179 results about "Single fault" patented technology

A rolling bearing combined fault diagnosis method based on a multi-domain feature construction is provided, including: collecting vibration signals of rolling bearings, extracting time-domain and frequency-domain features of fault-sensitive vibration signals of the rolling bearings, and obtaining an in-domain feature set; performing an improved empirical mode decomposition on the vibration signals of the rolling bearings to obtain time-frequency features; constructing a multi-domain fault sample set based on the in-domain feature set and the time-frequency features; performing a fault mechanism analysis on the multi-domain fault sample set to obtain modulation features under each single fault; carrying out a feature engineering on the time-domain and frequency-domain features, and screening out relevant features, redundant features and irrelevant features; performing an unsupervised hierarchical clustering on test set fault samples, and then inputting the test set fault samples into a KNN model for a classification, and obtaining rolling bearing combined fault diagnosis results.

The invention discloses a digital chip fault detection method and system based on big data, and the method comprises the steps: collecting the historical hierarchy data of chip failure fault analysis, extracting the feature data of each stage, and building the multi-dimensional feature association of the failure fault analysis data based on the feature data; synchronizing a single fault positioning model of the chip failure fault established based on the single failure root cause and a multi-fault positioning model of the chip failure fault established based on the associated interaction failure multiple root causes; failure fault positioning is carried out through a single fault positioning model and a multi-fault positioning model, a failure fault positioning result is output, and finally, the fault positioning output results of the single fault positioning model and the multi-fault positioning model are verified and reproduced. According to the method, the corresponding fault positioning model is constructed by using the judgment result of the failure root cause, and the problem of low positioning precision caused by various influence factors and interaction of an existing single fault positioning method is solved.

The invention discloses an unmanned aerial vehicle automatic test method, which comprises the steps of building a high-fidelity semi-physical simulation platform which comprises an unmanned aerial vehicle motion simulator, a three-dimensional environment simulator, a flight control module and a ground control station, and loading a complete machine fault model and a dynamic environment model; designing an intelligent multi-fault injection scheme, and defining a single fault scene, a combined fault scene and a fault evolution scheme; configuring a dynamic environment simulation scene including static environment parameters, dynamic environment elements and environment, and a fault interaction scene; executing a self-adaptive test process, automatically generating a test case, intelligently scheduling a test sequence and dynamically adjusting test parameters; and performing multi-source data intelligent analysis and evaluation, collecting test data, performing fusion analysis on fault influence, and generating an evaluation report. By constructing a whole machine fault and dynamic environment model, the scene authenticity is improved by 40%, and for example, the motor fault yaw deviation under strong wind is closer to a real machine compared with a traditional method.

The invention discloses a fault simulation method and equipment in a complex flight scene, belongs to the technical field of flight fault simulation, and aims to improve the fault-tolerant capability of a system and realize full-coverage simulation of the complex flight scene through state injection and fault simulation. The problems of insufficient fault scene coverage, real-time control and data reproducibility in the prior art can be solved; moreover, the method can inject the fault states of a plurality of devices in parallel in the same simulation process, and compared with a traditional method which only supports a single-device single-fault simulation mode, the method has the advantages that the capability of restoring a composite fault scene is greatly enhanced, and the method is suitable for limiting condition verification of a high-reliability aircraft system.

The invention belongs to the technical field of hydroelectric generating set monitoring, and relates to a water turbine bearing temperature and lubricating oil state monitoring and fault diagnosis method and system. According to the method, triple-redundancy temperature measurement values of a water turbine bearing are adopted, multiple parameters are fused, redundancy design is adopted, sensor failure diagnosis is executed, a temperature-vibration-oil pressure combined feature space is constructed according to the triple-redundancy temperature measurement values and online oil quality parameters, a fault propagation map is established, and the fault propagation map is analyzed. And finally, based on the multi-level diagnosis model and in combination with the fault propagation atlas, composite fault mode recognition is realized, a fault classification result is obtained, and the composite fault mode recognition is realized based on the multi-level diagnosis model, so that the problems of low reliability, single monitoring dimension and insufficient fault recognition capability of a sensor in the prior art are effectively solved. And the equipment reliability and the operation safety are obviously improved.

The invention relates to the technical field of fault prediction and computer big data processing, in particular to a generalized zero sample composite fault diagnosis method, device and system based on anti-fact reasoning. According to the generalized zero sample composite fault diagnosis method based on the anti-fact reasoning, a two-stage generalized zero sample composite fault diagnosis model based on the anti-fact reasoning is constructed. According to the model, internal causal components of fault data are pointed out from the angle of causal theory, and then a structural causal model is constructed to describe decoupling and generation of fault features under the guidance of anti-factual reasoning. On the basis, a generative model is improved through a reinforced discriminator in the first stage so as to realize binary classification of a single fault and a composite fault. In the second stage, a single fault category is predicted through supervised training of a classifier, and meanwhile, a traditional zero sample learning method is designed to classify composite faults. According to the method, the diagnosis precision of the model is greatly improved, and the problem of deviation of model diagnosis on visible classes and invisible classes is solved.

The invention relates to the technical field, and discloses a power distribution network multi-time scale fault scene deduction method comprising the following steps: obtaining meteorological and power grid operation data, establishing a time sequence fault tree model, and analyzing the trigger probability of multi-line disconnection and rainstorm short circuit faults in a target time period; extracting cross-level fault propagation features, analyzing a dynamic coupling relationship among multi-line disconnection, transformer substation flooding and cascading trip, forming a fault feature mode set, and identifying a single fault and a cascading fault in combination with time sequence analysis; historical fault data are analyzed, time sequence features and topological features of single and cascading faults are extracted, if a single fault propagation path is in a single level, a support vector machine is used for being combined with the features to judge fault types, and a classification result is output; and performing anomaly detection and confidence evaluation on a fault classification result, outputting a fault evolution path and risk evaluation, and analyzing the contribution degree of cascading trip to a large-area power failure risk in combination with historical blackout data to obtain power failure risk probability distribution.

A photovoltaic array fault diagnosis method for optimizing LightGBM based on an improved Heiwen algorithm comprises the following steps: simulating a photovoltaic array fault, analyzing I-V and P-V curves, and extracting a fault characteristic quantity; carrying out data acquisition and preprocessing on the extracted fault characteristic quantity, and dividing the fault characteristic quantity into a training set and a test set; a lens imaging reverse learning strategy, a sine and cosine algorithm strategy and a self-adaptive T distribution disturbance strategy are adopted to optimize and improve the BKA, and the global optimization capacity and convergence speed of the BKA are improved; a photovoltaic array fault diagnosis model based on the IBKA-LightGBM is constructed, and the photovoltaic array fault diagnosis model based on the IBKA-LightGBM is trained by using the training set; and verifying the validity of the photovoltaic array fault diagnosis model of the IBKA-LightGBM through the test set, and carrying out photovoltaic array fault detection. The fault diagnosis rate of a single fault and a composite fault is excellent; the fault diagnosis accuracy is higher, and the method can be effectively applied to photovoltaic array fault diagnosis.

The invention discloses a ship system fault diagnosis method and device based on multi-source information fusion, and belongs to the field of prediction and health management, and the method comprises the steps: collecting monitoring data including voltage, current, vibration acceleration, rotating speed, displacement and noise; preprocessing the monitoring data, respectively inputting each type of preprocessed monitoring data into a single parameter fault diagnosis model, and outputting a single fault diagnosis result; analyzing the plurality of single fault diagnosis results according to a multi-source information fusion diagnosis rule to obtain a fusion diagnosis result; and according to a fusion diagnosis result, determining a fault occurrence part and a fault property. According to the invention, multi-source and multi-dimensional parameters are collected to carry out fault diagnosis on a ship key system and equipment, so that the detection accuracy and credibility are improved.

The invention discloses a rolling bearing fault diagnosis method based on MSDFM-ASTRSB under a small sample, and the method comprises the steps: collecting one-dimensional vibration signals of a rolling bearing under different fault states through a plurality of sensors; a one-dimensional vibration signal of a single sensor in a single fault state is converted into a corresponding two-dimensional time-frequency diagram through continuous wavelet transform, and the two-dimensional time-frequency diagrams of a plurality of sensors are fused to obtain a multi-sensor data fusion image in the single fault state. Further obtaining multi-sensor data fusion images in all fault states and taking the images as a data set; constructing an MSDFM-ASTRSB rolling bearing fault diagnosis model based on an asymmetric soft threshold residual shrinkage block and a position interaction self-attention mechanism, and training the fault diagnosis model by using a training set in the data set; and using the trained fault diagnosis model to complete fault diagnosis of the rolling bearing. According to the invention, the defects of training sample shortage and single data are overcome, and the accuracy of rolling bearing fault diagnosis is improved.

The invention discloses a network-on-chip fault-tolerant system based on a fault processing router and a dual fault-tolerant distributed route, and relates to the technical field of network-on-chip. The system comprises a fault processing router and a dual fault-tolerant distributed routing mechanism. The fault processing router comprises a port distribution module, a redirection FIFO module, an error correction module, a crossbar switch module, a crossbar switch bypass module and a detection master control module. The modules cooperate to realize fault isolation and path reconstruction. According to the dual fault-tolerant distributed routing mechanism, fault tolerance is realized through single fault isolation, composite fault collaboration and dynamic routing adjustment, and deadlock is avoided and network connectivity under fault topology is maximized by dynamically relaxing and forbidding a steering rule. The problems of single-point failure and composite fault accumulation caused by permanent faults of transistors of the network-on-chip are solved.

The invention discloses a fault injection and detection method based on RTL, and relates to the technical field of aerospace fault-tolerant calculation, the fault injection and detection method is compatible with three single-particle fault types of SEU, SET and SEL, the injection bit number, duration and position can be customized by a user, and based on random number file configuration, the problems of single fault type and parameter solidification of an existing tool are solved; a bypass injection mechanism controlled by a timer is adopted, and a fault data flow is switched in a specified clock period, so that a trunk data flow is not influenced, and the occupation of system resources is reduced; a forward detection module is designed based on (13, 8) extended Hamming codes, a receiving end quickly locates the fault type and position through a syndrome look-up table, original data does not need to be transmitted back, and detection delay is effectively controlled; a streamlined design is adopted, check bit generation, fault injection, syndrome generation and fault information output are executed in parallel, and hardware resource overhead is obviously optimized.

The invention belongs to the field of box-type substation fault detection, relates to an information fusion technology, is used for solving the problem that the accuracy of a detection result cannot be guaranteed due to the fact that only a single fault diagnosis mode is adopted for fault detection in the prior art, and particularly relates to a box-type substation 5G intelligent information fusion system which comprises an information fusion platform. The information fusion platform is in communication connection with a box transformer fault detection module, a detection verification module and an instant decision module; the box-type substation fault detection module comprises an electrical detection unit and a waveform detection unit, the electrical detection unit is used for performing electrical fault detection on the box-type substation, and the waveform detection unit is used for performing current waveform detection on the box-type substation; the electrical state of the box-type substation is comprehensively monitored, the winding overheating hidden danger can be found in time through dynamic temperature rise calculation, and the problem of insulation degradation or sealing failure can be accurately recognized in combination with partial discharge and gas concentration detection.

The invention relates to a diagnostic data dump method and device, equipment and a medium. The method comprises the steps that diagnosis data of a single fault event are stored in a target buffer area in an event buffer area array, the target buffer area is only used for storing the diagnosis data of the single fault event, and the event buffer area array is located in a running memory; when a dump indication signal is monitored, the diagnostic data stored in the target buffer area is written into a corresponding target storage block in a nonvolatile memory, and each storage block in the nonvolatile memory corresponds to each buffer area in the event buffer area array in a one-to-one mode. According to the invention, the write-in operation during the dump of the diagnostic data can be reduced, and the dump performance of the diagnostic data is improved.

The invention discloses an intelligent electric control valve fault diagnosis method, which comprises the steps of performing data expansion based on cloud oversampling, capturing uncertainty in fault data, and constructing a new sample reflecting inherent randomness of original data in a cloud feature space; optimizing the new sample, and controlling inherent random fluctuation caused by cloud oversampling; a cloud membership function is adopted as a fitness calculation function; constructing a random configuration network fault diagnosis model with a parallel structure, wherein the models are respectively used for predicting the number and category of faults; in combination with a cloud model similarity calculation method, quantifying potential correlation between a single fault and a concurrent fault; and integrating output results to obtain a final fault diagnosis result. According to the method, random fluctuation caused by inherent uncertainty of the cloud model is effectively controlled, so that the adaptivity to different data sets is enhanced; a parallel network model is constructed to predict the number and types of faults respectively, and the problem that single faults and concurrent faults are difficult to distinguish is solved.

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 discloses a cascade H-bridge frequency converter multi-fault source identification method. The method comprises the following steps: acquiring real-time time sequence data of a frequency converter on line; generating a real-time system residual function representing system deviation by using a physical information health system operator which performs dynamic weight modulation through the working condition state vector; and a three-layer cascade operator decomposition architecture considering physical topology constraints is adopted to decompose the residual function so as to identify a single fault and a coupling effect. The method can adapt to dynamic working conditions, effectively suppress pseudo residual errors, accurately decouple concurrent faults, and significantly improve the accuracy and robustness of diagnosis.

The invention relates to the technical field of communication, in particular to a ship-shore cooperative communication method and device, electronic equipment and a storage medium. According to the scheme, the defect that a traditional system is single in monitoring index is overcome by obtaining the basic index and the business customization index data, comprehensive monitoring of the operation state of the shipborne platform is achieved, and the monitoring precision is remarkably improved; potential fault information is predicted based on two types of index data, passive warning is changed into active warning, and the problem that fault warning is not timely is solved. The shore-based equipment communicates with other shipborne platforms, a target repair strategy is obtained, a cooperative control instruction is generated, a cross-platform cooperative mechanism is constructed, the limitation of isolated operation of a traditional system is broken through, and the shore-based cooperative capability is enhanced; for the condition of no matching self-repairing strategy, external strategy resources can be dynamically called, a single fault recovery mode is changed, the fault recovery efficiency is effectively improved, and stable operation of the shipborne platform is guaranteed.

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 intelligent circuit breaker fault detection and maintenance method based on double MCUs, and the method achieves the automatic uninterrupted switching when a single MCU breaks down through the main and standby redundancy design, avoids the system breakdown, and greatly improves the usability and reliability. Quantitative scoring of the state of the main control MCU is achieved through a health assessment self-checking algorithm, and the accuracy of fault judgment is guaranteed. Through an intelligent switching arbitration mechanism, on the basis of switching probability calculation and confidence evaluation (health degree stability), a secondary confirmation mechanism is matched, and the error switching risk is effectively reduced. Line fault and MCU hardware fault detection is supported, and fault self-healing is achieved. And after the faulted MCU is recovered, the master and standby roles are automatically returned, so that the manual operation and maintenance cost is reduced.

The invention relates to the technical field of fault diagnosis, in particular to a zero-sample speed reducer composite fault diagnosis method based on fast spectral kurtosis, which comprises the following steps: arranging multiple types of sensors at the output and input ends of a fault speed reducer, and collecting data according to a preset sampling frequency; the collected real-time signals are processed into one-dimensional time domain signals, the one-dimensional time domain signals are converted into an actual spectral kurtosis graph after accuracy and integrity analysis and adjustment, a single fault feature set is constructed by combining real-time temperature values and pressure values, and single fault categories are obtained through classification by using a clustering algorithm; dividing samples under a single fault category to construct a diagnosis model, performing combined simulation on the single fault category to construct a composite fault sample set and labeling, performing preliminary diagnosis by the diagnosis model to obtain an initial result, finally determining a final diagnosis result according to the initial result and a composite fault inference rule, evaluating a classification recognition effect, and adjusting a preset sampling frequency according to the final diagnosis result. Therefore, the accuracy of a fault diagnosis result is improved.

The invention discloses a channel environment measured data traveling wave fault distance measurement method, which belongs to the technical field of channel environment traveling wave fault distance measurement, and comprises the following steps of: 1, screening traveling wave fault recording data; step 2, calibrating a traveling wave head; step 3, carrying out power transmission line traveling wave fault distance measurement; and step 4, optimizing the traveling wave distance measurement device. According to the method, fractal dimensions and transient energy are used as feature vectors, a small number of known category historical samples are introduced as prompts, partial supervision clustering is formed, the fault membership degree of weak faults is improved, and blindness of clustering number and initial value selection is avoided. The continuity of a single fault event action and the tightness in time are considered, the time neighborhood constraint is added in the clustering process, and the detection capability of small-fault-angle faults and high-resistance faults far away from a clustering center recognition sample is enhanced. Interference waves are eliminated according to the length and slope characteristics, and reliable calibration of the wave head is achieved.

The embodiment of the invention provides a fault prediction method and electronic equipment, and the method comprises the steps: forming a dominant failure factor group through a basic data set of target equipment in combination with a fault tree and failure analysis data; a hidden failure factor is formed through calculation of the minimum support degree and the confidence degree; combining the weight coefficient of the dominant failure factor of the fault point and the confidence coefficient of the recessive failure factor, analyzing the contribution degree of each failure factor to the fault by utilizing sensitivity, and forming a knowledge base; searching layer by layer and establishing a frequent item set; quantizing confidence coefficients between bottom layer single faults and between the bottom layer faults and the upper layer faults to form an equipment twin fault data model; and through neural network training, a prediction result is obtained through re-fusion of an evidence theory. According to the method, real-time fault prediction is realized, deep mining analysis of historical data is enhanced, the equipment model fault baseline data quality is perfected, the weight between a monitoring point and a failure factor is optimized, and the prediction efficiency and precision are effectively improved.

The present invention discloses a rolling bearing composite fault diagnosis method based on deep graph convolution, comprising the following steps: first, collecting the vibration signal of the bearing and dividing it into sub-samples; second, forming a graph sample from each sub-sample; finally, extracting the features of the graph using a deep graph convolution (DGCN) model to achieve rapid classification of composite faults. The DGCN model can achieve an end-to-end diagnosis mode, eliminating the complex feature engineering in traditional diagnosis methods. The graph constructed using vertices and edges can provide more information for the training of the diagnosis model. Experimental results show that this method has great advantages in the composite faults of rolling bearings under the same working condition, different working conditions and sample imbalance. In view of the problem that the high correlation between composite faults and single fault samples can easily cause classification errors, this method can effectively avoid the misclassification between single faults and composite faults.

The present invention discloses a harmonic reducer fault diagnosis method based on multi-source heterogeneous data fusion, which relates to the field of collaborative robot joint fault diagnosis. In order to solve the problem of low diagnosis rate of existing harmonic reducer fault diagnosis methods, the present invention designs a harmonic reducer fault diagnosis method based on multi-source heterogeneous data fusion. By collecting the original data of multiple sensors such as vibration, torque and temperature of the harmonic reducer under different fault modes, the one-dimensional time domain signals of multiple sensors are converted into two-dimensional time-frequency images through continuous wavelet transform, and a fault feature time-frequency diagram dataset of the harmonic reducer is constructed. Feature selection and noise suppression are performed through the residual shrinkage unit in the DRSN-SE algorithm, and the feature representation capability is enhanced by the SE-Net attention mechanism. The features of multi-source heterogeneous data are fused to obtain the final fused features and output the fault diagnosis results through the classification head. The present invention can effectively solve the problem of poor reliability of single fault data and realize high-precision fault diagnosis and classification identification of harmonic reducers.

The embodiment of the invention provides a fault diagnosis method and circuit of a memory, electronic equipment and a readable medium, and relates to the technical field of integrated circuits, in the method, a test circuit sequentially executes data comparison operation on tested units in the memory according to data comparison operation corresponding to a preset test algorithm. After one-time data comparison operation is executed, a fault capturing circuit generates a single-time fault characteristic value corresponding to target comparison operation under the condition that a comparison result represents that the detected unit has a fault; the target comparison operation is a data comparison operation that the comparison result represents that the tested unit has a fault, and the single fault feature value is used for representing identification information of the target comparison operation; and after all data comparison operations corresponding to the preset test algorithm are executed, identifying the fault type of the tested unit based on all the single fault feature values. Therefore, the fault type of the tested unit can be identified based on all the single fault characteristic values, and then the fault type is determined.

The application provides a power distribution network fault disposal simulation training evaluation method based on a seven-layer track node tracking array. First, the simulation training operation result information of seven links, such as a sensing node, in the fault disposal process of a dispatcher is described by establishing a seven-layer track node tracking array model. Then, the fault disposal process of the dispatcher is quantitatively evaluated by establishing a sensing node evaluation index. Secondly, the whole process from the sensing node to the archiving node of the dispatcher in disposing a certain fault is evaluated by establishing a single fault disposal evaluation index. Finally, the comprehensive evaluation of all fault disposal conditions in the simulation training of the dispatcher is performed by establishing a power distribution network fault disposal simulation training comprehensive evaluation index. The scheme can comprehensively reflect the fault disposal process of the dispatcher, better reflect the fault disposal level of the dispatcher, the method is simple and reliable, can meet the field application requirements, and has good popularization value.

This invention discloses a method for identifying multiple fault sources in a cascaded H-bridge inverter. The method involves acquiring real-time time series data from the inverter online; generating a real-time system residual function representing system deviations using a physical information health system operator dynamically weighted by the operating state vector; and decomposing the residual function using a three-layer cascade operator decomposition architecture that accounts for physical topology constraints to identify single faults and coupled effects. This method is adaptive to dynamic operating conditions, effectively suppresses spurious residuals, and accurately decouples concurrent faults, significantly improving diagnostic accuracy and robustness.

The present invention provides a method and system for determining the root cause of large wind turbine faults. The method comprises the following steps: obtaining initialization information for a large wind turbine generator set from wind turbine configuration data; initializing a single fault map and fault spectrum corresponding to the wind turbine model using real-time and historical wind turbine data; obtaining wind turbine information at the instant of a wind turbine fault; inputting the wind turbine information into a database, and determining the first fault of the wind turbine using a fault spectrum and a fault root cause identification algorithm; if the fault spectrum and the fault root cause identification algorithm cannot identify the fault, prompting the user to manually determine the first fault through an expert system; after the fault is resolved, the expert system, combined with on-site operation and maintenance, completes the determination, stores the result in the database, and updates the fault spectrum. The system comprises a database, an inference engine unit, and a fault spectrum unit. This system can automatically and accurately determine the first fault of a large wind turbine generator set, safely and efficiently.

The present application relates to the technical field of fault prediction and computer big data processing, and particularly relates to a generalized zero-shot composite fault diagnosis method, device and system based on counterfactual reasoning. The generalized zero-shot composite fault diagnosis method based on counterfactual reasoning proposed by the present application constructs a two-stage generalized zero-shot composite fault diagnosis model based on counterfactual reasoning. The model firstly points out the internal causal components of fault data from the perspective of causality theory, and then constructs a structural causal model to describe the decoupling and generation of fault features under the guidance of counterfactual reasoning. On this basis, the model improves the generative model by strengthening the discriminator in the first stage to realize the binary classification of single fault and composite fault. In the second stage, the supervised training of the classifier is used to predict the single fault category, and a traditional zero-shot learning method is designed to classify the composite fault. The present application greatly improves the diagnosis accuracy of the model and solves the problem of model diagnosis deviation on visible and invisible classes.