Electrical equipment remote signaling monitoring method and system

Abstract

The invention discloses a power equipment remote signaling monitoring method and system, and relates to the field of power, and the method comprises the steps: connecting a power equipment real-time monitoring database, and obtaining real-time monitoring data and historical data; the method comprises the following steps: preprocessing text data on the basis of historical data and alarm information processing specifications, and clustering through text similarity in machine learning to obtain a retrieval text set and a topic vector; retrieving and classifying the real-time monitoring data to be processed based on the retrieval text set and the topic vector; performing signal monitoring and alarm processing based on a classification result; through accurate text processing, an optimized signal monitoring strategy and innovative functional interface design, the performance of the electrical equipment remote signaling monitoring system is remarkably improved. The method not only improves the accuracy of text similarity analysis, but also optimizes the efficiency and safety of signal processing, and improves the usability of the system and the user experience through the intelligent and humanized interface design.

Description

Technical Field

[0001] The present invention relates to the electric power field, and in particular to a remote signaling monitoring method and system for electric power equipment. Background Art

[0002] Nowadays, the demand for electricity maintains a rapid growth trend. In this context, the corresponding power equipment commissioning, planned maintenance, power outage operations, defect handling and other work are also increasing. The rapid growth of the number of power grid equipment has brought about a substantial increase in the amount of signals, which has put forward new requirements for the signal monitoring and handling of regional power grids, and also brought new and greater challenges.

[0003] At present, the local dispatching monitors mainly monitor the signals through the dispatching end OCS system during their duty. The conventional practice is to divide the substations in the whole area into two areas, A and B, to monitor and analyze the real-time operation of the power grid. With the continuous updating and iteration of the local dispatching OCS system and the continuous optimization and enrichment of functions, the dispatchers have also found some relative deficiencies in the system in their daily work, mainly focusing on: the monitoring signal messages and the light signs, telemetry and other information of each substation are relatively scattered, and there are many screens that need to be monitored at the same time; there are also many functional modules that need to be used, and the dispatching monitors often need to manually switch the screen frequently, which makes monitoring inconvenient and the operation cumbersome, and is not conducive to the dispatchers to quickly extract the key information of the power grid dispatching operation from the massive data, which invisibly increases the risk of "missing monitoring". Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to optimize the signal monitoring and alarm mechanism in the power grid dispatching system.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a remote signaling monitoring method for electric power equipment, comprising:

[0008] Connect to the real-time monitoring database of power equipment, read the remote signal alarm, remote signal position change, accident trip, channel alarm data table, and obtain real-time monitoring data and historical data;

[0009] Based on historical data and alarm information processing specifications, text data is preprocessed, and clustering is performed through text similarity in machine learning to obtain retrieval text sets and topic vectors;

[0010] Based on the retrieval text set and the topic vector, the real-time monitoring data to be processed is retrieved and classified;

[0011] Based on the classification results, signal monitoring and alarm processing are carried out.

[0012] As a preferred solution for the remote signaling monitoring method of power equipment, wherein:

[0013] The text data preprocessing includes:

[0014] Use the word segmentation library and custom dictionary to segment the text; create a stop word list to remove stop words, and remove common words that have no substantive meaning for analysis; extract a feature list for each question from the text after word segmentation and stop word removal.

[0015] As a preferred solution for the remote signaling monitoring method of power equipment, wherein:

[0016] The clustering is performed by using text similarity in machine learning to obtain the retrieved text set and topic vector, including:

[0017] For an m×n matrix A, it is decomposed into the following three matrices:

[0018]

[0019] Reducing the dimension of the matrix to k, the decomposition is expressed as:

[0020]

[0021] As a preferred solution for the remote signaling monitoring method of power equipment, wherein:

[0022] The clustering by using text similarity in machine learning to obtain a retrieval text set and a topic vector also includes:

[0023] Input m texts, each text has n words, A ij The feature value of the jth word corresponding to the i-th text, k is the number of topics set; after decomposition, U il Corresponding to the relevance between the ith text and the lth topic, V jm Corresponding to the relevance between the jth word and the mth word meaning, Σ lm Corresponding to the relevance between the lth topic and the mth word meaning.

[0024] As a preferred solution for the remote signaling monitoring method of power equipment, wherein:

[0025] The retrieving and classifying the real-time monitoring data to be processed comprises:

[0026] The telesignal alarms that appear in the real-time monitoring data to be processed are retrieved from the text collection to find the documents with the highest subject similarity: the telesignals and texts to be retrieved are expressed in the same vector space; an object for similarity calculation is initialized with the document vectors to be retrieved, the similarity matrix is ​​persisted, the cosine similarity between any telesignal alarm and all documents is calculated, and the document with the highest subject similarity is selected as the basis for classification.

[0027] As a preferred solution for the remote signaling monitoring method of power equipment, wherein:

[0028] The signal monitoring and alarm processing includes:

[0029] It automatically queries and analyzes every 30 seconds, and displays all unreset signals, special signals, and circuit breaker position change signals within the time range on the power equipment remote signal monitoring interface. At the same time, it issues a voice alarm to remind monitoring personnel to take action.

[0030] As a preferred solution for the remote signaling monitoring method of power equipment, wherein:

[0031] The signal monitoring and alarm processing also includes:

[0032] Once a special signal is issued, an alarm is sounded;

[0033] If the circuit breaker position change signal is not remotely operated and does not belong to tripping, it will be displayed in the local position change;

[0034] If the circuit breaker position change signal is remotely controlled, it will be displayed in the remote control position change signal;

[0035] Classify other signals other than special signals and position-changing signals as unrecovered signals. If they are not restored within 6 minutes, a dynamic screen display will be performed. If they are not restored for more than 6 minutes, a voice alarm will be issued.

[0036] If the signal has not been processed by the monitoring personnel, the current signal number will be played. If the signal has been processed by the monitoring personnel, no voice alarm will be issued, and it will only be displayed in the alarm window.

[0037] In a second aspect, an embodiment of the present invention provides a remote signaling monitoring system for electric power equipment, comprising:

[0038] The data acquisition module is used to connect to the real-time monitoring database of power equipment, read the remote signal alarm, remote signal position change, accident tripping, channel alarm data table, and obtain real-time monitoring data and historical data;

[0039] The data acquisition module is used to connect to the real-time monitoring database of power equipment, read the remote signal alarm, remote signal position change, accident tripping, channel alarm data table, and obtain real-time monitoring data and historical data;

[0040] The retrieval classification module makes judgments based on the attributes of the remote signaling data and classifies the signals into tripping signals, special signals, local position change signals, unreset signals, and remote position change signals;

[0041] Monitoring and alarm module, used for signal monitoring and alarm processing based on classification results;

[0042] The intelligent analysis module is used to pre-process text data based on historical data and alarm information processing specifications, cluster text similarity through machine learning, and provide remote signal processing decisions.

[0043] In a third aspect, an embodiment of the present invention provides a computing device, including:

[0044] Memory and processor;

[0045] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more processors implement the electric power equipment remote signaling monitoring method as described in any embodiment of the present invention.

[0046] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the electric power equipment remote signaling monitoring method.

[0047] Beneficial effects of the invention: The invention significantly improves the performance of the remote signaling monitoring system for electric power equipment through precise text processing, optimized signal monitoring strategy and innovative functional interface design. It not only improves the accuracy of text similarity analysis, but also optimizes the efficiency and safety of signal processing. At the same time, through intelligent and humanized interface design, it improves the ease of use and user experience of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0049] Figure 1 It is an overall flow chart of the remote signaling monitoring method for electric power equipment according to the first embodiment of the present invention;

[0050] Figure 2 The software operation interface in the simulation example of the electric power equipment remote signal monitoring method according to the second embodiment of the present invention is shown in FIG. Figure 1 ;

[0051] Figure 3 The software operation interface in the simulation example of the electric power equipment remote signal monitoring method according to the second embodiment of the present invention is shown in FIG. Figure 2 ;

[0052] Figure 4 The software operation interface in the simulation example of the electric power equipment remote signal monitoring method according to the second embodiment of the present invention is shown in FIG. Figure 3 . DETAILED DESCRIPTION

[0053] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] Example 1

[0057] Reference Figure 1 , which is the first embodiment of the present invention, provides a remote signaling monitoring method for electric power equipment, comprising:

[0058] S1: Connect to the real-time monitoring database of power equipment, read the remote signal alarm, remote signal change, accident trip, channel alarm data table, and obtain real-time monitoring data and historical data;

[0059] Specifically, it can connect to the safety production zone III database to read the remote signal alarm, remote signal change, accident tripping, and channel alarm data tables; when reading the data, perform text analysis, logical judgment, and identification statistics on the data one by one.

[0060] S2: Based on historical data and alarm information processing specifications, text data is preprocessed, and text similarity is clustered through machine learning to obtain retrieval text sets and topic vectors;

[0061] In the embodiment of the present application, a word segmentation library and a custom dictionary are used to segment the text; a stop word list is established to remove stop words, and common words that have no substantive meaning for analysis are removed; and a feature list for each question is extracted from the text after word segmentation and stop word removal.

[0062] Specifically, the hidden Markov model (HMM) can be used for word segmentation. The hidden Markov model is a statistical learning model that can be used for labeling problems and has a wide range of applications in speech recognition, natural language processing, pattern recognition, etc. The jieba word segmentation library is a third-party library in Python that uses a hidden Markov model based on the word-forming ability of Chinese characters and uses the Viterbi algorithm.

[0063] In another possible implementation, first improve and refine the "remote signal description" category in the "Guidelines for the Handling of Monitoring and Alarm Information of Integrated Substation Equipment of Kunming Power Supply Bureau", and then use the jieba word segmentation library to separate words with spaces to facilitate later data analysis. Although the jieba word segmentation library has a good effect on the segmentation of common words and has a certain ability to recognize new words, it is not capable of segmenting words related to the power field and related faults. By referring to the "Southern Power Grid Substation Secondary Equipment Important Alarm Information and Light Sign Setting Specifications", a custom dictionary is established to enter common power equipment, components, belonging to, etc., to improve the accuracy of word segmentation.

[0064] Specifically, a feature list of each question is extracted from the text after word segmentation and stop word removal, where the questions include operational problems: for example, “110kV Gangtou Village transformer 110kV #1 main transformer cooler fan failure”, “110kV Suyuan transformer 110kV Jinsutan line 151 switch control circuit broken”, and “35kV Shuanghe transformer 35kV Shuanghe I return 361 switch SF6 low pressure alarm”.

[0065] For example, after segmenting the question "35kV Shuanghe I circuit 361 switch SF6 low pressure alarm", we get: "35kV / Shuanghe transformer / 35kV / Shuanghe I circuit / 361 / switch / low pressure / alarm".

[0066] In the embodiment of the present application, an m×n matrix A is decomposed into the following three matrices:

[0067]

[0068] Reducing the dimension of the matrix to k, the decomposition is expressed as:

[0069]

[0070] Input m texts, each text has n words, A ij The feature value of the jth word corresponding to the i-th text, k is the number of topics set; after decomposition, U il Corresponding to the relevance between the ith text and the lth topic, V jm Corresponding to the relevance between the jth word and the mth word meaning, Σ lm Corresponding to the relevance between the lth topic and the mth word meaning.

[0071] Specifically, the index dictionary of corpus features is established by calling the API provided by Gensim, and the original expression of text features is converted into the sparse vector expression corresponding to the bag-of-words model. By mining the hidden semantic structure features in the corpus, a concise and efficient text vector is finally transformed. Each vector transformation operation corresponds to a topic model, and each model is a standard Python object. The first step is to initialize the model object, using a training corpus as the initialization parameter. Next, call this model to convert any corpus into a TF-IDF vector. Vector transformation is performed through the LSI topic model to generate the corresponding topic vector. Latent Semantic Indexing (LSI) is a simple and practical topic model that obtains the topic of the text based on the singular value decomposition (SVD) method.

[0072] For an m×n matrix A, SVD can be decomposed into the following three matrices:

[0073]

[0074] In order to reduce the dimension of the matrix to k, the SVD decomposition can be approximately written as:

[0075]

[0076] Substituting the above formula into the topic model, the SVD can be expressed as: input m texts, each text has n words. ij The feature value of the jth word in the i-th text is the most commonly used one based on the standardized TF-IDF value after preprocessing. k is the number of assumed topics, which is generally less than the number of texts. After SVD decomposition, U il Corresponding to the relevance between the ith text and the lth topic. jm Corresponding to the relevance between the jth word and the mth word meaning. Σ lm Corresponding to the relevance between the lth topic and the mth word meaning. In this way, through one SVD, we can get the relevance between the document and the topic, the relevance between the word and the word meaning, and the relevance between the word meaning and the topic.

[0077] S3: Retrieve and classify the real-time monitoring data to be processed based on the retrieval text set and topic vector;

[0078] In an embodiment of the present application, the telesignal alarm appearing in the real-time monitoring data to be processed is used to retrieve the document with the highest subject similarity from the text collection: the telesignal to be retrieved and the text are expressed in the same vector space; an object for similarity calculation is initialized with the document vector to be retrieved, the similarity matrix is ​​persisted, the cosine similarity between any telesignal alarm and all documents is calculated, and the document with the highest subject similarity is selected as the basis for classification.

[0079] Specifically, the similarity matrix is ​​persisted through the save() and load() methods, and the cosine similarity between any remote signal alarm and all documents is calculated with the help of the index object.

[0080] S4: Based on the classification results, perform signal monitoring and alarm processing.

[0081] In the embodiment of the present application, the system automatically queries and analyzes every 30 seconds, and displays all unreset signals, special signals, and circuit breaker position change signals within the time range on the remote signal monitoring interface of the power equipment, and issues a voice alarm at the same time to remind the monitoring personnel to handle the situation;

[0082] Specifically, special signals include tripping, low SF6 gas pressure, reclosing action signals, etc.

[0083] In the embodiment of the present application, an alarm is issued once the special signal is issued;

[0084] If the circuit breaker position change signal is not remotely operated and does not belong to tripping, it will be displayed in the local position change;

[0085] If the circuit breaker position change signal is remotely controlled, it will be displayed in the remote control position change signal;

[0086] Classify other signals other than special signals and position-changing signals as unrecovered signals. If they are not restored within 6 minutes, a dynamic screen display will be performed. If they are not restored for more than 6 minutes, a voice alarm will be issued.

[0087] If the signal has not been processed by the monitoring personnel, the current signal number will be played. If the signal has been processed by the monitoring personnel, no voice alarm will be issued, and it will only be displayed in the alarm window.

[0088] In another possible implementation, the most balanced point is selected for optimization between safety and efficiency, and an alarm range of 1-10 minutes is set for signals that do not require immediate treatment. According to the current rules and regulations of the main grid control room, after the signal is issued, the monitoring personnel need to observe and track it. If the signal is restored within a short time, the monitoring personnel do not need to notify the site (except for signals that need to be handled immediately, such as tripping, circuit breaker position change, SF6 gas pressure reduction, etc., which are handled immediately after being issued).

[0089] In order to reduce the number of signals processed per day, setting an upper limit on the time for signals that have not been restored is a prerequisite. According to statistics from the team members, 67.15% of the signals can be restored within the first 10 minutes. According to the time range set by the monitoring personnel, if the signal has not been restored after the timeout, the software will give a voice alarm to remind the monitoring personnel to handle it according to the process. This not only improves the timeliness of signal processing and ensures the quality of monitoring, but also reduces the number of signals processed per day and improves monitoring efficiency.

[0090] Combined with BI data dashboard function, data can be visualized.

[0091] Taking into account the actual work of monitoring personnel, during operation, the program automatically completes data extraction and analysis and voice alarm functions, and the process does not require human intervention.

[0092] The start time can be set by yourself. Once the monitoring personnel select the monitoring start time and click Start Monitoring, the program will automatically run. The start time can be set up to 100 hours in advance. When the program runs automatically, the start time will not change, and the end time will automatically update to the current system time. This is convenient for monitoring personnel to verify on-duty signals and off-duty signals to prevent missed monitoring.

[0093] From the status bar, you can clearly see the station, time range, and link where the program is running;

[0094] Learn from the design of traffic lights and set up obvious signs. The green light means the program is working, and the red light means the program is suspended.

[0095] The remote control signal is actively operated by personnel, there is no voice alarm, it is only displayed on the screen.

[0096] Audio peripherals: Optional portable speakers that can be used for both charging and audio transmission using just one cable, reducing desktop wiring and making placement and organization easier.

[0097] The above is a schematic scheme of the electric power equipment remote signaling monitoring method of this embodiment. It should be noted that the technical scheme of the electric power equipment remote signaling monitoring system and the technical scheme of the above electric power equipment remote signaling monitoring method belong to the same concept, and the details of the technical scheme of the electric power equipment remote signaling monitoring system in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the above electric power equipment remote signaling monitoring method.

[0098] The electric power equipment remote signal monitoring system in this embodiment includes:

[0099] The data acquisition module is used to connect to the real-time monitoring database of power equipment, read the remote signal alarm, remote signal position change, accident tripping, channel alarm data table, and obtain real-time monitoring data and historical data;

[0100] The retrieval classification module makes judgments based on the attributes of the remote signaling data and classifies the signals into tripping signals, special signals, local position change signals, unreset signals, and remote position change signals;

[0101] Monitoring and alarm module, used for signal monitoring and alarm processing based on classification results;

[0102] The intelligent analysis module is used to pre-process text data based on historical data and alarm information processing specifications, cluster text similarity through machine learning, and provide remote signal processing decisions.

[0103] This embodiment further provides a computing device, which is applicable to the case of the remote signaling monitoring method of electric power equipment, and includes:

[0104] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the electric power equipment remote signaling monitoring method proposed in the above embodiment.

[0105] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the remote signaling monitoring method for electric power equipment proposed in the above embodiment is implemented.

[0106] The storage medium proposed in this embodiment and the electric power equipment remote signaling monitoring method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0107] Example 2

[0108] Reference Figure 2-Figure 4 Table 1 is an embodiment of the present invention, which provides a remote signal monitoring method for power equipment. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0109] like Figure 2-Figure 4, which is a schematic diagram of the software operation interface in the method provided by the present invention;

[0110] The following is the model evaluation used in the present invention:

[0111] In the performance indicator parameters, precision represents the accuracy, and the calculation formula is:

[0112]

[0113] In the formula, TP represents the number of correct records identified as this category, and TP+FP represents the number of records actually identified as this category.

[0114] Recall represents the recall rate, and the calculation formula is:

[0115]

[0116] In the formula, TP+FN represents the number of records that should be identified as this category.

[0117] f1-score is the harmonic mean of precision and recall, and is calculated as:

[0118]

[0119] Support indicates the total number of records of this category in the test set.

[0120] By manually marking 100 telesignals, the model was evaluated and scored using the confusion matrix. The results are shown in the following table:

[0121] Table 1 Model evaluation scores

[0122] index statistics precision 0.81 recall 0.78 f1-score 0.73 support 100

[0123] As can be seen from the table: a total of 100 data were tested, with an accuracy of 81%, a recall of 78%, and an f1-score of 73%; with the enrichment of the corpus and the continuous improvement of the custom dictionary, the prediction effect will be further improved.

[0124] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A remote signaling monitoring method for electric power equipment, characterized in that: include: Connect to the real-time monitoring database of power equipment, read the remote signal alarm, remote signal position change, accident trip, channel alarm data table, and obtain real-time monitoring data and historical data; Based on historical data and alarm information processing specifications, text data is preprocessed, and clustering is performed through text similarity in machine learning to obtain retrieval text sets and topic vectors; Based on the retrieval text set and the topic vector, the real-time monitoring data to be processed is retrieved and classified; Based on the classification results, signal monitoring and alarm processing are carried out.

2. The remote signaling monitoring method for electric power equipment according to claim 1, characterized in that: The text data preprocessing includes: Use the word segmentation library and custom dictionary to segment the text; create a stop word list to remove stop words, and remove common words that have no substantive meaning for analysis; extract a feature list for each question from the text after word segmentation and stop word removal.

3. The remote signaling monitoring method for electric power equipment according to claim 2, characterized in that: The clustering is performed by using text similarity in machine learning to obtain the retrieved text set and topic vector, including: For an m×n matrix A, it is decomposed into the following three matrices: Reducing the dimension of the matrix to k, the decomposition is expressed as:

4. The remote signaling monitoring method for electric power equipment according to claim 3, characterized in that: The clustering by using text similarity in machine learning to obtain a retrieval text set and a topic vector also includes: Input m texts, each text has n words, A ij The feature value of the jth word corresponding to the i-th text, k is the number of topics set; after decomposition, U il Corresponding to the relevance between the ith text and the lth topic, V jm Corresponding to the relevance between the jth word and the mth word meaning, Σ lm Corresponding to the relevance between the lth topic and the mth word meaning.

5. The remote signaling monitoring method for electric power equipment according to claim 4, characterized in that: The retrieving and classifying the real-time monitoring data to be processed comprises: The telesignal alarms that appear in the real-time monitoring data to be processed are retrieved from the text collection to find the documents with the highest subject similarity: the telesignals and texts to be retrieved are expressed in the same vector space; an object for similarity calculation is initialized with the document vectors to be retrieved, the similarity matrix is ​​persisted, the cosine similarity between any telesignal alarm and all documents is calculated, and the document with the highest subject similarity is selected as the basis for classification.

6. The remote signaling monitoring method for electric power equipment according to claim 5, characterized in that: The signal monitoring and alarm processing includes: It automatically queries and analyzes every 30 seconds, and displays all unreset signals, special signals, and circuit breaker position change signals within the time range on the power equipment remote signal monitoring interface. At the same time, it issues a voice alarm to remind monitoring personnel to take action.

7. The remote signaling monitoring method for electric power equipment according to claim 6, characterized in that: The signal monitoring and alarm processing also includes: Once a special signal is issued, an alarm is sounded; If the circuit breaker position change signal is not remotely operated and does not belong to tripping, it will be displayed in the local position change; If the circuit breaker position change signal is remotely controlled, it will be displayed in the remote control position change signal; Classify other signals other than special signals and position-changing signals as unrecovered signals. If they are not restored within 6 minutes, a dynamic screen display will be performed. If they are not restored for more than 6 minutes, a voice alarm will be issued. If the signal has not been processed by the monitoring personnel, the current signal number will be played. If the signal has been processed by the monitoring personnel, no voice alarm will be issued, and it will only be displayed in the alarm window.

8. A system using the remote signaling monitoring method for electric power equipment as claimed in any one of claims 1 to 7, characterized in that: include: The data acquisition module is used to connect to the real-time monitoring database of power equipment, read the remote signal alarm, remote signal position change, accident tripping, channel alarm data table, and obtain real-time monitoring data and historical data; The retrieval classification module makes judgments based on the attributes of the remote signaling data and classifies the signals into tripping signals, special signals, local position change signals, unreset signals, and remote position change signals; Monitoring and alarm module, used for signal monitoring and alarm processing based on classification results; The intelligent analysis module is used to pre-process text data based on historical data and alarm information processing specifications, cluster text similarity through machine learning, and provide remote signal processing decisions.

9. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the electric power equipment remote signaling monitoring method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for remote signaling monitoring of electric power equipment as claimed in any one of claims 1 to 7.

Images