Abnormal modulation cause display device, abnormal modulation cause display method, and abnormal modulation cause display program

Abstract

The objective of the present invention is to improve the accuracy of identifying causes of abnormal modulation in a production facility, and to propose suitable measures to a user. This abnormal modulation cause display device is provided with: a process data acquiring unit for reading process data from a storage device which stores process data output continuously by a plurality of sensors provided in a production facility; an abnormality determining unit for calculating a degree of abnormality representing the extent of modulations in the process data read by the process data acquiring unit; a cause diagnosing unit for determining whether the degree of abnormality calculated by the abnormality determining unit satisfies a prescribed standard, in relation to the process data output by the plurality of sensors, using causal relationship information defining a combination of a cause and a modulation of the process data output by the plurality of sensors, manifested as an effect arising from said cause; and an output control unit for reading information indicating a measure to be taken, from a storage device which additionally stores information indicating measures to be taken with respect to causes, and causing an output device to output the information.

Description

[Technical Field]

[0001] The present disclosure relates to an abnormal modulation cause display device, an abnormal modulation cause display method, and an abnormal modulation cause display program. [Background technology]

[0002] Conventionally, a plant control and monitoring device has been proposed that includes a display device that indicates the operating status of each facility, device, and process by representing process status signals output from multiple facilities, equipment, and processes included in a plant using predetermined symbols, and the display device has at least a monitoring screen for monitoring the operation of the plant, a guidance screen including guidance selected according to the importance of the alarm for dealing with the above-mentioned alarms, and an operation screen for operating the plant, and is configured so that when an alarm occurs, the display device displays a display indicating whether or not a guidance screen corresponding to the alarm is available, and further includes a first input means for calling up a guidance screen corresponding to the alarm on the display screen when an alarm occurs (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 3699676 Summary of the Invention [Problem to be solved by the invention]

[0004] In general, it is desirable to prevent abnormalities in production facilities and minimize their impact on safety, stability, product quality, costs, etc. This technology aims to improve the accuracy of identifying the cause of abnormalities in production facilities and to propose appropriate countermeasures to users. [Means for solving the problem]

[0005] The abnormal modulation cause display device includes a process data acquisition unit that reads process data from a storage device that stores process data that is continuously output by multiple sensors equipped in the production equipment, an abnormality determination unit that calculates an abnormality level that indicates the degree of modulation of the process data read by the process data acquisition unit, a cause diagnosis unit that determines whether the abnormality level calculated by the abnormality determination unit for the process data output by the multiple sensors satisfies a predetermined standard by using causal relationship information that defines a combination of a cause and the modulation of the process data output by the multiple sensors that appears as an effect resulting from the cause, and an output control unit that reads information indicating the measures to be taken for the cause from the storage device that further stores information indicating the measures, and outputs the information to an output device.

[0006] By using the causal relationship information described above, the amount of process data output by multiple sensors affected by a cause that meets a predetermined standard of anomaly level increases, making it possible to detect an anomaly due to some cause. In other words, even if the amount of process data output by multiple sensors that meets a predetermined standard of anomaly level is small, it is possible to detect signs of an anomaly due to some cause. This improves the ability to identify the cause of abnormality in production equipment. Furthermore, based on the cause identified in this way, it becomes possible to suggest appropriate measures to the user depending on the situation.

[0007] The cause diagnosing unit may further include an output control unit that multiplies a plurality of types of process data by a coefficient according to the type of process data or a coefficient based on the magnitude of the degree of abnormality to determine the probability of the cause of the modulation, and outputs a plurality of candidate causes that may cause the modulation and the probability of the candidate causes to an output device. Based on the candidate causes and their probability, the user can select an appropriate measure.

[0008] Furthermore, the output control unit may be configured to output to the output device a logic tree in which, based on the causal relationship information, the modulation is taken as the root and the cause of the modulation is taken as the leaf, and events that appear in the process from the cause to the modulation are hierarchically connected, and to output to the output device information that is associated with the cause and indicates measures to be taken for the cause. Such a logic tree makes it possible to display events that appear in the process leading to the modulation and the cause of the modulation in a manner that is easy for the user to visually recognize.

[0009] The contents of the means for solving the problem can be combined as much as possible without departing from the problem and technical idea of the present disclosure. The contents of the means for solving the problem can be provided as a device such as a computer or a system including multiple devices, a method executed by a computer, or a program executed by a computer. A recording medium storing the program may also be provided. [Effects of the Invention]

[0010] According to the disclosed technology, it is possible to improve the accuracy of identifying the cause of abnormal modulation in production equipment and to propose appropriate countermeasures to the user. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a system according to this embodiment. [Figure 2] FIG. 2 is a schematic diagram showing an example of a process performed by equipment included in a plant. [Figure 3] FIG. 3 is a diagram illustrating an example of process data in a batch process. [Figure 4] FIG. 4 is a diagram showing an example of a process line definition table that is set in advance. [Figure 5] FIG. 5 is a diagram showing an example of a tag definition table that is set in advance. [Figure 6] FIG. 6 is a diagram for explaining an example of process data in a continuous process. [Figure 7] FIG. 7 is a diagram illustrating an example of traceability information. [Figure 8] FIG. 8 is a diagram for explaining the association between process data in a continuous process and a serial number in a batch process. [Figure 9] FIG. 9 is a diagram showing an example of information registered in advance in the knowledge base. [Figure 10] FIG. 10 is a diagram showing an example of a logic tree representing the relationship between modulation and its causes. [Figure 11] FIG. 11 is a diagram for explaining the synchronization process of the process data. [Figure 12] FIG. 12 is a diagram illustrating an example of calculating the degree of abnormality of time-series data based on the distance from the reference. [Figure 13] FIG. 13 is a diagram illustrating an example of calculating the degree of abnormality based on the distance from the reference, taking into consideration the positive and negative directions of the time-series data. [Figure 14] FIG. 14 is a diagram for explaining anomaly detection using an autoencoder. [Figure 15] FIG. 15 is a block diagram showing an example of the configuration of an abnormal modulation cause identifying device. [Figure 16] FIG. 16 is a process flow diagram showing an example of a learning process executed by the abnormal modulation cause identifying device. [Figure 17] FIG. 17 is a diagram illustrating an example of the action table. [Figure 18] FIG. 18 is a process flow diagram showing an example of an abnormality detection process executed by the abnormal modulation cause identifying device. [Figure 19] FIG. 19 is a diagram showing an example of a screen output to the input / output device. [Figure 20] FIG. 20 is a diagram showing another example of a screen output to the input / output device. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment of an abnormal modulation cause identifying device will be described with reference to the drawings.

[0013] <Embodiment> FIG. 1 is a diagram illustrating an example of a system according to this embodiment. The system 100 includes an abnormal modulation cause identification device 1, a control station 2, and a plant 3. The system 100 is, for example, a distributed control system (DCS) and includes multiple control stations 2. That is, the control system of the plant 3 is divided into multiple sections, and each control section is controlled in a distributed manner by the control station 2. The control station 2 is an existing facility in the DCS, and receives status signals output from sensors and the like provided in the plant 3, and outputs control signals to the plant 3. Then, actuators such as valves and other devices provided in the plant 3 are controlled based on the control signals.

[0014] The abnormal modulation cause identification device 1 acquires status signals (process data) from the plant 3 via the control station 2. The process data includes the temperature, pressure, flow rate, etc. of processing targets, such as raw materials and intermediate products, as well as set values that determine the operating conditions of equipment in the plant 3. The abnormal modulation cause identification device 1 also creates an abnormality detection model based on a knowledge base that stores correspondences between expected causes and, for example, effects that appear as abnormalities. For example, a model for identifying abnormal modulation, its signs, and its causes is created based on a method for detecting deviations from an allowable range in changes in process data created based on the knowledge base. The abnormal modulation cause identification device 1 can then detect the occurrence of abnormal modulation or its signs using the model and the process data. The abnormal modulation cause identification device 1 may also determine, for example, candidate operating conditions for suppressing abnormal modulation based on the identified cause and a table that stores causes of abnormal modulation and actions to address them, and present the candidate operating conditions to a user.

[0015] FIG. 2 is a schematic diagram showing an example of a process performed by equipment provided in a plant. In this embodiment, the process may include a batch process 31 and a continuous process 32. In the batch process 31, the processing target is sequentially processed for each predetermined processing unit, and processing such as receiving, holding, and discharging raw materials into each equipment is performed in sequence. In the continuous process 32, the processing target that is continuously introduced is continuously processed, and processing such as receiving, holding, and discharging raw materials is performed in parallel. In addition, the process may include multiple series 33 that perform the same processing in parallel.

[0016] The equipment performing each process includes, for example, a reactor, a distillation apparatus, a heat exchanger, a compressor, a pump, a tank, etc., which are connected via piping. In addition, sensors, valves, etc. are provided at predetermined positions in the equipment and piping. The sensors may include a thermometer, a flow meter, a pressure gauge, a level gauge, a concentration meter, etc. The sensors monitor the operating status of each equipment and output a status signal. Furthermore, the sensors provided in the plant 3 are assumed to be attached with "tags," which are identification information for identifying each sensor. In other words, the type of process data can be identified based on the tags. The abnormal modulation cause identification device 1 and the control station 2 manage the input / output signals to each equipment based on the tags.

[0017] <Batch process> FIG. 3 is a diagram illustrating an example of process data in a batch process. The left column of FIG. 3 shows a portion of the process of the batch process 31 shown in FIG. 2. Specifically, the process includes a shredder 301, a cyclone 302, pretreatment 303, a pre-cooler 304, and a reactor 305. These processes are further classified into a pretreatment process, a pre-cooling process, and a reaction process. The right column of FIG. 3 shows an example of process data acquired in each process. In the pretreatment process, time-series data is acquired from sensors with tags 001 and 002. In the pre-cooling process, time-series data is acquired from sensors with tags 003 and 004. In the reaction process, time-series data is acquired from sensors with tags 005, 006, and 007. In the batch process, processing objects associated with serial numbers (also referred to as "production numbers," "batch numbers," or "control numbers") are intermittently processed. In other words, the serial number is identification information for identifying processing targets that are processed collectively in a batch process. As shown in FIG. 3, time-series data related to processing targets associated with subsequent serial numbers is obtained over time. In this embodiment, the control station 2 manages serial numbers and steps that indicate processing stages in the subdivided processes that make up the batch process. When steps are reset by a programmable logic controller (PLC) in the plant 3 connected to the control station 2, the serial number of the process data output from the control station 2 may be used as appropriate in accordance with the timing of communication between the control station 2 and the plant 3 (for example, after a step is switched in the PLC, or after a set time has elapsed). The set time may also be set for each production line and each subdivided process.

[0018] FIG. 4 is a diagram showing an example of a process line definition table that is set in advance. In the process line definition table, for each series and process, a manufacturing number, a definition of a step indicating the stage of processing in each process, and the type of product to be processed in each process are registered. The process line definition table may be a so-called database table or a file in a predetermined format such as CSV. The process line definition table is also created in advance by the user and read out by the abnormal modulation cause identification device 1.

[0019] The process line definition table includes attributes such as series, process, serial number, step, and product type. The series field stores identification information for specifying the process series. The process field stores identification information for indicating the subdivided processes in a batch process. The serial number field stores a serial number, which is identification information for identifying the processing objects that are processed collectively in a batch process. The step field stores a definition of the timing of multiple steps that indicate the processing stages in the process. The product type field stores the type of processing object.

[0020] 5 is a diagram showing an example of a preset tag definition table, which defines the timing of acquiring process data obtained from a sensor corresponding to each tag. The tag definition table may be a so-called database table or a file in a predetermined format such as CSV (Comma Separated Values). The tag definition table is created in advance by a user and is read out by the abnormal modulation cause identifying device 1.

[0021] The tag definition table includes the attributes of tag, series, process, and collection interval. The tag field registers a tag that is identification information for a sensor. The series field registers identification information for specifying a process series. The process field registers identification information that indicates a subdivided process in a batch process. The collection interval field registers information that indicates the interval at which the sensor output value is acquired.

[0022] <Continuous process> FIG. 6 is a diagram illustrating an example of process data in a continuous process. The left column of FIG. 6 shows a part of the process of continuous process 32 shown in FIG. 2. Specifically, the process includes a tank 311 and a pump 312. The right column of FIG. 6 shows an example of process data acquired in each process. In continuous process 32, time-series data associated with tags but not with serial numbers is continuously acquired from sensors. In the continuous process, time-series data is acquired from sensors with tags 102 and 103. In the continuous process, equipment continuously receives processing objects and continuously processes them.

[0023] When a continuous process is performed after a batch process, traceability information set in advance by the user is used in this embodiment to link the processing target in the batch process with the processing target in the continuous process. FIG. 7 is a diagram showing an example of traceability information. The traceability information includes attributes of a sampling interval and a residence time. The sampling interval field is registered with the interval at which sampling is performed in the continuous process for process inspection using, for example, a reduction method. The residence time field is registered with the time the processing target remains in the process from the completion of the batch process until it reaches the process included in the continuous process.

[0024] FIG. 8 is a diagram illustrating the association between process data in a continuous process and serial numbers in a batch process. Process data is acquired, for example, at intervals set in the traceability information. Furthermore, when a continuous process is performed after a batch process, the product of the batch process completed within a predetermined period is introduced into a tank or the like as the processing target for the continuous process. Therefore, the process data for the continuous process can be traced back to the residence time of the processing target from the completion of the batch process to the time of measurement by a sensor, and associated with a group of serial numbers whose completion time of the batch process falls within the predetermined period. This association improves the accuracy of identifying the cause of an abnormality using the process data of the batch process when a batch process and a continuous process are performed consecutively.

[0025] As described above, by associating the serial number in batch processing with the timing of measurement in continuous processes, it is possible to improve the accuracy of identifying the cause of an abnormality.

[0026] FIG. 9 is a diagram showing an example of information pre-registered in a knowledge base. The knowledge base is pre-stored in a storage device of the abnormal modulation cause identification device 1. The table in FIG. 9 includes an "effect" column corresponding to each sensor (tag) and rows indicating the "assumed cause" of the modulation. That is, the direction of value fluctuation is registered in the column corresponding to the sensor affected by the cause such as "Cause 1" or "Cause 2" shown in each row. In the knowledge base, the direction of fluctuation is displayed as "up" which indicates an increase (rise) in the sensor output value or "down" which indicates a decrease (fall). As shown in FIG. 9 , the combination of cause and effect is not necessarily one-to-one. Furthermore, the process data calculation method, extraction timing, threshold values used for abnormality determination, and the like are defined for each sensor. The calculation method row registers information indicating the calculation to be performed on the output value of each sensor. In this embodiment, the calculation is performed using a machine learning method such as the Hotelling algorithm, k-nearest neighbor algorithm, DTW Barycenter Averaging, Autoencoder, or Graphical Lasso. The extraction timing row registers information indicating the timing at which a value to be used for abnormality determination is extracted from the output value of each sensor. For example, in batch processing, the timing may be defined by a step indicating a processing stage in each process, a specific period, or a specific time point. In continuous processing, the timing may be defined by a sampling interval, as shown in FIG. 7 . The threshold row registers a threshold value, which is the standard for determining an abnormality in each abnormality determination method. The threshold may include, for example, two limits, an upper limit and a lower limit. As described above, the knowledge base defines the combination of causal relationships between a causal event and an effect, which is the resulting process data modulation. In addition, combinations of causal relationships can be represented in a tree format, with the modulation that appears as an effect as the root and its assumed causes as the leaves, and the events that appear in the process from the cause to the modulation connected hierarchically in chronological order.

[0027] The knowledge base is prepared in advance by a user based on, for example, a Hazard and Operability Study (HAZOP). HAZOP is a method for comprehensively listing, in relation to, for example, detection methods at monitoring points using instrumentation in a plant, control ranges (upper and lower thresholds and alarm settings), deviations from the control ranges (abnormalities and abnormalities), a list of assumed causes of deviations from the control ranges, logic (detection methods) for determining which assumed cause caused the deviation, the impact of the deviation, measures to be taken when the deviation occurs, and actions to take in response to the measures. The knowledge base may be prepared based on methods other than HAZOP, such as Fault Tree Analysis (FTA), Failure Mode and Effect Analysis (FMEA), Event Tree Analysis (ETA), or methods based on these or similar methods, information extracted from operator interviews, or information extracted from work standards or technical standards. In this embodiment, anomaly detection is performed based on parameters that are considered to have a causal relationship in the knowledge base.

[0028] Based on the information set in the table, the abnormal modulation cause identification device 1 extracts data at a predetermined timing from the process data acquired from the plant 3 and performs an abnormality determination using a predetermined method. Figure 10 shows an example of a logic tree representing the relationship between modulations and their causes. The logic tree can be created based on the knowledge base shown in Figure 9. The logic tree in Figure 10 places early events on the upstream side of the production process on the left side, and later events on the downstream side of the production process on the right side. Arrows connect the assumed causes hierarchically to the modulations that appear as effects. If multiple assumed causes exist for a single modulation in the knowledge base table, the logic tree branches and connects them, and displays the events that commonly appear in the process from the assumed causes to the modulation. The thick solid-line rectangles at the upstream end of each branch correspond to the assumed causes in the knowledge base table, and correspond to the numbers in parentheses in Figures 9 and 10. The thin solid-line rectangles correspond to the effects in the knowledge base table and represent events that can be observed from the process data. For each of these effects, calculations are performed according to the calculation method defined in the knowledge base table. In addition, for each assumed cause, a model containing a formula for performing the above calculations is defined, and the model can be used to detect abnormalities or their precursors and to assist in identifying their causes.

[0029] <Calculation method> The above calculation may include, for example, the following methods: Furthermore, the abnormal modulation cause identifying device 1 may display the results of these calculations.

[0030] Hotelling method (T 2 law) For example, assuming that multiple process data obtained from one sensor follow a predetermined probability density function, the population mean and standard deviation are estimated from the sample mean and sample standard deviation calculated using the process data. The predetermined probability density function is, for example, a normal distribution. The degree of anomaly is then calculated based on the distance from the population mean to the process data to be verified. For example, the degree of anomaly is determined based on the square of the Mahalanobis distance. Note that the instantaneous value of the process data itself may be used, or the degree of anomaly based on Hotelling's theory may be calculated using the maximum value, minimum value, integral value, standard deviation, or differential coefficient (slope) of the process data over a predetermined period. The Hotelling's method makes it possible to detect outliers from a predetermined standard.

[0031] ·K-nearest neighbor method For example, time-series process data obtained from one or more sensors is vectorized or converted into a matrix, and the distance between the data is calculated. The distance may be Euclidean distance, Mahalanobis distance, or Manhattan distance. The degree of anomaly is then determined based on the distance from the data to be verified to the kth closest data. In the k-nearest neighbor method, the determination is based on the relationship with other data. Therefore, for example, in cases where normal values can be classified into multiple clusters, it is possible to detect outliers that are far from any of the clusters.

[0032] ·DTW(Dynamic Time Wrapping) Barycenter Averaging Average time series data can be calculated based on multiple time series data, such as process data from different batch processes. For example, the distance between each of the process data with different serial numbers in a corresponding section of the batch process and the average time series data can be calculated. Figure 11 is a diagram illustrating process data synchronization. For each element value contained in the time series data of batch processes with different serial numbers, the shortest distance between the values contained in the different time series data is calculated in a brute-force manner, and the time series data is aligned by sliding along the time axis to minimize the cumulative value of the shortest distances. In other words, multiple time series data are synchronized based on the similarity of the time series data. This allows multiple process data to be displayed overlapping each other so that the steps in the processes performed in plant 3 correspond in time series. The degree of anomaly is then calculated based on the cumulative value of the distance between the synchronized time series data using k-nearest neighbors or Hotelling's theory. DTW Barycenter Averaging enables anomalies to be detected based on the degree of similarity between time series data.

[0033] The degree of anomaly may be calculated by assigning a positive or negative sign to deviation from a reference such as an average. FIG. 12 is a diagram illustrating an example of calculating the degree of anomaly based on the magnitude of the distance from the reference for time-series data. FIG. 13 is a diagram illustrating an example of calculating the degree of anomaly based on the distance from the reference for the same time-series data, taking into account the positive and negative directions. In each diagram, the vertical axis represents, for example, the degree of deviation from the average. Although modulation actually occurs in the area indicated by the dashed rectangle, it is difficult to detect based only on the values shown in the example of FIG. 12. On the other hand, the example of FIG. 13 shows a tendency for deviations in the opposite positive and negative directions, making it easy to detect modulation.

[0034] For example, in the Hotelling method described above, the degree of deviation from the standard is calculated as a value with a positive or negative sign without squaring the distance, thereby obtaining the degree of anomaly as shown in Fig. 13. In DTW Barycenter Averaging and the like, a positive or negative sign is determined for characteristic points such as maximum values in time-series data using, for example, the following formula, and the calculated value is multiplied by the magnitude of the distance. Sign determination formula = (μ-x) / |μ-x| Here, μ is the average value (reference value) of the training data, and x is the process data to be verified. In this way, according to the sign determination formula, it is possible to determine the sign representing the direction of deviation from the reference at a given time point in time, depending on the magnitude relationship between the reference value at the given time point in time and the process data to be verified at the corresponding time point. Furthermore, by using a signed value indicating the degree of deviation from the reference, it is possible to obtain the degree of anomaly as shown in FIG. 13, thereby reducing false detections. Furthermore, in addition to local maximum values, local minimum values, the difference between process data at a certain time point and process data at another time point, etc. may also be used as characteristic points in the time series data.

[0035] Autoencoder FIG. 14 is a diagram illustrating anomaly detection using an autoencoder. This method performs anomaly detection based on the relationship between process data from multiple sensors. Specifically, a neural network is used to create a model that can compress (encode) and decode (decode) input data using, for example, continuous or batch process process data itself as training data. In a neural network, the number of nodes in the input and output layers corresponds to the number of sensors, while the number of nodes in the middle layer is less than the number of sensors. Information input to the input layer is compressed in the middle layer and restored in the output layer. Note that multiple middle layers may exist, and the connection structure between layers is not limited to full connections. Then, a learning process is performed using normal process data as training data, and a model is created with parameters adjusted to minimize the difference between the input layer and output layer values. Furthermore, in the anomaly detection process, the process data to be verified is input, and the degree of anomaly is calculated based on the difference between the input layer and output layer values. In other words, when anomalous process data is input, the information compressed in the middle layer cannot be properly restored in the output layer, resulting in a large difference between the values in the input layer and output layer. Anomaly detection can be performed based on this difference. An autoencoder can detect abnormalities based on the characteristics of the relationship between output values of multiple sensors.

[0036] Graphical Lasso For example, the dependency relationships between variables are quantified based on the covariance matrix of process data from multiple sensors in continuous or batch processing, and are represented as a sparse reference graph. Under normal conditions, it can be determined that the dependency relationships between variables do not deviate significantly from the reference. Then, in the anomaly detection process, the dependency relationships between variables are determined using the process data to be verified, and the degree of anomaly is calculated according to the magnitude of the difference from the above-mentioned reference. Using the Graphical Lasso, the correlation between process data can be quantified, and the degree of anomaly can be detected based on the disruption of the relationship.

[0037] Other general anomaly detection methods or methods that apply these may also be used. Furthermore, the threshold values used for anomaly detection in each method may be searched for using process data actually obtained during operation of the plant 3, so as to minimize erroneous judgments under normal conditions and to quickly detect the occurrence of an anomaly or its sign under abnormal conditions, and the searched values may be registered in the knowledge base shown in Fig. 9.

[0038] <Device configuration> FIG. 15 is a block diagram showing an example of the configuration of the abnormal modulation cause identifying device 1. The abnormal modulation cause identifying device 1 is a general-purpose computer and includes a communication interface (I / F) 11, a storage device 12, an input / output device 13, and a processor 14. The communication I / F 11 may be, for example, a network card or a communication module, and communicates with other computers based on a predetermined protocol. The storage device 12 may be a main storage device such as a random access memory (RAM) or a read-only memory (ROM), or an auxiliary storage device (secondary storage device) such as a hard-disk drive (HDD), a solid-state drive (SSD), or a flash memory. The main storage device temporarily stores programs read by the processor 14 and information exchanged with other computers, and secures a working area for the processor 14. The auxiliary storage device stores programs executed by the processor 14, information exchanged with other computers, and the like. The input / output device 13 is, for example, a user interface such as an input device such as a keyboard or a mouse, an output device such as a monitor, or an input / output device such as a touch panel. The processor 14 is an arithmetic processing device such as a CPU (Central Processing Unit), and executes programs to perform each process according to this embodiment. The example of Fig. 15 shows functional blocks within the processor 14. That is, by executing predetermined programs, the processor 14 functions as a process data acquisition unit 141, a preprocessing unit 142, a learning processing unit 143, an abnormality determination unit 144, a cause diagnosis unit 145, and an output control unit 146.

[0039] The process data acquisition unit 141 acquires process data from sensors provided in the plant 3, for example, via the communication I / F 11 and the control station 2, and stores the acquired process data in the storage device 12. As described above, the process data is associated with the sensors by tags.

[0040] The preprocessing unit 142 processes the process data when creating an anomaly detection model. For example, the preprocessing unit 142 links the process data with a serial number. That is, based on the traceability information previously stored in the storage device 12, the preprocessing unit 142 links the process data corresponding to a predetermined tag, system, and serial number in batch processing with the process data corresponding to a predetermined tag in continuous processing and output at a predetermined timing. The preprocessing unit 142 also extracts data for a predetermined period to be used for anomaly detection based on settings in a table such as a knowledge base, and calculates feature quantities according to each method. In the learning process, the preprocessing unit 142 may perform data cleansing to extract training data by excluding data from non-steady operating periods, data when an anomaly occurs, and outliers such as noise.

[0041] The learning processing unit 143 creates an anomaly detection model including one or more operations based on, for example, a knowledge base, and stores the model in the storage device 12. At this time, the learning processing unit 143 determines parameters that have learned the characteristics of the training data. Note that when performing learning processing using output values from multiple sensors, normalization may be performed as appropriate.

[0042] The abnormality determination unit 144 calculates the degree of abnormality using the process data and the abnormality detection model. That is, in the learning process, the anomaly determination unit 144 calculates the degree of anomaly using test data for cross-validation and the anomaly detection model, and in the anomaly determination process, calculates the degree of anomaly using process data acquired from the plant 3.

[0043] The cause diagnosis unit 145 calculates the probability (accuracy) of each of the multiple assumed causes using the calculated abnormality degree. The probability is calculated, for example, using the abnormality degree calculated by the abnormality determination unit, based on the proportion and degree of influence that appears in the process data among the influences associated with each assumed cause in the knowledge base. In addition, actions that indicate measures to be taken against the cause may be stored in the storage device 12 in association with each assumed cause, so that the actions can be presented to the user.

[0044] The output control unit 146 issues an alarm when an abnormality is detected, and outputs the probability of each assumed cause, for example, via the input / output device 13. The output control unit 146 is connected to the above-mentioned components via the bus 15 as appropriate in response to a user operation. For convenience, one device shown in Fig. 15 includes the process data acquisition unit 141, the preprocessing unit 142, the learning processing unit 143, the abnormality determination unit 144, the cause diagnosis unit 145, and the output control unit 146, but at least some of the functions may be distributed and provided in different devices.

[0045] <Learning process> FIG. 16 is a process flow diagram showing an example of a learning process executed by the abnormal modulation cause identification apparatus 1. The processor 14 of the abnormal modulation cause identification apparatus 1 executes a predetermined program to perform the process shown in FIG. 16. The learning process is performed at any timing using process data obtained through past operations of the plant 3. The learning process mainly includes pre-processing (FIG. 16: S1), model construction process (S2), and verification process (S3). That is, cross-validation may be performed using part of the process data as training data and the rest as test data. It is assumed that the above-mentioned tables and the like are created by a user and stored in the storage device 12 in advance. For convenience, the pre-processing, learning process, and verification process are described in one process flow shown in FIG. 16. However, at least part of the pre-processing, verification process, etc. may be distributed and executed by different devices.

[0046] The process data acquisition unit 141 of the abnormal modulation cause identification device 1 acquires process data (S11 in FIG. 16). In this step, data to be used in the anomaly detection model is extracted from the process data such as those shown in FIG. 3 and FIG. 6. The process data is assumed to be stored in the storage device 12 in a file of a predetermined format such as OPC data, a so-called database table, or CSV. The process data also includes attributes such as date and time and tags, and may further include attributes such as a serial number and step, particularly in the case of batch processing process data.

[0047] Furthermore, the pre-processing unit 142 of the abnormal modulation cause identifying device 1 links the process data of the continuous processing with the serial numbers (S12 in FIG. 16). In this step, as shown in FIG. 8, the process data acquired in the continuous process is associated with the group of serial numbers of the process data acquired in the batch processing, and the process data to be used in calculating the degree of abnormality is associated. That is, in the knowledge base shown in FIG. 9 or the logic tree shown in FIG. 11, if a certain cause affects both the process data of the batch processing and the process data of the continuous processing, the degree of abnormality and the degree of occurrence are calculated based on the data linked in this step.

[0048] Then, the pre-processing unit 142 extracts and processes data to be used in the abnormality determination model (FIG. 16: S13). In this step, the pre-processing unit 142 extracts data for a predetermined period to be used for abnormality determination based on the setting values of a table such as a knowledge base, and calculates feature quantities according to each method.

[0049] For example, when calculating the degree of anomaly using the Hotelling method, the preprocessing unit 142 extracts process data at a predetermined timing or period, calculates instantaneous values, which are the process data itself, maximum values, minimum values, integral values, or differences of the process data, integral values of reaction rates, and differential coefficients at predetermined times, and stores these values in the storage device 12. When calculating the degree of anomaly using the k-nearest neighbor method, the preprocessing unit 142 vectorizes or matrixes the time-series process data. When calculating the degree of anomaly using DTW Barycenter Averaging, the preprocessing unit 142 synchronizes multiple pieces of process data to obtain average time-series data. When calculating the degree of anomaly using an autoencoder or graphical lasso, the preprocessing unit 142 synchronizes multiple pieces of process data.

[0050] The pre-processing unit 142 may perform predetermined data cleansing on the process data. The data cleansing process is a process for eliminating outliers, and various methods can be used. For example, a moving average value may be calculated using the most recent data. Alternatively, the difference between the moving average value and the actual measurement value may be calculated to obtain the standard deviation σ, which represents the variation in the difference. Values that do not fall within a predetermined confidence interval, such as the interval from the mean value of the probability distribution -3σ to the mean value of the probability distribution +3σ (also called the 3σ interval), may be excluded. Similarly, values that do not fall within the 3σ interval for the difference between the actual measurement values before and after the value may be excluded.

[0051] Then, the learning processing unit 143 of the abnormal modulation cause identification device 1 performs an anomaly detection model construction process (S2 in FIG. 16). In this step, an anomaly detection model including an anomaly degree calculation is created based on the knowledge base shown in FIG. 9. Specifically, for one or more "effects" associated with each of the "assumed causes" in FIG. 9, the learning processing unit 143 calculates an anomaly degree using the method registered in the "calculation method" for each of the "impacts," and creates an anomaly detection model represented by a combination of anomaly degrees. Depending on the anomaly detection method, the learning processing unit 143 also adjusts the model parameters using training data. For example, when calculating an anomaly degree using an autoencoder, the learning processing unit 143 adjusts the weighting coefficients between layers so that the input process data can be restored after being compressed. When calculating an anomaly degree using a graphical lasso, the learning processing unit 143 quantifies the intervariance relationship between variables based on the covariance matrix of process data from multiple sensors. The learning processing unit 143 then stores the created anomaly detection model in the storage device 12.

[0052] The anomaly determination unit 144 of the abnormal modulation cause identification device 1 calculates the degree of anomaly using the created anomaly detection model and test data (FIG. 16: S31). In this step, the anomaly determination unit 144 calculates the degree of anomaly according to the method of calculating the degree of anomaly. For example, when calculating the degree of anomaly using the Hotelling method, the sample mean and sample standard deviation of the population are estimated using the process data, and the degree of anomaly is calculated based on the distance from the population mean to the process data to be verified. When calculating the degree of anomaly using the k-nearest neighbor method, the distance between data is calculated, and the degree of anomaly is calculated based on the distance from the data to be verified to the kth closest data. When calculating the degree of anomaly using DTW Barycenter Averaging, the degree of anomaly is calculated using the k-nearest neighbor method or the Hotelling theory based on the integrated value of the distance between time-series data synchronized in preprocessing. When calculating the degree of anomaly using an autoencoder, the process data to be verified is input to the autoencoder, and the degree of anomaly is calculated based on the difference between the value of the input layer and the value of the output layer. When calculating the degree of anomaly using the Graphical Lasso method, the process data to be verified is used to determine the dependency relationship between variables, and the degree of anomaly is calculated based on the magnitude of the difference from the reference dependency relationship.

[0053] The cause diagnosis unit 145 of the abnormal modulation cause identification device 1 calculates the degree of validity of the assumed cause using the calculated abnormality degree (S32 in FIG. 16). In this step, the degree of validity is calculated for each assumed cause in the knowledge base based on the rate at which the corresponding modulation appears as an effect. For example, cause (2) in FIG. 9 is associated with three effects: an increase in moisture content in tag 002, an increase in temperature 1 in tag 004, and a decrease in temperature 2 in tag 005. Using the abnormality degrees calculated for each effect in S31 in FIG. 16, the proportion of the three effects whose abnormality degrees exceed a threshold may be used to determine the degree of validity. If the abnormality degrees for two of the three effects exceed the threshold, the degree of validity may be, for example, 66.7%. Furthermore, weighting may be applied to the calculation of the degree of validity based on the type of effect (tag) or the magnitude of the abnormality degree. For example, the degree of validity may be calculated by multiplying each effect by a weight and then calculating the sum of the weights.

[0054] The output control unit 146 also outputs the anomaly degree calculated in S31 and the feasibility degree calculated in S32 so that the user can evaluate the created model (S33 in FIG. 16). In this step, cross-validation is performed using test data, which is different from the training data used to build the model, among process data collected during past operations of the plant 3. In this step, process data from when an anomaly occurred in the past is also used to verify whether the anomaly is appropriately detected and whether an alarm or an action to address the anomaly is output. The learning processing unit 143 also determines whether the anomaly can be detected with sufficient accuracy (S4 in FIG. 16). If it is determined that the accuracy is insufficient (S4: NO), the threshold value registered in the knowledge base (in other words, the normal range of the process data) is modified so that the anomaly can be appropriately detected, and the processing from S31 onwards is repeated. If it is determined in S4 that the anomaly can be detected with sufficient accuracy (S4: YES), operation is performed using the anomaly detection model and threshold value created in S2. Note that at least a part of the determination in S4 may be made by the user.

[0055] It should be noted that, with regard to the actions, for example, actions that should be taken by an operator of the plant 3 to deal with the assumed cause are associated with the assumed cause and are stored in advance in the storage device 12. FIG. 17 is a diagram showing an example of an action table. The table in FIG. 17 includes attributes of cause, action 1, and action 2. In the cause field, a cause corresponding to the assumed cause in the knowledge base is registered. In the action 1 and action 2 fields, information indicating measures that should be taken by an operator of the plant 3 to resolve the corresponding cause is registered.

[0056] <Abnormality detection processing> FIG. 18 is a process flow diagram showing an example of an abnormality detection process executed by the abnormal modulation cause identification device 1. The processor 14 of the abnormal modulation cause identification device 1 executes a predetermined program to perform the process shown in FIG. 18. The abnormality detection process is performed almost in real time using process data obtained by the operation of the plant 3. The abnormality detection process mainly includes preprocessing (FIG. 18: S10), model readout process (S20), and abnormality determination process (S30). In FIG. 18, steps corresponding to those in the learning process shown in FIG. 16 are assigned the same reference numerals, and the following description will focus on differences from the learning process. For convenience, the process will be described as being performed by the same device as the device that performs the learning process, but the device that performs the abnormality detection process may be different from the device that performs the learning process. In addition, it is assumed that tables such as an anomaly detection model, thresholds, and knowledge base created in the learning process are stored in advance in the storage device 12.

[0057] The process data acquisition unit 141 of the abnormal modulation cause identification device 1 acquires process data (S11 in FIG. 18). The process data is assumed to be stored in the storage device 12 in a file of a predetermined format such as OPC data, a so-called database table, CSV, etc. This step is almost the same as S11 in FIG. 16, but data related to processes currently in operation in the plant 3 is acquired. Furthermore, the pre-processing unit 142 of the abnormal modulation cause identification device 1 associates the process data of continuous processing with the serial number (S12 in FIG. 18). This step is similar to S12 in FIG. 16. Then, the pre-processing unit 142 extracts and processes data to be used in the abnormality determination model (S13 in FIG. 18). This step is almost similar to S13 in FIG. 16, but data cleansing does not need to be performed.

[0058] Thereafter, the abnormality determination unit 144 of the abnormal modulation cause identification device 1 reads out the abnormality detection model created in the learning process from the storage device 12 (FIG. 18: S20). Furthermore, the abnormality determination unit 144 calculates the degree of abnormality using the created abnormality detection model and process data obtained by operation of the plant 3 (FIG. 18: S31). This step is the same as S31 in FIG. 16. Furthermore, the cause diagnosis unit 145 of the abnormal modulation cause identification device 1 determines the probability of the assumed cause being established using the calculated degree of abnormality (FIG. 18: S32). This step is the same as S32 in FIG. 16.

[0059] Furthermore, the output control unit 146 outputs the degree of abnormality calculated in S31 and the degree of establishment calculated in S32, and issues an alarm if either degree of abnormality exceeds a predetermined threshold (FIG. 18: S303). In this step, the process data indicating the operating state of the plant 3, the degree of abnormality, and the degree of establishment of the assumed cause are presented to the user via the input / output device 13.

[0060] FIG. 19 is a diagram showing an example of a screen output to the input / output device 13. FIG. 19 is an example of a main control chart, and shows the transition of individual process data using a line graph. An area 131 displayed on the input / output device 13 displays multiple combinations of the identification information and the latest values of process data acquired from the plant 3. The control chart in area 132 shows the transition of values of specific process data using a line graph. The vertical axis represents the value of the process data, and the horizontal axis represents the time axis. In the example of FIG. 19, the solid line represents the true value, and the dashed line represents the estimated value. The true value is the process data itself for which the degree of anomaly is to be calculated, and the estimated value may be an estimated value obtained by regression analysis of the process data for which the degree of anomaly is to be calculated. The thin dashed lines represent the upper and lower limits of the normal range (in other words, the threshold for anomaly detection). As shown by the balloon in FIG. 19, when a user operates the input / output device 13, such as a pointing device, to move a pointer on the graph, the numerical value of the process data at the time indicated by the pointer may be displayed. The cause-and-effect diagram in area 133 displays the causes of the modulation of the process data displayed in area 132 or tags that can identify them on the horizontal axis, and the vertical axis shows the probability of each cause as a bar graph. The higher the probability, the more likely the cause is to be the cause of the modulation of the process data. The probability is calculated by the cause diagnosis unit 145 based on the abnormality degree calculated by the abnormality determination unit 144 for events that are assumed to be the cause of the modulation of the process data. Based on the magnitude of the probability, the user can recognize potential causes of the modulation and their probability, and easily identify the cause of the modulation. When the "Diagnose" button in area 134 is pressed, the abnormality determination unit 144 calculates the abnormality degree at a specified time or the current time, and the cause-and-effect diagram is displayed by the output control unit 146. When the user operates the input / output device 13 such as a pointing device to select one of the bar graphs in the cause-and-effect diagram, the cause of the modulation corresponding to the bar graph is highlighted in the logic tree.

[0061] FIG. 20 is a diagram showing another example of a screen output to the input / output device 13 by the output control unit 146. FIG. 20 is an example of a tree diagram, and displays a logic tree similar to that shown in FIG. 10. For example, when the bar graph for tag 004 is selected in FIG. 19, the impact corresponding to the process data for tag 004 is highlighted on the logic tree. The highlighting is achieved by changing the display mode, for example, by changing the color or the line type. In FIG. 20, the corresponding rectangle is hatched. The thick rectangle connected to the upstream side of the logic tree represents the assumed cause of the impact. Each cause may be displayed as shown in a speech bubble in FIG. 20, or the impact on the process data other than the cause may be displayed. The probability of each cause calculated in S32 of FIG. 18 may also be displayed, or an action may also be displayed. The cause may also be displayed when the user moves the pointer over each rectangle.

[0062] 19 and 20, the process trend of each tag listed in the cause-and-effect diagram may be displayed, and in particular, the process trend of a tag for which the cause of the modulation can be identified may be displayed. The process trend is calculated using the process data stored in the storage device 12, and values for each period, such as for each predetermined hour, each predetermined number of days, each predetermined number of months, or each season, are plotted on a graph.

[0063] The output control unit 146 may also be configured to output a log of the degree of abnormality when, for example, the degree of abnormality calculated by each calculation method exceeds a predetermined threshold. Also, the output control unit 146 may be configured to output a log of the assumed cause and the degree of occurrence. Each log may be output in association with the date and time, serial number, calculation method, anomaly detection model, etc., thereby facilitating the analysis of abnormal modulation.

[0064] <Modification> The configurations and combinations thereof in each embodiment are merely examples, and additions, omissions, substitutions, and other modifications of the configurations are possible as appropriate without departing from the spirit of the present invention. The present disclosure is not limited by the embodiments, but is limited only by the scope of the claims. Furthermore, each aspect disclosed in this specification can be combined with any other feature disclosed in this specification.

[0065] Although the above-described embodiment has been described using a chemical plant as an example, the present invention can be applied to manufacturing processes in general production facilities. For example, instead of the manufacturing number of the batch process in the embodiment, a lot number may be used as the processing unit, and a process similar to the batch process in the embodiment may be applied.

[0066] At least some of the functions of the abnormal modulation cause identification device 1 may be distributed among multiple devices, or multiple devices may provide the same functions in parallel. Also, at least some of the functions of the abnormal modulation cause identification device 1 may be provided on a so-called cloud.

[0067] The present disclosure also includes a method and a computer program for executing the above-described process, and a computer-readable recording medium having the program recorded thereon. The recording medium having the program recorded thereon enables the above-described process by causing a computer to execute the program.

[0068] Here, a computer-readable recording medium refers to a recording medium that stores information such as data and programs electrically, magnetically, optically, mechanically, or chemically and can be read by a computer. Among such recording media, those that can be removed from a computer include flexible disks, magneto-optical disks, optical disks, magnetic tapes, memory cards, etc. Furthermore, recording media that are fixed to a computer include HDDs, SSDs (Solid State Drives), ROMs, etc. [Explanation of symbols]

[0069] 1: Abnormal modulation cause identification device 11: Communication I / F 12: Storage device 13: Input / output devices 14: Processor 141: Process data acquisition unit 142: Preprocessing section 143: Learning processing unit 144: Abnormality determination section 145: Cause Diagnosis Department 146: Output control section 2: Control Station 3: Plant

Claims

1. a process data acquisition unit that reads out process data from a storage device that stores process data continuously output by a plurality of sensors provided in the production equipment; an abnormality determination unit that calculates an abnormality degree that indicates a degree of modulation of the process data read by the process data acquisition unit; a cause diagnosing unit that determines whether the degree of abnormality calculated by the abnormality determining unit for the process data output from the plurality of sensors satisfies a predetermined standard by using causal relationship information that defines a combination of a cause and a modulation of the process data output from the plurality of sensors that appears as an effect resulting from the cause; an output control unit that reads out information indicating a countermeasure to be taken for the cause from the storage device that further stores the information, and outputs the information to an output device; Equipped with the cause diagnosing unit multiplies the plurality of types of process data by a coefficient based on the magnitude of the degree of abnormality to determine the likelihood of the cause of the modulation; The output control unit outputs, to the output device, a plurality of candidates for causes that may cause the modulation and the likelihood of the causes. Abnormal modulation cause display device.

2. The output control unit causes the output device to output a logic tree based on the causal relationship information, in which the modulation is set as a root and a cause of the modulation is set as a leaf, and in which events that appear in a process from the cause to the modulation are hierarchically connected, and also causes the output device to output information indicating a measure to be taken for the cause, in association with the cause. The abnormal modulation cause display device according to claim 1 .

3. reading out process data from a storage device that stores process data continuously output by a plurality of sensors provided in the production equipment; Calculating an abnormality level that indicates the degree of modulation of the read process data; determining whether a calculated degree of anomaly for the process data output by the plurality of sensors satisfies a predetermined criterion using causal relationship information that defines a combination of a cause and a modulation of the process data output by the plurality of sensors that appears as an effect resulting from the cause; The storage device further stores information indicating a measure to be taken for the cause. and outputting the information indicating the processing to an output device. In the determination process, the plurality of types of process data are multiplied by a coefficient based on the magnitude of the degree of abnormality to determine the likelihood of the cause of the modulation; In the process of outputting to the output device, a plurality of candidates for causes that may cause the modulation and the likelihood of the causes are output to the output device. A method for displaying the cause of abnormal modulation in which processing is performed by a computer.

4. reading out process data from a storage device that stores process data continuously output by a plurality of sensors provided in the production equipment; Calculating an abnormality level that indicates the degree of modulation of the read process data; determining whether a calculated degree of anomaly for the process data output by the plurality of sensors satisfies a predetermined criterion using causal relationship information that defines a combination of a cause and a modulation of the process data output by the plurality of sensors that appears as an effect resulting from the cause; reading information indicating a measure to be taken for the cause from the storage device further storing the information, and outputting the information to an output device; In the determination process, the plurality of types of process data are multiplied by a coefficient based on the magnitude of the degree of abnormality to determine the likelihood of the cause of the modulation; In the process of outputting to the output device, a plurality of candidates for causes that may cause the modulation and the likelihood of the causes are output to the output device. An abnormal modulation cause display program that causes a computer to execute processing.

Images