1808 results about "Mechanical devices" patented technology

The invention discloses a mechanical equipment state monitoring method and system based on multiple sensors, and the method comprises the five core steps: multi-modal data collection and preprocessing, dynamic feature fusion, adaptive threshold diagnosis, digital twin fault tracing and predictive maintenance decision. All-domain coverage of equipment is realized through a three-layer sensor network architecture, the problems of data synchronization and interference resistance are solved by utilizing a temperature and vibration integrated sensor, deep fusion and anomaly detection of multi-source data are realized in combination with an attention mechanism, a Gaussian mixture model, a three-dimensional convolutional neural network and the like, and finally a precise maintenance strategy is generated through digital twinning and reinforcement learning. The multi-sensor-based mechanical equipment state monitoring system comprises a sensor network layer, an edge computing layer, a cloud platform layer and a man-machine interaction layer, supports federated learning to protect data privacy, improves real-time diagnosis capability through edge-cloud collaboration, and enhances a reality interface to realize intelligent operation and maintenance interaction.

The invention discloses a signal processing and intelligent algorithm fused main helium fan residual life prediction method, and relates to the technical field of mechanical equipment state monitoring and maintenance management, and the method comprises the steps: collecting equipment operation data through multiple sensors, carrying out the feature fusion through principal component analysis, and achieving the fault mode recognition through a deep learning algorithm; and the residual life of the equipment is predicted by utilizing transfer learning and an XGBoost algorithm, and a diagnosis and prediction model is integrated into an online monitoring system, so that real-time perception and dynamic prediction of the health state of the equipment are realized, and decision support for maintenance and spare part management is provided. According to the method, the accuracy of fault diagnosis and life prediction of the primary helium fan is effectively improved, and a new thought is provided for safe operation and intelligent maintenance of equipment.

The invention relates to the field of mechanical equipment health management, in particular to a large sliding bearing fault detection and evaluation method, device and system. Comprising the following steps: collecting multi-source sensing data, and constructing a comprehensive data set; constructing a state space model based on a sliding bearing physical mechanism; the multi-source sensing data and the state space model are fused through Bayesian filtering, and hidden state parameter posterior distribution is dynamically estimated; generating a virtual fault sample by using a generative adversarial network in combination with a physical rule base; designing a Bayesian space-time sequence diagnosis model based on an attention mechanism, and generating fusion health state features; processing and fusing the health state features by using a degradation process model, and predicting the remaining service life of the bearing; and based on the health state, the fault probability and the remaining service life, setting multi-stage early warning threshold values, and triggering intelligent early warning. According to the method, the defect that a single model is insufficient in adaptability and generalization ability under complex working conditions is overcome, and the accuracy and reliability of fault detection are remarkably improved.

The invention discloses a de-noising diffusion probability model-based semi-supervised intelligent fault diagnosis method and a medium, and the method comprises the steps: collecting a vibration signal sample set of different fault types of mechanical equipment as a training data set which comprises marked and unmarked samples; a semi-supervised intelligent fault diagnosis model containing DDPM, distribution alignment and a mix module is constructed, the DDPM module carries out data enhancement on the training data set, the distribution alignment module predicts a pseudo label for an enhanced unmarked sample, and the mix module combines related samples to generate a new training data set; inputting the new training data set into the diagnosis model, and carrying out iterative training through a minimum comprehensive loss function until an iteration stopping condition is met, so as to obtain a trained diagnosis model; and finally, inputting the vibration signal into the trained intelligent fault diagnosis model to realize fault diagnosis of the mechanical equipment. The number of samples used for training can be effectively increased, the model training effect is improved, and the accuracy and efficiency of fault diagnosis are improved.

The invention relates to the technical field of mechanical equipment state monitoring, in particular to a method and sensor for detecting temperature and vibration data of dynamic equipment, and the method comprises the steps: collecting a temperature signal and a vibration signal of the dynamic equipment, and carrying out the fusion processing, thereby obtaining a fusion feature set; establishing a feature distribution baseline based on a Gaussian mixture model, calculating a relative entropy of the fusion feature set and the feature distribution baseline, and generating a dynamic threshold sequence; constructing a detection model according to the fusion feature set and the dynamic threshold sequence, and outputting to obtain an abnormal mode label; performing time serialization processing on the abnormal mode label, predicting a fault probability in a future time period according to the abnormal mode label subjected to time serialization, and generating a fault prediction result; and performing priority ranking on the fault types in the fault prediction result, and generating a maintenance report according to a priority ranking result. The reliability and practicability of temperature vibration data detection of the dynamic equipment are comprehensively improved, and an efficient solution is provided for health management of the dynamic equipment.

The invention discloses a mechanical fault diagnosis method based on a GCN network and a knowledge graph, and belongs to the field of mechanical equipment fault diagnosis. According to the method, information from different sensors and data sources can be effectively fused by constructing the knowledge graph and combining the GCN network, the problem that the fusion effect is poor when multi-source heterogeneous data is processed through a traditional method is solved, and therefore the accuracy of fault diagnosis is improved; and in combination with the knowledge graph, not only can a fault diagnosis result be given, but also fault reason analysis and maintenance suggestions can be provided, the interpretability of the diagnosis result is enhanced, and the defect that a big data algorithm lacks interpretation capability is overcome.

The invention discloses an auxiliary control system and method for abnormal intervention of a manufacturing and assembling production line, and relates to the technical field of intelligent manufacturing workshop auxiliary equipment and physical execution control of the intelligent manufacturing workshop auxiliary equipment, and the system comprises a multi-dimensional physical state collection unit which is used for generating a multi-dimensional physical state data set; the dynamic mapping and anomaly detection unit is used for detecting an abnormal state in real time; the multi-process linkage intervention unit is used for generating a flexible intervention control instruction; the auxiliary control unit is used for executing an intervention action; and the closed-loop optimization unit is used for constructing feedback comparison and residual attitude error judgment of an intervention action effect and forming a self-adaptive correction closed loop of the auxiliary device. The flexible adaptive capacity and the plug-in mounting stability of the workshop auxiliary mechanical device are enhanced, and the workshop auxiliary mechanical device has the characteristics of non-intrusive mounting, modular expansion, multi-process rapid adaptation and the like, and is particularly suitable for auxiliary control and accurate intervention of various and batch workpieces in a complex assembly scene.

The invention discloses a mechanical fault diagnosis method and device, equipment and a storage medium, and relates to the technical field of mechanical equipment state monitoring, and the method comprises the steps: carrying out the signal collection of target rotating equipment, so as to obtain a target vibration signal, and carrying out the encoding of the target vibration signal through an original signal encoder, obtaining a feature vector corresponding to the target vibration signal; obtaining fault diagnosis information corresponding to the target vibration signal from a preset diagnosis knowledge base according to the feature vector, and generating a spectrum analysis conclusion corresponding to the target vibration signal by using a target large language model and the target vibration signal; generating a fault diagnosis analysis conclusion corresponding to the target rotating equipment by using the fault diagnosis information corresponding to the target vibration signal, the spectrum analysis conclusion and the target large language model; wherein the target large language model is a model obtained by training historical fault diagnosis information based on different types of rotating equipment. By using the large language model and the diagnosis knowledge base, fault diagnosis of multiple devices can be realized.

The present invention belongs to the technical field of signal processing, and particularly relates to a multi-source data fusion fault diagnosis method and system based on the DS evidence theory. The method of the present invention comprises: first, collecting multi-source information of a mechanical device, wherein the multi-source information includes vibration data, image data and sound data; respectively calculating corresponding feature indicators; then, using a PCA algorithm to perform dimensionality reduction processing on the indicators; using a Bayesian fault diagnosis model to perform fault diagnosis, so as to obtain a diagnosis result from each sensor; and then, using the DS evidence theory to perform fault fusion diagnosis. The present invention can comprehensively consider the characteristics of various types of data, extract more effective fault indicators, achieve more comprehensive fault identification, and fuse diagnosis results from a plurality of sensors, thereby ensuring the accuracy of final diagnosis. The present invention is suitable for fault diagnosis of various complex mechanical systems.

The invention relates to a ball mill-oriented integrated digital twinborn model construction method, and belongs to the field of intelligence of mining mechanical equipment. The method comprises the following steps: firstly, constructing a digital twinborn model which comprises a dimension module, a scale module, a scene module and a service module; a digital twinborn model is constructed by taking a dimension module as a reference and embedding a scale module, a scene module and a service module. Thirdly, constructing a multi-sensor information acquisition system, and acquiring actual operation data of the ball mill; and finally, inputting the collected data and the constructed digital twinborn model into a consistency evaluation system, and performing consistency evaluation on the constructed integrated digital twinborn model. And a twinning model support is provided for monitoring the state of the ball mill based on digital twinning. And the current state of the physical entity ball mill is reflected in real time through the state change of the digital twin model in the operation process. And intelligent fault diagnosis of the ball mill is facilitated.

The invention discloses an unmanned aerial vehicle safety scheduling optimization algorithm, and relates to the technical field of storage scheduling, and the algorithm comprises the steps: carrying out the modeling of a storage environment based on the position, shape and size information of goods shelves and mechanical equipment in a warehouse, and building a preliminary environment model; and scanning the environment by using a laser radar carried by the unmanned aerial vehicle to obtain environment data in the warehouse, and updating the environment model in real time in combination with the preliminary environment model. According to the unmanned aerial vehicle safety scheduling optimization algorithm, the accuracy and efficiency of a flight path are remarkably improved through an integrated path planning technology, the optimal flight path is customized for the unmanned aerial vehicle in combination with actual conditions of topography and landform of a storage area and obstacle distribution, redundancy and waste in the flight process are reduced, and meanwhile, the unmanned aerial vehicle safety scheduling optimization algorithm has good application prospects. And the path can be dynamically adjusted according to the real-time environment change to effectively deal with emergencies, so that the flight efficiency and safety are further improved.

The invention discloses a gap-controllable retainer and a frictional resistance measuring method thereof, belongs to the technical field of mechanical equipment manufacturing, and solves the problem that an existing device can only test a retainer with a fixed gap and cannot simulate the influence of dynamic gap change on bearing performance. The retainer capable of controlling the gap comprises a retainer body capable of adjusting the gap between the retainer body and a rolling body, a retainer moving assembly and a gap adjusting part. The gap adjusting part comprises an adjusting motor, an eccentric wheel and a motor fixing frame. According to the retainer capable of controlling the gap, the gap between the retainer and a rolling body can be dynamically adjusted, the retainer can be matched with different types of ball-disc testing machines (rotary type and linear contact type) for friction resistance measurement, the gap between the rolling body and a pocket of the retainer can be flexibly adjusted by adjusting the motor and the eccentric wheel, and the friction resistance of the rolling body is measured. And therefore, the retainer main body can meet the retaining and limiting requirements of different working conditions and different types of bearings, and the performance, the service life and the reliability of the bearings are remarkably improved.

The invention relates to a hydroelectric main shaft all-condition simulation test system and method, and the system comprises a fixed rack, one side of the fixed rack is provided with a tripping starting detection device, the fixed rack is provided with a hollow three-axis platform, a three-axis excitation system and a rotation driving part, the moving end of the three-axis platform is connected with a hollow floating rack, and a bearing is disposed in the floating rack. The rotation driving part comprises a power part and a main shaft connected to the torque output end of the power part, the main shaft is in transmission connection with the rotating disc, a hydroelectric large shaft used for a simulation test is installed on the rotating disc, and the three-shaft excitation system is used for applying X-direction, Y-direction and Z-direction high-frequency sine excitation loads to the hydroelectric large shaft of the rotating disc. The device is used for overcoming the defects that an existing testing device mainly focuses on vibration loading of a static mechanical device, simulation and performance testing cannot be carried out on dynamic behaviors under the composite working conditions of rotation, vibration and impact of a hydroelectric large shaft, and safety testing and rating cannot be carried out on a hydroelectric generating set sensor and a tripper overspeed protection device.

The invention discloses a motor current fault diagnosis method based on a de-noising diffusion probability model, and belongs to the technical field of mechanical equipment state monitoring and fault diagnosis, and the method comprises the steps: obtaining an original motor current signal sample, carrying out the wavelet transformation, obtaining a time-frequency grayscale image, and obtaining a time-frequency grayscale image; dividing the sample into a training sample used for diffusion model training and a test sample of a fault diagnosis model; constructing a diffusion model DDPM, carrying out training by adopting the training sample, and generating a pseudo sample based on the trained diffusion model; constructing a fault diagnosis model MAF-Cnet, and training the MAF-Cnet based on the training sample and the pseudo sample to obtain the trained MAF-Cnet; and inputting a test sample into the trained MAF-Cnet for diagnosis to obtain a motor current fault diagnosis result. The method solves the core problem that the generalization ability of the diagnosis model is insufficient due to scarcity of motor fault samples, improves the diagnosis accuracy, and is wider in application scene.

The invention discloses a vibration signal feature extraction method and system based on signal processing, and relates to the technical field of signal processing, and the method comprises the steps: obtaining a vibration signal of target mechanical equipment, and carrying out the preprocessing of the vibration signal; decomposing the preprocessed vibration signal by adopting multi-scale wavelet transform and frequency domain analysis to obtain time domain, frequency domain and time-frequency domain features; carrying out dimension reduction processing on the extracted feature data by using a deep learning model, and carrying out sequence feature processing on the data after dimension reduction to obtain dimension-reduced feature data; and training a deep learning mode, analyzing the dimension reduction feature data by using the trained deep learning model, identifying abnormality in the vibration signal, and outputting an abnormality monitoring result and fault early warning information. The method can provide reliable fault early warning under different working conditions, and is suitable for on-line monitoring and intelligent operation and maintenance of various mechanical devices.

An adjustable chest compression device that can adjust to accommodate a variety of patient sizes. The chest compression device can include adjustable support legs structured to support the chest compression mechanism at a distance from the base member and adjust to accommodate a patient size. Another adjustable chest compression device can include adjustable legs that can adjust to accommodate different patient sizes, as well as perform the chest compressions using the adjustable legs. An extension, such as a back plate and / or leg extension can be added to a chest compression device to make the chest compression device taller and / or wider to accommodate larger patients.

The invention discloses a remote control crawler-type mower, and relates to the technical field of agriculture and forestry machinery, and the remote control crawler-type mower comprises a machine body, a crawler belt, a front cover plate, an obstacle avoidance protection structure, a modular integrated structure, a height adjustment structure and an operation area expansion structure; the situation that the blade assembly is damaged by low obstacles is avoided, a modular installation mode is adopted, replacement and installation of internal assemblies can be rapidly conducted, the machine adapts to different mechanical devices, the use flexibility of the machine body is expanded, the ground clearance of the working end of the bottom of the mechanical device can be adjusted, and different working requirements are met; meanwhile, the signal tower can be fixed at a remote control signal receiving critical position when needed, and a signal transfer effect is achieved through the signal tower, so that the remote control operation distance and range of the mower are greatly expanded.

1. The name of this design product: electric omnidirectional wheel (double-row wheel set). 2. Purpose of this design product: used for the movement of mechanical equipment. 3. The design key point of this appearance design product lies in the shape. 4. The picture or photo that best illustrates the design points: Stereoscopic diagram 2.

The invention belongs to the technical field of aviation mechanical equipment, and provides aviation monitoring flight equipment and an implementation method thereof. The device comprises a framework, a floating ball arranged in the framework and restrained by the framework, spiral wings symmetrically arranged on the two sides of the framework, a control host arranged at the bottom of the lower end of the framework and a monitoring camera carried at the bottom of the control host, and a mounting table is arranged in the middle of the upper end of the framework; a wind speed and direction sensor and an adjustable mounting frame mechanism are arranged on the mounting table, and a flexible solar cell panel is mounted on the adjustable mounting frame mechanism. According to the unmanned aerial vehicle, the floating balls and the spiral wings adopted by the unmanned aerial vehicle are creatively combined, the floating balls are filled with helium, on one hand, the operation energy consumption of equipment can be reduced through buoyancy of the floating balls, the cruising ability of equipment operation is improved, on the other hand, based on the arrangement of the floating balls, the spiral wings can adopt small wing equipment, and the operation noise is lower.

The invention relates to a self-resetting three-dimensional damping rubber support based on SMA tows and a damping method, and belongs to the field of civil engineering structure damping. The support comprises an upper connecting plate, a lower connecting plate and a shock insulation rubber support, I-shaped sliding rails are fixed to the upper connecting plate and the lower connecting plate respectively, sliding pieces are connected to the sliding rails in a buckled mode, and multidirectional displacement is coordinated through sliding piece connecting rods; the SMA tow system is composed of a fixing rod, a push-pull rod and an annular tow, the two ends of the SMA tow system are anchored to the sliding rail and the connecting rod respectively, and energy consumption and self-resetting are achieved by stretching the tow through a sliding piece. When an earthquake causes horizontal deformation of the support, the SMA tows utilize the hyperelastic hysteretic characteristic to efficiently dissipate energy, automatically recover deformation after the earthquake and drive the sliding piece to reset. According to the invention, the vertical tensile function, the horizontal bidirectional free deformation function and the self-resetting function are integrated, the structure is simplified through the sliding rail-sliding piece module, a complex mechanical device is avoided, and the energy consumption efficiency and the engineering applicability are remarkably improved. And the problems of large residual deformation, poor multidirectional coordination and material fatigue are solved.

The invention relates to the field of mechanical equipment monitoring and intelligent diagnosis, in particular to an equipment real-time fault diagnosis method based on an FPGA and an SNN, and the method comprises the steps: obtaining an original vibration signal, and constructing a local training set; establishing an SNN diagnosis model based on an attention mechanism, and training the model by adopting a local training set; deploying the trained model to an FPGA (Field Programmable Gate Array) end; constructing a mechanical vibration signal real-time acquisition system based on the FPGA; the system obtains real-time vibration data and carries out cross point sliding window preprocessing on the real-time vibration data, the SNN model deployed to the FPGA end carries out reasoning on the preprocessed data, and a diagnosis result is obtained. The pulse neural network model and the FPGA technology are combined, low-energy-consumption and efficient calculation is achieved through edge calculation, the strict requirements for real-time performance and low delay in the industrial environment are met, and the intelligent level of equipment monitoring is effectively improved.

The invention relates to the technical field of industrial digital twinning manufacturing, and discloses an electromechanical equipment state digital twinning driving model based on multi-sensor monitoring, and the model comprises the steps: collecting the original vibration signal data of mechanical equipment through a vibration sensor, and transmitting the original vibration signal data to edge computing equipment for coding; performing clustering on a normal point signal coefficient and an outlier signal coefficient obtained after discrete cosine transform by using a 3 sigma criterion; quantizing a normal point signal coefficient and an outlier signal coefficient corresponding to each vibration sensor by using a selected bit number, then fusing the normal point signal coefficient and the outlier signal coefficient, and carrying out lossless compression on the obtained fusion coefficient; and transmitting the compressed data from the edge computing device to a twin virtual side for decoding, unpacking fusion and quantization inversion. According to the method, the data volume is reduced through discrete cosine transform processing of original data, clustering of discrete cosine transform coefficients, quantitative mapping and coefficient fusion, and the data reconstruction precision is ensured.

The invention belongs to the technical field of intelligent fault diagnosis of mechanical equipment, and discloses a multi-noise robust cross-working-condition migration fault diagnosis method under a time-varying working condition, and the method comprises the following steps: obtaining a signal sample, and carrying out the preprocessing of the signal sample; a correction network module and a domain adaptation network module are established, the correction network module is used for screening clean samples and re-marking and inhibiting feature noise, label noise and mixed noise of the feature noise and the label noise, and the domain adaptation network module is used for feature clustering and cross-working-condition migration diagnosis; establishing a multi-noise robust fault diagnosis training model; performing model training according to the loss function and an optimization algorithm; according to the method, the problem of low fault identification accuracy caused by various noise interferences under the time-varying working condition is solved.

The invention relates to the field of agricultural machinery, in particular to multifunctional tea garden weeding, soil loosening and fertilizing integrated mechanical equipment which comprises a mounting frame, a driving module is mounted at the bottom of the mounting frame, a weeding module, a soil loosening module and a fertilizing module are mounted at the top of the mounting frame, and the weeding module comprises a power part which is fixedly connected with the top of the mounting frame; an output shaft of the power part is connected with a roller, the outer side wall of the roller is fixedly connected with a plurality of wave-shaped blades, the soil loosening module is installed in the roller, and an opening is formed in the side wall of the roller and used for loosening tea garden soil based on the centrifugal force effect; the driving module is in signal connection with a controller, the controller is in signal connection with the power piece and the fertilization module, and the controller is used for adjusting the power of the driving module and the rotating speed and the output power of the power piece according to preset terrain information. The method is used for improving the efficiency of weeding, soil loosening and fertilizing operation of the tea garden and enhancing the collaboration of all operation links.

The invention discloses an active compliance control method for a power transmission line live-line maintenance mechanical device, belongs to the technical field of power detection equipment, and aims to solve the problem that safety accidents are caused by the fact that an existing control method does not fully consider influence of strong wind interference working conditions on movement of the mechanical device. According to the method, the strong wind interference working conditions are accurately divided by establishing a multi-modal dynamic model of a normal working condition model and a plurality of strong wind interference working condition models, model parameters under each working condition are determined in combination with wind tunnel experimental data and kinematics and dynamic characteristics of the mechanical device, behaviors of the mechanical device under different working conditions are accurately described, and the working conditions of the mechanical device are accurately determined. When the mechanical device is interfered by complex and changeable strong wind, a control decision can be made, the accuracy and adaptability of control are greatly improved, the influence of the strong wind on maintenance operation is effectively reduced, and safe interaction between the mechanical device and power transmission line equipment in the maintenance process is guaranteed.

The utility model relates to the field of agricultural mechanical equipment, in particular to an automatic lifting and self-unloading integrated device for an orchard working platform, which comprises a bottom frame, a lifting and overturning driving component, a fixed guide rail and an adjusting track, the adjusting block is provided with a movable guide rail, and when the adjusting block moves on the adjusting rail, the movable guide rail is in butt joint with or separated from the fixed guide rail; the scissor-fork type platform is provided with a hinge part, a supporting part and a sliding connection part, the hinge part is hinged to the bottom frame, the supporting part is connected with the lifting turnover driving assembly, and the sliding connection part is in sliding connection with the fixed guide rail and the movable guide rail. According to the automatic lifting and self-discharging integrated device for the orchard working platform, the operation difficulty and labor intensity of the orchard working platform are reduced, the working efficiency is improved, the automation degree is high, the lifting function and the overturning and self-discharging function of the platform can be rapidly switched, and the discharging precision is high.

The invention relates to the technical field of design and manufacturing of automatic carrying mechanical devices for heavy-load parts on automobile production lines, in particular to an automatic carrying device for heavy-load parts on automobile production lines, which is used for automatically grabbing and transporting large-mass parts on the automobile production lines. Comprising a carrying mechanism and a control mechanism, and the carrying mechanism comprises a carrying machine translation track, a carrying machine lifting air cylinder, a carrying machine body, a rotating device, a clamping jaw telescopic track and a carrying machine clamping jaw; the upper end part of the transporter lifting cylinder is mounted on a rack of the production line, and a running track is arranged on the rack of the production line; the control mechanism is composed of a controller and a hydraulic pipe connecting base. The controller is mounted on the equipment mounting frame; a cable on the controller is connected with the hydraulic pipeline and hydraulic-electric pipeline connecting seat; according to the transporter clamping jaw structure designed by the device, grabbing and transporting of a full-automatic automobile chassis structure are achieved, the defects that in the current automobile manufacturing process, when heavy objects are hoisted by manpower at high frequency, the efficiency is low, and the load is high are overcome, and the production efficiency and the automation degree are greatly improved.

The invention discloses a high PV value polytetrafluoroethylene integral sliding bearing and a preparation method thereof, and the high PV value polytetrafluoroethylene integral sliding bearing is prepared by using polytetrafluoroethylene and fusible polytetrafluoroethylene as polymer matrixes, using sizing modified polytetrafluoroethylene fiber as a main reinforcing component, combining with a lubricating filler, and carrying out low temperature mechanical blending, bidirectional pressing and sinter molding processes. According to the invention, the fusible polytetrafluoroethylene is introduced to modify polytetrafluoroethylene, and the creep resistance and wear resistance of the composite material are improved by constructing a polymer alloy; the polytetrafluoroethylene fiber sized and modified by the heat-conducting filler is used as a main reinforcing filler, so that the heat-conducting property and the bearing capacity of the composite material are improved, and the reduction of strength and toughness caused by introduction of a large amount of high-modulus inorganic filler is avoided. The composite bearing has the advantages of high bearing capacity, high heat conductivity, high strength, high flexibility and excellent friction and wear performance, particularly has a relatively high PV value, and can be applied to transmission parts of mechanical devices in many industries such as chemical engineering, automobiles, pharmacy, food and the like.

The invention discloses a bearing life prediction method based on data feature optimization and deep learning, and the method comprises the steps: collecting vibration signals of a bearing in different states, carrying out the processing of the signals through MEMD-DisEn, and decomposing the signals into an intrinsic mode function, so as to reveal the features of a bearing fault; expanding fault sample data by using a WGAN-GP strategy so as to improve the processing capability of the model on abnormal samples and enhance the prediction accuracy; a TimeKAN model is applied to analyze the enhanced data, large-scale time series data are processed, a long-term dependency relationship in the data is captured, and the remaining service life of the bearing is accurately predicted; an escape optimization algorithm is improved, and hyper-parameters of the TimeKAN model are optimized through the improved escape optimization algorithm, so that the distinguishing capability and the response speed of the model are improved. The method can effectively improve the prediction accuracy and robustness, and is of great significance to the maintenance and safety production of mechanical equipment.