CN113687242A - Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm - Google Patents
Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm Download PDFInfo
- Publication number
- CN113687242A CN113687242A CN202111150229.XA CN202111150229A CN113687242A CN 113687242 A CN113687242 A CN 113687242A CN 202111150229 A CN202111150229 A CN 202111150229A CN 113687242 A CN113687242 A CN 113687242A
- Authority
- CN
- China
- Prior art keywords
- gru
- data
- lithium ion
- ion battery
- algorithm
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 24
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 18
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims abstract description 24
- 229910052744 lithium Inorganic materials 0.000 claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000002474 experimental method Methods 0.000 claims abstract description 14
- 230000006872 improvement Effects 0.000 claims abstract description 12
- 238000010606 normalization Methods 0.000 claims abstract description 11
- 238000007600 charging Methods 0.000 claims abstract description 9
- 238000007599 discharging Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 210000002569 neuron Anatomy 0.000 claims description 21
- 230000002068 genetic effect Effects 0.000 claims description 11
- 230000004913 activation Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 6
- 230000036541 health Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010280 constant potential charging Methods 0.000 description 1
- 238000010277 constant-current charging Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
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]
- G01R31/367—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]
- G01R31/385—Arrangements for measuring battery or accumulator 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses a method for estimating SOH of a lithium ion battery based on GA algorithm optimization improvement GRU neural network, which comprises the following steps: 1. acquiring experimental data: setting a lithium battery charging and discharging experiment working condition to charge and discharge the lithium battery, and recording voltage, current and temperature data of the lithium battery and the capacity of the battery which is completely discharged each time in the experiment process; 2. data preprocessing: deleting invalid values of the acquired original data and carrying out data normalization processing; 3. and constructing a network model. 4. And taking the normalized data as the input of a network model for estimating the SOH of the lithium ion battery. The method has the advantages of simple process, accurate estimation result and high precision.
Description
Technical Field
The invention relates to the technical field of power battery management, in particular to a method for estimating SOH of a lithium ion battery based on GA algorithm optimization improvement GRU neural network.
Background
The rapid development of the automotive industry inevitably produces a number of negative effects: large consumption of non-renewable energy sources such as petroleum and the like, generation of automobile exhaust gas, greenhouse gas and the like. In the face of severe challenges such as resource shortage and environmental pollution, automobile enterprises are beginning to vigorously develop electric automobiles using power batteries as new energy sources to reduce dependence on petroleum energy and reduce automobile exhaust emission. Lithium ion batteries are widely used in the field of electric vehicles because of their high energy density, light weight, and long charge-discharge cycle life. The state of health (SOH) of the lithium battery not only represents the attenuation and the deterioration condition of the battery capacity, but also estimates one of important parameters of the endurance mileage of the automobile; secondly, the SOH of the power battery is monitored in real time, so that potential safety hazards can be avoided, and the service life of the battery is prolonged. Accurate estimation of state of health (SOH) of a lithium ion battery is critical to ensure safe and efficient operation of the battery. However, since the state of health of the battery cannot be measured directly by the sensor, it can only be estimated indirectly by external characteristics (voltage, current, temperature, etc.). It is considered that most of the current estimation methods artificially extract the health factor from the external characteristic data of the battery and then estimate the SOH of the battery by using the extracted health factor. The degree to which the health factor correlates with SOH determines the accuracy of the estimation. This not only requires complex data preprocessing of the raw data, but also does not take full advantage of the useful information in the raw data. Therefore, the method has important practical significance for accurately estimating the SOH of the lithium battery.
Disclosure of Invention
The invention aims to provide a method for estimating SOH of a lithium ion battery based on GA algorithm optimization improvement GRU neural network. The method has the advantages of simple process, accurate estimation result and high precision.
The technical scheme of the invention is as follows: a lithium ion battery SOH estimation method for optimizing and improving a GRU neural network based on a GA algorithm comprises the following steps:
step 3, constructing a network model: the network model adopts a time sequence of GRU processing input data, a self-attention layer is used for redistributing weight to output components of the GRU, then a full-connection layer is set for fusing output of the self-attention layer, and finally a genetic algorithm is used for carrying out parameter optimization on the number of GRU layers, the number of GRU neurons, the number of full-connection layers and the number of full-connection neurons, so that the network prediction performance is improved for estimating SOH of the lithium ion battery;
and 4, taking the normalized data as the input of a network model for estimating the SOH of the lithium ion battery.
In the above lithium ion battery SOH estimation method based on GA algorithm optimization improvement GRU neural network, in step 2, a maximum and minimum normalization method is adopted to normalize the original data to between [0,1 ]; the formula of the maximum and minimum normalization method is as follows:
where x represents the raw data observation, min represents the minimum of the data values x, and max represents the maximum of the data values x.
In the foregoing method for estimating SOH of a lithium ion battery based on GA algorithm optimization and improvement of a GRU neural network, in step 3, a mathematical formula of an information transfer process in the GRU is as follows:
Rt=σ(XtWxr+Ht-1Whr+br);
Zt=σ(XtWxz+Ht-1Whz+bz);
in the formula: rtTo reset the gate, ZtIn order to update the door,as candidate hidden states, HtIs a hidden state of time step t; wxr,Whr,Wxz,Whz,Wxh,WhhWeights representing reset gate, refresh gate and hidden state respectively; br,bz,bhBiases representing reset gate, refresh gate and hidden state, respectively; sigma represents an activation function of an update gate and a reset gate, and a sigmoid function is adopted; tanh represents the activation function of the candidate hidden state for the current time step, and an element multiplication is indicated by a hyperbolic tangent function, for example.
In the foregoing method for estimating SOH of a lithium ion battery based on GA algorithm optimization and improvement of a GRU neural network, in step 3, the step of using a self-attention layer to reassign weights to outputs of GRU hidden units includes the following steps:
Q=WqI;
K=WkI;
V=WvI;
wherein I represents an input from the attention layer, I ═ a1,a2,...,at},atIs the t-th component of vector I; wq、Wk、WvQ, K and V, Q, K and V, respectively, represent Query vector Query, Key vector Key, and Value vector Value; kTRepresents the transpose of matrix K;represents the softmax activation function;representing a newly generated attention weight matrix; o denotes the output from the attention layer.
The lithium ion battery SOH estimation method based on GA algorithm optimization improvement GRU neural network is characterized in that: in the step 3, the number of GRU layers, the number of GRU neurons, the number of fully-connected layers, and the number of fully-connected neurons are optimized by a genetic algorithm, specifically:
step 3.1, encoding the GRU layer number, the GRU neuron number, the full-connection layer number and the full-connection neuron number into an initial population;
step 3.2, selecting a fitness function, taking the mean square error between the predicted value and the true value as the fitness function of the genetic algorithm, and selecting a certain number of better individuals through the fitness function;
3.3, carrying out selection, crossing and mutation operations on newly generated individuals to generate a new population;
and 3.4, after iteration of the designated population algebra, selecting the optimal individual from the population algebra, and searching the optimal solution.
Compared with the prior art, the method takes the discharge working condition of the battery in actual use into consideration, the lithium battery is charged and discharged by setting the charge and discharge experimental working condition of the lithium battery, the voltage, current and temperature data of the lithium battery and the capacity of the battery discharging completely each time in the experimental process are recorded, so that the original data of the lithium battery are obtained, and the data set for estimating the SOH of the lithium battery is constructed by using the original data. The GRU neural network is optimized and improved based on the GA algorithm, and the number of the GRU layers, the number of the GRU neurons, the number of the full-link layers and the number of the full-link neurons are optimized through the genetic algorithm in consideration of the fact that the number of the network layers and the number of the neurons have great influence on the prediction precision of the established model, so that the precision of the model is improved. Verification shows that the method has good prediction precision and robustness. The method has the advantages of simple process, accurate estimation result and high precision.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram of a GRU structure in the process of the present invention;
FIG. 3 is a schematic diagram of a self-attention layer in the method of the present invention;
FIG. 4 is a flow chart of a genetic algorithm in the method of the present invention;
FIG. 5 is a graph of the NASA battery RW20 prediction result in the method of the present invention;
FIG. 6 is a graph of the error of the prediction result of the NASA battery RW20 in the method of the present invention;
FIG. 7 is a graph of the NASA battery RW24 prediction result in the method of the present invention;
FIG. 8 is a graph of the error of the prediction result of the NASA battery RW24 in the method of the present invention.
Detailed Description
The invention is further illustrated by the following figures and examples, which are not to be construed as limiting the invention.
Example (b): the lithium ion battery SOH estimation method for optimizing and improving the GRU neural network based on the GA algorithm comprises the following steps as shown in figure 1:
step 1: acquiring experimental data: setting a lithium battery charging and discharging experiment working condition to charge and discharge the lithium battery, and recording voltage, current and temperature data of the lithium battery and the capacity of the battery which is completely discharged each time in the experiment process; the temperature of the lithium battery charging and discharging experiment environment is set to be 0 ℃, 25 ℃ and 45 ℃, and low temperature, normal temperature and high temperature in actual driving are simulated respectively; the lithium battery charging and discharging experiment comprises a charging experiment and a discharging experiment, wherein the charging experiment is to perform constant current charging to upper cut-off voltage by 1C multiplying power, then perform constant voltage charging to current reduction of 1/20C by the upper cut-off voltage, and finish charging; the discharge experiment simulates the discharge condition in the actual driving process by three different discharge multiplying factors of 1C, 3C and 5C; data are acquired through a sensor, and mainly battery end voltage, battery current and battery temperature are acquired, and capacity change is obtained through an ampere-hour integration method.
where x represents the raw data observation, min represents the minimum of the data values x, and max represents the maximum of the data values x.
Step 3, constructing a network model: the network model adopts a time sequence of GRU processing input data, a self-attention layer is used for redistributing weight to output components of the GRU, then a full-connection layer is set for fusing output of the self-attention layer, and finally a genetic algorithm is used for carrying out parameter optimization on the GRU layer number, the GRU neuron number, the full-connection layer number and the full-connection neuron number, so that the network prediction performance is improved for estimating SOH of the lithium ion battery. In particular, the method comprises the following steps of,
as shown in fig. 2, the GRU network is used to perform feature extraction on input data of a training data set (i.e., the GRU is used to process a time series of input data), and a mathematical formula of an information transfer process in the GRU is as follows:
Rt=σ(XtWxr+Ht-1Whr+br);
Zt=σ(XtWxz+Ht-1Whz+bz);
in the formula: rtTo reset the gate, ZtIn order to update the door,as candidate hidden states, HtIs a hidden state of time step t; wxr,Whr,Wxz,Whz,Wxh,WhhWeights representing reset gate, refresh gate and hidden state respectively; br,bz,bhBiases representing reset gate, refresh gate and hidden state, respectively; sigma represents an activation function of an update gate and a reset gate, and a sigmoid function is adopted; tanh represents the activation function of the candidate hidden state for the current time step, and an element multiplication is indicated by a hyperbolic tangent function, for example.
As shown in fig. 3, using the self-attention layer to re-assign weights to the outputs of the GRU concealment units comprises the following steps:
Q=WqI;
K=WkI;
V=WvI;
wherein I represents an input from the attention layer, I ═ a1,a2,...,at},atIs the t-th component of vector I; wq、Wk、WvQ, K and V, Q, K and V, respectively, represent Query vector Query, Key vector Key, and Value vector Value; kTRepresents the transpose of matrix K;represents the softmax activation function;representing a newly generated attention weight matrix; o denotes the output from the attention layer.
As shown in fig. 4, the genetic algorithm is used to perform parameter optimization on the GRU level, the GRU neuron number, the total ligation level and the total ligation neuron number, specifically:
step 3.1, encoding the GRU layer number, the GRU neuron number, the full-connection layer number and the full-connection neuron number into an initial population;
step 3.2, selecting a fitness function, taking the mean square error between the predicted value and the true value as the fitness function of the genetic algorithm, and selecting a certain number of better individuals through the fitness function;
3.3, carrying out selection, crossing and mutation operations on newly generated individuals to generate a new population;
and 3.4, after iteration of the designated population algebra, selecting the optimal individual from the population algebra, and searching the optimal solution.
And 4, taking the test data set as the input of the network model for estimating the SOH of the lithium ion battery.
In order to verify the superiority of the invention, the predictive performance of the algorithm of the invention is compared with the three algorithms, namely, the FCNN algorithm, the SVR algorithm and the GRU algorithm. Fig. 5 and fig. 7 show the predicted results of the four algorithms on RW20 and RW24 batteries on NASA random battery data sets, and it can be seen that the estimation of the SOH of the lithium battery by using the method of the present invention is very close to the true value, which indicates that the present invention has the characteristic of accurate estimation result. Fig. 6 and 8 are corresponding prediction error maps. Through the error analysis of fig. 6 and fig. 8, it can be found that the algorithm provided by the present invention can control the prediction error within 2%, and has higher prediction accuracy compared with the other three algorithms.
In summary, compared with most lithium battery SOH estimation methods for extracting health factors, the method provided by the invention has the advantages that the voltage, the current and the temperature of the lithium battery are used as the input of the network model, so that the complicated process of artificially extracting the health factors is omitted, the sampling data is directly utilized, and the useful information in the original data can be retained to the greatest extent. The method is based on GA algorithm optimization and improvement of GRU neural network, adopts optimized data driving algorithm, and has good prediction precision and robustness through verification. The method has the advantages of simple process, accurate estimation result and high precision.
Claims (5)
1. A lithium ion battery SOH estimation method for optimizing and improving a GRU neural network based on a GA algorithm is characterized by comprising the following steps: the method comprises the following steps:
step 1, acquiring experimental data: setting a lithium battery charging and discharging experiment working condition to charge and discharge the lithium battery, and recording voltage, current and temperature data of the lithium battery and the capacity of the battery which is completely discharged each time in the experiment process;
step 2, data preprocessing: deleting invalid values of the acquired original data and carrying out data normalization processing;
step 3, constructing a network model: the network model adopts a time sequence of GRU processing input data, redistributes weight to GRU output components by a self-attention layer, then sets a full-connection layer to fuse the output of the self-attention layer, and finally carries out parameter optimization on the GRU layer number, the GRU neuron number, the full-connection layer number and the full-connection neuron number by a genetic algorithm;
and 4, taking the normalized data as the input of a network model for estimating the SOH of the lithium ion battery.
2. The method for estimating SOH of lithium ion battery based on GA algorithm optimization improvement GRU neural network of claim 1, wherein: in the step 2, a maximum and minimum normalization method is adopted to normalize the original data to be between [0 and 1 ]; the formula of the maximum and minimum normalization method is as follows:
where x represents the raw data observation, min represents the minimum of the data values x, and max represents the maximum of the data values x.
3. The method for estimating SOH of lithium ion battery based on GA algorithm optimization improvement GRU neural network of claim 1, wherein: in step 3, the mathematical formula of the information transfer process in the GRU is as follows:
Rt=σ(XtWxr+Ht-1Whr+br);
Zt=σ(XtWxz+Ht-1Whz+bz);
in the formula: rtTo reset the gate, ZtIn order to update the door,as candidate hidden states, HtIs a hidden state of time step t; wxr,Whr,Wxz,Whz,Wxh,WhhWeights representing reset gate, refresh gate and hidden state respectively; br,bz,bhBiases representing reset gate, refresh gate and hidden state, respectively; sigma represents an activation function of an update gate and a reset gate, and a sigmoid function is adopted; tanh represents the activation function of the candidate hidden state for the current time step, and an element multiplication is indicated by a hyperbolic tangent function, for example.
4. The method for estimating SOH of lithium ion battery based on GA algorithm optimization improvement GRU neural network of claim 1, wherein: in the step 3, the step of using the self-attention layer to reassign the weight to the output of the GRU hiding unit includes the following steps:
Q=WqI;
K=WkI;
V=WvI;
wherein I represents an input from the attention layer, I ═ a1,a2,...,at},atIs the t-th component of vector I; wq、Wk、WvQ, K and V, Q, K and V, respectively, represent Query vector Query, Key vector Key, and Value vector Value; kTRepresents the transpose of matrix K;represents softmax activation function;representing a newly generated attention weight matrix; o denotes the output from the attention layer.
5. The method for estimating SOH of lithium ion battery based on GA algorithm optimization improvement GRU neural network of claim 1, wherein: in the step 3, the number of GRU layers, the number of GRU neurons, the number of fully-connected layers, and the number of fully-connected neurons are optimized by a genetic algorithm, specifically:
step 3.1, encoding the GRU layer number, the GRU neuron number, the full-connection layer number and the full-connection neuron number into an initial population;
step 3.2, selecting a fitness function, taking the mean square error between the predicted value and the true value as the fitness function of the genetic algorithm, and selecting a certain number of better individuals through the fitness function;
3.3, carrying out selection, crossing and mutation operations on newly generated individuals to generate a new population;
and 3.4, after iteration of the designated population algebra, selecting the optimal individual from the population algebra, and searching the optimal solution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111150229.XA CN113687242A (en) | 2021-09-29 | 2021-09-29 | Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111150229.XA CN113687242A (en) | 2021-09-29 | 2021-09-29 | Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113687242A true CN113687242A (en) | 2021-11-23 |
Family
ID=78587350
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111150229.XA Pending CN113687242A (en) | 2021-09-29 | 2021-09-29 | Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113687242A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114744309A (en) * | 2022-06-09 | 2022-07-12 | 深圳凌奈智控有限公司 | BMS-based battery safety management method, device, equipment and storage medium |
CN114779091A (en) * | 2022-04-28 | 2022-07-22 | 许昌许继软件技术有限公司 | Method and device for predicting health state of lithium battery of electric heavy truck |
CN115438588A (en) * | 2022-09-29 | 2022-12-06 | 中南大学 | Temperature prediction method, system, equipment and storage medium of lithium battery |
EP4270033A1 (en) * | 2022-04-28 | 2023-11-01 | Samsung SDI Co., Ltd. | Method and apparatus for estimating state of health of battery |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111726349A (en) * | 2020-06-16 | 2020-09-29 | 桂林电子科技大学 | GRU parallel network flow abnormity detection method based on GA optimization |
CN111832220A (en) * | 2020-06-16 | 2020-10-27 | 天津大学 | Lithium ion battery health state estimation method based on codec model |
CN112015719A (en) * | 2020-08-27 | 2020-12-01 | 河海大学 | Regularization and adaptive genetic algorithm-based hydrological prediction model construction method |
CN112098845A (en) * | 2020-08-17 | 2020-12-18 | 四川大学 | Lithium battery state estimation method for distributed energy storage system |
CN112328767A (en) * | 2020-11-11 | 2021-02-05 | 重庆邮电大学 | Question-answer matching method based on BERT model and comparative aggregation framework |
CN112557908A (en) * | 2020-12-17 | 2021-03-26 | 温州大学 | SOC and SOH joint estimation method for lithium ion power battery |
CN112733541A (en) * | 2021-01-06 | 2021-04-30 | 重庆邮电大学 | Named entity identification method of BERT-BiGRU-IDCNN-CRF based on attention mechanism |
CN112734097A (en) * | 2020-12-31 | 2021-04-30 | 中南大学 | Unmanned train energy consumption prediction method, system and storage medium |
CN112949164A (en) * | 2021-01-27 | 2021-06-11 | 上海电机学院 | Lithium battery health state prediction method |
CN113419187A (en) * | 2021-06-08 | 2021-09-21 | 上海交通大学 | Lithium ion battery health estimation method |
-
2021
- 2021-09-29 CN CN202111150229.XA patent/CN113687242A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111726349A (en) * | 2020-06-16 | 2020-09-29 | 桂林电子科技大学 | GRU parallel network flow abnormity detection method based on GA optimization |
CN111832220A (en) * | 2020-06-16 | 2020-10-27 | 天津大学 | Lithium ion battery health state estimation method based on codec model |
CN112098845A (en) * | 2020-08-17 | 2020-12-18 | 四川大学 | Lithium battery state estimation method for distributed energy storage system |
CN112015719A (en) * | 2020-08-27 | 2020-12-01 | 河海大学 | Regularization and adaptive genetic algorithm-based hydrological prediction model construction method |
CN112328767A (en) * | 2020-11-11 | 2021-02-05 | 重庆邮电大学 | Question-answer matching method based on BERT model and comparative aggregation framework |
CN112557908A (en) * | 2020-12-17 | 2021-03-26 | 温州大学 | SOC and SOH joint estimation method for lithium ion power battery |
CN112734097A (en) * | 2020-12-31 | 2021-04-30 | 中南大学 | Unmanned train energy consumption prediction method, system and storage medium |
CN112733541A (en) * | 2021-01-06 | 2021-04-30 | 重庆邮电大学 | Named entity identification method of BERT-BiGRU-IDCNN-CRF based on attention mechanism |
CN112949164A (en) * | 2021-01-27 | 2021-06-11 | 上海电机学院 | Lithium battery health state prediction method |
CN113419187A (en) * | 2021-06-08 | 2021-09-21 | 上海交通大学 | Lithium ion battery health estimation method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114779091A (en) * | 2022-04-28 | 2022-07-22 | 许昌许继软件技术有限公司 | Method and device for predicting health state of lithium battery of electric heavy truck |
EP4270033A1 (en) * | 2022-04-28 | 2023-11-01 | Samsung SDI Co., Ltd. | Method and apparatus for estimating state of health of battery |
CN114744309A (en) * | 2022-06-09 | 2022-07-12 | 深圳凌奈智控有限公司 | BMS-based battery safety management method, device, equipment and storage medium |
CN114744309B (en) * | 2022-06-09 | 2022-09-02 | 深圳凌奈智控有限公司 | BMS-based battery safety management method, device, equipment and storage medium |
CN115438588A (en) * | 2022-09-29 | 2022-12-06 | 中南大学 | Temperature prediction method, system, equipment and storage medium of lithium battery |
CN115438588B (en) * | 2022-09-29 | 2023-05-09 | 中南大学 | Temperature prediction method, system, equipment and storage medium for lithium battery |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113687242A (en) | Lithium ion battery SOH estimation method for optimizing and improving GRU neural network based on GA algorithm | |
CN110568359B (en) | Lithium battery residual life prediction method | |
CN111999649A (en) | XGboost algorithm-based lithium battery residual life prediction method | |
CN112557907A (en) | SOC estimation method of electric vehicle lithium ion battery based on GRU-RNN | |
CN110806541B (en) | AD-BAS-based lithium battery model parameter identification method | |
CN115308606B (en) | Lithium ion battery health state estimation method based on adjacent characteristics | |
CN114280490B (en) | Lithium ion battery state of charge estimation method and system | |
CN114726045B (en) | Lithium battery SOH estimation method based on IPEA-LSTM model | |
CN114384435A (en) | WSA-LSTM algorithm-based self-adaptive prediction method for residual service life of new energy automobile power battery | |
Wei et al. | State of health assessment for echelon utilization batteries based on deep neural network learning with error correction | |
Zhang et al. | A state-of-charge estimation method based on bidirectional LSTM networks for lithium-ion batteries | |
CN113627661A (en) | Method for predicting charging load of electric automobile | |
CN116298936A (en) | Intelligent lithium ion battery health state prediction method in incomplete voltage range | |
CN114895206B (en) | Lithium ion battery SOH estimation method based on RBF neural network of improved gray wolf optimization algorithm | |
CN115389946A (en) | Lithium battery health state estimation method based on isobaric rise energy and improved GRU | |
CN113311337A (en) | Lithium ion battery residual life detection method based on relevance vector regression | |
CN114545279B (en) | Lithium battery health state estimation method based on neural network ordinary differential equation | |
CN115963407A (en) | ICGWO (intensive care unit) optimization ELM (element-based robust model) based lithium battery SOC estimation method | |
Cao et al. | A flexible battery capacity estimation method based on partial voltage curves and polynomial fitting | |
CN114355218A (en) | Lithium ion battery charge state prediction method based on multi-feature quantity screening | |
CN114460481A (en) | Energy storage battery thermal runaway early warning method based on Bi-LSTM and attention mechanism | |
CN117150334B (en) | Lithium battery multi-condition prediction method and device based on optimized BiLSTM neural network | |
CN117554820A (en) | Battery health state prediction method, device, computer equipment and storage medium | |
CN117233635A (en) | Echelon utilization battery performance evaluation method based on two-way parallel network | |
Zhao et al. | State of Health Estimation of Electric Vehicle Batteries Using Transformer-Based Neural Network |
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 |