CN114545280B - New energy automobile lithium battery life prediction method based on optimization algorithm - Google Patents
New energy automobile lithium battery life prediction method based on optimization algorithm Download PDFInfo
- Publication number
- CN114545280B CN114545280B CN202210177290.1A CN202210177290A CN114545280B CN 114545280 B CN114545280 B CN 114545280B CN 202210177290 A CN202210177290 A CN 202210177290A CN 114545280 B CN114545280 B CN 114545280B
- Authority
- CN
- China
- Prior art keywords
- lithium battery
- algorithm
- optimal solution
- optimization
- lstm
- 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
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 74
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 74
- 238000005457 optimization Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000002245 particle Substances 0.000 claims abstract description 32
- 241000282461 Canis lupus Species 0.000 claims abstract description 23
- 230000036541 health Effects 0.000 claims abstract description 18
- 230000008859 change Effects 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims description 22
- 230000007246 mechanism Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 241000160777 Hipparchia semele Species 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000006731 degradation reaction Methods 0.000 description 6
- 230000015556 catabolic process Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008929 regeneration Effects 0.000 description 3
- 238000011069 regeneration method Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention provides a new energy automobile lithium battery life prediction method based on an optimization algorithm, which comprises the steps of firstly collecting the temperature, the discharge depth and the charging rate of a lithium battery, the ambient temperature of the lithium battery and the ambient temperature change rate of the lithium battery in a period of time as lithium battery health state data; then according to the discharge curve rule of the lithium battery, the health state data of the lithium battery is sent to an improved particle swarm algorithm based on a Hui wolf algorithm, and the lithium battery data of the optimal solution is output; and finally, sending the lithium battery data of the optimal solution into an LSTM prediction algorithm, establishing a life prediction model, predicting the actual life of the lithium battery according to the target life of the lithium battery, and finally outputting the predicted life of the lithium battery. The method has accurate prediction result.
Description
Technical Field
The invention belongs to the technical field of new energy automobile lithium batteries in the field of new energy automobile batteries, and particularly relates to a new energy automobile lithium battery service life prediction method based on an optimization algorithm.
Background
Factors influencing the health state of the battery comprise temperature, depth of discharge, charging rate and the like, but the indexes cannot directly represent the performance degradation degree of the battery, certain difficulty exists in online detection, and the actual capacity of the battery refers to the electric energy stored in the battery under the condition of full charge and can be directly represented. The existing lithium battery life prediction method can be divided into a failure physical model and a data driving model. The failure physical model is a process for expressing the performance degradation of the lithium battery by establishing a mathematical model, however, the method is easily interfered by noise and environment, is difficult to dynamically detect the health condition of the battery, and has poor robustness and adaptability. The algorithm extracts service life characteristic parameters from the performance degradation data of the battery, outputs a prediction result through modeling, and provides decision information for system maintenance. Local regeneration phenomenon can occur in the degradation process of the battery capacity, the performance of the prediction algorithm can be seriously influenced by the fluctuation generated by the phenomenon, and effective prediction is difficult to perform in practical situations.
Disclosure of Invention
Aiming at the problems, the invention provides a new energy automobile lithium battery service life prediction method based on an optimization algorithm, which is characterized in that local characteristics and global degradation trend in battery health indexes are subjected to self-adaptive separation through optimization of lithium battery parameters, so that the problem of severe fluctuation caused by regeneration of battery energy indexes is solved; and constructing a deep neural network temperature model, and establishing a temperature compensation model to obtain a reliable lithium battery service life prediction result.
In order to realize the purpose, the invention is realized by the following technical scheme:
a new energy automobile lithium battery life prediction method based on an optimization algorithm comprises the following steps:
and 3, sending the temperature T ', the discharge depth C ', the charging rate V ', the environment temperature T ' of the lithium battery, and the environment temperature change rate delta T ' of the lithium battery of the optimal solution output in the step 2 into an LSTM prediction algorithm, establishing a service life prediction model, predicting the actual service life of the lithium battery according to the target service life of the lithium battery, and finally outputting the predicted service life of the lithium battery.
Further, in the step 2, the improved particle swarm optimization based on the grayish wolf algorithm comprises the following specific processes:
9) Initializing an optimizing population of the algorithm, randomly scattering the optimizing population into the whole solution space, and setting alpha, beta and delta individuals for the wolf algorithm;
10 The optimizing population optimizes the whole solution space according to the optimizing process of the wolf algorithm;
11 Record the optimal solution V of the Grey wolf algorithm in each iteration beat-g ；
12 Judging according to a self-adaptive replacement mechanism, if the optimization algorithm is replaced by the particle swarm optimization algorithm, entering 5), and if not, returning to 2) to continue searching;
13 The optimization population excavates the position where the optimal solution possibly exists according to the optimization process of the particle swarm optimization;
14 Record the optimal solution V of the particle swarm optimization in each iteration process best-p ；
15 Judging according to an adaptive escape mechanism, returning to 1) if the optimizing population is trapped into local optimum, and otherwise, entering 8) and continuing searching;
16 Judging whether the algorithm meets the condition of ending, if not, returning to 5) continuing searching, otherwise, outputting the related information of the optimal solution.
Further, in step 5) of the improved particle swarm optimization based on the grayling algorithm, when a position where an optimal solution may exist is mined, the inertia coefficient w is subjected to nonlinear decrement processing, so that the searching and optimizing capability of the improved particle swarm optimization is improved.
Further on toAnd 3. The LSTM prediction algorithm in step 3 is a recurrent neural network structure, the basic structure of the LSTM network comprises a series of repeated units of each time step, and in each unit, at the time step t, an information storage part c t And three gate functions, i.e. input gate i t Output gate o t And forget door f t To regulate the flow of information for managing each unit in the LSTM network, and to decide how to update the current storage unit c t The current hidden state h of the unit and the information stored in t The correlation calculation function for each cell in the LSTM network module is shown in the following formula.
i t ＝σ(W i· [h t-1 +b i ]) (1)
f t ＝σ(W f· [h t-1 ，x t ]+b f ) (2)
q t ＝tanh(W q· [h t-1 ，x t ]+b q ) (3)
o t ＝σ(W o· [h t-1， x t ]+b o ) (4)
c t ＝f t ⊙c t-1 +i t ⊙q t (5)
h t ＝o t ⊙tanh(c t ) (6)
Wherein x t Is an input characteristic in LSTM network unit, σ represents Sigmod function, and "<" represents characteristic vector element by element multiplication, and W and b represent weight matrix and offset vector during training, respectively, the LSTM network uses an LSTM module directly placed behind a MaxPooling layer, including 64 LSTM units, in which a 0.2 Dropout layer is used as a regularization parameter to prevent over-fitting of the model, and a sense layer is the last layer of the entire model, i.e., a fully connected layer in the neural network for outputting a result, for classifying the lithium battery life-related parameters according to the output of the LSTM layer.
Has the advantages that:
1. according to the new energy automobile lithium battery life prediction method based on the optimization algorithm, the local characteristics and the global degradation trend in the battery health index are subjected to self-adaptive separation, and the problem of severe fluctuation caused by regeneration of the battery energy index is solved; and (3) constructing a deep neural network temperature model, and establishing a temperature compensation model to obtain a reliable lithium battery service life prediction result. In the research, the inventor finds that the optimization effect of the particle swarm optimization is very dependent on the initialization of the optimization population, and if the particles are mainly distributed near the local extreme points during the initialization, the whole optimization population is trapped into local optimization, so that the final optimization effect is influenced. Therefore, the gray wolf algorithm is introduced for improvement, the influence degree of the optimization process of the gray wolf algorithm on the population initialization effect is small, the whole population can be searched in the whole solution space after initialization, and therefore the algorithm can be effectively prevented from falling into local optimization. In the subsequent mining process, because the updated calculation formula of the wolf algorithm is more complex, more time is consumed in the process, and the optimal value is not easy to find. Therefore, in the subsequent mining of the possible region of the global optimum value, the particle swarm algorithm is adopted, and the speed and the effect of optimum value searching can be improved.
The problem to be solved in this respect is how to determine the opportunity to replace the optimization algorithm. Therefore, a self-adaptive replacement mechanism is provided, and when the gray wolf algorithm is used for optimizing, whether the optimization algorithm is replaced is judged according to the value of the found optimal solution and two thresholds. Firstly, recording the difference V between the adaptive value of the current optimal solution and the adaptive value of the previous generation optimal solution in the iterative process of the algorithm gwo When it is less than the fluctuation threshold V 1 Recording at any time, recording V gwo Number of times N of being successively smaller than fluctuation threshold V a . When N is present a Greater than a threshold N of the number of iterations 1 And replacing the particle swarm optimization for local optimization.
In addition, in the later stage of the optimization, along with the increase of the number of iterations, the optimization individuals of the whole population can be accumulated around the currently found optimal value, so that the optimization speed can continuously decrease, and the whole optimization process is adversely affected. To solve this problem, we calculate the wholeAn adaptive escape mechanism is added in the method. Similar to the adaptive alternative mechanism above, by two thresholds-the fluctuation threshold V 2 And N 2 A determination is made whether to re-disperse the particles. When the number of times of fluctuation N b Greater than N 2 And judging that the optimizing population is about to fall into local optimization. At this point, the particles need to be redistributed for global searching. By the aid of the mechanism, whether the particle swarm algorithm is trapped in a local optimal point can be judged in advance, the capability of the particles to get rid of the local optimal point can be enhanced, and the optimization level of the algorithm is improved.
Specifically, in the optimization process by using a GWOL algorithm, the optimization is firstly performed by using a wolf algorithm to search the whole solution space, and the position where the optimal solution possibly exists is obtained; after the judgment of the self-adaptive replacement mechanism, local excavation of a solution space is performed by using a particle swarm algorithm; if the self-adaptive escape mechanism judges that the population individuals fall into the local optimum, the optimized population is redistributed, and then optimization iteration is continued. And finally, ending the optimizing process according to the termination condition and outputting the optimal solution.
Drawings
FIG. 1 is a flow chart of the improved particle swarm optimization algorithm based on the Grey wolf algorithm of the invention;
FIG. 2 is a diagram of the LSTM algorithm learning process of the present invention;
FIG. 3 is a comparison of the present invention with other deep neural network optimization algorithms.
Detailed Description
The method comprises the following steps:
and 3, sending the temperature T ', the discharge depth C ', the charging rate V ', the environment temperature T ' of the lithium battery, and the environment temperature change rate delta T ' of the lithium battery of the optimal solution output in the step 2 into an LSTM prediction algorithm, establishing a service life prediction model, predicting the actual service life of the lithium battery according to the target service life of the lithium battery, and finally outputting the predicted service life of the lithium battery.
Further, in the step 2, the improved particle swarm algorithm based on the grayish wolf algorithm comprises the following specific processes:
17 Initializing an optimized population of the algorithm, randomly scattering the optimized population into the whole solution space, and setting alpha, beta and delta individuals for the wolf algorithm;
18 The optimizing population optimizes the whole solution space according to the optimizing process of the wolf algorithm;
19 Record the optimal solution V of the Grey wolf algorithm in each iteration best-g ；
20 Judging according to a self-adaptive replacement mechanism, if the optimization algorithm is replaced by the particle swarm optimization algorithm, entering 5), and if not, returning to 2) to continue searching;
21 The optimization population excavates the position where the optimal solution possibly exists according to the optimization process of the particle swarm optimization;
22 Record the optimal solution V of the particle swarm optimization in each iteration process best-p ；
23 Judging according to an adaptive escape mechanism, returning to 1) if the optimizing population is trapped into local optimum, and otherwise, entering 8) and continuing searching;
24 Judging whether the algorithm meets the condition of ending, if not, returning to 5) continuing searching, otherwise, outputting the related information of the optimal solution.
Further, in step 5) of the improved particle swarm optimization based on the grayling algorithm, when a position where an optimal solution may exist is mined, the inertia coefficient w is subjected to nonlinear decrement processing, so that the searching and optimizing capability of the improved particle swarm optimization is improved.
Further, in step 3The LSTM prediction algorithm is a recurrent neural network architecture, the basic structure of the LSTM network comprises a series of repeated units of each time step, and in each unit, at the time step t, an information storage part c t And three gate functions, i.e. input gate i t Output gate o t And forget door f t To regulate the flow of information for managing each element of the LSTM network, and to decide how to update the current storage unit c t The current hidden state h of the unit and the information stored in t The correlation calculation function for each cell in the LSTM network module is shown in the following formula.
i t ＝σ(W i· [h t-1 +b i ]) (1)
f t ＝σ(W f· [h t-1 ，x t ]+b f ) (2)
q t ＝tanh(W q· [h t-1 ，x t ]+b q ) (3)
o t ＝σ(W o· [h t-1 ，x t ]+b o ) (4)
c t ＝f t ⊙c t-1 +i t ⊙q t (5)
h t ＝o t ⊙tanh(c t ) (6)
Wherein x t Is an input characteristic in LSTM network unit, σ represents Sigmod function, and "<" represents characteristic vector element by element multiplication, and W and b represent weight matrix and offset vector during training, respectively, the LSTM network uses an LSTM module directly placed behind a MaxPooling layer, including 64 LSTM units, in which a 0.2 Dropout layer is used as a regularization parameter to prevent over-fitting of the model, and a sense layer is the last layer of the entire model, i.e., a fully connected layer in the neural network for outputting a result, for classifying the lithium battery life-related parameters according to the output of the LSTM layer.
In order to verify whether the improved algorithm is effectively applied to the service life prediction of the new energy automobile battery, 31 groups of feature data of the new energy automobile battery are selected to predict the service life, the traditional prediction method is compared, the details are shown in fig. 3, and as can be seen from fig. 3, the algorithm provided by the patent can be used for better predicting the service life of the new energy automobile battery, and compared with other algorithms, the accuracy and precision are greatly improved.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (3)
1. A new energy automobile lithium battery life prediction method based on an optimization algorithm is characterized by comprising the following steps:
step 1, collecting the temperature T, the depth of discharge C and the charging rate V of the lithium battery, the ambient temperature T of the lithium battery and the ambient temperature change rate delta T of the lithium battery in a period of time, recording the temperature T and the ambient temperature change rate delta T as health state data of a first group of lithium batteries, searching health state data of a plurality of groups of lithium batteries in different periods of time, and finding out the health state data of n groups of lithium batteries in total;
step 2, according to a lithium battery discharge curve rule, sending the health state data of the n groups of lithium batteries obtained in the step 1 into an improved particle swarm algorithm based on a gray wolf algorithm, and outputting the temperature T ', the discharge depth C ', the charging rate V ', the environment temperature T ' of the lithium batteries, and the environment temperature change rate delta T ' of the lithium batteries of an optimal solution;
step 3, sending the temperature T ', the discharge depth C ', the charging rate V ', the environment temperature T ' of the lithium battery, and the environment temperature change rate delta T ' of the lithium battery of the optimal solution output in the step 2 into an LSTM prediction algorithm, establishing a service life prediction model, predicting the actual service life of the lithium battery according to the target service life of the lithium battery, and finally outputting the predicted service life of the lithium battery;
the improved particle swarm algorithm based on the wolf's head algorithm in the step 2 comprises the following specific processes:
1) Initializing an optimizing population of the algorithm, randomly scattering the optimizing population into the whole solution space, and setting alpha, beta and delta individuals for the wolf algorithm;
2) The optimizing population optimizes the whole solution space according to the optimizing process of the Hui wolf algorithm;
3) Recording the optimal solution V of the gray wolf algorithm in each iteration process best-g ；
4) Judging according to a self-adaptive replacement mechanism, if the optimization algorithm is replaced by a particle swarm algorithm, entering 5), and if not, returning to 2) to continue searching; the self-adaptive replacement mechanism judges whether to replace the optimization algorithm according to the value of the found optimal solution and two threshold values when the gray wolf algorithm is used for optimization, and firstly records the difference V between the adaptive value of the current optimal solution and the adaptive value of the previous generation optimal solution in the algorithm iteration process gwo When it is less than the fluctuation threshold V c Recording at any time, recording V gwo Number N of consecutive times less than fluctuation threshold V a When N is present a When the iteration times are larger than the threshold value N1 of the iteration times, the local optimization is performed by replacing the particle swarm algorithm;
5) The optimizing population excavates the position where the optimal solution possibly exists according to the optimizing process of the particle swarm algorithm;
6) Recording the optimal solution V of the particle swarm algorithm in each iteration process best-p ；
7) Judging according to a self-adaptive escape mechanism, if the optimizing population is trapped into local optimum, returning to 1), otherwise, entering 8) and continuing searching;
8) Judging whether the algorithm meets the condition of ending, if not, returning to 5) to continue searching, otherwise, outputting the related information of the optimal solution.
2. The method for predicting the lithium battery life of the new energy automobile based on the optimization algorithm as claimed in claim 1, wherein in the step 5) of the improved particle swarm optimization based on the grayling algorithm, when a position where an optimal solution may exist is mined, the inertia coefficient w is subjected to nonlinear decrement processing to improve the searching and optimization capability.
3. The method of claim 1, wherein the LSTM prediction algorithm in step 3 is a recurrent neural network structure, the basic structure of the LSTM network comprises a series of repeating units for each time step, and at each unit, at time step t, an information storage part c is provided t And three gate functions, i.e. input gate i t Output gate o t And forget door f t To regulate the flow of information for managing each unit in the LSTM network, and to decide how to update the current storage unit c t The information stored in and the current hidden state h of the unit t The correlation calculation function for each unit in the LSTM network module is shown in the following equation:
i t ＝σ(W i .[h t-1 +b i ]) (1)
f t ＝σ(W f .[h t-1 ，x t ]+b f ) (2)
q t ＝tanh(W q .[h t-1 ，x t ]+b q ) (3)
o t ＝σ(W o .[h t-1 ，x t ]+b o ) (4)
c t ＝f t ⊙c t-1 +i t ⊙q t (5)
h t ＝o t ⊙tanh(c t ) (6)
wherein x t Is an input characteristic in LSTM network unit, σ represents Sigmod function, and "<" represents characteristic vector element by element multiplication, and W and b represent weight matrix and offset vector during training, respectively, the LSTM network uses an LSTM module directly placed behind a MaxPooling layer, including 64 LSTM units, in which a 0.2 Dropout layer is used as a regularization parameter to prevent over-fitting of the model, and a sense layer is the last layer of the entire model, i.e., a fully connected layer in the neural network for outputting a result, for classifying the lithium battery life-related parameters according to the output of the LSTM layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210177290.1A CN114545280B (en) | 2022-02-24 | 2022-02-24 | New energy automobile lithium battery life prediction method based on optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210177290.1A CN114545280B (en) | 2022-02-24 | 2022-02-24 | New energy automobile lithium battery life prediction method based on optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114545280A CN114545280A (en) | 2022-05-27 |
| CN114545280B true CN114545280B (en) | 2022-11-15 |
Family
ID=81679040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210177290.1A Active CN114545280B (en) | 2022-02-24 | 2022-02-24 | New energy automobile lithium battery life prediction method based on optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114545280B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117129899B (en) * | 2023-08-31 | 2024-05-10 | 重庆跃达新能源有限公司 | Battery health state prediction management system and method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460451A (en) * | 2018-02-12 | 2018-08-28 | 北京新能源汽车股份有限公司 | Method and device for optimizing key parameters for battery state of charge estimation based on particle swarm optimization |
| CN109993270A (en) * | 2019-03-27 | 2019-07-09 | 东北大学 | Lithium ion battery residual life prediction technique based on grey wolf pack optimization LSTM network |
| CN110443002A (en) * | 2019-08-16 | 2019-11-12 | 中国水利水电科学研究院 | A kind of Deformation of Steep Slopes prediction technique and system |
| CN111709524A (en) * | 2020-07-03 | 2020-09-25 | 江苏科技大学 | RBF neural network optimization method based on improved GWO algorithm |
| CN112258587A (en) * | 2020-10-27 | 2021-01-22 | 上海电力大学 | Camera calibration method based on wolf-wolf particle swarm hybrid algorithm |
| AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
| CN112734097A (en) * | 2020-12-31 | 2021-04-30 | 中南大学 | Unmanned train energy consumption prediction method, system and storage medium |
| CN113049960A (en) * | 2021-02-07 | 2021-06-29 | 安徽贵博新能科技有限公司 | Battery health state estimation method based on intelligent optimization algorithm |
| CN113434856A (en) * | 2021-07-06 | 2021-09-24 | 中国人民解放军空军工程大学 | Network intrusion detection method based on PSOGWO-SVM algorithm |
| CN113671401A (en) * | 2021-08-30 | 2021-11-19 | 武汉理工大学 | Lithium battery health state assessment method based on optimization algorithm and data driving |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9442165B2 (en) * | 2012-07-07 | 2016-09-13 | Nec Corporation | Method for estimating battery life in presence of partial charge and discharge cycles |
| US11340306B2 (en) * | 2017-11-16 | 2022-05-24 | Semiconductor Energy Laboratory Co., Ltd. | Lifetime estimation device, lifetime estimation method, and abnormality detection method of secondary battery |
-
2022
- 2022-02-24 CN CN202210177290.1A patent/CN114545280B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460451A (en) * | 2018-02-12 | 2018-08-28 | 北京新能源汽车股份有限公司 | Method and device for optimizing key parameters for battery state of charge estimation based on particle swarm optimization |
| CN109993270A (en) * | 2019-03-27 | 2019-07-09 | 东北大学 | Lithium ion battery residual life prediction technique based on grey wolf pack optimization LSTM network |
| CN110443002A (en) * | 2019-08-16 | 2019-11-12 | 中国水利水电科学研究院 | A kind of Deformation of Steep Slopes prediction technique and system |
| CN111709524A (en) * | 2020-07-03 | 2020-09-25 | 江苏科技大学 | RBF neural network optimization method based on improved GWO algorithm |
| CN112258587A (en) * | 2020-10-27 | 2021-01-22 | 上海电力大学 | Camera calibration method based on wolf-wolf particle swarm hybrid algorithm |
| AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
| CN112734097A (en) * | 2020-12-31 | 2021-04-30 | 中南大学 | Unmanned train energy consumption prediction method, system and storage medium |
| CN113049960A (en) * | 2021-02-07 | 2021-06-29 | 安徽贵博新能科技有限公司 | Battery health state estimation method based on intelligent optimization algorithm |
| CN113434856A (en) * | 2021-07-06 | 2021-09-24 | 中国人民解放军空军工程大学 | Network intrusion detection method based on PSOGWO-SVM algorithm |
| CN113671401A (en) * | 2021-08-30 | 2021-11-19 | 武汉理工大学 | Lithium battery health state assessment method based on optimization algorithm and data driving |
Non-Patent Citations (4)
| Title |
|---|
| A Hybrid Multi-group Co-evolution Intelligent Optimization Algorithm: PSO-GWO;Ziheng Li 等;《2021 IEEE International Conference on Electrical Engineering and Mechatronics Technology (ICEEMT) 》;20211107;全文 * |
| A method for state-of-charge estimation of lithium-ion batteries based on PSO-LSTM;Ren Xiaoqing;《Energy》;20210908;全文 * |
| 具有自适应逃逸的环状全互连结构粒子群算法;靳雁霞 等;《微电子学与计算机》;20180205;全文 * |
| 基于IGWO-RBF的LTE-R切换算法研究;苏佳丽等;《计算机工程与应用》;20190430(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114545280A (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993270B (en) | Lithium ion battery residual life prediction method based on gray wolf group optimization LSTM network | |
| CN112487702B (en) | Method for predicting residual service life of lithium ion battery | |
| CN113156325A (en) | Method for estimating state of health of battery | |
| CN113821875B (en) | Intelligent vehicle fault real-time prediction method and system based on end cloud cooperation | |
| CN117010576B (en) | Energy consumption prediction method based on elastic dynamic neural network | |
| CN114545280B (en) | New energy automobile lithium battery life prediction method based on optimization algorithm | |
| CN112000015A (en) | Intelligent BIT design method for heavy-duty gas turbine control system controller module based on LSTM and bio-excitation neural network | |
| CN110794308B (en) | Method and device for predicting train battery capacity | |
| CN112363896A (en) | Log anomaly detection system | |
| CN116306229A (en) | Power short-term load prediction method based on deep reinforcement learning and migration learning | |
| CN113658423B (en) | Vehicle track abnormality detection method based on circulation gating unit | |
| CN114596726A (en) | Parking position prediction method based on interpretable space-time attention mechanism | |
| Hu et al. | Multi-objective optimization estimation of state of health for lithium-ion battery based on constant current charging profile | |
| CN113884936A (en) | Lithium ion battery health state prediction method based on ISSA coupling DELM | |
| CN116844340B (en) | Road traffic risk prediction method based on artificial intelligence | |
| CN117648675A (en) | Early warning method for abrasion loss of pantograph of urban rail train | |
| CN115495661A (en) | Self-adaptive interest point recommendation method based on long-term and short-term preference of user | |
| CN114971022A (en) | Wind power prediction method based on D-value-LSTM neural network model | |
| CN114444737A (en) | Intelligent pavement maintenance planning method based on transfer learning | |
| CN116299005B (en) | Power battery health state prediction method based on AAF and deep learning | |
| CN117633916B (en) | Data destruction safety control method based on BP neural network and genetic algorithm | |
| CN112712159A (en) | LSTM short-time traffic flow prediction method based on improved PSO algorithm | |
| CN116203448B (en) | Power battery residual life prediction method based on Monte Carlo and deep learning | |
| EP4170151A1 (en) | Engine control device, and engine control method | |
| CN117216492A (en) | Lithium battery SOH and RUL collaborative prediction method based on nonlinear enhanced LSTM |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230913 Address after: 230000 B-2704, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui. Patentee after: HEFEI LONGZHI ELECTROMECHANICAL TECHNOLOGY Co.,Ltd. Address before: No. 106 Zhineng Avenue, International Education Park, Wuzhong District, Suzhou City, Jiangsu Province Patentee before: SUZHOU VOCATIONAL University |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240313 Address after: Floor 13, No. 161 Zhongshan 3rd Road, Yuzhong District, Chongqing, 400000 Patentee after: Qicheng New Energy Technology (Chongqing) Co.,Ltd. Country or region after: China Address before: 230000 B-2704, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui. Patentee before: HEFEI LONGZHI ELECTROMECHANICAL TECHNOLOGY Co.,Ltd. Country or region before: China |