CN112287967A - Electric vehicle battery secondary utilization safety detection and evaluation method - Google Patents
Electric vehicle battery secondary utilization safety detection and evaluation method Download PDFInfo
- Publication number
- CN112287967A CN112287967A CN202011003898.XA CN202011003898A CN112287967A CN 112287967 A CN112287967 A CN 112287967A CN 202011003898 A CN202011003898 A CN 202011003898A CN 112287967 A CN112287967 A CN 112287967A
- Authority
- CN
- China
- Prior art keywords
- voltage curve
- battery
- diagnosed
- relevant parameters
- secondary utilization
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a secondary utilization safety detection and evaluation method for batteries of electric vehicles, which comprises the steps of firstly establishing a lithium battery formation safety voltage curve, then extracting relevant parameters from the lithium battery formation safety voltage curve as reference characteristics, and carrying out model training and optimization on all parameters of the reference characteristics to obtain an SVM diagnosis model; when the diagnosed battery is detected, the diagnosed voltage curve of the old battery is detected, relevant parameters of the diagnosed voltage curve are extracted to serve as comparison characteristics, and the comparison characteristics are matched with an SVM diagnosis model in a calculation mode to obtain a diagnosis result. The invention can realize the detection of whether the old battery can be secondarily applied, can greatly improve the secondary utilization of the old battery in practice, is very environment-friendly and avoids waste.
Description
Technical Field
The invention belongs to the technical field of secondary utilization of batteries, and particularly relates to a method for detecting and evaluating secondary utilization safety of batteries of an electric vehicle.
Background
The main power source of the electric automobile is a battery, and the battery of many electric automobiles has the potential of recycling after being scrapped, and whether the old battery can be applied or not is not detected by a good powerful method at present.
The present invention has been made in view of this situation.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for detecting and evaluating the secondary utilization safety of an electric vehicle battery, and in order to solve the technical problems, the basic concept of the technical scheme adopted by the invention is as follows:
a method for detecting and evaluating secondary utilization safety of an electric vehicle battery comprises the steps of firstly establishing a lithium battery formation safety voltage curve, then extracting relevant parameters from the lithium battery formation safety voltage curve to serve as reference characteristics, and carrying out model training and optimization on all parameters of the reference characteristics to obtain an SVM diagnosis model; when the diagnosed battery is detected, the diagnosed voltage curve of the old battery is detected, relevant parameters of the diagnosed voltage curve are extracted to serve as comparison characteristics, and the comparison characteristics are matched with an SVM diagnosis model in a calculation mode to obtain a diagnosis result.
Preferably, the relevant parameters extracted from the lithium battery formation safety voltage curve comprise internal resistance, capacity and voltage, and the relevant parameters are calculated through an FCM fuzzy clustering algorithm.
After the technical scheme is adopted, compared with the prior art, the invention has the following beneficial effects.
The invention can realize the detection of whether the old battery can be secondarily applied, can greatly improve the secondary utilization of the old battery in practice, is very environment-friendly and avoids waste.
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention to its proper form. It is obvious that the drawings in the following description are only some embodiments, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 is a three-dimensional vector model based on static indicators;
FIG. 2 is a graph showing the results of the consistency test;
FIG. 3 is a model diagram of cell electrochemistry P2D;
FIG. 4 is a graph showing the results of the experiment at 25 ℃;
FIG. 5 is a diagram of an internal short circuit model;
FIG. 6 is a schematic flow chart of the present invention.
It should be noted that the drawings and the description are not intended to limit the scope of the inventive concept in any way, but to illustrate it by a person skilled in the art with reference to specific embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and the following embodiments are used for illustrating the present invention and are not intended to limit the scope of the present invention.
Three-dimensional vector model consistency detection based on static indexes
As shown in fig. 1, a three-dimensional coordinate system is established by using internal resistance, capacity and voltage as indexes, and a space vector from an average point to a farthest point is used as a sphere radius. The degree of consistency of the thought based on "mean-difference" is uniquely determined by the sphere volume.
Consistency detection based on dynamic state indicators
The consistency detection algorithm based on FCM (fuzzy C-means clustering) is as follows:
and T (i) represents the membership degree of the digital signal i to the fuzzy set T in the battery charging and discharging curve.
Where i represents the digital signal form of the acquired voltage curve.
To achieve a comparison of the similarity of the two voltage profiles, the arrays { ai }, { bi } and ai-bi, i ═ 1,2,. n are obtained.
Si=1-max(ci) Axle of similarity
The results of the consistency test are shown in FIG. 2:
the similarity threshold u is 0.7, 0.8 and 0.9 respectively
Internal short circuit
The electrochemical process in the internal short circuit adopts the most classical physical ion battery electrochemical P2D model established by J.Newman. Meanwhile, the process of internal short circuit of the lithium ion battery is simulated by assuming equivalent short circuit internal resistance, as shown in fig. 3.
The simulation results of the P2D model fit well regardless of whether charging or discharging
The results of the experiment at 25 ℃ are shown in FIG. 4.
Establishing an internal short circuit model
Assuming that an internal short circuit occurs at the center of the lithium ion battery, and the internal short circuit area is a cylinder with a radius of 0.5mm and a height of 2mm, an internal short circuit model is established as shown in fig. 5,
the severity of the short circuit is simulated by varying the different sizes of Rshort.
The equivalent resistance value of the internal short circuit is Rs, and the internal short circuit current is calculated through ohm's law.
And simulating by using the established internal short circuit model, researching the normal charge-discharge characteristics of the lithium ion battery and the charge-discharge characteristics under the condition of the internal short circuit, and detecting the internal short circuit. When an internal micro short circuit exists in the lithium ion battery, a charging voltage curve of the lithium ion battery can have a rapid descending process, namely, the instantaneous voltage rapidly descends.
SVM-based internal short circuit detection algorithm
Data processing-extracting relevant features
The voltage curve is cut into 8 sections, and the voltage of each section is selected from 6 large influence factors, namely the maximum value, the median, the difference between the maximum value and the median, the mean value, the voltage value change in unit time and the variance. At this time, the corresponding eigenvector of each voltage curve will have 48 pieces of characteristic information. The combination will result in a feature vector of dimension 48.
Feature vector calculation
Assuming that P represents the charging voltage curve and T represents the time span of P, the time periods arePV represents generated specific PVk,k+1={(p,t)t∈[(k-1)*t,k*t],(p,t)∈p k=1,2,3...,7}
pk5=Nk k=1,2,3,...,8
pk6=Pk1-pk4 k=1,2,3,...,8
And (5) sign vectors.
Nonlinear support vector machine learning algorithm
Inputting: training data set T { (x)1,y1),(x2,y2),...,(xn,yn) In which xi∈R,yi={+1,-1},i=1,2....,N
And (3) outputting: separating hyperplane and classification decision function
(1) Selecting proper kernel function k (x, z) and penalty parameter C > 0
0≤αi≤C,i=1,2,...,N
Kernel function selection and parameter optimization
Sigmoid kernel function: k (x, z) ═ tanh [ a (x · z) + c ]
polynomial kernel function: k (x, z) ═ x · z) +1]d
(2) Computing
(3) Classification decision function
(4) Selecting a kernel function-Gaussian kernel function
(5) The obtained SVM is a Gaussian radial basis function classifier with a classification decision function of
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (2)
1. A method for detecting and evaluating secondary utilization safety of an electric vehicle battery is characterized by comprising the following steps: firstly, establishing a lithium battery formation safety voltage curve, extracting relevant parameters from the lithium battery formation safety voltage curve as reference characteristics, and performing model training and optimization on each parameter of the reference characteristics to obtain an SVM diagnostic model; when the diagnosed battery is detected, the diagnosed voltage curve of the old battery is detected, relevant parameters of the diagnosed voltage curve are extracted to serve as comparison characteristics, and the comparison characteristics are matched with an SVM diagnosis model in a calculation mode to obtain a diagnosis result.
2. The method as claimed in claim 1, wherein the relevant parameters extracted from the lithium battery formation safety voltage curve include internal resistance, capacity and voltage, and the relevant parameters are calculated by an FCM fuzzy clustering algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011003898.XA CN112287967A (en) | 2020-09-22 | 2020-09-22 | Electric vehicle battery secondary utilization safety detection and evaluation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011003898.XA CN112287967A (en) | 2020-09-22 | 2020-09-22 | Electric vehicle battery secondary utilization safety detection and evaluation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112287967A true CN112287967A (en) | 2021-01-29 |
Family
ID=74421950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011003898.XA Pending CN112287967A (en) | 2020-09-22 | 2020-09-22 | Electric vehicle battery secondary utilization safety detection and evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112287967A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115880565A (en) * | 2022-12-06 | 2023-03-31 | 江苏凤火数字科技有限公司 | Neural network-based scraped vehicle identification method and system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104597405A (en) * | 2014-12-22 | 2015-05-06 | 余姚亿威电子科技有限公司 | Method for detecting electric quantity of lithium ion battery for electric vehicle |
-
2020
- 2020-09-22 CN CN202011003898.XA patent/CN112287967A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104597405A (en) * | 2014-12-22 | 2015-05-06 | 余姚亿威电子科技有限公司 | Method for detecting electric quantity of lithium ion battery for electric vehicle |
Non-Patent Citations (1)
Title |
---|
李小龙: "一种电动汽车电池二次利用安全性检测评估方法", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115880565A (en) * | 2022-12-06 | 2023-03-31 | 江苏凤火数字科技有限公司 | Neural network-based scraped vehicle identification method and system |
CN115880565B (en) * | 2022-12-06 | 2023-09-05 | 江苏凤火数字科技有限公司 | Neural network-based scraped vehicle identification method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Feng et al. | Propagation mechanisms and diagnosis of parameter inconsistency within Li-Ion battery packs | |
Li et al. | Battery fault diagnosis for electric vehicles based on voltage abnormality by combining the long short-term memory neural network and the equivalent circuit model | |
CN110045298B (en) | Method for diagnosing parameter inconsistency of power battery pack | |
CN111398837A (en) | Vehicle battery health state estimation method based on data driving | |
CN110568360B (en) | Lithium battery aging diagnosis method based on fuzzy logic algorithm | |
CN104809722A (en) | Electrical device fault diagnosis method based on infrared thermography | |
CN107741568A (en) | A kind of lithium battery SOC estimation method that optimization RBF neural is shifted based on state | |
CN115859058B (en) | UPS fault prediction method and system based on width learning network | |
CN111257753B (en) | Battery system fault diagnosis method | |
CN108303649A (en) | A kind of cell health state recognition methods | |
CN112287967A (en) | Electric vehicle battery secondary utilization safety detection and evaluation method | |
CN113608140A (en) | Battery fault diagnosis method and system | |
CN115327403A (en) | Power battery safety evaluation method and device based on new energy automobile big data | |
Deng et al. | Fault diagnosis for electric vehicle lithium batteries using a multi-classification support vector machine | |
Lin et al. | Screening of retired batteries with gramian angular difference fields and ConvNeXt | |
CN117261599B (en) | Fault detection method and device of electric automobile, electronic equipment and electric automobile | |
Yao et al. | An intelligent fault diagnosis method for lithium-ion battery pack based on empirical mode decomposition and convolutional neural network | |
CN117067921B (en) | Fault detection method of electric automobile and electric automobile | |
CN114290954A (en) | Battery consistency monitoring method and system based on differential pressure analysis and vehicle | |
EP4291908A1 (en) | Early fault detection method for a battery | |
Gotz et al. | Diagnosing failures in lithium-ion batteries with Machine Learning techniques | |
Xia et al. | External short circuit fault diagnosis based on supervised statistical learning | |
CN116243194A (en) | On-line prediction method for battery health state under mixed working condition | |
CN113884903B (en) | Battery fault diagnosis method based on multi-layer perceptron neural network | |
CN114398989A (en) | Integrated universal electric chassis multi-target cooperative 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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210129 |