279 results about "Fault occurrence" patented technology

A method, system, and readable storage medium for fault line selection in distribution networks is provided. The method includes: obtaining the zero-sequence current of each feeder and the zero-sequence voltage of the busbar within a preset time window after a fault occurs; using these to process the feeder's short-time window zero-sequence instantaneous power curve cluster in the distribution network through KPCA (Kernel Principal Component Analysis) for dimensionality reduction, determining the principal component scores; and performing BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) clustering based on these scores to identify whether a feeder is faulted. This clustering process allows for precise and rapid identification of the faulted feeder, even when the current is small, improving detection accuracy. This solves the problem of quickly identifying the faulted feeder in a small current grounding distribution network during single-phase grounding faults.

The invention provides a circuit board electrical performance test and diagnosis method, which comprises the following steps of: constructing a structured process-electrical data set by collecting process parameters such as etching time, pressing temperature, drilling precision, copper foil thickness and the like and electrical test indexes such as impedance deviation, leakage current, signal attenuation and the like; screening key process variables by adopting mutual information analysis and a maximum correlation-minimum redundancy criterion; through modeling of a three-layer causal diagram and a structural equation, quantitative influence evaluation of process parameters on electrical performance and fault types is realized; when a fault is detected, the system can automatically perform reverse reasoning, identify a main manufacturing deviation item and generate attribution diagnosis and process optimization suggestions, so that the accuracy of fault diagnosis and the pertinence of process adjustment are improved, and the fault occurrence rate is reduced and the product quality is improved.

The invention relates to the field of high-voltage cable fault diagnosis, and discloses a high-voltage cable insulation fault intelligent diagnosis method and system based on multi-information fusion, and the method comprises the following steps: S1, obtaining the operation multi-source data of a high-voltage cable, and constructing a multi-source original data matrix; s2, preprocessing to obtain a time-space aligned standardized data matrix; s3, performing feature extraction to obtain a multi-dimensional feature vector, and learning internal association between features by using a multi-modal deep network to obtain a joint multi-modal feature; s4, constructing a fault type identification model based on Bayesian reasoning and Monte Carlo sampling, and obtaining a fault type classification result; s5, in combination with deep learning and a physical model, obtaining a fault occurrence interval, positioning information and a fault level; and S6, based on a fault type classification result, a fault occurrence interval and positioning information, obtaining a fault level, and carrying out early warning pushing on a generated diagnosis report. According to the invention, high-precision identification, positioning and risk assessment of high-voltage cable insulation faults are realized.

The invention discloses an electrical pipeline fault early warning method and system, and relates to the technical field of electrical pipelines, and the method comprises the steps: collecting electrical pipeline data, carrying out the preprocessing of the collected data, packaging the processed data, transmitting the packaged data to a central processing unit, analyzing the data, extracting characteristic parameters, and combining a predefined rule base, the method comprises the following steps: carrying out fault feature identification and abnormity determination, matching a fault mode based on identification features, evaluating a fault type and a severity degree, predicting a fault probability in combination with a historical data trend, automatically generating an early warning message when real-time data exceeds a preset threshold value, sending structured early warning information through a multi-mode communication channel, and tracking and confirming a state. And triggering preset emergency operation, and meanwhile, providing a manual intervention interface and recording a processing process. By monitoring the parameters of the electrical pipeline in real time and triggering an early warning mechanism, the safety problem is identified and processed before the fault occurs, the downtime is reduced, the reliability of the pipeline is improved, and preventive maintenance is realized so as to reduce the emergency maintenance cost.

The invention discloses a fault detection method and a fault detection device for an accelerometer of a downhole tool. Taking an accelerometer and a gyroscope as state quantities, establishing a generalized nonlinear system for the downhole tool sensor model, and performing linearization processing to obtain a generalized linear variable parameter system; based on a T-N-L observer architecture, constructing a system state estimation error equation and a residual error generation equation, establishing a fault sensitivity and interference robustness evaluation system on the basis of the system state estimation error equation and the residual error generation equation, and determining observer parameters; and the sensor obtains a system state value, an estimated value is obtained through the observer, a residual value of a current system state quantity is calculated to judge an occurrence event, and a threshold value of sensor fault occurrence under the current event is calculated to judge a fault occurrence condition. A nonlinear model is adopted, the system dynamic state is described more accurately, the model is linearized, it is guaranteed that the model and the actual working condition have the high matching degree, and meanwhile a corresponding linear variable parameter system is obtained to reduce the calculated amount.

The invention discloses an automatic debugging and fault diagnosis system, which relates to the field of automatic equipment maintenance and comprises a data acquisition and preprocessing module, a chaotic feature analysis module, a fault mode identification and prediction module, a debugging and diagnosis execution module and a system management and interaction module. The chaos phenomenon in equipment operation data is deeply analyzed through the chaos feature analysis module, whether the equipment operation state is in a chaos state or not and the chaos degree are accurately judged by using chaos feature parameters such as a Lyapunov index, fractal dimension and correlation dimension, and the fault mode identification and prediction module is combined, so that the fault detection accuracy is improved. The system can recognize a potential intermittent fault mode in advance, predict the fault occurrence time and probability and send out an early warning signal, the fault diagnosis method based on the chaos theory remarkably improves the accuracy and timeliness of fault diagnosis, workers are helped to take preventive maintenance measures in time, the non-planned downtime is shortened, and the fault diagnosis efficiency is improved. The production efficiency is improved.

The invention discloses an automatic fault repairing method for an operating system based on artificial intelligence, and relates to the technical field of automatic fault repairing, and the method comprises the steps: carrying out the feature analysis of system operation data through a pre-trained fault feature extraction model, generating a fault feature vector, inputting the fault feature vector into a fault classifier, and obtaining a fault feature vector; a current fault type is identified through a multi-classification algorithm, fault cause primary tracing is performed according to the fault type to obtain a fault generation factor, secondary tracing is performed on the fault generation factor to obtain a fault influence factor, positioning is performed based on the fault generation factor, and a corresponding repair strategy is matched from a knowledge base. The method comprises the following steps: acquiring historical system operation data with relevance on the basis of a fault influence factor, acquiring updated real-time system operation data after executing a repair operation to calculate a system optimization coefficient, judging a forward trend of a repair strategy according to a preset optimization threshold value, and updating the forward trend into a knowledge base to realize rapid and efficient automatic repair.

Disclosed is a method for predicting faults in an electric grid, the method comprising: detecting one or more events (102) that are precursors of one or more faults in the electric grid, the detection is based parameters associated with signals propagating in the electric grid or radiation produced by components in the electric grid; determining one or more locations (104), in the electric grid where the one or more events are detected, the determination is based on one or more of: a pattern of detection of the one or more events, weather conditions, traveling wave analysis, or location-specific sensor measurements; and generating an alert (100) that includes the one or more events, the one or more locations, and one or more components (106) of the electric grid in which the one or more events are detected, the alert corresponds to predictions of occurrences of the one or more faults.

The invention discloses a fault detection method, a chip, a storage medium and an electronic device, and relates to the technical field of computers, and the method comprises the steps: carrying out the edge detection of a pulse signal received from a fault counting pin of a processor, and when the pulse signal is detected to be at a first edge of a first level, carrying out the detection; and the number of the received pulse signals at the first level is accumulated, so that the fault occurrence frequency can be accurately counted. And then, generating an interrupt signal based on the first edge, and sending the cumulative number of the interrupt signal and the pulse signal to the controller unit, so that the controller unit triggers an interrupt program in time and stores the cumulative number in real time, thereby not only quickly finishing fault processing when a fault is detected, but also storing the cumulative number of the fault in real time, and improving the fault processing efficiency. The fault detection accuracy and the fault processing efficiency are improved, and the technical problem that the fault detection accuracy is low is solved.

The invention discloses a power transmission cable ground fault adaptive diagnosis method and system, and the method comprises the steps: collecting multi-modal data, and carrying out the preprocessing and extraction of the multi-modal data, and forming a statistical feature vector; the method comprises the following steps: adaptively decomposing sheath current data by adopting OVMD, calculating segmented TKEO energy operators, and realizing fault early warning through a ratio criterion of maximum values of TKEO derivatives of adjacent segments; inputting the real-time acquisition time sequence working condition class feature vector into a trained LSTM to obtain a fault probability, dynamically updating a fault probability threshold based on LSTM output, and judging that a fault occurs when the fault probability exceeds a continuous set period of the fault probability threshold; and inputting the statistical class feature vector into ANN, inputting the sheath current data into 1D-CNN for fault classification, and performing adaptive weighted voting integrated decision on the output of the two types of networks to identify the fault type. According to the invention, the problems of low fault detection sensitivity, poor positioning precision, lack of early warning capability and the like in the prior art are solved.

The invention discloses an error reporting method of a processor platform and electronic equipment, and relates to the technical field of computer hardware, and the error reporting method comprises the steps that a plurality of error identifiers of the processor platform are acquired, and the error identifiers are used for representing information of fault types of the processor platform; the prediction model is constructed according to the historical data and the real-time operation parameters, the prediction model can improve the predictive maintenance capability of the processor platform, and then the fault type generated by the processor platform in a period of time in the future is determined according to the error identifier and the prediction model. The technical problem that a processor platform is difficult to warn potential faults in advance in the prior art can be solved, and the technical effects that the fault which is about to occur on the processor platform can be detected in time, then the fault is processed in time according to the prediction result, and the chance of taking preventive measures before the fault occurs is prevented from being missed easily are achieved.

The invention relates to the field of shield tunneling machines, and discloses a fault diagnosis method for a quasi-rectangular shield tunneling machine based on artificial intelligence, and the method comprises the steps: collecting the operation state data of the shield tunneling machine through a sensor array, so as to obtain the operation data of the shield tunneling machine; performing component operation state difference analysis on the operation data of the shield tunneling machine to obtain shield component state difference data; performing abnormal feature distribution density analysis according to the shield part state difference data to obtain abnormal feature distribution density data; according to the method, sensor data collection, state difference analysis and abnormal feature analysis are combined, so that the operation state and the abrasion condition of each part of the shield tunneling machine can be accurately monitored, and the reliability of the shield tunneling machine is improved. A fault prediction model is established through a deep reinforcement learning method, potential faults can be recognized in advance, sudden faults are reduced, and the reliability and safety of equipment are improved.

The application relates to the field of high-voltage cable fault diagnosis, and discloses a high-voltage cable insulation fault intelligent diagnosis method and system based on multi-information fusion, which comprises the following steps: S1: acquiring operation multi-source data of a high-voltage cable, and constructing a multi-source original data matrix; S2: preprocessing to obtain a time-space aligned standardized data matrix; S3: performing feature extraction, acquiring a multi-dimensional feature vector, and learning the internal correlation among features by using a multi-modal deep network to obtain joint multi-modal features; S4: constructing a fault type recognition model based on Bayesian inference and Monte Carlo sampling, and acquiring a fault type classification result; S5: combining deep learning and a physical model to acquire interval and positioning information of fault occurrence and a fault grade; and S6: acquiring the fault grade based on the fault type classification result and the interval and positioning information of fault occurrence, and generating a diagnosis report for early warning pushing. The application realizes high-precision identification, positioning and risk assessment of high-voltage cable insulation faults.

The invention discloses a power distribution network small current grounding fault diagnosis positioning method and system based on edge calculation, and belongs to the field of power system automation, and the method comprises the steps: extracting and recognizing transient features, if a suspected grounding fault is detected, carrying out the multi-source feature fusion analysis through a regional main node, and constructing a transient response time sequence map; a weighted fuzzy clustering algorithm is combined with a multi-channel criterion to determine a fault channel, and a specific fault branch is further positioned through a topology tracking algorithm; introducing a multi-scale wavelet packet energy analysis method into the regional main node, performing energy inversion calculation on the transient current signal under multiple frequency bands, and identifying an energy concentration region near the grounding point through an energy distribution gradient; and constructing a robustness data redundancy model based on the historical data of the edge nodes and the topological relation, and identifying and eliminating abnormal feature data containing noise or distortion. According to the method, transient characteristics are rapidly extracted and preliminary judgment is made after a fault occurs, so that the real-time performance of fault response is greatly improved.

The invention discloses an elevator fault detection method and system based on big data analysis, and relates to the technical field of elevator safety, and the method comprises the following steps: obtaining operation data from various sensors on an elevator in real time, and collecting building access control data at the same time to form multi-modal data; preprocessing the operation data and integrating the operation data according to a timestamp to form a multi-dimensional time sequence data set; the trained time sequence model is used for monitoring multi-modal data collected in real time, the multi-modal data are compared with historical data during normal operation of the elevator, abnormal data are recognized, and potential fault signals are detected; and in combination with the detected abnormal data and the corresponding multi-modal data, fault classification is carried out by using an integrated learning algorithm, the fault type is identified, and the fault occurrence position is positioned. Through multi-modal data collection and long-short-term memory network analysis, accurate recognition and classified positioning of elevator faults are achieved, and the accuracy and intelligence of fault detection are improved.

The invention discloses a distribution line fault detection method and device, equipment and a storage medium, and relates to the technical field of electric power inspection, hidden danger features are extracted through LSTM time sequence analysis, time sequence modeling is performed on current and voltage waveforms, harmonic distortion rate, waveform distortion and other features are extracted, and early abnormality of the equipment can be accurately identified through quantitative analysis of the features, so that the fault detection accuracy is improved. Early warning before a fault is achieved, and the passive situation that an existing system can only conduct positioning after the fault occurs is changed. The fault type is subjected to weighted fusion judgment by using the random forest + SVM algorithm, and the advantages of the two algorithms are integrated, so that the possible misjudgment condition of a single algorithm is greatly reduced, and the accuracy of fault judgment is improved. Secondly, waveform correction is introduced into a traditional double-end positioning formula, local spectrum analysis of edge nodes is combined, traveling wave propagation speed errors are corrected, dependence on clock synchronization of equipment at the two ends is reduced, and the fault positioning precision is improved.

The invention relates to the technical field of supercomputing system operation and maintenance, and discloses a method for resetting an intelligent operating system of a supercomputing system node, which comprises the following steps of: 101, acquiring data of each computing node of a supercomputing system in real time, transmitting the data to a monitoring center through an RDMA (Remote Direct Memory Access) high-speed network for retention to form historical operating data, the historical operation data comprises historical index time sequence data and historical fault label data; 102, a three-dimensional array is generated in the historical operation data through a sliding window method, the three-dimensional array comprises sample information, time information and feature information, and the information in the three-dimensional array is spliced in sequence; and step 103, constructing a fault prediction model, inputting the three-dimensional array into the fault prediction model, and outputting a fault probability by the fault prediction model. According to the method, the fault prediction model is constructed, the node data of the supercomputing system is collected and processed in real time, the fault occurrence probability can be predicted, and an intelligent decision basis is provided for resetting of the supercomputing node operating system.

The invention relates to the field of data processing, in particular to a fault prediction method, device and equipment, a storage medium and a computer program product, and the method comprises the steps: obtaining the current operation and maintenance data of at least one type of Internet data center IDC machine room equipment; generating a fault prediction result based on the current operation and maintenance data and a first prediction model; and determining whether to generate a fault early warning notification based on the fault prediction result and a first preset rule. Fault prediction and judgment are carried out through the prediction model, and when it is predicted that a fault exists, the position where the fault occurs can be judged, and early warning notification is carried out. The fault solving efficiency is effectively improved, and the influence of the fault on services and clients is analyzed.

The invention relates to a computer-aided maintenance method (10) for correcting a fault condition (12) on a processing machine (14, 14a-c), comprising the method steps: a) Detecting (16) the fault condition (12) by identifying an error message (18) on the processing machine (14, 14a-c) and determining the time of the fault; b) Creating (22) a fault description (24) by determining fault data (26) at the time of the fault; c) Identifying (38) similar and / or identical fault conditions (42) by comparing (40) the fault description (24) with stored fault descriptions (42) by comparing the fault data (26) determined for the fault descriptions (24, 42); e) Issuing (50) a recommendation for action (52), including at least one suggestion for remedying the fault condition (12).

The invention discloses a fault diagnosis and self-healing control method, system, equipment and medium for a flexible interconnection device of a power distribution network, and belongs to the technical field of fault diagnosis and control of the power distribution network, and the method comprises the steps: building a system state vector, collecting operation parameters of the power distribution network, and carrying out the weighted fusion; performing quality inspection on the original data based on the acquired operation parameters, and dynamically adjusting model parameters through digital twin synchronization and model parameter updating; deep learning is carried out to carry out multi-level fault feature extraction, and multi-scale feature fusion is carried out; a fault mode identification module is started, and fault probability is calculated for fault classification; evaluating the severity of the fault according to a fault diagnosis result, selecting an optimal control strategy, and carrying out self-healing control; and fault early warning is started to estimate a future fault occurrence probability, and early warning information of different levels is issued to perform preventive maintenance. According to the invention, full-process automation and intelligentization from data perception and intelligent diagnosis to active control and prospective maintenance are realized.

The invention relates to the technical field of equipment fault diagnosis, and particularly discloses a fault diagnosis method and system for water station equipment, and the method comprises an information collection module which collects the operation data information of all equipment of a water station in real time; the data processing module is used for receiving the operation data information of each device and preprocessing the operation data information; the fault diagnosis module is used for comparing the operation data information of each device with the normal operation parameters to judge whether a fault exists or not, and predicting the fault occurrence rate of the corresponding device within a period of time according to the previous data; and the display control module is used for automatically displaying a fault judgment result of the fault diagnosis module when a fault occurs and giving a possible reason. According to the invention, the real-time operation parameters of each device of the water station are collected, the abnormal state of the device is found in time, the fault is quickly responded, the influence of the fault on the operation of the water station is reduced, possible reasons and the fault occurrence rate are given, workers are reminded to overhaul and maintain in time, the overhaul efficiency is improved, and the fault probability is reduced.

The invention relates to an energy storage power supply fault detection method and system and computer equipment. Extracting fault correlation characteristics from the real-time operation data of the energy storage power supply; performing digital twinborn simulation processing based on the real-time operation data, establishing a digital twinborn model, and synchronously mapping the real-time operation data to the digital twinborn model; performing prediction based on the digital twin model to obtain a first fault prediction result; performing fault trend prediction based on a digital twinborn model; calling the current fault diagnosis model to predict and obtain a second fault prediction result based on the fault trend prediction data and the fault correlation characteristics; obtaining a target fault prediction result according to the first fault prediction result and the second fault prediction result; and simulating operation data of the energy storage power supply based on the target fault prediction result through the digital twin model when the multiple types of associated faults occur, obtaining a sample data set corresponding to the multiple types of associated faults, and updating and training the current fault diagnosis model based on the sample data set. The method can improve the fault detection accuracy.

The invention relates to the technical field of power equipment, in particular to a high-voltage cable fault diagnosis method and system. The method comprises the following steps: collecting discharge data in a discharge process of a to-be-detected high-voltage cable, and analyzing fault trend data of the high-voltage cable in a target interval to obtain a trend prediction waveform; the method comprises the following steps: constructing a reference fault-sample waveform signal mapping library through historical discharge data of a to-be-detected high-voltage cable, selecting at least one reference fault from the reference fault-sample waveform signal mapping library to form a fault combination, and superposing sample waveform signals corresponding to the reference faults in the fault combination to obtain a sample waveform signal; obtaining a sample comprehensive signal corresponding to the fault combination; and predicting a potential fault and a possible occurrence time point of the high-voltage cable based on the sample comprehensive signal and the corresponding fault combination. According to the invention, before the fault occurs, the possible fault can be checked in time, and targeted advanced processing is carried out.

The invention provides a fault diagnosis method fusing adaptive wavelet threshold denoising and auto-encoder contribution degree weighting. The method comprises the following steps: carrying out wavelet denoising and standardization processing on training data in a training set based on an adaptive threshold function; using the trained residual error neural network ResNet to extract off-line related features; establishing an MSDAE off-line detection model, taking off-line related features corresponding to a plurality of modes as input for training, and calculating SPE and SPE control limits; acquiring an online test set, extracting online fault related features by using the trained residual neural network ResNet, calculating a Bayesian fusion index BIP according to the online fault related features, and judging whether online data have faults or not; and when a fault occurs, calculating the local linear propagation contribution degree of each process variable in the online data, establishing a contribution heat map, and performing fault diagnosis on the online data according to the contribution heat map. According to the invention, high-frequency noise components can be effectively filtered, and key variables causing process anomalies can be accurately positioned.

The invention discloses an electrical equipment fault prediction method and system based on big data, and relates to the technical field of electrical equipment data management.The electrical equipment fault prediction system comprises an extraction module, a construction module and a prediction module; a hierarchical fault sensitive feature library is built, a prediction model is built in combination with the hierarchical fault sensitive feature library and the correlation degree, the input quantity of the prediction model is feature data, the output quantity of the prediction model is the fault occurrence probability and the fault type of the electrical equipment, and the hierarchical fault sensitive feature library is built by extracting the feature data and combining a health degree quantification result; a long-short-term memory network architecture with three or more hidden layers is adopted, feature priorities are dynamically adjusted according to the load rate and the health degree of the electrical equipment, the sample proportion is controlled, parameters are finely adjusted according to the fault frequency, the fault probability and the fault type are accurately output, reliable operation of the electrical equipment is supported, the cost is reduced, and stable energy supply is achieved.

The invention discloses a GIS latent defect diagnosis method and system based on multi-source signal fusion, and belongs to the field of power equipment fault diagnos.The method comprises the steps that a UWB sensor is adopted to monitor PD signals in a GIS, real-time filtering and spectral analysis are conducted on the signals in combination with an FPGA preprocessing chip, and the sampling sensitivity is dynamically adjusted according to the PD signal strength; gIS internal ultrasonic source three-dimensional imaging is realized by adopting a three-dimensional ultrasonic array; pD and ultrasonic signals are processed based on wavelet transform, PD and ultrasonic data are processed based on CNN, and a signal time sequence is processed by LSTM; constructing a GIS fault knowledge graph, setting expert rules, and calculating a GIS fault occurrence probability by adopting Bayesian reasoning; and predicting a GIS fault evolution path according to the Markov chain model, and performing dynamic adjustment in combination with reinforcement learning. According to the method, the fault state transition model of the GIS equipment is established based on the Markov chain, the evolution probability between different fault states is quantified, long-term steady-state fault risk assessment is provided, and the operation health condition of the GIS equipment can be prejudged.

The invention provides a power distribution network early fault section identification method and system based on multi-dimensional feature probability mapping, and belongs to the technical field of power system power distribution network fault detection. The method comprises the following steps: collecting zero-sequence voltage of a power distribution network bus and zero-sequence current signals of head ends of all feeder lines, and obtaining derivative signals of the zero-sequence voltage and the zero-sequence current signals; calculating the third harmonic energy of the zero-sequence current of each feeder line, and when the third harmonic energy exceeds a set threshold value, judging that the feeder line has an early fault; processing the zero-sequence current signal, and extracting an IMF1 component; calculating a correlation characteristic quantity and a dot product characteristic quantity for each section formed by the current difference values of the adjacent measuring devices based on the IMF1 component; and respectively carrying out standardized transformation on the correlation characteristic quantity and the dot product characteristic quantity, substituting the correlation characteristic quantity and the dot product characteristic quantity into a Laplacian cumulative distribution function, calculating a probability value of a fault in each section, and judging a fault section according to a set probability threshold value. The method can effectively and reliably identify the early fault section of the power distribution network.

The invention discloses a fault tracing method and system based on a double-knowledge graph, a medium and a product, and relates to the field of electric digital data processing, and the method comprises the steps: obtaining a multi-dimensional data source of a to-be-analyzed industrial product, and constructing the double-knowledge graph; receiving a tracing request, and determining a target component node based on the equipment identity identifier and the fault occurrence time window; calculating semantic similarity of entities in the fault description text and the fault knowledge graph, and determining a target fault phenomenon entity; searching a causal association path connecting the target component node and the target fault phenomenon entity, and extracting the entity on the path as a candidate fault root cause set; skipping to a standard knowledge graph through a public mapping center of the product structure tree, and determining compliance parameter thresholds corresponding to the candidate fault root causes; and acquiring actual operation state data, and generating a fault tracing report containing a comparison out-of-limit result. According to the invention, the method can improve the positioning accuracy of the fault root cause of the complex industrial product in the whole life cycle operation and maintenance.

The invention provides an information system fault early warning method and device, electronic equipment and a storage medium, and belongs to the technical field of network operation and maintaining.The method comprises the steps that feature extraction is conducted on target data in real time based on a convolutional neural network, a first feature is obtained, and the target data is obtained by conducting data preprocessing on original data; performing causal relationship reasoning on the target data in real time to obtain a second feature; fusing the first feature and the second feature to obtain a fused feature; the fusion features are input into a Transform encoder, and sequence features output by the Transform encoder are obtained; and determining a system state corresponding to the target data based on the sequence features. According to the method, the causal invariance principle is fused, the complex time sequence information of the data is subjected to causal reasoning analysis, feature expression is optimized, and the fault recognition accuracy is improved; the real-time fault prediction timeliness of the system is high, the system has perspectiveness, and the fault occurrence probability is reduced.

The invention discloses a phase deviation testing method based on a rotation test of a self-aligning rolling bearing, relates to the technical field of bearing detection, and solves the technical problems that potential risks in a normal state are lack of dynamic monitoring, a real-time operation state and a risk level are not combined, and the deviation between a prediction result and the reality is large. According to the method, by analyzing the stability of the periodic offset characteristic and the association rule of the periodic offset characteristic, the rotating speed and the load, an abnormal reason can be directly positioned, a basis is provided for targeted maintenance, blind shutdown and maintenance cost are reduced, and for a bearing in a normal state, the change rate of a key index is calculated in real time by establishing a phase-deviation-free reference database, so that the reliability of the bearing is improved. And comparing with a preset comparison value, so that a potential risk can be found before a fault occurs, precautions are taken in the bud, and a residual life calculation formula is dynamically corrected based on a risk early warning level in combination with a basic rated dynamic load, an actual equivalent dynamic load and a working condition correction coefficient, so that a prediction result is more fit with an actual operation state of equipment.