Fault detection method and system based on large model

Abstract

The invention discloses a fault detection method and system based on a large model, and belongs to the technical field of fault detection, and the method specifically comprises the steps: collecting multi-source fault data from an industrial system, carrying out the preprocessing, and extracting fault features to form a data set; loading a pre-trained large language model, and performing fine tuning according to the fault feature data set; constructing a fault detection model by using the fine-tuned model and the fault feature data set, and performing training and evaluation in combination with an adaptive optimization strategy to obtain a trained model; fault data collected in real time are input into the model, a preliminary fault detection result is output, fault types, positions and probability information are further obtained through a multi-level fault analysis method, meanwhile, the result is fed back to optimize the model, and the accuracy and efficiency of fault detection are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault detection, and in particular to a fault detection method and system based on a large model. Background Art

[0002] Fault detection methods collect and analyze various data during the operation of the system, and use specific algorithms or models to determine whether the system has abnormalities or faults. The purpose is to discover and locate the fault in a timely manner so that appropriate measures can be taken to repair it, thereby avoiding or reducing the impact and loss caused by the fault to the system. Traditional fault detection methods, such as rule-based methods, statistical methods, and machine learning-based methods, can meet the fault detection needs in specific fields to a certain extent, but often have problems such as insufficient generalization ability, high model complexity, and limited ability to process large-scale data.

[0003] For example, the Chinese patent application with publication number CN118069400A discloses a fault detection method, system and electronic device, including: obtaining target data corresponding to a target device, the target device is a device to be detected for fault, the target data includes multiple sub-data, each sub-data is data for fault identification in different data sources corresponding to the target device; inputting the target data into a fault analysis model, so that the fault analysis model obtains a target fault detection result according to the target data, the target fault detection result includes the fault type and fault cause of the target device, and the fault analysis model is a model trained based on historical fault data. The method of using a large model effectively reduces the manpower input of fault detection, and the target data corresponding to the target device including multiple sub-data for fault identification is analyzed through the fault analysis model, which improves the accuracy and comprehensiveness of the fault detection result compared with the method of identifying faults only from a single data bus or diagnostic data.

[0004] For example, the Chinese patent with the authorization announcement number CN115629930B discloses a fault detection method, device, equipment and storage medium based on a DSP system, including: obtaining a fault signal; inputting the fault signal into a preset fault detection model, classifying and processing the fault signal based on the fault detection model, and performing fault information diagnosis processing on the classified fault signal to obtain fault information; wherein the fault detection model is obtained after iterative training of the training model based on the fault signal sample, the category weight information of the fault signal sample and the fault information label of the fault signal sample. This technical solution is based on the pre-trained fault detection model, classifies the fault signals and diagnoses the fault information in the signal processing system of the DSP processor, and outputs the fault information quickly and accurately, without the need for developers or users to manually debug the location of a large number of problems, thereby improving the efficiency of DSP system fault detection.

[0005] The above existing technologies all have the following problems: in CN118069400A, although it is mentioned that the target data is input into the fault analysis model to obtain the fault detection result, the real-time requirement and feedback mechanism are not mentioned; only the fault type and fault cause are mentioned, but the fault location and fault probability information are not mentioned; in CN115629930B, the focus is mainly on the fault signals inside the DSP system, and classification and diagnosis are performed based on these signals; the detail and accuracy of the fault detection results are limited; although it is mentioned that the fault information is output quickly and accurately, the real-time requirement and feedback mechanism may not be discussed in detail. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes a fault detection method and system based on a large model, which collects multi-source fault data from an industrial system and performs preprocessing, extracts fault features to form a data set; loads a pre-trained large language model and performs fine-tuning according to the fault feature data set; constructs a fault detection model using the fine-tuned model and the fault feature data set, and performs training and evaluation in combination with an adaptive optimization strategy to obtain a trained model; inputs the fault data collected in real time into the model, outputs preliminary fault detection results, and further obtains fault type, location and probability information through a multi-level fault analysis method, and feeds back the results to optimize the model. The present invention improves the accuracy and efficiency of fault detection.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] Fault detection methods based on large models include:

[0009] Step S1: Collect multi-source fault data from the industrial system and perform preprocessing. At the same time, extract fault features from the preprocessed multi-source fault data to obtain a fault feature data set;

[0010] Step S2: Load the pre-trained large language model and fine-tune it according to the fault feature dataset;

[0011] Step S3: construct a fault detection model using the fine-tuned large language model and the fault feature data set, train and evaluate the fault detection model in combination with the adaptive optimization strategy, and optimize the fault detection model according to the evaluation results to obtain a trained fault detection model;

[0012] Step S4: Input the real-time collected fault data into the trained fault detection model. The fault detection model outputs preliminary fault detection results based on the input data. Combined with the multi-level fault analysis method, the preliminary fault detection results are analyzed at a multi-level to obtain the fault type, fault location and fault probability information. The real-time fault detection results and the results of the multi-level analysis are fed back to the fault detection model for optimization.

[0013] Specifically, the specific formula of the adaptive optimization strategy in step S3 is:

[0014] ;

[0015] Among them, t represents the current time, and They represent the first-order moment estimation and second-order moment estimation of the fault detection model at time t, respectively. represents the fault detection model parameters at time t+1, represents the fault detection model parameters at time t, represents the step size of the control parameter update, and represents the exponential decay rate of the moment estimate at time t, and b represents a constant.

[0016] Specifically, the specific steps of step S4 include:

[0017] S4.1: Obtain real-time fault data and perform preprocessing to obtain preprocessed real-time fault data ,in, represents the Mth preprocessed real-time fault data, and M represents the number of preprocessed real-time fault data;

[0018] S4.2: The trained fault detection model is input, and the fault detection model outputs preliminary fault detection results based on the input data;

[0019] S4.3: Combine multi-level fault analysis methods to conduct in-depth analysis of preliminary fault detection results, and use knowledge graphs and expert systems to combine feature information in real-time fault data and historical fault cases to determine fault type, fault location, and fault probability information;

[0020] S4.4: Feed back the real-time fault detection results and multi-level analysis results to the fault detection model, and use the reinforcement learning algorithm to perform online updates based on the feedback results.

[0021] Specifically, the specific steps of S4.3 include:

[0022] S4.31: Acquisition and preliminary fault detection results;

[0023] S4.32: Extract fault knowledge from historical fault cases, expert experience, and equipment manuals, and use the knowledge graph method to represent the extracted fault knowledge as a graphical knowledge structure, where the fault type, fault location, and fault probability information are represented as nodes, and the relationship between them is represented as edges;

[0024] S4.33: Input the preliminary fault detection results into the preloaded expert system. The expert system matches and infers the fault detection results according to the fault knowledge in the knowledge graph to obtain the fault type, fault location and fault probability information;

[0025] S4.34: Based on the reasoning results of the expert system, combined with , determine the specific type and location of the fault;

[0026] S4.35: Use machine learning algorithms to analyze historical failure cases to obtain the probability distribution of failures, and evaluate the probability of failures based on the current operating status of the equipment, the specific type and location of the failure.

[0027] Specifically, the specific steps of S4.4 include:

[0028] S4.41: Integrate the real-time fault detection results and multi-level analysis results to generate a fault detection report;

[0029] S4.42: Load the pre-built reinforcement learning model, use the fault detection report as the feedback result, input it into the reinforcement learning model, design the reward function and state transition rules, use the reinforcement learning strategy to train the reinforcement learning model, so that the reinforcement learning model can learn and adapt to the new fault mode, and obtain the trained reinforcement learning model. The formula is:

[0030] ;

[0031] in, represents the quality function under state z, action d, fault feature f and context information g at time t+1, represents the quality function under state z, action d, fault feature f and context information g at time t, represents the learning rate, represents the reward obtained immediately after taking action d, represents the discount factor, represents the maximum value of the quality function under the next state, action, fault characteristics and context information at time t, , , , Respectively represent the next state, action, fault characteristics and context information, represents the feature weight, represents the characteristic function, represents the constraint weight, represents the constraint function;

[0032] S4.43: According to the training results of the reinforcement learning model, adjust the parameters of the fault detection model, and evaluate the accuracy of the adjusted fault detection model. At the same time, according to the evaluation results, further optimize and adjust the fault detection model;

[0033] If the evaluation result is not satisfactory, return to step S4.42, retrain the reinforcement learning model, and update the fault detection model again;

[0034] If the evaluation result meets the requirements, the result is output and the process ends.

[0035] The fault detection system based on the large model includes: data processing module, model fine-tuning module, fault detection module, and fault analysis module;

[0036] The data processing module is used to collect multi-source fault data from the industrial system and perform preprocessing and feature extraction;

[0037] The model fine-tuning module is used to fine-tune the pre-trained large language model using the fault feature dataset;

[0038] The fault detection module is used to construct a fault detection model using the fine-tuned large language model and the fault feature data set, and to perform training and evaluation, and optimize the model according to the evaluation results;

[0039] The fault analysis module is used to input the real-time collected fault data into the trained fault detection model, output the preliminary fault detection results, and perform multi-level analysis in combination with the multi-level fault analysis method.

[0040] Specifically, the fault analysis module includes: a real-time detection unit, a multi-level analysis unit, and a feedback optimization unit;

[0041] The real-time detection unit is used to input the real-time collected fault data into the trained fault detection model and output preliminary fault detection results;

[0042] The multi-level analysis unit is used to perform multi-level analysis on the preliminary fault detection results;

[0043] The feedback optimization unit is used to feed back the real-time detection results and the results of the multi-level analysis to the fault detection model for optimization.

[0044] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a fault detection method based on a large model when executing the computer program.

[0045] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a fault detection method based on a large model.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. The present invention proposes a fault detection system based on a large model, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0048] 2. The present invention proposes a fault detection method based on a large model. By collecting multi-source fault data from the industrial system and performing preprocessing and feature extraction, and fine-tuning it in combination with a pre-trained large language model, a fault detection model is constructed and optimized. This process not only improves the accuracy and efficiency of fault detection, but also enables the model to better adapt to the actual situation of the industrial system, reducing the probability of false alarms and missed alarms.

[0049] 3. The present invention proposes a fault detection method based on a large model, which inputs the real-time collected fault data into a trained fault detection model, and can quickly output preliminary fault detection results; the results are further analyzed by a multi-level fault analysis method to obtain detailed fault type, location and probability information, which provides strong support for the rapid location and repair of faults; at the same time, the real-time detection results and analysis results are fed back to the model for optimization, which can continuously improve the detection capability and accuracy of the model and improve the stability of the industrial system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of a fault detection method based on a large model of the present invention;

[0051] Figure 2 This is a principle flow chart of the fault detection method based on a large model of the present invention;

[0052] Figure 3 A flowchart for realizing real-time fault detection results in the fault detection method based on a large model of the present invention;

[0053] Figure 4 This is an architecture diagram of the fault detection system based on a large model of the present invention. DETAILED DESCRIPTION

[0054] Example 1

[0055] See also Figure 1-Figure 3, an embodiment of the present invention provides: a fault detection method based on a large model, comprising the following steps:

[0056] Step S1: Collect multi-source fault data from the industrial system and perform preprocessing. At the same time, extract fault features from the preprocessed multi-source fault data to obtain a fault feature data set;

[0057] Furthermore, the specific steps of step S1 include:

[0058] S1.1: Determine the types of fault data that need to be collected, such as vibration signals, temperature signals, and pressure signals, and install sensors at key locations of the industrial system to collect fault data in real time. At the same time, ensure the accuracy and reliability of the sensors, as well as the real-time and continuity of data collection;

[0059] S1.2: Clean the collected raw data to remove noise, outliers and duplicate data, and format the data to convert it into a data format suitable for data mining algorithm processing;

[0060] S1.3: Use a decision tree classification algorithm to mine the preprocessed multi-source fault data to extract feature information related to the fault, such as fault frequency, fault amplitude, and fault type. The decision tree classification algorithm is a prior art in this field and is not an inventive solution of the present application, and will not be described in detail here.

[0061] S1.4: Integrate the extracted fault feature information into a fault feature data set for subsequent fault detection and diagnosis.

[0062] Step S2: Load the pre-trained large language model and fine-tune it according to the fault feature dataset;

[0063] Furthermore, the specific steps of step S2 include:

[0064] S2.1: Select a pre-trained model: Select a model suitable for the current task from the existing pre-trained large language models. These models have usually been trained on large-scale text data and have certain language understanding and generation capabilities. In the present invention, the ERNIE large model is selected, where the ERNIE large model is a pre-trained model developed by Baidu, which enhances the representation ability of the model by introducing entity and semantic information.

[0065] S2.2: Loading a pre-trained large language model: Loading the selected pre-trained large language model into a memory or computing device for subsequent fine-tuning tasks;

[0066] S2.3: Prepare fault feature dataset;

[0067] S2.4: Model fine-tuning: Use the fault feature dataset to fine-tune the pre-trained large language model to make it better suited to the current fault detection task. During the fine-tuning process, the parameters of the large language model, learning rate and other hyperparameters can be adjusted to optimize the performance of the large language model in the fault detection task. The large language model parameter optimization formula is:

[0068] ;

[0069] in, represents the loss function, Represents a large language model given input features and parameters Next prediction label The probability of represents the label of the i-th fault feature data, i.e., the fault type or category, represents the i-th fault feature data, represents the large language model parameters, and N represents the number of samples in the fault feature dataset.

[0070] It should be noted that the goal of the fine-tuning process is to adjust the parameters To minimize the loss function , thereby improving the accuracy of large language models on fault detection tasks.

[0071] Step S3: construct a fault detection model using the fine-tuned large language model and the fault feature data set, train and evaluate the fault detection model in combination with the adaptive optimization strategy, and optimize the fault detection model according to the evaluation results to obtain a trained fault detection model;

[0072] Furthermore, the specific steps of step S3 include:

[0073] S3.1: Build a fault detection model framework and integrate adaptive optimization strategies;

[0074] S3.2: Divide the fault feature dataset into a training set and a test set in a ratio of 7:3, use the training set in the fault feature dataset to train the fault detection model, calculate the loss through forward propagation, and update the fault detection model parameters through back propagation;

[0075] S3.3: Based on the evaluation results on the validation set, such as accuracy, determine whether the performance of the fault detection model meets the requirements. If the performance of the fault detection model is poor, optimize the fault detection model, including adjusting the model architecture, adding training data, adjusting optimization algorithm parameters, and repeating the training, evaluation and optimization process until the performance of the fault detection model reaches the preset level;

[0076] S3.4: When the fault detection model shows good performance on the validation set, the fault detection model is considered to have been trained, and the parameters and structure of the fault detection model are saved for subsequent deployment and use in the actual environment.

[0077] Step S4: Input the real-time collected fault data into the trained fault detection model. The fault detection model outputs preliminary fault detection results based on the input data. Combined with the multi-level fault analysis method, the preliminary fault detection results are analyzed at a multi-level to obtain the fault type, fault location and fault probability information. The real-time fault detection results and the results of the multi-level analysis are fed back to the fault detection model for optimization.

[0078] The specific formula of the adaptive optimization strategy in S3 is:

[0079] ;

[0080] Among them, t represents the current time, and They represent the first-order moment estimation and second-order moment estimation of the fault detection model at time t, respectively. represents the fault detection model parameters at time t+1, represents the fault detection model parameters at time t, represents the step size of the control parameter update, and represents the exponential decay rate of the moment estimate at time t, and b represents a constant.

[0081] The specific steps of S4 include:

[0082] S4.1: Obtain real-time fault data and perform preprocessing to obtain preprocessed real-time fault data ,in, represents the Mth preprocessed real-time fault data, and M represents the number of preprocessed real-time fault data;

[0083] S4.2: The trained fault detection model is input, and the fault detection model outputs preliminary fault detection results based on the input data;

[0084] Furthermore, the specific steps of S4.2 include:

[0085] S4.21: Acquisition , and load the trained fault detection model to ensure that the model file is complete and not damaged, and the model parameters have been optimized to the best state;

[0086] S4.22: Use normalization to Perform format conversion into the input format of the fault detection model and convert the converted Input into the fault detection model;

[0087] The specific process of data conversion includes:

[0088] (1) Standardize or normalize continuous numerical features so that all fault feature data are on the same scale and eliminate the dimension effect;

[0089] (2) Fill missing values ​​using mean, median or mode;

[0090] (3) Complete data type conversion. For example, convert the integer type to the floating-point type.

[0091] S4.23: Fault detection model transforms the input Perform calculations, extract features and apply learned rules to identify potential failures;

[0092] S4.24: Output preliminary fault detection results. The fault detection results are usually presented in numerical, label or text form, depending on the design and requirements of the system.

[0093] S4.3: Combine multi-level fault analysis methods to conduct in-depth analysis of preliminary fault detection results, and use knowledge graphs and expert systems to combine feature information in real-time fault data and historical fault cases to determine fault type, fault location, and fault probability information;

[0094] S4.4: Feed back the real-time fault detection results and multi-level analysis results to the fault detection model, and use the reinforcement learning algorithm to perform online updates based on the feedback results.

[0095] The specific steps of S4.3 include:

[0096] S4.31: Acquisition and preliminary fault detection results;

[0097] S4.32: Extract fault knowledge from historical fault cases, expert experience, and equipment manuals, and use the knowledge graph method to represent the extracted fault knowledge as a graphical knowledge structure, where the fault type, fault location, and fault probability information are represented as nodes, and the relationship between them is represented as an edge. At the same time, the knowledge graph method is the prior art content in this field and is not an inventive solution of the present application, and will not be described in detail here;

[0098] S4.33: Input the preliminary fault detection results into the preloaded expert system. The expert system matches and infers the fault detection results according to the fault knowledge in the knowledge graph to obtain the fault type, fault location and fault probability information;

[0099] Furthermore, the specific steps of S4.33 include:

[0100] (1) Obtain preliminary fault detection results, which are usually manifested as a series of fault signals, and preprocess the collected fault signals, including filtering, denoising, normalization and other operations, to improve the accuracy and reliability of the signals;

[0101] (2) Input the preprocessed fault signal into the preloaded expert system. The expert system is a computer program based on artificial intelligence technology, which contains a large amount of fault knowledge and reasoning rules;

[0102] (3) The expert system uses the fault knowledge in the knowledge graph to match the input fault signal. The knowledge graph is a graph structure containing a large number of entities, relationships, and attributes. The entities can be equipment, components, or fault types, etc., the relationships can be connection relationships, causal relationships, etc., and the attributes can be equipment models and parameters.

[0103] (4) Based on the matching results, the expert system uses a built-in reasoning mechanism to perform fault reasoning. The reasoning process adopts a case-based reasoning method. The case-based reasoning method is a prior art in this field and is not an inventive solution of the present application, so it will not be described in detail here.

[0104] (5) After reasoning and analysis, the expert system outputs fault type, fault location, and fault probability information, which can help users quickly locate and resolve faults.

[0105] S4.34: Based on the reasoning results of the expert system, combined with , determine the specific type and location of the fault;

[0106] S4.35: Use machine learning algorithms to analyze historical failure cases to obtain the probability distribution of failures, and evaluate the probability of failures based on the current operating status of the equipment, the specific type and location of the failure.

[0107] Furthermore, the specific steps of S4.35 include:

[0108] (1) Obtain and historical fault case data, and preprocess them to generate raw data;

[0109] (2) Use statistical analysis methods to extract features from the original data and obtain fault characteristics;

[0110] (3) Loading a pre-built decision tree-based machine learning model, and using the obtained fault features to train and evaluate the decision tree-based machine learning model, wherein the training and evaluation of the machine learning model is the prior art content in this field, and is not the inventive solution of the present application, and is not described in detail here;

[0111] (4) The real-time fault data is input into the trained decision tree-based machine learning model. The decision tree-based machine learning model will output the probability distribution of the fault occurrence. Based on the probability distribution, the possibility of failure of the current equipment can be evaluated.

[0112] The specific steps of S4.4 include:

[0113] S4.41: Integrate the real-time fault detection results and multi-level analysis results to generate a fault detection report;

[0114] S4.42: Load the pre-built reinforcement learning model, use the fault detection report as the feedback result, input it into the reinforcement learning model, design the reward function and state transition rules, use the reinforcement learning strategy to train the reinforcement learning model, so that the reinforcement learning model can learn and adapt to the new fault mode, and obtain the trained reinforcement learning model. The formula is:

[0115] ;

[0116] in, represents the quality function under state z, action d, fault feature f and context information g at time t+1, represents the quality function under state z, action d, fault feature f and context information g at time t, represents the learning rate, represents the reward obtained immediately after taking action d, represents the discount factor, represents the maximum value of the quality function under the next state, action, fault characteristics and context information at time t, , , , Respectively represent the next state, action, fault characteristics and context information, represents the feature weight, represents the characteristic function, which is used to indicate the importance of fault characteristics. represents the constraint weight, Represents constraint functions, which are used to express resource restrictions and security requirements;

[0117] In the present invention, the characteristic function is introduced , used to emphasize the importance of certain specific features. For example, in fault detection, some fault features may be more important than other features, which can be achieved by To reflect this, the feature weights Control the influence of the characteristic function. And introduce the constraint function , used to ensure that certain constraints are met when taking actions. For example, in an industrial environment, some actions may be constrained by resource limitations or safety requirements, which can be achieved by To represent these constraints, the constraint weights Controls the influence of the constraint function.

[0118] S4.43: According to the training results of the reinforcement learning model, adjust the parameters of the fault detection model, and evaluate the accuracy of the adjusted fault detection model. At the same time, according to the evaluation results, further optimize and adjust the fault detection model. The accuracy evaluation is the prior art content in this field, and is not the inventive solution of the present application, and is not elaborated here.

[0119] If the evaluation result is not satisfactory, return to step S4.42, retrain the reinforcement learning model, and update the fault detection model again;

[0120] If the evaluation result meets the requirements, the result is output and the process ends.

[0121] Example 2

[0122] See also Figure 4 Another embodiment provided by the present invention is a fault detection system based on a large model, comprising:

[0123] Data processing module, model fine-tuning module, fault detection module, fault analysis module;

[0124] The data processing module is used to collect multi-source fault data from industrial systems and perform preprocessing and feature extraction, including collecting fault data from various sensors and log file sources. The preprocessing includes cleaning, formatting, and normalization to improve data quality;

[0125] The model fine-tuning module is used to fine-tune the pre-trained large language model using the fault feature dataset to make it more suitable for fault detection tasks;

[0126] The fault detection module is used to build a fault detection model using the fine-tuned large language model and fault feature dataset, and to train and evaluate the model, and optimize the model based on the evaluation results;

[0127] The fault analysis module is used to input the real-time collected fault data into the trained fault detection model, output the preliminary fault detection results, and perform multi-level analysis in combination with the multi-level fault analysis method.

[0128] The fault detection module includes: a model building unit, an evaluation unit, and a model optimization unit;

[0129] A model building unit, used to build a fault detection model by combining the fine-tuned large language model and the fault feature data set to form a preliminary model capable of detecting faults;

[0130] The training and evaluation unit is used to train the fault detection model and evaluate its performance, such as accuracy and recall, to understand the performance of the fault detection model on the fault detection task;

[0131] The model optimization unit is used to optimize the fault detection model according to the evaluation results, such as adjusting the model structure and parameters to improve the detection performance and generalization ability of the fault detection model.

[0132] The fault analysis module includes: real-time detection unit, multi-level analysis unit, feedback optimization unit;

[0133] The real-time detection unit is used to input the real-time collected fault data into the trained fault detection model, output the preliminary fault detection results, and realize the real-time detection of faults;

[0134] Multi-level analysis unit, used to perform multi-level analysis on the preliminary fault detection results, such as analysis based on fault type, fault location and fault probability, to provide more detailed and accurate fault information, which is helpful for rapid fault location and resolution;

[0135] The feedback optimization unit is used to feed back the real-time detection results and the results of multi-level analysis to the fault detection model for optimization, so as to realize continuous learning and optimization of the model and improve the adaptability and accuracy of the model.

[0136] Example 3

[0137] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a fault detection method based on a large model are implemented. For details, please refer to the above method embodiment, which will not be repeated here.

[0138] A computer-readable storage medium stores computer instructions, which execute the steps of a large model-based fault detection method when the computer instructions are executed, wherein the storage medium may be a volatile or non-volatile computer-readable storage medium.

[0139] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

Claims

1. A fault detection method based on a large model, characterized in that: include: Step S1: Collect multi-source fault data from the industrial system and perform preprocessing. At the same time, extract fault features from the preprocessed multi-source fault data to obtain a fault feature data set; Step S2: Load the pre-trained large language model and fine-tune it according to the fault feature dataset; Step S3: construct a fault detection model using the fine-tuned large language model and the fault feature data set, train and evaluate the fault detection model in combination with the adaptive optimization strategy, and optimize the fault detection model according to the evaluation results to obtain a trained fault detection model; Step S4: Input the real-time collected fault data into the trained fault detection model. The fault detection model outputs preliminary fault detection results based on the input data. Combined with the multi-level fault analysis method, the preliminary fault detection results are analyzed at a multi-level to obtain the fault type, fault location and fault probability information. The real-time fault detection results and the results of the multi-level analysis are fed back to the fault detection model for optimization.

2. The large model-based fault detection method according to claim 1, characterized in that: The specific formula of the adaptive optimization strategy in step S3 is: ； Among them, t represents the current time, and They represent the first-order moment estimation and second-order moment estimation of the fault detection model at time t, respectively. represents the fault detection model parameters at time t+1, represents the fault detection model parameters at time t, represents the step size of the control parameter update, and represents the exponential decay rate of the moment estimate at time t, and b represents a constant.

3. The large model-based fault detection method according to claim 2, characterized in that: The specific steps of step S4 include: S4.1: Obtain real-time fault data and perform preprocessing to obtain preprocessed real-time fault data ,in, represents the Mth preprocessed real-time fault data, and M represents the number of preprocessed real-time fault data; S4.2: The trained fault detection model is input, and the fault detection model outputs preliminary fault detection results based on the input data; S4.3: Combine multi-level fault analysis methods to conduct in-depth analysis of preliminary fault detection results, and use knowledge graphs and expert systems to combine feature information in real-time fault data and historical fault cases to determine fault type, fault location, and fault probability information; S4.4: Feed back the real-time fault detection results and multi-level analysis results to the fault detection model, and use the reinforcement learning algorithm to perform online updates based on the feedback results.

4. The large model-based fault detection method according to claim 3, characterized in that: The specific steps of S4.3 include: S4.31: Acquisition and preliminary fault detection results; S4.32: Extract fault knowledge from historical fault cases, expert experience, and equipment manuals, and use the knowledge graph method to represent the extracted fault knowledge as a graphical knowledge structure, where the fault type, fault location, and fault probability information are represented as nodes, and the relationship between them is represented as edges; S4.33: Input the preliminary fault detection results into the preloaded expert system. The expert system matches and infers the fault detection results according to the fault knowledge in the knowledge graph to obtain the fault type, fault location and fault probability information; S4.34: Based on the reasoning results of the expert system, combined with , determine the specific type and location of the fault; S4.35: Use machine learning algorithms to analyze historical failure cases to obtain the probability distribution of failures, and evaluate the probability of failures based on the current operating status of the equipment, the specific type and location of the failure.

5. The large model-based fault detection method according to claim 4, characterized in that: The specific steps of S4.4 include: S4.41: Integrate the real-time fault detection results and multi-level analysis results to generate a fault detection report; S4.42: Load the pre-built reinforcement learning model, use the fault detection report as the feedback result, input it into the reinforcement learning model, design the reward function and state transition rules, use the reinforcement learning strategy to train the reinforcement learning model, so that the reinforcement learning model can learn and adapt to the new fault mode, and obtain the trained reinforcement learning model. The formula is: ； in, represents the quality function under state z, action d, fault feature f and context information g at time t+1, represents the quality function under state z, action d, fault feature f and context information g at time t, represents the learning rate, represents the reward obtained immediately after taking action d, represents the discount factor, represents the maximum value of the quality function under the next state, action, fault characteristics and context information at time t, , , , Respectively represent the next state, action, fault characteristics and context information, represents the feature weight, represents the characteristic function, represents the constraint weight, represents the constraint function; S4.43: According to the training results of the reinforcement learning model, adjust the parameters of the fault detection model, and evaluate the accuracy of the adjusted fault detection model. At the same time, according to the evaluation results, further optimize and adjust the fault detection model; If the evaluation result is not satisfactory, return to step S4.42, retrain the reinforcement learning model, and update the fault detection model again; If the evaluation result meets the requirements, the result is output and the process ends.

6. A large model-based fault detection system, which is used to implement the large model-based fault detection method according to any one of claims 1 to 5, characterized in that: include: Data processing module, model fine-tuning module, fault detection module, fault analysis module; The data processing module is used to collect multi-source fault data from the industrial system and perform preprocessing and feature extraction; The model fine-tuning module is used to fine-tune the pre-trained large language model using the fault feature dataset; The fault detection module is used to construct a fault detection model using the fine-tuned large language model and the fault feature data set, and to perform training and evaluation, and optimize the model according to the evaluation results; The fault analysis module is used to input the real-time collected fault data into the trained fault detection model, output the preliminary fault detection results, and perform multi-level analysis in combination with the multi-level fault analysis method.

7. The large model-based fault detection system according to claim 6, characterized in that: The fault analysis module includes: a real-time detection unit, a multi-level analysis unit, and a feedback optimization unit; The real-time detection unit is used to input the real-time collected fault data into the trained fault detection model and output preliminary fault detection results; The multi-level analysis unit is used to perform multi-level analysis on the preliminary fault detection results; The feedback optimization unit is used to feed back the real-time detection results and the results of the multi-level analysis to the fault detection model for optimization.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the large model-based fault detection method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of the large model-based fault detection method described in any one of claims 1 to 5 are executed.

Images