CN111983465A - Electric vehicle charging safety protection method based on residual electric quantity estimation - Google Patents
Electric vehicle charging safety protection method based on residual electric quantity estimation Download PDFInfo
- Publication number
- CN111983465A CN111983465A CN202010855001.XA CN202010855001A CN111983465A CN 111983465 A CN111983465 A CN 111983465A CN 202010855001 A CN202010855001 A CN 202010855001A CN 111983465 A CN111983465 A CN 111983465A
- Authority
- CN
- China
- Prior art keywords
- adaboost
- safety protection
- predictor
- electric vehicle
- lssvm
- 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]
- G01R31/367—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]
- G01R31/371—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] with remote indication, e.g. on external chargers
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
Abstract
The invention relates to the technical field of electric vehicle charging safety management, in particular to an electric vehicle charging safety protection method based on residual electric quantity estimation. The invention provides a novel SOC estimation method for safety protection in the charging process of an electric automobile, and aims to establish an SOC estimation algorithm with higher accuracy on the charging pile side on the basis of a big data platform and form a synchronous process with SOC estimation in a BMS (battery management system), so that whether the SOC change process of an electric automobile end is normal or not is judged, and theoretical and method bases are provided for finding out abnormal SOC change in the charging process as soon as possible. The SOC estimation method designed by the method has the advantages of high accuracy, short training time and the like, and the proposed double-SOC safety protection process has the advantages of low scheme implementation difficulty, low cost, good protection effect and the like, and has wide application prospects in charging operation enterprises.
Description
Technical Field
The invention relates to the technical field of electric vehicle charging safety management, in particular to an electric vehicle charging safety protection method based on residual electric quantity estimation.
Background
Estimation of the remaining power of the power battery of the electric vehicle is an indicator that needs to be focused on in the charging process of the electric vehicle, and is generally referred to as soc (state of charge) for short. The SOC cannot be measured directly, and it is generated indirectly by a vehicle-mounted power Battery Management System (BMS) according to parameters that can be measured directly during charging, and through a specific estimation algorithm. The accuracy of SOC estimation is the core function of a power battery management system, and the accurate SOC estimation is an important prerequisite for ensuring the safe and reliable work of the electric automobile and provides necessary basis for the energy management and the safety management of the electric automobile. However, the SOC estimation work has been very challenging, and on one hand, the directly measurable parameters that can be used for SOC estimation are limited in number and have the characteristics of nonlinearity, strong coupling and strong time variation. On the other hand, the working environment of the power battery system is complex, the system faces a complex system formed by connecting a plurality of battery packs in series and in parallel, and simultaneously faces severe requirements of all working conditions (wide-rate charge and discharge) and all climates (the temperature range of minus 30-45 ℃). Therefore, research on a more accurate SOC estimation method is of great significance to safety management of electric vehicles, for example, overcharge of electric vehicles is a common charging safety accident caused by inaccurate estimation of the remaining energy.
At present, in the charging process of an electric automobile, people usually only pay attention to the change of the SOC in the BMS, the charging pile side passively receives a charging instruction of the BMS and strictly transmits energy to a power battery according to the voltage and current required by the instruction until the residual capacity meets the requirement of a specific threshold value, and then the charging pile stops the transmission process of the energy. Obviously, the charging pile itself does not undertake the estimation work of the SOC, but passively receives the charging requirement of the BMS all the way. In fact, most BMS adopt ampere-hour integration or improved ampere-hour integration methods for SOC estimation, and the two SOC estimation methods have the advantages of simple principle, easy implementation, small occupied calculation space, etc., but the disadvantages are not negligible, and the accuracy of the two proposed SOC estimation methods can greatly reduce the estimation performance along with the aging of the battery and the increase of environmental interference factors. If the performance reduction cannot be detected in time, a serious inaccurate SOC estimation result is generated, if the charging pile receives the inaccurate SOC value, the charging stops early if the charging pile is light, and the overcharging is generated if the charging pile receives the inaccurate SOC value, so that serious safety accidents such as battery ignition are caused.
In fact, the charging pile relies on a charging operation platform with powerful computing function and sufficient storage space, and a powerful implementation basis is provided for bearing a more comprehensive and advanced SOC algorithm. In order to get rid of the passive state of the charging pile in the energy output process, the SOC estimation module is designed on the charging pile operation platform side, a double SOC estimation process is established in the charging process, and evaluation indexes of double SOCs are designed to monitor the estimation accuracy of the BMS on the SOC and install double guarantees for the charging process.
Disclosure of Invention
In order to solve the above problem, a first aspect of the present invention provides a method for protecting charging safety of an electric vehicle based on remaining power estimation, including the following steps:
the method comprises the following steps: establishing an AdaBoost-LSSVM algorithm at a charging operation platform end;
step two: when the electric automobile starts to be charged, the AdaBoost-LSSVM algorithm is established in the step (1) of using the charging operation platform section, and the AdaBoost-LSSVM algorithm and the electric automobile battery management system calculate the residual electric quantity value at the same time tAnd calculateDistance L of1t:
Step three: if L is1tIf the content is (0, 5%), the content does not exceed the standard, and the charging can be continued; if L is1tIf not (0, 5%), the charging is stopped if the result exceeds the standard.
As a preferred technical scheme of the invention, the step one of establishing the AdaBoost-LSSVM algorithm comprises the following steps:
(1) inputting a data set: inputting a charging data set T of the electric automobile: t { (x)1,y1),···,(xi,yi),…,(xN,yN) Therein ofIs N charging process parameters;is an estimated residual magnitude;
(2) constructing an LSSVM predictor: setting M LSSVM predictors Pm(xi) M1, 2, M, learning from the data set to obtain each predictor Pm(xi) Four key parameters alpha ofm、bm、γm、σm;
(3) Calculating the normalized coefficient of the predictor: computing predictor Pm(xi) Prediction error rate e on data setmTo obtain a normalized coefficient cm;
(4) Calculating a linear combination of AdaBoost-LSSVM algorithm: for each predictor Pm(xi) The four final parameters alpha of the AdaBoost-LSSVM algorithm are obtained by summing the parametersfinal、bfinal、γfinal、σfinal:
(5) Outputting AdaBoost-LSSVM algorithm: the formula of the AdaBoost-LSSVM algorithm Y (x) is as follows:
as a preferred technical solution of the present invention, the constructing of the LSSVM predictor in step (2) includes the steps of:
2-1) setting initialization weight distribution D1:D1=(w11,w12,…,w1i,…,w1N) Wherein, in the step (A),
2-2) use of a weight distribution D for m-11Learning the data set to obtain a predictor P1(xi) Four key parameters of (1): alpha is alpha1、b1、γ1、σ1And weight distribution D2(ii) a By analogy, for M2, …, M, a weight distribution D is usedmLearning the data set to obtain a predictor Pm(xi) Four key parameters alpha ofm、bm、γm、σmAnd weight distribution Dm+1。
As a preferable technical solution of the present invention, the calculating of the normalized coefficient of the predictor in the step (3) includes:
3-1) calculating Pm(xi) Error prediction rate e on training data setm,emThe formula of (1) is:
3-2) design psi (x)i) The function discretizes the continuous error and sets the error threshold to 0.01, ψ (x)i) The formula is as follows:
3-3) to psi (x)i) Summing the results of the functions to obtain pm,pmThe formula is as follows:
3-4) calculating normalized coefficient c of predictorm;
3-5) updating the weight distribution Dm+1。
As a preferred technical solution of the present invention, the predictor normalizes the coefficient cmThe formula of (1) is:
as a preferred technical solution of the present invention, the weight distribution Dm+1The formula of (1) is: dm+1=(wm+1,1,wm+1,2,…,wm+1,i,…,wm+1,N) Wherein, in the step (A), Zmis a normalization coefficient for normalizing wm+1,i,
As a preferable technical scheme of the invention, in the step (4) of calculating the linear combination of the AdaBoost-LSSVM algorithm, alpha isfinalThe formula of (1) is:
as a preferable technical scheme of the invention, in the step (4) of calculating the linear combination of the AdaBoost-LSSVM algorithm, bfinalThe formula of (1) is:
as a preferable technical scheme of the invention, the step (4) calculates the linear combination of AdaBoost-LSSVM algorithm,γfinalThe formula of (1) is:
as a preferable technical scheme of the invention, in the step (4) of calculating the linear combination of the AdaBoost-LSSVM algorithm, sigma isfinalThe formula of (1) is:
compared with the prior art, the invention has the following beneficial effects:
(1) the invention provides a novel SOC estimation method which is used for safety protection in the charging process of an electric automobile. In the charging process of the electric automobile, the charging pile side lacks an effective supervision process for charging safety. On the basis of a big data platform, the SOC estimation method aims at establishing an SOC estimation algorithm with higher accuracy on the charging pile side, and forming a synchronous process with SOC estimation in the BMS, so that whether the SOC change process of the electric automobile end is normal or not is judged, and theoretical and method bases are provided for early finding of abnormal change of the SOC in the charging process.
(2) The technical scheme of the invention is to improve an LSSVM (least squares support vector machine) method by using an AdaBoost algorithm and use the LSSVM method for SOC estimation. The designed SOC estimation algorithm is used in a charging pile operation platform, and the specific scheme is as follows: the early charging process data of the power battery of the electric vehicle is used as training data of an algorithm (generally, the early SOC estimation accuracy of the BMS is high), and after the algorithm is trained, a mature SOC estimation model is obtained and is used as an SOC health detector in the charging process of the electric vehicle. In this case, a double SOC estimation process is established during charging of the electric vehicle by calculating L of two process quantities1tAnd the distance is used for evaluating the good condition of SOC estimation in the BMS.
(3) The SOC estimation method designed by the method has the advantages of high accuracy, short training time and the like, and the proposed double-SOC safety protection process has the advantages of low scheme implementation difficulty, low cost, good protection effect and the like, and has wide application prospects in charging operation enterprises.
Drawings
Fig. 1 is a flowchart of the electric vehicle charging safety protection method based on the remaining power estimation.
Fig. 2 is a flowchart for establishing an AdaBoost-LSSVM algorithm at a charging operation platform end.
Detailed Description
The disclosure may be understood more readily by reference to the following detailed description of preferred embodiments of the invention and the examples included therein. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. In case of conflict, the present specification, including definitions, will control.
When a parameter is expressed as a range, preferred range, or as a range defined by a list of upper preferable values and lower preferable values, this is to be understood as specifically disclosing all ranges formed from any pair of any upper range limit or preferred value and any lower range limit or preferred value, regardless of whether ranges are separately disclosed. For example, when a range of "1 to 5" is disclosed, the described range should be interpreted to include the ranges "1 to 4", "1 to 3", "1 to 2 and 4 to 5", "1 to 3 and 5", and the like. When a range of values is described herein, unless otherwise stated, the range is intended to include the endpoints thereof and all integers and fractions within the range.
The singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise. "optional" or "any" means that the subsequently described event or events may or may not occur, and that the description includes instances where the event occurs and instances where it does not.
Approximating language, as used herein throughout the specification and claims, is intended to modify a quantity, such that the invention is not limited to the specific quantity, but includes portions that are literally received for modification without substantial change in the basic function to which the invention is related. Accordingly, the use of "about" to modify a numerical value means that the invention is not limited to the precise value. In some instances, the approximating language may correspond to the precision of an instrument for measuring the value. In the present description and claims, range limitations may be combined and/or interchanged, including all sub-ranges contained therein if not otherwise stated.
In addition, the indefinite articles "a" and "an" preceding an element or component of the invention are not intended to limit the number requirement (i.e., the number of occurrences) of the element or component. Thus, "a" or "an" should be read to include one or at least one, and the singular form of an element or component also includes the plural unless the stated number clearly indicates that the singular form is intended.
The present invention is illustrated by the following specific embodiments, but is not limited to the specific examples given below.
As shown in fig. 1, a first aspect of the present invention provides a method for protecting charging safety of an electric vehicle based on remaining power estimation, including the following steps:
the method comprises the following steps: establishing an AdaBoost-LSSVM algorithm at a charging operation platform end;
step two: when the electric automobile starts to be charged, the AdaBoost-LSSVM algorithm is established in the step (1) of using the charging operation platform section, and the AdaBoost-LSSVM algorithm and the electric automobile battery management system calculate the residual electric quantity value at the same time tAnd calculateDistance L of1t:
Step three: if L is1tIf the content is (0, 5%), the content does not exceed the standard, and the charging can be continued; if L is1tIf not (0, 5%), the charging is stopped if the result exceeds the standard.
In a preferred embodiment, as shown in fig. 2, the first step of establishing the AdaBoost-LSSVM algorithm of the present invention comprises the following steps:
(1) inputting a data set: inputting a charging data set T of the electric automobile: t { (x)1,y1),···,(xi,yi),…,(xN,yN) Therein ofIs N charging process parameters;is an estimated residual magnitude;
(2) constructing an LSSVM predictor: setting M LSSVM predictors Pm(xi) M1, 2, M, learning from the data set to obtain each predictor Pm(xi) Four key parameters alpha ofm、bm、γm、σm;
(3) Calculating the normalized coefficient of the predictor: computing predictor Pm(xi) Prediction error rate e on data setmTo obtain a normalized coefficient cm;
(4) Calculating a linear combination of AdaBoost-LSSVM algorithm: for each predictor Pm(xi) The four final parameters alpha of the AdaBoost-LSSVM algorithm are obtained by summing the parametersfinal、bfinal、γfinal、σfinal:
(5) Outputting AdaBoost-LSSVM algorithm: the formula of the AdaBoost-LSSVM algorithm Y (x) is as follows:
the data set input by the invention is charging data of the battery in the early use stage, which is regarded as healthier data, wherein the data set T comprisesParameter x of the charging processiThe matrix formed for the general performance parameters of the cell is well known in the art and may be enumerated by current, voltage, cell temperature, and the like.
LSSVM is a weak learning algorithm, and M predictors P are setm(xi). Each predictor Pm(xi) Is determined by four key parameters, respectively alpham、bm、γm、σmIn which α ism、bmDetermining the direction of the hyperplane, gamma, for the normal vector and displacement in the hyperplane functionmIs L2Regular coefficient, σmIs the width parameter of the gaussian kernel function.
In one embodiment, the step (2) of the present invention of constructing the LSSVM predictor comprises the following steps:
2-1) setting initialization weight distribution D1:D1=(w11,w12,…,w1i,…,w1N) Wherein, in the step (A),
2-2) use of a weight distribution D for m-11Learning the data set to obtain a predictor P1(xi) Four key parameters of (1): alpha is alpha1、b1、γ1、σ1And weight distribution D2(ii) a By analogy, for M2, …, M, a weight distribution D is usedmLearning the data set to obtain a predictor Pm(xi) Four key parameters alpha ofm、bm、γm、σmAnd weight distribution Dm+1。
In one embodiment, the step (3) of calculating the normalized coefficient of the predictor includes the following steps:
3-1) calculating Pm(xi) Error prediction rate e on training data setm,emThe formula of (1) is:
3-2) design psi (x)i) The function discretizes the continuous error and sets the error threshold to 0.01, ψ (x)i) The formula is as follows:
3-3) to psi (x)i) Summing the results of the functions to obtain pm,pmThe formula is as follows:
3-4) calculating normalized coefficient c of predictorm;
3-5) updating the weight distribution Dm+1。
Preferably, the predictor normalization coefficient c of the present inventionmThe formula of (1) is:
more preferably, the weight distribution D of the present inventionm+1The formula of (1) is: dm+1=(wm+1,1,wm+1,2,…,wm+1,i,…,wm+1,N) Wherein, in the step (A), Zmis a normalization coefficient for normalizing wm+1,i,
In one embodiment, the step (4) of calculating the linear combination of the AdaBoost-LSSVM algorithm, alpha, is performed byfinalThe formula of (1) is:
in one embodiment, in the step (4) of calculating the linear combination of the AdaBoost-LSSVM algorithm, bfinalThe formula of (1) is:
in one embodiment, step (4) of the present invention calculates γ in a linear combination of the AdaBoost-LSSVM algorithmfinalThe formula of (1) is:
in one embodiment, the step (4) of calculating the linear combination of the AdaBoost-LSSVM algorithm according to the invention is implemented by calculating the sigmafinalThe formula of (1) is:
the AdaBoost-LSSVM algorithm is established at the charging operation platform end, the electric vehicle battery management system carries out double SOC estimation, whether the charging process is in fault or not is judged according to the difference value of the AdaBoost-LSSVM algorithm and the electric vehicle battery management system, the accuracy and the reliability of SOC estimation are improved, and the faults in the charging process can be effectively reduced by the obtained safety protection method.
The foregoing examples are merely illustrative and serve to explain some of the features of the method of the present invention. The appended claims are intended to claim as broad a scope as is contemplated, and the examples presented herein are merely illustrative of selected implementations in accordance with all possible combinations of examples. Accordingly, it is applicants' intention that the appended claims are not to be limited by the choice of examples illustrating features of the invention. Also, where numerical ranges are used in the claims, subranges therein are included, and variations in these ranges are also to be construed as possible being covered by the appended claims.
Claims (10)
1. The electric vehicle charging safety protection method based on the residual electric quantity estimation is characterized by comprising the following steps of:
the method comprises the following steps: establishing an AdaBoost-LSSVM algorithm at a charging operation platform end;
step two: when the electric automobile starts to be charged, the AdaBoost-LSSVM algorithm is established in the step (1) of using the charging operation platform section, and the AdaBoost-LSSVM algorithm and the electric automobile battery management system calculate the residual electric quantity value at the same time tAnd calculateDistance L of1t:
Step three: if L is1tIf the content is (0, 5%), the content does not exceed the standard, and the charging can be continued; if L is1tIf not (0, 5%), the charging is stopped if the result exceeds the standard.
2. The electric vehicle charging safety protection method based on the residual capacity estimation is characterized in that the step one of establishing the AdaBoost-LSSVM algorithm comprises the following steps:
(1) inputting a data set: inputting a charging data set T of the electric automobile: t { (x)1,y1),···,(xi,yi),…,(xN,yN) Therein ofIs N charging process parameters;is an estimated residual magnitude;
(2) constructing an LSSVM predictor: setting M LSSVM predictors Pm(xi) M1, 2, M, learning from the data set to obtain each predictor Pm(xi) Four key parameters alpha ofm、bm、γm、σm;
(3) Calculating the normalized coefficient of the predictor: computing predictor Pm(xi) Prediction error rate e on data setmTo obtain a normalized coefficient cm;
(4) Calculating a linear combination of AdaBoost-LSSVM algorithm: for each predictor Pm(xi) The four final parameters alpha of the AdaBoost-LSSVM algorithm are obtained by summing the parametersfinal、bfinal、γfinal、σfinal:
(5) Outputting AdaBoost-LSSVM algorithm: the formula of the AdaBoost-LSSVM algorithm Y (x) is as follows:
3. the electric vehicle charging safety protection method based on the remaining power estimation as claimed in claim 2, wherein the step (2) of constructing the LSSVM predictor comprises the following steps:
2-1) setting initialization weight distribution D1:D1=(w11,w12,…,w1i,…,w1N) Wherein, in the step (A),
2-2) use of a weight distribution D for m-11Learning the data set to obtain a predictor P1(xi) Four key parameters of (1): alpha is alpha1、b1、γ1、σ1And weight distribution D2(ii) a By analogy, for M2, …, M, a weight distribution D is usedmLearning the data set to obtain a predictor Pm(xi) Four key parameters alpha ofm、bm、γm、σmAnd weight distribution Dm+1。
4. The electric vehicle charging safety protection method based on the remaining power estimation as claimed in claim 3, wherein the step (3) of calculating the normalized coefficient of the predictor comprises the following steps:
3-1) calculating Pm(xi) Error prediction rate e on training data setm,emThe formula of (1) is:
3-2) design psi (x)i) The function discretizes the continuous error and sets the error threshold to 0.01, ψ (x)i) The formula is as follows:
3-3) to psi (x)i) Summing the results of the functions to obtain pm,pmThe formula is as follows:
3-4) calculating normalized coefficient c of predictorm;
3-5) updating the weight distribution Dm+1。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010855001.XA CN111983465B (en) | 2020-08-24 | 2020-08-24 | Electric vehicle charging safety protection method based on residual electric quantity estimation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010855001.XA CN111983465B (en) | 2020-08-24 | 2020-08-24 | Electric vehicle charging safety protection method based on residual electric quantity estimation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111983465A true CN111983465A (en) | 2020-11-24 |
CN111983465B CN111983465B (en) | 2022-07-19 |
Family
ID=73443910
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010855001.XA Active CN111983465B (en) | 2020-08-24 | 2020-08-24 | Electric vehicle charging safety protection method based on residual electric quantity estimation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111983465B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112782588A (en) * | 2020-12-30 | 2021-05-11 | 深圳市加码能源科技有限公司 | SOC online monitoring method based on LSSVM and storage medium thereof |
CN112836174A (en) * | 2020-12-31 | 2021-05-25 | 深圳市加码能源科技有限公司 | AHP-based real-time charging safety evaluation method and storage medium |
CN113406500A (en) * | 2021-06-29 | 2021-09-17 | 同济大学 | Method for estimating residual electric quantity of power lithium battery |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105574231A (en) * | 2015-11-27 | 2016-05-11 | 上海交通大学 | Storage battery surplus capacity detection method |
CN106093783A (en) * | 2016-06-03 | 2016-11-09 | 哈尔滨工业大学 | The battery SOC method of estimation that Kalman filtering merges with data-driven |
CN106585396A (en) * | 2016-11-17 | 2017-04-26 | 上海理工大学 | Redundancy active monitoring electric automobile charging charger control method |
CN108712404A (en) * | 2018-05-04 | 2018-10-26 | 重庆邮电大学 | A kind of Internet of Things intrusion detection method based on machine learning |
CN109165819A (en) * | 2018-08-03 | 2019-01-08 | 国网山东省电力公司聊城供电公司 | A kind of active power distribution network reliability fast evaluation method based on improvement AdaBoost.M1-SVM |
CN111157899A (en) * | 2020-01-20 | 2020-05-15 | 南京邮电大学 | Method for estimating SOC of battery based on model fusion idea |
-
2020
- 2020-08-24 CN CN202010855001.XA patent/CN111983465B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105574231A (en) * | 2015-11-27 | 2016-05-11 | 上海交通大学 | Storage battery surplus capacity detection method |
CN106093783A (en) * | 2016-06-03 | 2016-11-09 | 哈尔滨工业大学 | The battery SOC method of estimation that Kalman filtering merges with data-driven |
CN106585396A (en) * | 2016-11-17 | 2017-04-26 | 上海理工大学 | Redundancy active monitoring electric automobile charging charger control method |
CN108712404A (en) * | 2018-05-04 | 2018-10-26 | 重庆邮电大学 | A kind of Internet of Things intrusion detection method based on machine learning |
CN109165819A (en) * | 2018-08-03 | 2019-01-08 | 国网山东省电力公司聊城供电公司 | A kind of active power distribution network reliability fast evaluation method based on improvement AdaBoost.M1-SVM |
CN111157899A (en) * | 2020-01-20 | 2020-05-15 | 南京邮电大学 | Method for estimating SOC of battery based on model fusion idea |
Non-Patent Citations (1)
Title |
---|
杜文莉 等: "The Time Series Soft-sensor Modeling based on Adaboost_LS-SVM", 《2010 8TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112782588A (en) * | 2020-12-30 | 2021-05-11 | 深圳市加码能源科技有限公司 | SOC online monitoring method based on LSSVM and storage medium thereof |
CN112782588B (en) * | 2020-12-30 | 2023-02-17 | 深圳市加码能源科技有限公司 | SOC online monitoring method based on LSSVM and storage medium thereof |
CN112836174A (en) * | 2020-12-31 | 2021-05-25 | 深圳市加码能源科技有限公司 | AHP-based real-time charging safety evaluation method and storage medium |
CN113406500A (en) * | 2021-06-29 | 2021-09-17 | 同济大学 | Method for estimating residual electric quantity of power lithium battery |
Also Published As
Publication number | Publication date |
---|---|
CN111983465B (en) | 2022-07-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111983465B (en) | Electric vehicle charging safety protection method based on residual electric quantity estimation | |
CN110208704B (en) | Lithium battery modeling method and system based on voltage hysteresis effect | |
Wang et al. | Power capability evaluation for lithium iron phosphate batteries based on multi-parameter constraints estimation | |
Wang et al. | Probability based remaining capacity estimation using data-driven and neural network model | |
CN102866361B (en) | A kind of electric battery SOH estimation on line method | |
US9411019B2 (en) | Method and system for estimating state of health of battery set | |
CN111679201B (en) | Method for detecting short circuit in power battery pack | |
WO2014054259A1 (en) | Device for estimating parameters of battery, and estimation method | |
CN106443459A (en) | Evaluation method of state of charge of vehicle lithium ion power battery | |
CN110148991B (en) | Big data-based battery overcharge early warning method and system | |
CN108089133A (en) | Energy-storage system consistency of battery pack detection method and detection device | |
CN110940921A (en) | Multi-fault diagnosis method and system of lithium ion battery string based on correction variance | |
Lee et al. | Enhanced coulomb counting method for SoC and SoH estimation based on coulombic efficiency | |
EP4148439A1 (en) | Battery state calculation method and calculation device, and storage medium | |
JP5803767B2 (en) | Secondary battery charge equivalent amount calculation device | |
CN104502853A (en) | Lithium battery SOC (Stress Optical Coefficient) estimation method based on EKF (Extended Kalman Filter) | |
CN107091994A (en) | Method and computer-readable recording medium for estimating battery SOC | |
CN108535653B (en) | Storage battery internal resistance estimation method and device | |
Lin et al. | State of health estimation of lithium-ion batteries based on remaining area capacity | |
CN103296324B (en) | Vehicle power battery pack charging method | |
CN107024666A (en) | device for estimating battery SOC | |
US20230324463A1 (en) | Method and Apparatus for Operating a System for Detecting an Anomaly of an Electrical Energy Store for a Device by Means of Machine Learning Methods | |
CN117031337A (en) | Method, device, storage medium and equipment for detecting short circuit in battery cell | |
Tang et al. | An aging-and load-insensitive method for quantitatively detecting the battery internal-short-circuit resistance | |
CN113884922B (en) | Battery internal short circuit quantitative diagnosis method based on voltage and electric quantity outlier coefficient |
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 |