229 results about "Multiple fault" patented technology

The invention discloses an intelligent power grid fault prediction method, system and device, and relates to the technical field of power grid fault prediction, and the method comprises the steps: carrying out the real-time collection of the multi-source operation data of a target intelligent power grid, and obtaining a multi-dimensional power grid operation feature set; operation fault analysis is carried out, a fault feature vector group is generated, transfer learning is carried out, and a fault probability distribution matrix is generated; performing fault risk analysis according to the fault probability distribution matrix, and dividing a plurality of risk levels; and performing propagation path simulation of the target smart power grid on the plurality of fault early warning signals to generate a fault prediction report. According to the invention, the technical problems of low prediction precision and poor timeliness caused by fault prediction lagging and inaccurate fault propagation path simulation of the smart grid in the prior art are solved, and the technical effects of accurate prediction and risk early warning of the smart grid fault and improvement of the timeliness and accuracy of fault pre-judgment are realized.

The invention discloses an air pre-heater cold end multi-fault diagnosis method and device based on a panorama and a dynamic intelligent model, and relates to the technical field of thermal power plant auxiliary engine fault diagnosis, and the method comprises the steps: constructing a panorama monitoring image of an air pre-heater rotor, and dividing the panorama monitoring image into a plurality of independent monitoring regions; extracting color channel information of each monitoring area, and dynamically updating a threshold range of each color channel based on a multi-trigger condition; obtaining morphological edge contour features and color channel deviation features, and jointly inputting the morphological edge contour features and the color channel deviation features into a pre-trained multi-fault classification model; the fault type recognition result, the confidence coefficient and the preset fault type weight are fused, the comprehensive degradation index of each monitoring area is calculated, a three-dimensional diagnosis result is output in combination with the spatial position information of the monitoring areas, and accurate positioning diagnosis, degradation trend quantification and multi-fault intelligent distinguishing of the cold end area of the air preheater are achieved. The method is suitable for full-life-cycle online monitoring and maintenance decision making of the rotary air pre-heater.

The invention discloses a photovoltaic power station fault diagnosis method based on digital twinning and transfer learning, and belongs to the technical field of photovoltaic power generation fault detection. According to the method, a photovoltaic power station digital twin model based on a physical mechanism is constructed, operation behaviors in normal and multiple fault states are simulated, and a simulation data set with an accurate label is generated; in combination with the acquired real operation data, a fault diagnosis model is trained by adopting a transfer learning framework containing a domain adaptation loss item, so that the distribution difference between simulation data and real data is effectively reduced; a physical consistency loss item is innovatively introduced, and a physical rule is used as a constraint embedded model, so that the reliability and interpretability of a diagnosis result are improved; and finally, performing accurate fault diagnosis on the real-time operation data by using the trained model. According to the method, the model training problem caused by scarcity of real fault data is solved, the diagnosis precision and generalization ability are remarkably improved, and the method is suitable for intelligent operation and maintenance of the photovoltaic power station.

The invention discloses a flexible AC / DC hybrid power distribution network fault recovery optimization method and system based on multi-agent deep reinforcement learning, a computer device and a non-transient computer readable storage medium, and the method comprises the steps: firstly constructing an AC / DC power distribution network model considering the operation characteristics of a flexible switch and a voltage source converter; then, flexible equipment is modeled as an independent agent, a multi-agent training architecture is established, a composite reward function fusing a load recovery rate, voltage stability and operation safety is designed, and a mechanism combining centralized training and distributed execution is adopted to realize multi-point cooperative control between the flexible equipment; and finally, designing a recovery optimization process for rapid decision and control execution after the fault. The method can realize higher load recovery rate and better voltage control performance in various fault scenes, has the advantages of strong decision real-time performance, good system expandability, strong strategy generalization ability and the like, and is suitable for autonomous recovery and intelligent regulation and control of the novel flexible AC / DC hybrid power distribution network.

The invention provides a crown block operation fault detection method and system, electronic equipment and a storage medium, and belongs to the technical field of fault detection, and the method comprises the steps: detecting a crown block based on a first detection frequency, and obtaining target state detection data; and if the target state detection data does not meet the first condition, detecting operation data of the crown block based on the target state detection data to obtain crown block operation detection data. And inputting the crown block operation detection data and the target state detection data into the crown block fault detection model to generate a detection result. The crown block fault detection model is obtained by training crown block fault sample data and comprises a first correlation coefficient and a second correlation coefficient. The first correlation coefficient represents the correlation between each fault feature in the crown block fault sample data and the crown block fault type, and the second correlation coefficient represents the correlation among a plurality of fault features in the crown block fault sample data. According to the invention, the accuracy of crown block fault detection can be improved.

The invention relates to the technical field of photovoltaic equipment diagnosis, in particular to a distributed photovoltaic diagnosis method and system based on multi-modal time sequence data. The invention discloses a distributed photovoltaic diagnosis system based on multi-modal time sequence data. The distributed photovoltaic diagnosis system comprises a multi-modal time sequence data acquisition module, an electrical feature vector extraction module, a single fault source judgment module and a fault source combination judgment module. According to the method, the electrical feature vector and the electrical feature fingerprint database are matched, the similarity is calculated, and the threshold value is set, so that the fault source can be directly judged under the condition of a single fault source, linear splitting is performed through a group optimization algorithm under the condition of multiple fault sources, and the fault source can be determined in combination with the contribution component and the occurrence frequency of the fault source. The occurrence probability of the fault sources is calculated and analyzed with a set fault source combination probability threshold value, it is ensured that fault source combination information is output only when contribution of the multiple fault sources reaches a certain threshold value, and then the diagnosis precision of the fault sources is optimized.

The invention relates to the technical field of smart power grids, in particular to a smart power grid fault real-time diagnosis system based on digital twinning. The system comprises a multi-point detection arrangement unit, a multi-fault feedback unit and a virtual digital twinning unit. Through cooperation of multi-point detection, dual fault feedback and digital twinborn mapping, high-precision real-time diagnosis of smart power grid faults is realized, a microscopic clustering and macroscopic verification combined mechanism is adopted, true and false faults are effectively distinguished, and islanding effect misjudgment is inhibited; reverse reasoning and pseudo-cluster filtering are introduced, so that the robustness of the system is improved; the fault situation is dynamically rendered based on BIM + GIS, visual operation and maintenance are supported, the problems that in traditional diagnosis, single-point misinformation is difficult to eliminate, and large-range positioning is delayed are solved, and the fault recognition accuracy and the power grid operation reliability are remarkably improved.

The invention provides a steer-by-wire vehicle fault processing method, device and equipment and a medium, and belongs to the technical field of vehicle fault processing, and the method comprises the steps: dividing a plurality of fault categories based on corresponding fault causes and fault influences when a redundant steer-by-wire system breaks down; respectively determining the function state of each sub-function module in the system when the redundant steer-by-wire system is subjected to different fault types; and respectively formulating a corresponding fault processing strategy for each degraded sub-function module based on the current fault category and the function state of each sub-function module. Through the technical scheme in the embodiment of the invention, corresponding fault-tolerant processing can be designed according to different function degradation conditions.

The invention discloses a substation high-voltage switchgear multi-dimensional data fault diagnosis system, which comprises a multi-dimensional data acquisition module, a data processing module and a diagnosis decision module, and is characterized in that the multi-dimensional data acquisition module is used for acquiring multi-dimensional data information of substation high-voltage switchgear; the data processing module is used for preprocessing the collected multi-dimensional data information, and the diagnosis decision module comprises a historical data-based fault diagnosis unit, a data mining-based fault diagnosis unit, a machine learning-based fault diagnosis unit and a high-voltage switchgear-based fault diagnosis unit. The multi-dimensional data information of the switchgear is collected, information of different sources is integrated and analyzed, and support is provided for comprehensive and accurate diagnosis results. And meanwhile, fault diagnosis is performed on information of different sources in a targeted manner by adopting multiple fault diagnosis modes, so that the accuracy, effectiveness and reliability of fault diagnosis are improved, and clear guidance and requirements are provided for research of a fault diagnosis technology.

The invention discloses a single-multiple fault combined diagnosis method and system for textile logistics equipment, and the method comprises the steps: obtaining equipment operation data, carrying out the preprocessing and feature extraction, and forming a standardized feature data set; performing single-fault diagnosis on the standardized feature data set, outputting a confidence result, completing confidence judgment according to a preset threshold value, and selectively outputting a single-fault conclusion or entering multi-fault combined diagnosis; in the multi-fault combined diagnosis stage, a fault relevance matrix is constructed through data relevance analysis, a causal relation graph is generated, the coupling relation between different faults is recognized, combined reasoning is completed, and a multi-fault combined diagnosis result is obtained. And finally, carrying out visual display on the diagnosis conclusion, and generating alarm grading and operation and maintenance auxiliary decision-making information. According to the method, self-adaptive switching between single-fault diagnosis and multi-fault combined diagnosis can be achieved, and the fault recognition precision and diagnosis reliability under the complex working condition are improved by combining correlation analysis and causal reasoning.

The invention provides an extension value intelligent monitoring bolt and a real-time monitoring and fault early warning method. A miniature piezoelectric sensing intelligent bolt is integrated, and extension is sensed through integrated packaging; dual-mode wired / wireless transmission is achieved, and remote real-time monitoring is achieved; aI threshold early warning is carried out, a comparison curve is automatically generated, looseness, overload, bolt breakage and signal abnormity are intelligently recognized, and full-life-cycle safe operation and maintenance are achieved. According to the invention, real-time continuous monitoring and multi-fault-mode intelligent early warning of the bolt elongation value can be realized, and the safety and the operation and maintenance efficiency of the bolt connection structure are effectively improved.

The invention discloses a single-phase earth fault comprehensive discrimination method based on multiple fault criteria and weight dynamic calculation, and the method comprises the steps: collecting phase voltage and zero sequence voltage characteristic quantities before and after a power distribution network fault, and discriminating the type of a single-phase earth fault according to the change rule of the characteristic quantities; the method comprises the following diagnosis steps: a, adopting a new zero-sequence current method, calculating the zero-sequence current break variable of each feeder switch based on a zero-sequence current reference value, and achieving the positioning of a fault feeder and a section; b, a new phase current method is adopted, a phase current fault characteristic quantity is defined based on the sum of three-phase current difference values before and after a fault, and positioning of a fault feeder line and a section is achieved; constructing an evaluation model by adopting a fuzzy analytic hierarchy process according to the fault category judged by the parallel diagnosis, and dynamically determining a weight coefficient; and performing weighted fusion on the confidence coefficient according to the weight coefficient to obtain the comprehensive fault probability of each feeder line, selecting the feeder line with the maximum comprehensive fault probability as a fault feeder line, and judging a fault interval.

The invention relates to the technical field of sensors, and discloses a signal optimization method based on a diagnosability evaluation result, and the method comprises the following steps: S1, obtaining monitoring signal data collected by a plurality of candidate sensors in a normal state and a plurality of fault states of equipment, and S2, carrying out the optimization of the signals based on the monitoring signal data, according to the method, a fault detectability model is constructed, the fault detectability model is used for quantifying the difference between a fault state and a normal state on sensor signals, and when sensor signal optimization is carried out, the fault detectability model and the fault isolability model are constructed in a unified manner; and a detectability evaluation index and an isolability evaluation index are calculated based on a joint mean-variance difference value, so that comprehensive quantitative evaluation of the signal fault detection capability and the fault isolation capability is realized, and it is ensured that performance requirements of different dimensions of fault diagnosis in a signal optimization process are balanced. And the comprehensiveness and accuracy of fault diagnosis are improved.

The invention relates to the technical field of new energy power generation and power grid modeling, in particular to a multi-working-condition matching model parameter identification method for new energy actual measurement modeling. According to the technical scheme, the multi-working-condition matching model parameter identification method for new energy actual measurement modeling comprises the following steps that actual measurement data of a new energy converter under multiple fault working conditions are obtained, and a fault parameter matrix containing current control values during symmetric faults and asymmetric faults is constructed; calculating a current limiting value parameter based on the fault parameter matrix; an initial identification matrix is constructed, an intermediate matrix is generated according to the current limiting value parameters, and the intermediate matrix is used for marking elements reflecting real control characteristics in the identification matrix. Multi-working-condition parameter intelligent optimization and model verification are achieved, repeated simulation and comparison calculation of a large number of working conditions are avoided, and a modeling scene with the large number of working conditions, the large deviation item calculation amount and the complex model parameters can be efficiently completed.

The present disclosure provides an operation and maintenance platform and a fault troubleshooting method. The operation and maintenance platform includes: a debugging interface, a proxy module, and multiple fault troubleshooting engines. The debugging interface is configured to receive operation and maintenance information and return a fault troubleshooting report. The proxy module is configured to determine a backend cloud environment based on environment information in the operation and maintenance information and submit the operation and maintenance information to a fault troubleshooting engine corresponding to the backend cloud environment. The fault troubleshooting engine is configured to determine a fault troubleshooting link graph based on the information on the problem description, perform fault troubleshooting on the maintenance object based on the fault troubleshooting link graph and an identity of the maintenance object, determine a root cause of a fault corresponding to the problem description, and generate the fault troubleshooting report.

The invention relates to the technical field of motor fault identification, in particular to a permanent magnet synchronous motor fault identification and analysis method for a belt conveyor, which comprises the following steps of: extracting a characteristic change rule of a stator current signal and a vibration acceleration signal of a permanent magnet synchronous motor under a typical fault condition; collecting a vibration signal and a current signal of the fault motor; carrying out noise reduction processing on the collected vibration signals and current signals; converting the vibration signal and the current signal after noise reduction into a two-dimensional image data set; vertically splicing and fusing the vibration signal image and the current signal image; dividing the fused image data into a training set and a test set according to a preset proportion; establishing a convolutional neural network model; and inputting the training set into the convolutional neural network model. According to the permanent magnet synchronous motor fault diagnosis method based on the data layer fusion strategy, the feature information of multiple fault modes of the permanent magnet synchronous motor is comprehensively captured, and the accuracy and robustness of fault recognition are remarkably improved.

The application discloses a kind of power battery fault processing method and device, nonvolatile storage medium and vehicle.Therein, the method relates to the field of intelligent automobile, and the method comprises: in response to the time length that power battery appears fault state is monitored and exceeds preset time length, obtains the current state parameter of power battery;Determine the target fault level corresponding to fault state from multiple fault levels based on current state parameter, wherein multiple fault levels are used to distinguish the severity of the fault that power battery appears;According to target fault level, power battery is processed, and fault processing result is obtained, wherein fault processing result is used to indicate whether power battery eliminates fault state.The present application solves the technical problem that the accuracy of fault processing is low.

The application discloses a kind of based on panoramic map and dynamic intelligent model's air preheater cold end multiple fault diagnosis method and device, it is related to the technical field of auxiliary machine fault diagnosis of thermal power plant, method includes: constructing the panoramic monitoring image of air preheater rotor, and is divided into multiple independent monitoring areas;Extract the color channel information of each monitoring area, based on multiple trigger conditions dynamically update the threshold range of each color channel;Obtain morphological edge contour feature and color channel deviation feature, input to pre-trained multiple fault classification model together;Fusion fault type identification result, confidence and preset fault type weight, calculate the comprehensive degradation index of each monitoring area, combined with the spatial position information of monitoring area output three-dimensional diagnosis result, realize the accurate positioning diagnosis of air preheater cold end area, degradation trend quantification and multiple fault intelligent distinction, suitable for the whole life cycle online monitoring and maintenance decision of rotary air preheater.

According to the artificial intelligence ammeter data visualization-based power distribution system fault position identification method provided by the invention, three basic learners, namely a random forest, a K-proximity algorithm and an artificial neural network, are combined, and an integration method of combining a plurality of different machine learning models into a prediction model can be adapted to different scenes, so that the accuracy of the prediction model is improved. For example, noise and data loss, fault resistance change, load or power distribution feeder structure change and the like can be realized. An integrated voting classifier is developed, and a random forest, kNN and an artificial neural network model are utilized to classify fault types and identify a limited number of data points of FL only using voltage measurement. According to the method, the key problem of insufficient multiple features is overcome, the fault position can be quickly identified, the method is not influenced by the initial angle of the fault and the resistance on the line, the anti-interference capability is high, the classification accuracy of multiple fault types is high, the detection precision is high, and the cost is not too high.

This invention relates to the field of power distribution fault location technology, specifically to an AI-driven power distribution fault location system and method. The system includes: a state projection construction unit that constructs multiple fault state projection surfaces; a state collision elimination unit that uses a topology response collaborative constraint model to identify structural logic conflicts and uses a structural collision-driven multi-path filtering mechanism to eliminate fault state projection surfaces with structural logic conflicts; a differential comparison scoring unit that uses an AI response scoring model to generate confidence scores for each candidate fault state projection surface and uses a working condition semantic embedding model to correct the confidence scores; a structural feedback location unit that uses the AI ​​response scoring model to update and sort the confidence score sequence to determine the fault point; and a fault terminal processing and display unit that displays the fault points of each power distribution station and generates inspection tasks and maintenance work orders. This invention combines AI-driven intelligent judgment and location of power distribution faults and constructs a fault identification method for multi-site maintenance scenarios.

The application discloses a power distribution network primary and secondary collaborative planning method and system based on a whale optimization algorithm. Multiple fault scenarios are constructed and classified, each fault scenario containing one or more lines; the fault recovery time of users under each type of fault scenario is calculated; a power distribution network primary and secondary network architecture collaborative planning model is constructed, which is used to calculate the optimal configuration of primary equipment and secondary equipment when the power outage loss and network loss of users under the fault scenario are the lowest; and the whale optimization algorithm is used to solve the power distribution network primary and secondary network architecture collaborative planning model to obtain the optimal configuration of the primary equipment and the secondary equipment of the power distribution network when the objective function is the minimum. Through the introduction of randomness and diversity operations, and the adjustment of the parameter balance of exploration and utilization ratio, the application can efficiently handle faults under various weather scenarios, solve the fault problems that may occur to distributed photovoltaic power sources and other power distribution network equipment under various weather scenarios, and thus significantly improve the reliability and stability of the system.

The invention discloses a military crane chassis fault reproduction and practical training system based on working condition simulation, and relates to the technical field of military equipment practical training, and the system comprises an entity chassis building unit which selects and uses entity parts of subsystems of a military automobile crane to be arranged and installed according to a real automobile, retains a key relation, presets an interface, defines a safety threshold value and the like; the dual-mode fault generation unit constructs an initial library, and an intelligent agent is embedded to generate a fault; the multi-dimensional data acquisition unit responds to the trigger signal to acquire multiple types of data; the fault diagnosis practical operation unit is used for trainees to operate; the training evaluation and fault iteration unit generates a report and feeds back optimization suggestions; according to the invention, a dual-mode fault generation unit is constructed, an initial fault library and an intelligent agent exploration capability are integrated, a screening algorithm is matched, and multiple fault scenes are provided; a complete practical training system is built, multi-dimensional data acquisition is achieved, practical operation and evaluation iteration are standardized, the practical training quality is improved through closed-loop design, and the military crane chassis fault practical training requirements are met.

The application discloses a kind of power grid fault diagnosis method and system based on electric power data analysis, it is related to electric power system fault diagnosis related field, including: the multiple electric power data sources of constructing electric power network, extract multiple electric power data;Multiple electric power data are carried out semi-supervised separation according to fault type using blind signal separation algorithm, obtain multiple separation signals;The fault feature similarity between the pairs of multiple electric power data sources is calculated;According to the cross-source end clustering of fault feature similarity calculation result, the multiple separation signal clusters output are respectively input power grid fault diagnosis model analysis, obtain multiple fault types, send power grid fault diagnosis result after joint identification.Solve the technical problem that existing power grid fault diagnosis exists in mixed fault scene and is easy to produce misjudgment due to signal coupling, leading to insufficient diagnostic accuracy and reliability, achieve the technical effect of accurate separation and identification through complex mixed fault, improve fault diagnosis accuracy and reliability.

The present application relates to the technical field of fault type identification acceleration, in particular to a kind of multi-modal sound feature fusion's fluid transmission equipment fault classification acceleration method and system;After sound sensor collects fluid transmission component operation sound signal, pre-processing is removed interference noise;Time domain feature extraction module extracts multi-scale space-time feature by multi-scale time convolution fusion unit;Frequency domain feature extraction module is converted by FFT, amplitude and phase separation processing and IFFT restoration, and time domain feature after frequency domain processing is obtained;Dual-domain feature fusion module fuses dual-domain feature by real Gabor wavelet function, and then excavates deep feature by Transform module;Fault diagnosis module outputs fault classification result by convolution, fully connected and Softmax function, and hardware platform outputs recognition accuracy by UART serial communication.This application detects comprehensively, responds quickly, has strong stability, low power consumption, good portability, can be adapted to different environments, identifies multiple fault types, and can also be extended to other related fields.

The invention relates to the technical field of transport vehicle electric appliance testing, and provides a general transport vehicle whole-vehicle electric appliance fault simulation system which comprises a fault scene configuration unit, a multi-protocol self-adaption interaction unit, an electric appliance fault simulation unit, a whole-vehicle bus closed-loop simulation unit and a fault triggering and feedback unit. The fault scene configuration unit generates a reusable fault script; the multi-protocol adaptive interaction unit realizes seamless communication adaptation; the electric device fault simulation unit accurately simulates various faults; the whole vehicle bus closed-loop simulation unit ensures that fault propagation is real; the fault triggering and feedback unit realizes fault triggering and closed-loop verification, supports visual configuration of multi-type fault scenes and generation of reusable scripts through a built-in multi-vehicle-type electric appliance topology template library, can adapt to different vehicle types, is short in matching time consumption, is high in fault simulation precision, can accurately simulate various faults, and is high in reliability and high in reliability through combination with the multi-protocol self-adaptive interaction unit. The fault simulation universality and accuracy are greatly improved, and the test cost is reduced.

The invention discloses a fault identification and diagnosis system for power distribution equipment edge calculation, and relates to the technical field of power distribution equipment management. Constructing a chained fault propagation path composed of at least two observable fault feature nodes arranged in sequence and an allowable time delay interval, and issuing and storing the chained fault propagation path in an edge node; the evidence generation module is used for collecting operation parameters in real time and extracting features; and when the features have stable deviation and meet a preset change rate or acceleration threshold, constructing a fault evidence node containing the type, the timestamp and the amplitude. According to the method, a chain fault propagation path is constructed, so that edge nodes can execute closed-loop inspection according to an equipment operation mechanism and a characteristic evolution rule; when the appearance sequence and the time difference of a plurality of fault evidence nodes are consistent with the chained propagation path, the propagation logic of the internal fault of the equipment can be accurately identified.

The present application relates to the field of artificial intelligence system, industrial artificial intelligence network system and other fields in the production field of new generation information technology, especially to a kind of asynchronous motor multi-fault intelligent diagnosis system.The asynchronous motor multi-fault intelligent diagnosis system includes: sensor network, including: M type sensor, for collecting induction signal in the process of asynchronous motor operation, M is greater than or equal to 2;Signal processing module, for processing the induction signal collected by M type sensor, extracting characteristic parameters;Fault diagnosis module, connected with signal processing module, for taking the characteristic parameters output by signal processing module as data input, judging the running condition of asynchronous motor through neural network model, outputting the representation of normal state when running normally, and outputting fault type when fault occurs.The present application realizes comprehensive and accurate intelligent diagnosis of various faults of asynchronous motor, improves the efficiency and accuracy of fault diagnosis, and improves the trust and satisfaction of users.

The invention relates to the technical field of direct current fault detection, and discloses a direct current series arc fault detection method and device, a photovoltaic inverter and a medium. And processing the input voltage and the input current of the photovoltaic inverter to obtain a characteristic data training set under the condition that the arc generator simulates the photovoltaic inverter to generate a direct current series arc fault and the condition of normal operation, wherein each arc fault detection model is obtained by pre-training based on the corresponding characteristic data set. The method comprises the following steps: firstly, acquiring an input side voltage and an input side current of the photovoltaic inverter, and processing the input side voltage and the input side current respectively to obtain multiple groups of feature data including voltage feature parameters and current feature parameters; then, the multiple sets of feature data are input into a pre-trained corresponding arc fault detection model for processing, and multiple fault detection results are obtained. And finally, based on a plurality of fault detection results, a voting mechanism is adopted to determine whether the photovoltaic inverter has a DC series arc fault.

The application relates to the technical field of fault injection, and particularly discloses a software fault injection automatic testing method and system, which specifically operates as follows: a user first performs fault configuration on a PC end and issues a fault injection command; the fault injection command is sent to a measured chip in the form of a communication message; the measured chip enters an interrupt receiving mode, analyzes the communication message, and starts to execute fault injection; a GPIO port starts timing of a fault injection response time, and a PC end collects fault injection process and result data; after the fault injection is completed, a power supply restarts a system reset. The method can configure the category, injection times, time and other attributes of faults, can automatically implement multiple fault injections, makes the entire fault injection process flexible, can automatically calculate the response time of each fault injection, improves fault injection test efficiency, and the entire fault injection process data and result are collected and counted, so that the entire test is visualized and traceable.

This application provides a chaos testing method, apparatus, device, storage medium, and program product, which can be applied to the big data field. The method includes: modifying the business data of key nodes based on fault factors in a business knowledge graph to obtain multiple fault nodes. The business knowledge graph is obtained from historical business data, and the key nodes are determined based on their impact on the business. Fault factors include adjustment values ​​for logical judgment conditions and timing delay values. The method also involves extracting the relationships between nodes in the business knowledge graph, and using multiple fault nodes as starting points, traversing the business knowledge graph based on these relationships to obtain multiple fault chains. Finally, the method injects the faults in each of the multiple fault chains into a test system to obtain test results.