CN116626515A - Random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation - Google Patents
Random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation Download PDFInfo
- Publication number
- CN116626515A CN116626515A CN202310616982.6A CN202310616982A CN116626515A CN 116626515 A CN116626515 A CN 116626515A CN 202310616982 A CN202310616982 A CN 202310616982A CN 116626515 A CN116626515 A CN 116626515A
- Authority
- CN
- China
- Prior art keywords
- random forest
- ukf
- cloud
- soc
- lithium 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.)
- Pending
Links
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 42
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007637 random forest analysis Methods 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000005259 measurement Methods 0.000 claims description 16
- 238000003066 decision tree Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 8
- 238000012952 Resampling Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000006467 substitution reaction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 230000004044 response Effects 0.000 abstract description 2
- 238000007500 overflow downdraw method Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004146 energy storage Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
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
-
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation. The SOC estimation method is a Random Forest and unscented Kalman filtering fusion method (Random Forest-Unscented Kalman Filter, RF-UKF), a Random Forest model is used as an observation equation of the UKF, strong nonlinear fitting capacity of the Random Forest is utilized, and meanwhile, the UKF is combined, so that noise errors or the influence of other uncertain factors are reduced, and a more accurate SOC estimation result is obtained. The training of the random forest model requires larger computing resources, so that the training is completed at a cloud server; meanwhile, the UKF filtering algorithm is calculated on the edge side, so that cloud edge data transmission is reduced. Therefore, the cloud edge cooperative technology-based cloud edge cooperative system not only utilizes the strong computing power of the cloud server, but also ensures the response speed of the system.
Description
Technical Field
The invention belongs to the field of lithium battery SOC estimation, and particularly relates to a random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation.
Background
The application of the advanced energy storage technology can effectively promote the large-scale grid connection of renewable energy sources and improve the efficiency of the power system. In the use process of the battery, a battery health management system (battery management system, BMS) is required to estimate and predict various states of the battery in the energy storage system, wherein the state of charge (SOC) of the battery is taken as an important basis for judging the running state of the battery, and is one of key parameters of the BMS.
The lithium battery SOC estimation method mainly comprises an ampere-hour integration method, an open-circuit voltage method, a state observer estimation method, a data driving estimation method and the like. Because hysteresis effect, various field stress interferences and measurement equipment have direct influence on the voltage of the battery terminal under the dynamic working condition, the accuracy of an ampere-hour integration method and an open-circuit voltage estimation method is limited; the recursive calculation process of the state observer estimation method is influenced by the assumption condition, working condition factors, system noise and measurement noise, and the Kalman filtering algorithm influences the nonlinear mapping adjustment capability of the battery, so that the calculation precision is directly limited; the machine learning and deep learning algorithm has strong nonlinear mapping capability, and can improve the estimation precision and generalization capability of the algorithm by training and optimizing a network structure, but the capability of coping with abnormal sampling data, battery aging and the like is still to be improved. Therefore, the Kalman filtering type algorithm based on data driving can be fused, the deep learning provides more time history data for the recursive filtering algorithm, and the Kalman filtering type algorithm can avoid the over fitting of the deep learning algorithm to certain abnormal values.
With the deepening of the intelligent degree of the power grid, the total capacity of the monitoring data is continuously enlarged, and powerful computing resources are needed to serve as technical support. Therefore, cloud computing technology is required to process and solve mass data in real time. However, battery SOC estimation places high demands on the inferred time delay. The transmission of data by using the Internet has certain delay and delay jitter, which can cause problems of overlarge bandwidth load of the cloud platform, poor system instantaneity, inaccurate delay model and the like.
Disclosure of Invention
The invention mainly aims to provide a random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation. The random forest and UKF are fused and calculated, so that the problem that the nonlinear mapping adjustment capability of a Kalman filtering algorithm on a battery is limited is solved, and the problem that the sensor has a certain range of measurement errors or sporadic measurement outliers and can be directly transmitted to an SOC estimation result in a machine learning algorithm is solved. Meanwhile, by utilizing cloud edge cooperative technology, not only is the strong calculation force of cloud computing utilized, but also the real-time performance of the system is ensured, and the real-time, efficient and accurate estimation of the SOC of the lithium battery is realized.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a random forest-UKF lithium battery SOC estimation method based on cloud edge cooperation comprises the following steps:
s10, the cloud server acquires historical operation parameters of the battery in a normal charge and discharge state of the lithium battery, and takes the historical operation parameters as a sample data set;
s20, training a random forest estimation model at a cloud server through a cloud random forest algorithm, and establishing a nonlinear relation between the SOC and the characteristic quantity;
s30, inputting the feature quantity measurement value of the battery to be estimated into a random forest estimation model trained on a cloud server, calculating and outputting an SOC value estimated by the random forest, and transmitting the SOC value to an edge end;
s40, calculating by the edge end through a UKF algorithm, and obtaining a final SOC estimated value by using the received SOC estimated value of the random forest estimated model and the characteristic measurement value of the battery to be estimated.
The invention is further improved in that the historical operating parameters include: real-time battery voltage, current, temperature, and state of charge.
The invention is further improved in that the random forest estimation model building steps are as follows:
the sample data is divided into two parts: the training set D and the test set S are used for recording the sample capacity of the D as N and recording the attribute capacity of the sample in the D as M;
extracting a training set with a sample capacity of N from the training set D by utilizing a bootstrap resampling method, repeating K times to obtain K training sets, wherein each training set can generate a decision tree corresponding to the training set, so that K is the number of decision trees of a random forest;
generating corresponding CART decision trees by using K training sets;
each decision tree is trained until a termination condition is reached.
The invention is further improved in that the bootstrap resampling method is characterized in that: a sample may be put back, i.e. the resulting sample is repeatable.
The invention is further improved in that the training process of the CART decision tree is as follows:
for each split node, extracting M-dimensional attribute features from the M-dimensional attribute features without substitution, wherein M < M;
traversing the attributes and the values corresponding to the attributes, and calculating a minimum mean square value; that is, for the arbitrary division feature a, the corresponding arbitrary division point s is divided into the data sets D on both sides 1 And D 2 Find the D 1 And D 2 The mean square error of each set is minimum, and D is recorded simultaneously 1 And D 2 The expression of the feature and feature value dividing point corresponding to the minimum sum of mean square errors is:
wherein, c 1 For D 1 Of data setsSample output average value, c 2 For D 2 The samples of the dataset output a mean.
The invention is further improved in that the termination condition of the training decision tree is one of the following:
reaching the set tree depth;
fewer samples are present at the node than the minimum number of samples;
the minimum mean square error reaches a threshold.
The invention is further improved in that the state equation and the observation equation of the UKF algorithm are respectively as follows:
y(k)＝SOC R (k-1)+ω k
wherein I (k) is the current at time k, deltaT is the interval time, Q n For battery capacity, v k To process noise covariance ω k To observe noise covariance, SOC R (k-1) is the predicted value of SOC output by the random forest estimation model at the moment (k-1).
Random forest-UKF lithium battery SOC estimation device based on cloud limit cooperation for cloud server includes:
s51, an acquisition unit is used for acquiring historical operation parameters of the battery in a normal charge and discharge state of the lithium battery and a characteristic measurement value of the battery to be estimated;
s52, a training set determining unit is used for generating a sample data set;
s53, a model training unit is used for training a random forest estimation model by using a sample data set to obtain a random forest SOC estimation model;
s54, a cloud estimation unit, which is used for estimating an SOC value estimated by a random forest through a random forest estimation model by utilizing a characteristic measurement value of a battery to be estimated;
and S55, a transmitting unit used for transmitting the SOC value estimated by the random forest estimation model to the edge end.
Random forest-UKF lithium battery SOC estimation device based on cloud limit cooperation is used for the edge, includes:
s61, an acquisition unit is used for acquiring a characteristic measurement value of a battery to be estimated of the lithium battery;
s62, a receiving unit is used for receiving the SOC value estimated by the random forest estimation model issued by the cloud server;
s63, an edge end estimation unit is used for estimating and obtaining a final SOC estimation value through a UKF algorithm by utilizing the SOC value estimated by the random forest issued by the cloud server and the characteristic measurement value of the battery to be estimated.
Random forest-UKF lithium battery SOC estimation system based on cloud edge cooperation includes edge and cloud server:
the cloud server comprises a random forest-UKF lithium battery SOC estimation device based on cloud edge cooperation;
the edge end comprises the random forest-UKF lithium battery SOC estimation device based on cloud edge cooperation.
The invention has at least the following beneficial technical effects:
according to the random forest-UKF lithium battery SOC estimation method based on cloud edge cooperation, a random forest algorithm is fused with UKF filtering, so that the strong nonlinear fitting capacity of the random forest is utilized, and the influence of noise or other uncertain factors is reduced through UKF filtering, and a more accurate SOC estimation result is obtained.
The random forest-UKF lithium battery SOC estimation device based on cloud edge cooperation provided by the invention comprises two estimation devices which are respectively applied to a cloud server and an edge end. The random forest model training requires larger computing resources, so that the random forest model training is completed in an estimation device applied to a cloud server; the UKF filtering algorithm calculates in an estimation device applied to the edge end so as to reduce cloud edge data transmission and ensure estimation instantaneity.
According to the random forest-UKF lithium battery SOC estimation system based on cloud edge cooperation, a cloud edge cooperation technology is adopted, and a cloud server and an edge device are cooperatively matched, so that the problems of real-time processing and response of the edge application of the estimation system are solved, the bandwidth pressure of data communication between the cloud and the edge is reduced, and meanwhile, the cloud server provides strong calculation support for the estimation system.
Drawings
The accompanying drawings are included to provide a further understanding of 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, without limitation, the embodiments of the invention. In the drawings:
FIG. 1 is a schematic flow chart of a random forest-UKF lithium battery SOC estimation method based on cloud edge coordination;
fig. 2 is a schematic structural diagram of a random forest-UKF lithium battery SOC estimation device based on cloud edge cooperation;
FIG. 3 is a schematic structural diagram of another random forest-UKF lithium battery SOC estimation device based on cloud edge coordination provided by the invention;
fig. 4 is a schematic structural diagram of a random forest-UKF lithium battery SOC estimation system based on cloud edge cooperation.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
Examples
1. The present case is analyzed by taking the public data set of NASA (national aerospace agency), and lithium battery experimental data of number 29 in the public data set. The cloud server collects discharge data of the first group to the fifth group of lithium batteries, and the cloud server comprises: real-time battery voltage, current, temperature, and state of charge are used as sample data sets.
2. And building a prediction model through a cloud random forest algorithm. The discharge data of the first group to the fourth group of the lithium battery are used as training set D of the model, 721 groups of data are recorded as sample capacity N, and the sample capacity attribute M is 3. The fifth set of data was used as test set S for a total of 174 sets of data. The method of resampling by bootstrap is used in training set D to carry out replaceable sampling, the training set with sample capacity of N is extracted, 100 times of repetition are carried out, 100 training sets can be obtained, each training set can generate decision trees corresponding to the training sets, and therefore 100 is the number of decision trees of random forests. And training the CART decision tree by using the K training sets through a written program to obtain a random forest estimation model, and establishing a nonlinear relation between the SOC and the feature quantity.
3. And inputting the characteristic quantity data set of the test set S, namely the battery voltage, the battery current and the battery temperature, into a random forest estimation model trained on the cloud server, outputting an SOC value estimated by the random forest by the model, and transmitting the value to an edge.
4. The edge end receives the SOC estimation value of the random forest model and the characteristic quantity data set of the test set S, calculates to obtain a final SOC estimation value, and carries out SOC estimation through a UKF algorithm, wherein a state equation and an observation equation of the UKF algorithm are respectively as follows:
y(k)＝SOC R (k-1)+ω k
wherein I (k) is the current at time k, deltaT is the interval time, Q n For battery capacity, v k To process noise covariance ω k To observe noise covariance, SOC R (k-1) is the predicted value of SOC output by the random forest model at the moment (k-1).
While the invention has been described in detail in the foregoing general description and with reference to specific embodiments thereof, it will be apparent to one skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (10)
1. The random forest-UKF lithium battery SOC estimation method based on cloud edge cooperation is characterized by comprising the following steps of:
s10, the cloud server acquires historical operation parameters of the battery in a normal charge and discharge state of the lithium battery, and takes the historical operation parameters as a sample data set;
s20, training a random forest estimation model at a cloud server through a cloud random forest algorithm, and establishing a nonlinear relation between the SOC and the characteristic quantity;
s30, inputting the feature quantity measurement value of the battery to be estimated into a random forest estimation model trained on a cloud server, calculating and outputting an SOC value estimated by the random forest, and transmitting the SOC value to an edge end;
s40, calculating by the edge end through a UKF algorithm, and obtaining a final SOC estimated value by using the received SOC estimated value of the random forest estimated model and the characteristic measurement value of the battery to be estimated.
2. The cloud edge synergy-based random forest-UKF lithium battery SOC estimation method of claim 1, wherein the historical operating parameters comprise: real-time battery voltage, current, temperature, and state of charge.
3. The cloud edge collaboration-based random forest-UKF lithium battery SOC estimation method of claim 1, wherein the random forest estimation model building step comprises the following steps:
the sample data is divided into two parts: the training set D and the test set S are used for recording the sample capacity of the D as N and recording the attribute capacity of the sample in the D as M;
extracting a training set with a sample capacity of N from the training set D by utilizing a bootstrap resampling method, repeating K times to obtain K training sets, wherein each training set can generate a decision tree corresponding to the training set, so that K is the number of decision trees of a random forest;
generating corresponding CART decision trees by using K training sets;
each decision tree is trained until a termination condition is reached.
4. The random forest-UKF lithium battery SOC estimation method based on cloud edge co-operation according to claim 3, wherein the bootstrap resampling method is characterized in that: a sample may be put back, i.e. the resulting sample is repeatable.
5. The cloud edge collaboration-based random forest-UKF lithium battery SOC estimation method of claim 3, wherein the training process of the CART decision tree is as follows:
for each split node, extracting M-dimensional attribute features from the M-dimensional attribute features without substitution, wherein M < M;
traversing the attributes and the values corresponding to the attributes, and calculating a minimum mean square value; that is, for the arbitrary division feature a, the corresponding arbitrary division point s is divided into the data sets D on both sides 1 And D 2 Find the D 1 And D 2 The mean square error of each set is minimum, and D is recorded simultaneously 1 And D 2 The expression of the feature and feature value dividing point corresponding to the minimum sum of mean square errors is:
wherein, c 1 For D 1 Sample output mean value of dataset, c 2 For D 2 The samples of the dataset output a mean.
6. The cloud edge synergy-based random forest-UKF lithium battery SOC estimation method of claim 3, wherein the termination condition of the training decision tree is one of the following:
reaching the set tree depth;
fewer samples are present at the node than the minimum number of samples;
the minimum mean square error reaches a threshold.
7. The cloud edge synergy-based random forest-UKF lithium battery SOC estimation method of claim 1, wherein the state equation and the observation equation of the UKF algorithm are respectively as follows:
y(k)＝SOC R (k-1)+ω k
wherein I (k) is the current at time k, deltaT is the interval time, Q n For battery capacity, v k To process noise covariance ω k To observe noise covariance, SOC R (k-1) is the predicted value of SOC output by the random forest estimation model at the moment (k-1).
8. Random forest-UKF lithium battery SOC estimation device based on cloud limit cooperation, its characterized in that is used for high in the clouds server, includes:
s51, an acquisition unit is used for acquiring historical operation parameters of the battery in a normal charge and discharge state of the lithium battery and a characteristic measurement value of the battery to be estimated;
s52, a training set determining unit is used for generating a sample data set;
s53, a model training unit is used for training a random forest estimation model by using a sample data set to obtain a random forest SOC estimation model;
s54, a cloud estimation unit, which is used for estimating an SOC value estimated by a random forest through a random forest estimation model by utilizing a characteristic measurement value of a battery to be estimated;
and S55, a transmitting unit used for transmitting the SOC value estimated by the random forest estimation model to the edge end.
9. Random forest-UKF lithium battery SOC estimation device based on cloud limit cooperation, its characterized in that is used for the marginal end, includes:
s61, an acquisition unit is used for acquiring a characteristic measurement value of a battery to be estimated of the lithium battery;
s62, a receiving unit is used for receiving the SOC value estimated by the random forest estimation model issued by the cloud server;
s63, an edge end estimation unit is used for estimating and obtaining a final SOC estimation value through a UKF algorithm by utilizing the SOC value estimated by the random forest issued by the cloud server and the characteristic measurement value of the battery to be estimated.
10. Random forest-UKF lithium battery SOC estimation system based on cloud edge cooperation, which is characterized by comprising an edge end and a cloud server:
the cloud server comprises the random forest-UKF lithium battery SOC estimation device based on cloud edge coordination of claim 8;
the edge comprises the random forest-UKF lithium battery SOC estimation device based on cloud edge coordination as claimed in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310616982.6A CN116626515A (en) | 2023-05-29 | 2023-05-29 | Random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310616982.6A CN116626515A (en) | 2023-05-29 | 2023-05-29 | Random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116626515A true CN116626515A (en) | 2023-08-22 |
Family
ID=87641341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310616982.6A Pending CN116626515A (en) | 2023-05-29 | 2023-05-29 | Random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116626515A (en) |
-
2023
- 2023-05-29 CN CN202310616982.6A patent/CN116626515A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022151819A1 (en) | Clustering analysis-based battery system online fault diagnosis method and system | |
| CN107957562B (en) | Online prediction method for residual life of lithium ion battery | |
| CN112331941B (en) | Cloud auxiliary battery management system and method | |
| CN107918103B (en) | Lithium ion battery residual life prediction method based on gray particle filtering | |
| CN109543317B (en) | Method and device for predicting remaining service life of PEMFC | |
| CN108832619A (en) | Transient stability evaluation in power system method based on convolutional neural networks | |
| CN110658459B (en) | Lithium ion battery state of charge estimation method based on bidirectional cyclic neural network | |
| CN114252103B (en) | Fusion power station operation fault prediction method | |
| CN112881930A (en) | Energy storage battery health management prediction method and system based on Internet of things | |
| CN105223512A (en) | Based on the method for the dynamic rectification dump energy of battery behavior | |
| CN115114878A (en) | Method and device for online prediction of battery life of energy storage power station and storage medium | |
| CN112528472A (en) | Multi-innovation hybrid Kalman filtering and H-infinity filtering algorithm | |
| CN114123344A (en) | Power system inertia evaluation method and device based on adaptive recursive least squares | |
| CN113027658A (en) | Real-time state evaluation method for water turbine runner and application thereof | |
| CN111654392A (en) | Low-voltage distribution network topology identification method and system based on mutual information | |
| CN114280494A (en) | Lithium battery health state monitoring method and device based on cloud cooperation | |
| CN117289142B (en) | Method and device for detecting internal short circuit fault of lithium ion energy storage power station battery | |
| CN117129879B (en) | Threshold adjustment method and training method of battery state of health prediction model | |
| CN117074955A (en) | Cloud-end correction OCV-based lithium battery state joint estimation method | |
| CN114660461A (en) | Battery health state evaluation method and device, electronic equipment and storage medium | |
| CN116626515A (en) | Random forest-UKF lithium battery SOC estimation method, device and system based on cloud edge cooperation | |
| CN112649746A (en) | Charge state estimation method combining circuit equivalence and recursion iteration | |
| CN107918920A (en) | The output correlation analysis method of more photovoltaic plants | |
| CN115577750A (en) | Method, device and equipment for estimating system-level state of charge of energy storage power station | |
| CN115374829A (en) | Deep learning-based bearing fault diagnosis method and system |
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 |