Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

32results about How to "Life Prediction is Accurate" patented technology

Optimization design method for storage life of rubber seal ring

The invention discloses an optimization design method for the storage life of a rubber seal ring. The method includes the steps of conducting the aging acceleration test on a rubber test piece under different installation compression ratios and different temperatures to contain a test curve of the deformation rate and the aging time tau of the rubber test piece, determining A, K and / or alpha through the least square method, determining Z and delta E / R through the least square method, calculating the As value, the value (please see the symbol in the specification) and the Ks value under different installation compression ratios and the storage temperature of Ts, and substituting the values into the formula (please see the formula in the specification) to obtain the aging time tau under different installation compression ratios. By considering the rule of influences of compression ratios on the storage life of the rubber seal ring, the prediction of the life of the rubber seal ring is more accurate; the storage life of the rubber seal ring can be prolonged through optimization design, and guidance is provided for the life design of the seal ring.
Owner:CASIC DEFENSE TECH RES & TEST CENT

Self-adaptive filtering method for data of pipeline magnetic flux leakage inner detector

The invention provides a self-adaptive filtering method for data of a pipeline magnetic flux leakage inner detector, and relates to the technical field of fault diagnosis techniques of pipelines. The method comprises the following steps that magnetic flux leakage signals are acquired by the pipeline inner detector, are amplified and stored, and are transformed into the actual digital voltage signals, the digital voltage signals are subjected to baseline correction, and then the abnormal data are searched, eliminated and compensated; the single-channel signal classification are conducted, and different types of signals are subjected to line filtering through corresponding single-channel self-adaptive filtering algorithms; the influence degree of noises between the adjacent channels is compared and analyzed to implement multi-channel equalization on the magnetic flux leakage signals; and the multi-channel signal area classification is conducted, and the different signal areas are subjected to surface filtering through corresponding multi-channel self-adaptive filtering algorithms. According to the method provided by the invention, the predication of the service life of the pipeline is more accurate, the feature is much easier to extract in the fault diagnosis of the pipeline, the filtering effect is more obvious, and the function of rapidly and accurately processing big data is achieved.
Owner:NORTHEASTERN UNIV

Method for predicting service life of key system of rail transit vehicles

The invention discloses a method for predicting the service life of a key system of rail transit vehicles. The method comprises the following steps of firstly, determining the key system of urban rail vehicles, and bringing in a proportional hazard model to carry out service life prediction on the key system; secondly, screening historical overhauling data of the key system to obtain concomitant variable factors, and processing concomitant variables by applying a principal component analysis method so as to obtain a concomitant variable matrix; thirdly, solving a parameter estimation value in the proportional hazard model by adopting a maximum likelihood estimation method and a Newton iteration method; finally, calculating the predicted service life of the key system of the rail transit vehicles by utilizing the obtained proportional hazard model. According to the method disclosed by the invention, the influence of the concomitant variable factors on the service life of the key system of the rail transit vehicles is considered, and the defect that the service life prediction is inaccurate as only system failure is considered in traditional service life prediction is overcome.
Owner:NANJING UNIV OF SCI & TECH

Safety management system for high-speed train braking component

The invention discloses a safety management system for a high-speed train braking component, which comprises a driving data acquisition module, a wear data acquisition module, a time life prediction module and a mileage life prediction module, wherein the driving data acquisition module is used for acquiring driving data of the high-speed train; the wear data acquisition module is used for acquiring wear data w of a braking component on an axle; the time life prediction module is used for acquiring a fitting function T(w) for detection days t and the wear data w through fitting of a least square method, and the detection days t0 when the braking component reaches a wear limit are deduced; and the mileage life prediction module is used for acquiring a fitting function M(w) for a driving mileage m and the wear data w through fitting of the least square method, and the driving mileage m0 when the braking component reaches the wear limit is deduced. Detection data on the braking components corresponding to each high-speed train are unified, service lives of different braking components can be predicted accurately, the maintenance efficiency and the replacement efficiency can be mastered reasonably and effectively, and the driving safety of the high-speed train is improved.
Owner:SOUTHWEST JIAOTONG UNIV

Data processing device of production equipment

To provide a data processing device of production equipment that can generate data usable by an operator or an administrator by performing processing for a collected plurality of types of data. A data processing device includes a reference-data acquiring unit configured to acquire, in production equipment, reference data including information concerning time in which a reference for grouping of data operates, a target-data acquiring unit configured to acquire target data concerning a state of the production equipment detected by detectors provided in the production equipment, and a combined-data generating unit configured to generate, for each group of the reference data, combined data for each group obtained by combining, with the reference data, data detected in the same period of time as an operation period of time of the reference data in the target data.
Owner:JTEKT CORP

Battery life prediction method and system, electronic device and storage medium

The invention discloses a battery life prediction method and system, an electronic device and a storage medium. The method comprises the following steps: acquiring historical data of battery capacity; preprocessing the historical data to obtain principal component data and secondary component data of battery capacity attenuation; inputting the principal component data and the secondary component data into a pre-trained long short-term memory neural network; receiving an output result of the long short-term memory neural network, and processing the output result to obtain an attenuation sequence of the battery capacity; and judging whether the numerical value in the attenuation sequence reaches a preset battery failure threshold value or not so as to predict the residual life of the battery, and inputting historical data and a prediction result into a long-short-term memory neural network for reverse training, so that generalization, long-term and effective prediction of the service life of the battery can be realized.
Owner:SHENZHEN TECH UNIV

System for preparing wire harness production

In preparing a wire harness production, modified wire harness wiring pattern information is generated. The generated information relates to second patterns, in which some parts of a first pattern are altered. Each of the second patterns is simulated for practicality. Where practical, according to the simulation, a first sub-pattern is modified to one of the second sub-patterns to achieve the desired second pattern. Jig arrangement pattern information is generated by applying at least one sub jig arrangement pattern to each of the wire harness path patterns of a standard type vehicle included in wire harness path pattern information. Path decision information is used to select one wire harness path pattern. A jig arrangement pattern selector selects a jig arrangement pattern. A path plan is generated by integrating the modified second sub pattern having the necessary alterations and the selected jig arrangement pattern.
Owner:YAZAKI CORP

Balance control module life prediction method and device based on health indexes

The invention discloses a balance control module service life prediction method and device based on health indexes. The method comprises the following steps: S1, calculating the characteristic value of a balance control module during each action based on the data of the balance control module in each action; S2, constructing a health index model, and determining model parameters based on the characteristic values of balance control module samples; based on the extracted characteristic values, calculating health indexes of the balance control module in each action by adopting the health index model after parameter determination; S3, constructing a life prediction model, and training prediction model parameters based on a health index sequence and a residual service life sequence of the balance control module samples to obtain a trained life prediction model; and S4, inputting a historical health index sequence of a balance control module to be detected into the trained life prediction model, and outputting the remaining service life of the balance control module. The service life of the balance control module can be predicted, and the accuracy is high.
Owner:CENT SOUTH UNIV

Mining lithium battery life prediction method based on grey vector machine and management system

The invention discloses a mining lithium battery life prediction method based on a grey vector machine and a management system. The life prediction method adopts a mining lithium battery capacity as atraining sample to establish a grey RVM regression prediction model; a DGM is built according to the training sample data, a predicted value of the DGM is used as input, the original training sampleis used as output, and an RVM regression prediction model is obtained by training; a DGM(1,1) is adopted to performing capacity short-term prediction, a predicted value is taken as the input of the RVM regression prediction model to obtain a short-term regression prediction result and a prediction probability value of the obtained capacity, a metabolic process is introduced, so that the training sample data are updated; and relevance is analyzed and judged through grey correlation, the RVM model is dynamically updated according to the result so as to obtain a new relevance vector, thereby obtaining a long-term trend prediction result of the method. According to the method, lithium battery monitoring data is acquired in real time, so that the service life prediction precision of the mininglithium battery is more accurate.
Owner:CHINA UNIV OF MINING & TECH

Vibration curve normalized average life prediction method of equipment components

The invention aims to provide a vibration curve normalized average life prediction method of equipment components. The load is normalized, the loading force is comprehensively considered, the use state and the predicted use time of the equipment components are accurately analyzed based on the ambient temperature and humidity, and lubrication. In order to achieve the aim, a rotary machinery system fault diagnosis method based on an adaptive noise reduction algorithm is provided and includes acquiring a trend curve and calculating the average curve of a component, comparing the trend curve with the average curve of the component, and determining the accurate component service life information based on the distance D between the trend curve and the average curve of the component on a specific time point. Therefore, the root cause of the component fault is obtain through analysis according to the influence factors of the work state and the environmental parameters to the vibration curve.
Owner:CHANGXING SHENGYANG TECH CO LTD

Life prediction apparatus

A life prediction apparatus is configured to accurately predict a life of a cable wired at a joint part of a robot. The life prediction apparatus includes a fatigue-level estimation unit for estimating a fatigue level of the cable based on encoder information of an actuator which moves the joint part of the robot, and a life prediction unit for predicting the life of the cable based on a fatigue level of the cable estimated by the fatigue-level estimation unit and an allowable value of the cable.
Owner:FANUC CORP

Method for predicting residual mechanical life of contact system of universal circuit breaker based on deep learning

The invention relates to a method for predicting residual mechanical life of a universal circuit breaker contact system based on deep learning. The method adopts a deep learning method to carry out life prediction research, and comprises the following steps: firstly, proposing a mechanical life prediction vibration signal effective fragment concept; secondly, introducing a VMD algorithm and double thresholds based on short-time energy to automatically calibrate the interval; constructing a multi-channel convolutional auto-encoder network (MCCAE) again, adopting an unsupervised learning mode for training, and extracting effective fragment deep degradation time sequence features; and finally, constructing a long-short term memory (LSTM) neural network, taking the time sequence characteristics as input, adopting a supervised learning training mode, completing the steps of prediction and the like, and effectively completing the prediction of the residual mechanical life of the contact system of the universal circuit breaker.
Owner:HEBEI UNIV OF TECH

Method for predicting service life of structural concrete under erosion of sulfate environment

The invention discloses a method for predicting the service life of structural concrete under sulfate environment erosion, which comprises the following steps: based on the Fick's second law and the law of conservation of mass, solving a sulfate transmission constitutive equation by adopting an alternating implicit finite difference method to meet unconditional convergence conditions, and performing programming and calculating by using MATLAB (Matrix Laboratory) software, and achieving analogue simulation and life prediction of the transmission process of sulfate ion erosion in the concrete. The method is accurate in calculation, high in stability and high in efficiency, and based on the Fick law and the chemical reaction kinetics theory, the diffusion-reaction model of the sulfate ions in the concrete structure with the boundary moving and the calculation method of the erosion product generation amount are achieved.
Owner:SOUTHEAST UNIV

Novel high-reliability slewing bearing service life evaluation method

The invention discloses a novel high-reliability slewing bearing service life evaluation method. The method comprises the following steps of: extracting an effective average value of positive and negative vibration signals in a short time according to a denoised slewing bearing vibration acceleration signal to obtain time-space information data, and determining actual balance position informationof the slewing bearing; determining whether the average value of the positive and negative vibration signals has false fluctuation or not according to the obtained information of the actual balance position, if so, repairing the signal data, and subsequently obtaining two groups of time indexes through adoption of a smooth curve method; and establishing a relationship between the obtained index and the residual service life by utilizing the obtained high-quality time index and the fault index of the slewing bearing through a time and fault index hybrid embedded long-short-term memory network based on the generative adversarial network. According to the method, high-quality sample data are obtained under complex working conditions, the number of samples is increased, the reliability of lifeprediction under the complex working conditions is effectively improved, and the method has a certain application value.
Owner:NANJING UNIV OF TECH +1

System for preparing wire harness production

In a system for preparing a wire harness production, a modified wiring pattern generator generates modified wire harness wiring pattern information related to at least one second pattern in which at least one of parts, electric circuits, and wirings of a first pattern including the parts, the electric circuits, and the wirings of a standard type vehicle is altered. A parts information storage stores parts specification information including specifications of the parts, the electric circuits and the wiring included in the second patterns. A simulator simulates whether each of the second patterns is practical while referring to the parts specification information. A sub wiring pattern modifier modifies at least one of first sub patterns constituting the first pattern to at least one of second sub patterns so as to constitute the second pattern judged as practical by the simulator. A jig arrangement pattern information generator generates jig arrangement pattern information related to jig arrangement patterns prepared by applying at least one sub jig arrangement pattern to each of a plurality of wire harness path patterns of the standard type vehicle included in wire harness path pattern information. Path decision information selects one wire harness path pattern among the plurality of wire harness path patterns. Alternation information indicates at least one of alternation portions altered from the first pattern. A jig arrangement pattern selector selects one jig arrangement pattern corresponding to the selected wire harness path pattern among the plurality of wire harness path patterns. A path plan generator generates a path plan by integrating the modified second sub pattern having the alternation portions which is indicated in the alternation information and the selected jig arrangement pattern.
Owner:YAZAKI CORP

Airport multi-platform multi-device complex system health management method

The invention relates to an airport multi-platform multi-device complex system health management method, which combines nominal values of components for physical modeling, can simply perform physicalmodeling on different components, and can estimate the remaining life of the components in real time according to the change of the environment. Meanwhile, a data modeling mode is used for an automatic switch type device, data models of pull-in time and time of different types of components under different working conditions can be established, accurate service life prediction is carried out, important reference is provided for predictive diagnosis, and the failure rate of an airport electrical system is effectively reduced.
Owner:SHANGHAI JIAO TONG UNIV

Discharge charge amount measuring method and device

The invention provides a discharge charge amount measuring method and a discharge charge amount measuring device, so as to more accurately evaluate service lifetime of a lead wire. The discharge charge amount measuring method includes generating a partial discharge in a sample by applying a voltage from a voltage impressing device connected to the sample, the voltage being higher than a partial discharge inception voltage, continuously measuring and recording terminal voltages of a capacitor connected in series between the sample and a ground at least until a breakdown of the sample occurs by alternately operating at least two data loggers connected to the capacitor at intervals of a predetermined time, calculating an amount of electric charge discharged from the sample and remaining in the capacitor by multiplying a difference in the recorded terminal voltages of the capacitor by a capacitance of the capacitor, and calculating an accumulated discharge amount by accumulating the discharged amount of electric charge at earliest until the breakdown of the sample occurs.
Owner:PROTERIAL LTD

Fastener system capable of monitoring dynamic characteristics of track and monitoring method thereof

The invention relates to the technical field of rail traffic, in particular to a fastener system capable of monitoring dynamic characteristics of a rail and a monitoring method thereof.The fastener system comprises an under-rail elastic cushion, a rigid base plate, an under-plate elastic cushion and a sleeper and further comprises a vibration electric energy conversion device, a plurality of wireless sensing integrated assemblies and a terminal data processing unit; according to the application, the elastic pad is extruded and deformed to cause the dynamic change of the resistance or voltage of the wireless sensing integrated assembly in the elastic pad, and the change electric signal is transmitted to the terminal data processing unit to be processed and analyzed, so that the system integration degree is high; according to the monitoring method, through the wireless intelligent sensing technology, the electric signal data are collected and transmitted in real time through the multiple wireless sensing integrated assemblies along with extrusion deformation of the under-rail elastic cushion and the under-plate elastic cushion, and then the dynamic characteristics and disease phenomena of the rail system are monitored and fed back in real time; dynamic, reliable and accurate big data support and part service life prediction are provided for intelligent operation and maintenance of rail transit.
Owner:GUANGDONG SUNLITE MATERIAL SCI & TECH

Substation relay protection device service life prediction method

The invention relates to a method for predicting the service life of a transformer substation relay protection device. The method comprises the following steps: S1, selecting evaluation indexes, and obtaining the sample data of the corresponding evaluation indexes; s2, quantifying the sample data; s3, establishing a multi-classification support vector machine model; s4, training and optimizing themulti-class support vector machine model by utilizing the quantized sample data; and S5, obtaining evaluation indexes of the relay protection device, inputting the evaluation indexes into the multi-classification support vector machine model, and outputting the predicted life length of the relay protection device by the multi-classification support vector machine model.
Owner:CHENGDU UNIV

A self-adaptive filtering method for pipeline magnetic flux leakage internal detector data

The invention provides a self-adaptive filtering method for data of a pipeline magnetic flux leakage inner detector, and relates to the technical field of fault diagnosis techniques of pipelines. The method comprises the following steps that magnetic flux leakage signals are acquired by the pipeline inner detector, are amplified and stored, and are transformed into the actual digital voltage signals, the digital voltage signals are subjected to baseline correction, and then the abnormal data are searched, eliminated and compensated; the single-channel signal classification are conducted, and different types of signals are subjected to line filtering through corresponding single-channel self-adaptive filtering algorithms; the influence degree of noises between the adjacent channels is compared and analyzed to implement multi-channel equalization on the magnetic flux leakage signals; and the multi-channel signal area classification is conducted, and the different signal areas are subjected to surface filtering through corresponding multi-channel self-adaptive filtering algorithms. According to the method provided by the invention, the predication of the service life of the pipeline is more accurate, the feature is much easier to extract in the fault diagnosis of the pipeline, the filtering effect is more obvious, and the function of rapidly and accurately processing big data is achieved.
Owner:NORTHEASTERN UNIV LIAONING

Water pump remaining service life prediction method and device, equipment and storage medium

The invention provides a water pump remaining service life prediction method and device, equipment and a storage medium, and relates to the technical field of industrial equipment maintenance. The method comprises the steps of collecting vibration information, pressure value information and water pump flow value information of a water pump; performing time-frequency domain information extraction on the vibration information, and constructing a feature set of the water pump; and performing data dimension reduction on the feature set, predicting the feature set after dimension reduction, and determining the remaining service life of the water pump. The invention comprises that various information of the water pump during operation is obtained, and features of the water pump are extracted through a preset prediction model for prediction. Various operation data of the water pump are fully considered, and the prediction result is more accurate. And time-frequency domain information is extracted from vibration information, and input is constructed with water pump inlet and outlet pressure and a water pump fluid flow value, so that service life prediction is more accurate. The accuracy of predicting the residual life of the water pump is guaranteed, maintenance personnel can maintain or replace the water pump conveniently, and the production safety is improved.
Owner:ZHEJIANG COLLEGE OF ZHEJIANG UNIV OF TECHOLOGY

Bearing cross-working-condition fault prediction method based on adversarial transfer learning

PendingCN114722879ALife Prediction is AccurateImproving the Accuracy of Transmission Fault PredictionCharacter and pattern recognitionWind energy generationBall bearingFeature set
The invention discloses a bearing cross-working-condition fault prediction method based on adversarial transfer learning, and the method comprises the steps: setting different working conditions, carrying out the signal collection of a bearing, and obtaining a vibration signal; recognizing the vibration signal based on a continuous abnormal point detection method of peak measurement to obtain a health stage signal and a degradation stage signal; performing preprocessing and fault feature extraction on the degradation stage signal to obtain a fault feature set; inputting the fault feature set into a domain adversarial transfer learning double-branch neural network and carrying out updating training to obtain a prediction model; and obtaining to-be-tested data and inputting the to-be-tested data into the prediction model to obtain a fault prediction result. By using the method, accurate service life prediction of the high-speed shaft ball bearing of the gear box of the large fan under different working conditions is realized, wherein the service life of the high-speed shaft ball bearing faces to actual working condition characteristics. The bearing cross-working-condition fault prediction method based on adversarial transfer learning can be widely applied to the field of engineering part service life prediction.
Owner:SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products