Power generation system fault rapid processing method based on speculative retrieval enhancement generation

Abstract

The invention belongs to the technical field of power generation systems, and discloses a power generation system fault rapid processing method based on speculative retrieval enhancement generation. Comprising the following steps: S1, collecting related data of a power generation system, and constructing a fault symptom query library based on the related data; s2, obtaining a current fault symptom description of the power generation system, and performing retrieval in the fault symptom query library based on the current fault symptom description, thereby obtaining a plurality of data fragments related to the current fault symptom description; s3, performing data coding on the plurality of data fragments to form a set, and dividing the set into K clusters through a clustering algorithm to obtain M fault knowledge enhanced subsets; according to the method, different fault problems can be more comprehensively considered, and deviation possibly caused by a single view angle is avoided, so that the accuracy of a fault disposal decision is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power generation systems, and more particularly to a method for quickly handling power generation system faults based on speculative retrieval enhancement generation. Background Art

[0002] In modern power generation systems, fault diagnosis and response processing are the key to ensuring system stability and safety. With the increase in the types of renewable energy power generation, the stability of the power system has been challenged. In the face of the increase in the types of equipment and the complexity of fault modes in the power system, machine learning and artificial intelligence technologies have been introduced into the field of fault diagnosis in recent years, and have achieved certain results. However, the existing intelligent decision-making system still has some key problems, such as response delays during data processing, poor adaptability to real-time data, and the accuracy and efficiency of decision-making in complex fault scenarios still have much room for improvement.

[0003] Moreover, in the process of fault handling, it is usually necessary to retrieve and analyze a large amount of sensor data, historical fault records, operating status data and other information. This information is often redundant and the data sources are diverse. Therefore, how to intelligently and in real time process and analyze massive data in complex power generation systems to improve the decision-making efficiency and accuracy of fault handling is a key technical problem that needs to be solved in the present invention.

[0004] In view of this, the present invention proposes a method for quickly handling power generation system faults based on speculative retrieval enhanced generation to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for quickly handling power generation system faults based on speculative retrieval enhanced generation, comprising the following steps:

[0006] S1. Collect relevant data of the power generation system and build a fault symptom query library based on the relevant data;

[0007] S2. Obtain a current fault symptom description of the power generation system, and search in a fault symptom query library based on the current fault symptom description, thereby obtaining multiple data fragments related to the current fault symptom description;

[0008] S3, encoding multiple data fragments and forming a set, dividing the set into K clusters through a clustering algorithm, and then obtaining M fault knowledge enhanced subsets;

[0009] S4. Train a lightweight language model as a fault handling draft generator, input M fault knowledge enhancement subsets into the fault handling draft generator, and then obtain M fault handling drafts;

[0010] S5. Use the general large language model as the fault handling decision model, score the M fault handling drafts, and use the optimal fault handling draft as the final fault handling decision;

[0011] S6. The final fault handling decision is taken as the final response strategy and executed.

[0012] Furthermore, the step of collecting relevant data of the power generation system and building a fault symptom query library based on the relevant data includes:

[0013] Collect technical documents, books, historical fault records, maintenance manuals, and fault analysis reports of the power generation system as relevant data of the power generation system;

[0014] The relevant data are divided into text blocks, encoded into vectors using the BEG model and stored in a vector database, which is used as a fault diagnosis query library.

[0015] Furthermore, the step of obtaining a current fault symptom description of the power generation system, and searching in a fault symptom query library based on the current fault symptom description to obtain a plurality of data segments related to the current fault symptom description includes:

[0016] Obtaining a current fault symptom description of the power generation system, and retrieving a text block corresponding to the current fault symptom description in a fault symptom query library;

[0017] The corresponding text blocks are used as multiple data segments related to the current fault symptom description.

[0018] Furthermore, the step of encoding the multiple data fragments to form a set, dividing the set into K clusters by a clustering algorithm, and then obtaining M fault knowledge enhanced subsets includes:

[0019] Set the collection of multiple data fragments to , based on the sentence-BERT algorithm, multiple data fragments are Mapping to vector , , and then the vectors of multiple data fragments constitute a set ,in, Indicates that the data fragment is converted using the Sentence-BERT algorithm Encoded as semantic vector ;

[0020] Based on the K-means algorithm, the set V is clustered into k clusters. , the clustering process of set V satisfies the objective function Minimize, its objective function is:

[0021] ,

[0022] In the formula, To minimize the objective function, is the jth cluster, yes The cluster center of is the i-th vector in the set V;

[0023] A data segment is randomly selected from each of the k clusters, and then M fault knowledge enhancement subsets are obtained, where the preset generated M fault knowledge enhancement subsets are , then, Fault Knowledge Enhanced Subset It is expressed as:

[0024] ,

[0025] In the formula, Indicates that in clustering A randomly selected data segment from .

[0026] Furthermore, the step of training the lightweight language model as a fault handling draft generator, inputting M fault knowledge enhancement subsets into the fault handling draft generator, and then obtaining M fault handling drafts includes:

[0027] Train a lightweight language model as a fault handling draft generator. Given a fault event , the answer A of the fault knowledge enhancement subset S is enhanced to generate reason E, that is, As training data T, where Q is a given query, ;

[0028] The lightweight pre-trained language model is fine-tuned using the loss function, and the loss function L is:

[0029] ,

[0030] In the formula, In a given query and fault knowledge enhanced subset The fault handling draft generator generates answers under the conditions and reasons probability;

[0031] Enhance the subset of all fault knowledge The fault handling draft generator is input in parallel. Then, the fault handling draft generated for each fault knowledge enhancement subset and its corresponding reasoning process are as follows:

[0032] ,

[0033] In the formula, The fault handling draft generated for the jth fault knowledge enhanced subset, represents the reason for generating the jth fault handling plan, Represents a fault handling draft generator;

[0034] Finally, M fault handling drafts are obtained , The expression is:

[0035] .

[0036] Furthermore, the step of using the general large language model as the fault handling decision model, scoring the M fault handling drafts, and taking the optimal fault handling draft as the final fault handling decision includes:

[0037] The general large language model is used as the fault handling decision model and M fault handling drafts are respectively The consistency, reliability and consistency of historical fault records are scored, and then M fault handling drafts are obtained. Consistency score, reliability score and historical failure record consistency score;

[0038] According to the percentiles of the scores of the M fault handling drafts, the minimum qualified score thresholds of the three dimensions of consistency, reliability and historical fault record consistency are determined respectively. The minimum qualified score thresholds of the three dimensions are expressed as , and , the scores of the three dimensions are expressed as , and , the weights corresponding to the scores of the three dimensions are expressed as ;

[0039] The optimal fault handling draft is calculated by the scores of the three dimensions and the minimum qualified score thresholds of the three dimensions. The calculation formula is:

[0040] ,

[0041] In the formula, is the optimal fault handling protocol, represents the consistency score of the jth fault handling protocol, represents the reliability score of the jth fault handling plan, represents the score of the consistency of historical fault records of the jth fault handling draft, The weight corresponding to the consistency score, The weight corresponding to the reliability score, The weight corresponding to the score of the consistency of historical fault records is represented by the optimal fault handling draft when: and and The highest scoring draft fault disposal in the case.

[0042] Furthermore, the scoring expression for the consistency of the j-th fault handling protocol is:

[0043] ,

[0044] In the formula, is the scoring function for consistency;

[0045] The scoring expression of the reliability of the j-th fault handling plan is:

[0046] ,

[0047] In the formula, is the scoring function for reliability;

[0048] The scoring expression for the consistency of the historical fault records of the j-th fault handling draft is:

[0049] ,

[0050] In the formula, is the scoring function for the consistency of historical fault records, Similar cases recorded for historical failures.

[0051] Furthermore, the step of taking the final fault handling decision as the final response strategy and executing it includes:

[0052] The final response strategy is automatically executed or handed over to the operator for execution. During the execution process, the recovery status of the current fault symptom description is monitored in real time and corresponding adjustments are made.

[0053] The technical effects and advantages of the method for quickly handling power generation system faults based on speculative retrieval enhanced generation of the present invention are as follows:

[0054] By introducing a multi-perspective data sampling strategy, multiple fault handling drafts can be generated from different fault knowledge enhancement subsets, and each fault handling draft is reasoned based on a different fault scenario perspective; compared with traditional methods, this diversified draft generation method can consider different fault problems more comprehensively, avoiding the deviation that may be caused by a single perspective, thereby significantly improving the accuracy of fault handling decisions; by fine-tuning the fault handling draft generator model, the present invention can quickly and concurrently generate multiple fault handling drafts, and these drafts are uniformly verified by adopting a larger fault handling verifier model, and the divide-and-conquer strategy is used to avoid the inefficient operation of repeatedly retrieving and verifying a large amount of redundant information in the traditional method; this process not only improves the decision-making processing speed, but also greatly reduces the system delay, significantly improving the timeliness of fault response. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of the method for rapid handling of power generation system faults based on speculative retrieval enhanced generation of the present invention. DETAILED DESCRIPTION

[0056] 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.

[0057] Example 1

[0058] See also Figure 1 As shown, the method for quickly handling power generation system faults based on speculative retrieval enhanced generation described in this embodiment includes the following steps:

[0059] S1. Collect relevant data of the power generation system and build a fault symptom query library based on the relevant data;

[0060] S2. Obtain a current fault symptom description of the power generation system, and search in a fault symptom query library based on the current fault symptom description, thereby obtaining multiple data fragments related to the current fault symptom description;

[0061] S3, encoding multiple data fragments and forming a set, dividing the set into K clusters through a clustering algorithm, and then obtaining M fault knowledge enhanced subsets;

[0062] S4. Train a lightweight language model as a fault handling draft generator, input M fault knowledge enhancement subsets into the fault handling draft generator, and then obtain M fault handling drafts;

[0063] S5. Use the general large language model as the fault handling decision model, score the M fault handling drafts, and use the optimal fault handling draft as the final fault handling decision;

[0064] S6. The final fault handling decision is taken as the final response strategy and executed.

[0065] Furthermore, the step of collecting relevant data of the power generation system and building a fault symptom query library based on the relevant data includes:

[0066] Collect technical documents, books, historical fault records, maintenance manuals, and fault analysis reports of the power generation system as relevant data of the power generation system;

[0067] The relevant data are divided into text blocks, encoded into vectors using the BEG model and stored in a vector database, which is used as a fault diagnosis query library.

[0068] Furthermore, the step of obtaining a current fault symptom description of the power generation system, and searching in a fault symptom query library based on the current fault symptom description to obtain a plurality of data segments related to the current fault symptom description includes:

[0069] Obtaining a current fault symptom description of the power generation system, and retrieving a text block corresponding to the current fault symptom description in a fault symptom query library;

[0070] The corresponding text blocks are used as multiple data fragments related to the current fault symptom description;

[0071] Specifically, the fault symptom description includes real-time sensor data of the control system, equipment operating status description, historical fault records, temperature and other factors; based on the current fault symptom description, the sensor data, equipment operating status description, technical documents, books, historical fault records, maintenance manuals, fault analysis reports and other related data (document data) in the fault symptom query library are retrieved by text similarity (retrieval methods include keyword-based, BGE retrieval model, etc.), and multiple data fragments related to the current fault symptom description or scenario can be obtained.

[0072] Furthermore, the step of encoding the multiple data fragments to form a set, dividing the set into K clusters by a clustering algorithm, and then obtaining M fault knowledge enhanced subsets includes:

[0073] Set the collection of multiple data fragments to , based on the sentence-BERT algorithm, multiple data fragments are Mapping to vector , , and then the vectors of multiple data fragments constitute a set ,in, Indicates that the data fragment is converted using the Sentence-BERT algorithm Encoded as semantic vector ;

[0074] Based on the K-means algorithm, the set V is clustered into k clusters. , the clustering process of set V satisfies the objective function Minimize, its objective function is:

[0075] ,

[0076] In the formula, To minimize the objective function, is the jth cluster, yes The cluster center of is the i-th vector in the set V;

[0077] A data segment is randomly selected from each of the k clusters, and then M fault knowledge enhancement subsets are obtained, where the preset generated M fault knowledge enhancement subsets are , then, Fault Knowledge Enhanced Subset It is expressed as:

[0078] ,

[0079] In the formula, Indicates that in clustering A randomly selected data segment from .

[0080] Specifically, the sentence-bert algorithm is used to encode the retrieved data fragments into vectors, and then the retrieval results are clustered based on the K-means clustering algorithm, and each cluster represents a different fault analysis perspective; then, a data fragment is randomly selected from each cluster to generate multiple fault knowledge enhanced subsets; through the multi-perspective sampling strategy, the system efficiently clusters the vectors of multiple data fragments into a set V to reduce redundancy and ensure multi-perspective fault analysis, ensuring the diversity of different fault characteristics; the role of multi-perspective sampling: these data fragments may come from different technical data or different monitoring equipment, sensors or historical fault records, and have a lot of redundancy; in order to avoid information redundancy and improve data diversity, a multi-perspective sampling strategy is introduced.

[0081] Furthermore, the step of training the lightweight language model as a fault handling draft generator, inputting M fault knowledge enhancement subsets into the fault handling draft generator, and then obtaining M fault handling drafts includes:

[0082] Train a lightweight language model as a fault handling draft generator. Given a fault event , the answer A of the fault knowledge enhancement subset S is enhanced to generate the reason (reasoning process) E, that is, As training data T, Q is a given query, , where the reasoning process E extracts key information from the fault knowledge enhancement subset S and briefly explains why the answer is reasonable for the question; the length of the reasoning should be kept short (the number of words should not exceed H, which is set by relevant personnel according to actual conditions), and its meaning should be consistent with the content of the fault knowledge enhancement subset S; ChatGpt (or other large artificial intelligence models) is used based on the thinking prompt chain technology to automatically generate the reasoning E of each triple, that is, As training data T;

[0083] The lightweight pre-trained language model is fine-tuned using the loss function, and the loss function L is:

[0084] ,

[0085] In the formula, In a given query and fault knowledge enhanced subset The fault handling draft generator generates answers under the conditions and reasons The probability of ; by maximizing this probability, the model is trained so that it can more accurately predict answers and reasons;

[0086] Enhance the subset of all fault knowledge The fault handling draft generator is input in parallel. Then, the fault handling draft generated for each fault knowledge enhancement subset and its corresponding reasoning process are as follows:

[0087] ,

[0088] In the formula, The fault handling draft generated for the jth fault knowledge enhanced subset, ,Each fault handling draft represents a potential fault handling solution; represents the reason for generating the jth fault handling plan, , Represents a fault handling draft generator;

[0089] Finally, M fault handling drafts are obtained , The expression is:

[0090] .

[0091] Specifically, the draft generation process is parallelized, which not only improves efficiency but also avoids position deviation in long texts and model input token overflow caused by long texts.

[0092] Furthermore, the step of using the general large language model as the fault handling decision model, scoring the M fault handling drafts, and taking the optimal fault handling draft as the final fault handling decision includes:

[0093] Use a general large language model (such as ChatGPT) as a fault handling decision model and perform M fault handling drafts separately The consistency, reliability and consistency of historical fault records are scored, and then M fault handling drafts are obtained. Consistency score, reliability score and historical failure record consistency score;

[0094] According to the percentiles of the scores of the M fault handling drafts, the minimum qualified score thresholds of the three dimensions of consistency, reliability and historical fault record consistency are determined respectively. The minimum qualified score thresholds of the three dimensions are expressed as , and , the scores of the three dimensions are expressed as , and , the weights corresponding to the scores of the three dimensions are expressed as ;

[0095] The optimal fault handling draft is calculated by the scores of the three dimensions and the minimum qualified score thresholds of the three dimensions. The calculation formula is:

[0096] ,

[0097] In the formula, is the optimal fault handling protocol, represents the consistency score of the jth fault handling protocol, represents the reliability score of the jth fault handling plan, represents the score of the consistency of historical fault records of the jth fault handling draft, The weight corresponding to the consistency score, The weight corresponding to the reliability score, The weight corresponding to the score of the consistency of historical fault records is represented by the optimal fault handling draft when: and and The highest scoring draft fault disposal in the case.

[0098] Furthermore, the scoring expression for the consistency of the j-th fault handling protocol is:

[0099] ,

[0100] In the formula, is a consistency scoring function, which represents a function that calculates the matching degree between the fault handling draft and the current fault scenario. The consistency score is a score for the consistency of the fault handling draft and the reasoning process (reason) under the current fault symptom description corresponding to the current fault scenario.

[0101] The scoring expression of the reliability of the j-th fault handling plan is:

[0102] ,

[0103] In the formula, is a reliability scoring function, where the reliability score is to score the rationality of the draft through the fault handling decision model to ensure that the generated fault handling draft can be effectively executed in the actual fault handling;

[0104] The scoring expression for the consistency of the historical fault records of the j-th fault handling draft is:

[0105] ,

[0106] In the formula, is the scoring function for the consistency of historical fault records, is a similar case of historical fault records, where the consistency of historical fault records is used to measure the consistency between the fault handling draft and the historical fault records. The scoring function of the consistency of historical fault records matches and compares the fault handling draft with the historical fault records, and outputs a consistency score of the historical fault records. In addition, the historical fault records can also increase attention and serve as a separate input variable;

[0107] Specifically, the scoring function is scored by the fault handling decision model. The consistency scoring function includes: evaluating the consistency between the fault handling draft, the reasons for the fault handling draft and the current fault symptoms. The evaluation criteria are whether the reasoning process of the draft matches the current fault symptom description, and giving a consistency score in the range of [0-10];

[0108] The scoring process of the consistent scoring function is as follows: Fault symptom: {input fault symptom description content};

[0109] Fault handling draft: {Enter the content of the fault handling draft};

[0110] Reasons for the draft fault handling: {Enter the content of the reasons for the draft fault handling};

[0111] A consistency score of [0-10] can be obtained.

[0112] The reliability scoring function includes:

[0113] Evaluate the consistency between the fault handling draft, the reasons for the fault handling draft and the current fault symptoms. The evaluation criteria are whether the draft is reasonable and can be effectively implemented in the actual fault handling. A reliability score is given in the range of [0-10];

[0114] The scoring process of the reliability scoring function is as follows: Fault symptom: {input fault symptom description};

[0115] Fault handling draft: {Enter the content of the fault handling draft};

[0116] Reasons for the draft fault handling: {Enter the content of the reason for the draft fault handling};

[0117] A reliability score of [0-10] can be obtained.

[0118] The scoring function for the consistency of historical fault records includes: evaluating the consistency of the fault handling draft, the reasons for the fault handling draft, the current fault symptoms and the historical fault records. The evaluation criteria are to measure the consistency between the fault handling draft and the historical fault records, and give a historical fault record consistency score, with a score range of [0-10];

[0119] The scoring process of the scoring function for consistency of historical fault records is:

[0120] Fault symptom: {Enter the fault symptom description};

[0121] Historical fault records: {enter historical fault record content};

[0122] Fault handling draft: {Enter the content of the fault handling draft};

[0123] Reasons for the draft fault handling: {Enter the content of the reason for the draft fault handling};

[0124] You can get a historical fault record consistency score of [0-10].

[0125] Furthermore, the step of taking the final fault handling decision as the final response strategy and executing it includes:

[0126] The final response strategy is automatically executed or handed over to the operator for execution. During the execution process, the recovery status of the current fault symptom description is monitored in real time and corresponding adjustments are made.

[0127] In this embodiment, the large language model can analyze and compare similar abnormal situations according to the type of fault occurring in the power generation system, forming a closed loop of "fast response-parallel analysis-joint decision-making"; in the early stage of the fault, the large language model can analyze and match the type of fault and the fault elimination measures in parallel, effectively shortening the overall response time for troubleshooting; by using the large language model, useful and readable fault auxiliary decision-making solutions can be generated, greatly reducing the time for fault auxiliary decision-making and the time cost required for manual fault analysis; by allowing the large language model to perform speculative retrieval to enhance the analysis of problems from multiple angles, the risk of traditional single-angle misjudgment can be reduced; by realizing information exchange in the large language model analysis process, it is possible to integrate data to form a more comprehensive A comprehensive and accurate auxiliary decision-making plan; by clustering the retrieved fault data to form multiple fault knowledge enhanced subsets from different perspectives, repeated calculation of redundant data is avoided, and valuable fault information can be obtained from multiple perspectives. Therefore, this multi-perspective sampling technology improves the comprehensiveness and accuracy of the diagnosis results; multiple disposal plan drafts are generated by parallel processing, and verified and scored from three dimensions of consistency, reliability score and consistency of historical fault records through a general large language model; different from the linear reasoning and manual intervention of traditional methods, the parallel draft generation method of the present invention not only improves the response speed of fault disposal, but also ensures that the final response strategy plan has higher accuracy and reliability.

[0128] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0129] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only an example. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0131] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for quickly handling power generation system faults based on speculative retrieval enhanced generation, characterized in that: The following steps are involved: S1. Collect relevant data of the power generation system and build a fault symptom query library based on the relevant data; S2. Obtain a current fault symptom description of the power generation system, and search in a fault symptom query library based on the current fault symptom description, thereby obtaining multiple data fragments related to the current fault symptom description; S3, data encoding multiple data fragments to form a set, and dividing the set into K clusters through a clustering algorithm, thereby obtaining M fault knowledge enhanced subsets; S4. Train a lightweight language model as a fault handling draft generator, input M fault knowledge enhancement subsets into the fault handling draft generator, and then obtain M fault handling drafts; S5. Use the general large language model as the fault handling decision model, score the M fault handling drafts, and use the optimal fault handling draft as the final fault handling decision; S6. The final fault handling decision is taken as the final response strategy and executed.

2. The method for rapid handling of power generation system faults based on speculative retrieval enhanced generation according to claim 1, characterized in that: The step of collecting relevant data of the power generation system and building a fault symptom query library based on the relevant data includes: Collect technical documents, books, historical fault records, maintenance manuals, and fault analysis reports of the power generation system as relevant data of the power generation system; The relevant data are divided into text blocks, encoded into vectors using the BEG model and stored in a vector database, which is used as a fault diagnosis query library.

3. The method for rapid handling of power generation system faults based on speculative retrieval enhanced generation according to claim 2, characterized in that: The step of obtaining the current fault symptom description of the power generation system and searching in a fault symptom query library based on the current fault symptom description to obtain a plurality of data segments related to the current fault symptom description includes: Obtaining a current fault symptom description of the power generation system, and retrieving a text block corresponding to the current fault symptom description in a fault symptom query library; The corresponding text blocks are used as multiple data segments related to the current fault symptom description.

4. The method for rapid handling of power generation system faults based on speculative retrieval enhanced generation according to claim 1, characterized in that: The step of encoding the multiple data fragments to form a set, dividing the set into K clusters by a clustering algorithm, and then obtaining M fault knowledge enhanced subsets includes: Set the collection of multiple data fragments to , based on the sentence-BERT algorithm, multiple data fragments are Mapping to vector , , and then the vectors of multiple data fragments constitute a set ,in, Indicates that the data fragment is converted using the Sentence-BERT algorithm Encoded as semantic vector ; Based on the K-means algorithm, the set V is clustered into k clusters. , the clustering process of set V satisfies the objective function Minimize, its objective function is: ， In the formula, To minimize the objective function, is the jth cluster, yes The cluster center of is the i-th vector in the set V; A data segment is randomly selected from each of the k clusters, and then M fault knowledge enhancement subsets are obtained, where the preset generated M fault knowledge enhancement subsets are , then, Fault Knowledge Enhanced Subset It is expressed as: ， In the formula, Indicates that in clustering A randomly selected data segment from .

5. The method for rapid handling of power generation system faults based on speculative retrieval enhanced generation according to claim 4, characterized in that: The step of training a lightweight language model as a fault handling draft generator, inputting M fault knowledge enhancement subsets into the fault handling draft generator, and then obtaining M fault handling drafts includes: Train a lightweight language model as a fault handling draft generator. Given a fault event , the answer A of the fault knowledge enhancement subset S is enhanced to generate reason E, that is, As training data T, where Q is a given query, ; The lightweight pre-trained language model is fine-tuned using the loss function, and the loss function L is: ， In the formula, In a given query and fault knowledge enhanced subset The fault handling draft generator generates answers under the conditions and reasons The probability of Enhance the subset of all fault knowledge The fault handling draft generator is input in parallel. Then, the fault handling draft generated for each fault knowledge enhancement subset and its corresponding reasoning process are as follows: ， In the formula, The fault handling draft generated for the jth fault knowledge enhanced subset, represents the reason for generating the jth fault handling plan, Represents a fault handling draft generator; Finally, M fault handling drafts are obtained , The expression is: 。 6. The method for rapid handling of power generation system faults based on speculative retrieval enhanced generation according to claim 5, characterized in that: The steps of using the general large language model as the fault handling decision model, scoring M fault handling drafts, and taking the optimal fault handling draft as the final fault handling decision include: The general large language model is used as the fault handling decision model and M fault handling drafts are respectively The consistency, reliability and consistency of historical fault records are scored, and then M fault handling drafts are obtained. Consistency score, reliability score and historical failure record consistency score; According to the percentiles of the scores of the M fault handling drafts, the minimum qualified score thresholds of the three dimensions of consistency, reliability and historical fault record consistency are determined respectively. The minimum qualified score thresholds of the three dimensions are expressed as , and , the scores of the three dimensions are expressed as , and , the weights corresponding to the scores of the three dimensions are expressed as ; The optimal fault handling draft is calculated by the scores of the three dimensions and the minimum qualified score thresholds of the three dimensions. The calculation formula is: ， In the formula, is the optimal fault handling protocol, represents the consistency score of the jth fault handling protocol, represents the reliability score of the jth fault handling plan, represents the score of the consistency of historical fault records of the jth fault handling draft, The weight corresponding to the consistency score, The weight corresponding to the reliability score, The weight corresponding to the score of the consistency of historical fault records is represented by the optimal fault handling draft when: and and The highest scoring draft fault disposal in the case.

7. The method for rapid handling of power generation system faults based on speculative retrieval enhanced generation according to claim 6, characterized in that: The scoring expression for the consistency of the j-th fault handling protocol is: ， In the formula, is the scoring function for consistency; The scoring expression of the reliability of the j-th fault handling plan is: ， In the formula, is the scoring function for reliability; The scoring expression for the consistency of the historical fault records of the j-th fault handling draft is: ， In the formula, is the scoring function for the consistency of historical fault records, Similar cases recorded for historical failures.

8. The method for rapid handling of power generation system faults based on speculative retrieval enhanced generation according to claim 1, characterized in that: The step of taking the final fault handling decision as the final response strategy and executing it includes: The final response strategy is automatically executed or handed over to the operator for execution. During the execution process, the recovery status of the current fault symptom description is monitored in real time and corresponding adjustments are made.

Images