CN113761789A - Method for estimating SOC of battery based on BP neural network optimized by firefly swarm algorithm - Google Patents
Method for estimating SOC of battery based on BP neural network optimized by firefly swarm algorithm Download PDFInfo
- Publication number
- CN113761789A CN113761789A CN202110834539.7A CN202110834539A CN113761789A CN 113761789 A CN113761789 A CN 113761789A CN 202110834539 A CN202110834539 A CN 202110834539A CN 113761789 A CN113761789 A CN 113761789A
- Authority
- CN
- China
- Prior art keywords
- firefly
- neural network
- value
- battery
- fluorescein
- 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
- 241000254158 Lampyridae Species 0.000 title claims abstract description 100
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 35
- 210000002569 neuron Anatomy 0.000 claims abstract description 36
- 238000005457 optimization Methods 0.000 claims abstract description 6
- 238000010606 normalization Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 4
- GNBHRKFJIUUOQI-UHFFFAOYSA-N fluorescein Chemical compound O1C(=O)C2=CC=CC=C2C21C1=CC=C(O)C=C1OC1=CC(O)=CC=C21 GNBHRKFJIUUOQI-UHFFFAOYSA-N 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 4
- 241000238631 Hexapoda Species 0.000 claims description 2
- 230000007704 transition Effects 0.000 claims description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 abstract 1
- 229910052744 lithium Inorganic materials 0.000 abstract 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 3
- 229910001416 lithium ion Inorganic materials 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Secondary Cells (AREA)
Abstract
The invention provides a method for estimating the SOC of a battery based on a BP neural network optimized by a firefly swarm algorithm, and belongs to the technical field of battery management of electric vehicles. The method comprises the following steps: acquiring the state of charge and external characteristic data of the power battery, and carrying out normalization processing on the external characteristic data; optimizing the BP neural network by using a firefly group algorithm, wherein the optimization content comprises the number of neurons of the optimal hidden layer, weight values and threshold values, the weight values and the threshold values of the optimal hidden layer are used as parameters to be optimized, iterative solution is carried out on the basis of the firefly group algorithm, and the BP neural network is updated by using the weight values and the threshold values corresponding to the optimal position points; and finally, estimating the SOC of the battery through the optimized BP neural network. The method can dynamically predict the SOC of the battery, namely, the SOC of the lithium battery can be accurately estimated under different battery states.
Description
Technical Field
The invention belongs to the technical field of electric vehicle battery management, and particularly relates to a method for estimating battery SOC based on a firefly swarm algorithm optimized BP neural network.
Background
Transportation carbon emissions account for 24% of fuel combustion from a global perspective, leading to global warming and climate change problems. To address these problems, electric vehicles have proven to be a good alternative to using batteries as a substitute for diesel and gasoline. The electric automobile is popular because of reducing carbon emission and improving performance and efficiency, and the accurate estimation of the SOC of the lithium ion battery is a necessary condition for improving the endurance, the service life and the safety of the electric automobile.
Because the internal structure of a power battery system of the electric automobile is extremely complex and has complex nonlinearity, a battery equivalent model is difficult to accurately establish; in order to ensure the stable and safe operation of the electric automobile, the SOC of the battery needs to be accurately predicted with high precision. At present, the domestic and foreign common method for estimating the state of charge of the battery mainly comprises the following steps: open circuit voltage method, ampere-hour integral method, Kalman filtering method, neural network method, etc. However, these methods have their own drawbacks, and many researchers combine the above methods to estimate SOC. The open-circuit voltage method needs to keep the lithium ion battery still for a long enough time, and is difficult to apply to real-time measurement of the battery; the ampere-time integration method is the most common method for estimating the SOC of the lithium ion battery, the current value to be measured is accurate enough, and no feedback correction is carried out; the Kalman filtering method needs to carry out high-precision modeling on the battery, has strong dependence on a model, and is too complex and not beneficial to calculation; the neural network method takes factors such as voltage, current and internal resistance as input samples, and then realizes the estimation of the SOC of the battery by training a network, but the method is greatly influenced by the sample precision.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for estimating the SOC of a battery based on a BP neural network after the firefly swarm algorithm is optimized, so that the accurate estimation of the SOC of the power battery can be realized under different battery states.
The present invention achieves the above-described object by the following technical means.
The method for estimating the SOC of the battery based on the BP neural network optimized by the firefly swarm algorithm comprises the following steps:
s1, acquiring the state of charge and external characteristic data of the power battery, and carrying out normalization processing on the external characteristic data;
s2, optimizing the BP neural network by using a firefly swarm algorithm, iteratively solving the weight and the threshold of the optimal hidden layer as parameters to be optimized based on the firefly swarm algorithm, and updating the BP neural network by using the weight and the threshold corresponding to the optimal position point;
and S3, importing the measured external characteristic data of the power battery into the updated BP neural network, and obtaining an output value which is the SOC of the battery.
In a further technical scheme, the weight and the threshold of the optimal hidden layer are used as parameters to be optimized, iterative solution is carried out based on a firefly swarm algorithm, and the weight and the threshold corresponding to the optimal position point are used for updating the BP neural network, specifically:
s2.1, coding the fireflies by taking the weight and the threshold of the optimal hidden layer as parameters to be optimized, wherein each firefly is expressed as X (t) ═ (V)11,...Vnm,b1,...bm,W11,...Wmk,θ1,...θk) In which V isnmRepresenting the weight of the input layer nth neuron to the hidden layer mth neuron, bmThreshold, W, representing the mth neuron of the hidden layermkRepresents the weight, θ, from the mth neuron of the hidden layer to the kth neuron of the output layerkA threshold value representing an output layer neuron;
s2.2, calculating the fitness of each current firefly by taking the reciprocal of the root mean square error between the predicted output of the BP neural network and the expected output as a fitness function and comparing the fitness with the expected output, wherein the maximum value is marked as CtT is the current iteration number;
s2.3, calculating the position x of each firefly p in the population in t +1 iterationsp(t +1) and simultaneously solving the fluorescein value of the firefly p;
s2.4, if the firefly p finds out the firefly q with a better fluorescein value in the neighborhood set, the firefly p moves towards the direction of the firefly q with the better fluorescein value;
s2.5, updating step length
S2.6, updating the decision radius
S2.7, comparing the maximum value C of the fitness when the ending condition is mettAnd taking the maximum value as an optimal position point, obtaining an optimal weight value and a threshold value corresponding to the optimal position point, and giving the optimal weight value and the threshold value to the BP neural network, wherein t is 1, 2, 3 … Nmax，NmaxIs the maximum number of iterations.
In a further technical scheme, the fitness function has a formula of
Wherein y iscIs BP neural netExpected output value o of c-th nodecPredicting an output value, x, for the c-th node of the BP neural networkh(t) indicates the position of the h-th firefly.
In a further technical scheme, the solving formula of the fluorescein value is lp(t+1)＝(1-ρ)lp(t)+γf(xp(t +1)), wherein lp(t) is the fluorescein value of the firefly p in the tth iteration, rho fluorescein volatility coefficient, rho is the (0,1), and gamma is the fluorescein update rate.
In a further technical scheme, the firefly P moves towards the firefly q with a better fluorescein value in the direction of transition probability Ppq(t) shifted position with weight
Wherein
XpPosition of firefly p, XqPosition of firefly q, NpThe number of fireflies with the fluorescein value higher than that of the fireflies per se is collected in the neighborhood of the fireflies p; if there is no firefly q with a better fluorescein value in the neighborhood set for firefly p, the shifted position is
XbestThe most firefly sites for fluorescein.
In a further technical scheme, the step length adopts the following formula:
wherein d ismaxThe maximum distance between the firefly with the highest fluorescein value and other fireflies.
In a further technical solution, the formula of the decision radius is: r isp(t+1)＝min(rs,max{0,rp(t)+β(nt-|Np(t) |) }), where r issFor firefly to perceive radius, ntThe maximum number of neighbors allowed around the firefly is defined, and beta is the neighborhood change rate.
In a further technical scheme, the upper limit of the number of the neurons of the hidden layer of the BP neural network is 100 for optimization, 5 is taken as a step length from 5 to 100 for optimization, the neural networks containing different numbers of the neurons of the hidden layer are trained, errors of the neural networks are calculated, and the minimum error is taken as the optimal number of the hidden neurons.
The invention has the beneficial effects that:
the method is used for optimizing the firefly swarm algorithm of the BP neural network, and when the position is updated, whether the firefly p has the firefly q with a better fluorescein value in a neighborhood set or not is considered, and different moving directions are set; and when the step length is updated, an unfixed step length formula is set, so that the optimized BP neural network is more accurate in estimating the SOC of the power battery.
Drawings
FIG. 1 is a schematic diagram of the BP neural network structure according to the present invention;
fig. 2 is a flowchart of a method for estimating the SOC of a battery based on a firefly population algorithm optimized BP neural network according to the present invention.
Detailed Description
The invention will be further described with reference to the following figures and specific examples, without limiting the scope of the invention.
As shown in fig. 2, the method for estimating the SOC of the battery based on the BP neural network optimized by the firefly swarm algorithm is specifically implemented according to the following steps:
the method comprises the following steps of (1) acquiring the charge state and external characteristic data of the power battery, and carrying out normalization processing on the external characteristic data;
the external characteristic data comprises voltage, current and temperature; the data normalization process is carried out by formula
Reducing the range of external characteristic data to [0, 1 ]]In which X*Denotes the normalized value, xmaxIs the maximum value, x, in the external characteristic dataminIs the minimum value of the external characteristic data, and x is the external characteristic data.
And (2) constructing a BP neural network structure model (as shown in figure 1, X1, X2 and X3 in the figure respectively represent voltage, current and temperature, phi 1 … … phi m represents the number of neurons of the hidden layer, Y1 represents the SOC of the battery), optimizing the BP neural network by using a firefly swarm algorithm, wherein the optimization content comprises the number of the neurons of the optimal hidden layer, a weight value and a threshold value, iteratively solving the weight value and the threshold value of the optimal hidden layer as parameters to be optimized based on the firefly swarm algorithm, and updating the BP neural network by using the weight value and the threshold value corresponding to the optimal position point.
The BP neural network structure is determined by the number of input layers, hidden layers and output layers and respective neurons; the number of neurons of the input layer is determined by the external characteristics of the battery; when the number of the neurons of the hidden layer is more, the error of the estimated battery SOC is smaller (namely the fitting degree is higher), but the time spent is also increased correspondingly, so that the upper limit is taken as 100 for optimizing, namely the optimization is carried out by 5-100 steps, the neural network containing different numbers of the neurons of the hidden layer is trained and the error is calculated, and the minimum error is taken as the optimal number of the hidden neurons; the value of the neuron of the output layer is the SOC value.
SOC representation of the BP neural network output layer as
Wherein f is sigmoid function and the expression is
n is the number of neurons in the input layer, m is the number of neurons in the hidden layer, and k is the number of neurons in the output layer (1 is taken); vijAnd WjkRepresents a weight value, VijRepresents the weight of the ith neuron in the input layer to the jth neuron in the hidden layer, WjkRepresenting weights from the jth neuron of the hidden layer to the kth neuron of the output layer; bjThreshold, θ, representing the jth neuron of the hidden layerkThreshold, x, representing output layer neuronsiRepresenting the value of the ith neuron in the input layer.
Iterative solution is carried out by taking the weight and the threshold of the optimal hidden layer as parameters to be optimized based on a firefly swarm algorithm, and the specific steps of updating the BP neural network by using the weight and the threshold corresponding to the optimal position point comprise:
step (2.1), population initialization, setting H fireflies and initial moving step length s0Volatility coefficient rho, fluorescein updating rate gamma and maximum iteration number NmaxAnd assigning the same fluorescein and sensing radius to each firefly;
step (2.2), firefly coding, namely coding the firefly by taking the weight and the threshold of the optimal hidden layer as parameters to be optimized, wherein each firefly can be expressed as:
X(t)＝(V11,...Vnm,b1,...bm,W11,...Wmk,θ1,...θk)
and (2.3) setting a fitness function, taking the reciprocal of the root mean square error between the predicted output and the expected output as the fitness function, and adopting a calculation formula as follows:
wherein y iscExpected output value (i.e. state of charge), o, for the c-th node of the BP neural networkcPredicting an output value for the c node of the BP neural network; calculating the adaptability of each current fluorescent insect and comparing the sizes, and recording the maximum value as CtT is the current iteration number, xh(t) indicates the position of the h-th firefly.
Step (2.4), updating fluorescein, calculating the position x of each firefly p in the population in t +1 iterationsp(t +1) fitness value, reuse of equation lp(t+1)＝(1-ρ)lp(t)+γf(xp(t +1)), the fluorescein value of firefly p, where lp(t) is a fluorescein value of the firefly p in the t iteration, and rho epsilon (0,1) is a constant and represents a fluorescein volatilization coefficient; gamma is the fluorescein renewal rate.
Step (2.5), updating the position, calculating a neighborhood set, and if the firefly P finds the firefly q with a better fluorescein value in the neighborhood set, moving the firefly P towards the firefly q with the better fluorescein value to transfer the probability Ppq(t) is weight shiftMoving to obtain the moved position
If firefly p does not have a firefly q with a better fluorescein value in the neighborhood set, the shifted position is
Wherein
NpThe number of fireflies with a higher fluorescein value than that of the fireflies in the neighborhood of the fireflies p, XbestThe location of the most firefly of fluorescein, XpPosition of firefly p, XqThe location of firefly q.
Step (2.6), step length is updated, if the step length s is a fixed value, the algorithm is easy to fall into local optimum, and the step length s is enabled to be a fixed value
dmaxThe maximum distance between the firefly with the highest fluorescein value and other fireflies.
Step (2.7), updating the decision radius, wherein the radius is increased if the density of surrounding fireflies is small because the distribution density of the fireflies in the space is inconsistent, so that a larger number of individuals are searched; otherwise, the radius is reduced, and the radius formula is as follows: r isp(t+1)＝min(rs，max{0，rp(t)+β(nt-|Np(t) |) }), where r issFor firefly to perceive radius, ntThe maximum value of the number of neighbors allowed around the firefly, and beta is the neighborhood change rate.
Step (2.8), judging the end condition, not meeting the maximum iteration number NmaxAnd (5) returning to the step (2.4); otherwise, comparing the fitness maximum value Ct，t＝1，2，3...NmaxAnd taking the maximum value as an optimal position point, obtaining the optimal weight value and the threshold value corresponding to the optimal position point, and giving the optimal weight value and the threshold value to the BP neural network.
And (3) acquiring measured external characteristic data of the power battery, and introducing the measured external characteristic data into the updated BP neural network to obtain an output value, namely the SOC of the battery.
The present invention is not limited to the above-described embodiments, and any obvious improvements, substitutions or modifications can be made by those skilled in the art without departing from the spirit of the present invention.
Claims (8)
1. The method for estimating the SOC of the battery based on the BP neural network optimized by the firefly swarm algorithm is characterized by comprising the following steps of:
s1, acquiring the state of charge and external characteristic data of the power battery, and carrying out normalization processing on the external characteristic data;
s2, optimizing the BP neural network by using a firefly swarm algorithm, iteratively solving the weight and the threshold of the optimal hidden layer as parameters to be optimized based on the firefly swarm algorithm, and updating the BP neural network by using the weight and the threshold corresponding to the optimal position point;
and S3, importing the measured external characteristic data of the power battery into the updated BP neural network, and obtaining an output value which is the SOC of the battery.
2. The method for estimating the SOC of the battery based on the firefly swarm algorithm-optimized BP neural network according to claim 1, wherein the weight and the threshold of the optimal hidden layer are iteratively solved based on the firefly swarm algorithm with the weight and the threshold corresponding to the optimal position point as parameters to be optimized, and the method updates the BP neural network with the weight and the threshold corresponding to the optimal position point specifically comprises:
s2.1, coding fireflies by taking the weight and threshold of the optimal hidden layer as parameters to be optimized, wherein each firefly is expressed as X (t) ═ V11,...Vnm,b1,...bm,W11,...Wmk,θ1,...θk) In which V isnmRepresenting the weight of the input layer nth neuron to the hidden layer mth neuron, bmThreshold, W, representing the mth neuron of the hidden layermkRepresenting weights from the mth neuron of the hidden layer to the kth neuron of the output layerValue of thetakA threshold value representing an output layer neuron;
s2.2, calculating the fitness of each current fluorescent insect and comparing the fitness with the fitness function by taking the reciprocal of the root mean square error between the predicted output of the BP neural network and the expected output, and marking the maximum value as CtT is the current iteration number;
s2.3, calculating the position x of each firefly p in the population in t +1 iterationsp(t +1) and simultaneously solving the fluorescein value of the firefly p;
s2.4, if the firefly p finds the firefly q with a better fluorescein value in the neighborhood set, the firefly p moves towards the direction of the firefly q with the better fluorescein value;
s2.5, updating step length
S2.6, updating the decision radius
S2.7, comparing the maximum value C of the fitness when the ending condition is mettAnd taking the maximum value as an optimal position point, obtaining an optimal weight value and a threshold value corresponding to the optimal position point, and giving the optimal weight value and the threshold value to the BP neural network, wherein t is 1, 2, 3 … Nmax，NmaxIs the maximum number of iterations.
3. The method of claim 2, wherein the fitness function is formulated as
Wherein y iscExpected output value, o, for the c-th node of BP neural networkcPredicting an output value, x, for the c-th node of the BP neural networkh(t) indicates the position of the h-th firefly.
4. The method of claim 3, wherein the solution formula of the fluorescein value is lp(t+1)＝(1-ρ)lp(t)+γf(xp(t +1)), wherein lp(t) is the fluorescein value, rho fluorescein volatility coefficient, of firefly p in the tth iteration, and rhoEpsilon (0,1), and gamma is the fluorescein update rate.
5. The method of claim 4, wherein the firefly P moves towards the firefly q with better fluorescein value with transition probability Ppq(t) shifted position with weight
Wherein
XpPosition of firefly p, XqPosition of firefly q, NpThe number of fireflies with the fluorescein value higher than that of the fireflies per se is collected in the neighborhood of the fireflies p; if there is no firefly q with better fluorescein value in the neighborhood set for firefly p, the shifted position is
XbestThe most firefly sites for fluorescein.
6. The method for estimating the SOC of the battery based on the firefly swarm algorithm optimized BP neural network of claim 5, wherein the step size is represented by the following formula:
wherein d ismaxThe maximum distance between the firefly with the highest fluorescein value and other fireflies.
7. The method for estimating the SOC of the battery according to claim 6, wherein the formula of the decision radius is as follows: r isp(t+1)＝min(rs,max{0,rp(t)+β(nt-|Np(t) |) }), where r issFor firefly to perceive radius, ntIs fireflyThe maximum number of neighbors allowed around, beta is the neighborhood change rate.
8. The method for estimating the SOC of the battery according to claim 1, wherein the upper limit of the number of the neurons in the hidden layer of the BP neural network is optimized to 100, the optimization is performed in 5-100 steps, the neural network with different numbers of the neurons in the hidden layer is trained, the error is calculated, and the minimum error is used as the optimal number of the hidden neurons.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834539.7A CN113761789A (en) | 2021-07-23 | 2021-07-23 | Method for estimating SOC of battery based on BP neural network optimized by firefly swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834539.7A CN113761789A (en) | 2021-07-23 | 2021-07-23 | Method for estimating SOC of battery based on BP neural network optimized by firefly swarm algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113761789A true CN113761789A (en) | 2021-12-07 |
Family
ID=78787818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110834539.7A Pending CN113761789A (en) | 2021-07-23 | 2021-07-23 | Method for estimating SOC of battery based on BP neural network optimized by firefly swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113761789A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359762A (en) * | 2023-04-27 | 2023-06-30 | 北京玖行智研交通科技有限公司 | Battery state of charge estimation method based on deep learning and network compression |
| CN117074437A (en) * | 2023-10-11 | 2023-11-17 | 青岛金诺德科技有限公司 | Nondestructive testing method and application thereof in recovery of lithium battery of new energy automobile |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111582541A (en) * | 2020-03-27 | 2020-08-25 | 合肥学院 | Firefly algorithm-based inland inundation model prediction method |
-
2021
- 2021-07-23 CN CN202110834539.7A patent/CN113761789A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111582541A (en) * | 2020-03-27 | 2020-08-25 | 合肥学院 | Firefly algorithm-based inland inundation model prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 张丽红: "萤火虫优化算法及其在流水线调度问题中的应用研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 4, pages 21 - 22 * |
| 王丙元 等: "基于GSO-BP神经网络的磷酸铁锂电池SOC预测", 《中国民航大学学报》, vol. 36, no. 5, pages 60 - 64 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359762A (en) * | 2023-04-27 | 2023-06-30 | 北京玖行智研交通科技有限公司 | Battery state of charge estimation method based on deep learning and network compression |
| CN116359762B (en) * | 2023-04-27 | 2024-05-07 | 北京玖行智研交通科技有限公司 | Battery state of charge estimation method based on deep learning and network compression |
| CN117074437A (en) * | 2023-10-11 | 2023-11-17 | 青岛金诺德科技有限公司 | Nondestructive testing method and application thereof in recovery of lithium battery of new energy automobile |
| CN117074437B (en) * | 2023-10-11 | 2024-01-12 | 青岛金诺德科技有限公司 | Nondestructive testing method and application thereof in recovery of lithium battery of new energy automobile |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114372417A (en) | Electric vehicle battery health state and remaining life evaluation method based on charging network | |
| CN110175672A (en) | The battery charging state assessment system and appraisal procedure combined based on Extended Kalman filter and Genetic BP Neutral Network | |
| CN113702843B (en) | Lithium battery parameter identification and SOC estimation method based on suburb optimization algorithm | |
| CN111007399A (en) | Lithium battery state of charge prediction method based on improved generation countermeasure network | |
| CN111398832A (en) | Bus battery SOC prediction method based on ANFIS model | |
| CN113761789A (en) | Method for estimating SOC of battery based on BP neural network optimized by firefly swarm algorithm | |
| CN113253116A (en) | Lithium ion battery state of charge estimation method and storage medium | |
| CN114970332B (en) | Lithium battery model parameter identification method based on chaotic quantum sparrow search algorithm | |
| CN115983134B (en) | Battery power state prediction method and system based on neural network | |
| CN112883632B (en) | Lithium battery equivalent circuit model parameter identification method based on improved ant colony algorithm | |
| CN116609676B (en) | Method and system for monitoring state of hybrid energy storage battery based on big data processing | |
| CN116774088A (en) | Lithium ion battery health state estimation method based on multi-objective optimization | |
| CN112269133B (en) | SOC estimation method based on pre-charging circuit model parameter identification | |
| CN112465160A (en) | VR-based vehicle maintenance auxiliary system | |
| CN112649736A (en) | SOC and SOH joint estimation method for retired battery | |
| CN110570042B (en) | Short-term electric vehicle charging load prediction method and system | |
| CN116125278A (en) | Lithium battery SOC estimation method and system based on LSTM-EKF algorithm | |
| CN117391233A (en) | Electric automobile charging load prediction method and system | |
| CN111260015A (en) | Lithium ion battery model parameter identification method based on chaotic cat swarm algorithm | |
| CN117150334B (en) | Lithium battery multi-condition prediction method and device based on optimized BiLSTM neural network | |
| CN116819372A (en) | Method for calculating health state of energy storage battery by neural network | |
| CN115327389A (en) | Lithium battery SOC estimation method based on genetic algorithm improved double-Kalman filtering | |
| CN112578286B (en) | Battery SOC estimation method and device | |
| CN115648973B (en) | Improved DDPG reinforcement learning hybrid energy management method based on local sensitive hash | |
| CN117630682B (en) | Random degradation process-based RUL prediction method for lithium ion battery |
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 |