CN104021238A - Lead-acid power battery system fault diagnosis method - Google Patents
Lead-acid power battery system fault diagnosis method Download PDFInfo
- Publication number
- CN104021238A CN104021238A CN201410113369.3A CN201410113369A CN104021238A CN 104021238 A CN104021238 A CN 104021238A CN 201410113369 A CN201410113369 A CN 201410113369A CN 104021238 A CN104021238 A CN 104021238A
- Authority
- CN
- China
- Prior art keywords
- lead
- parameter
- fault
- battery system
- vector machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Secondary Cells (AREA)
Abstract
The invention provides a lead-acid power battery system fault diagnosis method. The method involves an off-line part and an on-line part. The method includes the specific steps that in the off-line state, data are collected through a simulation model, the data are preprocessed by using a normalization method, a data classification training set and a testing set of a power battery system of a support vector machine are obtained, parameter adaptive optimization is conducted through a GA algorithm, a one-to-one method is used for training to obtain a diagnostic model of the support vector machine, and SVM decision classification is conducted; in the on-line state, a fault generating device is used for simulating fault signals, the signals are collected through a collection module, the data are preprocessed by using the normalization method, the data are further input into an SVM module in off-line training, and fault online classification based on an SVM algorithm is conducted. According to the lead-acid power battery system fault diagnosis method, intelligent off-line and on-line diagnosis of faults of the battery system can be achieved, and meanwhile the fault diagnosis recognition rate is increased.
Description
Technical field
This patent belongs to new-energy automobile system fault diagnosis field, particularly relates to a kind of lead-acid power accumulator diagnosis method for system fault of the support vector machine (SVM:Support Vector Machine) based on GA preferred parameter.
Background technology
Electric automobile is the important developing direction of future automobile industry.Electrokinetic cell system is as electric automobile important component part, and its safe reliability is directly connected to the safe driving of people's car.Yet present stage, electrokinetic cell system fault can not be by quick, accurate, intelligent being diagnosed, thereby affect normally travelling of vehicle, even causes some potential safety hazards, and driver safety is brought to great threat.
In battery system, parameter brings very big difficulty too much to the exploitation of fault diagnosis functions, and how quick, accurate, intelligent its fault is judged is the difficult problem that electrokinetic cell system fault diagnosis faces.In existing patent, also once there is pair associated description of battery management system fault diagnosis, as the diagnosis control method (patent No. 201110214891) of a kind of power battery management system by name, it in this patent, is mainly a diagnosis to several parameters such as battery voltage sampling, current sensor or loop damage, temperature samplings.In described voltage sample fault diagnosis, battery management system BMS within the sampling period to sampling threshold values compare judgement fault, or through excessive current ratio the situation of change of each sampling channel magnitude of voltage diagnose.These class methods reckon without the coupling between each detected parameters, and intelligent not, have certain limitation.
For can be accurate, the intelligent lead-acid power accumulator system failure be diagnosed, the present invention proposes a kind of lead-acid power accumulator diagnosis method for system fault.With the comparison of existing battery system method for diagnosing faults Patents, the present invention by support vector machine (SVM) algorithm application in lead-acid power accumulator system fault diagnosis, and by adding genetic algorithm (GA) to carry out parameter adaptive optimizing, can be quick, accurate, the intelligent lead-acid power accumulator system failure be diagnosed, thereby improve the overall performance of battery system, greatly reduce the operation and maintenance cost of car load.
Summary of the invention
The object of the invention is to overcome the judgement discrimination that existing electrokinetic cell system fault diagnosis technology exists not high, and the defect of intelligence not, and a kind of lead-acid power accumulator diagnosis method for system fault has been proposed.
A kind of lead-acid power accumulator system failure detection method that the present invention proposes comprises the steps:
1) set up SVM Data classification training set
First in MATLAB, set up lead-acid power accumulator system model, then this model is added to commissioning test success in vehicle simulation model, the operation that adopts the complex conditions circulation (ECE+EUDC) of travelling in standard state of cyclic operation to carry out standard condition circulates the parameters data of battery system is gathered.Regulate relevant parameter in simulated environment model simultaneously, obtain the supplemental characteristic of electrokinetic cell system under unusual service condition and extreme operating condition running status, by image data being carried out to the screening of characteristic feature, obtain electrokinetic cell system fault data classification based training collection.
2) data pre-service
The pre-service being mainly normalized for fault data training set data, the normalized mapping of employing is as follows:
In formula, x, y ∈ R
n, x
min=min (x), x
max=max (x), normalized effect is that raw data is arrived in [0,1] scope by regular, i.e. y
i∈ [0,1], i=1,2 ..., n, this normalization mode is called [0,1] interval normalization.
In MATLAB, by function mapminmax, realize the normalization of training set data (dataset), that is:
[dataset_scale,ps]=mapminmax(dataset’,0,1) (2)
3) structure multiple faults sorter
What the present invention adopted is that " one-against-one " method is processed.The method realizes many classification problems based on two classification problems by constructing or set up a plurality of two sorters." one-against-one " is the how possible binary classifier of structure in N class training sample, and each sorter is only trained on two class training samples in N class, and result is constructed N (N-1)/2 sorter altogether.Test sample book is classified through each sorter, and all composite class are voted, and who gets the most votes's class is the class under test sample book.
4) parameter adaptive that utilizes genetic algorithm to realize support vector machine is selected
Utilize genetic algorithm to realize the method step that SVM parameter adaptive selects as follows:
(1) the optimizing space of C, g is set;
(2) genetic algorithm fitness function is set, cross and variation probability, population size and evolutionary generation, the initial population of generation C, g;
(3) application training sample set and parameters C, g, train support vector machine, draws parameters C, the Lagrangian α that g is corresponding
inumerical value;
(4) by α
iin substitution fitness function f (C, g), obtain the fitness size of different parameters C, g;
(5) according to fitness function and intersection, variation probable value to the population of parameters C, g select, copy, crossover and mutation operation, obtain the new population of C, g;
(6) judge whether evolutionary generation meets, as do not met, continue to rerun from step (3), otherwise proceed to next step;
(7) get the optimal value of parameter, the parameter that completes support vector machine is selected automatically, has finally realized the support vector machine method that parameter is selected automatically.
5) off-line data diagnosis
Fault sample is broken down into k (k-1)/2 binary classifier, the parameter value of genetic algorithm self-adaptation optimizing is added in SVM algorithm simultaneously, and utilizes " One-against-one " to carry out the training of SVM model, obtains the SVM model of battery system fault.By in lead-acid power accumulator system failure test set data input SVM model, by SVM algorithm, carry out Data Comparison, and adopt ballot method to choose, who gets the most votes's classification is judged as the affiliated classification of test set data the most at last, this classification and the original classification of fault data are compared simultaneously, obtain lead-acid power accumulator system fault diagnosis discrimination.
6) real-time online diagnosis
Design lead-acid power accumulator system failure generating means, realizes the adjustable analog signal output of multichannel; Output signal gathers and passes through CAN bus input host computer through slave computer battery management system, and host computer, by logarithm Data preprocess, is input in support vector machine lead-acid power accumulator system model, finally realizes on-line fault diagnosis.
Accompanying drawing explanation
Fig. 1 is method for diagnosing faults flowage structure figure of the present invention.
Fig. 2 is genetic algorithm self-adaptation optimizing parameter process flow diagram of the present invention.
Fig. 3 is the decomposing schematic representation of the present invention's " one-against-one " method.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail:
The present invention is a kind of lead-acid power accumulator diagnosis method for system fault, comprises off-line training identifying and inline diagnosis identification two parts of adding genetic algorithm optimizing parameter support vector machine.The steps flow chart adopting as shown in Figure 1.Concrete operations comprise the steps:
One: off-line operation
(1) by regulating battery system that different parameters obtains at standard condition in car load virtual emulation model, unusual service condition, the data that gather under extreme operating condition form fault detect sample classification training set, the battery system fault sample of choosing in this project is divided into non-fault sample, battery total voltage exceptional sample, battery cell electric voltage exception sample, environment temperature exceptional sample, battery temperature exceptional sample, battery charging and discharging current anomaly sample, battery SOC exceptional sample, battery SOH exceptional sample, the excessive exceptional sample of pressure reduction between battery cell, excessive temperature differentials exceptional sample between battery cell.Each 10 samples of every kind of status data wherein, 10 kinds of states are totally 100 samples.
(2) in order to improve battery system fault Fault Identification accuracy rate under SVM algorithm, battery system fault sample classification based training collection is carried out to [0,1] normalization pre-service, and all raw data are arrived [0 by regular, 1] in scope, and set up new battery system fault sample classification based training collection.
(3) in order further to improve fault diagnosis precision, the value of support vector machine penalty factor parameter and gaussian kernel function width parameter is passed through automatic given its flow chart of steps of offline mode as Fig. 2 by genetic algorithm (GA), the optimizing interval of genetic algorithm is (0, 100), the population MAXIMUM SELECTION of parameter is 10, maximum iteration time is chosen as 200, crossover probability Pc=0.9, variation probability selection is Pm=0.1%, fitness function is set to the accuracy of classification, training sample is the yojan subset that step (2) obtains, 7 steps that concrete steps are selected automatically with reference to the parameter of utilizing genetic algorithm to realize support vector machine in instructions, by optimizing finishing screen repeatedly, selecting that group parameter value with best result class precision is bestC and bestg.Repeatedly optimizing obtains this group parameter value that nicety of grading is the highest, and then is joined in the fault diagnosis algorithm of SVM.
(4) the present invention adopts is that the multiple faults that " one-against-one " method is carried out battery system is diagnosed, so need to set up corresponding a plurality of two sorters, realize many classification problems, and concrete assorting process is as Fig. 3.Owing to having the data of 10 kinds of states in training set, according to formula, can be calculated and need to construct altogether 45 two sorters, be respectively SVM12, SVM13, SVM14 ... SVM89, SVM80, SVM90 (SVMij represents the SVM setting up between i class and j).
(5) in the battery system fault sample obtaining by adjusting different parameters from car load virtual emulation model, every class fault sample random choose goes out 5 groups of data, totally 50 groups of data form battery system fault test collection, then test set is input in step (4) support vector machine battery system fault diagnosis model, through a series of Data Matching contrast, and classification under each two sorter is predicted, and then adopt ballot method to choose, who gets the most votes's classification is planned for the affiliated classification of test set data the most at last, classification and the original classification of fault data after the judgement of SVM algorithm are compared simultaneously, according to misjudgment class number and test set sum, compare, obtain SVM algorithm battery system fault diagnosis discrimination, this kind of method realized SVM algorithm battery system fault off-line verification.
Two: on-line operation
(1) by regulating cell system failure generating means, all kinds of typical fault signals that its analog electrical output cell system is prone in operational process.Its output signal is carried out Collection through slave computer battery management system, and further by CAN bus, outputs to host computer.
(2) host computer is resolved the fault-signal receiving, and changes preservation according to support vector machine test sample book form simultaneously.Fault test sample is by [0,1] normalization pre-service, and its data are arrived in [0,1] scope by regular.
(3) will be input in the battery system fault model based on support vector machine training under offline mode through pretreated battery system fault test sample.
(4) host computer calculates by the algorithmic match of battery system fault test sample and supporting vector machine model, and fault category described in fault sample is carried out to diagnosis and distinguish, realizes the identification of battery system on-line fault diagnosis.
Claims (5)
1. a lead-acid power accumulator diagnosis method for system fault, is characterized in that: in failure diagnostic process, adopt the support vector machine based on genetic algorithm self-adaptation preferred parameter, comprising:
(1) build lead-acid power accumulator system simulation model, obtain battery system running state data;
(2) by adopting genetic algorithm to carry out the self-adaptation optimizing of support vector machine parameter;
(3) the battery system on-line fault diagnosis based on algorithm of support vector machine.
2. a kind of lead-acid power accumulator diagnosis method for system fault according to claim 1, it is characterized in that: described step (1) refers to: the Acid Battery System model of design is added in vehicle simulation model, first adopt complex conditions circulation (ECE+EUDC) to gather each running state parameter data of battery system, then regulate relevant parameter, battery system supplemental characteristic under unusual service condition and extreme operating condition running status is gathered, finally from each supplemental characteristic of electrokinetic cell system gathering, find out coupling relation between each parameter.
3. a kind of lead-acid power accumulator diagnosis method for system fault according to claim 1, it is characterized in that: described step (2) refers to: electrokinetic cell system fault recognition rate is made as to the fitness function in genetic algorithm, and corresponding penalty factor parameter and radial basis kernel functional parameter value while utilizing genetic algorithm to obtain to make fitness function get maximal value.
Utilize genetic algorithm to realize SVM parameter adaptive preferred parameter step as follows:
(1) the optimizing space of C, g is set;
(2) genetic algorithm fitness function is set, cross and variation probability, population size and evolutionary generation, the initial population of generation C, g;
(3) application training sample set and parameters C, g, train support vector machine, draws parameters C, the Lagrangian α that g is corresponding
inumerical value;
(4) by α
iin substitution fitness function f (C, g), obtain the fitness size of different parameters C, g;
(5) according to fitness function and intersection, variation probable value to the population of parameters C, g select, copy, crossover and mutation operation, obtain the new population of C, g;
(6) judge whether evolutionary generation meets, as do not met, continue to rerun from step (3), otherwise proceed to next step;
(7) get the optimal value of parameter, the parameter adaptive that completes support vector machine is selected, and has finally realized the support vector machine method that parameter adaptive is selected.
4. a kind of lead-acid power accumulator diagnosis method for system fault according to claim 1, is characterized in that: described step (3) refers to: design lead-acid power accumulator system failure generating means, realize the adjustable analog signal output of multichannel; Output signal is inputted in host computer support vector machine lead-acid power accumulator system model and is realized on-line fault diagnosis through the collection of slave computer battery management system and by CAN bus.
5. according to arbitrary described method in claim 1-4, it is characterized in that: the method is applied in the fault diagnosis of electric automobile lead-acid power accumulator system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410113369.3A CN104021238A (en) | 2014-03-25 | 2014-03-25 | Lead-acid power battery system fault diagnosis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410113369.3A CN104021238A (en) | 2014-03-25 | 2014-03-25 | Lead-acid power battery system fault diagnosis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104021238A true CN104021238A (en) | 2014-09-03 |
Family
ID=51437992
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410113369.3A Pending CN104021238A (en) | 2014-03-25 | 2014-03-25 | Lead-acid power battery system fault diagnosis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104021238A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104503874A (en) * | 2014-12-29 | 2015-04-08 | 南京大学 | Hard disk failure prediction method for cloud computing platform |
CN105450451A (en) * | 2015-12-01 | 2016-03-30 | 上海第二工业大学 | Network-based fault diagnosis simulation system and method thereof |
CN105955233A (en) * | 2016-04-28 | 2016-09-21 | 郑州宇通客车股份有限公司 | Vehicle fault diagnosis method and system based on data excavation |
CN106383951A (en) * | 2016-09-20 | 2017-02-08 | 北京理工大学 | Fault diagnosis method and system for electric driven traffic tool |
CN107180983A (en) * | 2017-05-16 | 2017-09-19 | 华中科技大学 | A kind of SOFC pile method for diagnosing faults and system |
CN107229614A (en) * | 2017-06-29 | 2017-10-03 | 百度在线网络技术(北京)有限公司 | Method and apparatus for grouped data |
CN108805217A (en) * | 2018-06-20 | 2018-11-13 | 山东大学 | A kind of health state of lithium ion battery method of estimation and system based on support vector machines |
CN109165687A (en) * | 2018-08-28 | 2019-01-08 | 哈尔滨理工大学 | Vehicle lithium battery method for diagnosing faults based on multi-category support vector machines algorithm |
CN109604186A (en) * | 2018-12-14 | 2019-04-12 | 北京匠芯电池科技有限公司 | Power battery performance flexibility assesses method for separating |
CN110110385A (en) * | 2019-04-12 | 2019-08-09 | 电子科技大学 | Application method of the Adaptive proxy model in battery module optimization design based on complex |
CN110705114A (en) * | 2019-10-10 | 2020-01-17 | 辽宁工程技术大学 | Ventilation fault diagnosis method without training sample |
CN111025153A (en) * | 2018-10-09 | 2020-04-17 | 上海汽车集团股份有限公司 | Electric vehicle battery fault diagnosis method and device |
CN112036480A (en) * | 2020-08-29 | 2020-12-04 | 大连海事大学 | Ship refrigeration system fault diagnosis method and device and storage medium |
CN112287979A (en) * | 2020-10-14 | 2021-01-29 | 北方工业大学 | Mutual information-based energy storage battery state judgment method |
CN113343633A (en) * | 2021-06-10 | 2021-09-03 | 上海交通大学 | Thermal runaway fault classification and risk prediction method and system for power lithium battery |
CN113467423A (en) * | 2021-07-01 | 2021-10-01 | 中山大学 | PEMFC fault diagnosis method and system based on cloud platform |
CN113625692A (en) * | 2021-08-23 | 2021-11-09 | 公安部交通管理科学研究所 | Electric automobile battery security inspection system based on fault injection |
CN113844266A (en) * | 2021-08-20 | 2021-12-28 | 云度新能源汽车有限公司 | Method and storage device for predicting and identifying faults of power battery |
CN114781551A (en) * | 2022-06-16 | 2022-07-22 | 北京理工大学 | Battery multi-fault intelligent classification and identification method based on big data |
US11468715B2 (en) | 2017-01-13 | 2022-10-11 | Huawei Technologies Co., Ltd. | Cloud-based vehicle fault diagnosis method, apparatus, and system |
CN115731228A (en) * | 2022-11-30 | 2023-03-03 | 杭州数途信息科技有限公司 | Gold-plated chip defect detection system and method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040204915A1 (en) * | 2002-07-19 | 2004-10-14 | Cyrano Sciences Inc. | Chemical and biological agent sensor array detectors |
CN102332616A (en) * | 2011-07-29 | 2012-01-25 | 奇瑞汽车股份有限公司 | Diagnosis and control method for power battery management system |
CN102566505A (en) * | 2012-02-27 | 2012-07-11 | 温州大学 | Intelligent fault diagnosis method for numerical control machine |
-
2014
- 2014-03-25 CN CN201410113369.3A patent/CN104021238A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040204915A1 (en) * | 2002-07-19 | 2004-10-14 | Cyrano Sciences Inc. | Chemical and biological agent sensor array detectors |
CN102332616A (en) * | 2011-07-29 | 2012-01-25 | 奇瑞汽车股份有限公司 | Diagnosis and control method for power battery management system |
CN102566505A (en) * | 2012-02-27 | 2012-07-11 | 温州大学 | Intelligent fault diagnosis method for numerical control machine |
Non-Patent Citations (5)
Title |
---|
应俊: "基于S V M 和遗传算法的变频器故障诊断研究", 《微电子学》 * |
张大为等: "基于遗传算法和支持向量机的故障诊断方法", 《计算机测量与控制》 * |
王凯等: "遗传算法和支持向量机在机械故障诊断中的应用研究", 《机械强度》 * |
王莹等: "遗传算法支持向量机在故障诊断中的应用", 《火力与指挥控制》 * |
许宝立等: "电动汽车动力电池故障诊断系统设计", 《第六届中国智能交通年会暨第七届国际节能与新能源汽车创新发展论坛优秀论文集(新能源汽车)》 * |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104503874A (en) * | 2014-12-29 | 2015-04-08 | 南京大学 | Hard disk failure prediction method for cloud computing platform |
CN105450451A (en) * | 2015-12-01 | 2016-03-30 | 上海第二工业大学 | Network-based fault diagnosis simulation system and method thereof |
CN105450451B (en) * | 2015-12-01 | 2018-10-30 | 上海第二工业大学 | A kind of network-based Fault Diagnosis Simulation system and method |
CN105955233A (en) * | 2016-04-28 | 2016-09-21 | 郑州宇通客车股份有限公司 | Vehicle fault diagnosis method and system based on data excavation |
CN105955233B (en) * | 2016-04-28 | 2018-09-25 | 郑州宇通客车股份有限公司 | A kind of car fault diagnosis method and system based on data mining |
CN106383951A (en) * | 2016-09-20 | 2017-02-08 | 北京理工大学 | Fault diagnosis method and system for electric driven traffic tool |
CN106383951B (en) * | 2016-09-20 | 2019-08-06 | 北京理工大学 | A kind of method for diagnosing faults being driven by electricity the vehicles and system |
US11468715B2 (en) | 2017-01-13 | 2022-10-11 | Huawei Technologies Co., Ltd. | Cloud-based vehicle fault diagnosis method, apparatus, and system |
CN107180983B (en) * | 2017-05-16 | 2020-01-03 | 华中科技大学 | Fault diagnosis method and system for solid oxide fuel cell stack |
CN107180983A (en) * | 2017-05-16 | 2017-09-19 | 华中科技大学 | A kind of SOFC pile method for diagnosing faults and system |
CN107229614A (en) * | 2017-06-29 | 2017-10-03 | 百度在线网络技术(北京)有限公司 | Method and apparatus for grouped data |
CN107229614B (en) * | 2017-06-29 | 2020-11-10 | 百度在线网络技术(北京)有限公司 | Method and apparatus for classifying data |
CN108805217B (en) * | 2018-06-20 | 2020-10-23 | 山东大学 | Lithium ion battery health state estimation method and system based on support vector machine |
CN108805217A (en) * | 2018-06-20 | 2018-11-13 | 山东大学 | A kind of health state of lithium ion battery method of estimation and system based on support vector machines |
CN109165687A (en) * | 2018-08-28 | 2019-01-08 | 哈尔滨理工大学 | Vehicle lithium battery method for diagnosing faults based on multi-category support vector machines algorithm |
CN109165687B (en) * | 2018-08-28 | 2021-06-15 | 哈尔滨理工大学 | Vehicle lithium battery fault diagnosis method based on multi-classification support vector machine algorithm |
CN111025153A (en) * | 2018-10-09 | 2020-04-17 | 上海汽车集团股份有限公司 | Electric vehicle battery fault diagnosis method and device |
CN109604186B (en) * | 2018-12-14 | 2021-12-07 | 蓝谷智慧(北京)能源科技有限公司 | Flexible evaluation and sorting method for performance of power battery |
CN109604186A (en) * | 2018-12-14 | 2019-04-12 | 北京匠芯电池科技有限公司 | Power battery performance flexibility assesses method for separating |
CN110110385A (en) * | 2019-04-12 | 2019-08-09 | 电子科技大学 | Application method of the Adaptive proxy model in battery module optimization design based on complex |
CN110705114A (en) * | 2019-10-10 | 2020-01-17 | 辽宁工程技术大学 | Ventilation fault diagnosis method without training sample |
CN110705114B (en) * | 2019-10-10 | 2023-04-07 | 辽宁工程技术大学 | Ventilation fault diagnosis method without training sample |
CN112036480A (en) * | 2020-08-29 | 2020-12-04 | 大连海事大学 | Ship refrigeration system fault diagnosis method and device and storage medium |
CN112287979A (en) * | 2020-10-14 | 2021-01-29 | 北方工业大学 | Mutual information-based energy storage battery state judgment method |
CN112287979B (en) * | 2020-10-14 | 2023-05-23 | 北方工业大学 | Mutual information-based energy storage battery state judging method |
CN113343633B (en) * | 2021-06-10 | 2022-04-26 | 上海交通大学 | Thermal runaway fault classification and risk prediction method and system for power lithium battery |
CN113343633A (en) * | 2021-06-10 | 2021-09-03 | 上海交通大学 | Thermal runaway fault classification and risk prediction method and system for power lithium battery |
CN113467423A (en) * | 2021-07-01 | 2021-10-01 | 中山大学 | PEMFC fault diagnosis method and system based on cloud platform |
CN113844266A (en) * | 2021-08-20 | 2021-12-28 | 云度新能源汽车有限公司 | Method and storage device for predicting and identifying faults of power battery |
CN113625692A (en) * | 2021-08-23 | 2021-11-09 | 公安部交通管理科学研究所 | Electric automobile battery security inspection system based on fault injection |
CN114781551A (en) * | 2022-06-16 | 2022-07-22 | 北京理工大学 | Battery multi-fault intelligent classification and identification method based on big data |
CN114781551B (en) * | 2022-06-16 | 2022-11-29 | 北京理工大学 | Battery multi-fault intelligent classification and identification method based on big data |
CN115731228A (en) * | 2022-11-30 | 2023-03-03 | 杭州数途信息科技有限公司 | Gold-plated chip defect detection system and method |
CN115731228B (en) * | 2022-11-30 | 2023-08-18 | 杭州数途信息科技有限公司 | Gold-plated chip defect detection system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104021238A (en) | Lead-acid power battery system fault diagnosis method | |
Li et al. | Battery fault diagnosis for electric vehicles based on voltage abnormality by combining the long short-term memory neural network and the equivalent circuit model | |
CN110262463B (en) | Rail transit platform door fault diagnosis system based on deep learning | |
CN102944416B (en) | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades | |
US11756349B2 (en) | Electronic control unit testing optimization | |
CN102944418B (en) | Wind turbine generator group blade fault diagnosis method | |
CN102707256B (en) | Fault diagnosis method based on BP-Ada Boost nerve network for electric energy meter | |
CN111090050A (en) | Lithium battery fault diagnosis method based on support vector machine and K mean value | |
CN104155574A (en) | Power distribution network fault classification method based on adaptive neuro-fuzzy inference system | |
CN106017876A (en) | Wheel set bearing fault diagnosis method based on equally-weighted local feature sparse filter network | |
CN111914883A (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
CN101871994B (en) | Method for diagnosing faults of analog circuit of multi-fractional order information fusion | |
CN103838229A (en) | Diagnosis method and device of electric car | |
CN102435910A (en) | Power electronic circuit health monitoring method based on support vector classification | |
KR102215107B1 (en) | Vehicle state predicting system and method based on driving data | |
CN103512751A (en) | Bearing health state identification method based on probabilistic neural network | |
CN105606914A (en) | IWO-ELM-based Aviation power converter fault diagnosis method | |
CN108304567A (en) | High-tension transformer regime mode identifies and data classification method and system | |
CN105241665A (en) | Rolling bearing fault diagnosis method based on IRBFNN-AdaBoost classifier | |
CN114036998A (en) | Method and system for fault detection of industrial hardware based on machine learning | |
Yao et al. | Fault identification of lithium-ion battery pack for electric vehicle based on ga optimized ELM neural network | |
CN117056678B (en) | Machine pump equipment operation fault diagnosis method and device based on small sample | |
CN114036647A (en) | Power battery safety risk assessment method based on real vehicle data | |
CN114115199A (en) | Monitoring and fault diagnosis system for new energy sanitation vehicle | |
CN117491872A (en) | Reconfigurable battery module fault multistage diagnosis method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140903 |
|
RJ01 | Rejection of invention patent application after publication |