CN113376536A - Data-driven high-precision lithium battery SOC (State of Charge) joint estimation method and system - Google Patents
Data-driven high-precision lithium battery SOC (State of Charge) joint estimation method and system Download PDFInfo
- Publication number
- CN113376536A CN113376536A CN202110435042.8A CN202110435042A CN113376536A CN 113376536 A CN113376536 A CN 113376536A CN 202110435042 A CN202110435042 A CN 202110435042A CN 113376536 A CN113376536 A CN 113376536A
- Authority
- CN
- China
- Prior art keywords
- svm model
- condition
- particle
- fitness
- judged
- 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 70
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 30
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 9
- 239000002245 particle Substances 0.000 claims description 57
- 230000001133 acceleration Effects 0.000 claims description 6
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 230000008569 process Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction 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]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
-
- 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]
- G01R31/3644—Constructional arrangements
- G01R31/3648—Constructional arrangements comprising digital calculation means, e.g. for performing an algorithm
-
- 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]
- G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a data-driven high-precision lithium battery SOC joint estimation method and system, and belongs to the technical field of SOC estimation of lithium batteries. The method comprises the following steps: constructing an initial SVM model; determining a penalty factor of the SVM model by adopting a PSO method; updating the SVM model according to the penalty factor; training and testing the SVM model to determine the accuracy of the SVM model in estimating SOC; judging whether the precision is smaller than a preset threshold value or not; under the condition that the precision is judged to be greater than or equal to the threshold value, determining a penalty factor of the SVM again by adopting a PSO method, and executing corresponding steps of the method until the precision is judged to be less than the threshold value; and under the condition that the accuracy is judged to be smaller than the threshold value, outputting the SVM model, and estimating the SOC value by adopting the SVM model. The method and the system can accurately estimate the SOC value of the lithium battery.
Description
Technical Field
The invention relates to the technical field of SOC estimation of lithium batteries, in particular to a data-driven high-precision lithium battery SOC joint estimation method and system.
Background
At present, aiming at a great deal of research of a power battery model, an electrochemical model can deeply describe microscopic chemical reactions in a power lithium battery, but the complexity of the model is too high due to a plurality of related parameters, the equivalent circuit model has simple parameter identification and is more suitable for online real-time estimation, but electrochemical explanation of the microscopic reactions in the battery is lacked, and the natural attenuation and cyclic attenuation characteristics of the lithium battery change the model parameters, so that the modeling precision of the electrochemical power battery is insufficient, the adaptation range of the model is small, the parameters are uncertain, and the parameters have great influence on the estimation precision of the State of charge (SOC) of the lithium battery. In recent years, a learning algorithm based on data driving is widely applied to lithium battery SOC estimation, while a lithium ion battery is taken as a typical nonlinear complex system, the internal complex chemical reaction process and the uncertain external environment have certain advantages in the aspects of training a battery model by adopting a nonlinear relation between input and output data and describing the dynamic characteristics of the battery, but the accuracy of the constructed model directly determines the SOC estimation precision of the lithium battery.
Disclosure of Invention
The invention aims to provide a data-driven high-precision lithium battery SOC joint estimation method and system, which can accurately estimate the SOC value of a lithium battery.
In order to achieve the above object, an embodiment of the present invention provides a data-driven high-precision lithium battery SOC joint estimation method, including:
constructing an initial SVM model;
determining a penalty factor of the SVM model by adopting a PSO method;
updating the SVM model according to the penalty factor;
training and testing the SVM model to determine the accuracy of the SVM model in estimating SOC;
judging whether the precision is smaller than a preset threshold value or not;
under the condition that the precision is judged to be greater than or equal to the threshold value, determining a penalty factor of the SVM again by adopting a PSO method, and executing corresponding steps of the method until the precision is judged to be less than the threshold value; and
and under the condition that the accuracy is judged to be smaller than the threshold value, outputting the SVM model, and estimating the SOC value by adopting the SVM model.
Optionally, the determining the penalty factor of the SVM model by using the PSO method includes:
determining kernel parameters of the SVM model by adopting a PSO algorithm;
the updating the SVM model according to the penalty factor comprises:
and updating the SVM model according to the penalty factor and the nuclear parameter.
Optionally, the PSO method includes:
initializing each particle of the respective population of particles;
calculating the fitness of each particle;
updating each particle and the corresponding position and velocity;
judging whether the exiting condition of the algorithm is met or not at present;
outputting the optimal particles under the condition of judging that the exit condition of the algorithm is met;
under the condition that the exit condition of the algorithm is judged not to be met, the fitness of each particle is calculated again and the corresponding steps of the method are executed until the exit condition of the algorithm is judged to be met.
Optionally, said initializing each particle of the respective particle population comprises:
and encoding the particles by using a binary symbol string with a preset length, and representing the gene value of each particle by using a number 0 or 1.
Optionally, the updating each particle and the corresponding position and velocity comprises:
the speed is updated according to equation (1),
vk+1=ωvk+c1r1(pb-xk)+c2r2(gb-xk), (1)
wherein v isk+1For updated velocity, ω is the inertial weight, vkTo speed before update, c1、c2Is an acceleration constant, r1、r2Is an acceleration weight coefficient, pbFor the individual optimal solution, gbFor a global optimal solution, xkIs the current position of the particle.
Optionally, the updating each particle and the corresponding position and velocity comprises:
said position is further described according to equation (2),
xk+1=xk+vk, (2)
wherein x isk+1For the updated position, xkFor said position before updating, vkIs the current velocity of the particle.
Optionally, the determining whether the exit condition of the algorithm is currently satisfied includes:
judging whether the current iteration times are larger than or equal to a preset time threshold value or not;
determining that the exit condition is satisfied under the condition that the iteration number is judged to be greater than or equal to the number threshold;
and determining that the exit condition is not met under the condition that the iteration number is judged to be smaller than the number threshold.
Optionally, the calculating the fitness of each particle comprises:
adding parameters in the particles into an SVM model;
calculating the accuracy of the added SVM model to be used as the fitness;
the judging whether the exiting condition of the algorithm is met currently comprises the following steps:
judging whether the fitness of the current optimal particle is smaller than or equal to a preset fitness threshold value or not;
determining that the exit condition is met under the condition that the fitness of the current optimal particle is judged to be less than or equal to the fitness threshold;
and under the condition that the fitness of the current particle is judged to be larger than the fitness threshold, determining that the exit condition is not met.
In another aspect, the invention further provides a data driving type high-precision lithium battery SOC joint estimation system, which includes a processor for executing any one of the methods described above.
In yet another aspect, the present invention also provides a storage medium storing instructions for reading by a machine to cause the machine to perform a method as claimed in any one of the above.
By adopting the technical scheme, the data-driven high-precision lithium battery SOC joint estimation method and system provided by the invention optimize a plurality of parameters of the SVM model by adopting the PSO algorithm, overcome the technical defect of low estimation precision caused by the fact that the SVM model is not combined with uncertain characteristics of a lithium battery when the SOC value is directly estimated, and improve the estimation precision of the SOC value of the lithium battery.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
fig. 1 is a flow chart of a data-driven high-precision lithium battery SOC joint estimation method according to an embodiment of the present invention;
FIG. 2 is a partial flow diagram of a method for jointly estimating SOC of a data-driven high-precision lithium battery according to an embodiment of the present invention;
FIG. 3 is a partial flow diagram of a method for jointly estimating SOC of a data-driven high-precision lithium battery according to an embodiment of the present invention; and
fig. 4 is a partial flowchart of a data-driven high-precision lithium battery SOC joint estimation method according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
In the embodiments of the present invention, unless otherwise specified, the use of directional terms such as "upper, lower, top, and bottom" is generally used with respect to the orientation shown in the drawings or the positional relationship of the components with respect to each other in the vertical, or gravitational direction.
In addition, if there is a description of "first", "second", etc. in the embodiments of the present invention, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between the various embodiments can be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not be within the protection scope of the present invention.
Fig. 1 is a flowchart of a method for jointly estimating SOC of a data-driven high-precision lithium battery according to an embodiment of the present invention. In fig. 1, the method may include:
in step S10, an initial SVM model is constructed;
in step S11, determining a penalty factor of the SVM model by using a PSO method;
in step S12, updating the SVM model according to the penalty factor;
in step S13, training and testing the SVM model to determine the accuracy of the SVM model to estimate SOC;
in step S14, it is determined whether the accuracy is less than a preset threshold;
under the condition that the judgment precision is greater than or equal to the threshold, determining the penalty factor of the SVM again by adopting the PSO method (namely returning to the step of executing S11), and executing the corresponding steps of the method until the judgment precision is less than the threshold;
in step S15, when the determination accuracy is smaller than the threshold, an SVM model is output, and the SOC value is estimated using the SVM model.
In the method shown in fig. 1, it is obvious that training and testing directly by using an initial SVM model cannot meet the requirement of estimating SOC with high accuracy, and meanwhile, the number of training iterations is greatly increased in the process of training the SVM model because the values of the penalty factor and the kernel parameter in the initial stage are often default values. Therefore, in step S11, the inventor first determines the penalty factor by using the PSO algorithm, which reduces the difficulty of the SVM model in subsequent training and testing, thereby improving the efficiency of the algorithm. In the case that it is determined in step S14 that the accuracy of the SVM model is smaller than the preset threshold, this indicates that the accuracy of the SVM model can meet the requirement, so the SOC value can be estimated by directly using the SVM model.
Further, in the method as shown in fig. 1, the inventors determined penalty factors using the PSO algorithm can achieve a reduction in the number of iterations in training and testing of SVM models. Then similarly, the PSO algorithm may also be used to determine the kernel parameters of the SVM model, i.e. the method as shown in fig. 2. Compared with the method shown in fig. 1, the method shown in fig. 2 determines the kernel parameter and the penalty factor at the same time, so that the SVM model can obtain a better initial value before training, thereby further reducing the number of iterations of training and testing. Specifically, in fig. 2, the method may include:
in step S20, an initial SVM model is constructed;
in step S21, determining a penalty factor and a kernel parameter of the SVM model by using a PSO method;
in step S22, updating the SVM model and the kernel parameters according to the penalty factor;
in step S23, training and testing the SVM model to determine the accuracy of the SVM model to estimate SOC;
in step S24, it is determined whether the accuracy is less than a preset threshold;
under the condition that the judgment precision is greater than or equal to the threshold, determining the penalty factor of the SVM again by adopting the PSO method (namely returning to the step of executing S21), and executing the corresponding steps of the method until the judgment precision is less than the threshold;
in step S25, when the determination accuracy is smaller than the threshold, an SVM model is output, and the SOC value is estimated using the SVM model.
In addition, in this embodiment, the PSO algorithm may be a method known to those skilled in the art. However, in a preferred example of the present invention, the PSO algorithm may also include the steps shown in fig. 3. In fig. 3, the PSO algorithm may include:
in step S30, each particle of the respective particle group is initialized. In this case, the process of initializing each particle may be various methods known to those skilled in the art, but in a preferred example of the present invention, in order to reduce the amount of calculation in the updating process in consideration of the process of subsequent updating, the particles may be encoded by using a binary symbol string of a preset length, and the gene value of each particle may be represented by using a number of 0 or 1.
In step S31, the fitness of each particle is calculated. The calculation method of the fitness may be various methods known to those skilled in the art. However, considering that the fitness directly determines whether the determined penalty factor/kernel parameter can provide a good initial value to the SVM model, in a preferred example of the present invention, the fitness may be calculated by first adding the parameters in the particles to the SVM model, and then calculating the accuracy of the added SVM model as the fitness.
In step S32, each particle and the corresponding position and velocity are updated. The method of updating the position and velocity, among others, can be in a number of ways known to those skilled in the art. In a preferred example of the present invention, the position and velocity may be updated using formula (1) and formula (2),
vk+1=ωvk+c1r1(pb-xk)+c2r2(gb-xk), (1)
wherein v isk+1For updated velocity, ω is the inertial weight, vkTo speed before update, c1、c2Is an acceleration constant, r1、r2Is an acceleration weight coefficient, pbFor the individual optimal solution, gbFor a global optimal solution, xkThe current position of the particle;
xk+1=xk+vk, (2)
wherein x isk+1For updated position, xkTo the position before update, vkIs the current velocity of the particle.
In step S33, it is determined whether the exit condition of the algorithm is currently satisfied. Wherein the exit conditions can be in a variety of ways known to those skilled in the art. In an example of the present invention, the exit condition may be directly determining whether the current iteration number is greater than or equal to a preset number threshold; determining that an exit condition is met under the condition that the iteration number is judged to be greater than or equal to the number threshold; and under the condition that the iteration number is judged to be less than the number threshold, determining that the exit condition is not met. The method can also avoid long-time execution of the algorithm under the condition that the optimal solution cannot be obtained. In another example of the present invention, the exit condition may also be to determine whether the fitness of the current optimal particle is less than or equal to a preset fitness threshold; determining that an exit condition is met under the condition that the fitness of the current optimal particle is judged to be less than or equal to a fitness threshold; and under the condition that the fitness of the current particle is judged to be larger than the fitness threshold, determining that the exit condition is not met. This method ensures a higher accuracy of the particles obtained compared to the former. In yet another example of the present invention, the inventor considers that the algorithm needs to avoid the occurrence of the defect of dead loop that the optimal solution cannot be obtained, and also needs to ensure that the obtained precision is in a more accurate range. The two can thus be combined directly. In particular, the exit condition may comprise the steps as shown in fig. 4:
in step S40, determining whether the fitness of the current optimal particle is less than or equal to a preset fitness threshold;
in step S41, in a case that it is determined whether the fitness of the current optimal particle is greater than a preset fitness threshold, it is determined whether the current iteration number is greater than or equal to a preset number threshold;
in step S42, determining that an exit condition is satisfied when the fitness of the current optimal particle is determined to be less than or equal to a preset fitness threshold and/or the current iteration number is determined to be greater than or equal to a preset number threshold;
in step S43, in the case where it is determined that the current iteration number is smaller than the preset number threshold, it is determined that the exit condition is not satisfied.
In step S34, when it is determined that the exit condition of the algorithm is satisfied, the optimal particle is output.
In the case where it is judged that the exit condition of the algorithm is not satisfied, the fitness of each particle is calculated again and the corresponding step of the method is performed (i.e., the execution returns to the step S31) until it is judged that the exit condition of the algorithm is satisfied.
In another aspect, the invention further provides a data driving type high-precision lithium battery SOC joint estimation system, which includes a processor for executing any one of the methods described above.
In yet another aspect, the present invention also provides a storage medium storing instructions for reading by a machine to cause the machine to perform a method as claimed in any one of the above.
By adopting the technical scheme, the data-driven high-precision lithium battery SOC joint estimation method and system provided by the invention optimize a plurality of parameters of the SVM model by adopting the PSO algorithm, overcome the technical defect of low estimation precision caused by the fact that the SVM model is not combined with uncertain characteristics of a lithium battery when the SOC value is directly estimated, and improve the estimation precision of the SOC value of the lithium battery.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solution of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications all belong to the protection scope of the embodiments of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, the embodiments of the present invention will not be described separately for the various possible combinations.
Those skilled in the art can understand that all or part of the steps in the method for implementing the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, various different embodiments of the present invention may be arbitrarily combined with each other, and the embodiments of the present invention should be considered as disclosed in the disclosure of the embodiments of the present invention as long as the embodiments do not depart from the spirit of the embodiments of the present invention.
Claims (10)
1. A data-driven high-precision lithium battery SOC joint estimation method is characterized by comprising the following steps:
constructing an initial SVM model;
determining a penalty factor of the SVM model by adopting a PSO method;
updating the SVM model according to the penalty factor;
training and testing the SVM model to determine the accuracy of the SVM model in estimating SOC;
judging whether the precision is smaller than a preset threshold value or not;
under the condition that the precision is judged to be greater than or equal to the threshold value, determining a penalty factor of the SVM again by adopting a PSO method, and executing corresponding steps of the method until the precision is judged to be less than the threshold value; and
and under the condition that the accuracy is judged to be smaller than the threshold value, outputting the SVM model, and estimating the SOC value by adopting the SVM model.
2. The method of claim 1, wherein determining the penalty factor for the SVM model using the PSO method comprises:
determining kernel parameters of the SVM model by adopting a PSO algorithm;
the updating the SVM model according to the penalty factor comprises:
and updating the SVM model according to the penalty factor and the nuclear parameter.
3. The method of claim 1, wherein the PSO method comprises:
initializing each particle of the respective population of particles;
calculating the fitness of each particle;
updating each particle and the corresponding position and velocity;
judging whether the exiting condition of the algorithm is met or not at present;
outputting the optimal particles under the condition of judging that the exit condition of the algorithm is met;
under the condition that the exit condition of the algorithm is judged not to be met, the fitness of each particle is calculated again and the corresponding steps of the method are executed until the exit condition of the algorithm is judged to be met.
4. The method of claim 3, wherein initializing each particle of the respective population of particles comprises:
and encoding the particles by using a binary symbol string with a preset length, and representing the gene value of each particle by using a number 0 or 1.
5. The method of claim 3, wherein updating each particle and corresponding position and velocity comprises:
the speed is updated according to equation (1),
vk+1=ωvk+c1r1(pb-xk)+c2r2(gb-xk), (1)
wherein v isk+1For updated velocity, ω is the inertial weight, vkTo speed before update, c1、c2Is an acceleration constant, r1、r2Is an acceleration weight coefficient, pbFor the individual optimal solution, gbFor a global optimal solution, xkIs the current position of the particle.
6. The method of claim 3, wherein updating each particle and corresponding position and velocity comprises:
said position is further described according to equation (2),
xk+1=xk+vk, (2)
wherein x isk+1For the updated position, xkFor said position before updating, vkIs the current velocity of the particle.
7. The method of claim 3, wherein said determining whether an exit condition of the algorithm is currently satisfied comprises:
judging whether the current iteration times are larger than or equal to a preset time threshold value or not;
determining that the exit condition is satisfied under the condition that the iteration number is judged to be greater than or equal to the number threshold;
and determining that the exit condition is not met under the condition that the iteration number is judged to be smaller than the number threshold.
8. The method of claim 3, wherein calculating the fitness for each particle comprises:
adding parameters in the particles into an SVM model;
calculating the accuracy of the added SVM model to be used as the fitness;
the judging whether the exiting condition of the algorithm is met currently comprises the following steps:
judging whether the fitness of the current optimal particle is smaller than or equal to a preset fitness threshold value or not;
determining that the exit condition is met under the condition that the fitness of the current optimal particle is judged to be less than or equal to the fitness threshold;
and under the condition that the fitness of the current particle is judged to be larger than the fitness threshold, determining that the exit condition is not met.
9. A data-driven high-precision combined estimation system for the SOC of a lithium battery, the system comprising a processor configured to perform the method according to any one of claims 1 to 8.
10. A storage medium storing instructions for reading by a machine to cause the machine to perform a method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110435042.8A CN113376536A (en) | 2021-04-22 | 2021-04-22 | Data-driven high-precision lithium battery SOC (State of Charge) joint estimation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110435042.8A CN113376536A (en) | 2021-04-22 | 2021-04-22 | Data-driven high-precision lithium battery SOC (State of Charge) joint estimation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113376536A true CN113376536A (en) | 2021-09-10 |
Family
ID=77569863
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110435042.8A Pending CN113376536A (en) | 2021-04-22 | 2021-04-22 | Data-driven high-precision lithium battery SOC (State of Charge) joint estimation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113376536A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107132490A (en) * | 2017-07-05 | 2017-09-05 | 福州大学 | A kind of method for realizing the estimation of lithium battery group state-of-charge |
CN107274012A (en) * | 2017-06-06 | 2017-10-20 | 上海电机学院 | Short-term wind power forecast method based on cloud evolution particle cluster algorithm |
WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
CN108120451A (en) * | 2017-12-21 | 2018-06-05 | 苏州大学 | Based on silicon micro accerometer temperature-compensation method, the system for improving PSO optimization neural networks |
CN109344918A (en) * | 2018-12-05 | 2019-02-15 | 国网陕西省电力公司宝鸡供电公司 | Based on the big data distribution network fault line selection analysis method for improving particle swarm algorithm |
US20210049515A1 (en) * | 2019-08-16 | 2021-02-18 | China Institute Of Water Resources And Hydropower Research | Prediction method and system of high slope deformation |
CN112379268A (en) * | 2020-09-29 | 2021-02-19 | 合肥工业大学 | Lithium battery SOC estimation method and device based on SVM _ EKF algorithm and storage medium |
-
2021
- 2021-04-22 CN CN202110435042.8A patent/CN113376536A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
CN107274012A (en) * | 2017-06-06 | 2017-10-20 | 上海电机学院 | Short-term wind power forecast method based on cloud evolution particle cluster algorithm |
CN107132490A (en) * | 2017-07-05 | 2017-09-05 | 福州大学 | A kind of method for realizing the estimation of lithium battery group state-of-charge |
CN108120451A (en) * | 2017-12-21 | 2018-06-05 | 苏州大学 | Based on silicon micro accerometer temperature-compensation method, the system for improving PSO optimization neural networks |
CN109344918A (en) * | 2018-12-05 | 2019-02-15 | 国网陕西省电力公司宝鸡供电公司 | Based on the big data distribution network fault line selection analysis method for improving particle swarm algorithm |
US20210049515A1 (en) * | 2019-08-16 | 2021-02-18 | China Institute Of Water Resources And Hydropower Research | Prediction method and system of high slope deformation |
CN112379268A (en) * | 2020-09-29 | 2021-02-19 | 合肥工业大学 | Lithium battery SOC estimation method and device based on SVM _ EKF algorithm and storage medium |
Non-Patent Citations (1)
Title |
---|
张凯: "基于粒子群算法优化SVM在电池SOC估算中的应用", 《机械工程与自动化》, no. 2, pages 154 - 155 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110766044B (en) | Neural network training method based on Gaussian process prior guidance | |
CN113253116A (en) | Lithium ion battery state of charge estimation method and storage medium | |
CN113561986A (en) | Decision-making method and device for automatically driving automobile | |
CN114194211B (en) | Automatic driving method and device, electronic equipment and storage medium | |
CN111951901A (en) | Optimization apparatus, optimization system, optimization method, and recording medium | |
CN112232495A (en) | Prediction model training method, device, medium and computing equipment | |
CN116596060B (en) | Deep reinforcement learning model training method and device, electronic equipment and storage medium | |
CN111626489A (en) | Shortest path planning method and device based on time sequence difference learning algorithm | |
CN112613608A (en) | Reinforced learning method and related device | |
CN112379268A (en) | Lithium battery SOC estimation method and device based on SVM _ EKF algorithm and storage medium | |
TWI465939B (en) | A Multi - stage Fast Charge Method for Optimizing Lithium Batteries | |
CN113376536A (en) | Data-driven high-precision lithium battery SOC (State of Charge) joint estimation method and system | |
CN116388864B (en) | Quantum network device performance prediction method and device, electronic device and storage medium | |
CN110443292B (en) | Multi-influence-factor crowdsourcing answer decision method | |
CN114859231B (en) | Battery remaining life prediction method based on wiener process and extreme learning machine | |
CN116595865A (en) | Equipment residual life prediction method based on wiener process | |
CN115951236A (en) | Lithium battery state monitoring method, system, device and storage medium | |
CN116224070A (en) | OCV (open circuit voltage) -SOC (system on a chip) model-based full-temperature lithium ion battery OCV (open circuit voltage) evaluation method and system | |
CN112836381B (en) | Multi-source information-based ship residual life prediction method and system | |
CN114814628A (en) | Method and device for predicting service life of energy storage battery | |
CN116340766B (en) | Sliding window-based lithium battery SOC online prediction method and related equipment | |
CN116299005B (en) | Power battery health state prediction method based on AAF and deep learning | |
CN114895190B (en) | Method and equipment for estimating charge quantity based on extreme learning and extended Kalman filtering | |
CN113822445B (en) | Model integrated prediction method, system, electronic equipment and storage medium | |
CN114566227B (en) | PH neutralization process model identification method based on Newton iteration algorithm |
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 |