CN109738808A - The method of SOC is estimated based on the BP neural network after Simulated Anneal Algorithm Optimize - Google Patents
The method of SOC is estimated based on the BP neural network after Simulated Anneal Algorithm Optimize Download PDFInfo
- Publication number
- CN109738808A CN109738808A CN201910005852.2A CN201910005852A CN109738808A CN 109738808 A CN109738808 A CN 109738808A CN 201910005852 A CN201910005852 A CN 201910005852A CN 109738808 A CN109738808 A CN 109738808A
- Authority
- CN
- China
- Prior art keywords
- neural network
- soc
- threshold value
- weight
- power battery
- 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.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Secondary Cells (AREA)
Abstract
A kind of method that the present invention provides the BP neural network based on after Simulated Anneal Algorithm Optimize to estimate SOC, including determine BP neural network and the corresponding neuron of input layer, hidden layer, output layer, and determine weight and threshold value in BP neural network；It is iteratively solved using weight and threshold value as parameter to be optimized based on simulated annealing, obtain optimal location point, and by corresponding weight in obtained optimal location point and threshold value in BP neural network weight and threshold value updated accordingly, obtain updated BP neural network；The measured data for obtaining power battery external behavior imports in updated BP neural network as input, and obtained SOC value is required SOC estimated value.Implement the present invention, the shortcomings of the prior art can be overcome, it is ensured that can realize the accurate estimation to power battery SOC under the conditions of different battery status, dynamic load and temperature.
Description
Technical field
The present invention relates to power battery technology field more particularly to a kind of BP nerves based on after Simulated Anneal Algorithm Optimize
Network is come the method for estimating SOC.
Background technique
With the rapid development of our country's economy, the quantity of automobile is consequently increased rapidly, increasingly so as to cause environmental pollution
Seriously.While environmental pollution mouth becomes serious, the shortage problem of the non-renewable resources such as coal, petroleum is also more and more prominent.
Environmental pollution and the huge consumption of the energy will become the huge obstacle for hindering China's economic social development, and new-energy automobile is energetically
Popularization plays the role of the alleviation of this two large problems very big.But it is constrained to the technical level of battery at this stage, Ren Menli
The service efficiency that battery itself is improved with battery management system keeps battery efficient as far as possible under existence conditions.Cell tube
Most important technology is exactly SOC estimation technique in reason system, and SOC is for characterizing the remaining active volume of battery, i.e., in fixed current
Lower electric discharge, present battery it is remaining can discharge electricity amount and it is total can discharge electricity amount ratio.Since battery SOC cannot pass through instrument
Device directly measures, all indirect gains that can only be performed mathematical calculations using other external characteristics parameters of battery.
The estimation method of current battery SOC has very much, but they all have the defects that it is certain.For example, discharge test
Method is most reliable SOC estimation method, can be used for the electricity estimation of all batteries, by given current discharge, passes through electric current
It is obtained with the product of time and uses electricity, but time-consuming, and battery not can be carried out normal work during estimation, be not used to drive
Electric car when sailing.For another example, current integration method convenience of calculation, as long as acquisition real-time current, passes through the integral of Current versus time
It can estimate SOC, but as the error that the growth measurement of time generates can be accumulated constantly, cause to estimate accuracy decline.
For another example, the relatively-stationary functional relation of open-circuit voltage and SOC of the open circuit voltage method using battery after long-time is stood carries out
The estimation of SOC, this method is although simple and easy, and precision increases with the time of repose of battery and increased, however due to electric car
Frequent start-stop, battery are unable to get enough time of repose, so being not used to real-time estimation SOC.
Therefore, need it is a kind of estimate power battery SOC new method, can overcome the deficiencies in the prior art it
Place, it is ensured that the accurate estimation to power battery SOC can be realized under the conditions of different battery status, dynamic load and temperature.
Summary of the invention
The technical problem to be solved by the embodiment of the invention is that providing a kind of BP based on after Simulated Anneal Algorithm Optimize
Neural network can overcome the shortcomings of the prior art come the method for estimating SOC, it is ensured that different battery status, dynamic
The accurate estimation to power battery SOC can be realized under the conditions of load and temperature.
In order to solve the above-mentioned technical problem, the embodiment of the invention provides a kind of BP based on after Simulated Anneal Algorithm Optimize
Neural network is come the method for estimating SOC, comprising the following steps:
Step S1, BP neural network and its corresponding neuron of contained input layer, hidden layer, output layer are determined,
And according to input layer, hidden layer, the corresponding neuron of output layer in the BP neural network, the BP nerve is determined
Weight and threshold value in network；Wherein, the neuron of input layer is determined by power battery external behavior in the BP neural network；
The neuron of output layer is SOC value in the BP neural network；
Step S2, it is iteratively solved, is obtained based on simulated annealing using identified weight and threshold value as parameter to be optimized
To optimal location point, and by corresponding weight and threshold value in obtained optimal location point to the weight in the BP neural network
It is updated accordingly with threshold value, obtains updated BP neural network；
Wherein, the step S2 is implemented as follows:
The scale of population in step 21, initialization simulated annealing, maximum number of iterations, initial temperature and to be optimized
The dimension of parameter；
Step 22 generates two random initial points；Wherein, described two random initial points are by identified all weights
It is determined with threshold value, and each weight and threshold value have determined the coordinate in the one-dimensional space；
Step 23 is iterated update to temperature using moving back warm function；
Step 24, under Current Temperatures, carry out Markov chain length L iteration；
Step 25, row bound of being gone forward side by side using the next location point of state generation function generation are handled, so that newly generated position
The coordinate set in each some dimension is in range required by weight and threshold value；Wherein, described to generate function using state
The next location point generated is to calculate to generate on the basis of initial position；
The smallest optimum individual of fitness function value at this temperature is found in step 26, the judgement of Utilization assessment function；
Step 27, progress Metropolis criterion judge whether to receive new explanation, if receiving to continue, if not accepted, return
Return to step 25 iteration again；
Step 28 generates new location point after receiving, i.e. generation new explanation
Step 29, judge whether reach Markov chain length L, if not up to, return to step 25, if reaching, downwards into
Row；
Step 30 judges whether to reach algorithm stop criterion, if so, output new explanation is as a result, the new explanation should be that algorithm solves
Optimal location point out；If not back to step 23, continuation iteration, until meeting termination condition；
Step S3, the measured data of the power battery external behavior is obtained, and will be outside accessed power battery
The measured data of characteristic imports in the updated BP neural network, and obtained SOC value is required final SOC estimation
Value.
Wherein, the power battery external behavior includes electric current, voltage and temperature.
Wherein, in the power battery external behavior measured data of electric current, voltage and temperature be on power battery with
FUDS operating condition carries out acquisition when charge and discharge.
The implementation of the embodiments of the present invention has the following beneficial effects:
The present invention has stronger robustness using BP neural network, can be in different battery status, dynamic load and temperature
The lower work of degree, and the prior art is overcome the advantages that do not need mathematical model, any non-linear and complicated system can be handled
Present in shortcoming, it is ensured that can realize under the conditions of different battery status, dynamic load and temperature to power battery SOC's
It estimates, while further promoting the performance of BP neural network by Simulated Anneal Algorithm Optimize BP neural network, to improve
The estimation precision of power battery SOC.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without any creative labor, according to
These attached drawings obtain other attached drawings and still fall within scope of the invention.
Fig. 1 is a kind of BP neural network based on after Simulated Anneal Algorithm Optimize of proposition of the embodiment of the present invention to estimate
The flow chart of the method for SOC.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, the present invention is made into one below in conjunction with attached drawing
Step ground detailed description.
As shown in Figure 1, in the embodiment of the present invention, a kind of BP nerve net based on after Simulated Anneal Algorithm Optimize of proposition
Network is come the method for estimating SOC, comprising the following steps:
Step S1, BP neural network and its corresponding neuron of contained input layer, hidden layer, output layer are determined,
And according to input layer, hidden layer, the corresponding neuron of output layer in the BP neural network, the BP nerve is determined
Weight and threshold value in network；Wherein, the neuron of input layer is determined by power battery external behavior in the BP neural network；
The neuron of output layer is SOC value in the BP neural network；
Step S2, it is iteratively solved, is obtained based on simulated annealing using identified weight and threshold value as parameter to be optimized
To optimal location point, and by corresponding weight and threshold value in obtained optimal location point to the weight in the BP neural network
It is updated accordingly with threshold value, obtains updated BP neural network；
Step S3, the measured data of the power battery external behavior is obtained, and will be outside accessed power battery
The measured data of characteristic imports in the updated BP neural network, and obtained SOC value is required final SOC estimation
Value.
Detailed process is that in step sl, BP neural network is made of input layer, hidden layer and output layer, input layer
Neuron determines by power battery external behavior, and the neuron of hidden layer can be according to being actually adjusted (generally and input layer
Neuron it is corresponding), the neuron of output layer is SOC value.
At this point, the SOC expression of output layer is in BP neural networkF generation
Table activation primitive, expression formula areWherein, i indicates i-th of neuron of input layer from 1 to n；J from 1 to
N indicates j-th of neuron of hidden layer；K=1 indicates the number of output layer；wjiAnd wkjIndicate weight, wjiFor input layer
Weight of i-th of neuron to j-th of neuron of hidden layer, wkjFor k-th of neuron of output layer to j-th of neuron of hidden layer
Weight；θjAnd θkIndicate threshold value.
In one embodiment, power battery external behavior includes electric current, voltage and temperature, and power battery external behavior
The measured data of middle electric current, voltage and temperature is to carry out charge and discharge on power battery with the United States Federal city driving operating condition FUDS
When obtain.It should be noted that in order to meet the needs of BP neural network processing, the actual measurement of power battery external behavior
Data should be narrowed between [- 1,1] by moving average filtering denoising and normalization.
At this point, the neuron number of input layer have 3, the neuron number of hidden layer have the neuron of 3, output layer
Number has 1, obtain weight include input layer to hidden layer weight 3*3=9 and hidden layer to output layer weight 3*1=3
Totally 12, threshold value has 3+1=4.
In step s 2, step 21, the scale of population, maximum number of iterations, initial temperature in initialization simulated annealing
The dimension of degree and parameter to be optimized；
Step 22 generates two random initial points；Wherein, described two random initial points are by identified all weights
It is determined with threshold value, and each weight and threshold value have determined the coordinate in the one-dimensional space；
Step 23 is iterated update to temperature using moving back warm function；
Step 24, under Current Temperatures, carry out Markov chain length L iteration；
Step 25, row bound of being gone forward side by side using the next location point of state generation function generation are handled, so that newly generated position
The coordinate set in each some dimension is in range required by weight and threshold value；Wherein, described to generate function using state
The next location point generated is to calculate to generate on the basis of initial position；
The smallest optimum individual of fitness function value at this temperature is found in step 26, the judgement of Utilization assessment function；
Step 27, progress Metropolis criterion judge whether to receive new explanation, if receiving to continue, if not accepted, return
Return to step 25 iteration again；
Step 28 generates new location point after receiving, i.e. generation new explanation
Step 29, judge whether reach Markov chain length L, if not up to, return to step 25, if reaching, downwards into
Row；
Step 30 judges whether to reach algorithm stop criterion, if so, output new explanation is as a result, the new explanation should be that algorithm solves
Optimal location point out；If not back to step 23, continuation iteration, until meeting termination condition.
In step s3, the measured data of the measured data of electric current, voltage and temperature in power battery external behavior is obtained,
And import in updated BP neural network, obtained SOC value is required final SOC estimated value.
The implementation of the embodiments of the present invention has the following beneficial effects:
The present invention has stronger robustness using BP neural network, can be in different battery status, dynamic load and temperature
The lower work of degree, and the prior art is overcome the advantages that do not need mathematical model, any non-linear and complicated system can be handled
Present in shortcoming, it is ensured that can realize under the conditions of different battery status, dynamic load and temperature to power battery SOC's
It estimates, while further promoting the performance of BP neural network by Simulated Anneal Algorithm Optimize BP neural network, to improve
The estimation precision of power battery SOC.
Those of ordinary skill in the art will appreciate that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, the program can be stored in a computer readable storage medium,
The storage medium, such as ROM/RAM, disk, CD.
Above disclosed is only a preferred embodiment of the present invention, cannot limit the power of the present invention with this certainly
Sharp range, therefore equivalent changes made in accordance with the claims of the present invention, are still within the scope of the present invention.
Claims (3)
1. a kind of BP neural network based on after Simulated Anneal Algorithm Optimize is come the method for estimating SOC, which is characterized in that including with
Lower step:
Step S1, BP neural network and its corresponding neuron of contained input layer, hidden layer, output layer, and root are determined
According to input layer, hidden layer, the corresponding neuron of output layer in the BP neural network, the BP neural network is determined
In weight and threshold value；Wherein, the neuron of input layer is determined by power battery external behavior in the BP neural network；It is described
The neuron of output layer is SOC value in BP neural network；
Step S2, it is iteratively solved, is obtained most based on simulated annealing using identified weight and threshold value as parameter to be optimized
Excellent location point, and by corresponding weight and threshold value in obtained optimal location point to the weight and threshold in the BP neural network
Value is updated accordingly, obtains updated BP neural network；
Wherein, the step S2 is implemented as follows:
Scale, maximum number of iterations, initial temperature and the parameter to be optimized of population in step 21, initialization simulated annealing
Dimension；
Step 22 generates two random initial points；Wherein, described two random initial points are by identified all weights and threshold
Value determines, and each weight and threshold value have determined the coordinate in the one-dimensional space；
Step 23 is iterated update to temperature using moving back warm function；
Step 24, under Current Temperatures, carry out Markov chain length L iteration；
Step 25, row bound of being gone forward side by side using the next location point of state generation function generation are handled, so that newly generated location point
Coordinate in each dimension is in range required by weight and threshold value；Wherein, described to generate function generation using state
Next location point be on the basis of initial position calculate generate；
The smallest optimum individual of fitness function value at this temperature is found in step 26, the judgement of Utilization assessment function；
Step 27, progress Metropolis criterion judge whether to receive new explanation, if receiving to continue, if not accepted, return to
Step 25 iteration again；
Step 28 generates new location point after receiving, i.e. generation new explanation
Step 29 judges whether to reach Markov chain length L, if not up to, returning to step 25, if reaching, carries out downwards；
Step 30 judges whether to reach algorithm stop criterion, if so, output new explanation is as a result, the new explanation should be that algorithm solves
Optimal location point；If not back to step 23, continuation iteration, until meeting termination condition；
Step S3, the measured data of the power battery external behavior is obtained, and by accessed power battery external behavior
Measured data import in the updated BP neural network, obtained SOC value is required final SOC estimated value.
2. the method for estimating SOC based on the BP neural network after Simulated Anneal Algorithm Optimize as described in claim 1, special
Sign is that the power battery external behavior includes electric current, voltage and temperature.
3. the method for estimating SOC based on the BP neural network after Simulated Anneal Algorithm Optimize as claimed in claim 2, special
Sign is that the measured data of electric current, voltage and temperature is on power battery with FUDS work in the power battery external behavior
Condition carries out acquisition when charge and discharge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910005852.2A CN109738808B (en) | 2019-01-03 | 2019-01-03 | Method for estimating SOC (State of Charge) based on BP (Back propagation) neural network optimized by simulated annealing algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910005852.2A CN109738808B (en) | 2019-01-03 | 2019-01-03 | Method for estimating SOC (State of Charge) based on BP (Back propagation) neural network optimized by simulated annealing algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109738808A true CN109738808A (en) | 2019-05-10 |
| CN109738808B CN109738808B (en) | 2021-02-19 |
Family
ID=66363264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910005852.2A Active CN109738808B (en) | 2019-01-03 | 2019-01-03 | Method for estimating SOC (State of Charge) based on BP (Back propagation) neural network optimized by simulated annealing algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109738808B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717422A (en) * | 2019-09-25 | 2020-01-21 | 北京影谱科技股份有限公司 | Method and system for identifying interactive action based on convolutional neural network |
| CN115236535A (en) * | 2022-07-18 | 2022-10-25 | 湖北文理学院 | Battery SOC estimation method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700153A (en) * | 2014-12-05 | 2015-06-10 | 江南大学 | PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization |
| 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 |
| CN106815660A (en) * | 2017-01-23 | 2017-06-09 | 东南大学 | Customer charge combined optimization method based on simulated annealing |
| CN108365784A (en) * | 2017-11-24 | 2018-08-03 | 天津大学 | Based on the control method for brushless direct current motor for improving PSO-BP neural networks |
| CN109000733A (en) * | 2018-08-15 | 2018-12-14 | 西安科技大学 | Visibility sensor and its detection method based on simulated annealing optimization neural network |
-
2019
- 2019-01-03 CN CN201910005852.2A patent/CN109738808B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700153A (en) * | 2014-12-05 | 2015-06-10 | 江南大学 | PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization |
| CN106501721A (en) * | 2016-06-03 | 2017-03-15 | 湘潭大学 | A kind of lithium battery SOC estimation method based on biological evolution |
| CN106443453A (en) * | 2016-07-04 | 2017-02-22 | 陈逸涵 | Lithium battery SOC estimation method based on BP neural network |
| CN106815660A (en) * | 2017-01-23 | 2017-06-09 | 东南大学 | Customer charge combined optimization method based on simulated annealing |
| CN108365784A (en) * | 2017-11-24 | 2018-08-03 | 天津大学 | Based on the control method for brushless direct current motor for improving PSO-BP neural networks |
| CN109000733A (en) * | 2018-08-15 | 2018-12-14 | 西安科技大学 | Visibility sensor and its detection method based on simulated annealing optimization neural network |
Non-Patent Citations (1)
| Title |
|---|
| 周爱武等: "基于模拟退火算法改进的BP神经网络算法", 《微电子学与计算机》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717422A (en) * | 2019-09-25 | 2020-01-21 | 北京影谱科技股份有限公司 | Method and system for identifying interactive action based on convolutional neural network |
| CN115236535A (en) * | 2022-07-18 | 2022-10-25 | 湖北文理学院 | Battery SOC estimation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109738808B (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guo et al. | SoC estimation of Lithium battery based on improved BP neural network | |
| CN110554324B (en) | SOC and SOH joint estimation method | |
| CN112269134B (en) | Battery SOC and SOH joint estimation method based on deep learning | |
| CN113030764A (en) | Battery pack health state estimation method and system | |
| CN112557907A (en) | SOC estimation method of electric vehicle lithium ion battery based on GRU-RNN | |
| CN112540298B (en) | Lithium ion battery SOC estimation method based on deep-migration learning | |
| CN106501721A (en) | A kind of lithium battery SOC estimation method based on biological evolution | |
| CN104077664B (en) | Confidence capacity assessment method of energy storage and generation system of wind power | |
| CN110659693A (en) | K-nearest neighbor classification-based rapid topology identification method and system for power distribution network and readable storage medium | |
| CN108376985A (en) | A kind of electric vehicle charging load model is established and node voltage computational methods | |
| CN109346787B (en) | Self-adaptive optimized charging method for power battery of electric automobile | |
| CN105225000A (en) | A kind of wind power probability model nonparametric probability method optimized based on Fuzzy Ordered | |
| CN109738808A (en) | The method of SOC is estimated based on the BP neural network after Simulated Anneal Algorithm Optimize | |
| Liu et al. | Wind power short-term forecasting based on LSTM neural network with dragonfly algorithm | |
| CN110212592A (en) | Fired power generating unit Load Regulation maximum rate estimation method and system based on piecewise linearity expression | |
| Monteiro et al. | Long-term sizing of lead–acid batteries in order to reduce technical losses on distribution networks: A distributed generation approach | |
| CN106443496A (en) | Battery charge state estimation method with improved noise estimator | |
| CN116796403A (en) | Building energy saving method based on comprehensive energy consumption prediction of commercial building | |
| CN116960487B (en) | Sodium ion battery system capacity estimation method and device considering monomer inconsistency | |
| CN102880917B (en) | Method for predicting medium-term and long-term power load on basis of logarithmical load density growth curve | |
| CN109738807A (en) | The method for estimating SOC based on the BP neural network after ant group algorithm optimization | |
| CN112332416A (en) | Power distribution network load prediction method and system based on photovoltaic electric heating load correlation | |
| CN117572236A (en) | Lithium battery state of charge estimation method based on transfer learning | |
| CN111369159A (en) | Reliability assessment method for electric power traffic coupling network | |
| CN112332446B (en) | Distributed power supply planning method and device based on K-medoid cluster analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190510 Assignee: Tianjin Aikong Technology Co.,Ltd. Assignor: Wenzhou University Contract record no.: X2023330000260 Denomination of invention: Method for estimating SOC based on BP neural network optimized by simulated annealing algorithm Granted publication date: 20210219 License type: Common License Record date: 20230424 |