DCS system alarm information analysis method, storage medium and electronic equipment

Abstract

The invention relates to an analysis method of alarm information of a DCS system, a storage medium and electronic equipment. The analysis method comprises the following steps: receiving real-time alarm information from OPC AE service; performing word segmentation processing on the real-time alarm information to obtain a first word segmentation result, and encoding all segmented words in the first word segmentation result by using a specified vocabulary to obtain a plurality of text feature vectors; inputting all the text feature vectors into a pre-trained alarm information recognition model for recognition to obtain probability output results corresponding to all the segmented words; determining a classification result corresponding to each segmented word in the real-time alarm information according to a preset classification rule and a probability output result, and storing the classification result in a specified database; and according to the received statistical display instruction, the classification result related to the statistical display instruction is read from the specified database and statistical display is performed, so that the processing efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the process industry neighborhood, and in particular to an analysis method, storage medium and electronic equipment for alarm information of a DCS system. Background Art

[0002] In process industries such as petroleum, chemical, electric power and pharmaceutical, AE (Alarm Event) alarm information of automation control systems is an important part of ensuring production safety and process monitoring. The AE alarm system is responsible for capturing and reporting equipment operating status, process parameter abnormalities and other events that may affect production safety and efficiency. However, with the improvement of production automation level and the expansion of factory scale, the number and complexity of AE alarm information have also increased, which has brought challenges to information processing and decision support.

[0003] However, the AE alarm information processing in most process industries still relies on manual interpretation and response by operators, so the existing alarm methods at least have the problem of relatively low processing efficiency. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a method for analyzing alarm information of a DCS system, a storage medium and an electronic device, which solve the technical problem of relatively low processing efficiency in the prior art.

[0006] (II) Technical solution

[0007] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides an analysis method for alarm information of a DCS system, the analysis method comprising: receiving real-time alarm information from an OPC AE service; performing word segmentation processing on the real-time alarm information to obtain a first word segmentation result, and encoding all word segmentations in the first word segmentation result using a specified vocabulary to obtain multiple text feature vectors; inputting all text feature vectors into a pre-trained alarm information recognition model for recognition to obtain probability output results corresponding to all word segmentations; determining, according to preset classification rules and probability output results, classification results corresponding to each word segmentation in the real-time alarm information, and storing the classification results in a specified database; according to the received statistical display instruction, reading the classification results related to the statistical display instruction from the specified database and performing statistical display.

[0009] In a possible embodiment, the alarm information recognition model includes an LSTM layer, an MLP layer and an output layer connected in sequence.

[0010] In a possible embodiment, the vocabulary used in the training process of the alarm information recognition model is a specified vocabulary.

[0011] In a possible embodiment, the classification rule includes event type, operation type and bit number type.

[0012] In a possible embodiment, event types include simple events, operation events, and alarm events.

[0013] In a possible embodiment, the operation types include alarm information, modifying set values, modifying valve position values, manual-automatic state switching, switching on / off quantity, silencing alarms, canceling alarms, selecting alarms, modifying PID parameters, and others.

[0014] In a possible embodiment, the bit type includes flow, level, temperature, pressure, quality and others.

[0015] In a second aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to execute the method described in the first aspect or any optional implementation of the first aspect.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the method described in the first aspect or any optional implementation method of the first aspect is performed.

[0017] In a fourth aspect, the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0018] (III) Beneficial effects

[0019] The beneficial effects of the present invention are:

[0020] The embodiment of the present application provides an analysis method, storage medium and electronic device for alarm information of a DCS system, which receives real-time alarm information from an OPC AE service, performs word segmentation processing on the real-time alarm information, obtains a first word segmentation result, and uses a specified vocabulary to encode all the word segments in the first word segmentation result to obtain multiple text feature vectors, and inputs all the text feature vectors into a pre-trained alarm information recognition model for recognition to obtain the probability output results corresponding to all the word segments, and determines the classification results corresponding to each word segmentation in the real-time alarm information according to the preset classification rules and the probability output results, and stores the classification results in a specified database, and reads the classification results related to the statistical display instruction from the specified database according to the received statistical display instruction and performs statistical display, so as to automatically identify and classify AE alarm information, effectively distinguish key alarms from conventional information, and effectively filter false alarms and redundant data. This innovative method significantly reduces the phenomenon of information overload, thereby improving the response efficiency and decision-making quality of operators.

[0021] In order to make the above-mentioned objectives, features and advantages to be achieved by the embodiments of the present application more obvious and understandable, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flowchart showing a method for analyzing alarm information of a DCS system provided in an embodiment of the present application

[0024] Figure 2 A structural block diagram of an alarm information recognition model provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0026] Although some companies have introduced preliminary automated alarm systems in recent years, there are still many technical defects, such as information overload and false alarms, heavy decision-making burden, insufficient statistics and trend analysis, and poor integration.

[0027] Of course, the industry has also tried to introduce data mining, machine learning and other technologies to perform preliminary automated processing of AE alarm information. For example, some systems use keyword matching algorithms to filter and classify alarm information according to preset rules, simplifying the screening work of operators. Other solutions try to provide decision-making suggestions for operators based on historical data and industry experience by building expert systems.

[0028] Although the above methods have alleviated the challenges of AE alarm information processing to a certain extent, they still have shortcomings such as low information processing efficiency, false alarms and missed alarms, insufficient decision support, and lack of statistical and analytical functions.

[0029] Based on this, the embodiment of the present application provides an analysis method, storage medium and electronic device for alarm information of a DCS system, which receives real-time alarm information from an OPC AE service, performs word segmentation processing on the real-time alarm information, obtains a first word segmentation result, and uses a specified vocabulary to encode all the word segments in the first word segmentation result to obtain multiple text feature vectors, and inputs all the text feature vectors into a pre-trained alarm information recognition model for recognition to obtain the probability output results corresponding to all the word segments, and determines the classification results corresponding to each word segmentation in the real-time alarm information according to the preset classification rules and the probability output results, and stores the classification results in a specified database, and reads the classification results related to the statistical display instruction from the specified database according to the received statistical display instruction and performs statistical display, so as to automatically identify and classify AE alarm information, effectively distinguish key alarms from conventional information, and effectively filter false alarms and redundant data. This innovative method significantly reduces the phenomenon of information overload, thereby improving the response efficiency and decision-making quality of operators.

[0030] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0031] In order to facilitate understanding of the embodiments of the present application, some terms involved in the present application are explained as follows:

[0032] DCS (Distributed Control System): It is a new generation of instrument control system based on microprocessors, adopting the design principles of decentralized control functions, centralized display operations, and taking into account both division and autonomy and comprehensive coordination;

[0033] Named Entity Recognition (NER): It is an important task in the field of natural language processing (NLP). Its goal is to automatically identify and classify entities with specific meanings from text, such as names of people, places, and organizations.

[0034] Long Short-Term Memory (LSTM): It is a special recurrent neural network (RNN) architecture that aims to solve the gradient vanishing or gradient exploding problems that traditional RNNs are prone to when processing long sequence data, so that it can more effectively capture long-term dependencies.

[0035] Multilayer Perceptron (MLP): It is a feedforward artificial neural network model with a multi-layer structure consisting of multiple neurons;

[0036] Central Control Intelligent Operation Cockpit Software: In view of the current situation that enterprises have few operators, many operators and low monitoring efficiency after highly autonomous production, the intelligent operation cockpit uses the intelligent AI assistant to realize early warning of key process indicators, active reminders of disposal procedures and key events, and guide operators to perform safe and compliant disposal operations according to operating procedures. At the same time, it integrates operation indicators, control status, alarm information, operation disposal and other information to achieve more efficient and safe monitoring and operation.

[0037] See also Figure 1 , Figure 1 A flowchart of a method for analyzing alarm information of a DCS system provided by an embodiment of the present application is shown. It should be understood that the analysis method can be executed by an electronic device, and the specific device of the electronic device can be set according to actual needs, and the embodiment of the present application is not limited thereto. For example, the electronic device can be a computer, or a server, etc.

[0038] Specifically, the analysis method includes:

[0039] Step S110: receiving real-time alarm information from the OPC AE service.

[0040] Specifically, after starting the AE data analysis service, real-time alarm information from the OPC AE service can be automatically received, wherein the real-time alarm information can come from intelligent instruments such as DCS instruments and PLC instruments.

[0041] Step S120, performing word segmentation processing on the real-time alarm information to obtain a first word segmentation result, and encoding all the words in the first word segmentation result using a specified vocabulary to obtain multiple text feature vectors.

[0042] Specifically, the real-time alarm information is preprocessed, which may include removing noise and unifying the format, etc., to obtain preprocessed data. Subsequently, the preprocessed data is segmented, and all the segmented words in the first segmentation result are encoded using the specified vocabulary used in the training of the alarm information recognition model to obtain multiple text feature vectors, thereby ensuring that the vocabulary in the prediction matches the training vocabulary set.

[0043] Step S130: input all text feature vectors into a pre-trained alarm information recognition model for recognition, so as to obtain probability output results corresponding to all word segments.

[0044] It should be understood that the specific model structure of the alarm information recognition model and its training process can be set according to actual needs, and the embodiments of the present application are not limited to this.

[0045] Optionally, see Figure 2 , Figure 2 FIG. 4 shows a structural block diagram of an alarm information recognition model provided by an embodiment of the present application. Figure 2 As shown, the alarm information recognition model includes an LSTM layer, an MLP layer and an output layer connected in sequence. Among them, the LSTM layer is used to realize named entity recognition; the MLP layer is used to realize state change word recognition; and the output layer is used to output probability output results.

[0046] Based on the above model, the training process of the alarm information recognition model includes:

[0047] Historical alarm information is obtained in batches to generate an initial text set. Then, regular expression technology is used to extract key information related to event type, operation type, bit number type, and state change from the initial text set to form a second text set. Subsequently, data enhancement is performed on the second text set, and the data is expanded through synonym replacement, random insertion, random ordering of words and sentences, random deletion, and text back translation to obtain a third text set.

[0048] Subsequently, word segmentation can be performed based on the content of the third text set, and each word segmentation can be annotated using the BIO (Begin, Inside, Outside) label system, and each word segmentation can be encoded using a specified vocabulary to obtain multiple training text feature vectors. When inputting the model, the training text feature vectors can be sorted according to their corresponding historical alarm information to generate a training text feature vector sequence corresponding to each historical alarm information.

[0049] Subsequently, the text feature vector sequence used for training can be input into the alarm information recognition model so that the LSTM layer combines the input text feature vector sequence with the context information to generate the corresponding feature vector, and the MLP layer determines the distribution probability of the specific word as a named entity based on the feature vector output by the LSTM layer, and the output layer outputs the probability output result based on the distribution probability.

[0050] Therefore, on the basis of the completion of model training, all text feature vectors are sorted according to the order of words in the real-time alarm information to obtain a text feature vector sequence, and the text feature vector sequence is input into the pre-trained alarm information recognition model for recognition to obtain the probability output results corresponding to all word segmentations.

[0051] Step S140, according to the preset classification rules and probability output results, the classification results corresponding to each word segment in the real-time alarm information are determined, and the classification results are stored in a designated database.

[0052] It should be understood that the specific rules of the classification rules can be set according to actual needs, and the embodiments of the present application are not limited to this.

[0053] Optionally, the classification rule includes event type, operation type and bit number type.

[0054] The event types include simple events, operation events and alarm events. Simple events refer to events other than operation events and alarm events.

[0055] And, the operation types include alarm information, modifying set values, modifying valve position values, manual-automatic state switching, switching switch quantity, alarm silencing, canceling alarms, selecting alarms, modifying PID parameters and others;

[0056] And, the tag types include flow, level, temperature, pressure, quality and others.

[0057] It should be noted here that each of the classification rules has a corresponding template.

[0058] On the basis of the above-mentioned preset classification rules, the classification results corresponding to each word segmentation in the real-time alarm information can be determined based on the probability output results and the preset classification rules, and the classification results are stored in a designated database. Among them, the specific database of the designated database can be set according to actual needs, and the embodiment of the present application is not limited to this. For example, the designated database can be a SQLite database.

[0059] Step S150: According to the received statistical display instruction, the classification results related to the statistical display instruction are read from the designated database and statistical display is performed.

[0060] Therefore, with the help of the above technical solution, the core goal of this application includes realizing intelligent information screening and classification: by applying natural language processing technology, the present invention can automatically identify and classify AE alarm information, effectively distinguish key alarms from conventional information, and thus effectively filter out false alarms and redundant data. In addition, this method significantly reduces the phenomenon of information overload, thereby improving the response efficiency and decision-making quality of operators.

[0061] In order to facilitate understanding of the embodiments of the present application, a description is given below using specific embodiments.

[0062] Specifically, when the real-time alarm information obtained is "Operator John modified the opening of valve V123 from 30% to 50%, causing the liquid level L101 to rise", the following classification results can be obtained through the alarm information analysis method of the DCS system of the present application:

[0063] Event type: Modify valve position value;

[0064] Position number grouping: liquid level control system;

[0065] Position name: L101;

[0066] Position number type: liquid level;

[0067] Position number prefix: L;

[0068] Position number suffix: 101;

[0069] Position value changes: the opening of valve V123 changes from 30% to 50%;

[0070] Position number status change: Liquid level L101 rises;

[0071] Executor ID: John;

[0072] Event Time: [Timestamp read from OPC AE].

[0073] It should be understood that the above-mentioned method for analyzing alarm information of the DCS system is only exemplary, and those skilled in the art may make various modifications based on the above-mentioned method, and the modified schemes also fall within the protection scope of the present application.

[0074] The present application provides a storage medium having a computer program stored thereon. The computer program is executed by a processor to execute the method described in the embodiment.

[0075] The present application also provides a computer program product, which, when executed on a computer, enables the computer to execute the method described in the method embodiment.

[0076] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0078] It should be noted that in the claims, any reference numerals placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by the same hardware. The use of the words first, second, third, etc., is for convenience of expression only and does not indicate any order. These words may be understood as part of the component name.

[0079] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0080] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments after knowing the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0081] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include these modifications and variations.

Claims

1. A method for analyzing alarm information of a DCS system, characterized in that: include: Receive real-time alarm information from OPC AE services; Performing word segmentation processing on the real-time alarm information to obtain a first word segmentation result, and encoding all the words in the first word segmentation result using a specified vocabulary to obtain multiple text feature vectors; Input all the text feature vectors into a pre-trained alarm information recognition model for recognition, so as to obtain probability output results corresponding to all the segmentations; According to the preset classification rules and the probability output result, determine the classification result corresponding to each word segment in the real-time alarm information, and store the classification result in a designated database; According to the received statistical display instruction, the classification results related to the statistical display instruction are read from the designated database and statistical display is performed.

2. The analysis method according to claim 1, characterized in that The alarm information recognition model includes an LSTM layer, an MLP layer and an output layer connected in sequence.

3. The analysis method according to claim 1, characterized in that The vocabulary used in the training process of the alarm information recognition model is the specified vocabulary.

4. The analysis method according to claim 1, characterized in that The classification rules include event type, operation type and bit number type.

5. The analysis method according to claim 4, characterized in that The event types include simple events, operation events and alarm events.

6. The analysis method according to claim 4, characterized in that The operation types include alarm information, modifying set values, modifying valve position values, switching between manual and automatic states, switching between switch quantities, silencing alarms, canceling alarms, selecting alarms, modifying PID parameters, and others.

7. The analysis method according to claim 4, characterized in that The bit type includes flow, level, temperature, pressure, quality and others.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing alarm information of a DCS system according to any one of claims 1 to 7 is executed.

9. An electronic device comprising a processor, a memory and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method for analyzing alarm information of a DCS system according to any one of claims 1 to 7.

Images