CN104375091A - Monitoring method for electric vehicle power storage battery - Google Patents
Monitoring method for electric vehicle power storage battery Download PDFInfo
- Publication number
- CN104375091A CN104375091A CN201410655446.8A CN201410655446A CN104375091A CN 104375091 A CN104375091 A CN 104375091A CN 201410655446 A CN201410655446 A CN 201410655446A CN 104375091 A CN104375091 A CN 104375091A
- Authority
- CN
- China
- Prior art keywords
- battery pack
- storage battery
- data
- monitoring method
- network
- 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)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The invention discloses a monitoring method for an electric vehicle power storage battery. According to the method, data samples, under various working conditions, of the specific model of lead-acid storage battery are collected, a neutral network toolbox in Matlab is used for modeling and training the lead-acid storage battery, data collecting is completed in real time through a microprocessor, and based on iterative computation, communication and displaying of a neutral network, the remaining capacity of the storage battery is predicted accurately in real time. For the storage battery arranged on an electric vehicle (EV), a BP neutral network model based on the external features of the storage battery is established without consideration of complex internal factors influencing the remaining capacity of the storage battery, and therefore the remaining capacity of the storage battery is predicted accurately in real time.
Description
Technical field
The present invention relates to the detection of electric powered motor accumulator, specifically a kind of electric powered motor battery pack monitoring method.
Background technology
Electric automobile (ElectricVehicle, EV) has low noise, and the advantage that almost zero-emission and comprehensive energy utilization etc. are outstanding is the important channel solving the problem such as the energy, environmental protection now.Although Development of Electric Vehicles is rapid, its power source power accumulator group, be the bottleneck of its development all the time.Storage battery energy administrative skill is just for addressing this problem and proposing.Wherein, prediction EV residue exercises mileage, improves the work efficiency of battery, ensures that battery is in best duty, effectively increases the service life, have great importance to EV.
But, be in the accumulator under actual working state, internal-response is very complicated, and the factor affecting accumulator capacity is also a lot, such as discharge rate, discharge type, final voltage, temperature, electrode structure, manufacturing process etc., the nonlinearity often of the relation between these parameters.Because the relation between these battery parameter and residual capacities is complicated, and non-linear, traditional accumulator monitoring method has certain limitation, cannot realize online Real-Time Monitoring.
Summary of the invention
For overcoming the deficiencies in the prior art, the invention provides a kind of electric powered motor battery pack monitoring method, this method monitoring to as if certain electric automobile lead-acid batteries of specific model of assembling.Monitoring comprises two contents: the residual capacity of lead-acid accumulator and accumulator in the residual capacity of in use (electric discharge) after charging completely, the EV remaining driving mileage namely in routine use.The fault detect of battery pack comprises lead-acid batteries serviceability, depends on the state of each Series Sheet accumulator body, and cell batteries is because the factors such as quality cause initial failure.Capacity decline or fault can affect the serviceability of unitary battery group.
A kind of electric powered motor battery pack of the present invention monitoring method, the method is by gathering the data sample of specific model lead-acid batteries under various operating mode, by the Neural Network Toolbox in Matlab, modeling, training are carried out to this lead-acid batteries, by the real-time data acquisition of microprocessor, based on the iterative computation of neural network, communication and display, realize real-time, the Accurate Prediction to remaining battery capacity.
Particularly, for the battery pack of one group of known models, under certain working condition, its terminal voltage U, discharge current I, temperature T, discharge time H there is certain corresponding relation, that is:
U＝f(I，T，H) (1)
When known discharge current, terminal voltage and battery temp, can discharge time be extrapolated, and then obtain the residual capacity of accumulator.
Further, carry out fault detect according to the conforming principle of battery pack operating mode to battery pack, for same group of model and use working time identical accumulator, under heavy-current discharge condition, each cell batteries external characteristics should be consistent; If there is larger difference, then can judge that the cell batteries corresponding to this circuit voltage breaks down.
Particularly, carrying out in modeling, training by the Neural Network Toolbox in Matlab to this lead-acid batteries, selected battery discharging electric current, temperature and terminal voltage composition 30 × 3 input vectors, the numerical value of 30 battery remaining powers of corresponding practical measurement, constitutes 30 input and output samples pair of BP neural network model; Wherein, 24 input and output samples are to being used for training network, and remaining 6 samples are to being used for the accuracy of test network.
Particularly, because each input data of network usually have different physical significances and dimension, in order to make network train status just of equal importance to each input component at the beginning, change of scale to be carried out to the component of all inputs; Because the output of Sigmoid transforming function transformation function is between 0 ~ 1 or-1 ~+1, value inputoutput data being transformed to [-1,1] interval commonly uses following transformation for mula:
xmid＝(xmax+xmin)/2 (2)
In formula: xi is for inputing or outputing data; Xj be conversion after input, export data; Xmid is the intermediate value of data variation scope; Xmin is the minimum value of data variation scope; Xmax is the maximal value of data variation scope.
Due to technique scheme, the present invention has following beneficial effect: the lead-acid batteries that the present invention is directed to EV configuration, get around and affect the numerous and diverse internal factor of remaining battery capacity, propose a kind of BP neural network model built based on accumulator external characteristics, achieve real-time, the Accurate Prediction to remaining battery capacity.
Accompanying drawing explanation
In order to be illustrated more clearly in technical scheme of the present invention, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is 40A constant-current discharge voltage-time curve;
Fig. 2 is the result schematic diagram of network training in embodiment.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under the prerequisite of not making creative work, all belongs to the scope of protection of the invention.
Be in the accumulator under actual working state, internal-response is very complicated, the factor affecting accumulator capacity is also a lot, such as discharge rate, discharge type, final voltage, temperature, electrode structure, manufacturing process etc., the nonlinearity often of the relation between these parameters.Because the relation between these battery parameter and residual capacities is complicated, and non-linear, traditional accumulator monitoring method has certain limitation, cannot realize online Real-Time Monitoring.
But, for the battery pack of one group of known models, under certain working condition, its terminal voltage U, discharge current I, temperature T, discharge time H there is certain corresponding relation, that is:
U＝f(I，T，H) (1)
When known discharge current, terminal voltage and battery temp, can discharge time be extrapolated, and then obtain the residual capacity of accumulator.Such as, Fig. 1 is 6DA150 type lead-acid battery 40A constant-current discharge characteristic under room temperature (255) environment.
As can be known from Fig. 1, accumulator is electric discharge from 11.8V (set now capacity as 100%), 9V (set now capacity as 0%) stops electric discharge, totally 206 automotive electronics Lee Chang'an etc.: the research used time 210min of electric powered motor battery pack monitoring system.When terminal voltage is reduced to 10V, discharge time is 205min.As calculated, battery remaining power is 5.1%.
In reality detects, by gathering the data sample of this specific model lead-acid batteries under various operating mode, by the Neural Network Toolbox in Matlab, modeling, training are carried out to this lead-acid batteries.By the real-time data acquisition of microprocessor, based on the iterative computation of neural network, communication and display.The method gets around the numerous and diverse internal factor of accumulator, obtains corresponding remaining battery capacity and prediction EV residue enforcement mileage real-time online.
The fault detect principle of battery pack is according to the conforming principle of battery pack operating mode, namely for same group of model with use working time identical accumulator for, under heavy-current discharge condition, each cell batteries external characteristics should basically identical (terminal voltage decline amplitude should be basically identical).If there is the cell batteries of larger difference, then can think that this cell batteries corresponding to voltage of road breaks down.
Matlab based on BP network realizes:
BP neural network has the superperformance to complicated nonlinear system prediction, effectively can describe the nonlinear characteristic [8] that uncertain, the multi input itself had etc. is complicated.A large amount of tests shows, under given remaining battery capacity state, terminal voltage and the temperature of accumulator change along with the difference of discharge-rate, and terminal voltage, temperature and discharge current namely can be utilized to estimate the residual capacity of accumulator and to judge the consistance of battery pack operating mode.Carry out orecontrolling factor device with a feed forward type network herein, set up neural network inference rule by the self-study habit of BP neural network from dynamic.
Because discharge current conventional on electric automobile is 10 ~ 20A, add the restriction of experiment condition, in native system sample, the scope of discharge current is 10 ~ 30A, and voltage reference terminal is 14.2 ~ 9.6V, and range of temperature is 20 ~ 44.Selected battery discharging electric current, temperature and terminal voltage form 303 input vectors, the numerical value of 30 battery remaining powers of corresponding practical measurement, constitute 30 input and output samples pair of BP neural network model.Wherein, 24 input and output samples are to being used for training network, and remaining 6 samples are to being used for the accuracy of test network.
Because each input data of network usually have different physical significances and dimension, in order to make network train status just of equal importance to each input component at the beginning, change of scale to be carried out to the component of all inputs; Because the output of Sigmoid transforming function transformation function is between 0 ~ 1 or-1 ~+1, value inputoutput data being transformed to [-1,1] interval commonly uses following transformation for mula:
xmid＝(xmax+xmin)/2 (2)
In formula: xi is for inputing or outputing data; Xj be conversion after input, export data; Xmid is the intermediate value of data variation scope; Xmin is the minimum value of data variation scope; Xmax is the maximal value of data variation scope.
As stated above after conversion, the raw data of the value that mediates is converted into 0, and minimum value and maximal value are converted to-1 and 1 respectively.
The input and output layer neuron number of BP network is determined by the dimension of input and output vector.Here have chosen accumulator voltage, temperature and electric current 3 factors, so the neuron number of input layer is 3.Owing to exporting the residual capacity only having accumulator, so the neuron number of output layer is 1.Practice shows, the increase of hidden layer number can improve the non-linear mapping capability of BP network, but hidden layer number exceedes certain value, and the performance of network can decline on the contrary.Therefore, 3 layers of BP neural network residual capacity to accumulator based on LM algorithm are adopted to predict here.The neuron number of hidden layer directly affects the nonlinear prediction performance of network, but because choosing of network hidden layer there is no theoretic guidance at present, after test of many times, find in hidden layer, adopt 16 neurons just can describe the relation of battery discharging electric current, temperature and voltage and battery remaining power more exactly.
We all carry out all operations of BP neural metwork training and emulation in graphic user interface GUI.The activation function of hidden layer neuron adopts S type tan Tansig; Output layer adopts Purelin linear function; Select Trainlm function to train network, maximum train epochs epochs is 100, goal be 110-6, show is 1, and other parameters all select default value.
The training of network and test process all carry out under Matlab environment.By the sample data input network of 244 after normalized, adopt LM Algorithm for Training network, after 26 training, the target error of network reaches requirement, and training result as shown in Figure 2.
The test and evaluation of network: so-called test, is actually and utilizes simulated function to obtain the output of network, whether the error that then checking exports between actual measured value meets the demands.After normalization 63 test data is inputted the network trained, Output rusults is obtained after renormalization process the residual capacity of accumulator, as shown in table 1.
Table 1 actual capacity value and prediction capability value
From table 1, by compared with the capacity of reality, the mean absolute error that can obtain network is 0.048.Consider the smaller reason of sample size, this is good result.
The weight matrix of network and inclined value matrix can be obtained according to the BP neural network model trained above, they are put in host computer procedure, the residual capacity of battery under the different electric currents, temperature and the voltage that utilize the measurable slave computer of this program to test like this.By test, demonstrate this model and there is higher accuracy.
Above disclosedly be only several preferred embodiment of the present invention, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.
Claims (5)
1. an electric powered motor battery pack monitoring method, it is characterized in that: by gathering the data sample of specific model lead-acid batteries under various operating mode, by the Neural Network Toolbox in Matlab, modeling, training are carried out to this lead-acid batteries, by the real-time data acquisition of microprocessor, based on the iterative computation of neural network, communication and display, realize real-time, the Accurate Prediction to remaining battery capacity.
2. electric powered motor battery pack monitoring method according to claim 1, it is characterized in that: for the battery pack of one group of known models, under certain working condition, its terminal voltage U, discharge current I, temperature T, discharge time H there is certain corresponding relation, that is:
U＝f(I，T，H) (1)
When known discharge current, terminal voltage and battery temp, can discharge time be extrapolated, and then obtain the residual capacity of accumulator.
3. electric powered motor battery pack monitoring method according to claim 2, it is characterized in that: according to battery pack operating mode conforming principle, fault detect is carried out to battery pack, for same group of model and use working time identical accumulator, under heavy-current discharge condition, each cell batteries external characteristics should be consistent; If there is larger difference, then can judge that the cell batteries corresponding to this circuit voltage breaks down.
4. the electric powered motor battery pack monitoring method according to claim 1-3 any one, it is characterized in that: carrying out in modeling, training by the Neural Network Toolbox in Matlab to this lead-acid batteries, selected battery discharging electric current, temperature and terminal voltage composition 30 × 3 input vectors, the numerical value of 30 battery remaining powers of corresponding practical measurement, constitutes 30 input and output samples pair of BP neural network model; Wherein, 24 input and output samples are to being used for training network, and remaining 6 samples are to being used for the accuracy of test network.
5. electric powered motor battery pack monitoring method according to claim 4, it is characterized in that: because each input data of network usually have different physical significances and dimension, in order to make network train status just of equal importance to each input component at the beginning, change of scale to be carried out to the component of all inputs; Because the output of Sigmoid transforming function transformation function is between 0 ~ 1 or-1 ~+1, value inputoutput data being transformed to [-1,1] interval commonly uses following transformation for mula:
x
mid＝(x
max+x
min)/2 (2)
In formula: xi is for inputing or outputing data; Xj be conversion after input, export data; Xmid is the intermediate value of data variation scope; Xmin is the minimum value of data variation scope; Xmax is the maximal value of data variation scope.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410655446.8A CN104375091A (en) | 2014-11-18 | 2014-11-18 | Monitoring method for electric vehicle power storage battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410655446.8A CN104375091A (en) | 2014-11-18 | 2014-11-18 | Monitoring method for electric vehicle power storage battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104375091A true CN104375091A (en) | 2015-02-25 |
Family
ID=52554127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410655446.8A Pending CN104375091A (en) | 2014-11-18 | 2014-11-18 | Monitoring method for electric vehicle power storage battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104375091A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021923A (en) * | 2016-05-19 | 2016-10-12 | 江苏理工学院 | Method and system for predicting state of charge of power battery of pure electric vehicle |
| CN108267696A (en) * | 2018-04-09 | 2018-07-10 | 广东电网有限责任公司 | A kind of accumulator capacity shallow discharge detection device |
| CN108303658A (en) * | 2018-03-01 | 2018-07-20 | 杭州高特新能源技术有限公司 | Lead-acid battery difference charging and discharging curve acquisition methods |
| CN109856544A (en) * | 2019-01-24 | 2019-06-07 | 努比亚技术有限公司 | Terminal power uses time analysis method, terminal and computer readable storage medium |
| CN110187287A (en) * | 2019-06-24 | 2019-08-30 | 安徽师范大学 | A kind of retired lithium battery complementary energy rapid detection method |
| CN111191824A (en) * | 2019-12-20 | 2020-05-22 | 北京理工新源信息科技有限公司 | Power battery capacity attenuation prediction method and system |
| CN112415397A (en) * | 2020-11-27 | 2021-02-26 | 广东电网有限责任公司佛山供电局 | Method for diagnosing faults of backup lead-acid storage battery pack of integrated intelligent terminal in real time |
| CN112632850A (en) * | 2020-12-14 | 2021-04-09 | 华中科技大学 | Method and system for detecting abnormal battery in lithium battery pack |
| WO2021088216A1 (en) * | 2019-11-04 | 2021-05-14 | 广东小鹏汽车科技有限公司 | Method and apparatus for detecting data on state of charge of battery pack, medium, terminal and vehicle |
| CN112986830A (en) * | 2021-04-22 | 2021-06-18 | 湖北工业大学 | Lithium battery capacity estimation method based on convolution time memory neural network |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1890574A (en) * | 2003-12-18 | 2007-01-03 | 株式会社Lg化学 | Apparatus and method for estimating state of charge of battery using neural network |
| CN1916653A (en) * | 2005-08-19 | 2007-02-21 | 株式会社Ntt设施 | Deterioration judging device and method, computer program |
| CN101539612A (en) * | 2008-03-19 | 2009-09-23 | 衣文所 | System for on-line monitoring of running quality of battery |
| CN101764417A (en) * | 2009-05-19 | 2010-06-30 | 甘肃卓越电子科技有限公司 | Intelligent adaptive charge management device for lithium polymer storage battery and control system thereof |
| CN102230953A (en) * | 2011-06-20 | 2011-11-02 | 江南大学 | Method for predicting left capacity and health status of storage battery |
| CN102279370A (en) * | 2011-07-26 | 2011-12-14 | 重庆长安汽车股份有限公司 | State monitoring device for lead-acid storage battery of automobile |
| CN102324582A (en) * | 2011-08-12 | 2012-01-18 | 重庆东电通信技术有限公司 | Intelligent maintenance device of multifunctional lead-acid battery and capacity prediction method |
| CN102680903A (en) * | 2012-05-11 | 2012-09-19 | 山东轻工业学院 | Portable storage battery state detection system and method |
| CN102721931A (en) * | 2012-06-27 | 2012-10-10 | 陈逸 | On-line remote monitoring and managing system for storage battery |
| CN103105585A (en) * | 2011-11-10 | 2013-05-15 | 宋洋 | Charge-discharge full-time online testing method for performance of storage battery |
| CN103302777A (en) * | 2013-06-26 | 2013-09-18 | 广东工业大学 | Neural-network-based energy consumption anomaly detection method of tire vulcanizing machine |
-
2014
- 2014-11-18 CN CN201410655446.8A patent/CN104375091A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1890574A (en) * | 2003-12-18 | 2007-01-03 | 株式会社Lg化学 | Apparatus and method for estimating state of charge of battery using neural network |
| CN1916653A (en) * | 2005-08-19 | 2007-02-21 | 株式会社Ntt设施 | Deterioration judging device and method, computer program |
| CN101539612A (en) * | 2008-03-19 | 2009-09-23 | 衣文所 | System for on-line monitoring of running quality of battery |
| CN101764417A (en) * | 2009-05-19 | 2010-06-30 | 甘肃卓越电子科技有限公司 | Intelligent adaptive charge management device for lithium polymer storage battery and control system thereof |
| CN102230953A (en) * | 2011-06-20 | 2011-11-02 | 江南大学 | Method for predicting left capacity and health status of storage battery |
| CN102279370A (en) * | 2011-07-26 | 2011-12-14 | 重庆长安汽车股份有限公司 | State monitoring device for lead-acid storage battery of automobile |
| CN102324582A (en) * | 2011-08-12 | 2012-01-18 | 重庆东电通信技术有限公司 | Intelligent maintenance device of multifunctional lead-acid battery and capacity prediction method |
| CN103105585A (en) * | 2011-11-10 | 2013-05-15 | 宋洋 | Charge-discharge full-time online testing method for performance of storage battery |
| CN102680903A (en) * | 2012-05-11 | 2012-09-19 | 山东轻工业学院 | Portable storage battery state detection system and method |
| CN102721931A (en) * | 2012-06-27 | 2012-10-10 | 陈逸 | On-line remote monitoring and managing system for storage battery |
| CN103302777A (en) * | 2013-06-26 | 2013-09-18 | 广东工业大学 | Neural-network-based energy consumption anomaly detection method of tire vulcanizing machine |
Non-Patent Citations (1)
| Title |
|---|
| 李长安等: "电动汽车动力蓄电池组监测系统的研究", 《现代电子技术》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021923A (en) * | 2016-05-19 | 2016-10-12 | 江苏理工学院 | Method and system for predicting state of charge of power battery of pure electric vehicle |
| CN108303658A (en) * | 2018-03-01 | 2018-07-20 | 杭州高特新能源技术有限公司 | Lead-acid battery difference charging and discharging curve acquisition methods |
| CN108303658B (en) * | 2018-03-01 | 2020-06-02 | 杭州高特新能源技术有限公司 | Method for acquiring different charging and discharging curves of lead-acid battery |
| CN108267696A (en) * | 2018-04-09 | 2018-07-10 | 广东电网有限责任公司 | A kind of accumulator capacity shallow discharge detection device |
| CN109856544A (en) * | 2019-01-24 | 2019-06-07 | 努比亚技术有限公司 | Terminal power uses time analysis method, terminal and computer readable storage medium |
| CN110187287A (en) * | 2019-06-24 | 2019-08-30 | 安徽师范大学 | A kind of retired lithium battery complementary energy rapid detection method |
| WO2021088216A1 (en) * | 2019-11-04 | 2021-05-14 | 广东小鹏汽车科技有限公司 | Method and apparatus for detecting data on state of charge of battery pack, medium, terminal and vehicle |
| CN111191824A (en) * | 2019-12-20 | 2020-05-22 | 北京理工新源信息科技有限公司 | Power battery capacity attenuation prediction method and system |
| CN111191824B (en) * | 2019-12-20 | 2024-03-26 | 北京理工新源信息科技有限公司 | Power battery capacity attenuation prediction method and system |
| CN112415397A (en) * | 2020-11-27 | 2021-02-26 | 广东电网有限责任公司佛山供电局 | Method for diagnosing faults of backup lead-acid storage battery pack of integrated intelligent terminal in real time |
| CN112632850A (en) * | 2020-12-14 | 2021-04-09 | 华中科技大学 | Method and system for detecting abnormal battery in lithium battery pack |
| CN112986830A (en) * | 2021-04-22 | 2021-06-18 | 湖北工业大学 | Lithium battery capacity estimation method based on convolution time memory neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104375091A (en) | Monitoring method for electric vehicle power storage battery | |
| Panchal et al. | Thermal and electrical performance assessments of lithium-ion battery modules for an electric vehicle under actual drive cycles | |
| CN107870306A (en) | A kind of lithium battery charge state prediction algorithm based under deep neural network | |
| CN106443453A (en) | Lithium battery SOC estimation method based on BP neural network | |
| JP7446990B2 (en) | Method for estimating state of charge of power storage device and state of charge estimation system for power storage device | |
| EP4198531A1 (en) | Battery cell defectiveness and fire early diagnosis method and apparatus based on neural network | |
| Mamo et al. | Long short-term memory with attention mechanism for state of charge estimation of lithium-ion batteries | |
| US20220179009A1 (en) | Method and Apparatus for Operating a System for Providing Predicted States of Health of Electrical Energy Stores for a Device Using Machine Learning Methods | |
| CN102540081B (en) | Method for determining charge state of vehicle-mounted storage battery | |
| CN112986830A (en) | Lithium battery capacity estimation method based on convolution time memory neural network | |
| Barreras et al. | Multi-objective control of balancing systems for li-ion battery packs: A paradigm shift? | |
| CN108284752B (en) | Extended range type fuel cell electric automobile power device and control method thereof | |
| CN110568360B (en) | Lithium battery aging diagnosis method based on fuzzy logic algorithm | |
| CN105021994A (en) | Method and device for detecting consistency of single batteries in battery pack | |
| Einhorn et al. | Comparison of electrical battery models using a numerically optimized parameterization method | |
| CN107539306A (en) | Automobile torque distribution control method based on Study On Reliability Estimation Method For Cold Standby Systems | |
| CN103983920A (en) | Method for establishing model of power battery of electric vehicle | |
| US20220099743A1 (en) | Method and Apparatus for Operating a System for Providing Predicted States of Health of Electrical Energy Stores for a Device Using Machine Learning Methods | |
| Shi et al. | Battery state-of-charge estimation in electric vehicle using elman neural network method | |
| CN112101597A (en) | Electric vehicle leasing operation platform vehicle fault pre-judging system, method and device | |
| CN115718263B (en) | Attention-based lithium ion battery calendar aging prediction model and method | |
| Amanathulla et al. | An extensive comparison of state of charge estimation of lithium ion battery—towards predictive intelligent battery management system for electric vehicles | |
| Mesbahi et al. | Improved model of battery/supercapacitor hybrid energy storage system based on thermo-electrical and aging behaviors | |
| CN107255786B (en) | LOC model of lithium iron phosphate battery | |
| Swarnkar et al. | Electric Vehicle Lithium-ion Battery Ageing Analysis Under Dynamic Condition: A Machine Learning Approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150225 |
|
| WD01 | Invention patent application deemed withdrawn after publication |