CN113203954A - Battery fault diagnosis method based on time-frequency image processing - Google Patents
Battery fault diagnosis method based on time-frequency image processing Download PDFInfo
- Publication number
- CN113203954A CN113203954A CN202110453564.0A CN202110453564A CN113203954A CN 113203954 A CN113203954 A CN 113203954A CN 202110453564 A CN202110453564 A CN 202110453564A CN 113203954 A CN113203954 A CN 113203954A
- Authority
- CN
- China
- Prior art keywords
- battery
- time
- fault diagnosis
- frequency image
- image processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003745 diagnosis Methods 0.000 title claims abstract description 44
- 238000012545 processing Methods 0.000 title claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims description 8
- 238000012847 principal component analysis method Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 208000032953 Device battery issue Diseases 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 abstract description 3
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 7
- 229910001416 lithium ion Inorganic materials 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Secondary Cells (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The invention provides a battery fault diagnosis method based on time-frequency image processing, which comprises the following steps: collecting one-dimensional voltage data of a normal battery and a fault battery as an original data set; carrying out time-frequency processing on the acquired voltage data, and converting the voltage data into a two-dimensional time-frequency graph; performing graying processing on the two-dimensional time-frequency diagram, and calculating to obtain a gray level co-occurrence matrix; extracting a related feature set of the gray level co-occurrence matrix, and diagnosing and identifying image features by using a density-based clustering algorithm; thereby realizing battery failure diagnosis. The invention has the characteristics that after the one-dimensional voltage signal is converted into the two-dimensional time-frequency diagram, the battery fault information can be reflected, and the fault diagnosis has high accuracy and stability. The invention provides a method for detecting a single battery with high accuracy and less false alarm, which solves the problem that the single battery with the fault is difficult to diagnose effectively in the prior art.
Description
Technical Field
The invention belongs to the technical field of battery fault diagnosis, and particularly relates to a battery fault diagnosis method based on time-frequency image processing.
Background
The lithium ion battery has the advantages of long cycle life, high specific energy, low self-discharge rate and the like, so that the electric automobile taking the lithium ion battery as the power battery gradually becomes the mainstream direction of the future automobile development. However, thermal runaway ignition accidents caused by lithium ion battery failures occur, and the life safety of people is seriously threatened.
When the vehicle-mounted battery system is subjected to mechanical-electrical-thermal abuse to a certain degree in the actual operation process, the performance of the battery can be rapidly degraded, even battery failure can be caused and thermal runaway can be finally developed, so that serious safety accidents are caused. In order to avoid such situations, it is necessary to rapidly and accurately diagnose a fault occurring in the battery and perform a safety precaution, thereby improving the safety of the use of the battery.
At present, the lithium ion battery fault diagnosis technology is still a difficulty in the research of battery safety problems, and fault diagnosis methods are mainly divided into model-based fault diagnosis and data-driven fault diagnosis. Due to the real-time change of the battery operation condition and the high nonlinearity of the lithium ion battery, the establishment of a high-accuracy model is difficult. The fault diagnosis method based on data driving does not need to establish an accurate battery model, only needs to process battery data, diagnoses battery faults by setting a threshold value, is simple in processing method and low in accuracy, and is difficult to effectively diagnose a single battery with faults.
Disclosure of Invention
In view of the above, it is necessary to provide a more accurate method for diagnosing a faulty battery.
The invention provides a battery fault diagnosis method based on time-frequency image processing, which comprises the steps of collecting voltage data of each single battery in the using process of a lithium ion battery system in real time, and innovatively converting one-dimensional voltage data of each single battery into a two-dimensional time-frequency image; and then, analyzing a time-frequency image corresponding to each single battery based on a time-frequency image processing algorithm, extracting an image gray level co-occurrence matrix characteristic set, realizing the diagnosis of the single battery with the fault by using a density-based clustering algorithm, and improving the accuracy of the diagnosis of the fault battery. The invention adopts the following technical scheme:
a battery fault diagnosis method based on time-frequency image processing is characterized by comprising the following steps:
s1, collecting one-dimensional voltage data of the battery pack in the using process as an original data set, wherein the original data set comprises voltage data of normal single batteries and voltage data of fault single batteries;
s2, carrying out time-frequency processing on the acquired one-dimensional voltage data to obtain a two-dimensional time-frequency image of the battery;
s3, calculating the obtained time-frequency image to obtain a gray level co-occurrence matrix, and describing image texture distribution characteristics;
s4, selecting five feature sets of the gray level co-occurrence matrix, namely energy, contrast, entropy, correlation and inverse difference moment, and reducing dimensions by using a principal component analysis method to obtain a 2-dimensional fault feature set;
and S5, performing single battery fault diagnosis by using a density-based clustering algorithm.
In the above time-frequency image processing-based battery fault diagnosis method, in step S2, the acquired one-dimensional voltage data u (t) is subjected to time-frequency processing, and converted into a two-dimensional time-frequency image; wherein the time-frequency processing adopts wavelet transform:
wherein
Representing the mother wavelet, a being a scale factor, b being a translation factor, and C (a, b) being wavelet transform coefficients.
In the above method for diagnosing battery failure based on time-frequency image processing, in step S4, a gray level co-occurrence matrix p is obtained by calculation according to the formula:
p(i,j,α,β)＝{(m,n),(m+dm,n+dn)∈M*M,f(m,n)＝i,f(m+dm,n+dn)＝j} (2)
where M × M is the picture size, (M, n) is the reference point, (M + dm, n + dn) is the offset point, f (M, n) ═ i denotes that the gray-scale value of the reference point is i, f (M + dm, n + dn) ═ j denotes that the gray-scale value of the offset point is j, and α β denotes the offset value and the offset angle of the offset point, respectively.
In the above method for diagnosing battery failure based on time-frequency image processing, the energy POWER extracted in step S5 is, according to the formula:
in the above time-frequency image processing-based battery fault diagnosis method, the characteristic entropy value ENY extracted in step S5 is according to the formula:
in the above method for diagnosing battery failure based on time-frequency image processing, the characteristic contrast CON extracted in step S5 is, according to the formula:
in the above time-frequency image processing-based battery fault diagnosis method, the feature correlation DB extracted in step S5 is, according to the formula:
wherein,
in the above time-frequency image processing-based battery fault diagnosis method, the characteristic inverse difference moment DM extracted in step S5 reflects the uniformity of the image texture, and measures the local variation of the image texture; the larger the value, the less obvious the image texture varies between different regions, and the worse the local uniformity, according to the formula:
in the above battery fault diagnosis method based on time-frequency image processing, the principal component analysis method in step S5 mainly includes the following steps:
s5.1, the number of the batteries is N, each battery has 5 characteristic quantities, and an original matrix (X) is formedij)N*5Wherein X isijThe j characteristic value of the ith battery;
s5.2, carrying out standardization processing on the original matrix X to obtain a standardized matrix Y, namely:
wherein, YijRepresents the normalized value of the jth characteristic quantity of the ith battery,
is the average value of the ith cell characteristic, and Si is the standard deviation of the ith cell characteristic
S5.3, calculating a correlation coefficient matrix R of the matrix Y, namely:
s5.4, calculating the characteristic value lambda of the matrix RiAnd the feature vector eiAssuming that R has q non-negative eigenvalues, it is sorted in descending order, i.e.: lambda [ alpha ]1≥λ2≥…≥λq (10)
Then, a feature vector e corresponding to the feature value is obtainedi(i ═ 1,2 … q), and the norm of the eigenvector is 1;
s5.4, two principal components are extracted in the invention, so that the feature values are, the calculation expression of the principal components is as follows: z is YE (11)
Wherein E ═ E1,e2]And 2 orthonormal matrixes corresponding to the characteristic values in the front sequence.
In the above method for diagnosing battery failure based on time-frequency image processing, in step S6, the battery is diagnosed for failure by using density-based clustering, which means that the feature value of an abnormal battery is different from the domain density of a normal battery; the method has two core parameters R and MinrWhere R refers to the area of the fault signature within a given radius, MinrWhether the fault feature sample is a core object is determined, namely the number of sample points in the field of the sample R is more than or equal to MinrDetermining the object as a core object; the method comprises the steps that firstly, a sample point is selected randomly, all points in the radius range of the point R are found, if the number of data points with the distance within R is larger than that of the data points, the point is marked as a core sample and is marked as the core sample, a new cluster label is distributed, then an algorithm returns a set with connected densities, and all objects in the set are represented as the same cluster; otherwise, the outliers are marked.
Compared with the prior art, the method for diagnosing the single battery with the fault analyzes the voltage data acquired in the operation process of the battery pack, innovatively converts one-dimensional voltage data into a two-dimensional time-frequency image, and extracts related characteristic parameters from the image. By utilizing a time-frequency image processing algorithm and a density-based clustering algorithm, the detection and diagnosis of the single battery with the fault can be carried out in real time, the accuracy of the fault diagnosis of the single battery is improved, and the missing report rate is reduced. The battery fault diagnosis method provided by the invention has higher robustness.
Drawings
Fig. 1 is a diagnosis flow chart of a battery fault diagnosis method based on time-frequency image processing.
Detailed Description
The method for detecting a faulty cell provided by the present invention will be described in further detail below.
The invention provides a battery fault diagnosis method, which comprises the following specific steps:
s1, collecting voltage data in the battery charging process as an original data set, wherein the original data set comprises voltage data of a normal single battery and voltage data of a fault single battery;
s2, performing wavelet transformation time-frequency processing on the acquired one-dimensional voltage data to obtain a two-dimensional time-frequency image of the battery;
s2.1, recording the one-dimensional voltage data of the battery collected in the corresponding time window as u (t);
s2.2, performing continuous wavelet transformation on the voltage signal u (t) according to a formula (1) to obtain a two-dimensional time-frequency graph:
wherein
Representing the mother wavelet, a being a scale factor, b being a translation factor, and C (a, b) being wavelet transform coefficients.
And S3, calculating the obtained time-frequency image to obtain a gray level co-occurrence matrix, and describing the image texture distribution characteristics.
S4, selecting five feature sets of the gray level co-occurrence matrix, namely energy, contrast, entropy, correlation and inverse difference moment.
And S5, reducing the dimension of the 5-dimensional feature quantity into 2 dimensions by using a principal component analysis method.
S6, performing single battery fault diagnosis by using a density-based clustering algorithm;
in step S1, the battery type of the battery pack is not limited to a certain type, and in this embodiment, a lithium ion battery is detected. The battery pack comprises N single batteries which are numbered 1,2 and 3 … N in sequence, wherein N is an integer greater than 1.
In step S1, N in the provided battery pack is collected respectivelyCharging voltage u of single batteryi(t), wherein i represents any one of the N unit cells.
In step S3, a gray level co-occurrence matrix is calculated, and if the size of the time-frequency diagram is M × M, the elements in the gray level co-occurrence matrix p are:
p(i,j,α,β)＝{(m,n),(m+dm,n+dn)∈M*M,f(m,n)＝i,f(m+dm,n+dn)＝j} (2)
where, (m, n) is a reference point, (m + dm, n + dn) is an offset point, where f (m, n) ═ i denotes that the grayscale value of the reference point is i, f (m + dm, n + dn) ═ j denotes that the grayscale value of the offset point is j, and α β denotes the offset value and the offset angle of the offset point, respectively.
In step S4, the energy POWER represents the uniformity and texture thickness of the gray scale distribution of the image, and the formula is:
in step S4, the contrast CON indicates the degree of image sharpness and texture depth. According to the formula:
in step S4, the entropy value ENY represents the complexity of the image texture. According to the formula:
in step S4, the correlation DB is a parameter for measuring the similarity in the row or column direction of the elements in the gray level co-occurrence matrix, and is according to the formula:
wherein,
in step S4, the inverse difference moment DM reflects the uniformity of the image texture, and measures the local variation of the image texture. The larger the value, the less obvious the image texture varies between different regions, and the worse the local uniformity, according to the formula:
the principal component analysis method in step S5 mainly includes the steps of:
s5.1, the number of the batteries is N, each battery has 5 characteristic quantities, and an original matrix (X) is formedij)N*ΩWherein X isijIs the j characteristic value of the i battery.
S5.2, carrying out standardization processing on the original matrix X to obtain a standardized matrix Y, namely:
wherein, YijRepresents the normalized value of the jth characteristic quantity of the ith battery,
is the average of the i-th cell characteristic, SiIs the standard deviation of the ith cell characteristic.
S5.3, calculating a correlation coefficient matrix R of the matrix Y, namely:
s5.4, calculating the characteristic value lambda of the matrix RiAnd the feature vector eiAssuming that R has q non-negative eigenvalues, it is sorted in descending order:
λ1≥λ2≥…≥λq (10)
then, a feature vector e corresponding to the feature value is obtainedi(i ═ 1,2 … q), and the norm of the eigenvector is 1.
S5.4 in the invention, two main components are extracted, so that the characteristic value is lambda1,λ2Then, the calculation expression of the principal component is:
Z＝YE (11)
wherein E ═ E1,e2]Is the orthonormal matrix corresponding to the prior eigenvalue. In the invention, two main components are extracted.
Step S6 is to perform failure diagnosis on the battery using density-based clustering, in which the feature value of the abnormal battery is different from the domain density of the normal battery. The method has two core parameters R and MinrWhere R refers to the area of the subject within a given radius, MinrIs to determine whether the object is a core object, i.e. the number of sample points in the field of object R is greater than or equal to MinrThen the object is determined to be a core object. First, arbitrarily selecting any sample point, finding all points in the radius range of the point R, if the number of data points within the distance R is more than MinrThen this point is marked as a core sample, and assigned a new cluster label, and then the algorithm returns a densely connected set, representing all objects in this set as the same cluster. Otherwise, the outliers are marked.
Compared with the prior art, the fault single battery diagnosis method provided by the invention analyzes the voltage data acquired in the operation process of the battery pack, innovatively converts one-dimensional voltage signals into two-dimensional time-frequency images by using a wavelet analysis method, can detect and diagnose the fault single battery in real time by using a time-frequency image processing algorithm and a density-based clustering algorithm, improves the fault diagnosis accuracy of the single battery, and reduces the missing report rate.
In addition, other modifications within the spirit of the invention may occur to those skilled in the art of battery technology, and it is understood that such modifications are intended to be included within the scope of the invention as claimed.
Claims (10)
1. A battery fault diagnosis method based on time-frequency image processing is characterized by comprising the following steps:
s1, collecting one-dimensional voltage data of the battery pack in the using process as an original data set, wherein the original data set comprises voltage data of normal single batteries and voltage data of fault single batteries;
s2, carrying out time-frequency processing on the acquired one-dimensional voltage data to obtain a two-dimensional time-frequency image of the battery;
s3, calculating the obtained time-frequency image to obtain a gray level co-occurrence matrix, and describing image texture distribution characteristics;
s4, selecting five feature sets of the gray level co-occurrence matrix, namely energy, contrast, entropy, correlation and inverse difference moment, and reducing dimensions by using a principal component analysis method to obtain a 2-dimensional fault feature set;
and S5, performing single battery fault diagnosis by using a density-based clustering algorithm.
2. The time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the step S2 is performed with time-frequency processing on the collected one-dimensional voltage data u (t) to convert the data into a two-dimensional time-frequency image; wherein the time-frequency processing adopts wavelet transform:
wherein
Representing the mother wavelet, a being a scale factor, b being a translation factor, and C (a, b) being wavelet transform coefficients.
3. The time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the step S4 obtains a gray level co-occurrence matrix p by calculation according to the formula:
p(i,j,α,β)＝{(m,n),(m+dm,n+dn)∈M*M,f(m,n)＝i,f(m+dm,n+dn)＝j} (2)
where M × M is the picture size, (M, n) is the reference point, (M + dm, n + dn) is the offset point, f (M, n) ═ i denotes that the gray-scale value of the reference point is i, f (M + dm, n + dn) ═ j denotes that the gray-scale value of the offset point is j, and α β denotes the offset value and the offset angle of the offset point, respectively.
4. The time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the energy POWER extracted in the step S5 is according to the formula:
5. the time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the characteristic entropy value ENY extracted in the step S5 is according to the formula:
6. the time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the characteristic contrast CON extracted in step S5 is according to the formula:
7. the time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the feature correlation DB extracted in step S5 is according to the formula:
wherein,
8. the time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the inverse difference moment DM extracted in step S5 is a characteristic that reflects the uniformity of the image texture and measures the local variation of the image texture; the larger the value, the less obvious the image texture varies between different regions, and the worse the local uniformity, according to the formula:
9. the time-frequency image processing-based battery fault diagnosis method of claim 1, wherein the principal component analysis method in step S5 mainly comprises the following steps:
s5.1, the number of the batteries is N, each battery has 5 characteristic quantities, and an original matrix (X) is formedij)N*5Wherein X isijThe j characteristic value of the ith battery;
s5.2, carrying out standardization processing on the original matrix X to obtain a standardized matrix Y, namely:
wherein, YijRepresents the normalized value of the jth characteristic quantity of the ith battery,
is the average of the i-th cell characteristic, SiStandard deviation of characteristic of ith battery
S5.3, calculating a correlation coefficient matrix R of the matrix Y, namely:
s5.4, calculating the characteristic value lambda of the matrix RiAnd the feature vector eiAssuming that R has q non-negative eigenvalues, it is sorted in descending order, i.e.: lambda [ alpha ]1≥λ2≥…≥λq (10)
Then, a feature vector e corresponding to the feature value is obtainedi(i ═ 1,2 … q), and the norm of the eigenvector is 1; s5.4, two principal components are extracted in the invention, so that the feature values are, the calculation expression of the principal components is as follows:
Z＝YE (11)
wherein E ═ E1,e2]And 2 orthonormal matrixes corresponding to the characteristic values in the front sequence.
10. The time-frequency image processing-based battery fault diagnosis method according to claim 1, wherein the step S6 performs fault diagnosis on the battery by using density-based clustering, which means that the feature value of an abnormal battery is different from the domain density of a normal battery; the method has two core parameters R and MinrWhere R refers to the area of the fault signature within a given radius, MinrWhether the fault feature sample is a core object is determined, namely the number of sample points in the field of the sample R is more than or equal to MinrDetermining the object as a core object; the method comprises the steps of firstly, randomly selecting a sample point, finding all points in the radius range of the point R, if the number of data points within the distance R is larger than that of the data points within the distance R, marking the point as a core sample, marking the point as the core sample, allocating a new cluster label, and then returning a density-connected algorithmA set, representing all objects in the set as a same cluster; otherwise, the outliers are marked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110453564.0A CN113203954A (en) | 2021-04-26 | 2021-04-26 | Battery fault diagnosis method based on time-frequency image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110453564.0A CN113203954A (en) | 2021-04-26 | 2021-04-26 | Battery fault diagnosis method based on time-frequency image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113203954A true CN113203954A (en) | 2021-08-03 |
Family
ID=77028904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110453564.0A Pending CN113203954A (en) | 2021-04-26 | 2021-04-26 | Battery fault diagnosis method based on time-frequency image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113203954A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418465A (en) * | 2022-03-29 | 2022-04-29 | 湖北工业大学 | Data-driven power battery use behavior quantitative evaluation method |
| CN115166520A (en) * | 2022-07-07 | 2022-10-11 | 重庆邮电大学 | Lithium ion battery pack short-circuit fault diagnosis method based on entropy and clustering algorithm |
| CN115308631A (en) * | 2022-10-09 | 2022-11-08 | 湖北工业大学 | Fault diagnosis method and system for new energy automobile power battery pack |
| CN117169732A (en) * | 2023-10-26 | 2023-12-05 | 宁德时代新能源科技股份有限公司 | Battery fault detection method, device, computing equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631553A (en) * | 2016-02-01 | 2016-06-01 | 浙江工业大学 | Charging and discharging automatic demand response optimization method for electric car |
| US20170229891A1 (en) * | 2016-02-05 | 2017-08-10 | Korea Advanced Institute Of Science And Technology | Optimized battery charging method based on thermodynamic information of battery |
| CN107643495A (en) * | 2017-11-08 | 2018-01-30 | 中国科学院电工研究所 | A kind of battery consistency evaluation method based on principal component analysis |
| KR20180021570A (en) * | 2016-08-22 | 2018-03-05 | 한국과학기술원 | Method for determining state of charge and method for measuring charge loss of battery using the same |
| CN111693868A (en) * | 2019-03-12 | 2020-09-22 | 天津工业大学 | Lithium battery state of charge estimation method based on density feature clustering integration |
-
2021
- 2021-04-26 CN CN202110453564.0A patent/CN113203954A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631553A (en) * | 2016-02-01 | 2016-06-01 | 浙江工业大学 | Charging and discharging automatic demand response optimization method for electric car |
| US20170229891A1 (en) * | 2016-02-05 | 2017-08-10 | Korea Advanced Institute Of Science And Technology | Optimized battery charging method based on thermodynamic information of battery |
| KR20180021570A (en) * | 2016-08-22 | 2018-03-05 | 한국과학기술원 | Method for determining state of charge and method for measuring charge loss of battery using the same |
| CN107643495A (en) * | 2017-11-08 | 2018-01-30 | 中国科学院电工研究所 | A kind of battery consistency evaluation method based on principal component analysis |
| CN111693868A (en) * | 2019-03-12 | 2020-09-22 | 天津工业大学 | Lithium battery state of charge estimation method based on density feature clustering integration |
Non-Patent Citations (4)
| Title |
|---|
| 刘思洋: "水面垃圾清理机器人电控系统及目标识别算法的研究", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》 * |
| 孙逢春 等: "电池自身的异常", 《"装甲车辆混合动力电传动技术（第2版）》 * |
| 陈宗海: "基于信号处理的方法", 《系统仿真技术及其应用》 * |
| 马宏忠 等: "基于MRSVD和时频灰度图的储能电池过充特征识别", 《电源技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418465A (en) * | 2022-03-29 | 2022-04-29 | 湖北工业大学 | Data-driven power battery use behavior quantitative evaluation method |
| CN114418465B (en) * | 2022-03-29 | 2022-08-05 | 湖北工业大学 | Data-driven power battery use behavior quantitative evaluation method |
| CN115166520A (en) * | 2022-07-07 | 2022-10-11 | 重庆邮电大学 | Lithium ion battery pack short-circuit fault diagnosis method based on entropy and clustering algorithm |
| CN115308631A (en) * | 2022-10-09 | 2022-11-08 | 湖北工业大学 | Fault diagnosis method and system for new energy automobile power battery pack |
| CN117169732A (en) * | 2023-10-26 | 2023-12-05 | 宁德时代新能源科技股份有限公司 | Battery fault detection method, device, computing equipment and medium |
| CN117169732B (en) * | 2023-10-26 | 2024-04-26 | 宁德时代新能源科技股份有限公司 | Battery fault detection method, device, computing equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113203954A (en) | Battery fault diagnosis method based on time-frequency image processing | |
| CN111695598B (en) | Monitoring data abnormity diagnosis method based on generation countermeasure network | |
| CN108398939B (en) | Fault diagnosis method based on DS evidence theory | |
| CN114559819A (en) | Electric vehicle battery safety early warning method based on signal processing | |
| CN113406524B (en) | Inconsistent fault diagnosis method and system for power battery system | |
| CN116400244B (en) | Abnormality detection method and device for energy storage battery | |
| CN114118219A (en) | Data-driven real-time abnormal detection method for health state of long-term power-on equipment | |
| CN116503354A (en) | Method and device for detecting and evaluating hot spots of photovoltaic cells based on multi-mode fusion | |
| CN118427681A (en) | Cross-working condition open-set fault diagnosis method and equipment based on self-supervision contrast learning enhancement | |
| CN117036732B (en) | Electromechanical equipment detection system, method and equipment based on fusion model | |
| CN112880726A (en) | Sensor fault diagnosis method and device based on variational modal decomposition sample entropy | |
| CN108681802A (en) | A kind of electric vehicle electrically-charging equipment Information Interoperability evaluation method | |
| CN112419243A (en) | Power distribution room equipment fault identification method based on infrared image analysis | |
| CN116381493A (en) | Battery pack fault detection method, system, electronic equipment and storage medium | |
| CN116434258A (en) | Automatic identification method for form data | |
| CN112014821B (en) | Unknown vehicle target identification method based on radar broadband characteristics | |
| CN116956089A (en) | Training method and detection method for temperature anomaly detection model of electrical equipment | |
| CN118514566B (en) | Detection method for illegal charging of storage battery car | |
| CN118470442B (en) | Small sample anomaly detection method based on multi-scale hypergraph and feature registration | |
| CN116819378B (en) | Energy storage battery abnormality detection method and device | |
| CN117688496B (en) | Abnormality diagnosis method, system and equipment for satellite telemetry multidimensional time sequence data | |
| CN117935030B (en) | Multi-label confidence calibration method and system for double-view-angle correlation perception regularization | |
| CN114863178A (en) | Image data input detection method and system for neural network vision system | |
| CN117723299A (en) | Small sample bearing fault detection classification method and system based on deep learning | |
| CN118033425A (en) | Battery cell fault type detection method, detection device, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210803 |