WO2019181572A1 - Abnormality monitoring device, abnormality monitoring method, program, control device, and plant - Google Patents

Abstract

In this abnormality monitoring device 300, a degree of abnormality display unit 100 displays time series data of the degree of abnormality of a system. A determination result display unit 110 displays a determination result of whether the system is in a normal state or an abnormal state. From multiple process values relating to the state of the system, a process data selection unit 70 allows an operator to select a process value to be viewed. An original data display unit 80 and a statistically processed data display unit 90 display time series data of a process value relating to the state of the system.

Description

[Name of invention determined by ISA based on Rule 37.2] Abnormality monitoring device, abnormality monitoring method, program, control device and plant

The present invention relates to an abnormality monitoring apparatus and an abnormality monitoring method.

There is a system that detects abnormalities such as high-pressure steam and high-pressure water leaks caused by blasting of various boiler piping by analyzing and monitoring process data patterns. In general, a plant abnormality detection system performs statistical processing on a large number of process data, evaluates how much the pattern of these process data differs from the normal pattern, calculates the degree of abnormality, and determines the degree of abnormality. Determine whether normal or abnormal.

JP 2017-211839 A

Such an anomaly detection system outputs an anomaly judgment result comprehensively by combining multiple types of process data in order to improve the anomaly detection performance. For this reason, it is difficult for the operator to know what pattern change has occurred in which process data and which is determined to be abnormal. When the anomaly detection system reports an anomaly, the operator cannot confirm the validity of the anomaly judgment result by checking the pattern of individual process data, and the operator makes a final decision on whether to operate or stop the plant. May hesitate.

One of the exemplary purposes of an aspect of the present invention is to provide an abnormality monitoring technique capable of easily verifying the validity of an abnormality determination result.

In order to solve the above problems, an abnormality monitoring apparatus according to an aspect of the present invention includes an abnormality degree display unit that displays time series data of an abnormality degree of a system and time series data of process values related to the state of the system. And a process data display unit.

こ の According to this aspect, it is possible to check the validity of the abnormality determination by individually browsing the time series data of the process values of the system.

Another aspect of the present invention is an abnormality monitoring method. This method includes an abnormality degree display step for displaying time series data of the degree of abnormality of the system, and a process data display step for displaying time series data of process values related to the state of the system.

Note that any combination of the above-described constituent elements and the constituent elements and expressions of the present invention are mutually replaced among methods, apparatuses, systems, computer programs, data structures, recording media, and the like. It is effective as

According to the present invention, the validity of the abnormality determination result can be easily verified.

It is a block diagram of the abnormality monitoring apparatus which concerns on this Embodiment. It is a figure explaining the example of a screen of the abnormality monitoring apparatus of FIG. It is a flowchart which shows the procedure of the abnormality monitoring process by the abnormality monitoring apparatus of FIG.

Hereinafter, the present invention will be described based on preferred embodiments with reference to the drawings. The same or equivalent components, members, and processes shown in the drawings are denoted by the same reference numerals, and repeated descriptions are omitted as appropriate. The embodiments do not limit the invention but are exemplifications, and all features and combinations thereof described in the embodiments are not necessarily essential to the invention.

FIG. 1 is a configuration diagram of an abnormality monitoring apparatus 300 according to the present embodiment. The abnormality monitoring device 300 is used for monitoring an abnormality in a process system such as a chemical plant or a power plant. The abnormality monitoring device 300 includes a process data acquisition unit 10, an abnormality detection data selection unit 20, a statistical processing unit 30, an abnormality degree calculation unit 40, a normal / abnormality determination unit 50, a selection target display unit 60, It includes a process data selection unit 70, an original data display unit 80, a post-statistical data display unit 90, an abnormality level display unit 100, a determination result display unit 110, and a contribution level display unit 120.

FIG. 2 is a diagram illustrating a screen example of the abnormality monitoring apparatus 300. Each configuration of the abnormality monitoring apparatus 300 in FIG. 1 will be described with reference to the screen example in FIG.

The process data acquisition unit 10 acquires a plurality of process values as time series data from sensors and measurement devices of the process system. The abnormality detection data selection unit 20 selects a process value to be used for specific abnormality detection from among a plurality of process values acquired by the process data acquisition unit 10. For example, when detecting abnormalities such as leaks of high-pressure steam or high-pressure water due to blasting of various pipes of the boiler, several process values used for blasting detection are selected.

The statistical processing unit 30 performs statistical processing on each abnormality detection process value selected by the abnormality detection data selection unit 20 and supplies each process value after statistical processing to the abnormality degree calculation unit 40.

The abnormality degree calculation unit 40 comprehensively evaluates each process value after statistical processing and calculates the abnormality degree. Evaluate how much the time-series pattern of each process value differs from the normal pattern, and perform an overall evaluation by weighted addition of the evaluation values indicating the degree of abnormality of each process value to calculate the final degree of abnormality .

The abnormality degree display unit 100 displays the abnormality degree calculated by the abnormality degree calculation unit 40 on a screen as a graph. The abnormality degree graph 200 in FIG. 2 is time series data of the degree of abnormality displayed by the degree of abnormality display unit 100. As an example, a history of the degree of abnormality for the past 24 hours is displayed as a graph. Also, the abnormality level indicator 210 in FIG. 2 represents the current abnormality level as a bar graph.

The normal / abnormality determination unit 50 determines whether the system is in a normal state or an abnormal state in light of the abnormality level calculated by the abnormality level calculation unit 40 in accordance with a determination criterion.

The determination result display unit 110 displays the determination result by the normal / abnormal determination unit 50 on the screen. The determination window 220 in FIG. 2 displays, for example, blue in the normal state, and displays in red, for example, in the abnormal state.

By indicating the result of determination as normal or abnormal in the determination window 220 in binary, the operator can easily grasp the case of abnormality. Even if the determination window 220 indicates normality, the operator can check the abnormality level indicator 210 and check the abnormality level index with an analog value. It is possible to distinguish between the normal state far from the normal state and the normal state before the abnormality.

The selection target display unit 60 displays a list of a plurality of process values acquired by the process data acquisition unit 10 in a list format or the like, and the process value for abnormality detection selected by the data selection unit for abnormality detection 20 is displayed in the list. Highlight.

The selection window 260 in FIG. 2 is a list of a plurality of process values displayed by the selection target display unit 60, and the items in the window can be browsed by scrolling up and down. In this example, among the process values A to L, the process values B, D, F, G, and J are selected by the abnormality detection data selection unit 20 and used to calculate the abnormal values. Highlighted. By highlighting in this way, the operator can easily select the process value used for the evaluation of the degree of abnormality.

It should be noted that only the process values used for calculating the abnormal value may be displayed in the selection window 260, and other process values may be selected from another window.

The process data selection unit 70 selects a process value to be browsed from among a plurality of process values displayed as a list by the selection target display unit 60. The operator may select a process value to be browsed from the process values for abnormality detection highlighted in the selection window 260, and browse from among process values not highlighted, that is, not used for abnormality detection. You may select the process value you want.

The operator can select a process value to be viewed from among a plurality of process values listed in the selection window 260 with a mouse or the like, and click another process value with a mouse to view another process value. Then it switches. FIG. 2 shows an example in which the operator selects the process value F for detecting an abnormality in the selection window 260.

The process data selection unit 70 notifies the process value selected by the operator to the original data display unit 80, the post-statistical data display unit 90, and the contribution display unit 120. The original data display unit 80 and the post-statistic processing data display unit 90 function as a process data display unit.

The original data display unit 80 acquires the original data before statistical processing of the process value selected by the operator from the abnormality detection data selection unit 20 and displays it on the screen as a graph. The original data graph 230 in FIG. 2 is a graph showing the original data of the process value F selected by the operator in time series.

The post-statistic processing data display unit 90 acquires the post-statistic processing data of the process value selected by the operator from the statistical processing unit 30 and displays it on the screen as a graph. The post-statistic processing data graph 240 in FIG. 2 is a graph showing the post-statistic processing data of the process value F selected by the operator in time series.

By referring to the original data graph 230, the operator can see the time change of the original data before statistical processing of the process value to be viewed. By observing the raw data, the operator can examine the signs of the process system that cannot be grasped from the data after statistical processing based on the experience and knowledge of the operator. In addition, the operator can observe the temporal change of the process value in a state where the feature to be noticed is extracted by the statistical processing by referring to the data graph 240 after the statistical processing, and thus the feature that appears in the process value. Therefore, it is possible to easily check the state of the process system early and accurately.

When the operator selects a process value that has not been selected for abnormality detection, the original data display unit 80 uses the process data acquisition unit 10 and the statistical processing unit 30 to obtain the source of the process value that has not been selected for abnormality detection. Data is supplied, and the statistical processing unit 30 performs statistical processing on the process values not selected for abnormality detection, and supplies them to the post-statistic processing data display unit 90.

When the operator selects a process value to be viewed from the process values for abnormality detection displayed on the selection window 260, the time change of the process value to be viewed is displayed in parallel with the abnormality degree graph 200 in which the time change of the abnormality is displayed. Are displayed in the original data graph 230 and the statistical data graph 240. When the degree of abnormality changes, the process value that has influenced the calculation of the degree of abnormality is considered to show the same time change. The operator compares the abnormality degree graph 200 with the original data graph 230 or the post-statistical processing data graph 240, compares the time change of the abnormality degree with the time change of the process value, and determines whether the currently viewed process value is abnormal. It is possible to visually grasp whether or not it contributes to.

The operator switches the process value desired to be browsed from among the process values for abnormality detection displayed in the selection window 260, so that a plurality of process values used for calculating the degree of abnormality are successively displayed in the original data graph 230 and the statistical process. It can be displayed on the subsequent data graph 240 to check whether or not the process value currently being viewed contributes to the abnormality determination. In general, not all process values used for calculating the degree of abnormality contribute to abnormality determination, and the degree of contribution even when contributing to abnormality determination varies depending on the process value. The operator can check the time change of each process value individually by switching the process value to be viewed in the selection window 260, and can grasp the difference in influence on abnormality determination individually.

In addition, the operator selects a process value that is not used for abnormality detection displayed in the selection window 260, so that it is not directly used for calculation of the degree of abnormality, but the time value of the process value that the operator pays attention to is changed. It can be displayed on the original data graph 230 and the post-statistical data graph 240 and compared with the temporal change of the abnormality degree of the abnormality degree graph 200. In general, in the process in which a process system transitions to an abnormal state, process values that are not used for calculating the degree of abnormality often show abnormal values. The operator is not directly used to calculate the degree of abnormality, but by selecting a process value that seems to be relevant and looking at the change over time, the degree of abnormality is spreading. Can be determined.

Even if the abnormality degree graph 200 does not indicate a peculiar change in the abnormality degree, the operator selects the process value displayed in the selection window 260 and individually shows the time change of the process value in the original data graph 230. In addition, it can be displayed and viewed on the data graph 240 after statistical processing. As a result, even if there is no unusual change in the degree of abnormality in the abnormality degree graph 200, it can be monitored whether or not any unusual change has occurred in any of the process values, and can be used for abnormality detection.

In this example, since the operator has a pattern similar to the time series data of the degree of abnormality displayed in the abnormality degree graph 200, the time series data of the process value F displayed in the post-statistical processing data graph 240 is the process value. It can be understood that F greatly contributes to the abnormality determination. If no sign of abnormality appears in the time change of the process value F, it can be understood that the process value F does not contribute to the calculation of the degree of abnormality. The operator also displays the time series of the original data before the statistical processing of the process value F displayed on the original data graph 230 and the time series of the statistical data after the statistical processing of the process value F displayed on the post-statistic processing data graph 240. The effectiveness of the statistical processing can also be confirmed by comparing whether or not a signal feature is extracted from the statistical processed data.

The contribution level display unit 120 displays a contribution rate indicating how much the process value selected by the operator contributes to the abnormality level determination. The contribution window 250 in FIG. 2 indicates that the contribution of the process value F selected by the operator is 35%. The contribution of each process may be displayed in association with the process values listed in the selection window 260. By displaying the contribution in the selection window 260, a process value having a large contribution can be quickly found. You may display the contribution of each process value used for abnormality detection with a pie chart or a bar graph. Thereby, the difference and magnitude of the contribution of each process value can be easily discriminated.

Even if several process values are used to calculate the degree of abnormality, if the abnormality spreads, the effect will appear on other process values. Therefore, in order to confirm whether the abnormality determination is not a false alarm, the operator selects a process value that is not directly used for calculation of the abnormality degree from the selection window 260 and displays a time series pattern of the process value. It can be confirmed that there is no false alarm.

FIG. 3 is a flowchart showing a procedure of an abnormality monitoring process performed by the abnormality monitoring apparatus 300.

The abnormality degree display unit 100 displays the abnormality degree history in a graph (S10). The determination result display unit 110 displays a result of determining whether the system is normal or abnormal (S12). The selection target display unit 60 highlights the process value used for calculating the degree of abnormality in the process value list (S14).

The process data selection unit 70 causes the operator to select a process value to be browsed individually from the list (S16). The original data display unit 80 and the post-statistic processing data display unit 90 respectively display the original data of the process value selected by the operator and the post-statistical processing data on a graph in time series (S18).

When the process value selected by the operator is used for abnormality detection (Y in S20), the contribution display unit 120 displays the degree of contribution of the process value selected by the operator to the evaluation of the abnormality (S22). ). Returning to step S16, the operator selects another process value, and the subsequent processing is repeated.

If the process value selected by the operator is not used for calculating the degree of abnormality (N in S20), the process skips step S22, returns to step S16, causes the operator to select another process value, and performs the subsequent processing. repeat.

According to the abnormality monitoring apparatus 300 of the present embodiment, when an abnormality is notified, the operator individually selects and browses the process data that contributed to the abnormality determination, and the time series pattern of the abnormality degree and the selected process data By comparing the time series patterns, the validity of the abnormality determination result can be easily verified. In addition, the operator can display not only the time-series pattern of process values directly used for abnormality detection but also the process value that is not directly used for abnormality detection, so that the time-series pattern can be displayed on the graph. It is possible to confirm whether or not the judgment is a false alarm. In this manner, the abnormality monitoring apparatus 300 can support the operator's final determination as to whether or not to stop the plant.

The present invention has been described above based on the embodiments. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiment, and various design changes are possible, various modifications are possible, and such modifications are within the scope of the present invention. By the way.

Can be used for system abnormality monitoring technology.

10 process data acquisition unit, 20 anomaly detection data selection unit, 30 statistical processing unit, 40 anomaly degree calculation unit, 50 normality / abnormality determination unit, 60 selection target display unit, 70 process data selection unit, 80 original data display unit, 90 Post-statistical data display section, 100 abnormality degree display section, 110 judgment result display section, 120 contribution display section, 300 abnormality monitoring device.

Claims (9)

An anomaly display section that displays time series data of the system anomaly,
And a process data display unit that displays time-series data of process values related to the state of the system. The abnormality monitoring apparatus according to claim 1, further comprising a determination result display unit that displays a determination result indicating whether the system is in a normal state or an abnormal state. A selection unit that allows an operator to select a process value to be viewed from a plurality of process values related to the state of the system;
The abnormality monitoring apparatus according to claim 1, wherein the process data display unit switches and displays time-series data of process values selected by the operator. The abnormality monitoring apparatus according to claim 3, further comprising a selection target display unit that displays a list of a plurality of process values related to the state of the system and highlights the process values used for the evaluation of the degree of abnormality. 5. The abnormality monitoring apparatus according to claim 1, further comprising a contribution degree display unit that displays a degree that a process value related to the state of the system contributes to the degree of abnormality. An abnormality level display step for displaying time series data of the system abnormality level,
And a process data display step for displaying time-series data of process values related to the state of the system. An abnormality level display step for displaying time series data of the system abnormality level,
A program causing a computer to execute a process data display step of displaying time-series data of process values related to the state of the system. A control device that displays time-series data of the degree of abnormality of the system and time-series data of process values related to the state of the system in order to support the control of the system. A plant that displays time series data of the degree of abnormality of the process system and time series data of process values related to the state of the process system when the process system is abnormal.

Images