46results about How to "Predict remaining life" patented technology

The invention provides a prediction method of electric vehicle power battery service life. The method includes the following steps that (1) data collection is conducted on the voltage curve of a power battery in the process of electro-discharge, battery residual life characterization is extracted, and a recession point is gained; (2) clustering is conducted on the collected voltage curve by the adoption of an ART2 neural network, and recession pattern classification is conducted on the voltage curve; (3) predication is conducted on the recession pattern of the power battery by the adoption of a weighted Markov model; (4) a single mode of recession pattern is built; (5) prediction is conducted on the residual service life of the power battery by the adoption of a linear superposition method. By means of the prediction method of electric vehicle power battery service life, the health condition of batteries can be evaluated conveniently, quickly and accurately, the residual service life of the power battery of an electric vehicle can be accurately predicted aiming to individuals according to different driving habits of different people, and the battery can be better managed, planned and used.

The invention relates to a lithium ion battery cycle life prediction technology, in particular, a deep belief network and relevance vector machine fusion-based lithium battery residual life prediction method. An existing lithium battery residual life prediction method relies on accurate physical models or complex signal processing technologies, as a result, the existing lithium battery residual life prediction method needs heavy investment, or the existing method is based on a shallow structures, as a result, the performance of fault prediction will be limited, and the existing method is vulnerable to curse of dimensionality, while with the method of the invention adopted, the problems of the existing method can be solved. A charging and discharging period-based lithium battery capacity degradation data set is obtained; the data are pre-processed; the fusion models of a DBN (deep belief network) and an RVM (relevance vector machine) are built; a DBN model and a RVM model are trained; and the trained fusion models of the DBN and the RVM is adopted to predict the residual life of a lithium battery. The method of the invention is suitable for predicting the residual life of the lithium battery.

As for a multilayer coating system in use or a multilayer coating system sample for carrying out a natural environment test, the invention provides a method for rapidly evaluating a coating critical corrosion damage value on the basis of macroscopic appearance features and electrochemical features according to the characteristic that the corrosion damage degree of a first coating of the multilayer coating system directly affects the protecting performance of the coating system. According to the method, the macroscopic appearance features of the multilayer coating system are detected visually, the electrochemical impedance spectroscopy of a portion which has an aging failure or is seriously damaged is measured, a multilayer coating system physical model and an electrochemical impedance spectroscopy CM equivalent circuit model are established according to the preparation mode of the multilayer coating system and the characteristic that the thickness is large, the capacitance and the resistance of each coating of the multilayer coating system are obtained by carrying out analysis through an electrochemical feature analysis system, and the critical corrosion damage value of the multilayer coating system is rapidly evaluated according to the impedance value of the first coating. The method is simple, data are reliable, and an evaluating result is accurate and practical.

The invention relates to a roller bearing service life predicting model of a self-adaptive multi-kernel combination relevance vector machine. The roller bearing service life predicting model comprises the following steps of utilizing particle filter to initialize a combination kernel function weighting matrix, so as to obtain a combination kernel function set; establishing a multi-kernel combination relevance vector machine set; performing iteration predicting, weight updating and re-sampling self-adaption to obtain an optimal multi-kernel combination relevance vector machine model; finally, predicting the running state and remaining life of the rolling bearing. The roller bearing service life predicting model has the advantages that the excellent characteristics of a plurality of single kernel functions are adaptively integrated, the reliance of the single kernel function relevance vector machine model on the parameters is reduced, the predicting accuracy is improved, the predicting stability is better, the robustness of the model is higher, and the engineering application value is higher.

The invention relates to a power distribution network risk planning method and a system thereof. The method comprises the steps of acquiring original data of the power distribution network and generating an alternative planning scheme; setting the alternative planning scheme to a chromosome, and solving a pre-established power distribution network multi-target optimization planning model by meansof a genetic algorithm for obtaining an optimal power distribution network risk plan; wherein the power distribution network original data comprise a power distribution network health index. Accordingto the method and the system, on one hand, an asset management concept is combined, thereby realizing a more accurate power supply reliability evaluation result, effectively reducing reconstruction and changing cost of the equipment or postponing the reconstruction and changing time of the equipment, and saving investment of the power distribution network; and on the other hand, output uncertainty of distributed energy DER can be settled, thereby effectively promoting conversion of modern power distribution network planning technology from single-target planning to multi-target optimized planning and asset management integrated planning, reducing power grid investment risk and improving economic and social benefit of the power distribution network.

The invention relates to a power cable operation maintenance method based on historical fault information and an operating state, wherein the method is used for predicting the residual life of a power cable and formulating a replacement strategy of the power cable. The method comprises the following steps of establishment of a weibull proportional hazard model, solution to parameters in the weibull proportional hazard model, resolving of a power cable state decision curve, prediction of the residual life of the power cable; and formulation of a maintenance and replacement strategy of the power cable. With the method, reasonability and reliability of cable fault prediction are improved; the operating situation of the cable can be displayed visually and clearly; and a reference can be provided for making a decision of cable maintenance and replacement. A minimum cost method and a maximum availability method are brought forward based on the weibull proportional hazard model; and with consideration of economic factors, a proper strategy of cable maintenance and replacement can be formulated.

The invention relates to a method for vacuum degree measurement and life management of a vacuum arc extinguish chamber, which is based on an expert system in electric grid. The invention comprises anexpert system main module, a residual life predicating module and a life management module, a vacuum degree measurement device by a magnetic control method, and a vacuum degree measurement device by ashielding case potential method, wherein the expert system main module is respectively connected with the residual life predicating module and the life management module, and the vacuum degree measurement device by the magnetic control method and the vacuum degree measurement device by the shielding case potential method. The data measured on line by the vacuum degree measurement device by the magnetic control method and the vacuum degree measurement device by the shielding case potential method is provided to the expert system which provides results and outputs life management information based on a reliability knowledge base of the measured data. In the invention, the vacuum degree in the vacuum arc extinguish chamber can be measured in the power grid, and also the residual life can bepredicated and off-line monitoring can be realized so as to avoid the reduction of reliability coefficient of a powder system due to the access of on-line measurement equipment, thereby meeting the requirement of switch electrical applicance state examination, and realizing the intelligentizing of a vacuum switch.

The invention relates to a method for evaluating the remanufacturing access period of an engineering mechanical arm rest class structure. The method comprises the specific steps of a, formulating an evaluation criteria of a solid web type arm rest failure mode, b, correcting and perfecting a parameterized finite element model and a simulation computing platform, c, setting up the performance under the remanufactured arm rest typical service working condition, namely, a database of the failure form, d, conducting traceability analyzing on the failure form and the main influence factor, and e, predicating the residual service life of an arm rest, and forming the remanufacturing arm rest access period evaluating method. The computer virtual simulation technology is utilized by the method, an expert evaluation system of an arm rest class structure part is set by processing related measured data, and the system is used for evaluating the residual life and the related technical index of the arm rest class structure.

The invention discloses an industrial equipment remaining useful life prediction model and a construction method and application thereof. The method comprises the steps that full-life multi-feature datasets of multiple sets of identical industrial equipment under different fault modes are collected, and a multidimensional matrix of each full-life multi-feature dataset is constructed; a sliding window is adopted to perform time sequence slicing on each multidimensional matrix, and multiple time slice matrixes of each multidimensional matrix are obtained; according to the types of the fault modes, all the time slice matrixes are sorted; and based on all the time slice matrixes corresponding to each fault mode, a CNN-RNN (Convolutional Neural Network-Recurrent Neural Network) hybrid prediction model of each fault mode is trained to obtain the remaining useful life of the industrial equipment. According to the prediction model, by using the sliding window to perform time sequence slicing on multidimensional data, the diversity of hybrid model input is improved; a model base is constructed by use of pre-sorting, and the datasets containing the multiple fault modes are processed to improve the model prediction precision; and by constructing a CNN-RNN hybrid network, the end-to-end remaining useful life prediction model without self-definition of a failure threshold is realized.

The invention discloses an online management method of a numerical control machine tool cutter. The method comprises the steps of firstly establishing a numerical control machine tool cutter online management system, establishing a database in a cutter management server, developing a corresponding functional module interface on a workshop tool magazine terminal, programming a sub-program on the numerical control machine tool according to an adopted numerical control system programming rule, receiving and transmitting information between a machine tool and the cutter management server by the cutter management server through calling a function in a serial-port server, performing processing according to the read program data, rewriting or searching the database, and transmitting the searchedinformation to the corresponding numerical control machine tool. Through networking all machining centers and workshop tool magazine terminals, the online management method has advantages of realizingaccurate recording and searching for cutter information, reducing cutter exchange time, sufficiently utilizing the residual service life of the cutter, saving manpower resource and improving production efficiency.

The invention discloses a method for predicting the service life of a transformer by using multiple parameters. The method comprises the following steps of S1, performing state evaluation on the transformer by using state data of the transformer; S2, constructing an evaluation database by utilizing the historical data of the transformer and the retirement data of the same type of transformer; andS3, predicting the transformer evaluation parameters by using an Elman network prediction method to obtain a predicted residual life. The transformer state data comprises transformer electrical test project data, analysis data of dissolved gas in oil, transformer oil characteristic data and working condition data, wherein the analysis data of the dissolved gas in the oil comprises hydrogen, methane, ethane, ethylene, acetylene, carbon monoxide and carbon dioxide, the transformer oil characteristic data comprises micro-water content, acid value, breakdown voltage and oil dielectric loss. The method can be used for predicting the service life of the transformer, accurately replacing the transformer and guaranteeing healthy operation of the transformer.

The invention discloses a nuclear reactor control rod driving mechanism monitoring and management system and method. The system comprises sensors (1 and 2), a data acquisition module (3), a data storage module (4), a local upper computer (5) and a server computer (6); the local upper computer (4) communicates with an embedded controller, completes data preprocessing and feature value extraction, and stores and manages the data in the two modes of an offline file and a local database; and the server computer (5) communicates with the local upper computer (4), calls standardized signal data entries, and completes characteristic value trend statistics and residual life calculation. A small number of sensors are additionally arranged on the basis of existing maturely-applied rod control rod position and control rod driving mechanism equipment of a nuclear power plant, and a feasible, accurate and reliable state monitoring and health management method and system meeting engineering requirements are provided for four component objects.

The invention provides a lithium ion battery residual life detection method based on relevance vector regression, which comprises the following steps of (1) data feature extraction: extracting the data of the discharge voltage of a lithium battery along with time change according to the charge and discharge data of the lithium battery, and extracting the voltage change time as the data feature according to the voltage change gradient, (2) data feature normalization: carrying out normalization processing on the data, (3) building a model: selecting a Gaussian kernel function according to a relevance vector machine (RVM) algorithm model, building mapping from a data set sample to high-dimensional data, and performing data training to obtain the RVM algorithm model, and (4) prediction: predicting the residual capacity of the lithium battery by using a relevance vector machine (RVM) algorithm model so as to effectively detect the residual life of the battery.

The invention discloses a lithium ion battery residual life prediction method and system. The method comprises the steps of collecting state data of the lithium ion battery; acquiring electric quantity data of the lithium ion battery according to the state data; and inputting the electric quantity data into a pre-trained quantum echo state network to obtain the residual life of the lithium ion battery. The invention further discloses a corresponding system. Through the quantum echo state network, the residual life of the lithium ion battery is effectively predicted, and the method has important significance for guaranteeing safe and reliable operation of equipment.

The invention discloses a residual life prediction method of an electromechanical system based on a dual-time scale particle filter, which comprises the following steps of: a continuous system state space equation is discretized by adopting an Euler discretization method to obtain a discrete system state space equation under the dual-time scale; The state and fault parameters of the system are estimated by using the dual-time-scale particle filter algorithm, and the fault source is identified by the estimated value of the fault parameters; A degradation model of system parameters is predicted,and the residual life of the system is calculated by using the estimated value of the fault parameters and the fault failure threshold. The invention solves the problem that a large amount of computational resources are wasted during the joint estimation of the system state and the fault parameters in the time period when the fault parameters are basically unchanged, improves the efficiency of the fault diagnosis, and guarantees the real-time performance of the residual life prediction.

The invention discloses a life prediction method and system based on the degradation state of a welding spot of an IGBT module. The method comprises the following steps: starting ultrasonic scanning of a welding flux layer of a target IGBT module; determining the cavity condition of each welding spot of the welding flux layer according to the ultrasonic scanning result; determining a level corresponding to a solder layer of the target IGBT module according to the void condition; querying in a preset grade life database to obtain a life standard value corresponding to the grade, and taking the life standard value as a life prediction value of the target IGBT module; and generating a grade life database based on the result of the accelerated aging power module cycle test on the sample IGBT module and storing the life standard value corresponding to the solder layer of each grade. The cavity problem of the solder layer is detected by adopting a simple and easy-to-operate ultrasonic detection technology, so that the residual life of the IGBT module can be efficiently and accurately predicted, the efficiency and rationality of equipment operation and maintenance are improved, and the economic benefits of products are effectively improved.

The invention discloses a method for forecasting the residual service life of a steel-cored aluminum strand overhead conductor, wherein the method is characterized by forecasting the residual service life Nr of the serviced steel-cored aluminum strand overhead conductor under the condition of aeolian vibration based on the final motion simulation test and the cumulative damage criterion of the steel-cored aluminum strand overhead conductor of a laboratory. The method in the invention has important meanings for improving the safety management level of a transmission line of a power supply unit, and improving the running reliability of a power grid.

The invention discloses a transformer insulation life loss calculation method, and belongs to the technical field of transformers. The method comprises two steps of correcting an insulation life agingfactor of the transformer and calculating the insulation life loss of the transformer. The method has the advantages that by monitoring the key data of the running state of the transformer, the insulation life loss can be accurately calculated, and then the remaining life and the overall running state of the transformer are predicted; operation and maintenance personnel are helped to make accurate and efficient decisions in time, customers are helped to arrange product maintenance in a planned mode, the number of products needing to be replaced is accurately provided, and product inventory isreduced; potential hazards are effectively eliminated through timely judgment, downtime is shortened, and power supply is ensured.

The invention provides a predictive maintenance method and system for a high-speed bearing of a wind driven generator, and belongs to the technical field of industrial automation. The predictive maintenance method for the high-speed bearing of the wind driven generator comprises the following steps: collecting vibration data of the high-speed bearing of the wind driven generator, processing the vibration data, fitting an index degradation model according to the processed vibration data, carrying out incremental updating on the index degradation model, and predicting the residual life of the wind power generation high-speed bearing. According to the predictive maintenance method, prediction of the residual life of the high-speed bearing of the wind driven generator without historical numbers in the initial stage of production is achieved, and then predictive maintenance is guided. Moreover, the method provided by the invention can update model parameters on line by utilizing newly acquired data along with the operation of equipment, can predict the residual life of the wind power generation high-speed bearing in real time, and can calculate the confidence coefficient of a predictionresult at the same time.

The invention relates to a buried pipeline service performance evaluation method, a computer readable medium and equipment. A buried pipeline service performance evaluation method comprises the stepsthat S1, a buried pipeline model is constructed in combination with influence variables, and a regression equation of pipeline stress and the influence variables is obtained; s2, constructing a relation curve between influence variables and pipeline stress based on the regression equation; s3, variable measurement data in the actual working condition of the pipeline are measured, and the service life of the pipeline is predicted. According to the method, the built pipeline service performance evaluation model is adopted, the stress of various buried pipelines under multiple diseases and complex service conditions can be directly solved, the contribution percentage of variables contained in an equation to the pipeline stress is calculated, and the residual life of the pipelines is predicted.

The invention discloses a non-linear ultrasonic testing, grading evaluation method for performance degradation of a heat-resistant steel part, which comprises the following steps: manufacturing an initial manual comparison micro sample, obtaining the failure time of a performance degradation acceleration test of the heat-resistant steel part, manufacturing a manual comparison micro sample group for non-linear ultrasonic testing, grading and evaluating, building a nonlinear high-energy ultrasonic testing system, testing ultrasonic nonlinear coefficients of an artificial contrast micro sample group for nonlinear ultrasonic detection grading evaluation, drawing a weighted average ultrasonic nonlinear coefficient-performance degradation damage level reference curve, and performing performance degradation damage level evaluation on the heat-resistant steel part to be detected; predicting the residual life of the heat-resistant steel part to be detected. According to the method, grading evaluation of nonlinear ultrasonic detection of performance degradation of the heat-resistant steel part is realized, the performance degradation degree of the heat-resistant steel part can be measured, the residual life of the detected heat-resistant steel part can be predicted, and the quantitative grading problem of nonlinear ultrasonic detection of the performance degradation of the heat-resistant steel part is solved.

The embodiment of the invention provides a method for predicting the residual life of a dynamic filtering compensator. The method comprises the following steps of: obtaining monitoring data, and preprocessing of the monitoring data; calculating a Spearman correlation coefficient between the monitoring data and the residual life, and setting a threshold value to perform feature screening so as to obtain feature-screened data related to degradation; constructing a mixed attention time convolutional network according to the feature-screened data; and obtaining a prediction model according to the mixed attention time convolutional network, and obtaining residual life data according to the prediction model. The method can effectively improve the prediction efficiency and precision.