Intelligent error prevention method and device for synthetic loop synchronous control mode
Through the intelligent error prevention method of synthesized loop synchronization control mode, the maintenance order and operation ticket characteristics are extracted, and the prediction model is established and adjusted, which solves the operation inaccuracy of high-voltage DC circuit breakers and achieves more efficient and safe power system operation.
Patent Information
- Application Number
- CN202410983490.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-07-22
AI Technical Summary
Existing high-voltage DC circuit breakers have operational inaccuracy in the fault handling, which leads to threatening grid stability and safety, especially in high-voltage DC systems, where finer control strategies are required to ensure accurate circuit breakers are opened.
The synthetic loop synchronization control mode intelligent error prevention method is adopted, and the characteristics of the maintenance order issuance opinions and operation tickets are extracted, the prediction model is established, and the model parameters are adjusted using improved genetic algorithms to achieve intelligent error prevention.
It improves the efficiency and accuracy of circuit breaker operation, prevents potential error control, provides personalized and adaptive anti-error strategies, and enhances the stability and safety of the power system.
Smart Images

Figure CN118502339B_ABST
Abstract
Description
Background Art
[0002] In modern power systems, especially in grid areas close to load centers, efficient and accurate fault handling mechanisms are essential. Some electronic components, such as circuit breakers, as key components of grid protection, are responsible for quickly isolating short-circuit faults to prevent a single fault event from causing system paralysis. However, inaccuracies in the circuit breaker's breaking operation will not only shorten its own life, but may also affect adjacent equipment, seriously threatening the stable operation of the entire power grid. Especially in high-voltage direct current (HVDC) systems, although circuit breaker technology mostly draws on mature AC system breaking test methods, the uniqueness of DC systems requires more sophisticated control strategies, especially the synthetic loop synchronous control mode, which is the core to ensure accurate breaking of circuit breakers.
[0003] Existing error-prevention technologies have covered a variety of strategies, including but not limited to error-prevention threshold setting based on current analysis, secondary equipment control guided by expert systems, intelligent error-prevention algorithms that integrate grid structure and expert knowledge, linkage mechanisms between instruction tickets and error-prevention systems, and intelligent error-prevention integrated operation platforms that integrate micro-topology analysis. These methods are all committed to improving the reliability and accuracy of operations. However, in the face of increasingly complex grid environments and increasing system capacity, the demand for higher-level intelligent error-prevention methods is becoming increasingly urgent, especially intelligent control systems that can dynamically adapt to changes in operating conditions, predict and avoid potential errors in real time, which has become a key technical gap in ensuring the efficient and safe operation of high-voltage DC circuit breakers. Summary of the invention
[0004] In order to overcome the problems existing in the related art, the present invention provides an intelligent error prevention method and device for a synthetic loop synchronous control mode.
[0005] According to a first aspect of an embodiment of the present invention, there is provided an intelligent error prevention method for a synthetic loop synchronous control mode, the intelligent error prevention method for a synthetic loop synchronous control mode comprising:
[0006] Extract the idiom features of the synthetic loop synchronous control mode maintenance order issuance opinion and the features of some operation items of the operation ticket to obtain the extraction results;
[0007] Using the extraction results, a prediction model for the synchronous control mode of the synthetic loop is established;
[0008] Adjusting the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model;
[0009] The final prediction model is used to predict the synchronous control mode of the synthetic loop to achieve intelligent error prevention.
[0010] In some exemplary embodiments of the present invention, based on the above scheme, the extracting of synthetic loop synchronous control mode maintenance list idiom features includes:
[0011] Receive the original text of the synthetic loop synchronous control mode maintenance order issuance opinion;
[0012] Performing word segmentation processing on the original text to obtain a word attribute list including words and their parts of speech;
[0013] Split the original text into multiple sentences, form a sentence attribute list, and record the index of each sentence;
[0014] Eliminate words with useless parts of speech in the word attribute list to obtain a new word attribute list;
[0015] The position of each word in the new word attribute list in each sentence and the sentence index to which it belongs are recorded as the word displacement position;
[0016] Identify and merge synonyms in the original text, mark the merged words, and point to the merged representative words;
[0017] Creating nodes based on each word in the new word attribute list and storing them in a node list;
[0018] Add edges between nodes according to the word displacement position and the sentence index to which it belongs. For the marked node, add the corresponding edge from its master node to the neighbor node, and the corresponding edge weight between the two nodes is fixed;
[0019] Based on the nodes and edges, a text network structure of the idioms of the inspection and issuance opinion of the synthetic loop synchronization control mode inspection and maintenance order is generated and output;
[0020] Counting the frequency of occurrence of each word in the new word attribute list in the original text;
[0021] Calculating a preliminary feature weight for each node based on the occurrence frequency;
[0022] According to the preliminary feature weight of each node, the node comprehensive feature value is calculated;
[0023] All nodes are arranged based on their comprehensive feature values, and the top n words are output, which are the idiomatic features of opinions on issuing circuit breaker maintenance orders.
[0024] In some exemplary embodiments of the present invention, based on the above solution, extracting the operation item features of some operation tickets includes:
[0025] Receive the operation item statement of the operation ticket of the synthetic loop synchronous control mode;
[0026] Performing word segmentation operation on the operation item statement of the synthetic loop synchronous control mode operation ticket to obtain a word segmentation result;
[0027] Performing part-of-speech tagging on the word segmentation result to obtain a tagging result;
[0028] According to the annotation results and in combination with grammatical rules, the operation item features of the operation ticket of the synthetic loop synchronous control mode are extracted.
[0029] In some example embodiments of the present invention, based on the above scheme, using the extraction results to establish a synthetic loop synchronous control mode prediction model includes:
[0030] Dividing the extraction result to obtain a division result, wherein the division result includes training data;
[0031] Using the training data to train a fuzzy weighted neural network to obtain a trained fuzzy weighted neural network;
[0032] The trained fuzzy weighted neural network is output as the synthetic loop synchronous control mode prediction model.
[0033] In some example embodiments of the present invention, based on the above scheme, adjusting the parameters of the synthetic loop synchronous control mode prediction model to obtain the final prediction model includes:
[0034] The improved genetic algorithm is used to adjust the position parameter, width parameter and membership function support value of the synthetic loop synchronous control mode prediction model.
[0035] In some example embodiments of the present invention, based on the above scheme, adjusting the position parameter, width parameter and membership function support value of the synthetic loop synchronous control mode prediction model by using an improved genetic algorithm includes:
[0036] Initialization step: let each individual in the improved genetic algorithm represent the adjustment result of the position parameter, width parameter and membership function support value in a synthetic loop synchronous control mode prediction model;
[0037] Steps to establish a population: Generate L individuals in a decimal way to establish an initial population;
[0038] Fitness solving steps: taking the minimum output error of the prediction model of the synthetic loop synchronous control mode as the fitness and solving the fitness;
[0039] Crossover and mutation steps: According to the fitness value, the roulette wheel selection method is used to select the better individuals from the current individuals, and adaptive crossover and mutation operations are carried out to obtain a new offspring population;
[0040] Immigration step: using the immigration mechanism to replace individuals whose fitness is lower than the threshold in the new offspring population;
[0041] Judgment step: judge whether the stopping condition is met. If so, output the current new offspring population and obtain the final prediction model based on the current new offspring population; otherwise, return to the crossover mutation step.
[0042] In some exemplary embodiments of the present invention, based on the above scheme, the migration step includes:
[0043] If the current new offspring population is premature, the number of immigrants is determined according to the evolutionary state, and a corresponding number of immigrants are produced according to preset rules to replace some individuals in the new offspring population.
[0044] According to a second aspect of an embodiment of the present invention, there is provided an intelligent error prevention device for a synthetic loop synchronous control mode, comprising:
[0045] The data extraction module is used to extract the idiom features of the synthetic loop synchronous control mode maintenance order issuance opinion and the features of some operation items of the operation ticket to obtain the extraction results;
[0046] A model building module, used to build a synthetic loop synchronous control mode prediction model using the extraction results;
[0047] A parameter adjustment module, used to adjust the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model;
[0048] The result output module is used to predict the synchronous control mode of the synthetic loop using the final prediction model to achieve intelligent error prevention.
[0049] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the intelligent error prevention method for the synthetic loop synchronous control mode in the first aspect is implemented.
[0050] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the intelligent error prevention method for the synthetic loop synchronous control mode in the first aspect is implemented.
[0051] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:
[0052] Improve operational efficiency and accuracy: By automatically extracting the features of idiomatic expressions in the maintenance order and the features of key operation items in the operation ticket, it can quickly identify and summarize the key factors affecting the safety of circuit breaker operation, reduce the time cost and human errors of manual review, and ensure the accuracy of each step of the operation instruction;
[0053] Preventive error control: The synthetic loop synchronization control mode prediction model established is based on in-depth learning of historical data and operating habits. It can proactively identify potential operating risks and error modes, and prevent equipment damage or power grid accidents caused by improper operation sequence, unsatisfied conditions, etc. from the source, thus achieving a shift from passive response to active prevention.
[0054] Personalization and adaptive optimization: The prediction model is optimized through parameter adjustment, and can be adaptively adjusted according to different circuit breaker models to ensure the high personalization and scenario adaptability of the prediction model, thereby providing an intelligent error prevention strategy that is more in line with actual needs;
[0055] Intelligent decision support: The optimized prediction model is finally used to make intelligent predictions of the synchronous control mode of the circuit breaker synthesis loop, which can provide operators with accurate operation suggestions and early warning information in real time, greatly enhancing the stability and safety of power system operation.
[0056] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0058] Figure 1 A schematic diagram showing a system architecture of an exemplary application environment of an intelligent error prevention method and device for a synthetic loop synchronous control mode to which an embodiment of the present invention can be applied;
[0059] Figure 2 A schematic diagram of a flow chart of an intelligent error prevention method for a synthetic loop synchronous control mode according to some embodiments of the present invention is shown;
[0060] Figure 3 Schematically showing a circuit breaker synthesis loop synchronous control principle diagram according to some embodiments of the present invention;
[0061] Figure 4 Schematically shows a schematic diagram of intelligent error prevention results of a synthetic loop synchronous control mode according to some embodiments of the present invention;
[0062] Figure 5 Schematically showing a schematic diagram of prediction results of a synthetic loop synchronous control mode according to some embodiments of the present invention;
[0063] Figure 6 Schematically shows a schematic diagram of an intelligent error prevention device of a synthetic loop synchronous control mode according to some embodiments of the present invention;
[0064] Figure 7 A schematic diagram schematically shows a structure of a computer system of an electronic device according to some embodiments of the present invention;
[0065] Figure 8 A schematic diagram of a computer-readable storage medium according to some embodiments of the present invention is schematically shown. DETAILED DESCRIPTION
[0066] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.
[0067] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0068] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0069] Figure 1 A schematic diagram of a system architecture of an exemplary application environment of an intelligent error prevention method and device for a circuit breaker synthetic loop synchronous control mode to which an embodiment of the present invention can be applied is shown.
[0070] like Figure 1As shown, the system architecture 100 may include one or more terminal devices such as a desktop computer 101, a portable computer 102, a smart phone 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the terminal device and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables, etc. The terminal device may be any electronic device with data processing capabilities, which has a display screen for displaying target structure feature points or three-dimensional spatial information of each independent pipeline to the user, including but not limited to the above-mentioned desktop computers, portable computers, smart phones, etc. It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. According to the implementation requirements, there may be any number of terminal devices, networks and servers. For example, the server 105 may be a sub-server cluster composed of multiple sub-servers.
[0071] The intelligent error prevention method for the synchronous control mode of the circuit breaker synthesis circuit provided in the embodiment of the present invention can generally be executed by the terminal device, and accordingly, the intelligent error prevention device for the synchronous control mode of the circuit breaker synthesis circuit is generally set in the terminal device. However, it is easy for those skilled in the art to understand that the intelligent error prevention method for the synchronous control mode of the circuit breaker synthesis circuit provided in the embodiment of the present invention can also be executed by the server 105, and accordingly, the intelligent error prevention device for the synchronous control mode of the circuit breaker synthesis circuit can also be set in the server 105, which is not particularly limited in this exemplary embodiment.
[0072] In addition, it should be understood that the intelligent error prevention method of the circuit breaker synthesis circuit synchronous control mode of the embodiment of the present invention can be configured as a software module. In some implementation scenarios, the intelligent error prevention scheme of the circuit breaker synthesis circuit synchronous control mode of the present invention can be deployed separately to realize the intelligent error prevention of different circuit breaker synthesis circuit synchronous control modes. In other implementation scenarios, the intelligent error prevention scheme of the circuit breaker synthesis circuit synchronous control mode of the present invention can be deployed in other software as a functional module of the software, such as deployed in the analysis software of the intelligent error prevention of the circuit breaker synthesis circuit synchronous control mode. The present invention does not impose any special restrictions on the application method of the intelligent error prevention method of the circuit breaker synthesis circuit synchronous control mode.
[0073] Next, the embodiments of the present invention are described in detail.
[0074] like Figure 2 As shown, Figure 2 The present invention is a flow chart of an intelligent error prevention method for a circuit breaker synthesis loop synchronous control mode according to an exemplary embodiment of the present invention. The intelligent error prevention method for a circuit breaker synthesis loop synchronous control mode includes:
[0075] S210: extracting the idiom features of the circuit breaker maintenance sheet issuance opinion and the features of some operation items of the operation sheet to obtain the extraction results;
[0076] S220: Establishing a synthetic loop synchronous control mode prediction model using the extraction result;
[0077] S230: adjusting the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model;
[0078] S240: Utilize the final prediction model to predict the circuit breaker synthesis loop synchronization control mode to achieve intelligent error prevention.
[0079] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:
[0080] Improve operational efficiency and accuracy: By automatically extracting the features of idiomatic expressions in the maintenance order and the features of key operation items in the operation ticket, it can quickly identify and summarize the key factors affecting the safety of circuit breaker operation, reduce the time cost and human errors of manual review, and ensure the accuracy of each step of the operation instruction;
[0081] Preventive error control: The established synthetic loop synchronous control mode prediction model is based on in-depth learning of historical data and operating habits. It can proactively identify potential operating risks and error modes, and prevent equipment damage or power grid accidents caused by improper operating sequence, unmet conditions, etc. from the source, thereby achieving a shift from passive response to active prevention.
[0082] Personalization and adaptive optimization: The prediction model is optimized through parameter adjustment, and can be adaptively adjusted according to different circuit breaker models to ensure the high personalization and scenario adaptability of the prediction model, thereby providing an intelligent error prevention strategy that is more in line with actual needs.
[0083] Intelligent decision support: The optimized prediction model is finally used to make intelligent predictions of the synchronous control mode of the circuit breaker synthesis loop, which can provide operators with accurate operation suggestions and early warning information in real time, greatly enhancing the stability and safety of power system operation.
[0084] In S210, the features of idioms in issuing opinions for maintenance orders in the synthetic loop synchronous control mode are extracted, including:
[0085] In power system control, multiple components and loops may work together to complete specific operational tasks. A synthetic loop refers to the integration of multiple related circuits or control signals to form a unified control loop in order to manage the operating status of the power system more efficiently and accurately. When performing operations such as grid dispatching, fault handling, and load adjustment, synthetic loops can ensure seamless connection of various links, reduce operational delays, and improve system stability and reliability.
[0086] Multiple components may include circuit breakers, relays, transformers, mutual inductors, lightning rods, busbars, switchgear, relay protection devices, automated control systems (including SCADA data acquisition and monitoring control systems, DCS distributed control systems, etc.), communication systems (such as optical fiber communication, wireless communication, etc.), etc. For example, in some implementations, the control signals or physical connections generated by some or all of these components are integrated, and through carefully designed control logic and communication protocols, they work together as a whole. This includes not only physical connections at the hardware level, but also logical integration at the software and algorithm levels to achieve precise control and efficient management of the operating status of the entire power system.
[0087] The synchronous control mode requires that the various related circuits or control signals in the synthetic loop are highly coordinated and consistent when performing operations, that is, they are precisely synchronized in time to ensure that all control actions are executed accurately in the predetermined order and conditions.
[0088] The synthetic circuit maintenance order issuance opinion refers to a formal document written by professional technicians or maintenance teams after completing on-site inspections and tests when performing regular maintenance, troubleshooting or upgrading of synthetic circuits, focusing on the problems found, maintenance suggestions, required materials, and operational safety precautions. This opinion letter is not only the basis for maintenance work, but also an important reference for subsequent maintenance execution, quality control, and system recovery. Its content usually covers fault description, impact analysis, maintenance suggestions, operational safety measures, work plans, quality control requirements, and subsequent monitoring suggestions, etc.
[0089] The present invention does not limit the method for extracting the idiom features of the circuit breaker maintenance order issuance opinion. For example, natural language processing technology (such as bag-of-words model, TF-IDF, word embedding, etc.) can be used to analyze the original text of the circuit breaker maintenance order issuance opinion to extract sentiment tendencies, keywords, themes and other features; rule matching method can also be used, that is, based on expert experience and a common problem library, a series of rules and keyword matching patterns are set to automatically identify key information in the maintenance opinion, such as fault type, recommended measures, etc.; or machine learning models, deep learning methods and other methods.
[0090] Considering the accuracy of feature extraction, the method for extracting the feature of the customary phrases of the synthetic loop synchronous control mode maintenance order issuance opinion provided by the present invention includes:
[0091] Receive the original text of the synthetic loop synchronous control mode maintenance order issuance opinion;
[0092] Performing word segmentation processing on the original text to obtain a word attribute list including words and their parts of speech;
[0093] Split the original text into multiple sentences, form a sentence attribute list, and record the index of each sentence;
[0094] Eliminate words with useless parts of speech in the word attribute list to obtain a new word attribute list;
[0095] The position of each word in the new word attribute list in each sentence and the sentence index to which it belongs are recorded as the word displacement position;
[0096] Identify and merge synonyms in the original text, mark the merged words, and point to the merged representative words;
[0097] Creating nodes based on each word in the new word attribute list and storing them in a node list;
[0098] Add edges between nodes according to the word displacement position and the sentence index to which it belongs. For the marked node, add the corresponding edge from its master node to the neighbor node, and the corresponding edge weight between the two nodes is fixed;
[0099] Based on the nodes and edges, a text network structure of the idioms of the inspection and issuance opinion of the synthetic loop synchronization control mode inspection and maintenance order is generated and output;
[0100] Counting the frequency of occurrence of each word in the new word attribute list in the original text;
[0101] Calculating a preliminary feature weight for each node based on the occurrence frequency;
[0102] According to the preliminary feature weight of each node, the node comprehensive feature value is calculated;
[0103] All nodes are arranged based on their comprehensive feature values, and the top n words are output, which are the idiomatic features of opinions on issuing circuit breaker maintenance orders.
[0104] Here, the original text can be segmented by means of preset word segmentation rules (such as the maximum matching method, the minimum segmentation method), statistical word segmentation (such as the HMM hidden Markov model, the maximum entropy model), deep learning methods (such as the RNN recurrent neural network, the LSTM long short-term memory network, the bidirectional LSTM combined with the CRF conditional random field, etc.), and of course, for the convenience of processing, ready-made natural language processing tools can also be used, such as the jieba word segmentation library, NLTK, spaCy, etc. in Python. Those skilled in the art can select a suitable processing method according to the needs to segment the original text of the present invention and obtain a word attribute list containing words and their part-of-speech tags.
[0105] A word is the smallest meaningful unit in a text. For example, in a sentence, "is", "wrong", "complete", etc. are all words. The part-of-speech is the grammatical category of a word, which describes the grammatical role played by the word in a sentence. The part-of-speech classification may be different in different languages, but common parts-of-speech include nouns, verbs, adjectives, adverbs, etc. The word attribute list is a set or sequence that contains each word and the corresponding part-of-speech information in the text. Each record usually includes the word itself and the part-of-speech tag corresponding to the word.
[0106] When performing sentence splitting on the original text, tools or methods similar to those for word segmentation can also be used, such as preset sentence splitting rules, ready-made natural language processing tools, etc. In order to be simple, efficient, and meet the sentence splitting requirements of most general texts, the present invention uses punctuation marks to perform sentence splitting on the original text, which can be specifically carried out in the following manner:
[0107] Scan the text to identify all potential end punctuation marks of sentences; for the dialogues within quotation marks and the additional explanations within parentheses, design an algorithm to determine whether they truly mark the end of a sentence; for the split sentences, record their start and end positions in the original text, or directly assign a unique index to form a sentence attribute list for subsequent feature extraction and analysis.
[0108] When extracting the idiomatic expression feature of the signature opinion of the maintenance list for the synthetic circuit synchronization control mode, some words are not very helpful for achieving the goal of idiomatic expression feature extraction or may introduce noise, and these are usually called useless words. Common useless words include the corresponding part-of-speech tags of stop words (such as "of", "and", "in", etc.). In the present invention, those skilled in the art can define a list of useless words according to the purpose of idiomatic expression feature extraction and remove all words with useless part-of-speech tags. After removal, what remains is a new list that only contains useful or target part-of-speech words and their part-of-speech tags. This refined list is more concise and more suitable for subsequent natural language processing tasks such as sentiment analysis, topic modeling, and keyword extraction.
[0109] After getting the new word attribute list, find the exact position of each word in the sentence it belongs to. The position is usually the word number counted from the beginning of the sentence, for example, the first word of a sentence is position 1, the second word is position 2, and so on. In addition to the position of the word within the sentence, it is also necessary to record which sentence each word belongs to. The sentence index assigns a unique numeric identifier to each sentence, so that each word can be traced back to the complete sentence environment in which it is located. Recording the position of the word in the sentence together with the index of the sentence it belongs to forms the displacement position of the word.
[0110] In addition, the present invention also considers the processing of synonyms, and synonyms can be identified with the help of dictionaries, word networks or machine learning models. For example, "damage" and "damage" can be regarded as synonyms. After identifying synonyms, in order to simplify text representation, reduce dimensions, and improve analysis efficiency, the same word is merged into a representative word. For example, when "damage" and "damage" are regarded as synonyms, in subsequent analysis, the two words will no longer be regarded as independent entities, but will be uniformly represented by a representative word, which may be any one of the two or a neutral alternative word. In order to maintain the transparency and traceability of information, the merged synonyms will be marked with a special symbol, which can be an "M" or a mark of other content, not limited to alphanumeric characters or symbols, indicating that they have been processed and no longer exist independently. At the same time, each "M"-marked word will have a link or reference to its merged representative word to ensure that it can be traced back to the actual word when needed. This is conducive to reducing data redundancy and improving processing efficiency without affecting the analysis results.
[0111] In addition, the present invention also uses each word in the new word attribute list as the smallest unit of text analysis and abstracts it into a node, each node representing a unique word in the text. All created nodes are organized and stored in a structured data set, namely the "node list". This list maintains a collection of all related word nodes in text analysis, which is not only convenient for management and query, but also facilitates the construction of associations between words (such as co-occurrence relationships, dependency relationships, etc.).
[0112] Adding edges between nodes based on the displacement position of words and the index of the sentences they belong to means that if two words are adjacent in the text or closely related in the same sentence, there will be an edge connecting them to reflect their connection in the context. For nodes marked as M, instead of establishing edges directly at their original positions, edges are added to the master nodes they point to (synonym nodes are merged to point to a common representative node) to the nodes that were originally adjacent to these synonyms. Doing so actually maintains the clarity of the network structure, avoids duplication, and ensures that the semantics of synonyms are correctly integrated into the context of the representative node. Whether in regular nodes or in the process of processing synonym nodes (M nodes), each edge established has a fixed weight, which means that no matter what context the relationship between words is based on, the edges between them are considered equivalent in weight. Fixed edge weights simplify the analysis of the network, especially in scenarios where the specific association strength or frequency differences between words are not considered.
[0113] The preliminary feature weight of each node can be calculated as follows:
[0114]
[0115] in, Representation Node No. The initial feature weights of the iteration, is the coefficient factor, For Node The neighbor nodes of Representation Node No. The initial feature weights for the iteration, Representation Node The word frequency, Representation Node The word frequency, Is a node i The set of neighbor nodes of Is a node Neighbor nodes of Is a node and nodes The sharing weight of and Respectively represent nodes The neighbor node set and node The set of neighbor nodes; is the total number of nodes.
[0116] Node comprehensive eigenvalue It is calculated by:
[0117]
[0118] in, is the weight distribution coefficient, It is the semantic weight of the word node in the text network of the idiom of the synthetic loop synchronous control mode maintenance order issuance opinion; Representation Node No. The initial feature weight of the iteration, when the node is in the title sentence position of the idiomatic text of the inspection form issuance opinion, ; When the node is in the text of the maintenance order issuance opinion idiom text, ; The higher the value, the The greater the possibility of the synthetic loop synchronous control mode maintenance order issuance opinion idiomatic characteristics.
[0119] Finally, follow Arrange all word nodes by value and output the top n words, i.e. the idiomatic features of the opinions on the issuance of maintenance orders for the synthesis loop synchronization control mode .
[0120] In S210, extracting the operation item features of some operation tickets includes:
[0121] An operation ticket is usually a document used to guide staff to perform specific operation steps in power systems, industrial control or other fields that require strict operating procedures. It lists in detail the sequence and specific actions that need to be followed to perform a task (such as equipment maintenance, startup, shutdown, etc.).
[0122] Characteristics of operation items may include, but are not limited to, operation type (basic classifications such as opening equipment, closing valves, adjusting setting parameters, etc.), operation object (referring to the specific target equipment or system components of the operation, such as circuit breakers, transformers, pumps, etc.), operation conditions (conditions that must be met before performing the operation, such as system pressure, voltage level or safety lock status), sequence of operation steps (whether the operation depends on the completion of the previous step, the position in the operation sequence), safety criticality (the potential impact of the operation on personnel safety, equipment integrity or system stability), execution time (the estimated time required to complete each operation) and required tools or equipment (special tools or auxiliary equipment required to perform the operation).
[0123] The present invention does not specifically limit the method for extracting the characteristics of the operation items in the operation ticket. Those skilled in the art may use manual analysis, natural language processing, machine learning / deep learning, etc. to extract the characteristics.
[0124] In order to achieve efficient and accurate feature extraction, the present invention uses the Chinese word segmentation method based on Hidden Markov Model (HMM) to extract the operation item features of the operation ticket of the synthetic loop synchronization control mode. The Chinese word segmentation algorithm based on the word formation is divided into word position categories according to the position of the word in the word, which are word , the beginning of the word 、 ,suffix . To an existence The Chinese sentence of the operation item of the operation ticket of the synthesis loop synchronous control mode operation ticket of the word, the formula representing the word segmentation principle is:
[0125]
[0126] in, Represents the joint probability of the Chinese sentence sequence of the operation items of the operation ticket of the synthetic loop synchronous control mode, Represents the observed variables of the operation items of the operation ticket of the synthetic loop synchronous control mode; express arrive The joint probability of different observed variables appearing together is express The probability of occurrence of the operation item in the operation ticket, express arrive Under the premise that different observed variables appear, The probability of operating an item in an operation ticket, Represents observed variables Expanding forward l , expand backward to After that, the operation ticket operation items appear The probability of Represents the observed variables of the operation items of the operation ticket of the synthetic loop synchronous control mode; Indicates the name of the operation item in the operation ticket; Represents observed variables Expanding forward l , represents the observed variable, Represents observed variables Expand backward to , Indicates The word position of each word ; Synthetic loop synchronous control mode operation ticket operation item Chinese sentence number is ~ ; and The word in the context of the word is the word position feature of the operation ticket of the operation project of the synthesis loop synchronous control mode. HMM is used to complete the Chinese word segmentation formed by the word. The observation sequence corresponding to the Chinese sentence of the synthesis loop synchronous control mode operation ticket operation project is that the word and the observation value correspond to each other, the sentence and the observation sequence correspond to each other, and the word position sequence and the state sequence correspond to each other. In this case, if the word position of a character depends only on the word position of the previous character, then HMM can complete the Chinese word segmentation by character. The output result after word segmentation is input into the part-of-speech tagging model, and the corresponding part-of-speech of the operation ticket operation item is output. The state space of the operation ticket operation item of the synthetic loop synchronous control mode of the HMM model is , the observation space is , The corresponding parts of speech are verbs, nouns, place names, prepositions, adverbs, and punctuation marks. Represents a non-repeating set of terms constructed from all operation item terms in the operation ticket.
[0127] Furthermore, the features of some operation items of the operation ticket are extracted, including:
[0128] Receive the operation item statement of the operation ticket of the synthetic loop synchronous control mode;
[0129] Performing word segmentation operation on the operation item statement of the synthetic loop synchronous control mode operation ticket to obtain a word segmentation result;
[0130] Performing part-of-speech tagging on the word segmentation result to obtain a tagging result;
[0131] According to the annotation results and in combination with grammatical rules, the operation item features of the operation ticket of the synthetic loop synchronous control mode are extracted.
[0132] Here, grammatical rules refer to the rules of how words in a language are combined into phrases and sentences, such as subject-verb-object structure, modification relationship, etc. By applying these rules, the logical relationship and meaning level between the annotated content can be understood more accurately. The ultimate goal is to "extract the characteristics of the operation items." This means that after understanding the structure and meaning of the text, the key characteristics or elements related to the operation items are identified and summarized. For example, specific operation steps (such as "start the generator"), operating conditions (such as "after the system pressure reaches the threshold"), and equipment components involved (such as "second loop controller") are extracted from the text.
[0133] In S220, a synthetic loop synchronous control mode prediction model is established using the extraction result.
[0134] From the above content, it can be clearly known that the extraction results include the idiomatic features of the issuance opinions of the maintenance order of the synthetic loop synchronous control mode and the characteristics of some operation items of the operation ticket.
[0135] On this basis, a suitable network model can be selected as the basic model to establish a synthetic loop synchronization control mode prediction model. For example, in some embodiments, a machine learning model such as a random forest, a support vector machine, a neural network, or a deep learning model such as a recurrent neural network (RNN) or a long short-term memory network (LSTM) is selected as the basic model.
[0136] In order to flexibly adjust the network structure and fuzzy rules, so as to effectively extract features from the original data, the present invention uses the fuzzy weighted neural network as the basic network, and uses the extraction results to train the basic network to establish a synthetic loop synchronous control mode prediction model. The specific steps include:
[0137] Dividing the extraction result to obtain a division result, wherein the division result includes training data;
[0138] Using the training data to train the fuzzy weighted neural network to obtain a trained fuzzy weighted neural network;
[0139] The trained fuzzy weighted neural network is output as the synthetic loop synchronous control mode prediction model.
[0140] Idiomatic features of the synthetic loop synchronous control mode maintenance order issuance opinions to be extracted , and the extracted operation item features of the operation ticket , as the input of the fuzzy weighted neural network ,Will The data is divided into two parts, one for training and the other for evaluating the effect of the fuzzy weighted network model. A reasonable prediction model for the synchronous control mode of the synthetic loop is established. The training is completed with the prediction model achieving ideal recognition accuracy, thereby improving the prediction accuracy of the synchronous control mode of the synthetic loop and realizing intelligent error prevention. The prediction model is tested through the reserved evaluation data, and the prediction result of the synchronous control mode of the synthetic loop is output.
[0141] Order Input data samples The number of fuzzy subsets is , the number of fuzzy subsets of the output synthesis loop synchronous control mode prediction result Y is ; The maximum number of fuzzy rules is , the number of samples of idiom features and operation item feature data of operation tickets is The fuzzy weighted neural network consists of five layers: input layer , Rule Condition Layer , variable rule layer , Rule Conclusion Layer , output layer . Output for:
[0142]
[0143] Responsible for fuzzy processing , Output for:
[0144]
[0145] in, The internal node number is ; The width parameter of the membership function is , the positional parameters are .
[0146] Each node in the fuzzy rule corresponds to a fuzzy rule, which is responsible for simplifying the number of fuzzy rules. Output for:
[0147]
[0148] in, The internal node number is ; Neidi The data samples of the synthetic loop synchronous control mode idiom features and operation item feature data of the operation ticket are . Responsible for fuzzy partitioning of the output results of the synchronous control mode of the synthesis loop, Output for:
[0149]
[0150] The correction factor is ; The weight is ; The input data sample when the number of fuzzy subsets of the prediction result Y of the synthetic loop synchronous control mode is 1 is The defuzzification is completed through the centroid method, and the prediction result of the synthetic loop synchronous control mode is output. Output as follows:
[0151]
[0152] Among them, the membership function support value of the output result is ; The number of fuzzy subsets is The input data sample is , the correction factor is .
[0153] In S310, in order to improve the prediction accuracy of the synthetic loop synchronous control mode prediction model, the present invention further adjusts the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model.
[0154] The parameters of the synthetic loop synchronous control mode prediction model can be adjusted by using a grid search method, a random search method, a Bayesian optimization method, a cross-validation method, a learning rate adjustment method, etc. Since the genetic algorithm has the characteristics of strong global search capability, parallel processing capability and robustness, etc., therefore, optionally, as an implementation method, the present invention uses an improved genetic algorithm to adjust the position parameter, width parameter and membership function support value of the synthetic loop synchronous control mode prediction model.
[0155] Further, the adjusting step includes:
[0156] Initialization step: let each individual in the improved genetic algorithm represent the adjustment result of the position parameter, width parameter and membership function support value in a synthetic loop synchronous control mode prediction model;
[0157] Steps to establish a population: Generate L individuals in a decimal way to establish an initial population;
[0158] Fitness solving steps: taking the minimum output error of the prediction model of the synthetic loop synchronous control mode as the fitness and solving the fitness;
[0159] Fitness The solution formula is:
[0160]
[0161]
[0162] in, The minimum output error of the prediction model for the synthetic loop synchronous control mode, is the expected output of the prediction model for the synthetic loop synchronization control mode, The actual output of the prediction model for the synthetic loop synchronization control mode, is an adjustable factor; the number of samples of idiom features and operation item feature data of operation tickets is , Indicates input data samples.
[0163] Crossover and mutation steps: According to the fitness value, the roulette wheel selection method is used to select the better individuals from the current individuals, and adaptive crossover and mutation operations are carried out to obtain a new offspring population;
[0164] No. Individual adaptive crossover probability The formula is as follows:
[0165]
[0166] Among them, the largest The value is ; The mean is ; The random number is ; The larger of the two individuals to be crossed The value is ; , For the collection , The adaptive crossover probability of individuals, and .
[0167] The roulette selection method includes: calculating the cumulative probability of each individual, then simulating the roulette wheel, making the size of each sector on the roulette wheel proportional to the probability of the corresponding individual, and then matching the random number to the area on the roulette wheel by generating random numbers.
[0168] Immigration step: using the immigration mechanism to replace individuals whose fitness is lower than the threshold in the new offspring population;
[0169] If the current new offspring population is premature, the number of immigrants is determined according to the evolutionary state, and a corresponding number of immigrants are produced according to preset rules to replace some individuals in the new offspring population.
[0170] This step can effectively avoid premature maturity and improve population diversity. , analyze the premature situation of the group, determine the rules for adding immigrants according to the number of iterations, and when premature situation occurs, determine the number of immigrants according to the evolutionary state, and produce the required number of high-quality immigrants according to the specified rules to replace the poor individuals in the group. The calculation formula is:
[0171]
[0172] in, It is The fitness of an individual, The mean square error of the generation group is ;No. An individual is , the random number is , is the total number of nodes.
[0173] Design Immigration Addition Guidelines , the number of migration operation intervals is ; Each interval When , a certain number of superior individuals are added to the group. as follows:
[0174]
[0175] The maximum number of iterations is ; The default number of immigrants is ; Rounding the parameter is , For The exponential function with base , Indicates generation.
[0176] Judgment step: judge whether the stopping condition is met. If so, output the current new offspring population and obtain the final prediction model based on the current new offspring population; otherwise, return to the crossover mutation step.
[0177] That is, analyze whether , if it reaches , then the output is the result of fine-tuning the parameters of the prediction model of the synthetic loop synchronous control mode. Otherwise, , return to the crossover mutation step.
[0178] In S240, the final prediction model is used to predict the circuit breaker synthesis loop synchronization control mode to achieve intelligent error prevention.
[0179] The present invention takes a certain power grid circuit breaker as an experimental object, and uses the final prediction model to perform intelligent error prevention control on the circuit breaker in the power grid, verifying the feasibility of the method of the present invention in the intelligent error prevention of the synthetic loop synchronous control mode.
[0180] The principle of synchronous control of the circuit breaker synthesis loop in the power grid is as follows Figure 3 shown.
[0181] The method of the present invention is used to extract the habitual features of the wording used in the issuance of the maintenance order of the synthetic loop synchronous control mode, as well as the features of the operation items of the operation ticket. The extraction results are shown in Tables 1 and 2.
[0182] Table 1. Feature extraction results of idiomatic expressions in the issuance opinions of some maintenance orders
[0183]
[0184] Table 2. Feature extraction results of some operation items in operation tickets
[0185]
[0186] Comprehensive analysis of Table 1 and Table 2 shows that the present invention can effectively extract the idiom features of the synthetic loop synchronous control mode maintenance order issuance opinions and the operation item features of the operation ticket, providing data support for the subsequent synthetic loop synchronous control mode intelligent error prevention.
[0187] There are six synthetic loop synchronous control modes, which are denoted as 1, 2, 3, 4, 5, and 6. The final prediction model of the present invention is used to predict the synthetic loop synchronous control mode of the circuit breaker in the power grid, and the results are as follows: Figure 4 shown.
[0188] analyze Figure 4 It can be seen that the present invention can effectively realize the intelligent error prevention of the synthetic loop synchronous control mode. The intelligent error prevention result shows that the closing function of circuit breaker 2 and the ignition signal input function of ignition ball 2 are not started. The maintenance personnel need to inspect these two parts according to the intelligent error prevention result to ensure that the circuit breaker 2 is closed normally and the ignition ball 2 sends out the ignition signal normally, thereby improving the stability of power grid operation. When different faults occur in the power grid, the effect of the synthetic loop synchronous control mode is predicted by the present invention. When different power grid faults occur, the prediction results of the synthetic loop synchronous control mode are as follows: Figure 5 shown.
[0189] analyze Figure 5 It can be seen that when the power grid has a disconnection fault and an asymmetric lateral fault, the present invention can effectively predict the synthetic loop synchronous control mode, and the predicted result is exactly the same as the actual result; when the power grid has an asymmetric longitudinal fault, the present invention can still effectively predict the synthetic circuit synchronous control mode. That is, when different faults occur in the power grid, the present invention can accurately predict the synthetic loop synchronous control mode, timely discover whether the circuit breaker can work normally, complete intelligent error prevention control, and improve the stability of power grid operation.
[0190] According to a second aspect of an embodiment of the present invention, there is provided an intelligent error prevention device 600 for a synthetic loop synchronous control mode, referring to Figure 6 As shown, including:
[0191] The data extraction module 610 is used to extract the idiom features of the synthetic loop synchronous control mode maintenance order issuance opinion and the features of some operation items of the operation ticket to obtain the extraction results;
[0192] A model building module 620, used to build a synthetic loop synchronous control mode prediction model using the extraction results;
[0193] A parameter adjustment module 630, used to adjust the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model;
[0194] The result output module 640 is used to predict the synthetic loop synchronization control mode using the final prediction model to achieve intelligent error prevention.
[0195] In an exemplary embodiment of the present invention, based on the above solution, the data extraction module 610 may further include a first extraction submodule and a second extraction submodule.
[0196] The first extraction submodule is used to extract the idiomatic features of the synthetic loop synchronous control mode maintenance order issuance opinion;
[0197] The second extraction submodule is used to extract the characteristics of some operation items in the operation ticket.
[0198] It should be noted that, although several modules and submodules of the underground pipeline detection device are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or submodules described above can be embodied in one module or unit. Conversely, the features and functions of one module or submodule described above can be further divided into multiple modules or submodules to be embodied.
[0199] In addition, in an exemplary embodiment of the present invention, an electronic device capable of implementing the above-mentioned underground pipeline detection method is also provided.
[0200] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware embodiments, complete software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, which may be collectively referred to herein as "circuits", "modules" or "systems".
[0201] Refer to the following Figure 7 An electronic device 700 according to such an embodiment of the present invention is described. Figure 7 The electronic device 700 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0202] like Figure 7 As shown, the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 may include but are not limited to: the at least one processing unit 710, the at least one storage unit 720, a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710), and a display unit 740.
[0203] The storage unit stores program codes, which can be executed by the processing unit 710, so that the processing unit 710 performs the steps of various exemplary embodiments of the present invention described in the above “Exemplary Method” section. For example, the processing unit 710 can perform the following steps: Figure 2 As shown in S210, the idiom features of the synthetic loop synchronous control mode maintenance order issuance opinions and the operation item features of some operation tickets are extracted to obtain extraction results; S220, a synthetic loop synchronous control mode prediction model is established using the extraction results; S230, the parameters of the synthetic loop synchronous control mode prediction model are adjusted to obtain a final prediction model; S240, the synthetic loop synchronous control mode is predicted using the final prediction model to achieve intelligent error prevention.
[0204] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 721 and / or a cache memory unit 722 , and may further include a read-only memory unit (ROM) 723 .
[0205] The storage unit 720 may also include a program / utility 724 having a set (at least one) of program modules 725, such program modules 725 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0206] Bus 730 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
[0207] The electronic device 700 may also communicate with one or more external devices 770 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 700, and / or communicate with any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface 750. In addition, the electronic device 700 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 760. As shown, the network adapter 760 communicates with other modules of the electronic device 700 through a bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.
[0208] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the exemplary embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present invention.
[0209] In an exemplary embodiment of the present invention, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present invention is stored. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps of various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present invention.
[0210] refer to Figure 8 As shown, a program product 800 for implementing the above-mentioned underground pipeline detection method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In the present invention, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.
[0211] The program product may use any combination of one or more readable storage media. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
[0212] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).
[0213] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.
[0214] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the exemplary embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiment of the present invention.
[0215] Other embodiments of the invention will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. The invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the claims.
[0216] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. An intelligent error prevention method for a synthetic loop synchronous control mode, characterized in that: include: Extract the idiom features of the synthetic loop synchronous control mode maintenance order issuance opinion and the features of some operation items of the operation ticket to obtain the extraction results; Using the extraction results, a prediction model for the synchronous control mode of the synthetic loop is established; Adjusting the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model; The final prediction model is used to predict the synchronous control mode of the synthetic loop to achieve intelligent error prevention; The features of the customary terms for issuing opinions on the inspection form for the synchronous control mode of the synthetic loop are as follows: Receive the original text of the synthetic loop synchronous control mode maintenance order issuance opinion; Performing word segmentation processing on the original text to obtain a word attribute list including words and their parts of speech; Split the original text into multiple sentences, form a sentence attribute list, and record the index of each sentence; Eliminate words with useless parts of speech in the word attribute list to obtain a new word attribute list; The position of each word in the new word attribute list in each sentence and the sentence index to which it belongs are recorded as the word displacement position; Identify and merge synonyms in the original text, mark the merged words, and point to the merged representative words; Creating nodes based on each word in the new word attribute list and storing them in a node list; Add edges between nodes according to the word displacement position and the sentence index to which it belongs. For the marked node, add the corresponding edge from its master node to the neighbor node, and the corresponding edge weight between the two nodes is fixed; Based on the nodes and edges, a text network structure of the idioms of the inspection and issuance opinion of the synthetic loop synchronization control mode inspection and maintenance order is generated and output; Counting the frequency of occurrence of each word in the new word attribute list in the original text; Calculating a preliminary feature weight for each node based on the occurrence frequency; According to the preliminary feature weight of each node, the node comprehensive feature value is calculated; Arrange all nodes based on their comprehensive feature values, output the top n words, and output the idiomatic features of the opinions on issuing circuit breaker maintenance orders; The characteristics of the operation items of extracting part of the operation ticket include: Receive the operation item statement of the operation ticket of the synthetic loop synchronous control mode; Performing word segmentation operation on the operation item statement of the synthetic loop synchronous control mode operation ticket to obtain a word segmentation result; Performing part-of-speech tagging on the word segmentation result to obtain a tagging result; According to the annotation results, combined with grammatical rules, the operation item features of the operation ticket of the synthetic loop synchronous control mode are extracted; Using the extraction results to establish a synthetic loop synchronous control mode prediction model includes: Dividing the extraction result to obtain a division result, wherein the division result includes training data; Using the training data to train a fuzzy weighted neural network to obtain a trained fuzzy weighted neural network; Outputting the trained fuzzy weighted neural network as the synthetic loop synchronous control mode prediction model; Adjusting the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model includes: The improved genetic algorithm is used to adjust the position parameter, width parameter and membership function support value of the synthetic loop synchronous control mode prediction model.
2. The intelligent error prevention method for the synthetic loop synchronous control mode according to claim 1 is characterized in that: The improved genetic algorithm is used to adjust the position parameters, width parameters and membership function support values of the synthetic loop synchronous control mode prediction model, including: Initialization step: let each individual in the improved genetic algorithm represent the adjustment result of the position parameter, width parameter and membership function support value in a synthetic loop synchronous control mode prediction model; Steps to establish a population: Generate L individuals in a decimal way to establish an initial population; Fitness solving steps: taking the minimum output error of the prediction model of the synthetic loop synchronous control mode as the fitness and solving the fitness; Crossover and mutation steps: According to the fitness value, the roulette wheel selection method is used to select the better individuals from the current individuals, and adaptive crossover and mutation operations are carried out to obtain a new offspring population; Immigration step: using the immigration mechanism to replace individuals whose fitness is lower than the threshold in the new offspring population; Judgment step: judge whether the stopping condition is met. If so, output the current new offspring population and obtain the final prediction model based on the current new offspring population; otherwise, return to the crossover mutation step.
3. The intelligent error prevention method for the synthetic loop synchronous control mode according to claim 2 is characterized in that: The immigration steps include: If the current new offspring population is premature, the number of immigrants is determined according to the evolutionary state, and a corresponding number of immigrants are produced according to preset rules to replace some individuals in the new offspring population.
4. An intelligent error prevention device for a synthetic loop synchronous control mode based on the intelligent error prevention method for a synthetic loop synchronous control mode according to any one of claims 1 to 3, characterized in that: include: The data extraction module is used to extract the idiom features of the synthetic loop synchronous control mode maintenance order issuance opinion and the features of some operation items of the operation ticket to obtain the extraction results; A model building module, used to build a synthetic loop synchronous control mode prediction model using the extraction results; A parameter adjustment module, used to adjust the parameters of the synthetic loop synchronous control mode prediction model to obtain a final prediction model; The result output module is used to predict the synchronous control mode of the synthetic loop using the final prediction model to achieve intelligent error prevention.
5. An electronic device, characterized in that: include: processor; as well as A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the processor, implement the intelligent error-preventing method for the synthetic loop synchronous control mode as claimed in any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the intelligent error prevention method for the synthetic loop synchronous control mode as described in any one of claims 1 to 3 is implemented.
Citation Information
Patent Citations
Operation ticket content extraction method and system for electrical power system
CN108021552A
Power distribution network operation order rapid generation method and device
CN113792538A
Anti-error method and system for power grid dispatching operation, equipment and medium
CN113991843A
Maintenance order issuing opinion identification intelligent ticket forming system based on machine learning
CN114254900A
Intelligent operation ticket error correction method and device based on natural language processing
CN117407749A
