SER event sequence link prediction-based high-voltage DC power transmission system fault diagnosis method and system

Abstract

The invention discloses a high-voltage direct-current power transmission system fault diagnosis method and system based on SER event sequence link prediction, and relates to the technical field of power system power transmission safety. An event knowledge graph is introduced, a plurality of direct-current project historical cases are fused, and a high-voltage direct-current power transmission system abnormal event knowledge graph with an SER abnormal event as a core is constructed; information islands between entities such as projects and faults and events are broken through, a global semantic network capable of migration and reasoning is formed, and deep coupling of services and knowledge is achieved; according to operation and maintenance expert experience, a sequence link prediction task is defined, a high-voltage direct-current power transmission system fault diagnosis data set is constructed, a pre-training language model is introduced, a high-voltage direct-current power transmission system fault diagnosis model and system based on SER event sequence link prediction are established, and high-dimensional correlation features hidden among projects, abnormal events and system faults are extracted. Therefore, the problems of weak adaptability, low automation degree and the like of the existing method are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system transmission safety, and more particularly to a high voltage direct current transmission system fault diagnosis method and system based on SER event sequence link prediction. Background Art

[0002] At present, with the rapid development and high-density access of renewable energy, the new power system faces challenges such as uneven energy distribution and difficult fault analysis. As the core link of the new power system, high voltage direct current (HVDC) transmission has the advantages of long transmission distance, large transmission capacity and good economy.

[0003] The structure of high-voltage direct current transmission equipment is very complex and highly automated. When a fault occurs or an abnormal state exists, the system will generate massive sequence of events recording (SER) data. SER data contains multiple state descriptions such as alarm groups, events, and levels. It is one of the important data for monitoring and evaluating the operating status of the power system. It has the characteristics of high real-time performance, large data volume, and strong serialization. The converter station generates about 100,000 SER data every day, and there are potential risks such as missing important signals, misjudging system status, and untimely operation and maintenance operations. In 2022, when the operation and maintenance personnel of a 500kV converter station in China reviewed the 19-page SER data, they failed to discover the switch on the medium-voltage side of the main transformer in time, resulting in the continuous expansion of the scope of the accident. Therefore, by mining the fault characteristics hidden in massive SER data, intelligent diagnosis of high-voltage direct current transmission system faults can be realized to ensure the safe and reliable operation of the system.

[0004] Currently, the main method used to analyze SER data is association rule mining, which is used for semi-automatic shallow feature extraction, mining strong association rules between SER abnormal events and system faults, and assisting operation and maintenance personnel to manually review and judge fault types according to established rules, such as typical operation and maintenance event diagnosis of converter stations based on association rules, similar fault feature extraction of converter station SER data, and SER data mining based on FP-Growth algorithm. The above research aims to mine the correlation between SER abnormal events and system faults, so as to assist in evaluating whether the system is abnormal. However, there are disadvantages such as heavy reliance on manual labor, poor real-time performance, and extremely low efficiency. The reasons are mainly reflected in the following aspects:

[0005] 1) Unable to extract hidden high-dimensional fault features: Existing research only performs feature extraction and association rule analysis on abnormal signal types, which cannot capture the rich semantic information and serialized structural features of SER abnormal events. The robustness and adaptability of the algorithm are weak;

[0006] 2) Lack of scalable SER data analysis model: Due to differences in line structures and signal naming methods among different DC projects, it is impossible to fuse features of multiple projects and conduct unified SER association rule joint modeling;

[0007] 3) Unable to give diagnostic results autonomously: Existing research can only mine strong correlation rules between abnormal events and system failures, and cannot achieve intelligent diagnosis of system failures. Operation and maintenance personnel are still required to view SER data according to established rules, which has poor real-time performance and low efficiency.

[0008] Therefore, how to solve the above-mentioned drawbacks is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0009] In view of this, the present invention provides a method and system for fault diagnosis of a high-voltage direct current transmission system based on SER event sequence link prediction, introduces event knowledge graph (EKG) technology, integrates multiple DC engineering historical cases, constructs a knowledge graph of abnormal events of a high-voltage direct current transmission system with SER abnormal events as the core, breaks through information islands between entities and events such as engineering and faults, forms a roamable and reasonable global semantic network, and realizes deep coupling of business and knowledge; according to SER data characteristics and operation and maintenance expert experience, defines sequence link prediction (SLP) tasks, constructs a high-voltage direct current transmission system fault diagnosis data set, introduces a pre-trained language model, establishes SER event sequence link prediction models SLP-PLM (Mul) and SLP-PLM (Bin) for fault diagnosis of a high-voltage direct current transmission system, builds a fault diagnosis system of a high-voltage direct current transmission system based on SER event sequence link prediction, extracts hidden high-dimensional correlation features between engineering, abnormal events and system faults, and independently completes fault diagnosis, thereby solving the problems of weak adaptability and low automation of existing methods.

[0010] In order to achieve the above object, the present invention adopts the following technical solution:

[0011] A fault diagnosis method for a high voltage direct current transmission system based on SER event sequence link prediction, comprising:

[0012] Introduce event knowledge graph technology into SER data analysis to build a knowledge graph of abnormal events in the HVDC transmission system;

[0013] Based on SER data features and fault diagnosis business logic, a sequence link prediction task suitable for HVDC system fault diagnosis is defined;

[0014] Based on the knowledge graph of abnormal events in the HVDC transmission system and its corresponding historical fault instances, the evolution link sequence of DC engineering and SER abnormal events under system faults is generated according to the form of sequence link prediction task. Various types of fault data are sampled based on fault cases to obtain the fault diagnosis data set of the HVDC transmission system.

[0015] Establish a SER event sequence link prediction model for HVDC system fault diagnosis;

[0016] The SER event sequence link prediction model is trained using the HVDC system fault diagnosis dataset to obtain a trained SER event sequence link prediction model.

[0017] The fault data of the HVDC transmission system to be tested is input into the SER event sequence link prediction model to obtain the fault diagnosis result of the HVDC transmission system.

[0018] Optionally, the process of constructing the knowledge graph of abnormal events in the high-voltage direct current transmission system is as follows:

[0019] Collect historical cases from multiple DC projects covering UHV, EHV, flexible and conventional DC, including SER files of each station and their corresponding fault types;

[0020] According to the SER data characteristics and fault diagnosis business logic, the abnormal event knowledge graph ontology architecture for HVDC transmission system fault diagnosis is designed. The ontology triples include <project name, SOE alarm, abnormal event>, <abnormal event, immediately after, abnormal event>, <abnormal event, diagnosis result, fault type>;

[0021] Using the TextRank algorithm, the text similarity between abnormal events of non-normal levels and standard protection signals in SER data is calculated;

[0022] Check the abnormal event-protection signal text pairs with similarity greater than 0.5 to obtain the abnormal event sequence of each case and its corresponding protection signal type;

[0023] According to the designed abnormal event knowledge graph ontology architecture, the engineering, abnormal event sequences and fault types are linked and aligned to obtain the abnormal event knowledge graph of the high-voltage direct current transmission system.

[0024] Optionally, the calculation formula for the text similarity is:

[0025]

[0026] Among them, t AE ,t PS are the abnormal event text and the protection signal text respectively, and w is the word that appears in the text pair at the same time.

[0027] Optionally, the definition is applicable to the sequence link prediction task for high voltage direct current transmission system fault diagnosis as follows:

[0028] Define the knowledge graph as Where E is the entity set, is a set of relations, is a set of triples, A collection of entity text descriptions;

[0029] The sequence link prediction task is defined as: given an anchor entity sequence and relationship Under the condition, predict the candidate entity in, is a set of anchor entity sequences, is a set of candidate entities; the sequence link prediction task is simply formalized as (a1, a2, …, a k ,r,? ), specifically divided into sequence scoring function modeling ψ: And the candidate entity probability distribution modeling f: Among them, ? represents the task goal of predicting candidate entity c, is a set of real numbers.

[0030] Optionally, the process of establishing the SER event sequence chaining prediction model for high voltage direct current transmission system fault diagnosis specifically includes:

[0031] A pre-trained language model with language understanding ability is introduced to extract the semantic features of SER event sequence text. According to the SER event sequence link prediction modeling paradigm, a SER event sequence link prediction model for high-voltage direct current transmission system fault diagnosis is constructed to realize the prediction of fault type candidate entities.

[0032] Optionally, the SER event sequence link prediction modeling paradigm is divided into sequence scoring function modeling and candidate entity probability distribution modeling;

[0033] For the input anchor entity sequence and relationship Sequence scoring function modeling calculates any candidate entity through a pre-trained language model The SER event sequence score s = ψ(a1, a2, ..., a k ,r,c * ), select the candidate entity with the highest score as the prediction result:

[0034]

[0035] The sequence scoring function modeling paradigm transforms sequence link prediction into a binary classification problem, enabling the model to fully model the high-dimensional semantic relationship between entities and relations and identify valid or invalid link sequences.

[0036] Candidate entity probability distribution modeling calculates the probability distribution of candidate entities under given conditions through the pre-trained language model:

[0037] s′=P(c * a1,a2,…,a k ,r)=f(a1,a2,…,a k ,r);

[0038] Take the candidate entity with the highest probability as the prediction result:

[0039]

[0040] The candidate entity probability distribution modeling paradigm regards sequence link prediction as a multi-classification or sequence generation problem. The model can directly capture the hidden association features between anchor entity sequences, relations and candidate entities.

[0041] Optionally, under the sequential scoring function modeling paradigm, the model is named SLP-PLM(Bin), and for the link sequence (a1, a2, …, a k ,r,c), with the special token [CLS] as the first and the special token [SEP] as the last, all the node and relationship description texts in the sequence are segmented, and the context text is connected with the special token [SEP] to obtain the token sequence for fine-tuning the pre-trained language model; in the input sequence, each token is embedded by the corresponding token Segmentation Embedding and position embedding The sum of is used to represent it together, that is, for token i, its feature is expressed as:

[0042]

[0043] Among them, for different node or relationship descriptions segmented by special token [SEP], odd elements share the same segmentation embedding e odd , while even elements share the same segmentation embedding e even ;

[0044] The pre-trained language model extracts the link sequence structure features and semantic features from the input sequence, and converts the hidden vector of the last layer encoder or decoder corresponding to the special token [CLS] As the aggregate feature used to calculate the sequence score, H is the hidden state dimension; the sequence scoring function is:

[0045] s=sigmoid(CW T );

[0046] in, is the binary classification weight matrix; in the fine-tuning process, the gradient descent method is used to optimize the pre-training parameter weights and weight matrix W, and the cross entropy loss function is:

[0047]

[0048] in, is the set of positive examples of linked sequences, is the set of negative examples of the linked sequence, y q ∈{0,1} is the negative / positive label of the link sequence, s q1 ,s q2 ∈[0,1] is the score for negative and positive examples; due to the transformation of anchor entity a in the positive example sequence i This will lead to uncertainty in the candidate entities, and the negative example sequence is obtained by randomly replacing the positive candidate entity c:

[0049]

[0050] Optionally, under the candidate entity probability distribution modeling paradigm, the model is named SLP-PLM(Mul). Compared with the SLP-PLM(Bin) model, only the candidate entity c in the link sequence is deleted, that is, (a1, a2, …, a k ,r) is used as the input sequence for fine-tuning the pre-trained language model, and the hidden vector C corresponding to the special token [CLS] of the last layer encoder or decoder is still used as the aggregated feature representation of the input sequence to predict the candidate entities under the current event sequence; the probability distribution of the candidate entities is:

[0051] s′=softmax(CW′ T );

[0052] in, is the multi-classification weight matrix;

[0053] During fine-tuning, the cross entropy loss function is:

[0054]

[0055] Among them, s′ qi ∈[0,1], and y′ qi is the indicator function of the link sequence candidate entity, when the predicted candidate entity is true value, y′ qi =1, otherwise, y′ qi =0.

[0056] Optionally, the step of inputting the fault data of the high voltage direct current transmission system to be tested into the SER event sequence chaining prediction model to obtain the fault diagnosis result of the high voltage direct current transmission system specifically comprises:

[0057] Before diagnosing a high-voltage DC transmission system fault, first confirm the name of the high-voltage DC project to be diagnosed;

[0058] After confirming the HVDC project, extract abnormal events of non-normal level and containing standard protection signals from SER data;

[0059] After confirming the HVDC project and extracting SER abnormal events, a fault diagnosis link sequence is constructed and text segmentation is performed on the link sequence;

[0060] After performing link sequence text segmentation, the token sequence is fed into the SER event sequence link prediction model to obtain the fault diagnosis results of the HVDC transmission system.

[0061] A high voltage direct current transmission system fault diagnosis system based on SER event sequence link prediction, comprising:

[0062] The knowledge graph construction module introduces event knowledge graph technology into SER data analysis to build a knowledge graph of abnormal events in the HVDC transmission system;

[0063] The task definition module defines the sequence link prediction task applicable to the fault diagnosis of the HVDC transmission system based on the SER data characteristics and fault diagnosis business logic;

[0064] The dataset construction module generates a link sequence of the evolution of DC engineering and SER abnormal events under system faults based on the knowledge graph of abnormal events in the HVDC transmission system and its corresponding historical fault instances according to the form of sequence link prediction tasks. It samples various types of fault data based on fault cases to obtain a fault diagnosis dataset for the HVDC transmission system.

[0065] Model building module, which builds the SER event sequence link prediction model for HVDC system fault diagnosis;

[0066] The model training module uses the high-voltage direct current transmission system fault diagnosis data set to train the SER event sequence link prediction model to obtain a trained SER event sequence link prediction model;

[0067] The fault diagnosis module inputs the fault data of the HVDC transmission system to be tested into the SER event sequence link prediction model to obtain the fault diagnosis result of the HVDC transmission system.

[0068] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method and system for high-voltage direct current transmission system fault diagnosis based on SER event sequence link prediction, which has the following beneficial effects:

[0069] 1) In view of the poor scalability of existing SER data analysis methods, event knowledge graph technology is introduced to integrate multiple DC engineering historical cases, and a knowledge graph of abnormal events in high-voltage DC transmission systems with SER abnormal events as the core is constructed. The information islands between entities such as projects and faults and events are connected to form a navigable and reasonable global semantic network with rich semantic information and structural features, which significantly improves the representation ability and scalability of SER data and realizes the deep coupling of business and knowledge.

[0070] 2) In view of the problems of weak adaptability and low degree of automation of existing SER data analysis methods, a sequence link prediction (SLP) task is defined based on SER data characteristics and fault diagnosis business logic, a high-voltage DC transmission system fault diagnosis dataset is constructed, and a pre-trained language model is introduced to establish a SER event sequence link prediction model for high-voltage DC transmission system fault diagnosis. By jointly modeling the high-dimensional fault characteristics of multiple DC projects, the model can adaptively capture the fine-grained semantic information of projects, events and faults in the fault diagnosis dataset and the deep correlation features hidden between them, and realize the fault diagnosis of the high-voltage DC transmission system autonomously and accurately.

[0071] 3) A high-voltage DC transmission system fault diagnosis system based on SER event sequence link prediction was built, which improved the efficiency and accuracy of SER abnormal event analysis and the intelligence level of system operation and maintenance business, reduced the review burden of operation and maintenance personnel, and reduced the potential risks that threaten the safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0073] Figure 1 A schematic diagram of the method provided by the present invention;

[0074] Figure 2 An example diagram of the knowledge graph of abnormal events in the high-voltage direct current transmission system provided by the present invention;

[0075] Figure 3 An example diagram of a sequence link prediction task provided by the present invention;

[0076] Figure 4 A schematic diagram of the process flow of the SER event sequence link prediction modeling method provided by the present invention;

[0077] Figure 5 A schematic diagram of the SLP-PLM (Bin) framework structure under the sequence scoring function modeling provided by the present invention;

[0078] Figure 6 Schematic diagram of the SLP-PLM (Mul) framework structure under the candidate entity probability distribution modeling provided by the present invention. DETAILED DESCRIPTION

[0079] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0080] The embodiment of the present invention discloses a method for diagnosing faults in a high-voltage direct current transmission system based on SER event sequence link prediction, such as Figure 1 As shown, including:

[0081] Introduce event knowledge graph technology into SER data analysis to build a knowledge graph of abnormal events in the HVDC transmission system;

[0082] Based on SER data features and fault diagnosis business logic, a sequence link prediction task suitable for HVDC system fault diagnosis is defined;

[0083] Based on the knowledge graph of abnormal events in the HVDC transmission system and its corresponding historical fault instances, the evolution link sequence of DC engineering and SER abnormal events under system faults is generated according to the form of sequence link prediction task. Various types of fault data are sampled based on fault cases to obtain the fault diagnosis data set of the HVDC transmission system.

[0084] Establish a SER event sequence link prediction model for HVDC system fault diagnosis;

[0085] The SER event sequence link prediction model is trained using the HVDC system fault diagnosis dataset to obtain a trained SER event sequence link prediction model.

[0086] The fault data of the HVDC transmission system to be tested is input into the SER event sequence link prediction model to obtain the fault diagnosis result of the HVDC transmission system.

[0087] In a specific embodiment, the process of constructing a knowledge graph of abnormal events in a high-voltage direct current transmission system is as follows:

[0088] In the HVDC transmission system, SER records system operation status information such as parameter exceeding the limit, alarm events, protection actions, etc. in real time, and serializes and outputs six types of data: time, host, system, level, alarm group, and event. Among them, "host" is the device server that records events, "system" refers to the redundant system used, "level" represents the operation status level of the current event, which is generally divided into "normal", "minor", "alarm" and "emergency", "alarm group" is the device group or software that generates the event, and "event" is a description of the current device operation status.

[0089] SER data has natural real-time and serialization characteristics, and is often used to explore the evolution process of abnormal events under different DC projects and their mapping relationship with system faults. Taking a domestic 500kV converter station as an example, tens of thousands of SER data are generated on average every day, and up to 500,000. Operation and maintenance personnel need to continue to pay attention to SER real-time information, judge the current system operation status, and timely discover the current fault type based on the sequence of abnormal protection action events generated by the alarm group, and take emergency measures to avoid the continued expansion of the scope of the accident.

[0090] Based on SER data features and fault diagnosis business logic, event knowledge graph technology is introduced. "Project name", "abnormal event", and "fault type" are used as node types, and "SOE alarm", "immediately", and "diagnosis result" are used as relationships to connect "project name" with "abnormal event", "abnormal event" with "abnormal event", and "abnormal event" with "fault type" respectively to build a knowledge graph of abnormal events in the high-voltage direct current transmission system, such as Figure 2 As shown in (Case), Class I nodes represent the "project name" entity type, Class II nodes represent the "abnormal event" event type, and Class III nodes represent the "fault type" entity type. The "abnormal event" node is represented by the concatenation of "alarm group" and "event" in the SER data. Compared with the traditional association rule representation method, the abnormal event knowledge graph connects the information islands between projects, events, and faults, forming a navigable and inferable global network with rich semantic information and structural features, which significantly improves the representation ability and scalability of SER data. The detailed process is as follows:

[0091] Collect a large number of historical cases from multiple DC projects covering UHV, EHV, flexible and conventional DC, including SER files of each station and their corresponding fault types;

[0092] According to the SER data characteristics and fault diagnosis business logic, the abnormal event knowledge graph ontology architecture for HVDC transmission system fault diagnosis is designed. The ontology triples include <project name, SOE alarm, abnormal event>, <abnormal event, immediately after, abnormal event>, <abnormal event, diagnosis result, fault type>;

[0093] Using the TextRank algorithm, the text similarity between abnormal events of non-normal levels and standard protection signals in the SER data is calculated:

[0094]

[0095] Among them, t AE ,t PS are the abnormal event text and the protection signal text respectively, and w is the word that appears in the text pair at the same time.

[0096] Check the abnormal event-protection signal text pairs with similarity greater than 0.5 to obtain the abnormal event sequence of each case and its corresponding protection signal type;

[0097] According to the designed abnormal event knowledge graph ontology architecture, the engineering, abnormal event sequences and fault types are linked and aligned to obtain the abnormal event knowledge graph of the high-voltage direct current transmission system.

[0098] In a specific embodiment, the sequence link prediction task applicable to the fault diagnosis of the high voltage direct current transmission system is defined as follows:

[0099] Fault diagnosis of HVDC transmission system is to predict the possible system faults under the condition of given DC project and SER abnormal event evolution process, that is, given the "project name" and "abnormal event" node link, predict the "fault type" node that the "diagnosis result" may point to, which is different from the traditional link prediction (LP) task and path query answering (PQA) task. Here, Figure 3 As shown in the figure, the sequence link prediction (SLP) task suitable for fault diagnosis of HVDC transmission system is redefined.

[0100] Define the knowledge graph as Where E is the entity set, is a set of relations, is a set of triples, A collection of entity text descriptions;

[0101] The sequence link prediction (SLP) task is defined as: given an anchor entity sequence and relationship Under the condition, predict the candidate entity in, is a set of anchor entity sequences, is a set of candidate entities; the sequence link prediction task is simply formalized as (a1, a2, …, a k,r,? ), specifically divided into sequence scoring function modeling ψ: And the candidate entity probability distribution modeling f: Among them, ? represents the task goal of predicting candidate entity c, is a set of real numbers.

[0102] Compared with the traditional link prediction (LP) task, the input of the sequence link prediction task has more entities and more detailed pre-information; compared with the path query question answering (PQA) task, the sequence link prediction task uses a more accurate entity sequence as the query path. Therefore, the sequence link prediction task combines the characteristics of link prediction and path query question answering tasks and is a new knowledge reasoning task.

[0103] In a specific embodiment, based on the knowledge graph of abnormal events in the high-voltage direct current transmission system and its corresponding historical fault instances, a link sequence of the evolution of DC engineering and SER abnormal events under system faults is generated according to the form of sequence link prediction tasks, and a fault case link sequence data set is obtained; taking the case as the unit, various types of fault data are sampled in a ratio of 3:1:1 among training set, validation set and test set, and a high-voltage direct current transmission system fault diagnosis data set is obtained.

[0104] In a specific embodiment, in order to make full use of the semantic features of the SER event sequence text, a pre-trained language model (PLM) is introduced, and candidate entity prediction is achieved by fine-tuning the pre-trained model. Here, the pre-trained language model includes but is not limited to autoencoder (encoder-only) models (such as BERT, RoBERTa, etc.), autoregressive (decoder-only) models (such as Qwen, Llama, etc.), encoder-decoder (encoder-decoder) models (such as GLM, BART, etc.). Based on the pre-trained language model with language understanding ability, a SER event sequence link prediction model SLP-PLM for high-voltage direct current transmission system fault diagnosis is established. The SER event sequence link prediction modeling paradigm is divided into sequence scoring function modeling and candidate entity probability distribution modeling, such as Figure 4 shown.

[0105] For the input anchor entity sequence and relationship Sequence scoring function modeling calculates any candidate entity through a pre-trained language model The SER event sequence score s = ψ(a1, a2, ..., a k ,r,c * ), select the candidate entity with the highest score as the prediction result:

[0106]

[0107] The sequence scoring function modeling paradigm transforms sequence link prediction into a binary classification problem, enabling the model to fully model the high-dimensional semantic relationship between entities and relations and identify valid or invalid link sequences.

[0108] Candidate entity probability distribution modeling calculates the probability distribution of candidate entities under given conditions through the pre-trained language model:

[0109] s′=P(c * |a1,a2,…,a k ,r)=f(a1,a2,…,a k ,r);

[0110] Take the candidate entity with the highest probability as the prediction result:

[0111]

[0112] The candidate entity probability distribution modeling paradigm regards sequence link prediction as a multi-classification or sequence generation problem. The model can directly capture the hidden association features between anchor entity sequences, relations and candidate entities, avoiding the traversal and scoring of all candidate entities.

[0113] Under the sequential scoring function modeling paradigm, the model is named SLP-PLM (Bin), and the model framework is as follows Figure 5 As shown. For the link sequence (a1, a2, ..., a k ,r,c), with the special token [CLS] as the first and the special token [SEP] as the last, all the node and relationship description texts in the sequence are segmented, and the context text is connected with the special token [SEP] to obtain the token sequence for fine-tuning the pre-trained language model; in the input sequence, each token is embedded by the corresponding token Segmentation Embedding and position embedding The sum of is used to represent it together, that is, for token i, its feature is expressed as:

[0114]

[0115] Among them, for different node or relationship descriptions segmented by special token [SEP], odd elements share the same segmentation embedding e odd , while even elements share the same segmentation embedding e even ;

[0116] The pre-trained language model extracts the link sequence structure features and semantic features from the input sequence, and converts the hidden vector of the last layer encoder or decoder corresponding to the special token [CLS] As the aggregated feature used to calculate the sequence score, where H is the hidden state dimension;

[0117] The sequence scoring function is:

[0118] s=sigmoid(CW T );

[0119] in, is the binary classification weight matrix; during the fine-tuning process, the gradient descent method is used to optimize the pre-training parameter weights and weight matrix W;

[0120] The cross entropy loss function is:

[0121]

[0122] in, is the set of positive examples of linked sequences, is the set of negative examples of the linked sequence, y q ∈{0,1} is the negative / positive label of the link sequence, s q1 ,s q2 ∈[0,1] is the score for negative and positive examples;

[0123] Since the anchor entity a in the transformed positive example sequence i This will lead to uncertainty in the candidate entities, and the negative example sequence is obtained by randomly replacing the positive candidate entity c:

[0124]

[0125] Under the candidate entity probability distribution modeling paradigm, the model is named SLP-PLM (Mul), and the model framework is as follows Figure 6 Compared with the SLP-PLM (Bin) model, only the candidate entity c in the link sequence is deleted, that is, (a1, a2, …, a k ,r) is used as the input sequence for fine-tuning the pre-trained language model, and the hidden vector C corresponding to the special token [CLS] of the last layer encoder or decoder is still used as the aggregated feature representation of the input sequence to predict the candidate entity under the current event sequence;

[0126] The probability distribution of candidate entities is:

[0127] s′=softmax(CW′ T );

[0128] in, is the multi-classification weight matrix;

[0129] During fine-tuning, the cross entropy loss function is:

[0130]

[0131] Among them, s′qi ∈[0,1], and y′ qi is the indicator function of the link sequence candidate entity, when the predicted candidate entity is true value, y′ qi =1, otherwise, y′ qi =0.

[0132] In a specific embodiment, the fault data of the high-voltage direct current transmission system to be tested is input into the SER event sequence link prediction model, and the high-voltage direct current transmission system fault diagnosis result is obtained, which specifically includes:

[0133] HVDC Engineering Confirmation

[0134] Before diagnosing a fault in a high-voltage direct current transmission system, first confirm the name of the high-voltage direct current project to be diagnosed. The system provides a high-voltage direct current project confirmation portal for the user to select or type in the name of the high-voltage direct current project. Here, the high-voltage direct current project specified by the user should belong to the scope of high-voltage direct current projects covered by the SER event sequence link prediction model. If not, the user needs to be prompted.

[0135] SER abnormal event extraction

[0136] After confirming the HVDC project, extract abnormal events of abnormal level that contain standard protection signals from the SER data. Here, the standard protection signal should belong to the specified HVDC project, and the abnormal event is represented by the splicing of "alarm group" and "event" in the SER data. The system provides a SER data upload portal or network interface for users to select offline or online data. Methods for determining whether an abnormal event contains a standard protection signal include but are not limited to word segmentation matching, fuzzy matching, semantic matching and other discrimination methods.

[0137] Link Sequence Text Segmentation

[0138] After confirming the HVDC project and extracting the SER abnormal events, a fault diagnosis link sequence is constructed and text segmentation is performed on the link sequence. If the constructed SER event sequence link prediction model belongs to the sequence scoring function modeling paradigm, the link sequence should contain the project name, abnormal event and fault category, such as Figure 5 As shown; if the constructed SER event sequence link prediction model belongs to the candidate entity probability distribution modeling paradigm, the link sequence should consist of the project name and the abnormal event link, such as Figure 6 The text segmentation method should be applicable to the SER event sequence link prediction model, including but not limited to subword level segmentation, character level segmentation, mixed segmentation and other methods.

[0139] Fault diagnosis of HVDC transmission system based on SER event sequence chaining prediction

[0140] After executing the link sequence text segmentation, the token sequence is sent to the SER event sequence link prediction model to obtain the fault diagnosis results of the high-voltage direct current transmission system. In order to facilitate user analysis and judgment, the system should display the N most confident fault types and their confidence levels in the diagnosis results, and provide a selection entry for the number of fault types to be displayed.

[0141] A high voltage direct current transmission system fault diagnosis system based on SER event sequence link prediction, comprising:

[0142] The knowledge graph construction module introduces event knowledge graph technology into SER data analysis to build a knowledge graph of abnormal events in the HVDC transmission system;

[0143] The task definition module defines the sequence link prediction task applicable to the fault diagnosis of the HVDC transmission system based on the SER data characteristics and fault diagnosis business logic;

[0144] The dataset construction module generates a link sequence of the evolution of DC engineering and SER abnormal events under system faults based on the knowledge graph of abnormal events in the HVDC transmission system and its corresponding historical fault instances according to the form of sequence link prediction tasks. It samples various types of fault data based on fault cases to obtain a fault diagnosis dataset for the HVDC transmission system.

[0145] Model building module, which builds the SER event sequence link prediction model for HVDC system fault diagnosis;

[0146] The model training module uses the high-voltage direct current transmission system fault diagnosis data set to train the SER event sequence link prediction model to obtain a trained SER event sequence link prediction model;

[0147] The fault diagnosis module inputs the fault data of the HVDC transmission system to be tested into the SER event sequence link prediction model to obtain the fault diagnosis result of the HVDC transmission system.

[0148] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0149] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction, characterized in that: include: Introduce event knowledge graph technology into SER data analysis to build a knowledge graph of abnormal events in the HVDC transmission system; Based on SER data features and fault diagnosis business logic, a sequence link prediction task suitable for HVDC system fault diagnosis is defined; Based on the knowledge graph of abnormal events in the HVDC transmission system and its corresponding historical fault instances, the evolution link sequence of DC engineering and SER abnormal events under system faults is generated according to the form of sequence link prediction task. Various types of fault data are sampled based on fault cases to obtain the fault diagnosis data set of the HVDC transmission system. Establish a SER event sequence link prediction model for HVDC system fault diagnosis; The SER event sequence link prediction model is trained using the HVDC system fault diagnosis dataset to obtain a trained SER event sequence link prediction model. The fault data of the HVDC transmission system to be tested is input into the SER event sequence link prediction model to obtain the fault diagnosis result of the HVDC transmission system.

2. A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 1, characterized in that: The process of constructing the knowledge graph of abnormal events in the HVDC transmission system is as follows: Collect historical cases from multiple DC projects covering UHV, EHV, flexible and conventional DC, including SER files of each station and their corresponding fault types; According to the SER data characteristics and fault diagnosis business logic, the abnormal event knowledge graph ontology architecture for HVDC transmission system fault diagnosis is designed. The ontology triples include <project name, SOE alarm, abnormal event>, <abnormal event, immediately after, abnormal event>, <abnormal event, diagnosis result, fault type>; Using the TextRank algorithm, the text similarity between abnormal events of non-normal levels and standard protection signals in SER data is calculated; Check the abnormal event-protection signal text pairs with similarity greater than 0.5 to obtain the abnormal event sequence of each case and its corresponding protection signal type; According to the designed abnormal event knowledge graph ontology architecture, the engineering, abnormal event sequences and fault types are linked and aligned to obtain the abnormal event knowledge graph of the high-voltage direct current transmission system.

3. A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 2, characterized in that: The calculation formula of the text similarity is: Among them, t AE ,t PS are the abnormal event text and the protection signal text respectively, and w is the word that appears in the text pair at the same time.

4. The method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 1, characterized in that: The definition is applicable to the sequential link prediction task of HVDC system fault diagnosis as follows: Define the knowledge graph as Where E is the entity set, is a set of relations, is a set of triples, A collection of entity text descriptions; The sequence link prediction task is defined as: given an anchor entity sequence and relationship Under the condition, predict the candidate entity in, is a set of anchor entity sequences, is a set of candidate entities; the sequence link prediction task is simply formalized as (a1, a2, …, a k ,r,? ), specifically divided into sequence scoring function modeling and candidate entity probability distribution modeling Among them, ? represents the task goal of predicting candidate entity c, is a set of real numbers.

5. A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 4, characterized in that: The process of establishing the SER event sequence link prediction model for high voltage direct current transmission system fault diagnosis specifically includes: A pre-trained language model with language understanding ability is introduced to extract the semantic features of SER event sequence text. According to the SER event sequence link prediction modeling paradigm, a SER event sequence link prediction model for high-voltage direct current transmission system fault diagnosis is constructed to realize the prediction of fault type candidate entities.

6. A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 5, characterized in that: The SER event sequence link prediction modeling paradigm is divided into sequence scoring function modeling and candidate entity probability distribution modeling; For the input anchor entity sequence and relationship Sequence scoring function modeling calculates any candidate entity through a pre-trained language model The SER event sequence score s = ψ(a1, a2, ..., a k ,r,c * ), select the candidate entity with the highest score as the prediction result: The sequence scoring function modeling paradigm transforms sequence link prediction into a binary classification problem, enabling the model to fully model the high-dimensional semantic relationship between entities and relations and identify valid or invalid link sequences; Candidate entity probability distribution modeling calculates the probability distribution of candidate entities under given conditions through the pre-trained language model: s′=P(c * a1,a2,…,a k ,r)=f(a1,a2,…,a k ,r); Take the candidate entity with the highest probability as the prediction result: The candidate entity probability distribution modeling paradigm regards sequence link prediction as a multi-classification or sequence generation problem. The model can directly capture the hidden association features between anchor entity sequences, relations and candidate entities.

7. A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 6, characterized in that: Under the sequential scoring function modeling paradigm, the model is named SLP-PLM(Bin). For the link sequence (a1, a2, …, a k ,r,c), with the special token [CLS] as the head and the special token [SEP] as the tail, all the node and relationship description texts in the sequence are segmented, and the context text is connected with the special token [SEP] to obtain the token sequence for fine-tuning the pre-trained language model; In the input sequence, each token is embedded by the corresponding token Segmentation Embedding and position embedding The sum of is used to represent, that is, for token i, Its characteristics are expressed as: Among them, for different node or relationship descriptions segmented by special token [SEP], odd elements share the same segmentation embedding e odd , while even elements share the same segmentation embedding e even ; The pre-trained language model extracts the link sequence structure features and semantic features from the input sequence, and converts the hidden vector of the last layer encoder or decoder corresponding to the special token [CLS] As the aggregate feature used to calculate the sequence score, H is the hidden state dimension; the sequence scoring function is: s=sigmoid(CW T ); in, is the binary classification weight matrix; in the fine-tuning process, the gradient descent method is used to optimize the pre-training parameter weights and weight matrix W, and the cross entropy loss function is: in, is the set of positive examples of linked sequences, is the set of negative examples of the linked sequence, y q ∈{0,1} is the negative / positive label of the link sequence, s q1 ,s q2 ∈[0,1] is the score for negative and positive examples; due to the transformation of anchor entity a in the positive example sequence i This will lead to uncertainty in the candidate entities, and the negative example sequence is obtained by randomly replacing the positive candidate entity c:

8. A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 7, characterized in that: Under the candidate entity probability distribution modeling paradigm, the model is named SLP-PLM(Mul). Compared with the SLP-PLM(Bin) model, only the candidate entity c in the link sequence is deleted, that is, (a1, a2, …, a k ,r) is used as the input sequence for fine-tuning the pre-trained language model, and the hidden vector C corresponding to the special token [CLS] of the last layer encoder or decoder is still used as the aggregated feature representation of the input sequence to predict the candidate entities under the current event sequence; the probability distribution of the candidate entities is: s′=softmax(CW′ T ); in, is the multi-classification weight matrix; During fine-tuning, the cross entropy loss function is: Among them, s′ qi ∈[0,1], and y′ qi is the indicator function of the link sequence candidate entity, when the predicted candidate entity is true value, y′ qi =1, otherwise, y′ qi =0.

9. The method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction according to claim 1, characterized in that: The step of inputting the fault data of the high-voltage direct current transmission system to be tested into the SER event sequence link prediction model to obtain the fault diagnosis result of the high-voltage direct current transmission system specifically includes: Before diagnosing a high-voltage DC transmission system fault, first confirm the name of the high-voltage DC project to be diagnosed; After confirming the HVDC project, extract abnormal events of non-normal level and containing standard protection signals from SER data; After confirming the HVDC project and extracting SER abnormal events, a fault diagnosis link sequence is constructed and text segmentation is performed on the link sequence; After performing link sequence text segmentation, the token sequence is fed into the SER event sequence link prediction model to obtain the fault diagnosis results of the HVDC transmission system.

10. A high voltage direct current transmission system fault diagnosis system based on SER event sequence link prediction, characterized in that: A method for fault diagnosis of a high voltage direct current transmission system based on SER event sequence link prediction as described in any one of claims 1 to 9 is applied, comprising: The knowledge graph construction module introduces event knowledge graph technology into SER data analysis to build a knowledge graph of abnormal events in the HVDC transmission system; The task definition module defines the sequence link prediction task applicable to the fault diagnosis of the HVDC transmission system based on the SER data characteristics and fault diagnosis business logic; The dataset construction module generates a link sequence of the evolution of DC engineering and SER abnormal events under system faults based on the knowledge graph of abnormal events in the HVDC transmission system and its corresponding historical fault instances according to the form of sequence link prediction tasks. It samples various types of fault data based on fault cases to obtain a fault diagnosis dataset for the HVDC transmission system. Model building module, which builds the SER event sequence link prediction model for HVDC system fault diagnosis; The model training module uses the high-voltage direct current transmission system fault diagnosis data set to train the SER event sequence link prediction model to obtain a trained SER event sequence link prediction model; The fault diagnosis module inputs the fault data of the HVDC transmission system to be tested into the SER event sequence link prediction model to obtain the fault diagnosis result of the HVDC transmission system.

Images