CN108572324A - Battery SOC estimation device based on immune algorithm Optimized BP Neural Network - Google Patents
Battery SOC estimation device based on immune algorithm Optimized BP Neural Network Download PDFInfo
- Publication number
- CN108572324A CN108572324A CN201810329478.7A CN201810329478A CN108572324A CN 108572324 A CN108572324 A CN 108572324A CN 201810329478 A CN201810329478 A CN 201810329478A CN 108572324 A CN108572324 A CN 108572324A
- Authority
- CN
- China
- Prior art keywords
- battery
- neural network
- estimation device
- immune algorithm
- soc estimation
- 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 present invention discloses the battery SOC estimation device based on immune algorithm Optimized BP Neural Network, including：Sensor group and the microprocessor for loading BP neural network model；Wherein, the following data of the sensor group acquisition battery：Charging and discharging currents, terminal voltage, environment temperature, charge and discharge number and previous battery charge state measured value, the microprocessor estimate the value of current time battery charge state according to the data acquired.The battery SOC estimation device based on immune algorithm Optimized BP Neural Network can establish power battery mathematical models, realize the accurate estimation to power battery nuclear power state.
Description
Technical field
The present invention relates to the measuring devices of battery charge state (State of Charge) estimation, and in particular, to a kind of
Battery SOC estimation device based on immune algorithm Optimized BP Neural Network.
Background technology
With the exhaustion of fossil fuel and the raising of environmental consciousness, the sales volume of electric vehicle is growing day by day.Accurate Prediction
The nuclear power state of power battery has great significance to improving the energy utilization efficiency of battery and extending battery.
However environment temperature, charging and discharging currents, charge and discharge number can all influence the inner parameter of battery, it is difficult to be established to battery accurate
Mathematical model, which increase the prediction difficulty of power battery nuclear power state.
Invention content
The object of the present invention is to provide a kind of battery SOC estimation devices based on immune algorithm Optimized BP Neural Network, should
Battery SOC estimation device based on immune algorithm Optimized BP Neural Network can establish mathematical models to power battery, real
Now to the accurate estimation of power battery charged state.
To achieve the goals above, the present invention provides a kind of battery SOC based on immune algorithm Optimized BP Neural Network and estimates
Counter device, the battery SOC estimation device include：Sensor group and the microprocessor for loading BP neural network model；Wherein, described
Sensor group acquires the following data of battery：Charging and discharging currents, terminal voltage, environment temperature, charge and discharge number and previous electricity
Pond state-of-charge measured value, the microprocessor estimate the value of current time battery charge state according to the data acquired.
Preferably, the sensor group includes：Temperature sensor, wherein the temperature sensor is connected to the battery,
To acquire the environment temperature of battery.
Preferably, the sensor group includes：Current sensor, wherein the current sensor is connected to the battery,
To acquire the charging and discharging currents of battery.
Preferably, the sensor group includes：Voltage sensor, wherein the voltage sensor is connected to the battery,
To acquire the terminal voltage of battery.
Preferably, the microprocessor prestores previous battery charge state measured value, and collects the charge and discharge of battery
The number of electricity.
Preferably, the microprocessor is connected to host computer, is based on being immunized using MATLAB softwares on the host computer
Algorithm optimization BP neural network weights and threshold value establish the mathematical model of lithium battery.
Through the above technical solutions, the present invention using BP neural network models fitting battery charge state and environment temperature,
Charging and discharging currents, sampling time, battery terminal voltage, previous sampling instant battery charge state value and battery charging and discharging number pair
The influence of battery parameter, the information that fusion mass data is included, accuracy is high, and cost is relatively low.Application field of the present invention is extensive,
It can be the occasions such as the energy management of batteries of electric automobile, the protection of battery pack, be particularly suitable for large-power occasions.
Other features and advantages of the present invention will be described in detail in subsequent specific embodiment part.
Description of the drawings
Attached drawing is to be used to provide further understanding of the present invention, an and part for constitution instruction, with following tool
Body embodiment is used to explain the present invention together, but is not construed as limiting the invention.In the accompanying drawings：
Fig. 1 is the BP for illustrating a kind of battery SOC estimation device based on immune algorithm Optimized BP Neural Network of the present invention
Neural network model；
Fig. 2 is the work flow diagram for illustrating a kind of immune algorithm Optimized BP Neural Network of the present invention；And
Fig. 3 is the mould for illustrating a kind of battery SOC estimation device based on immune algorithm Optimized BP Neural Network of the present invention
Block block diagram.
Specific implementation mode
The specific implementation mode of the present invention is described in detail below in conjunction with attached drawing.It should be understood that this place is retouched
The specific implementation mode stated is merely to illustrate and explain the present invention, and is not intended to restrict the invention.
The present invention provides a kind of battery SOC estimation device based on immune algorithm Optimized BP Neural Network, which estimates
Counter device includes：Sensor group and the microprocessor for loading BP neural network model；Wherein, the sensor group acquires battery
Following data：Charging and discharging currents, terminal voltage, environment temperature, charge and discharge number and previous battery charge state measured value, institute
State the value that microprocessor estimates current time battery charge state according to the data acquired.
Through the above technical solutions, the present invention using BP neural network models fitting battery charge state and environment temperature,
Charging and discharging currents, sampling time, battery terminal voltage, previous sampling instant battery charge state value and battery charging and discharging number pair
The influence of battery parameter, the information that fusion mass data is included, accuracy is high, and cost is relatively low.Application field of the present invention is extensive,
It can be the occasions such as the energy management of batteries of electric automobile, the protection of battery pack, be particularly suitable for large-power occasions.
In a kind of specific implementation mode of the present invention, the sensor group may include：Temperature sensor, wherein institute
It states temperature sensor and is close to the battery, to acquire the environment temperature of battery.
In a kind of specific implementation mode of the present invention, the sensor group may include：Current sensor, wherein institute
It states current sensor and is connected to the battery, to acquire the charging and discharging currents of battery.
In a kind of specific implementation mode of the present invention, the sensor group may include：Voltage sensor, wherein institute
It states voltage sensor and is connected to the battery, to acquire the terminal voltage of battery.
In a kind of specific implementation mode of the present invention, prestore previous battery charge state of the microprocessor measures
Value, and collect the number of the charge and discharge of battery.
In a kind of specific implementation mode of the present invention, the microprocessor is connected to host computer, on the host computer
It is based on immune algorithm Optimized BP Neural Network weights and threshold value using MATLAB softwares, establishes the mathematical model of lithium battery.
The present invention is based on BP neural network structure mathematical models to describe environment temperature, charging and discharging currents, charge and discharge number with
Non-linear relation between power battery charged state.BP neural network is built as shown in Figure 1, with environment temperature t, charge and discharge are electric
Flow I, sampling time T, battery terminal voltage U, the charge and discharge times N of power battery, previous sampling instant battery charge state SOC
(k-1) as input, current time battery charge state SOC (k) is as output, the BP neural network model of foundation.Using exempting from
Epidemic disease optimization algorithm optimizes the weights and threshold value of BP neural network, obtains the optimum performance of BP neural network.The stream of optimization
Journey is as shown in Figure 2：
Determine the topological structure of BP neural network；
The weights and threshold value of neural network are encoded, initiating antigen group is formed；
Initiating antigen is decoded, and is assigned to BP and puts in network；
BP neural network is trained using sample data；
BP neural network is tested using test sample, obtains the mistake between BP neural network output valve and actual value
Difference data；
According to above-mentioned error information, the fitness of antigen individual is evaluated；
Judge whether to meet condition, if it is, output result；If it is not, then according to the fitness of antigen individual, confrontation
Former group is promoted and is inhibited, and new antigen group is formed；
It returns (3), continues interative computation, until meeting the requirements.
In practical applications, as shown in figure 3, building BP neural network model using MATLAB Neural Network Toolbox
Afterwards, its weights and threshold value are determined using immune algorithm.It is then based on microprocessor programming and realizes above-mentioned BP neural network model.Often
A data are sampled every sampling time T, the charging and discharging currents I (k) of battery is obtained by current sensor, passes through voltage sensor
The terminal voltage U (k) for obtaining battery obtains environment temperature t (k) by temperature sensor and combines previous battery charge shape
State measurement data substitutes into BP neural network and is calculated, and estimates the value of current time battery charge state.
The present invention is based on immune algorithm Optimized BP Neural Network weights and threshold value on host computer using MATLAB softwares, builds
The mathematical model of vertical lithium battery, improves the precision of model.On this basis, the BP nerves after optimization are realized based on microprocessor
Network model reduces the cost of equipment, improves portability, the practicability of equipment.
When estimating power battery charged state, the present invention consider the sampling time, battery charging and discharging currents,
Terminal voltage, environment temperature t (k), charge and discharge number and the previous battery charge state measured value of battery are as BP nerves
The value of the input quantity estimation current time battery charge state of network, improves the precision of measuring device.
The preferred embodiment of the present invention is described in detail above in association with attached drawing, still, the present invention is not limited to above-mentioned realities
The detail in mode is applied, within the scope of the technical concept of the present invention, a variety of letters can be carried out to technical scheme of the present invention
Monotropic type, these simple variants all belong to the scope of protection of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case of shield, can be combined by any suitable means, in order to avoid unnecessary repetition, the present invention to it is various can
The combination of energy no longer separately illustrates.
In addition, various embodiments of the present invention can be combined randomly, as long as it is without prejudice to originally
The thought of invention, it should also be regarded as the disclosure of the present invention.
Claims (6)
1. a kind of battery SOC estimation device based on immune algorithm Optimized BP Neural Network, which is characterized in that the battery SOC is estimated
Counter device includes：Sensor group and the microprocessor for loading BP neural network model；Wherein, the sensor group acquires battery
Following data：Charging and discharging currents, terminal voltage, environment temperature, charge and discharge number and previous battery charge state measured value, institute
State the value that microprocessor estimates current time battery charge state according to the data acquired.
2. the battery SOC estimation device according to claim 1 based on immune algorithm Optimized BP Neural Network, feature exist
In the sensor group includes：Temperature sensor, wherein the temperature sensor is connected to the battery, to acquire battery
Environment temperature.
3. the battery SOC estimation device according to claim 1 based on immune algorithm Optimized BP Neural Network, feature exist
In the sensor group includes：Current sensor, wherein the current sensor is connected to the battery, to acquire battery
Charging and discharging currents.
4. the battery SOC estimation device according to claim 1 based on immune algorithm Optimized BP Neural Network, feature exist
In the sensor group includes：Voltage sensor, wherein the voltage sensor is connected to the battery, to acquire battery
Terminal voltage.
5. the battery SOC estimation device according to claim 1 based on immune algorithm Optimized BP Neural Network, feature exist
It prestores previous battery charge state measured value in, the microprocessor, and collects the number of the charge and discharge of battery.
6. the battery SOC estimation device according to claim 1 based on immune algorithm Optimized BP Neural Network, feature exist
In the microprocessor is connected to host computer, and immune algorithm optimization BP god is based on using MATLAB softwares on the host computer
Through network weight and threshold value, the mathematical model of lithium battery is established.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810329478.7A CN108572324A (en) | 2018-04-13 | 2018-04-13 | Battery SOC estimation device based on immune algorithm Optimized BP Neural Network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810329478.7A CN108572324A (en) | 2018-04-13 | 2018-04-13 | Battery SOC estimation device based on immune algorithm Optimized BP Neural Network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108572324A true CN108572324A (en) | 2018-09-25 |
Family
ID=63574647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810329478.7A Pending CN108572324A (en) | 2018-04-13 | 2018-04-13 | Battery SOC estimation device based on immune algorithm Optimized BP Neural Network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108572324A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109557475A (en) * | 2018-11-30 | 2019-04-02 | 北京新能源汽车股份有限公司 | Method and device for determining available capacity SOC of battery |
| CN109738807A (en) * | 2019-01-03 | 2019-05-10 | 温州大学 | The method for estimating SOC based on the BP neural network after ant group algorithm optimization |
| CN109895657A (en) * | 2019-03-22 | 2019-06-18 | 芜湖职业技术学院 | A kind of power battery SOC estimation device, automobile and method |
| CN109920516A (en) * | 2019-03-15 | 2019-06-21 | 重庆科技学院 | A kind of self-closing disease of user oriented experience embrace it is quick-witted can design setting model and decision parameters optimization method |
| CN109986997A (en) * | 2019-03-26 | 2019-07-09 | 芜湖职业技术学院 | A kind of power battery SOC prediction meanss, automobile and method |
| CN110689643A (en) * | 2019-09-24 | 2020-01-14 | 长安大学 | Intelligent networking automobile vehicle running state analysis method based on immune algorithm |
| CN111563826A (en) * | 2020-03-27 | 2020-08-21 | 青岛理工大学 | Battery information prediction system and method based on electric automobile power consumption behavior |
| CN114019380A (en) * | 2021-10-29 | 2022-02-08 | 天津市捷威动力工业有限公司 | Calendar life extension prediction method for battery cell |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231672A (en) * | 2008-02-02 | 2008-07-30 | 湖南大学 | Method for diagnosing soft failure of analog circuit base on modified type BP neural network |
| CN101964018A (en) * | 2010-08-26 | 2011-02-02 | 湘潭大学 | SOC estimation method of battery of electric vehicle |
| CN102721933A (en) * | 2012-06-29 | 2012-10-10 | 国家电网公司 | State of charge (SOC) evaluation method and SOC evaluation system of lithium ion battery |
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| CN105974327A (en) * | 2016-06-12 | 2016-09-28 | 广州市香港科大霍英东研究院 | Lithium battery pack SOC prediction method based on neural network and UKF |
| CN106443453A (en) * | 2016-07-04 | 2017-02-22 | 陈逸涵 | Lithium battery SOC estimation method based on BP neural network |
| CN106501721A (en) * | 2016-06-03 | 2017-03-15 | 湘潭大学 | A kind of lithium battery SOC estimation method based on biological evolution |
| CN106503794A (en) * | 2016-11-08 | 2017-03-15 | 上海电机学院 | A kind of gear case of blower method for predicting residual useful life |
| CN106779065A (en) * | 2016-11-30 | 2017-05-31 | 北京理工大学珠海学院 | The maximum power point tracing method and system of a kind of photovoltaic array |
-
2018
- 2018-04-13 CN CN201810329478.7A patent/CN108572324A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231672A (en) * | 2008-02-02 | 2008-07-30 | 湖南大学 | Method for diagnosing soft failure of analog circuit base on modified type BP neural network |
| CN101964018A (en) * | 2010-08-26 | 2011-02-02 | 湘潭大学 | SOC estimation method of battery of electric vehicle |
| CN102721933A (en) * | 2012-06-29 | 2012-10-10 | 国家电网公司 | State of charge (SOC) evaluation method and SOC evaluation system of lithium ion battery |
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| CN106501721A (en) * | 2016-06-03 | 2017-03-15 | 湘潭大学 | A kind of lithium battery SOC estimation method based on biological evolution |
| CN105974327A (en) * | 2016-06-12 | 2016-09-28 | 广州市香港科大霍英东研究院 | Lithium battery pack SOC prediction method based on neural network and UKF |
| CN106443453A (en) * | 2016-07-04 | 2017-02-22 | 陈逸涵 | Lithium battery SOC estimation method based on BP neural network |
| CN106503794A (en) * | 2016-11-08 | 2017-03-15 | 上海电机学院 | A kind of gear case of blower method for predicting residual useful life |
| CN106779065A (en) * | 2016-11-30 | 2017-05-31 | 北京理工大学珠海学院 | The maximum power point tracing method and system of a kind of photovoltaic array |
Non-Patent Citations (6)
| Title |
|---|
| 侯静等: "基于免疫遗传算法的BP神经网络模型", 《科技广场》 * |
| 吴斌等: "基于改进预测算法优化的风机齿轮箱维护策略", 《工业工程与管理》 * |
| 张国红 等: "电动汽车锂离子电池管理系统设计", 《2011中国电工技术学会学术年会论文集》 * |
| 朴昌浩 等: "基于人工神经网络的镍氢动力电池荷电状态预估", 《节能与新能源汽车年鉴.2010》 * |
| 赵妍: "《面向大数据的挖掘方法研究 第一版》", 31 July 2016, 电子科技大学出版社 * |
| 赵钢等: "基于BP神经网络的动力电池SOC估算", 《电源技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109557475A (en) * | 2018-11-30 | 2019-04-02 | 北京新能源汽车股份有限公司 | Method and device for determining available capacity SOC of battery |
| CN109738807A (en) * | 2019-01-03 | 2019-05-10 | 温州大学 | The method for estimating SOC based on the BP neural network after ant group algorithm optimization |
| CN109920516A (en) * | 2019-03-15 | 2019-06-21 | 重庆科技学院 | A kind of self-closing disease of user oriented experience embrace it is quick-witted can design setting model and decision parameters optimization method |
| CN109895657A (en) * | 2019-03-22 | 2019-06-18 | 芜湖职业技术学院 | A kind of power battery SOC estimation device, automobile and method |
| CN109986997A (en) * | 2019-03-26 | 2019-07-09 | 芜湖职业技术学院 | A kind of power battery SOC prediction meanss, automobile and method |
| CN109986997B (en) * | 2019-03-26 | 2022-05-03 | 芜湖职业技术学院 | Power battery SOC prediction device, automobile and method |
| CN110689643A (en) * | 2019-09-24 | 2020-01-14 | 长安大学 | Intelligent networking automobile vehicle running state analysis method based on immune algorithm |
| CN110689643B (en) * | 2019-09-24 | 2022-07-26 | 长安大学 | Intelligent networking automobile vehicle driving state analysis method based on immune algorithm |
| CN111563826A (en) * | 2020-03-27 | 2020-08-21 | 青岛理工大学 | Battery information prediction system and method based on electric automobile power consumption behavior |
| CN114019380A (en) * | 2021-10-29 | 2022-02-08 | 天津市捷威动力工业有限公司 | Calendar life extension prediction method for battery cell |
| CN114019380B (en) * | 2021-10-29 | 2024-05-17 | 天津市捷威动力工业有限公司 | Calendar life extension prediction method for battery cell |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108572324A (en) | Battery SOC estimation device based on immune algorithm Optimized BP Neural Network | |
| Murnane et al. | A closer look at state of charge (SOC) and state of health (SOH) estimation techniques for batteries | |
| CN103020445B (en) | A kind of SOC and SOH Forecasting Methodology of electric-vehicle-mounted ferric phosphate lithium cell | |
| Zheng et al. | A novel capacity estimation method based on charging curve sections for lithium-ion batteries in electric vehicles | |
| Pop et al. | Battery management systems: Accurate state-of-charge indication for battery-powered applications | |
| CN104267354B (en) | A kind of peak power Forecasting Methodology of electrokinetic cell | |
| Huria et al. | Simplified extended kalman filter observer for soc estimation of commercial power-oriented lfp lithium battery cells | |
| CN103969587A (en) | Power battery SOC (state of charge) estimation method for hybrid electric vehicles | |
| KR20170059208A (en) | Method of dynamically extracting entropy on battery | |
| CN104502858A (en) | Power battery SOC estimation method based on backward difference discrete model and system thereof | |
| CN104535932A (en) | Lithium ion battery charge state estimating method | |
| CN101430366A (en) | Battery charge state detection method | |
| CN103744026A (en) | Storage battery state of charge estimation method based on self-adaptive unscented Kalman filtering | |
| CN110426639B (en) | Lithium ion battery service life prediction method and system based on dynamic impedance spectrum | |
| CN110795851A (en) | Lithium ion battery modeling method considering environmental temperature influence | |
| CN110515011A (en) | A kind of Accurate Estimation Method of lithium-ion-power cell SOC | |
| CN102608540A (en) | Coulomb efficiency measuring method used for SOC (system-on-chip) evaluation of power battery | |
| CN107843845A (en) | SOH (State of health) online estimation method for power lithium ion battery | |
| Zhang et al. | Estimation of real-time peak power capability of a traction battery pack used in an HEV | |
| CN105203968A (en) | Lead-acid battery residual energy on-line measuring system | |
| KR20200031532A (en) | Secondary battery system and method of estimating an internal state of secondary battery | |
| CN103176137A (en) | Battery pack health condition evaluation method based on battery SOC (state of charge) inhomogeneity | |
| Cheng et al. | Extraction of intrinsic parameters of lead–acid batteries using energy recycling technique | |
| Paschero et al. | Estimation of lithium polymer cell characteristic parameters through genetic algorithms | |
| CN106093793A (en) | A kind of SOC estimation method based on battery discharge multiplying power and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180925 |