CN111965562A - Method for predicting residual cycle life of lithium battery based on random forest model - Google Patents
Method for predicting residual cycle life of lithium battery based on random forest model Download PDFInfo
- Publication number
- CN111965562A CN111965562A CN202011123025.2A CN202011123025A CN111965562A CN 111965562 A CN111965562 A CN 111965562A CN 202011123025 A CN202011123025 A CN 202011123025A CN 111965562 A CN111965562 A CN 111965562A
- Authority
- CN
- China
- Prior art keywords
- model
- charging
- lithium battery
- random forest
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a method for predicting the residual cycle life of a lithium battery based on a random forest model, which comprises the steps of collecting actual operation data of the lithium battery in the operation process of an energy storage power station, cleaning, selecting proper characteristic data as input and output of the model, training and scoring the model by adopting a random forest regression big data model and a 5-fold cross validation method, and predicting the residual cycle life of the lithium battery of the energy storage power station according to the trained model. The method can predict the residual cycle life of the lithium battery of the energy storage power station, and meanwhile, the prediction accuracy is high.
Description
Technical Field
The invention relates to a method for predicting the residual cycle life of a lithium battery in an energy storage system based on a random forest model, and belongs to the technical field of electric power.
Background
The lithium battery is used as an important component of the operation of the energy storage power station, and the operation state of the lithium battery has important influence on the operation state of the energy storage power station. Along with the increase of energy storage power station operating time, the lithium cell is constantly carried out charge and discharge, and along with the increase of lithium cell charge-discharge number of times, the capacity of lithium cell will constantly decay. The deterioration of lithium cell is inefficacy for a long-term process, if can the life-span state of accurate prediction lithium cell, changes ageing lithium cell, to the normal work of guarantee lithium cell, maintains energy storage power station operating efficiency, reduces energy storage power station economic loss, and the emergence of prevention incident has the significance.
The method for predicting the cycle life of the lithium battery in the industry at present is mainly based on life prediction of a model, is mature, and depends on the combination of battery load conditions, material properties and a degradation mechanism and a battery failure mechanism to realize the prediction of the residual life, wherein the prediction comprises the degradation mechanism model, an equivalent circuit model, an experience degradation model and the like. However, these research methods are directed to lithium batteries in specific and fixed working condition use environments, and the use conditions and environments of lithium batteries in energy storage power stations have obvious differences compared with the above methods, and meanwhile, because the energy storage power stations continuously operate, the lithium batteries are arranged in groups and are numerous, the lithium batteries cannot be disassembled and individually tested one by one, so that the lithium battery operation data collected only in the energy storage process can be analyzed and predicted.
Disclosure of Invention
The purpose of the invention is as follows: in consideration of the fact that no feasible method for predicting the residual cycle life of the lithium battery in the aspect of energy storage exists at present, the invention provides a method for predicting the residual cycle life of the lithium battery based on a random forest model.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the technical scheme that:
a method for predicting the residual cycle life of a lithium battery based on a random forest model comprises the following steps:
step 1, data acquisition: and acquiring actual operation data of the lithium battery in the operation process of the energy storage power station as a data set.
Step 2, data cleaning: and (4) sorting and cleaning the collected data of the data set, removing invalid and abnormal data points, and reserving valid data points to obtain the cleaned data set.
Step 3, feature selection: and constructing characteristic data according to the original data, analyzing the correlation among the characteristic data, and selecting the characteristic data, wherein the characteristic data comprises the charge electric quantity, the charge duration, the charge multiplying power, the SOC range, the voltage range, the average voltage, the average temperature and the accumulated charge times.
And 4, selecting a model: selecting a random forest regression big data model, selecting the charging capacity of a lithium battery as model output, and selecting the charging time length, charging rate, SOC range, voltage range, average voltage, average temperature and accumulated charging times of the lithium battery as model input.
Step 5, model training and evaluation: training and scoring the model by adopting a 5-fold cross validation method according to the size of the cleaned data set, wherein the evaluation standard of the model adopts a determination coefficient R2And meanwhile, an ROC curve is made, and the difference between the predicted value and the actual value is visually observed.
Determining a coefficient:
wherein the content of the first and second substances,
is the value to be fitted, the mean value of which is
The fitting value is
，nIs the data set size.
And 6, outputting a model: and (5) storing the random forest regression big data model for later use according to the random forest regression big data model obtained in the step (5).
And 7, predicting the residual life: and predicting the residual cycle life of the lithium battery of the energy storage power station according to the random forest regression big data model obtained by training.
And step 71, taking the charging time length, the charging rate, the SOC range, the voltage range, the average voltage, the average temperature, the accumulated charging times, the voltage range, the temperature difference, the charging time length, the SOC range and the accumulated charging and discharging times of the lithium battery under the same conditions as independent variables.
And step 72, accumulating the charging and discharging times + 1.
And 73, substituting the independent variable as an input into the trained random forest regression big data model, and calculating the daily charging capacity of the lithium battery.
And step 74, outputting the accumulated charging times when the daily charging capacity of the lithium battery is less than 80% of the rated capacity. Otherwise, the process returns to step 72.
In step 75, the predicted remaining charge/discharge frequency = accumulated charge frequency output in step 74 — accumulated charge/discharge frequency in step 71.
Preferably: the 5-fold cross validation method was as follows:
and step 51, dividing the whole training set S into 5 disjoint subsets, wherein the number of training samples in the training set S is m, so that each subset has m/5 training samples, and the corresponding subset is called { S1, S2, …, S5 }.
And step 52, taking out one from the divided subsets each time as a test set, and taking the other 4 as training sets.
And 53, training a random forest regression big data model according to training.
Step 54, substituting the test set into the random forest regression big data model, and calculating a decision coefficient R2The value is obtained.
And step 55, calculating the average value of the decision coefficients obtained in 5 times to serve as the accuracy of the random forest regression big data model.
Preferably: the lithium battery takes a single-cluster battery as a basic unit.
Preferably: the method comprises the steps of collecting the SOC of a battery cluster of a single-cluster battery, the SOH of the battery cluster, the lowest temperature of the battery cluster, the highest temperature of the battery cluster, the average temperature of the battery cluster, the lowest voltage of the battery cluster, the highest voltage of the battery cluster, the average voltage of the battery cluster, the total voltage of the battery cluster, the daily charging electric quantity of the battery cluster, the daily discharging electric quantity of the battery cluster, the maximum allowable charging current of the battery cluster, the maximum allowable discharging current of the battery cluster, the state of the battery cluster, the current of the battery cluster and the.
Preferably: the data acquisition time interval is 5min, and the value is the latest value of the time interval.
Compared with the prior art, the invention has the following beneficial effects:
1. and predicting the residual cycle life of the lithium battery of the energy storage power station by adopting a big data prediction method.
2. The lithium battery of the energy storage power station has multiple data acquisition points, the acquired lithium battery has large operation data quantity, multiple types, long time span and simple and convenient data acquisition.
3. The acquired original data are subjected to data cleaning and feature extraction by adopting a scientific method, the correlation analysis among features can more visually see the correlation among the features, and important factors influencing the residual cycle life of the lithium battery are found out.
4. And a classical life prediction big data model is adopted, so that the model is mature, and the prediction accuracy is high.
5. By adopting the cross validation method, the accuracy of the prediction model is improved, and the situations of over-fitting and under-fitting are avoided. .
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention is further illustrated by the following description in conjunction with the accompanying drawings and the specific embodiments, it is to be understood that these examples are given solely for the purpose of illustration and are not intended as a definition of the limits of the invention, since various equivalent modifications will occur to those skilled in the art upon reading the present invention and fall within the limits of the appended claims.
As shown in FIG. 1, the invention designs a method for predicting the residual cycle life of a lithium battery based on a random forest model, which comprises the following steps:
1. data acquisition
The method comprises the steps of collecting original operation data of a lithium battery of an energy storage power station, wherein the lithium battery takes a single-cluster battery as a basic unit, and collects the SOC of the single-cluster battery, the SOH of the battery cluster, the lowest temperature of the battery cluster, the highest temperature of the battery cluster, the average temperature of the battery cluster, the lowest voltage of the battery cluster, the highest voltage of the battery cluster, the average voltage of the battery cluster, the total voltage of the battery cluster, the daily charging electric quantity of the battery cluster, the daily discharging electric quantity of the battery cluster, the maximum allowable charging current of the battery cluster, the maximum allowable discharging current of the battery cluster, the state of the battery cluster, the current of the battery cluster and the accumulated charging and discharging times of the battery.
2. Data cleansing
According to the method, the lithium battery in the full-discharge state is considered, so that the data which are not fully discharged and the abnormal values of sampling are deleted, the lithium battery operation data in the full-discharge state are reserved, meanwhile, the charging and discharging processes of the battery in the full-discharge state are considered to be similar, so that the charging time period data are continuously extracted for analysis, and finally, all data in the charging time period of the lithium battery in the full-discharge state are reserved.
3. Feature extraction
The method comprises the following steps of analyzing daily charging period data of a lithium battery of the energy storage power station, and extracting the following 9 pieces of daily original characteristic data, wherein the characteristic data are respectively as follows:
charging capacity: end-of-charge amount-start-of-charge amount
Charging time duration: end time of charging-start time of charging
Charging rate: charging current/rated capacity
SOC is extremely poor: end of Charge SOC-Start of Charge SOC
Voltage range is as follows: maximum voltage maximum-minimum voltage minimum
Average voltage: mean voltage mean value
Extremely poor temperature: maximum temperature maximum value-minimum temperature minimum value
Average temperature: mean average temperature
Accumulating the charging times: cumulative charge and discharge times of lithium battery
The method is characterized in that the charging capacity of the lithium battery is used as a dependent variable, other characteristic data are used as independent variables, the correlation between the other characteristic data and the charging capacity of the lithium battery is analyzed, no obvious correlation exists between a temperature range index and the charging capacity through correlation analysis, and the characteristic is not considered. And finally, selecting the charging electric quantity of the lithium battery as model output, and using the charging time length, the charging rate, the SOC range, the voltage range, the average voltage, the average temperature and the accumulated charging times of the lithium battery as model input.
4. Model selection
The method adopts a Random Forest regression model, Random Forest (Random Forest) is an algorithm based on a classification tree (classification tree), and the Random Forest model selected by the method explains the effect of independent variables (charging duration, charging multiplying power, SOC range, voltage range, average voltage, average temperature and accumulated charging and discharging times) on dependent variable charging capacity. Dependent variable Y charging quantity hasnThere are 7 independent variables associated with each observed value (dataset). When the classification tree is constructed, the random forest can randomly reselect from the original datanAnd selecting observation values for a plurality of times, and not selecting observation values for a plurality of times, which is a Bootstrap resampling method. Meanwhile, the random forest randomly selects partial variables from 7 independent variables to determine the classification tree nodes. Thus, the classification trees may be different each time they are built. Typically, a random forest randomly generates hundreds to thousands of classification trees, and then selects the most repetitive tree as the final result.
The random forest model has the following advantages:
1) due to the adoption of the integrated algorithm, the accuracy of the method is better than that of most single algorithms.
2) The method has good performance on a test set, and random forests are not easy to fall into overfitting due to the introduction of sample randomness and characteristic randomness, so that the method has certain anti-noise capability.
3) Due to the combination of trees, the random forest can process nonlinear data, and belongs to a nonlinear classification (fitting) model.
4) The method can process data with high dimensionality (much features), does not need to make feature selection, and has strong adaptability to a data set: the method can process both discrete data and continuous data, and a data set does not need to be normalized.
5) The training speed is fast, and the method can be applied to large-scale data sets.
6) In the training process, the mutual influence among the features can be detected, the importance of the features can be obtained, and certain reference significance is achieved.
The method adopts a random forest regression model in a sklern library in python, and sets related parameters as follows, wherein model subtrees n _ estimators =200, the maximum depth max _ depth =3 of the tree, the feature number max _ features = Auto, and the random value random _ state = 123.
5. Model training and evaluation
The method adopts a 5-fold cross validation method to train the data set, can effectively avoid the problem of model overfitting, and has the following basic principle of the 5-fold cross validation method:
1. the total training set S is divided into 5 disjoint subsets, each of which has m/5 training samples assuming that the number of training samples in S is m, and the corresponding subsets are called S1, S2, …, S5.
2. And taking out one from the divided subsets each time as a test set, and taking the other 4 as training sets.
3. And training a regression model according to the training.
4. Substituting the test set into the model, calculating the decision coefficient, and calculating the R2 value.
5. The average of the 5 determined coefficients was calculated as the accuracy of the model.
The model evaluation adopts a decision coefficient R2, the decision coefficient reflects the percentage of Y fluctuation which can be described by the fluctuation of X, namely the percentage of the variation of the characterization variable Y can be explained by the controlled independent variable X, the higher the fitting goodness is, the higher the interpretation degree of the independent variable on the dependent variable is, the higher the percentage of the variation caused by the independent variable on the total variation is, the closer the observation points are near the regression line is, and the value range is [0,1 ]. The calculation formula is as follows:
R2=SSR/SST=1-SSE/SST
wherein: SST = SSR + SSE, SST (total sum of squares) being the total sum of squares, SSR (regression sum of squares) being the regression sum of squares, SSE (error sum of squares) being the residual sum of squares.
Is provided with
Is the value to be fitted, the mean value of which is
The fitting value is
Recording:
total Square Sum (SST):
regression Sum of Squares (SSR):
sum of squares residual (SSE):
then there are: SST = SSR + SSE
Determining a coefficient:
6. life prediction
And according to the output model, making the residual cycle life of the battery cluster, and comprising the following steps:
61. inputting independent variables such as voltage range, temperature difference, charging time, SOC range, accumulated charging and discharging times and the like under the same condition.
62. The number of charging and discharging times is accumulated to + 1.
63. And substituting the independent variable as an input into the model, and calculating the daily charging capacity of the lithium battery by using the model.
64. And when the daily charging capacity of the lithium battery is less than 80% of the rated capacity, outputting the accumulated charging times. Otherwise, the procedure returns to step 62.
The predicted remaining charge/discharge number = cumulative charge number output in step 64 — cumulative charge/discharge number in step 61.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (5)
1. A method for predicting the residual cycle life of a lithium battery based on a random forest model is characterized by comprising the following steps:
step 1, data acquisition: acquiring actual operation data of a lithium battery in the operation process of an energy storage power station as a data set;
step 2, data cleaning: the collected data of the data set is sorted and cleaned, invalid and abnormal data points are removed, valid data points are reserved, and the cleaned data set is obtained;
step 3, feature selection: constructing characteristic data according to the original data, analyzing the correlation among the characteristic data, and selecting the characteristic data, wherein the characteristic data comprises charging electric quantity, charging duration, charging rate, SOC range, voltage range, average voltage, average temperature and accumulated charging times;
and 4, selecting a model: selecting a random forest regression big data model, selecting the charging capacity of a lithium battery as model output, and using the charging time length, charging rate, SOC range, voltage range, average voltage, average temperature and accumulated charging times of the lithium battery as model input;
step 5, model training and evaluation: according to the data after cleaningTraining and scoring the model by adopting a 5-fold cross validation method according to the size of the set, and adopting a decision coefficient R as a model evaluation standard2Meanwhile, an ROC curve is made, and the difference between a predicted value and an actual value is visually observed;
determining a coefficient:
wherein the content of the first and second substances,
is the value to be fitted, the mean value of which is
The fitting value is
，nIs the data set size;
and 6, outputting a model: according to the random forest regression big data model obtained in the step 5, storing the random forest regression big data model for later use;
and 7, predicting the residual life: predicting the residual cycle life of the lithium battery of the energy storage power station according to the random forest regression big data model obtained by training;
step 71, taking the charging time length, the charging rate, the SOC range, the voltage range, the average voltage, the average temperature, the accumulated charging times, the voltage range, the temperature difference, the charging time length, the SOC range and the accumulated charging and discharging times of the lithium battery under the same conditions as independent variables;
step 72, accumulating the charging and discharging times plus 1;
step 73, substituting the independent variable as an input into the trained random forest regression big data model, and calculating daily charging capacity of the lithium battery;
step 74, outputting the accumulated charging times when the daily charging capacity of the lithium battery is less than 80% of the rated capacity; otherwise, returning to step 72;
in step 75, the predicted remaining charge/discharge frequency = accumulated charge frequency output in step 74 — accumulated charge/discharge frequency in step 71.
2. The method for predicting the residual cycle life of the lithium battery based on the random forest model as recited in claim 1, wherein: the 5-fold cross validation method was as follows:
step 51, dividing the whole training set S into 5 disjoint subsets, wherein the number of training samples in the training set S is m, each subset has m/5 training samples, and the corresponding subset is called { S1, S2, …, S5 };
step 52, taking out one from the divided subsets each time as a test set, and taking the other 4 as training sets;
step 53, training a random forest regression big data model according to training;
step 54, substituting the test set into the random forest regression big data model, and calculating a decision coefficient R2A value;
and step 55, calculating the average value of the decision coefficients obtained in 5 times to serve as the accuracy of the random forest regression big data model.
3. The method for predicting the residual cycle life of the lithium battery based on the random forest model as recited in claim 2, wherein: the lithium battery takes a single-cluster battery as a basic unit.
4. The method for predicting the residual cycle life of the lithium battery based on the random forest model as recited in claim 3, wherein: the method comprises the steps of collecting the SOC of a battery cluster of a single-cluster battery, the SOH of the battery cluster, the lowest temperature of the battery cluster, the highest temperature of the battery cluster, the average temperature of the battery cluster, the lowest voltage of the battery cluster, the highest voltage of the battery cluster, the average voltage of the battery cluster, the total voltage of the battery cluster, the daily charging electric quantity of the battery cluster, the daily discharging electric quantity of the battery cluster, the maximum allowable charging current of the battery cluster, the maximum allowable discharging current of the battery cluster, the state of the battery cluster, the current of the battery cluster and the.
5. The method for predicting the residual cycle life of the lithium battery based on the random forest model as recited in claim 4, wherein: the data acquisition time interval is 5min, and the value is the latest value of the time interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011123025.2A CN111965562B (en) | 2020-10-20 | 2020-10-20 | Method for predicting residual cycle life of lithium battery based on random forest model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011123025.2A CN111965562B (en) | 2020-10-20 | 2020-10-20 | Method for predicting residual cycle life of lithium battery based on random forest model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111965562A true CN111965562A (en) | 2020-11-20 |
| CN111965562B CN111965562B (en) | 2020-12-29 |
Family
ID=73386963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011123025.2A Active CN111965562B (en) | 2020-10-20 | 2020-10-20 | Method for predicting residual cycle life of lithium battery based on random forest model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111965562B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112630665A (en) * | 2020-12-18 | 2021-04-09 | 北京理工大学 | Lithium battery life prediction system based on intelligent network connection |
| CN113095000A (en) * | 2021-06-08 | 2021-07-09 | 蜂巢能源科技有限公司 | Method and device for obtaining battery cell discharge capacity, storage medium and electronic equipment |
| CN113119796A (en) * | 2021-03-29 | 2021-07-16 | 上海交通大学 | Electric vehicle residual charging time prediction method and system based on cloud sparse charging data |
| CN113466713A (en) * | 2021-07-15 | 2021-10-01 | 北京工业大学 | Lithium battery safety degree estimation method and device based on random forest |
| CN113839107A (en) * | 2021-09-22 | 2021-12-24 | 北京航空航天大学 | Early warning method for soft package lithium ion battery diving degradation mode |
| CN114216558A (en) * | 2022-02-24 | 2022-03-22 | 西安因联信息科技有限公司 | Method and system for predicting remaining life of battery of wireless vibration sensor |
| CN114755586A (en) * | 2022-04-27 | 2022-07-15 | 电子科技大学 | Lithium ion battery residual life prediction method |
| CN115958957A (en) * | 2023-01-03 | 2023-04-14 | 重庆大学 | Method and system for predicting charging overheating fault of power battery of electric automobile |
| CN116774081A (en) * | 2021-12-12 | 2023-09-19 | 崔跃芹 | Rechargeable battery life prediction method and device adopting composite life index, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516813A (en) * | 2019-08-09 | 2019-11-29 | 常伟 | A method of batteries of electric automobile RDR prediction is carried out based on big data machine learning |
| CN110596594A (en) * | 2019-09-23 | 2019-12-20 | 广东毓秀科技有限公司 | Method for predicting SOE of rail-traffic lithium battery through big data |
| CN110775065A (en) * | 2019-11-11 | 2020-02-11 | 吉林大学 | Hybrid electric vehicle battery life prediction method based on working condition recognition |
| CN110888059A (en) * | 2019-12-03 | 2020-03-17 | 西安科技大学 | Algorithm based on improved random forest combined cubature Kalman power battery state of charge estimation |
| CN110988693A (en) * | 2019-10-25 | 2020-04-10 | 沃特威（广州）电子科技有限公司 | Chemical battery energy storage application analysis method based on modeling simulation |
-
2020
- 2020-10-20 CN CN202011123025.2A patent/CN111965562B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516813A (en) * | 2019-08-09 | 2019-11-29 | 常伟 | A method of batteries of electric automobile RDR prediction is carried out based on big data machine learning |
| CN110596594A (en) * | 2019-09-23 | 2019-12-20 | 广东毓秀科技有限公司 | Method for predicting SOE of rail-traffic lithium battery through big data |
| CN110988693A (en) * | 2019-10-25 | 2020-04-10 | 沃特威（广州）电子科技有限公司 | Chemical battery energy storage application analysis method based on modeling simulation |
| CN110775065A (en) * | 2019-11-11 | 2020-02-11 | 吉林大学 | Hybrid electric vehicle battery life prediction method based on working condition recognition |
| CN110888059A (en) * | 2019-12-03 | 2020-03-17 | 西安科技大学 | Algorithm based on improved random forest combined cubature Kalman power battery state of charge estimation |
Non-Patent Citations (3)
| Title |
|---|
| CHUANJIANG LI等: "The Lithium-ion Battery State-of-Charge Estimation using Random Forest Regression", 《2014 IEEE》 * |
| YI LI等: "Random forest regression for online capacity estimation of lithium-ion batteries", 《APPLIED ENERGY》 * |
| 韦振汉等: "基于随机森林的锂离子电池荷电状态估算", 《广西师范大学学报（自然科学版）》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112630665A (en) * | 2020-12-18 | 2021-04-09 | 北京理工大学 | Lithium battery life prediction system based on intelligent network connection |
| CN113119796A (en) * | 2021-03-29 | 2021-07-16 | 上海交通大学 | Electric vehicle residual charging time prediction method and system based on cloud sparse charging data |
| CN113119796B (en) * | 2021-03-29 | 2022-10-18 | 上海交通大学 | Electric vehicle residual charging time prediction method and system based on cloud sparse charging data |
| CN113095000A (en) * | 2021-06-08 | 2021-07-09 | 蜂巢能源科技有限公司 | Method and device for obtaining battery cell discharge capacity, storage medium and electronic equipment |
| CN113466713A (en) * | 2021-07-15 | 2021-10-01 | 北京工业大学 | Lithium battery safety degree estimation method and device based on random forest |
| CN113466713B (en) * | 2021-07-15 | 2024-04-12 | 北京工业大学 | Lithium battery safety degree estimation method and device based on random forest |
| CN113839107A (en) * | 2021-09-22 | 2021-12-24 | 北京航空航天大学 | Early warning method for soft package lithium ion battery diving degradation mode |
| CN116774081A (en) * | 2021-12-12 | 2023-09-19 | 崔跃芹 | Rechargeable battery life prediction method and device adopting composite life index, electronic equipment and readable storage medium |
| CN116774081B (en) * | 2021-12-12 | 2024-02-09 | 崔跃芹 | Rechargeable battery life prediction method and device adopting composite life index, electronic equipment and readable storage medium |
| CN114216558B (en) * | 2022-02-24 | 2022-06-14 | 西安因联信息科技有限公司 | Method and system for predicting remaining life of battery of wireless vibration sensor |
| CN114216558A (en) * | 2022-02-24 | 2022-03-22 | 西安因联信息科技有限公司 | Method and system for predicting remaining life of battery of wireless vibration sensor |
| CN114755586A (en) * | 2022-04-27 | 2022-07-15 | 电子科技大学 | Lithium ion battery residual life prediction method |
| CN115958957A (en) * | 2023-01-03 | 2023-04-14 | 重庆大学 | Method and system for predicting charging overheating fault of power battery of electric automobile |
| CN115958957B (en) * | 2023-01-03 | 2023-12-22 | 重庆大学 | Method and system for predicting charging overheat faults of power battery of electric automobile |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111965562B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111965562B (en) | Method for predicting residual cycle life of lithium battery based on random forest model | |
| CN112485689B (en) | Method for predicting residual cycle life of lithium battery in energy storage system based on Xgboost model | |
| CN112731159B (en) | Method for pre-judging and positioning battery faults of battery compartment of energy storage power station | |
| CN112255559B (en) | Lithium battery energy storage power station residual life prediction method based on multiple linear regression | |
| CN113866642A (en) | Lithium ion battery fault diagnosis method based on gradient lifting tree | |
| CN113030761B (en) | Method and system for evaluating battery health state of ultra-large-scale energy storage power station | |
| CN113109715A (en) | Battery health condition prediction method based on feature selection and support vector regression | |
| CN110609233A (en) | Method for predicting SOH of energy storage battery based on big data | |
| CN116401585B (en) | Energy storage battery failure risk assessment method based on big data | |
| CN115511013A (en) | Large-scale energy storage power station abnormal battery identification method, device and storage medium | |
| CN114720899A (en) | Retired battery echelon utilization and sorting method and system, electronic equipment and storage medium | |
| CN113765179A (en) | Cloud battery pack consistency analysis method based on hierarchical clustering and class center distance | |
| CN112765149A (en) | System and method for calculating capacity of energy storage system | |
| CN116660759A (en) | Battery life prediction method and device based on BMS battery management system | |
| Savargaonkar et al. | A cycle-based recurrent neural network for state-of-charge estimation of li-ion battery cells | |
| Sohn et al. | CNN-based Online Diagnosis of Knee-point in Li-ion Battery Capacity Fade Curve | |
| CN116298910A (en) | Battery safety control method and device | |
| CN116842464A (en) | Battery system SOC estimation method | |
| Lin et al. | Research on Inconsistency Identification of Lithium-ion Battery Pack Based on Operational Data | |
| Lee et al. | Anomaly detection of storage battery based on isolation forest and hyperparameter tuning | |
| Dian-Gang et al. | Anomaly behavior detection based on ensemble decision tree in power distribution network | |
| CN114740377A (en) | Rapid sorting method based on retired power batteries and storage medium | |
| Xu et al. | Prediction of Lithium-ion Battery Remaining Useful Life Based on Long Short Term Memory | |
| CN117706377B (en) | Battery inconsistency identification method and device based on self-adaptive clustering | |
| CN112464146B (en) | Key subsystem based on historical telemetering data and single-machine correlation health baseline construction method |
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: 20211125 Address after: 226100 No.888, Jiuhua Road, high tech Zone, Nantong City, Jiangsu Province Patentee after: Wotai Energy Co.,Ltd. Address before: 211100 West unit, 1st floor, building D, Jinzhi science and Technology Park, 100 Jiangjun Avenue, Jiangning District, Nanjing City, Jiangsu Province Patentee before: JIANGSU HUIZHI ENERGY ENGINEERING TECHNOLOGY INNOVATION RESEARCH INSTITUTE Co.,Ltd. |