269 results about "Failure diagnosis" patented technology

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a fault diagnosis and recovery verification method and device, equipment and a medium. Inputting the candidate event and the context state into an intelligent diagnosis model to obtain a diagnosis result and a fault type, selecting a recovery path in a recovery strategy library based on the diagnosis result, generating a recovery execution instruction, creating a verification experiment based on the instruction, and injecting drill data to obtain verification data, and forming a verification conclusion according to the verification data, associating a recovery execution instruction, and issuing the instruction in the execution environment to complete recovery operation. According to the method, through multi-source monitoring data processing, intelligent diagnosis model reasoning, strategy library path selection, verification experiment verification and execution environment automatic recovery, a full-link automatic process from detection, diagnosis, recovery to verification is constructed, and accurate diagnosis and dynamic recovery in a complex environment are achieved.

The invention discloses a transformer multi-dimensional state sensing and diagnosing system, which comprises a multi-dimensional state sensing module for acquiring transformer multi-dimensional data in real time through various sensors; the data acquisition and processing module performs processing such as synchronous sampling and filtering on the data and extracts features; the state evaluation and fault diagnosis module evaluates a state and diagnoses a fault by using a three-dimensional evaluation model and a CNN-LSTM fusion model; the self-adaptive early warning module dynamically adjusts a threshold value according to an evaluation result and sends out multi-level early warning; the communication and interaction module realizes data encryption transmission, has a visual interface, and supports interaction diagnosis and remote configuration updating. The system can comprehensively collect data, accurately diagnose faults and efficiently early warn, is convenient to operate and maintain, and improves the operation reliability and the operation and maintenance efficiency of the transformer.

The invention relates to an LLM-based power distribution network knowledge graph construction and fault intelligent diagnosis method. The method comprises the steps of constructing a knowledge system, constructing a normal operation state model and an anomaly detection threshold value, performing fault diagnosis through an LSTM-BP cascade network, and performing fault classification. The abnormal parameters and the fault classification result are input into an LLM model, the fault type is judged, corresponding diagnosis information is obtained, and the system generates a scheduling instruction and an emergency decision suggestion according to the diagnosis information; and generating a detailed diagnosis report. According to the system, statistical analysis and deep learning algorithms are adopted for operation parameters such as voltage and current after preprocessing, and automatic detection and fault classification of abnormal parameters are realized in combination with a CNN recognition module; a preset rule base in the knowledge system is combined to accurately determine a fault type, generate a scheduling instruction and an emergency decision suggestion, and assist operation and maintenance personnel in rapid response and dynamic management; finally, a detailed diagnosis report is generated, thereby improving the fault handling efficiency and the guarantee capability of safe and stable operation of a power grid.

The invention relates to the technical field of equipment fault intelligent diagnosis, in particular to an equipment fault intelligent diagnosis method and system based on a Modbus protocol. The method comprises the following steps: acquiring real-time operation data from target industrial equipment through a Modbus protocol, dynamically adjusting an initial sampling frequency based on an equipment operation state, and performing multiple verification and compensation correction on the acquired data to obtain a stable data stream; performing multi-scale decomposition and feature enhancement processing on the stable data stream, extracting a time-frequency domain mixed feature set, and constructing a feature evolution trajectory; inputting the feature evolution trajectory into a double-branch diagnosis model integrating equipment state prediction and fault classification, and outputting an equipment health degree score and fault type probability distribution; and constructing a dynamic fault threshold curved surface, carrying out multi-dimensional fusion decision by combining the equipment health degree score and the fault type probability distribution, and generating a graded fault early warning and maintenance strategy. According to the invention, the accuracy, timeliness and adaptability of industrial equipment fault diagnosis can be greatly improved.

The invention relates to the technical field of fault diagnosis, in particular to an electromechanical equipment fault diagnosis method and system based on data analysis. The method comprises the following steps: extracting a historical operation log of a motor, analyzing a current overload state and constructing a current overload spectrogram; then, carrying out insulation layer performance loss gradient analysis based on the spectrogram, and calculating the failure probability of the motor; finally, a risk level is given to the overload current according to the failure probability, an equipment fault diagnosis framework is constructed, and the framework is sent to a control terminal to execute fault diagnosis. According to the invention, the electromechanical equipment fault diagnosis technology is optimized, so that the electromechanical equipment fault diagnosis technology is more accurate.

The invention provides a fault diagnosis method and system for a spindle box of a high-speed gear milling machine based on fault mechanism simulation and data fusion. The method mainly comprises the following steps: S1, calculating a tooth profile wear curve of a gear based on an Archard wear principle; s2, three-dimensional modeling software is used for building system models in different wear states, and simulation data sets under different wear degrees are obtained with the help of dynamics simulation software; s3, establishing a data acquisition system to obtain an experimental vibration data set under the actual working condition of the spindle box; s4, constructing a spindle box fault diagnosis model by using the analogue simulation data set obtained in the step S2; and S5, performing fault diagnosis on the experimental vibration data set obtained in the step S3 by using the spindle box fault diagnosis model constructed in the step S4, and identifying the health condition of the spindle box system. Important data support is provided for a main axle box fault diagnosis and health management system, and the diagnosis accuracy and reliability are improved.

The invention discloses a cable state monitoring and fault diagnosis device and method, equipment and a medium, and the device comprises a data collection module and an intelligent diagnosis unit, and the data collection module collects multi-source data used for diagnosing the state of a cable; the method comprises the following steps: converting multi-source data into a space-time matrix through an intelligent diagnosis unit, carrying out feature extraction, outputting a fault type and a corresponding prediction probability of a cable by adopting a preset multi-label classification and dynamic threshold decision-making mechanism according to the extracted features, and sending out early warning signals of different grades according to the prediction probability. The diagnosis device solves the problems that in the prior art, multi-dimensional data are not fully fused, so that the diagnosis result is not comprehensive and accurate enough; and new fault features caused by cable aging or operation environment change cannot be self-adapted, the model generalization ability is limited, and the model adaptability is poor.

The invention relates to the field of intelligent diagnosis of oil and gas field development, in particular to a fracturing wellhead device failure analysis method and system based on a large model and a knowledge graph. The system is helpful for solving the problem that the accuracy and timeliness of failure analysis and fault diagnosis of the fracturing wellhead device in the prior art are limited. The method comprises the steps of building a knowledge graph, setting a knowledge graph dynamic updating mechanism oriented to the fault evolution process, building an open source large model and introducing a closed loop feedback mechanism. According to the method, the large model, the knowledge graph and the RAG technology are applied to fracturing wellhead failure analysis, and the intelligent level of the oil and gas industry is remarkably improved; the problem that a large model is high in generalization but insufficient in specialty is optimized, and the accuracy of answer generation is improved.

The invention discloses a cascade fault diagnosis method based on a root cause intensity power set belief rule base. According to the technical scheme, the method comprises the steps of 1, constructing a power set belief rule base; the conclusion hypothesis unit can clearly describe a single-point fault state, a composite fault state and a causal chain fault state. And 2, introducing a root cause strength parameter: introducing the root cause strength parameter into the conclusion hypothesis unit constructed in the step 1 for quantifying the causal influence capability of the fault state as the root cause. And step 3, reasoning fusion: calculating the matching degree and the activation degree of each rule, and applying an evidence theory-based reasoning fusion algorithm to an output result to obtain power set confidence distribution of each fault hypothesis. And step 4, fault diagnosis and fault root cause positioning are carried out, and a main fault root cause is output, and the main fault root cause is the root cause with the maximum root cause strength. The method is mainly used for realizing accurate diagnosis of cascade faults in a complex system by popularizing a traditional BRB model to power set reasoning and introducing a root cause strength concept.

The invention discloses a punching machine bearing fault diagnosis method and equipment. The method comprises the following steps: establishing a diagnosis mechanism fusing time-frequency domain feature extraction and multi-branch depth feature modeling; original vibration signals are respectively converted into GADF images to capture time sequence dependence, CWT is adopted to extract transient frequency change, STFT is utilized to obtain frequency spectrum characteristics under a stable working condition, and joint input of a multi-view time-frequency graph is realized. On a model structure, a Swin Transform branch is designed for local space detail modeling, a global perception branch is constructed by combining a CNN module and a GAM module, and multi-category fault classification is completed through self-adaptive pooling and a full connection layer on fusion output. User-defined data loading and a standardized process guarantee the consistency of training data, multi-core maximum mean difference is introduced for feature distribution alignment, and the migration ability of the model under different working conditions and the decoupling recognition ability of composite faults are improved.

The invention discloses a fault diagnosis method and device and a computer readable storage medium. The fault diagnosis method comprises the steps that hardware layer data, system layer data and application layer data are acquired; based on the hardware layer data, the system layer data and the application layer data, constructing fusion feature information; performing fault diagnosis based on the fused feature information to obtain fault diagnosis information; and generating a fault processing strategy based on the fault diagnosis information. According to the method, the multi-dimensional data of the hardware layer, the system layer and the application layer are acquired, the fusion feature information is constructed to perform fault diagnosis and generate the processing strategy, so that the performance of the fault at different levels can be comprehensively captured, the accuracy of positioning the fault reason is improved, missed diagnosis and misdiagnosis are reduced, the comprehensiveness and accuracy of fault diagnosis are improved, and the fault diagnosis efficiency is improved. Meanwhile, a user can conveniently and autonomously solve faults.

The invention discloses a ship propulsion shafting fault diagnosis method based on multi-modal attention fusion, and relates to the technical field of ship fault diagnosis. According to the method, multi-modal data such as vibration parameters, lubricating oil parameters and cooling water parameters of key parts of a ship propulsion shafting are synchronously collected and preprocessed; a modal specific feature extraction strategy is adopted, a multi-modal attention fusion mechanism including intra-modal self-attention, inter-modal cross attention and adaptive dynamic weight distribution is designed, and heterogeneous modal features are effectively integrated. Compared with a single-mode method and a traditional feature splicing method, the method has the advantage that the diagnosis accuracy is remarkably improved. The method has high robustness, and can still maintain high diagnosis accuracy even under the condition that part of sensors fail.

The invention discloses a fault diagnosis method and system for a rotating machine bearing, and belongs to the technical field of fault diagnosis. The method comprises the following steps: acquiring a to-be-diagnosed vibration signal of the rotary mechanical bearing; inputting the to-be-diagnosed vibration signal into a pre-constructed bearing fault diagnosis model, and outputting a fault diagnosis result of the rotating machine bearing; the bearing fault diagnosis model comprises a feature extraction network, a GMM feature enhancement module, a projection distillation module and a dynamic extensible classifier which are connected in sequence. According to the method, catastrophic forgetting can be effectively relieved, continuous diagnosis of newly-occurring accidental faults can be achieved, in the initial task, the model learns and identifies different fault types through a fault bearing data set collected in advance, a basis is provided for the subsequent increment task, the increment task is composed of a plurality of stages, and in each stage, the fault bearing data set is subjected to fault detection. The model enhances playback of old knowledge through historical category pseudo features generated by a Gaussian mixture model, and aligns feature representations of new and old models by using a projection distillation module.

The invention discloses a carrier roller fault diagnosis method based on aliasing period fusion features, and particularly relates to the field of roller fault diagnosis. According to the scheme, the operation data of the carrier roller of the conveyor are collected through the sensor, and the collected original sensing data are preprocessed; the method comprises the following steps: dividing carrier roller sensing data into samples based on sliding window sampling, and dividing into a training set, a verification set and a test set according to 6: 3: 1; a carrier roller fault diagnosis model based on the Times-SCConv network is constructed, and parameters are initialized; training and verifying the Times-SCConv network based on the training set and the verification set, optimizing network parameters by using an optimization algorithm, and storing an optimal weight; and inputting the test set into the optimal Times-SCConv network model to carry out carrier roller fault diagnosis, and finally obtaining a carrier roller fault classification result and test accuracy. According to the technical scheme, the problem that fault feature extraction is difficult when sensing data signals of the carrier roller are subjected to aliasing coupling is solved, and modeling extraction of carrier roller data periodic change features is achieved.

The invention discloses a composite fault diagnosis method for motor overload and pressure abnormity of a wind power water cooling system. The method comprises the following steps: S1, data acquisition; the collected original signal data is preprocessed; s2, constructing a lightweight system performance model, and calculating a pressure residual error; s3, extracting time domain and frequency domain features from the original signal data and the residual signals to form feature vectors; s4, performing fault diagnosis based on a machine learning model, and inputting the feature vector into a trained model; the model outputs a diagnosis result and gives a fault confidence coefficient; and S5, outputting a result, and performing early warning. Predictive maintenance is achieved, early warning can be given out at the early stage of a fault when shutdown or secondary damage is not caused, a maintenance plan can be made in advance, passive first-aid repair is changed into active planning, the non-planned shutdown time is shortened, and the availability of a wind field is improved; the unnecessary on-site inspection frequency is reduced, the excessive dependence on the qualification operation and maintenance experts is reduced, and the troubleshooting time is shortened.

The invention relates to a harvester fault diagnosis method and device, electronic equipment and a storage medium. The method comprises the steps that fault information input by a user is acquired; carrying out vectorization coding on the fault information to obtain a query vector; according to the query vector, a preliminary retrieval result is obtained from a pre-constructed knowledge base, and the preliminary retrieval result comprises at least two fault-related historical cases corresponding to the query vector; and obtaining a fault diagnosis report through a pre-trained retrieval enhancement model according to the at least two historical cases and the query vector. By means of the method, the generated fault diagnosis report is comprehensive in content and clear in structure, explainable basis based on real cases can be provided, the reliability and operability of maintenance suggestions are enhanced, and finally the fault processing efficiency is improved, the misdiagnosis rate is reduced, and the downtime is shortened.

Embodiments of the present disclosure provide a fault diagnosis method and apparatus for service failure, and a storage medium. The method includes: acquiring abnormal information to be diagnosed described in a natural language; retrieving, from a fault knowledge base, similar target known fault knowledge based on the abnormal information to be diagnosed, where the fault knowledge base is used to maintain a plurality of sets of known fault knowledge; constructing a first fault analysis instruction of the abnormal information to be diagnosed according to the target known fault knowledge and the abnormal information to be diagnosed; and invoking a language model to take the first fault analysis instruction as an input, and output a fault analysis result of the abnormal information to be diagnosed.

The invention discloses an emergency hydraulic system and a control method thereof. The emergency hydraulic system comprises a multi-source redundant hydraulic loop, a multi-mode sensing and fault diagnosis module, a cooperative control strategy module, a man-machine cooperative emergency operation interface module and an intelligent energy management module. By adopting the multi-source redundant hydraulic loop design, the problems that a traditional emergency hydraulic system is single in power source and lacks redundancy are effectively solved, and the reliability and stability of the system are remarkably improved. When the main hydraulic pump breaks down, the standby hydraulic pump and the pneumatic auxiliary pump can be rapidly started, continuous operation of the hydraulic system is ensured, and shutdown or safety accidents caused by system faults are prevented. Key parameters of the hydraulic system are monitored in real time, feature extraction and fault recognition are carried out on sensor data in combination with a deep learning algorithm, and rapid positioning and accurate evaluation of faults of the hydraulic system are achieved.

The invention provides a ballast water emergency receiving and processing fault diagnosis method and system based on a knowledge graph, and the method comprises the steps: obtaining the fault performance, real-time operation and medium characteristic information of a ballast water emergency receiving and processing system, constructing a dynamic association link in a pre-configured knowledge association system, the knowledge association system comprises fault performance, causes, component association, medium influence nodes and dynamic association relationships, and is adjusted in real time along with the change of medium characteristics. And performing multipath fault source deduction along the dynamic association link, positioning fault cause nodes, and calling association processing operation node information to generate a fault diagnosis scheme including fault source description, processing flow and medium regulation and control suggestions. And finally, integrating implementation feedback information and fault data, and updating a node association relationship. According to the invention, the accuracy and comprehensiveness of fault diagnosis are improved.

The invention discloses an intelligent medical equipment fault diagnosis and prediction method based on deep learning, and the method comprises the following steps: S1, obtaining the data of medical equipment in an operation process, and constructing an original data set of the medical equipment; s2, preprocessing the original data set of the medical equipment, and extracting an input feature vector of the medical equipment; s3, constructing a multi-task deep neural network model, and combining and constructing an initial result set; s4, on the basis of the initial result set, constructing an overall performance index of the initial result set; s5, based on the overall performance index of the initial result set, a multi-target grey wolf optimization algorithm is adopted to carry out joint optimization on the result, and a final optimization parameter set is obtained; and S6, correcting the result by using the optimization parameter set, and outputting an optimization diagnosis result and an optimization prediction result. According to the method, a joint mechanism of the multi-task deep neural network and the multi-target grey wolf optimization algorithm is adopted, and cooperative output and precision enhancement of medical equipment fault diagnosis and life prediction results are realized.

The invention discloses a new energy vehicle fault diagnosis training system based on digital twinning, and the system comprises a data collection and assimilation module which is used for collecting vehicle operation data, and constructing a digital twinning body; the mechanism map construction module is used for constructing a causal failure mechanism map and generating a failure scene; the sample generation and management module is used for generating a virtual domain sample set, a disturbance domain sample set and a real domain sample set, and combining to form a training data set; the residual fusion diagnosis model module is used for setting a physical residual branch and a disturbance residual branch and outputting a fault diagnosis result; the consistency alignment training module is used for constructing joint loss and optimizing the residual fusion diagnosis model; and the intelligent diagnosis and simulation module is used for executing real-time diagnosis and risk prediction, generating a simulation drilling script and training maintenance personnel. According to the invention, through digital twinning, residual fusion modeling and three-dimensional consistency training, accurate diagnosis and safe and efficient training of new energy vehicle faults are realized.

The invention discloses a mobile application function exception processing method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the parallel monitoring of a system resource state and business behavior data through a buried point probe, generating a structured log with an exception type identifier, and storing the structured log in a local database; when an exception is responded, triggering an associated diagnostor based on an exception type identifier in the log, and analyzing log data through a predefined rule to judge an exception level; and executing the sub-path response according to the grade. According to the method, the problems of slow response and fuzzy positioning of manual operation and maintenance are solved through probe collaborative collection, dynamic grading of the diagnostor and automatic response closed loop, the key anomaly recognition accuracy is improved, and automatic fault diagnosis and user consultation processing are achieved.

The invention relates to the technical field of ships, in particular to an anchor chain lifter hydraulic device fault diagnosis method and device based on CNN-LSTM. According to the hydraulic device fault diagnosis method and system, the pressure sensor, the flow sensor and the temperature sensor are adopted to collect data in the hydraulic device, and the CNN-LSTM fault diagnosis model is established to diagnose the fault of the hydraulic device according to the data collected by the sensors; moreover, the CNN-LSTM fault diagnosis model can process the collected data from a multi-dimensional angle, thereby improving the fault diagnosis precision, increasing the number of fault diagnosis types, and better meeting the actual application demands.

The invention belongs to the technical field of diabetic foot detection, and provides a diabetic foot monitoring system. Comprising a multi-sensor collaborative data acquisition module, a data preprocessing and feature extraction module, a data encapsulation and transmission module, a time sequence data modeling module, a time sequence data training module, a model lightweight deployment and real-time prediction module, a multi-stage early warning trigger module, a personalized health suggestion generation module and a real-time monitoring module. A local fault diagnosis and abnormity determination module; and a user side interaction and maintenance execution module. By adopting the sensor array, the foot risk is comprehensively reflected, and the wearing experience of a user is improved; low-delay early warning is realized through a local deployment prediction model; by arranging the personalized health suggestion generation module, the threshold value is dynamically adjusted according to the medical history and living habits of the patient, and the personalization of the system is improved.

The invention relates to the technical field of power system fault detection and first-aid repair, and discloses an intelligent power transmission line first-aid repair evaluation system and a control method.The intelligent power transmission line first-aid repair evaluation method comprises the steps that firstly, line operation parameters of a target line are obtained in real time, and the line operation parameters comprise line operation data, historical fault data and environmental factor data; the method comprises the steps of acquiring line operation parameters, performing preprocessing and fusion operation on the acquired line operation parameters, providing a high-reliability input reference for subsequent fault diagnosis and first-aid repair decision by integrating the multi-source heterogeneous line operation parameters, improving the sufficiency of diagnosis and decision basis, and then based on the result of preprocessing and fusion operation, determining the fault diagnosis and first-aid repair decision. According to the method, a preset fault decision tree model is adopted for fault diagnosis, finally, an initial first-aid repair scheme is generated according to a fault diagnosis result, and the initial first-aid repair scheme is optimized by utilizing a preset game theory model to generate a final first-aid repair scheme, so that quick generation of the fault diagnosis and first-aid repair scheme is realized by utilizing the fault decision tree model and the game theory model; and the first-aid repair efficiency is obviously improved.

The invention discloses a CAN card control method and system based on fault diagnosis, and relates to the technical field of electronic information, the system is composed of a plurality of functional modules, and the system comprises a feature sensing prediction module which dynamically adjusts the sampling frequency based on a bus load, collects multi-dimensional data, fuses the data into time-space correlation features, and sends the features to a server; inputting the space-time correlation characteristics into a lightweight adaptive attention LSTM model, and outputting a real-time fault prediction probability and time delay; the optimization control module obtains a fault prediction probability, constructs a multi-objective optimization strategy based on different intervals of the fault prediction probability, and adaptively adjusts CAN card control parameters according to the multi-objective optimization strategy, and the CAN card control parameters comprise a CAN Carport rate, a data priority and a working mode; collecting the bit error rate, the data transmission time delay deviation and the channel equipment temperature of a channel, performing normalization processing, and performing weighted summation according to a preset weight to obtain a channel health degree; and a closed loop adaptation module.

The invention relates to the technical field of oil-gas field oil well fault diagnosis, in particular to an oil-gas field oil well intelligent fault diagnosis method and device based on a swan-gap system. According to the method, the multi-mode equipment is connected through the swan-Mongolia distributed soft bus to collect data, and the edge computing nodes are deployed to perform local diagnosis, so that the dependence on the network is reduced, and the real-time performance of fault diagnosis is improved; a generalized Choquet integral synthesis model is used for fusing load displacement, acoustic emission and motor electrical parameter sub-risk values, the fault risk is comprehensively evaluated, the diagnosis accuracy is improved, and the missed diagnosis and misdiagnosis probability is reduced; self-inspection data such as hardware state and signal quality are collected through the sensor self-inspection layer, a fusion instruction is generated through the data credibility analysis layer to adjust data weight, a fault sensor is isolated, and data reliability is guaranteed; based on hardware and communication parameter analysis of network transmission data, a network adaptation execution instruction is dynamically generated, stable data transmission is ensured, and the anti-interference capability of the system is improved.

The invention belongs to the technical field of fault diagnosis, and particularly relates to a base rod forming device and a fault diagnosis method and system thereof. The method comprises the following steps: S1, acquiring fault diagnosis section data in an operation process of a base rod forming device; the fault diagnosis data comprises real-time operation parameters and physical state parameters of the base rod forming device; the real-time operation parameters comprise the real-time operation speed of a pressing roller used for shredding sheets, the real-time operation speed of a cloth belt used for conveying forming paper and the real-time operation speed when a cutter cuts a base rod; the physical state parameters comprise one or a combination of two or three of temperature, pressure and vibration; and S2, inputting the fault diagnosis data into a pre-trained fault diagnosis model in the form of time sequence data to obtain the fault type of the base rod forming device. The technical problem that in the prior art, misjudgment and missed judgment are prone to occurring in fault diagnosis of the base rod forming device is solved.

The invention discloses a medical equipment remote fault diagnosis, maintenance and guidance system based on a cloud platform. According to the invention, the deep reconstruction of the medical equipment maintenance ecology is realized by constructing the digital service network covering the whole process. The AR cooperation platform of the maintenance engineer end and the real-time data intercommunication of the hospital end break through the space-time limitation of technical support in a traditional maintenance mode, so that remote experts can directly participate in field fault diagnosis and cooperate with historical maintenance archives and fault tree analysis provided by the intelligent work order system, and the first repair rate is greatly improved. An intelligent order sending algorithm of the management background is combined with an order grabbing mechanism of the mobile terminal, so that the geographical distribution efficiency of engineer resources is optimized, precise docking is realized through skill label matching, the industrial pain point of scarcity of special equipment maintenance resources is solved, and the service life of the mobile terminal is prolonged. Modular design and data interconnection characteristics bring systematic improvement to medical equipment operation and maintenance management, and fine control of equipment management cost and continuous improvement of service quality are realized.

The embodiment of the invention provides an agent reflection method and device. The method comprises the following steps: determining a failure diagnosis result corresponding to a cooperation failure trajectory of a plurality of agents, wherein the failure diagnosis result comprises a key failure step in the cooperation failure trajectory and a corresponding responsible agent; based on the failure diagnosis result, determining a correction result corresponding to the key failure step through anti-factual reasoning; and generating a reflection for the responsibility agent based on the failure diagnosis result and the correction result. According to the technical scheme provided by the embodiment of the invention, the targeted correction suggestions can be generated only for the responsibility agent in the decisive error step and the reflection is carried out, so that the reflection efficiency and the reflection quality of the multi-agent system are improved.