generation step of generating, by a diagnostic device, a normal model indicating a normal operating state of a machine or equipment based on previously acquired operating data indicating a time-series operating state of the machine or equipment for each predetermined period; and

a diagnosis step of performing, by the diagnosis device, a diagnosis regarding an abnormality in an operating state of the equipment or facility based on the normal model and the operation data of the equipment or facility acquired later during the predetermined period,

14. A diagnostic program that causes a diagnostic device to execute the steps of:

a diagnosis step of performing a diagnosis concerning an abnormality in an operating state of the machine or equipment based on the normal model and the operation data of the machine or equipment acquired later during the predetermined period,