Substation monitoring system alarm signal modeling method and system considering logical rules

CN115017880BActive Publication Date: 2024-11-22ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY +2
View PDF -1 Cites 0 Cited by

Patent Information

Application Number
CN202210737181.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-27
Publication Date
2024-11-22
Estimated Expiration
2042-06-27

Smart Images

  • Figure CN115017880B_ABST
    Figure CN115017880B_ABST
Patent Text Reader

Abstract

The present disclosure belongs to the field of intelligent substation monitoring technology of power system, and specifically relates to a substation monitoring system alarm signal modeling method and system considering logical rules, including: obtaining a substation SCD file; parsing the obtained substation SCD file to obtain primary equipment and secondary equipment; performing similarity matching on the obtained primary equipment and secondary equipment based on natural language processing and a preset power grid model database; and completing the modeling of the substation monitoring system alarm signal according to the result of the similarity matching. The present disclosure performs data management on the substation alarm information name string, including data parsing modeling, data cleaning of erroneous data, etc., so that the computer can identify the alarm information and match the alarm information according to the protection and measurement and control device to which the information belongs; when defects or failures occur in the substation equipment, the computer can classify and analyze the alarm information according to the primary equipment in an event-based manner, which provides a data basis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent substation monitoring in power systems, and in particular relates to a method and system for modeling alarm signals of a substation monitoring system taking into account logical rules. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] After years of operation, the power system has accumulated a large amount of historical data such as telemetry, telesignaling and alarm information. However, the correlation between the data is not strong and the data organization is poor, which brings difficulties to further data analysis and mining. In particular, when processing the alarm information of smart substations, it can only focus on shallow statistical calculations, and it is difficult to conduct in-depth mining based on the existing data. This has not yet met the requirements of providing accident warnings and fault handling plans for the safe operation of the power grid.

[0004] The alarm information of primary and secondary equipment in smart substations is directly uploaded to the substation monitoring background and energy management system (EMS). With the continuous improvement of the comprehensive automation level of substations and the continuous expansion of power grid scale, the master station receives more and more equipment information, resulting in a large amount of monitored alarm information, disordered sequence, poor logic, and a lot of inefficient information.

[0005] The alarm information in the smart substation monitoring background mainly exists in the form of text. Due to the different naming habits of smart substation equipment manufacturers and regions, the naming of various alarm information in the substation configuration description file (SCD) and the monitoring system is very different and the naming rules are confusing. Therefore, it is urgent to standardize the name string of the substation alarm information so that the monitoring system can efficiently identify the alarm information; finally, the alarm information is mapped to the secondary equipment corresponding to the alarm information number. When defects or failures occur in the substation equipment, the monitoring system can successfully complete the intelligent processing and event classification of the alarm information, providing guidance and reference for defect elimination and fault handling.

[0006] The alarm information of smart substations usually includes five categories: accidents, abnormalities, displacement, over-limit, and notifications. The equipment objects included in the alarm information cover all primary and secondary equipment in the substation, so it has the characteristics of large amount of information, various types, random occurrence, and centralized transmission in a short time. Due to the above characteristics, and the fact that the current intelligent alarm processing is only processed at the dispatching master station, and cannot be distributed at the substation end, after the alarm information of the substation is uploaded to the control master station, the phenomenon of synonymous alarm information with different names is common, resulting in low accuracy of automatic classification and recognition when the master station processes the alarm information; the fundamental reason for this phenomenon is the non-standard modeling of alarm information.

[0007] At present, the information modeling of the dispatching master station and substation often adopts the modeling method based on natural language processing (NLP). NLP is a research hotspot of artificial intelligence (AI). It is to make computers understand and utilize these text information by semantically parsing natural language text. The key core of the information modeling method based on NLP is semantic parsing, which is divided into the steps of dictionary generation, normalization, word segmentation, abstraction and combination. How to ensure that the words used to generate the dictionary have semantic uniqueness and how to improve the accuracy of the word segmentation process are two key problems that restrict the further improvement of the standardization of alarm information modeling. Summary of the invention

[0008] In order to solve the above problems, the present invention proposes a substation monitoring system alarm signal modeling method and system considering logical rules, parses SCD file alarm information based on natural language processing (Natural Language Processing, referred to as NLP), improves dictionary generation and word segmentation, improves the efficiency and standardization of alarm information modeling, and realizes comprehensive intelligent alarm of substations in combination with edge computing.

[0009] According to some embodiments, a first solution of the present disclosure provides a substation monitoring system alarm signal modeling method considering logic rules, which adopts the following technical solutions:

[0010] A method for modeling an alarm signal of a substation monitoring system considering logic rules, comprising:

[0011] Get the substation SCD file;

[0012] Parse the obtained substation SCD file to obtain primary equipment and secondary equipment;

[0013] Based on natural language processing and a preset power grid model database, similarity matching is performed on the obtained primary and secondary devices;

[0014] According to the similarity matching results, the modeling of the alarm signal of the substation monitoring system is completed.

[0015] As a further technical limitation, the acquired substation SCD file is parsed, the names of all equipment involved in the substation SCD file are extracted, and the names of all extracted equipment are used as words in the natural language processing dictionary. Through the subordinate logical relationship between the container and the object entity, it is ensured that an object entity only exists in one container, thereby ensuring the uniqueness of the words in the natural language processing dictionary.

[0016] Furthermore, based on the subordinate logical relationship between the object entity and the container, the unique corresponding relationship between the words in the natural language processing dictionary and the substation SCD file is determined, and by constructing a semantic information sample library of the natural language processing dictionary, the fixed collocations of the words in the natural language processing dictionary are expanded, and the fixed collocations corresponding to the semantic information sample library are used as the basic units of word segmentation of the natural language processing dictionary. The words in the natural language processing dictionary are expanded, and a complete natural language processing dictionary table is generated to obtain a preset power grid model library.

[0017] As a further technical limitation, the names of the primary and secondary devices contained in all devices in the obtained substation SCD file are matched with the device names in the preset power grid model library for similarity, and the output is sorted according to the degree of similarity matching, and the alarm signal of the substation monitoring system is modeled.

[0018] Furthermore, when the matching similarity is lower than the similarity threshold, it means that the matched device signal is unnecessary information in the substation SCD file. At this time, the primary device or secondary device in the substation SCD file is redundant equipment and needs to be removed. At this time, the substation monitoring system automatically determines that the substation SCD file at this time is bad data and performs data cleaning.

[0019] Furthermore, when the matching similarity is higher than the similarity threshold, the substation SCD file at this time is reminded and manually annotated to form a keyword sample.

[0020] Furthermore, when the acquired substation SCD file cannot form an alarm signal in the signal of the substation monitoring system, the similarity threshold is adjusted; the similarity threshold is lowered so that the matched similarity is lower than the similarity threshold, and data cleaning of the substation SCD file is performed.

[0021] According to some embodiments, a second solution of the present disclosure provides a substation monitoring system alarm signal modeling system considering logic rules, which adopts the following technical solutions:

[0022] A substation monitoring system alarm signal modeling system considering logic rules, comprising:

[0023] An acquisition module is configured to acquire a substation SCD file; parse the acquired substation SCD file to obtain primary equipment and secondary equipment;

[0024] A matching module, which is configured to perform similarity matching on the obtained primary devices and secondary devices based on natural language processing and a preset power grid model database;

[0025] The alarm module is configured to model the alarm signal of the substation monitoring system according to the result of similarity matching.

[0026] According to some embodiments, a third solution of the present disclosure provides a computer-readable storage medium, which adopts the following technical solution:

[0027] A computer-readable storage medium stores a program thereon, which, when executed by a processor, implements the steps in the method for modeling an alarm signal of a substation monitoring system considering logical rules as described in the first aspect of the present disclosure.

[0028] According to some embodiments, a fourth solution of the present disclosure provides an electronic device, which adopts the following technical solution:

[0029] An electronic device comprises a memory, a processor and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for modeling alarm signals of a substation monitoring system taking into account logical rules as described in the first aspect of the present disclosure are implemented.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] The present invention performs data management on the name character string of the substation alarm information, including data analysis and modeling, data cleaning of erroneous data, etc., so that the computer can recognize the alarm information and match the alarm information according to the protection and measurement and control device to which the information belongs; it provides a data basis for the computer to classify and analyze the alarm information according to the primary equipment in an event-based manner when defects or failures occur in the substation equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0033] Figure 1 is a flow chart of a method for modeling an alarm signal of a substation monitoring system considering logic rules in the first embodiment of the present disclosure;

[0034] Figure 2It is a structural block diagram of the substation monitoring system alarm signal modeling system considering logical rules in the second embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0036] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0037] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0038] In the absence of conflict, the embodiments in the present disclosure and the features in the embodiments may be combined with each other.

[0039] Embodiment 1

[0040] The alarm information of smart substations usually includes five categories: accidents, abnormalities, displacement, over-limit, and notifications. The equipment objects included in the alarm information cover all primary and secondary equipment in the substation, so it has the characteristics of large amount of information, various types, random occurrence, and centralized transmission in a short time. Due to the above characteristics, and the fact that the current intelligent alarm processing is only processed at the dispatching master station, and cannot be distributed at the substation end, after the alarm information of the substation is uploaded to the control master station, the phenomenon of synonymous alarm information with different names is common, resulting in low accuracy of automatic classification and recognition when the master station processes the alarm information; and the fundamental reason for this phenomenon is the non-standard modeling of the alarm information.

[0041] At present, the information modeling of the dispatching master station and substation often adopts the modeling method based on natural language processing (NLP). NLP is a research hotspot of artificial intelligence (AI). It allows computers to understand and utilize these text information by semantically parsing natural language texts. The key core of the information modeling method based on NLP is semantic parsing, which is divided into the steps of dictionary generation, normalization, word segmentation, abstraction and combination. The main problem restricting the improvement of the standardization of alarm information modeling is that it is difficult to ensure the semantic uniqueness of the generated words and the accuracy of the word segmentation process from a methodological perspective. It is urgent to improve the two steps of dictionary generation and word segmentation to improve the efficiency and standardization of alarm information modeling.

[0042] The alarm information in the smart substation monitoring background mainly exists in the form of text. Due to the different naming habits of smart substation equipment manufacturers and regions, the naming of various alarm information in the substation configuration description file (SCD) and the monitoring system is very different and the naming rules are confusing. Therefore, it is urgent to standardize the name string of the substation alarm information so that the monitoring system can efficiently identify the alarm information; finally, the alarm information is mapped to the secondary equipment corresponding to the alarm information number. When defects or failures occur in the substation equipment, the monitoring system can successfully complete the intelligent processing and event classification of the alarm information, providing guidance and reference for defect elimination and fault handling.

[0043] Based on this, the first embodiment of the present disclosure introduces a substation monitoring system alarm signal modeling method considering logical rules.

[0044] A method for modeling an alarm signal of a substation monitoring system considering logic rules, comprising:

[0045] Get the substation SCD file;

[0046] Parse the obtained substation SCD file to obtain primary equipment and secondary equipment;

[0047] Based on natural language processing and a preset power grid model database, similarity matching is performed on the obtained primary and secondary devices;

[0048] According to the similarity matching results, the modeling of the alarm signal of the substation monitoring system is completed.

[0049] As one or more implementation methods, construct words in the NLP dictionary, use all the equipment names and their abbreviations involved in the primary system and secondary system in the substation SCD file as words in the NLP dictionary, and ensure the uniqueness of the words through the logical relationship between the container and the object entity.

[0050] Define the concepts of object entities and containers. Define each primary device in the substation as an object entity, and define object entities within a certain category as containers. Ensure that an object entity only exists in one container through the subordinate logical relationship between the object entity and the container. For example, define a "substation container", then the object entities corresponding to the voltage level name, switch name, busbar name, knife switch name, ground switch name, etc. in the container are unique in the substation container; further, define a "voltage level container", then the object entities corresponding to the switch name, busbar name, knife switch name, knife switch name, etc. in the container are unique in the voltage level container.

[0051] According to the defined container and object entity, the words corresponding to the primary equipment are generated in sequence and added to the dictionary. The object entity is distinguished by substation container and voltage level container, and then the uniqueness of the word is verified by comparison. The subordinate logical relationship between the object entity and the container ensures the uniqueness of the signal name in the SCD file and improves the accuracy of NLP word parsing.

[0052] As one or more implementation modes, after constructing the NLP words, a complete NLP dictionary table is generated by sample construction.

[0053] Although the uniqueness of the correspondence between NLP words and signal names in the SCD file is ensured through the subordinate logical relationship between the object entity and the container, the constructed NLP words only correspond to the smallest semantic unit. When performing word segmentation analysis on the alarm information, if the dictionary words are directly used as the word segmentation object, there are still problems of too fine word segmentation granularity and inaccurate word segmentation. Especially for the names of secondary equipment such as protection and measurement and control, there are often many pre-qualified phrases, that is, the primary equipment to which the secondary equipment belongs needs to be expressed through the container and the object entity, resulting in low word segmentation efficiency and serious errors that the word segmentation does not conform to the actual subordinate logical relationship.

[0054] This embodiment expands the fixed collocation of words by constructing a semantic information sample library, and uses the fixed collocation corresponding to the sample as the basic unit of word segmentation, and expands the dictionary. When performing NLP analysis, the predefined samples in the information sample library are preferentially used as the basic unit for annotation and word segmentation operations. Through this analysis method, not only the length of the alarm information text that can be analyzed can be greatly increased, but also the accuracy and word segmentation efficiency of the alarm information analysis are improved. For example: after the information sample of "[Secondary General Contractor] Secondary General Contractor. [Secondary Device / Protection Device] First Set of Protection [Relay / Signal Reset] Signal Reset" is established in the sample library in advance, when the alarm information "500kV5042 Circuit Breaker First Set of Protection Signal Reset" is analyzed, the word segmentation results are "500kV5042 Circuit Breaker", "First Set of Protection" and "Signal Reset", instead of using the basic words "500kV", "5042", "Circuit Breaker" and so on analyzed by dictionary words, it can be seen that the analysis accuracy and efficiency are greatly improved.

[0055] In order to solve the problem that the signal name cannot be parsed due to incomplete terminology in the alarm signal, the signal is manually split and labeled, and new samples are added to the sample set to adapt to the formation of new terms; parsing training is also carried out to improve the recognition rate of parsing, and the maximum recognition and parsing of the signal is achieved through training.

[0056] As one or more implementation methods, the matching degree of the primary and secondary equipment names contained in all devices in the SCD file and the equipment names in the power grid model library are sorted and output. If the matching degree is large and the corresponding number is unique, a reminder is given and manually marked to form a keyword sample. If the matching degree is lower than a certain proportion, the device can be set as a redundant device after manual confirmation and removed as redundant data; and a similarity threshold is set. If the matching degree is lower than a certain value, it means that the signal is an unnecessary signal in the SCD file, and the computer automatically determines it as bad data for data cleaning. In the case where the signal in the monitoring background cannot be found in the alarm signal dictionary library formed by the SCD file, causing the signal to be unable to be parsed, the matching degree can be set to a minimum threshold. If it is less than a certain threshold, the alarm signal of the monitoring background is cleaned.

[0057] like Figure 1As shown, this embodiment uses NLP technology to perform text parsing on the IED layer, that is, the device layer in the SCD file, and extracts the primary device name contained in the device layer, such as "500kV5042 circuit breaker first set of protection", "500kV5032 circuit breaker measurement and control", and can obtain "500kV", "5042 circuit breaker", "5032 circuit breaker" and other information through NLP extraction, and match the device name, abbreviation and other attribute values ​​formed by the modeling of the same device, object-oriented processing, and match the primary device name contained in the name of the SCD file device with the device name in the power grid model library through the entity name recognition method. If the match is successful, a corresponding relationship is established between the device layer and the primary device. For a small number of names that fail to match, the string name of the device layer is marked, and a certain similarity percentage is formed at the same time. For example, 220kV#2B bus and 220kVB segment bus, the two strings contain 220kV, B, and bus respectively, and the similarity of the two strings can be set to a certain percentage.

[0058] Finally, the matching degree between the primary equipment names contained in all devices in the SCD file and the equipment names in the power grid model library is sorted and output. If the matching degree is large and the corresponding number is unique, a reminder is given and manual annotation is performed to form a keyword sample. If the matching degree is lower than a certain proportion, the device can be set as a redundant device after manual confirmation and removed as redundant data; and a similarity threshold is set. If the matching degree is lower than a certain value, it means that the signal is not needed in the SCD file, and the computer automatically determines it as bad data for data cleaning.

[0059] This embodiment performs data management on the substation alarm information name character string, including data analysis and modeling, data cleaning of erroneous data, etc., so that the computer can recognize the alarm information and match the alarm information according to the protection and measurement and control device to which the information belongs; it provides a data basis for the computer to classify and analyze the alarm information according to the primary equipment in an event-based manner when defects or failures occur in the substation equipment.

[0060] Embodiment 2

[0061] The second embodiment of the present disclosure introduces a substation monitoring system alarm signal modeling system considering logic rules.

[0062] like Figure 2 A substation monitoring system alarm signal modeling system considering logic rules is shown, comprising:

[0063] An acquisition module is configured to acquire a substation SCD file; parse the acquired substation SCD file to obtain primary equipment and secondary equipment;

[0064] A matching module, which is configured to perform similarity matching on the obtained primary devices and secondary devices based on natural language processing and a preset power grid model database;

[0065] The alarm module is configured to model the alarm signal of the substation monitoring system according to the result of similarity matching.

[0066] The detailed steps are the same as the substation monitoring system alarm signal modeling method considering logical rules provided in Example 1, and will not be repeated here.

[0067] Embodiment 3

[0068] A third embodiment of the present disclosure provides a computer-readable storage medium.

[0069] A computer-readable storage medium stores a program thereon, which, when executed by a processor, implements the steps in the method for modeling an alarm signal of a substation monitoring system considering logical rules as described in the first embodiment of the present disclosure.

[0070] The detailed steps are the same as the substation monitoring system alarm signal modeling method considering logical rules provided in Example 1, and will not be repeated here.

[0071] Embodiment 4

[0072] A fourth embodiment of the present disclosure provides an electronic device.

[0073] An electronic device comprises a memory, a processor and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for modeling an alarm signal of a substation monitoring system taking into account logical rules as described in the first embodiment of the present disclosure are implemented.

[0074] The detailed steps are the same as the substation monitoring system alarm signal modeling method considering logical rules provided in Example 1, and will not be repeated here.

[0075] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for modeling alarm signals of a substation monitoring system considering logical rules, characterized in that: include: Get the substation SCD file; Parse the obtained substation SCD file to obtain primary equipment and secondary equipment; Construct the words in the natural language processing dictionary, use all the equipment names and their abbreviations involved in the primary equipment and secondary equipment in the substation SCD file as the words in the natural language processing dictionary, and ensure that an object entity exists only in one container through the subordinate logical relationship between the container and the object entity, so as to ensure the uniqueness of the words in the natural language processing dictionary; perform similarity matching on the obtained primary equipment and secondary equipment based on natural language processing and the preset power grid model database; The similarity matching is as follows: the names of the primary equipment and secondary equipment contained in all devices in the obtained substation SCD file are matched with the names of the equipment in the preset power grid model library, and the output is sorted according to the similarity matching degree; when the matching similarity is higher than the similarity threshold, the substation SCD file at this time is reminded and manually marked to form a keyword sample; when the matching similarity is lower than the similarity threshold, it means that the matched device signal is unnecessary information in the substation SCD file. At this time, the primary equipment or secondary equipment in the substation SCD file is redundant equipment and needs to be removed. At this time, the substation monitoring system automatically determines that the substation SCD file at this time is bad data and performs data cleaning; According to the similarity matching results, the modeling of the alarm signal of the substation monitoring system is completed.

2. A method for modeling alarm signals of a substation monitoring system considering logical rules as described in claim 1, characterized in that: According to the subordinate logical relationship between the object entity and the container, the unique corresponding relationship between the words in the natural language processing dictionary and the substation SCD file is determined, and by constructing a semantic information sample library of the natural language processing dictionary, the fixed collocations of the words in the natural language processing dictionary are expanded, and the fixed collocations corresponding to the semantic information sample library are used as the basic units of word segmentation of the natural language processing dictionary. The words in the natural language processing dictionary are expanded, and a complete natural language processing dictionary table is generated to obtain a preset power grid model library.

3. A method for modeling alarm signals of a substation monitoring system considering logical rules as described in claim 1, characterized in that: When the obtained substation SCD file cannot form an alarm signal in the signal of the substation monitoring system, the similarity threshold is adjusted; the similarity threshold is lowered, and when the matched similarity is lower than the similarity threshold, data cleaning of the substation SCD file is performed.

4. A substation monitoring system alarm signal modeling system considering logical rules, characterized in that: include: An acquisition module is configured to acquire a substation SCD file; parse the acquired substation SCD file to obtain primary equipment and secondary equipment; A matching module is configured to construct words in a natural language processing dictionary, and use all the device names and their abbreviations involved in the primary and secondary devices in the substation SCD file as words in the natural language processing dictionary. Through the subordinate logical relationship between the container and the object entity, it is ensured that an object entity exists only in one container, and the uniqueness of the words in the natural language processing dictionary is ensured; based on natural language processing and a preset power grid model database, the obtained primary and secondary devices are matched by similarity; the similarity matching is: the names of the primary and secondary devices contained in all devices in the obtained substation SCD file are matched by similarity with the device names in the preset power grid model library, and the output is sorted according to the similarity matching degree; when the matching similarity is higher than the similarity threshold, the substation SCD file at this time is reminded and manually marked to form a keyword sample. When the matching similarity is lower than the similarity threshold, it means that the matched device signal is unnecessary information in the substation SCD file. At this time, the primary device or secondary device in the substation SCD file is a redundant device and needs to be removed. At this time, the substation monitoring system automatically determines that the substation SCD file at this time is bad data and performs data cleaning; The alarm module is configured to complete the modeling of the alarm signal of the substation monitoring system according to the result of similarity matching.

5. A substation monitoring system alarm signal modeling system considering logic rules as described in claim 4, characterized in that: According to the subordinate logical relationship between the object entity and the container, the unique corresponding relationship between the words in the natural language processing dictionary and the substation SCD file is determined, and by constructing a semantic information sample library of the natural language processing dictionary, the fixed collocations of the words in the natural language processing dictionary are expanded, and the fixed collocations corresponding to the semantic information sample library are used as the basic units of word segmentation of the natural language processing dictionary. The words in the natural language processing dictionary are expanded, and a complete natural language processing dictionary table is generated to obtain a preset power grid model library.

6. A substation monitoring system alarm signal modeling system considering logic rules as described in claim 4, characterized in that: When the obtained substation SCD file cannot form an alarm signal in the signal of the substation monitoring system, the similarity threshold is adjusted; the similarity threshold is lowered, and when the matched similarity is lower than the similarity threshold, data cleaning of the substation SCD file is performed.

7. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps in the method for modeling an alarm signal of a substation monitoring system considering logic rules as described in any one of claims 1 to 3 are implemented.

8. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the method for modeling an alarm signal of a substation monitoring system considering logical rules as described in any one of claims 1 to 3 are implemented.