CN115983134A - Battery power state prediction method and system based on neural network - Google Patents
Battery power state prediction method and system based on neural network Download PDFInfo
- Publication number
- CN115983134A CN115983134A CN202310065261.0A CN202310065261A CN115983134A CN 115983134 A CN115983134 A CN 115983134A CN 202310065261 A CN202310065261 A CN 202310065261A CN 115983134 A CN115983134 A CN 115983134A
- Authority
- CN
- China
- Prior art keywords
- neural network
- battery power
- prediction model
- power state
- battery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012937 correction Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 230000001276 controlling effect Effects 0.000 claims abstract description 7
- 230000001105 regulatory effect Effects 0.000 claims abstract description 4
- 241000272525 Anas platyrhynchos Species 0.000 claims description 36
- 241000272522 Anas Species 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 239000003795 chemical substances by application Substances 0.000 claims description 4
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 229910052744 lithium Inorganic materials 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 239000004459 forage Substances 0.000 claims description 2
- 230000002093 peripheral effect Effects 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 abstract description 4
- 238000003062 neural network model Methods 0.000 description 3
- 238000010845 search algorithm Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000003912 environmental pollution Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002431 foraging effect Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
Images
Landscapes
- Secondary Cells (AREA)
Abstract
The invention discloses a method and a system for predicting a battery power state based on a neural network, wherein the method comprises the following steps: establishing a generalized neural network prediction model for predicting new battery power states and predicting correction coefficients of few samples of historical experimental data of similar batteries; optimizing the model by using a DSA algorithm according to the obtained generalized regression neural network prediction model; obtaining a battery power state prediction result according to the optimized model; and intelligently regulating and controlling the energy distribution of the vehicle according to the obtained battery power state prediction result. According to the invention, by using the GRNN neural network prediction model, the battery power state can be predicted through the short-term data of a laboratory, accurate and reasonable data support is provided for energy distribution and the like of a vehicle, and the method has the advantages of better generalization capability, stronger optimization capability and no falling into local optimization.
Description
Technical Field
The invention relates to a battery prediction technology, in particular to a battery power state prediction method and system based on a neural network.
Background
Due to the recent rise of environmental awareness caused by environmental pollution and the exhaustion of traditional fuels such as petroleum, clean renewable energy is actively developed in the international society to realize the sustainable development of human society, new energy automobiles are in operation, and the environmental pollution is greatly reduced compared with that of the traditional automobiles. With the development of new energy vehicles in recent years, pure Electric Vehicles (EV), hybrid Electric Vehicles (HEV), plug-in hybrid electric vehicles (PHEV), and the like appear in the market. The battery is used as the heart of the new energy automobile, and the accurate evaluation of the power state of the battery plays an important role in the safety of the new energy automobile.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a method and a system for predicting a battery power state based on a neural network, so that the high calculation cost and the storage capacity of the neural network are reduced, the cost is saved, and the battery power state is rapidly and accurately predicted.
The technical scheme is as follows: the invention relates to a battery power state prediction method based on a neural network, which comprises the following steps:
(1) And establishing a generalized neural network prediction model for predicting the new battery power state and the prediction correction coefficient of the few samples of the historical experimental data of the similar battery.
(1.1) dividing the GRNN neural network into a few-sample state prediction model and a compensation correction prediction model, and combining the two models to establish a GRNN neural network battery power state prediction model.
(1.2) establishing a GRNN neural network battery power prediction model, wherein the formula is as follows:
Q(t)＝K(t)Q 1 (t)
wherein Q (t) represents the corrected prediction result, Q 1 (t) represents the prediction result of the low-sample prediction model, and K (t) represents the compensation correction prediction model result.
(1.3) calculating the output layer of the GRNN neural network battery power prediction model, wherein the formula is as follows:
where n is the sample volume, p is the dimension of the random variable x, and δ is the width of the Gaussian functionNumber, i.e. smoothing factor, X i And Y i Observed values for samples of random variables x and y.
(1.4) establishing a fitness function constructed by the average error function of the prediction model, wherein the formula is as follows:
where m is the number of test samples in the B subset,
is the j-th individual actual output value in the B subset.
(2) And (3) optimizing the model by using a DSA algorithm according to the generalized regression neural network prediction model obtained in the step (1).
(2.1) initializing parameters, inputting quantities which influence the accuracy of the battery power state prediction model: the gaussian kernel width coefficient σ.
(2.2) initializing population: the population number is set to be N, the grouping number is set to be D, and the maximum iteration number is maximum.
(2.3) establishing a group and queuing the duck group, and finding all members to perform fitness, wherein a position formula is as follows;
X i ＝L b +(U b -L b )o
in the formula, xi represents the spatial position of the ith duck in the duck group, i =1,2,3, …, and N is the number of the group size; u shape b And L b Representing the upper and lower limits of the search space, respectively, o is a random number matrix between (0,1).
(2.4) the adaptive mechanism exploration formula of the duck group is as follows:
K＝sin(2rand)+1
where sign (r-0.5) has an effect on the process of searching for food, and can be set to-1 or 1; μ denotes a parameter controlling the global search; p is the search transition probability of the exploration phase; CF1 and CF2 respectively represent competition and cooperation coefficients between ducks in a search stage;
a historical value representing the best duck position in the t iteration; />
Shows that the ducks in the t iteration are
Agents searching for food around.
(2.5) after the exploration of the duck group is finished, selecting the optimal duck position according to the fitness; if the fitness of one of the ducks is better than the current best duck, their position will be changed according to the following formula:
in the formula, mu represents a control parameter of global search in a development stage; parameter KF 1 And KF 2 Respectively representing the cooperation and competition coefficients of the ducks in the development stage;
the best duck position representing the current historical value in the tth iteration; />
And &>
Represents the foraging of the duck group in t iterations>
Surrounding proxies, k ≠ j.
(2.6) if the termination criteria are met, proceeding to step (2.7); otherwise, go to step (2.3).
And (2.7) outputting the obtained optimal solution.
(3) And (3) obtaining a battery prediction result according to the model optimized in the step (2).
(4) And (4) intelligently regulating and controlling the energy distribution of the vehicle according to the battery power state prediction result obtained in the step (3).
A battery power state prediction system based on a neural network, the system adopting the above battery power state prediction method based on the neural network, the system comprising the following modules:
GRNN neural network prediction model: the method comprises a few-sample state prediction model and a correction model, wherein battery information acquired by a real-time monitoring module is preprocessed and then input into a GRNN neural network optimized by a DSA algorithm, a preliminary predicted value is acquired through a battery power prediction model, and then an accurate value is acquired through correction through the correction model;
a real-time monitoring module: monitoring the working data of the lithium battery;
the vehicle VCU: acquiring the predicted power of the neural network, sending the predicted power to a control system to control the power output of a battery, and sending the acquired vehicle information to an information management module for storage;
the control system comprises: receiving power information sent by a vehicle VCU to adjust the power output of the battery pack;
an information management module: storing important data transmitted by a vehicle VCU;
a battery safety device: and detecting whether the battery pack has a fault, if so, carrying out emergency processing and transmitting information to a vehicle VCU.
A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a neural network-based battery power state prediction method as described above.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a neural network based battery power state prediction method as described above when executing the computer program.
Has the advantages that: compared with the prior art, the invention has the following advantages:
1. according to the invention, by using the GRNN neural network prediction model, the battery power state can be predicted through the short-term data of a laboratory, and accurate and reasonable data support is provided for energy distribution and the like of a vehicle; compared with the traditional neural network model, the GRNN neural network model has the advantages of better generalization capability, stronger optimization capability and no falling into local optimization.
2. According to the method, the duck group search algorithm is used for optimizing the model, so that the model error is smaller; the accurate battery power state prediction data enables the energy distribution and adjustment of the vehicle to be more reasonable, and the safety performance of the vehicle is improved.
3. The invention simplifies huge data required by the traditional neural network by using the compensation module, reduces high calculation cost and storage capacity of the neural network, and has better economic benefit.
4. The invention is suitable for new energy vehicles and accords with the design concept of green environmental protection.
Drawings
FIG. 1 is a block diagram of the present invention;
FIG. 2 is a flow chart of GRNN neural network prediction in accordance with the present invention;
FIG. 3 is a flow chart of a duck swarm search algorithm optimized GRNN neural network model according to the present invention;
FIG. 4 is a diagram of a battery power prediction model error of the present invention;
FIG. 5 is a corrected battery power prediction model error graph of the present invention;
FIG. 6 is an error graph of a neural network prediction model optimized by the duck swarm algorithm of the present invention;
FIG. 7 is a comparison graph of prediction accuracy of the power prediction model, the corrected power prediction model, and the algorithm-optimized neural network prediction model of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
A battery power state prediction method based on a neural network comprises the following steps:
(1) A generalized neural network prediction model for predicting new battery power states and prediction correction coefficients of a few samples of historical experimental data of the same battery is established, as shown in fig. 2.
(1.1) dividing the GRNN neural network into two parts, namely a few-sample state prediction model and a compensation model, and combining the two models to establish a neural network battery power state prediction model.
(1.2) establishing a GRNN neural network battery power prediction model, wherein the formula is as follows:
Q(t)＝K(t)Q 1 (t)
wherein Q (t) represents the corrected prediction result, Q 1 (t) represents the prediction result of the low-sample prediction model, and K (t) represents the compensation correction prediction model result.
(1.3) calculating the output layer of the GRNN neural network battery power prediction model, wherein the formula is as follows:
where n is the sample volume, p is the dimension of the random variable X, and δ is the width coefficient of the Gaussian function, i.e., smoothing factor, X i And Y i Observed values for samples of random variables x and y.
(1.4) establishing a fitness function constructed by the average error function of the prediction model, wherein the formula is as follows:
wherein m is the number of test samples in the B subset，
Is the j-th individual actual output value in the B subset.
(2) And (3) optimizing the model by using a DSA method according to the generalized regression neural network prediction model obtained in the step (1), as shown in figure 3.
(2.1) initializing parameters, inputting quantities which influence the accuracy of the battery power state prediction model: the gaussian kernel width coefficient σ.
(2.2) initializing population: the population number is set to be N, the grouping number is set to be D, and the maximum iteration number is maximum.
(2.3) establishing a group and queuing the duck group, and finding all members to perform fitness, wherein a position formula is as follows;
X i ＝L b +(U b -L b )o
in the formula, xi represents the spatial position of the ith duck in the duck group, i =1,2,3, …, and N is the number of the group size; u shape b And L b Representing the upper and lower limits of the search space, respectively, and o is the random number matrix between (0,1).
(2.4) the adaptive mechanism exploration formula of the duck group is as follows:
K＝sin(2rand)+1
where sign (r-0.5) has an effect on the process of searching for food, and can be set to-1 or 1; μ denotes a parameter controlling the global search; p is the search transition probability of the exploration phase; CF1 and CF2 respectively represent competition and cooperation coefficients between ducks in a search stage;
represents the best duck in the t iterationA historical value of the child location; />
Indicates that the ducks in the t iteration are
The surrounding search for agents of food.
(2.5) after the exploration of the duck group is finished, selecting the optimal duck position according to the fitness; if the fitness of one of the ducks is better than the current best duck, their position will be changed according to the following formula:
in the formula, mu represents a control parameter of global search in a development stage; parameter KF 1 And KF 2 Respectively representing the cooperation and competition coefficients of the ducks in the development stage;
the best duck position representing the current historical value in the tth iteration; />
And &>
Represents that the duck group forages in t iterations>
Surrounding proxies, k ≠ j.
(2.6) if the termination criteria are met, proceeding to step (2.7); otherwise, go to step (2.3).
And (2.7) outputting the obtained optimal solution.
(3) And (3) obtaining a battery prediction result according to the model optimized in the step (2).
(4) And (4) intelligently regulating and controlling the energy distribution of the vehicle according to the battery power state prediction result obtained in the step (3).
As shown in fig. 1, a battery power state prediction system based on a neural network, the system using the above battery power state prediction method based on a neural network, the system comprising the following modules:
GRNN neural network prediction model: the method comprises a few-sample state prediction model and a correction model, wherein battery information acquired by a real-time monitoring module is preprocessed and then input into a GRNN neural network optimized by a DSA algorithm, a preliminary predicted value is acquired through a battery power prediction model, and then an accurate value is acquired through correction through the correction model;
a real-time monitoring module: monitoring the working data of the lithium battery;
the vehicle VCU: acquiring the predicted power of the neural network, sending the predicted power to a control system to control the power output of the battery, and sending the acquired important vehicle information to an information management module for storage;
the control system comprises: receiving power information sent by a vehicle VCU to adjust the power output of the battery pack;
the information management module: storing important data transmitted by a vehicle VCU;
a battery safety device: and detecting whether the battery pack has a fault, if so, carrying out emergency processing and transmitting information to a vehicle VCU.
As shown in fig. 4-5, the prediction accuracy of the battery power prediction model is significantly improved after the correction of the correction model.
As shown in fig. 6, after the GRNN neural network prediction model is optimized by the duck swarm search algorithm, the fitting degree of the model prediction value to the true value is improved, so that the prediction is more accurate.
As shown in fig. 7, after the duck swarm algorithm optimizes the GRNN neural network prediction model, the maximum error value is lower than 0.02, and the matching degree to the predicted value is high.
Claims (6)
1. A battery power state prediction method based on a neural network is characterized by comprising the following steps:
(1) Establishing a generalized neural network prediction model for predicting new battery power states and predicting correction coefficients of few samples of historical experimental data of similar batteries;
(2) Optimizing the model by using a DSA algorithm according to the generalized regression neural network prediction model obtained in the step (1);
(3) Obtaining a battery prediction result according to the model optimized in the step (2);
(4) And (4) intelligently regulating and controlling the energy distribution of the vehicle according to the battery power state prediction result obtained in the step (3).
2. The neural network-based battery power state prediction method according to claim 1, wherein the step (1) is specifically as follows:
(1.1) dividing the GRNN neural network into a few-sample state prediction model and a correction prediction model, and establishing a GRNN neural network battery power state prediction model by combining the two models;
(1.2) establishing a GRNN neural network battery power prediction model, wherein the formula is as follows:
Q(t)＝K(t)Q 1 (t)
wherein Q (t) represents the corrected prediction result, Q 1 (t) represents the prediction result of the low-sample prediction model, and K (t) represents the compensation correction prediction model result;
(1.3) calculating the output layer of the GRNN neural network battery power prediction model, wherein the formula is as follows:
where n is the sample volume, p is the dimension of the random variable X, and δ is the width coefficient of the Gaussian function, i.e., smoothing factor, X i And Y i Sample observations for random variables x and y;
(1.4) establishing a fitness function constructed by the average error function of the prediction model, wherein the formula is as follows:
where m is the number of test samples in the B subset,
is the j-th individual actual output value in the B subset.
3. The neural network-based battery power state prediction method according to claim 1, wherein the step (2) is specifically as follows:
(2.1) initializing parameters, inputting quantities which influence the accuracy of the battery power state prediction model: a Gaussian kernel width coefficient σ;
(2.2) initializing population: setting the population number as N, the grouping number as D and the maximum iteration number as maximum;
(2.3) establishing a group and queuing the duck group, and finding all members to perform fitness, wherein a position formula is as follows;
X i ＝L b +(U b -L b )o
in the formula, xi represents the spatial position of the ith duck in the duck group, i =1,2,3, …, and N is the number of the group size; u shape b And L b Represents the upper and lower limits of the search space, respectively, o is a random number matrix between (0,1);
(2.4) the adaptive mechanism exploration formula of the duck group is as follows;
K＝sin(2rand)+1
where sign (r-0.5) has an effect on the process of searching for food, and can be set to-1 or 1; μ denotes a parameter controlling the global search; p is the search transition probability of the exploration phase; CF1 and CF2 respectively represent competition and cooperation coefficients between ducks in a search stage;
a historical value representing the best duck position in the t iteration; />
Indicates that the duck group is ^ or ^ s in the tth iteration>
Agents searching for food around;
(2.5) after the exploration of the duck group is finished, selecting the optimal duck position according to the fitness; if the fitness of one of the ducks is better than the current best duck, their position will be changed according to the following formula:
in the formula, mu represents a control parameter of global search in a development stage; parameter KF 1 And KF 2 Respectively representing the cooperation and competition coefficients of the ducks in the development stage;
the best duck position representing the current historical value in the t iteration; />
And &>
Represents that the duck group forages in t iterations>
Peripheral agents, k ≠ j;
(2.6) if the termination criteria are met, proceeding to step (2.7); otherwise, turning to the step (2.3);
and (2.7) outputting the obtained optimal solution.
4. A neural network-based battery power state prediction system employing a neural network-based battery power state prediction method according to any one of claims 1 to 3, the system comprising the following modules:
GRNN neural network prediction model: the method comprises the steps of preprocessing battery information acquired by a real-time monitoring module, inputting the preprocessed battery information into a GRNN neural network optimized by a DSA algorithm, acquiring a primary predicted value through a battery power prediction model, and then correcting the battery information through a correction model to acquire an accurate value;
a real-time monitoring module: monitoring the working data of the lithium battery;
the vehicle VCU: acquiring the predicted power of the neural network, sending the predicted power to a control system to control the power output of a battery, and sending the acquired vehicle information to an information management module for storage;
the control system comprises: receiving power information sent by a vehicle VCU to adjust the power output of the battery pack;
the information management module: storing important data transmitted by a vehicle VCU;
a battery safety device: and detecting whether the battery pack has a fault, if so, carrying out emergency processing and transmitting information to a vehicle VCU.
5. A computer storage medium on which a computer program is stored which, when executed by a processor, implements a neural network-based battery power state prediction method as claimed in any one of claims 1-3.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a neural network-based battery power state prediction method as claimed in any one of claims 1-3 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310065261.0A CN115983134B (en) | 2023-01-17 | 2023-01-17 | Battery power state prediction method and system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310065261.0A CN115983134B (en) | 2023-01-17 | 2023-01-17 | Battery power state prediction method and system based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115983134A true CN115983134A (en) | 2023-04-18 |
| CN115983134B CN115983134B (en) | 2024-02-23 |
Family
ID=85974189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310065261.0A Active CN115983134B (en) | 2023-01-17 | 2023-01-17 | Battery power state prediction method and system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983134B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116470623A (en) * | 2023-06-01 | 2023-07-21 | 苏州精控能源科技有限公司 | Large energy storage system charge and discharge power state prediction method, electronic equipment and medium |
| CN118391241A (en) * | 2024-06-25 | 2024-07-26 | 山东黄海智能装备有限公司 | Molar water spray speed control optimization method for dental unit |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012098971A (en) * | 2010-11-03 | 2012-05-24 | Chube Univ | Learning device for neural network, learning method, and controller for mppt converter using the same |
| CN108181591A (en) * | 2018-01-08 | 2018-06-19 | 电子科技大学 | A kind of Forecasting Methodology of the SOC value of battery based on Speed Controlling Based on Improving BP Neural Network |
| CN111103553A (en) * | 2019-12-26 | 2020-05-05 | 江苏大学 | Method for estimating health state of GRNN-adaptive electric vehicle lithium ion battery |
| CN111695301A (en) * | 2020-06-16 | 2020-09-22 | 中国科学院深圳先进技术研究院 | Method and device for predicting battery charge state, storage medium and equipment |
| WO2022101769A1 (en) * | 2020-11-13 | 2022-05-19 | Kpit Technologies Limited | A hybrid system and method for estimating state of charge of a battery |
| CN115498283A (en) * | 2022-08-27 | 2022-12-20 | 湖州师范学院 | Lithium ion battery health state prediction method optimized by improved sparrow algorithm |
-
2023
- 2023-01-17 CN CN202310065261.0A patent/CN115983134B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012098971A (en) * | 2010-11-03 | 2012-05-24 | Chube Univ | Learning device for neural network, learning method, and controller for mppt converter using the same |
| CN108181591A (en) * | 2018-01-08 | 2018-06-19 | 电子科技大学 | A kind of Forecasting Methodology of the SOC value of battery based on Speed Controlling Based on Improving BP Neural Network |
| CN111103553A (en) * | 2019-12-26 | 2020-05-05 | 江苏大学 | Method for estimating health state of GRNN-adaptive electric vehicle lithium ion battery |
| CN111695301A (en) * | 2020-06-16 | 2020-09-22 | 中国科学院深圳先进技术研究院 | Method and device for predicting battery charge state, storage medium and equipment |
| WO2022101769A1 (en) * | 2020-11-13 | 2022-05-19 | Kpit Technologies Limited | A hybrid system and method for estimating state of charge of a battery |
| CN115498283A (en) * | 2022-08-27 | 2022-12-20 | 湖州师范学院 | Lithium ion battery health state prediction method optimized by improved sparrow algorithm |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116470623A (en) * | 2023-06-01 | 2023-07-21 | 苏州精控能源科技有限公司 | Large energy storage system charge and discharge power state prediction method, electronic equipment and medium |
| CN116470623B (en) * | 2023-06-01 | 2023-08-29 | 苏州精控能源科技有限公司 | Large energy storage system charge and discharge power state prediction method, electronic equipment and medium |
| CN118391241A (en) * | 2024-06-25 | 2024-07-26 | 山东黄海智能装备有限公司 | Molar water spray speed control optimization method for dental unit |
| CN118391241B (en) * | 2024-06-25 | 2024-08-27 | 山东黄海智能装备有限公司 | Molar water spray speed control optimization method for dental unit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115983134B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ren et al. | A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life | |
| CN115983134A (en) | Battery power state prediction method and system based on neural network | |
| Zheng et al. | Performance prediction of fuel cells using long short‐term memory recurrent neural network | |
| CN112305423A (en) | Lithium ion power battery state of charge estimation method, device, medium and equipment | |
| CN117565727B (en) | Wireless charging automatic control method and system based on artificial intelligence | |
| CN114943372A (en) | Method and device for predicting life of proton exchange membrane based on Bayesian recurrent neural network | |
| AU2021101964A4 (en) | Artificial intelligence based smart electric vehicle battery management system | |
| Tu et al. | Integrating electrochemical modeling with machine learning for lithium-ion batteries | |
| CN108021028A (en) | A kind of various dimensions cooperative control method converted based on relevant redundancy with strengthening study | |
| CN113466710A (en) | SOC and SOH collaborative estimation method for energy storage battery in receiving-end power grid containing new energy | |
| CN113484774A (en) | Lithium battery pack capacity estimation method based on temperature calibration and neural network | |
| CN117312835A (en) | Fuel cell performance prediction method based on mixed probability data driving model | |
| CN114692956A (en) | Charging facility load prediction method and system based on multilayer optimization kernel limit learning machine | |
| CN111079349B (en) | Energy real-time optimization method for lithium battery and super capacitor composite power supply system | |
| CN115542168A (en) | Lithium battery residual service life prediction method based on fusion data driving model | |
| CN116596129A (en) | Electric vehicle charging station short-term load prediction model construction method | |
| CN114895206A (en) | Lithium ion battery SOH estimation method based on RBF neural network of improved wolf optimization algorithm | |
| CN113761789A (en) | Method for estimating SOC of battery based on BP neural network optimized by firefly swarm algorithm | |
| CN116819372A (en) | Method for calculating health state of energy storage battery by neural network | |
| CN117233635A (en) | Echelon utilization battery performance evaluation method based on two-way parallel network | |
| US11945559B2 (en) | Method for forecasting demand load of hybrid electric ship by means of working condition | |
| CN116245023A (en) | Spatial fuel cell system mixedness parameter matching optimization method | |
| CN115099282A (en) | Fault diagnosis system and method for lithium battery pack | |
| Zhou et al. | Combined sparse Bayesian learning strategy for remaining useful life forecasting of lithium-ion battery | |
| CN118171049B (en) | Big data-based battery management method and system for edge calculation |
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 |