139 results about "Diagnostic algorithms" patented technology

The invention relates to the technical field of motor fault diagnosis, in particular to a motor fault diagnosis algorithm based on multi-sensor fusion, and the algorithm comprises the steps: injecting a step excitation signal into a motor, synchronously collecting the original response waveforms of vibration and current sensors, and calculating the inherent response delay. Establishing a mapping relation library of delay values and current sensor filtering parameters, calling the delay values in real time according to the filtering parameters, performing reverse time offset compensation on a current harmonic signal time sequence, performing time alignment on the two types of data, finally performing cross-domain coupling analysis on the aligned data, extracting vibration pulse peak frequency and current harmonic fluctuation quantity, and determining the vibration pulse peak frequency and the current harmonic fluctuation quantity. Early faults are judged by combining the bearing outer ring fault characteristic frequency band and the load rate dynamic threshold value, graded alarm is generated by tracking characteristics, the problem of fault false judgment and missed judgment caused by sensor data space-time dislocation is solved, and the early fault diagnosis accuracy of the motor is improved.

The invention belongs to the technical field of power monitoring, and discloses a detection method for monitoring the state of a primary and secondary fusion circuit breaker, which comprises the following steps: acquiring state data of the circuit breaker, including electromagnetic waveform data, harmonic response characteristics and temperature distribution gradient; obtaining circuit breaker electric field distribution fingerprints through nonlinear segmented harmonic analysis, constructing a multi-dimensional permeation characteristic matrix, and establishing a micro-scale electrothermal coupling map; performing impedance distortion analysis to obtain a nonlinear region situation table, performing multi-frequency response analysis to obtain a harmonic penetration curve, and constructing a high-frequency harmonic penetration path spectrum; a micro-region diagnosis algorithm is established, nonlinear impedance calibration is carried out, and a multi-level protection instruction sequence is generated; adjusting the operation state of the circuit breaker to obtain a circuit breaker medium steady-state index, and performing risk analysis to obtain a harmonic penetration early warning report; according to the invention, accurate identification and early warning of the abnormal-state area in the circuit breaker are realized, and the safe and stable operation capability of the primary and secondary fusion circuit breaker is improved.

The invention provides a rolling bearing fault diagnosis algorithm based on an improved VMD optimized CNN-GRU neural network. The rolling bearing fault diagnosis algorithm aims at solving the problem that early faults of a rolling bearing are difficult to recognize under complex working conditions. The method comprises the steps of providing an OCSSA algorithm fusing an eagle algorithm and a Cauchy variation strategy, realizing adaptive optimization of VMD parameters, remarkably relieving modal aliasing, and improving signal decomposition precision; according to the method, the CNN-GRU end-to-end deep diagnosis framework is constructed, time-frequency fusion features are automatically extracted, time sequence dependence is modeled, and dependence on artificial features is reduced; the model performance is verified on a CWRU bearing data set, the average recognition accuracy rate reaches 98.67%, compared with a mainstream model, the precision and operation efficiency are obviously improved, and the good generalization ability and engineering application potential are achieved.

The invention belongs to the technical field of battery health detection, and particularly relates to a remote diagnosis and maintenance guiding system for a vehicle battery pack box. The remote diagnosis and maintenance guidance system comprises a data acquisition edge processing module, a multi-mode communication and cache transmission module, a composite fault diagnosis module, a sensor self-calibration and environment compensation module, a cloud big data analysis and model iteration module, a remote maintenance guidance and AR visualization module and a system monitoring module. According to the invention, through multi-mode communication and edge caching, data is ensured not to be lost in an extreme environment; a composite fault is identified through a fusion diagnosis algorithm, and maintenance direction deviation is avoided; according to the invention, a sensor self-calibration and compensation mechanism is provided, false alarms caused by low temperature / high humidity are inhibited, and the accuracy of battery data monitoring is improved.

The invention discloses a transformer substation primary equipment maintenance auxiliary system based on augmented reality, which dynamically associates an equipment three-dimensional model, maintenance regulations and historical maintenance records, and comprises the following steps: firstly, aligning the three-dimensional model of transformer substation primary equipment with physical equipment in real time in a field of view of an AR (Augmented Reality) terminal; the internal structure of the equipment and a highlighted fault area are displayed in a perspective manner, a maintainer can directly see the interior of the equipment and visually check fault points, blind disassembly is avoided, then accurate analysis and fault positioning of the equipment state are realized in combination with a preset intelligent diagnosis algorithm, the abnormal mode of the equipment is quickly identified, the dependence on artificial experience is reduced, the maintenance efficiency is improved, and the maintenance cost is reduced. And finally, according to a specific equipment maintenance type, matching a standardized maintenance regulation, and dynamically superposing maintenance guidance information of corresponding equipment in a view field of the AR terminal, thereby avoiding artificial missing of key steps, improving specific implementation of maintenance work, practically performing the maintenance work according to a standardized operation process, improving maintenance quality, and ensuring comprehensive maintenance.

The invention provides a power dispatching data asset full life cycle management method and system. The method comprises the following steps: firstly, collecting power grid real-time operation basic data, calculating a power grid risk grade by means of a power grid risk assessment model, formulating a matching collection strategy according to the grade, and collecting to obtain initial data assets; recognizing and processing abnormal data through a collaborative quality diagnosis algorithm in combination with the real-time state of the power grid, and screening effective data assets; and inputting into a power dispatching decision algorithm, and fusing risks and constraints to generate a power dispatching scheme. And then comprehensively evaluating the scheme by using the data asset utility index, analyzing and determining contribution data assets with remarkable scheduling contribution, and finally dynamically adjusting acquisition and decision algorithm parameters according to an evaluation result and the contribution data assets. According to the invention, full-process collaborative management and control of power dispatching data assets are realized, and the data utilization rate and the scientificity and reliability of dispatching decision are improved.

The invention discloses a hydropower station on-duty emergency processing method, system, equipment and medium based on a knowledge graph, and belongs to the technical field of hydropower station emergency processing, and the method comprises the steps: collecting the operation parameter data and historical fault information of a hydropower station, and carrying out the digital processing; based on a natural language processing and artificial intelligence training technology, constructing a knowledge graph including fault types, cause analysis and emergency disposal measures; establishing an intelligent fault diagnosis algorithm based on a knowledge graph, and carrying out fault identification and positioning on the operation data of the hydropower station; performing classification and priority ranking on the faults according to the identified fault result, and matching a corresponding processing flow; and according to the fault classification information, an emergency plan is started, a control instruction is executed to complete emergency processing operation, and recording is carried out. According to the invention, real-time sensing of the operation state of the hydropower station, accurate fault identification and priority classification are realized, and the response speed and processing accuracy of the hydropower station to emergencies are effectively improved.

The invention discloses a state monitoring method for a two-way liquid cooling energy storage system, and belongs to the field of energy storage system monitoring. According to the method, the problem that the system state is difficult to accurately monitor in real time in the prior art is solved, the detailed operation state of the system can be mastered in real time through comprehensive data acquisition, the data quality is improved through filtering, denoising and normalization operation in the data processing link, a foundation can be laid for subsequent accurate evaluation, and the system reliability is improved. Potential faults can be found in time through state evaluation and abnormal early warning links, fault positions and reasons are accurately positioned in combination with a fault diagnosis algorithm, the maintenance time is effectively shortened, fault risks are reduced, system operation parameters are automatically adjusted according to evaluation and diagnosis results in an operation optimization link, and the system reliability is improved. And the cooling liquid flow, the temperature and the battery charging and discharging strategy are optimized, so that efficient and safe operation of the two-way liquid cooling energy storage system is guaranteed.

The subject matter of the present invention includes a fully automatic, early detection fire suppression method. The fire suppression method implements MEMS technology combined with artificial intelligence (AI) and machine learning (ML). The fire suppression method includes real-time monitoring, fire detection sensors, and diagnostics algorithms. A uniquely integrated application of technologies provides for distinguishing between safe and dangerously destructive fire events and the instantaneous extinguishing of a dangerous fire at its inception.

A system and method for distinguishing the type of seizures in a human patient, such as an epileptic seizure (ES), or a functional or dissociative seizure (FDS). The system and method use a diagnostic analytical platform that gets heart rate variability (HRV) analytical metrics from a ECG and uses an analytical diagnostic algorithm to determine if an ES or FDS has occurred in the patient. The diagnostic analytical platform can create a model for distinguishing that a predetermined type of seizure has occurred from the HRV analytical metrics.

The invention discloses a historical building repairing method and system based on multi-source data fusion and AI diagnosis, and belongs to the technical field of historic building repairing. According to the method, the multi-source data of the historical building are integrated, the digital twinborn model of the historical building is constructed, defect identification and state evaluation are performed on the digital twinborn model based on the AI diagnosis algorithm, the repairing scheme of the historical building is generated, the repairing effect is fed back in real time through the digital twinborn model, the multi-source data cover full dimensions, and the repairing efficiency is improved. The model restores details of building components and can simulate structural deformation under the load effect and material attenuation caused by the environment, real-time data mapping enables the model to synchronously reflect the state of a solid building, defect danger coefficients are calculated through multi-parameter fusion, the types and positions of defects such as structural deformation and material degradation can be automatically recognized for generation of differentiated repairing schemes, and the method has the advantages of being high in practicability and easy to popularize. Hidden defects are prevented from being missed in manual detection, risk quantification is achieved by combining defect danger coefficients with weight distribution, and the generated scheme better fits the actual defect condition of historical buildings.

According to the coal mill health monitoring, fault early warning and fault diagnosis method and device, comprehensive monitoring of the running state of the coal mill and early fault early warning are achieved through combination of multi-parameter real-time monitoring and an intelligent diagnosis algorithm, various parameters such as vibration, temperature and pressure are collected, and the coal mill health monitoring, fault early warning and fault diagnosis method and device are obtained through spectral analysis and rule judgment. Various fault types such as oil system faults, bearing faults and grinding piece faults are accurately recognized, targeted processing suggestions are provided, and the operation reliability and maintenance efficiency of the coal mill are remarkably improved.

The invention discloses an intelligent diagnosis report generation system for an electrochemical energy storage lithium iron phosphate battery, and relates to the technical field of battery management, and the system comprises a traditional integrated hardware platform which is used for collecting real-time operation data monitored by a sensor; the intelligent diagnosis algorithm module is used for scoring the consistency, reliability and safety of the system, and performing integration in a weighted average mode according to the consistency, reliability and safety scores to obtain a comprehensive health score of the system; and the diagnosis report generation module is used for obtaining a system health comprehensive score by summarizing the scores of the ten key indexes, and presenting an index diagnosis level according to the system health comprehensive score. According to the method, the problems of inaccurate battery health assessment, low efficiency of fault diagnosis and inaccurate safety state assessment are solved, and the operation performance and safety of the energy storage system are enhanced while the user experience is improved through display in the form of a diagnosis report.

A method and system for diagnosing an idiopathic psychosis patient and improving treatment targeting for that patient. Cognitive performance is measured on the patient. Pro- and anti-saccade signals are measured on the patient. Motor inhibition is measured on the patient. EEG signals are measured on the patient. Principal components analysis is applied to the measured signals and scales to determine the most significant features. The patient is evaluating on at least 11 dimensions of neuro-cognitive performance. A trained numerical taxonomy approach is used to classify the patient as belonging to a B-SNP psychosis Biotype and the patient's condition is categorized based on the classified Biotype. The B-SNIP psychosis Biotype is used to implement targeted treatment for an individual patient. The diagnostic algorithm is continuously re-trained using new cases and new laboratory tests to improve precision of B-SNIP psychosis Biotypes diagnosis and the accuracy of selecting treatments for individual patients.

The invention relates to the field of electric reactor fault diagnosis, in particular to an electric reactor mechanical fault diagnosis method based on parameter adaptive optimization, which comprises the following steps: preprocessing vibration signals generated when an electric reactor has a mechanical fault through a wavelet threshold denoising method, extracting vibration signal characteristics through Fourier transform and wavelet packet transform, and calculating the mechanical fault of the electric reactor according to the vibration signal characteristics; according to the method, the high-voltage electric reactor is subjected to fault diagnosis, screening is carried out through a random forest method, fault diagnosis is mainly carried out through a convolutional neural network-Transform hybrid model (CNN-Transform), and accurate diagnosis of the fault of the high-voltage electric reactor is realized by utilizing the local and structured feature extraction capability of the CNN model and the global context and long-distance dependency relationship establishment capability of the Transform model. And an improved dung beetle optimization algorithm (MDBO) is introduced, internal parameters of the hybrid model are dynamically adjusted, parameter adaptive optimization is realized, and the diagnosis accuracy is improved.

The invention relates to the technical field of induced draft fan bearing seats, and discloses an induced draft fan high-temperature-resistant bearing seat structure and thermal state monitoring algorithm integrated system which comprises a bearing seat body. Four corner areas of the bearing seat body are respectively provided with a fixing hole used for being fixed with a base, and the center of the bearing seat body is provided with a circular bearing mounting hole; according to the induced draft fan high-temperature-resistant bearing seat structure and thermal state monitoring algorithm integrated system, the annular liquid storage cavity structure provides an optimal measurement point for the temperature sensor while actively dissipating heat, high unification of the heat dissipation efficiency and accurate monitoring is achieved, and secondly, through time sequence correlation analysis of temperature and vibration signals, a multi-parameter fusion diagnosis algorithm is used for diagnosing the heat dissipation efficiency of the bearing seat structure and the thermal state monitoring algorithm. In addition, localization processing is combined with the self-adaptive learning function, the anti-interference performance and long-term stability of the system are enhanced, and meanwhile the maintenance process is simplified through remote parameter configuration.

The invention relates to a planetary gear box fault diagnosis algorithm automatic generation system and method based on a large language model, and the system comprises a large language model generation module which is used for receiving cue words, selecting a parent planetary gear box fault diagnosis algorithm and architecture component knowledge, and combining the characteristics of a planetary gear box fault diagnosis task, calling a large language model to generate a new planetary gearbox fault diagnosis algorithm code; the dynamic code execution and verification module is used for code execution and verification; the architecture evaluator module is used for performing training and performance evaluation; the intelligent evolutionary strategy module is used for analyzing the training history to obtain an analysis result; the program database module is used for storing and managing populations of planetary gearbox fault diagnosis algorithms and constructing cue words; and the evolutionary control engine is used for coordinating and controlling the working process of each module and controlling the number of iterative evolutionary times to realize evolutionary circulation. Compared with the prior art, the method has the advantages of automatic generation, iterative evolution and the like.

The application discloses an out-of-hospital hierarchical diagnosis method based on IBS diseases, and relates to the technical field of medical diagnosis, and comprises the following steps: S1: acquiring multi-dimensional information related to IBS diseases provided by a patient in an out-of-hospital scene; S2: performing standardization preprocessing on the out-of-hospital multi-dimensional information to obtain feature data that can be input into an algorithm model; and S3: inputting the standardization feature data into a preset IBS hierarchical diagnosis algorithm model to output an IBS disease hierarchical diagnosis result of the patient. The out-of-hospital hierarchical diagnosis method based on IBS diseases integrates multi-dimensional out-of-hospital information, eliminates data errors by combining standardization preprocessing, adopts multi-feature screening and model optimization, references the Rome IV diagnostic standard to train the model, simultaneously judges the diagnosis reliability through the confidence, reduces the misdiagnosis and missed diagnosis rate, the model iteration updating mechanism can continuously improve the diagnosis accuracy, and adapts to the change of clinical requirements.

The application discloses a kind of T type three-level converter open-circuit fault diagnosis method with strong robustness, belong to the field of power electronic equipment fault diagnosis, to distinguish different switch similar open-circuit fault characteristics and accurately locate open-circuit fault tube.Considering different modulation strategies and modulation modes, the phase voltage residual is generated through the phase voltage model, so as to extract the fault characteristics of the converter under various open-circuit faults.Analyze the influence of factors such as parameter error, dead time and delay time of the system on the phase voltage vector residual, and the adaptive residual vector amplitude threshold based on uncertainty propagation theory.A hierarchical fault diagnosis scheme is proposed, which can locate the group-level open-circuit fault according to the voltage residual vector amplitude and angle, switch the three-level modulation mode of all phases of the converter to two-level mode, to further identify the specific fault switch from the fault group.A reasonable balance between robustness and speed can be achieved, and the complexity and adaptability of the diagnosis algorithm are fully considered.

The present invention discloses a fusion fault diagnosis method based on digital twins, comprising the following steps: (1) establishing a digital twin model of equipment; (2) updating the digital twin model of equipment; (3) running the digital twin model of equipment to simulate the fault operation state of equipment; (4) establishing a random forest fault diagnosis model to output equipment fault classification and fault prediction results; (5) preparing a verification data set, recording and evaluating the performance and indicators of the random forest fault diagnosis model; (6) evaluating the model performance indicators; (7) using a fusion fault diagnosis algorithm, using the optimized fault diagnosis model to correct the output of the digital twin model, and evaluating the model performance indicators; (8) judging whether a drone will fail based on the output results; the present invention can achieve the purpose of real-time detection of the equipment operation state and fault diagnosis of the equipment.

The application provides a real-time diagnosis and life prediction method based on edge computing, and relates to the technical field of extreme charging, which comprises the following steps: collecting electrochemical characteristic data in the process of extreme charging of different types of batteries, extracting electrochemical difference characteristics, and constructing a battery type distinguishing model. Based on the battery type distinguishing model, the influence of dynamic working condition data on battery aging is analyzed to obtain the working condition influence. Based on the current recognition result, the basic health data is calculated by the health diagnosis algorithm, and the current health status is evaluated to obtain the health evaluation data. Based on the health evaluation data, a life prediction model is constructed to predict the current battery life and output the remaining life prediction value. The application improves the accuracy and safety of battery management in the extreme charging scene of electric two-wheeled vehicles, realizes adaptive real-time diagnosis of health status, and considers the influence of working conditions on the remaining life prediction.

The application relates to the technical field of cloud computing, in particular to an intelligent network self-recovery method and system applied to a smart traffic system, which comprises the following steps: data collection, abnormality detection, fault diagnosis, automatic repair and self-learning optimization; the beneficial effects are that the intelligent network self-recovery method and system applied to the smart traffic system can immediately identify abnormal behaviors in the network and respond quickly through real-time monitoring and a quick abnormality detection mechanism, and the time for fault detection and response is greatly reduced; advanced fault diagnosis algorithms, including deep learning and pattern recognition technology, are used, and the system can accurately diagnose various complex faults, including unknown or novel fault modes.

The invention is suitable for the technical field of medical treatment, and provides a medical diagnosis system and method based on an AI application store. The system comprises at least one medical device and an AI application store, wherein the medical device is in communication connection with the AI application store; the medical equipment is provided with an AI application store connection port, and the AI application store connection port is used for sending an AI module downloading instruction received by the medical equipment to an AI application store; the AI application store is provided with an AI module, and the AI module comprises at least one diagnosis module and at least one algorithm module; the diagnosis module is used for automatic diagnosis of medical equipment, and the algorithm module is used for optimizing the diagnosis performance of the diagnosis module; the AI application store sends the corresponding AI module to the medical equipment based on the received AI module downloading instruction; the medical device performs automatic diagnosis based on its received AI module. By adopting the system, the AI module can be flexibly selected or replaced according to actual requirements, so that the flexibility and the accuracy of medical equipment diagnosis are improved.

The invention relates to a detection method of a driving motor for a new energy automobile in the technical field of detection of the driving motor for the new energy automobile. The detection method comprises the following steps: a dynamic excitation step: applying composite dynamic excitation to a detected driving motor; and a follow-up synchronous acquisition step: under the action of the composite dynamic excitation, controlling a detection execution mechanism to move relative to a shell of the detected driving motor according to a preset track, and synchronously acquiring a vibration signal, an acoustic signal and an electrical signal of the detected driving motor. According to the method, through sequential composite excitation and benefit from high efficiency of follow-up synchronous acquisition and rapid reasoning of a fusion diagnosis algorithm, the whole process from excitation to diagnosis report output can be strictly controlled within 90 seconds, and the problem that traditional subentry detection is low in efficiency is fundamentally solved.

The invention discloses a working condition self-adaption-based guide vane connecting rod stress trend diagnosis method, and relates to the technical field of intelligent diagnosis of hydroelectric generating sets, and the method comprises the steps: constructing an optical fiber stress monitoring system, setting an optical fiber grating sensor for a guide vane connecting rod, collecting a stress signal in real time, and collecting operation parameters; the method comprises the following steps: collecting multi-working-condition data within one month of normal operation after overhaul of a unit, calculating a correlation matrix between guide vane connecting rod stress and operation parameters, and establishing a stress working condition self-adaptive analysis model; and calculating a maximum value, a minimum value, an average value and a standard deviation of stress based on rolling statistics, determining a normal range of stress fluctuation, inputting real-time acquired data into a diagnosis algorithm, judging a stress deviation trend according to the reference model, outputting an alarm level, and updating the reference model. According to the method, the accuracy and timeliness of anomaly recognition are improved, the pertinence and the performability of maintenance decision making are enhanced, and the operation safety and the service life management effect of the guide vane connecting rod of the hydraulic unit are improved.

A system for intelligent surveillance of attention and recognition of computer-aided diagnosis system outputs. The system can include an endoscope, a computer-aided diagnostic module, a camera, a memory, and a controller. The endoscope can include an elongated member that can include a distal portion and a process camera attached to the distal portion. The process camera can capture a video stream during a procedure. The computer-aided diagnostic module can be configured to detect an abnormality within the video stream using a diagnostic algorithm and transmit a signal. The controller can be configured to determine a gaze location of the doctor during the procedure using a gaze algorithm, determine whether the doctor looked at the detected abnormality by comparing the signal from the computer-aided diagnostic module and the gaze location of the doctor, and trigger a countermeasure based on determining that the doctor did not look at the detected abnormality.

The invention discloses a lithium iron phosphate battery fault diagnosis algorithm. The algorithm comprises the following steps: collecting an information source data set of lithium iron phosphate battery faults; a genetic algorithm is adopted to search the information source data set, a search result serves as an initial clustering center to be input into a fuzzy C-means clustering algorithm for means clustering, and the clustering number and distance measurement are determined; the expert weight is calculated by using the distance measurement of the trapezoidal fuzzy number, and the attribute weight is calculated by using a deviation maximization method; calculating positive and negative ideal solutions based on the expert weight; and based on the attribute weights and the positive and negative ideal solutions, calculating group benefits, personal regret values and compromise compromise solutions to obtain a fuzzy fault sequence. According to the method, the genetic algorithm is combined with the FCM, the FCM is prevented from falling into a local minimum value in the iteration process, and finally the search result of the genetic algorithm is used as the initial clustering center of the FCM, so that the fault recognition rate of the algorithm is improved.

The invention relates to the technical field of water turbine maintenance, and particularly discloses a finite element intelligent maintenance scheduling system for a water turbine runner blade. According to the system, a stress-deformation coupling model of a runner blade is established through finite element numerical simulation, and a dynamic damage evaluation model is established in combination with real-time monitoring data; predicting a crack propagation trend by using an intelligent diagnosis algorithm, and generating a hierarchical maintenance decision; through a resource scheduling optimization module, maintenance personnel, spare parts and equipment resources are matched, a scheduling priority queue based on multi-dimensional constraints is established, and dynamic balance of maintenance tasks and resource allocation is realized. The system can effectively improve the crack detection precision, remarkably shorten the non-planned downtime and optimize the spare part inventory turnover rate, and has outstanding economic benefits and engineering application values.

The invention discloses a substation defect scene generation and fusion simulation method and device, and relates to the technical field of substations. The method comprises the following steps: acquiring a substation field image, constructing a time-space association scene library, collecting defect images of historical faults of the substation and defect characteristic parameters of the defect images, constructing a defect working condition traceability association library, obtaining a multi-dimensional defect generation constraint condition, and generating a multi-dimensional defect through an artificial intelligence content generation technology. Generating a transformer substation virtual defect image and virtual defect parameters, performing adaptive fusion on the virtual defect image and the space-time association scene library, constructing a transformer substation defect simulation scene, diagnosing the transformer substation defect simulation scene through a defect scene diagnosis algorithm, and generating scene diagnosis data. According to the method, the substation defect scene can be accurately generated and simulated, the problems of single traditional simulation scene and poor environmental adaptability are solved, the defect that virtual defects lack logic constraints is overcome, the fidelity of the simulation scene is improved, and the scene quality is guaranteed.

The invention discloses an intelligent bearing state monitoring and self-maintenance device based on multi-sensor fusion, and relates to the technical field of industrial equipment state monitoring and fault diagnosis. Comprising a bearing body, a sensing module, a control module and an execution module, the bearing body comprises a bearing inner ring, a bearing outer ring, a rolling body and a retainer; the sensing module is integrated on the outer side face of a bearing outer ring or the inner wall of a bearing mounting hole of a robot joint shell. The control module is packaged in the oil-resistant miniature sealing shell and fixed to the inner wall of the robot joint shell. And the execution module is integrated in the sealing shell and is communicated with the raceway area of the bearing body through a conveying pipeline. A multi-source diagnosis algorithm fusing time domain kurtosis, frequency domain envelope spectrum characteristics and temperature trend is executed through a microprocessing unit, normal vibration fluctuation caused by sudden load change and real abnormity caused by lubrication failure or material stripping are effectively distinguished, and the problems of high false alarm rate and automatic lubricating oil compensation under complex working conditions are solved.