CN114895206B - Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm - Google Patents
Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm Download PDFInfo
- Publication number
- CN114895206B CN114895206B CN202210448979.3A CN202210448979A CN114895206B CN 114895206 B CN114895206 B CN 114895206B CN 202210448979 A CN202210448979 A CN 202210448979A CN 114895206 B CN114895206 B CN 114895206B
- Authority
- CN
- China
- Prior art keywords
- neural network
- rbf neural
- generation
- improved
- soh
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/389—Measuring internal impedance, internal conductance or related variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- 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
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Abstract
The invention discloses a lithium ion battery SOH estimation method based on an RBF neural network of an improved gray wolf optimization algorithm, which comprises the following steps: 1. collecting historical data of a battery to be tested, 2, extracting characteristics based on a charging voltage curve and an incremental capacity curve, 3, constructing an improved RBF neural network, optimizing parameters in the network by adopting an improved gray wolf optimization algorithm based on the training set, and 4, estimating SOH based on a trained model. The method can solve the problems that the traditional RBF neural network is difficult to track the global linear change of the SOH of the battery and is easy to sink into local optimum, thereby improving the estimation precision of the model on the SOH of the lithium ion battery.
Description
Technical Field
The invention belongs to the technical field of power battery management, and particularly relates to a lithium ion battery SOH estimation method based on an RBF neural network of an improved gray wolf optimization algorithm.
Background
Lithium ion batteries have been developed as the most important driving energy source for electric vehicles at present by virtue of the advantages of high energy density, low self-discharge rate and the like. However, as the battery continues to operate, its performance may change, and may also present a safety problem, which directly limits the widespread popularity of electric vehicles. The state of health (SOH) of the battery is one of the most important parameters of the power battery management system, and accurately estimating the state of health not only helps to solve the above problem, but also improves the estimation accuracy of other parameters, such as: state of charge, state of energy.
Current SOH estimation methods are roughly classified into model-based methods and data-driven based methods. Although the model-based method has higher interpretability, the effect of the model-based method is greatly different according to the selection of the model, and the estimation accuracy is lower. Due to the development of big data technology and artificial intelligence technology, the SOH estimation method based on data driving has good application prospect. Among them, neural network algorithms are widely used in SOH estimation. However, the neural network-based SOH estimation method has some limitations. First, it is clearly known that the capacity decreases with an increase in charge-discharge period according to the battery aging principle, which indicates that the battery state-of-health degradation data can be regarded as a long-term time series. However, since the hidden layer function of the neural network nonlinearly converts the input characteristics, the direct linear correlation between the characteristics and SOH decreases. Therefore, the estimated SOH gradually deviates from the true value in the latter period, and the long-term linear change process cannot be accurately followed. Secondly, the traditional neural network has the problems of low convergence speed, easy sinking of local optimum, overfitting and the like in parameter selection. In recent years, the application of meta-heuristics in neural network training has attracted attention from many scientists, and the performance of neural networks has been greatly improved. There are many disadvantages such as slow convergence speed, poor intelligent searching ability, etc. that require further investigation. Therefore, how to optimize the parameters of the neural network in SOH estimation becomes another problem.
Disclosure of Invention
The invention aims to solve the defects of the prior art, and provides a lithium ion battery SOH estimation method based on an RBF neural network for improving a gray wolf optimization algorithm, so as to solve the problems that the traditional RBF neural network is difficult to track global linear change of the battery SOH and is easy to sink into local optimum, thereby improving the estimation precision of a model on the lithium ion battery SOH.
The invention discloses a lithium ion battery SOH estimation method based on an RBF neural network of an improved gray wolf optimization algorithm, which is characterized by comprising the following steps:
step S1, data acquisition:
carrying out n times of charging and discharging on any lithium battery, and recording current, voltage, temperature and time data of the lithium battery and the complete capacity of each discharging in the charging and discharging process;
step S2, constant current charging time f in the kth charging process 1 k Constant voltage charge time
Peak +.>
Peak->
Corresponding position->
The feature vector as the kth input is +.>
The true state of health value SOH of the kth lithium battery is taken as an output value +.>
From the input feature matrix f= [ F 1 ；F 2 ；…；F k ；…；F n ]And output vector +.>
Forming a training set;
s3, constructing an improved RBF neural network, and optimizing parameters in the network by adopting an improved gray wolf optimization algorithm based on the training set;
step 3.1, constructing an improved RBF neural network by using the formula (1):
in the formula (1), w i Representing the connection weights of the ith hidden layer node and the output nodes in the RBF neural network, and marking a vector formed by the connection weights of all hidden layer nodes and the output nodes in the RBF neural network as w and c i Representing the central point of the activation function at the i-th hidden layer node in the RBF neural network, marking a matrix formed by the central points of the activation functions at all hidden layer nodes in the RBF neural network as c, wherein phi is a coefficient of a linear polynomial, and h represents the number of hidden layer nodes; g (F-c) i ) Is an activation function of the hidden layer and is derived from equation (2):
in the formula (2), sigma i Is the variance parameter of the node of the i hidden layer in the RBF neural network; the vector formed by the variance parameters of all hidden layer nodes in the RBF neural network is marked as sigma;
step 3.2, optimizing five parameters [ sigma, c, w, phi, h ] of the improved RBF neural network through an improved gray wolf optimization algorithm:
step 3.2.1, defining the current iteration number as t, and initializing t=1;
defining and initializing various parameters in the modified wolf algorithm, including: size M of wolf group, maximum iteration number T, search space dimension D and T-th generation coefficient vector a t ；
Step 3.2.2, random initial t-th generation of the wealth population { X ] j (t)|j＝1,2,…,M}，Wherein X is j (t) represents the direction vector of the jth individual of the t generation, and the direction vector of each individual of the t generation is five parameters in the improved RBF neural network;
step 3.2.3, calculating the fitness function value find of the jth individual of the t generation of the wolf population by using the step 3 j (t) thereby obtaining an fitness function value for each individual of the t-th generation of the wolf population;
in the formula (3), the amino acid sequence of the compound,
and Y k Respectively a true value and a fitting value of SOH, wherein lambda is a parameter;
step 3.2.4, sorting the fitness function value of each individual of the t-th generation of the wealth, finding out the three first wealth individuals with the fitness function being marked as alpha (t), beta (t) and gamma (t), and marking the direction vector of the alpha (t) of the t-th generation of the wealth individuals as X α The direction vector of the individual beta (t) of the t th generation of the wolf is marked as X β The direction vector of the (t) th generation of the individual gamma (t) of the wolf is marked as X γ (t)；
Step 3.2.5, determining the direction vector X (t+1) of the optimal gray wolf individual in the t+1 generation by using the formula (4):
in the formula (4): gauchy (0, 1) represents a random number with a mean of 0 and a variance of 1;
step 3.2.6 updating the t-th generation coefficient vector a using (5) t ：
In formula (5): rand represents a random number between (0, 1);
step 3.2.7, after assigning t+1 to T, judging whether T > T is satisfied, if so, outputting the direction vector of the T-th generation optimal gray wolf individual, and taking the direction vector as the optimal parameter [ sigma ] of the improved RBF neural network after optimization * ,c * ,w * ,Φ * ,h * ]Otherwise, turning to the step 3.2.3 to be sequentially executed;
step S4, saving the optimal parameter [ sigma ] * ,c * ,w * ,Φ * ,h * ]The corresponding RBF neural network is used as an SOH estimation model; and the system is used for carrying out health state value SOH estimation on any input feature matrix.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention provides a method for estimating SOH of a battery based on an improved gray wolf optimization algorithm and an RBF neural network. According to the method, the improved RBF neural network parameters are optimized through the improved gray wolf optimization algorithm, so that the problems that the estimated value of the traditional RBF neural network is easy to deviate from a true value and easily falls into local optimum in the later stage of SOH estimation are effectively solved, and the accuracy and the robustness of SOH estimation are effectively improved.
2. The invention adds a linear polynomial directly related to the characteristic variable into the traditional RBF neural network function to track the linear trend of the battery in the long-term aging process. Compared with the traditional RBF neural network, the method can effectively track local nonlinear change generated by capacity regeneration and simulate the capacity attenuation trend in the long-term battery aging process, thereby being beneficial to improving SOH estimation accuracy.
3. According to the invention, a nonlinear self-adaptive convergence strategy and cauchy variation are introduced into a traditional gray wolf optimization algorithm so as to improve population diversity and global exploration development capability, avoid sinking into local optimum and improve convergence accuracy. The nonlinear adaptive convergence strategy converts the linear change of the convergence factor into nonlinear change to increase the diversity of the algorithm, and is more suitable for application scenes in the real world. In addition, the method of introducing the cauchy distribution function is used for carrying out variation on the position information of the global search of the wolves, so that the global search capacity of the wolves is improved, the algorithm can better achieve global optimum, and the estimation accuracy of the SOH of the lithium ion battery is greatly improved.
Drawings
FIG. 1 is a graph of charge voltage of an experimental lithium ion battery at different cycle times;
FIG. 2 is a graph of delta capacity of an experimental lithium ion battery at different cycle times;
FIG. 3 is a block diagram of an improved RBF neural network of the present invention;
FIG. 4 is a flow chart of a method for estimating SOH of a lithium ion battery based on an improved gray wolf optimization algorithm and RBF neural network;
fig. 5 is a graph of SOH estimation results and errors based on different algorithms.
Detailed Description
In this embodiment, a lithium ion battery SOH estimation method based on an RBF neural network of an improved gray wolf optimization algorithm, as shown in fig. 4, includes the following steps:
step S1, data acquisition:
and collecting historical operation data of the battery to be tested, wherein the historical operation data comprise charge and discharge times, voltage, current, operation time, complete discharge capacity and the like of each charge and discharge period. The battery was subjected to 166 charge and discharge cycles in total. Then, the battery SOH is defined from the viewpoint of capacity as shown in formula (1):
in the formula (1): SOH (solid oxide Fuel cell) k SOH value of current period, C k C is the battery capacity of the current period 0 Is the rated capacity of the battery in a completely new state.
And S2, extracting characteristics related to battery degradation from a battery charging voltage curve. Fig. 1 shows the charge voltage curves at different cycles. As the number of cycles increases, the constant current charging duration decreases, and the constant voltage charging time increases. Extracting characteristics related to battery degradation from an incremental capacity curve and fromThe compound of formula (2). Figure 2 shows incremental capacity curves at different cycles. As the number of cycles increases, the peak of the incremental capacity curve decreases and the peak correspondence position shifts to the right. The feature extraction is as follows: constant current charging time f in the kth charging process 1 k Constant voltage charge time
Peak +.>
Peak->
Corresponding position->
The feature vector as the kth input is +.>
The true state of health value SOH of the kth lithium battery is taken as an output value +.>
From the input feature matrix f= [ F 1 ；F 2 ；…；F n ]And output vector +.>
Forming a training set, wherein the features and SOH data of the first 116 times are the training set, and the rest is a test set;
s3, constructing an improved RBF neural network, and optimizing parameters in the network by adopting an improved gray wolf optimization algorithm based on a training set;
and 3.1, constructing an improved RBF neural network by using the formula (3), wherein the network structure is shown in figure 3. The RBF neural network comprises three layers, namely an input layer, an hidden layer and an output layer. Unlike conventional RBF neural network, the improved RBF neural network has an output layer with a linear polynomial directly related to features added on the basis of original RBF neural network to improve SOH estimation accuracy. The reason for this is that it is clearly known that the capacity decreases with the increase in the number of charge and discharge cycles according to the battery aging principle, which means that the battery state of health degradation data can be regarded as a long-term time series. However, since the function of the hidden layer of the neural network non-linearly transforms the input features, the direct linear correlation of the features with SOH is reduced. Therefore, the estimated SOH gradually deviates from the true value in the latter period, and cannot accurately follow the long-term linear change process. Therefore, the improved RBF neural network can not only solve the problem that the local nonlinear change of the SOH of the battery occurs due to various uncertain factors, but also accurately track the long-term linear change of the SOH of the battery;
in the formula (3), w i Representing the connection weights of the ith hidden layer node and the output nodes in the RBF neural network, and marking a vector formed by the connection weights of all hidden layer nodes and the output nodes in the RBF neural network as w and c i Representing the central point of the activation function at the i-th hidden layer node in the RBF neural network, marking a matrix formed by the central points of the activation functions at all hidden layer nodes in the RBF neural network as c, wherein phi is a coefficient of a linear polynomial, and h represents the number of hidden layer nodes; g (F-c) i ) Is an activation function of the hidden layer and is derived from equation (4):
in formula (4), σ i Is the variance parameter of the node of the i hidden layer in the RBF neural network; the vector formed by the variance parameters of all hidden layer nodes in the RBF neural network is marked as sigma;
and 3.2, optimizing five parameters [ sigma, c, w, phi, h ] of the improved RBF neural network through an improved gray wolf optimization algorithm. The invention mainly adopts a nonlinear self-adaptive strategy and cauchy variation to improve the traditional grey wolf optimization algorithm, and improves the problem that the traditional grey wolf optimization algorithm is easy to sink into local optimum, so that the improved grey wolf optimization algorithm can obtain the best RBF neural network parameters:
step 3.2.1, defining the current iteration number as t, and initializing t=1;
defining and initializing various parameters in the modified wolf algorithm, including: size M of wolf group, maximum iteration number T, search space dimension D and T-th generation coefficient vector a t ；
Step 3.2.2, random initial t-th generation of the wealth population { X ] j (t) |j=1, 2, …, M }, wherein X j (t) represents the direction vector of the jth individual of the t generation, and the direction vector of each individual of the t generation is five parameters in the improved RBF neural network;
step 3.2.3, calculating the fitness function value find of the jth individual of the t generation of the wolf population by using the method (5) j (t) thereby obtaining an fitness function value for each individual of the t-th generation of the wolf population;
in the formula (5), the amino acid sequence of the compound,
and Y k Lambda is a small number that needs to be kept on an order of magnitude from the previous term, the true and fit values for SOH, respectively.
Step 3.2.4, sorting the fitness function value of each individual of the t-th generation of the wealth, finding out the three first wealth individuals with the fitness function being marked as alpha (t), beta (t) and gamma (t), and marking the direction vector of the alpha (t) of the t-th generation of the wealth individuals as X α The direction vector of the individual beta (t) of the t th generation of the wolf is marked as X β (t), t-th generation of individual grey wolves gamma (t)The direction vector is denoted as X γ (t)；
And 3.2.5, determining a direction vector X (t+1) of the optimal gray wolf in the t+1st generation by using the formula (6), wherein aiming at the characteristic that the gray wolf optimization algorithm is easy to fall into local optimization, the diversity of the population is increased by using the cauchy variation, the global searching capability of the algorithm is improved, and the searching space is increased. The peak value of the cauchy distribution function at the original point is smaller, the distribution at the two ends is longer, and the cauchy variation can generate larger disturbance near the currently mutated gray wolf individual, so that the range of the cauchy distribution function is wider, and the distribution at the two ends of the cauchy variation is easier to jump out of a local optimal value;
in formula (6): gauchy (0, 1) represents a random number with a mean of 0 and a variance of 1;
step 3.2.6 updating the t-th generation coefficient vector a by using the method (7) t Convergence factor a in traditional wolf optimization algorithm t Is linearly reduced with the increase of the iteration number, however, when solving the problem of a plurality of unknown parameters, the mechanism can not reflect the convergence problem in the actual optimization process, so a nonlinear adaptive strategy is introduced to update the convergence factor a t ；
In the formula (12): rand represents a random number between (0, 1);
step 3.2.7, after assigning t+1 to T, judging whether T > T is satisfied, if so, outputting the direction vector of the T-th generation optimal gray wolf individual, and taking the direction vector as the optimal parameter [ sigma ] of the improved RBF neural network after optimization * ,c * ,w * ,Φ * ,h * ]Otherwise, turning to the step 3.2.3 to be sequentially executed;
step S4, saving the optimal parameter [ sigma ] * ,c * ,w * ,Φ * ,h * ]Corresponding toAnd used as an SOH estimation model; and the system is used for carrying out health state value SOH estimation on any input feature matrix.
To verify the superiority of the present invention, the predictive performance of the algorithm of the present invention was compared to the three algorithms SVR and GPR. Fig. 5 shows SOH estimation results and errors of the three algorithms on the test set, and it can be seen from part (a) in fig. 5 that the method of the present invention is very close to the actual value of the SOH estimated value of the lithium battery, which indicates that the method of the present invention has the characteristic of accurate estimation results. As can be seen from the error analysis of the part (b) in fig. 5, the algorithm provided by the present invention can control the estimation error within 2%, and has higher estimation accuracy compared with the other three algorithms.
Claims (1)
1. The lithium ion battery SOH estimation method based on the RBF neural network of the improved gray wolf optimization algorithm is characterized by comprising the following steps of:
step S1, data acquisition:
carrying out n times of charging and discharging on any lithium battery, and recording current, voltage, temperature and time data of the lithium battery and the complete capacity of each discharging in the charging and discharging process;
step S2, constant current charging time f in the kth charging process 1 k Constant voltage charge time
Peak f of incremental capacity curve 3 k Peak f 3 k Corresponding position->
The feature vector as the kth input is +.>
The true state of health value SOH of the kth lithium battery is taken as an output value +.>
From the input feature matrix f= [ F 1 ；F 2 ；…；F k ；…；F n ]And output vector
Forming a training set;
s3, constructing an improved RBF neural network, and optimizing parameters in the network by adopting an improved gray wolf optimization algorithm based on the training set;
step 3.1, constructing an improved RBF neural network by using the formula (1):
in the formula (1), w i Representing the connection weights of the ith hidden layer node and the output nodes in the RBF neural network, and marking a vector formed by the connection weights of all hidden layer nodes and the output nodes in the RBF neural network as w and c i Representing the central point of the activation function at the i-th hidden layer node in the RBF neural network, marking a matrix formed by the central points of the activation functions at all hidden layer nodes in the RBF neural network as c, wherein phi is a coefficient of a linear polynomial, and h represents the number of hidden layer nodes; g (F-c) i ) Is an activation function of the hidden layer and is derived from equation (2):
in the formula (2), sigma i Is the variance parameter of the node of the i hidden layer in the RBF neural network; the vector formed by the variance parameters of all hidden layer nodes in the RBF neural network is marked as sigma;
step 3.2, optimizing five parameters [ sigma, c, w, phi, h ] of the improved RBF neural network through an improved gray wolf optimization algorithm:
step 3.2.1, defining the current iteration number as t, and initializing t=1;
defining and initializing various parameters in the modified wolf algorithm, packageThe method comprises the following steps: size M of wolf group, maximum iteration number T, search space dimension D and T-th generation coefficient vector a t ；
Step 3.2.2, random initial t-th generation of the wealth population { X ] j (t) |j=1, 2, …, M }, wherein X j (t) represents the direction vector of the jth individual of the t generation, and the direction vector of each individual of the t generation is five parameters in the improved RBF neural network;
step 3.2.3, calculating the fitness function value find of the jth individual of the t generation of the wolf population by using the step 3 j (t) thereby obtaining an fitness function value for each individual of the t-th generation of the wolf population;
in the formula (3), the amino acid sequence of the compound,
and Y k Respectively a true value and a fitting value of SOH, wherein lambda is a parameter;
step 3.2.4, sorting the fitness function value of each individual of the t-th generation of the wealth, finding out the three first wealth individuals with the fitness function being marked as alpha (t), beta (t) and gamma (t), and marking the direction vector of the alpha (t) of the t-th generation of the wealth individuals as X α The direction vector of the individual beta (t) of the t th generation of the wolf is marked as X β The direction vector of the (t) th generation of the individual gamma (t) of the wolf is marked as X γ (t)；
Step 3.2.5, determining the direction vector X (t+1) of the optimal gray wolf individual in the t+1 generation by using the formula (4):
in the formula (4): gauchy (0, 1) represents a random number with a mean of 0 and a variance of 1;
step 3.2.6 updating the t-th generation coefficient vector a using (5) t ：
In formula (5): rand represents a random number between (0, 1);
step 3.2.7, after assigning t+1 to T, judging whether T > T is satisfied, if so, outputting the direction vector of the T-th generation optimal gray wolf individual, and taking the direction vector as the optimal parameter [ sigma ] of the improved RBF neural network after optimization * ,c * ,w * ,Φ * ,h * ]Otherwise, turning to the step 3.2.3 to be sequentially executed;
step S4, saving the optimal parameter [ sigma ] * ,c * ,w * ,Φ * ,h * ]The corresponding RBF neural network is used as an SOH estimation model; and the system is used for carrying out health state value SOH estimation on any input feature matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210448979.3A CN114895206B (en) | 2022-04-26 | 2022-04-26 | Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210448979.3A CN114895206B (en) | 2022-04-26 | 2022-04-26 | Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114895206A CN114895206A (en) | 2022-08-12 |
| CN114895206B true CN114895206B (en) | 2023-04-28 |
Family
ID=82719150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210448979.3A Active CN114895206B (en) | 2022-04-26 | 2022-04-26 | Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114895206B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116609672A (en) * | 2023-05-16 | 2023-08-18 | 国网江苏省电力有限公司淮安供电分公司 | Energy storage battery SOC estimation method based on improved BWOA-FNN algorithm |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007056870A1 (en) * | 2005-11-21 | 2007-05-24 | The Governors Of The University Of Alberta | Methods and compositions for pharmacologically controlled targeted immunotherapy |
| EP2808829A1 (en) * | 2013-05-28 | 2014-12-03 | Vrije Universiteit Brussel | Method and apparatus for predicting the perceptual quality of a signal |
| DE102017103377A1 (en) * | 2016-02-26 | 2017-08-31 | Ford Global Technologies, Llc | SYSTEMS AND METHOD FOR MONITORING THE HEALTH CONDITION OF A BATTERY |
| CN107741568A (en) * | 2017-11-08 | 2018-02-27 | 中南大学 | A kind of lithium battery SOC estimation method that optimization RBF neural is shifted based on state |
| CN108805217A (en) * | 2018-06-20 | 2018-11-13 | 山东大学 | A kind of health state of lithium ion battery method of estimation and system based on support vector machines |
| CN110309920A (en) * | 2019-06-24 | 2019-10-08 | 北京计算机技术及应用研究所 | The network RBF evaluation method of RBF neural based on Hybrid Hierarchy Genetic Algorithm |
| CN110377957A (en) * | 2019-06-20 | 2019-10-25 | 浙江大学 | A kind of overhead crane neural network modeling approach of whale search strategy grey wolf algorithm |
| CN111443293A (en) * | 2020-03-30 | 2020-07-24 | 青岛大学 | Lithium battery state of health (SOH) estimation method based on data driving |
| CN111709524A (en) * | 2020-07-03 | 2020-09-25 | 江苏科技大学 | RBF neural network optimization method based on improved GWO algorithm |
| CN112348080A (en) * | 2020-11-06 | 2021-02-09 | 北京石油化工学院 | RBF improvement method, device and equipment based on industrial control abnormity detection |
| CN112581263A (en) * | 2020-12-23 | 2021-03-30 | 百维金科(上海)信息科技有限公司 | Credit evaluation method for optimizing generalized regression neural network based on wolf algorithm |
| CN113406521A (en) * | 2021-06-11 | 2021-09-17 | 上海电力大学 | Lithium battery health state online estimation method based on feature analysis |
| WO2021185308A1 (en) * | 2020-03-18 | 2021-09-23 | 北京理工大学 | Online determination method and system for state of health of power battery pack of electric vehicle |
| CN113449464A (en) * | 2021-06-11 | 2021-09-28 | 淮阴工学院 | Wind power prediction method based on improved depth extreme learning machine |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10524465B2 (en) * | 2015-12-11 | 2020-01-07 | Joseph E. Kovarik | System and method to drive away geese |
-
2022
- 2022-04-26 CN CN202210448979.3A patent/CN114895206B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007056870A1 (en) * | 2005-11-21 | 2007-05-24 | The Governors Of The University Of Alberta | Methods and compositions for pharmacologically controlled targeted immunotherapy |
| EP2808829A1 (en) * | 2013-05-28 | 2014-12-03 | Vrije Universiteit Brussel | Method and apparatus for predicting the perceptual quality of a signal |
| DE102017103377A1 (en) * | 2016-02-26 | 2017-08-31 | Ford Global Technologies, Llc | SYSTEMS AND METHOD FOR MONITORING THE HEALTH CONDITION OF A BATTERY |
| CN107741568A (en) * | 2017-11-08 | 2018-02-27 | 中南大学 | A kind of lithium battery SOC estimation method that optimization RBF neural is shifted based on state |
| CN108805217A (en) * | 2018-06-20 | 2018-11-13 | 山东大学 | A kind of health state of lithium ion battery method of estimation and system based on support vector machines |
| CN110377957A (en) * | 2019-06-20 | 2019-10-25 | 浙江大学 | A kind of overhead crane neural network modeling approach of whale search strategy grey wolf algorithm |
| CN110309920A (en) * | 2019-06-24 | 2019-10-08 | 北京计算机技术及应用研究所 | The network RBF evaluation method of RBF neural based on Hybrid Hierarchy Genetic Algorithm |
| WO2021185308A1 (en) * | 2020-03-18 | 2021-09-23 | 北京理工大学 | Online determination method and system for state of health of power battery pack of electric vehicle |
| CN111443293A (en) * | 2020-03-30 | 2020-07-24 | 青岛大学 | Lithium battery state of health (SOH) estimation method based on data driving |
| CN111709524A (en) * | 2020-07-03 | 2020-09-25 | 江苏科技大学 | RBF neural network optimization method based on improved GWO algorithm |
| CN112348080A (en) * | 2020-11-06 | 2021-02-09 | 北京石油化工学院 | RBF improvement method, device and equipment based on industrial control abnormity detection |
| CN112581263A (en) * | 2020-12-23 | 2021-03-30 | 百维金科(上海)信息科技有限公司 | Credit evaluation method for optimizing generalized regression neural network based on wolf algorithm |
| CN113406521A (en) * | 2021-06-11 | 2021-09-17 | 上海电力大学 | Lithium battery health state online estimation method based on feature analysis |
| CN113449464A (en) * | 2021-06-11 | 2021-09-28 | 淮阴工学院 | Wind power prediction method based on improved depth extreme learning machine |
Non-Patent Citations (2)
| Title |
|---|
| Mingqiang Lin 等.State of health estimation of lithium-ion battery based on an adaptive tunable hybrid radial basis function network.《Journal of Power Sources》.2021,第第504卷卷全文. * |
| 李龙刚 等.基于改进灰狼优化与支持向量回归的锂电池健康状态预测.《南京理工大学学报》.2020,第第44卷卷(第第2期期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114895206A (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113064093B (en) | Method and system for jointly estimating state of charge and state of health of energy storage battery | |
| CN111832220A (en) | Lithium ion battery health state estimation method based on codec model | |
| CN110888058A (en) | Algorithm based on power battery SOC and SOH joint estimation | |
| CN111812519B (en) | Battery parameter identification method and system | |
| CN114970332B (en) | Lithium battery model parameter identification method based on chaotic quantum sparrow search algorithm | |
| CN116609668B (en) | Lithium ion battery health state and residual life prediction method | |
| CN114895206B (en) | Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm | |
| CN113687242A (en) | Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm | |
| CN114726045A (en) | Lithium battery SOH estimation method based on IPEA-LSTM model | |
| CN115308606A (en) | Lithium ion battery health state estimation method based on proximity features | |
| CN114839542A (en) | Sample data set generation method and SOC estimation method for power lithium battery | |
| Eleftheriadis et al. | Hyperband optimization of stacked bidirectional long short-term memory neural network for the state of charge estimation | |
| CN116774086B (en) | Lithium battery health state estimation method based on multi-sensor data fusion | |
| CN116540134A (en) | GWO-LSTM-based lithium ion battery health state estimation method | |
| Lyu et al. | State-of-charge estimation of lithium-ion batteries based on deep neural network | |
| CN116774088A (en) | Lithium ion battery health state estimation method based on multi-objective optimization | |
| CN117007974A (en) | Solid-state battery SOC estimation method based on model fusion | |
| CN116679213A (en) | SOH estimation method for electric vehicle power battery based on integrated deep learning | |
| CN113884936A (en) | Lithium ion battery health state prediction method based on ISSA coupling DELM | |
| CN113466710A (en) | SOC and SOH collaborative estimation method for energy storage battery in receiving-end power grid containing new energy | |
| Pyne et al. | Toward the Use of Operational Cycle Data for Capacity Estimation | |
| CN116362418B (en) | Online prediction method for application-level manufacturing capacity of intelligent factory of high-end battery | |
| CN117233627A (en) | Energy storage battery capacity estimation method based on wavelet packet transformation-deep convolution gate control neural network | |
| Wang et al. | Research on Lithium Battery SOC Prediction Method based on CSSA-BP | |
| CN116359745A (en) | Lithium ion battery health state estimation method based on incremental learning |
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 |