CN114818936A - Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm - Google Patents

Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm Download PDF

Info

Publication number
CN114818936A
CN114818936A CN202210467919.6A CN202210467919A CN114818936A CN 114818936 A CN114818936 A CN 114818936A CN 202210467919 A CN202210467919 A CN 202210467919A CN 114818936 A CN114818936 A CN 114818936A
Authority
CN
China
Prior art keywords
retired
battery
clustering
batteries
comprehensive
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
Application number
CN202210467919.6A
Other languages
Chinese (zh)
Inventor
李岩
尹浩杰
张承慧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University
Original Assignee
Shandong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong University filed Critical Shandong University
Priority to CN202210467919.6A priority Critical patent/CN114818936A/en
Publication of CN114818936A publication Critical patent/CN114818936A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/36—Sorting apparatus characterised by the means used for distribution
    • B07C5/361—Processing or control devices therefor, e.g. escort memory
    • 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
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/30—Administration of product recycling or disposal
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Human Resources & Organizations (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Probability & Statistics with Applications (AREA)
  • Marketing (AREA)
  • Manufacturing & Machinery (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Sustainable Development (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Secondary Cells (AREA)

Abstract

The invention belongs to the field of battery sorting, and provides a retired battery rapid comprehensive sorting method and system based on a K-means clustering algorithm, which are used for obtaining retired battery test data; preprocessing the test data of the retired batteries, establishing a comprehensive characteristic vector of each retired battery and constructing a comprehensive characteristic data set of all the retired batteries; based on the retired battery comprehensive characteristic data set and a K mean value clustering algorithm, a clustering center and a clustering number K are initialized through continuous optimization, and a class label of each retired battery is obtained through clustering; dividing the retired batteries with the same class labels into the same class, calculating the standard deviation and the average value of the comprehensive characteristics of the retired batteries, and analyzing the integral condition and the discrete degree of the retired batteries; the matching degree is calculated according to the requirements of different gradient utilization scenes, and the retired battery with the largest matching degree is recombined for gradient utilization, so that the retired battery is quickly and comprehensively sorted, the service life of the retired battery is prolonged, and the use value of the retired battery is maximized.

Description

Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm
Technical Field
The invention belongs to the field of battery sorting, and particularly relates to a method and a system for quickly and comprehensively sorting retired batteries based on a K-means clustering algorithm.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Because of the difference of manufacturers, electric automobile operating environment and operating mode etc., the uniformity between the lithium ion battery of retirement is extremely poor, carries out echelon after direct reorganization and utilizes and can bring a series of problems and difficult problem, if: overcharge, overdischarge, thermal runaway, and the like. Therefore, the method selects proper battery characteristics and a reasonably designed sorting method, sorts out the retired batteries with consistent comprehensive performance and recombines the retired batteries for use, and has important significance for gradient utilization of the retired lithium ion batteries.
At present, most of the commonly used sorting methods are sorting according to one or more of parameters such as capacity, temperature, internal resistance and voltage as sorting characteristics, but the characteristics are mostly in a short time scale, only the consistency of the sorted battery characteristics at the initial time or a certain time can be ensured, but the consistency of the sorted battery characteristics on the long time scale cannot be ensured, so that the problem of inconsistency is caused, the inconsistency is aggravated along with the increase of the working time of the battery, irreversible damage is caused to the battery, the scrapping process of the battery is accelerated, and potential safety hazards are caused. In addition, the number of the retired batteries is large, the characteristic parameters of the batteries are various, and the comprehensive performance of the batteries is difficult to evaluate.
In summary, in the prior art, the selection of appropriate battery characteristics is not considered to evaluate the comprehensive performance of the retired batteries on a long and short time scale, and a reasonable sorting method is designed to quickly sort the retired batteries with consistent comprehensive performance from a large number of retired batteries, match the demand of an actual echelon utilization scene, prolong the service life of the retired batteries and maximize the use value of the retired batteries.
Disclosure of Invention
In order to solve at least one technical problem in the background art, the invention provides a method and a system for rapidly and comprehensively sorting retired batteries based on a K-means clustering algorithm, which can comprehensively evaluate the performance of the retired batteries, sort the retired batteries with comprehensive consistency, and apply the retired batteries to a matched echelon utilization scene, so that the service life of the retired batteries in the echelon utilization process is prolonged to the maximum extent, and the use value of the retired batteries is maximized.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a rapid and comprehensive sorting method of retired batteries based on a K-means clustering algorithm, which comprises the following steps:
obtaining test data of a retired battery;
preprocessing the test data of the retired batteries, establishing a comprehensive characteristic vector of each retired battery and constructing a comprehensive characteristic data set of all the retired batteries;
based on the retired battery comprehensive characteristic data set and a K-means clustering algorithm, clustering retired batteries by continuously optimizing and initializing a clustering center, evaluating a clustering result by adopting a clustering comprehensive index, continuously optimizing and adjusting the number of clusters to obtain a class label of each retired battery, and classifying the retired batteries with the same class label into one class;
and comparing the matching degree of the characteristics of the same type of retired batteries with the requirements in different gradient utilization scenes and the corresponding comprehensive performance, and continuously recombining the battery with the maximum matching degree to obtain a final sorting result and applying the final sorting result to the corresponding gradient utilization scene.
The invention provides a retired battery rapid comprehensive sorting system based on a K-means clustering algorithm, which comprises:
the data acquisition module is used for acquiring retired battery test data;
the characteristic data set construction module is used for preprocessing the test data of the retired batteries, establishing a comprehensive characteristic vector of each retired battery and constructing a comprehensive characteristic data set of all the retired batteries;
the sorting module is used for clustering the retired batteries by continuously optimizing and initializing a clustering center based on a retired battery comprehensive characteristic data set and a K-means clustering algorithm, evaluating a clustering result by adopting a clustering comprehensive index, continuously optimizing and adjusting the clustering number to obtain class labels of each retired battery, and classifying the retired batteries with the same class labels into one class;
and the recombination and echelon matching module is used for comparing the matching degree of each characteristic of the same type of retired battery with the requirement in different echelon utilization scenes and the corresponding comprehensive performance, and continuously recombining the battery with the maximum matching degree to obtain a final sorting result and applying the final sorting result to the corresponding echelon utilization scene.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the retired battery rapid integrated sorting method based on K-means clustering algorithm as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-mentioned retired battery rapid integrated sorting method based on K-means clustering algorithm.
Compared with the prior art, the invention has the beneficial effects that:
the invention selects proper battery characteristics to evaluate the comprehensive performance of the retired battery on a long time scale by comprehensively considering the key characteristics of the battery, designs a reasonable sorting method, quickly sorts the retired batteries with consistent comprehensive performance from a large number of retired batteries, matches the demand of an actual echelon utilization scene, ensures the consistency of the sorted retired batteries in the actual operation process, reduces the irreversible damage of the batteries caused by the inconsistency of the retired batteries in the echelon utilization process, and sorts the retired batteries with comprehensive consistency for echelon utilization, so that the service life of the retired batteries in the echelon utilization process is prolonged to the maximum extent, and the use value of the retired batteries is maximized. Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow diagram of the overall method of the present invention;
FIG. 2 is a flow chart of a method for testing a retired battery according to the present invention;
FIG. 3 is a flow chart of the improved K-means clustering algorithm of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. 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.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
As shown in fig. 1, the embodiment provides a retired battery rapid comprehensive sorting method based on a K-means clustering algorithm, which includes the following steps:
step 1: obtaining test data of a retired battery;
step 2: preprocessing the test data of the retired batteries, establishing a comprehensive characteristic vector of each retired battery and constructing a comprehensive characteristic data set of all the retired batteries;
and step 3: based on the retired battery comprehensive characteristic data set and the K-means clustering algorithm, clustering retired batteries by continuously optimizing the initialized clustering center, evaluating clustering results by adopting clustering comprehensive indexes, and continuously optimizing and adjusting the number of clusters to obtain a class label of each retired battery;
and 4, step 4: classifying the retired batteries with the same class labels into one class, calculating the standard deviation and the average value of comprehensive characteristic indexes among the retired batteries of the same class, and analyzing the integral condition and the discrete degree of the retired batteries;
and 5: and comparing the matching degree of the comprehensive characteristics of the same type of retired batteries with the requirements in different echelon utilization scenes and the corresponding comprehensive performance, and continuously recombining the batteries with the maximum matching degree to obtain a final sorting result and applying the final sorting result to the corresponding echelon utilization scenes.
As one or more embodiments, in step 1, the method for testing retired battery test data is shown in fig. 2, and the specific operation steps include:
(1) constant-current charging is carried out on the retired batteries to be sorted until the voltages of the retired batteries are all 4.2V, so that the initial discharge voltage is ensured to be consistent;
(2) after the static preset time, discharging with the discharge capacity of 2A until the voltage reaches a second fixed value of 2.7V;
(3) measuring the temperature of the surface of the battery at the beginning and the end of the discharge by using a temperature sensor to obtain the temperature rise of the battery in the discharge process;
(4) in the whole discharging process, a sampling period is set, the voltage of the battery is sampled, a discharging voltage curve is obtained, and then the discharging capacity of the battery is calculated according to an ampere-hour integration method.
In order to solve the problems that the used characteristics of the existing sorting method are not comprehensive enough, the comprehensive consistency of the sorted batteries on the long and short time scales is difficult to guarantee, and the like, the comprehensive characteristics of the batteries sampled by the embodiment mainly comprise: discharge capacity, temperature rise, voltage plateau and voltage drop value under the same discharge capacity.
The battery pack is characterized in that the discharge capacity and the temperature rise are used as sorting characteristics, so that the consistency of the capacity and the temperature of the sorted battery can be ensured, the wooden barrel effect caused by inconsistent capacity in the echelon utilization process is avoided, and the difficulty of heat management of the battery pack in the echelon utilization process is reduced; and the voltage platform and the voltage drop value are used as the characteristics of sorting, so that the consistency of the sorted retired battery in the actual operation process can be ensured, and the irreversible damage of the retired battery caused by inconsistency in the echelon utilization process can be reduced. Based on the comprehensive characteristics of the batteries, the performance of the retired batteries can be comprehensively evaluated, and the retired batteries with comprehensive consistency on a long time scale and a short time scale are sorted for gradient utilization, so that the service life of the retired batteries in the gradient utilization process is prolonged to the maximum extent, and the use value of the retired batteries is maximized.
As one or more embodiments, in step 2, the preprocessing the retired battery test data specifically includes:
selecting a voltage value of a discharge voltage curve at a middle moment; calculation of voltage drop value at the same discharge capacity: the voltage of the retired battery decreases from the initial discharge time to the process of discharging 1Ah of electricity.
And (3) standardization treatment: and (3) carrying out standardization processing on the data by adopting a maximum and minimum standardization processing method to obtain characteristic data such as discharge capacity, a temperature rise voltage platform, a voltage drop value and the like so as to eliminate dimensional influence among all parameters.
The normalization processing formula is as follows:
Figure BDA0003625188560000061
constructing a decommissioned battery comprehensive characteristic data set: according to the characteristic data of standardized discharge capacity, temperature rise, voltage platform, voltage reduction value and the like obtained after the test data of the retired battery are preprocessed, the comprehensive characteristic vector x of each retired battery is constructed i ，x i ＝{x i1 ,x i2 ,x i3 ,x i4 And establishing a decommissioned battery comprehensive characteristic data set X ═ X 1 ,x 2 ,…,x n And n is the number of the ex-service batteries to be sorted.
As one or more embodiments, as shown in fig. 3, the improving the initial cluster center selection and the determination of the cluster number K by optimization, and obtaining the class label of each retired battery through cluster calculation includes the following steps:
(1) and inputting a decommissioned battery comprehensive characteristic data set X and an initial battery class number K.
(2) Randomly selecting a sample point as a processing cluster center, and calculating the distance D from each sample point in the retired battery data set to the cluster center, namely:
Figure BDA0003625188560000071
(3) and calculating the probability P of each sample point being selected as the next clustering center, and selecting the sample point with the highest probability as the next clustering center according to a roulette selection method.
(4) And (4) repeating the step (2) and the step (3) until K clustering centers are selected.
(5) And calculating the distance from each sample point in the retired battery data set to K clustering centers, and dividing the sample points into the class where the nearest clustering center is located.
(6) And calculating the mass center of each class as the clustering center of each class, and judging whether the clustering center is consistent with the current clustering center.
(7) And (4) when the two groups of clustering centers are inconsistent, continuously repeating the steps (5) and (6) until the clustering centers are not changed any more, and outputting the calculation result at the moment and the class label corresponding to each retired battery sample.
(8) And (3) evaluating the current clustering calculation result by adopting a clustering comprehensive evaluation index Davies-Bouldin (DB) index, and continuously adjusting the initial battery number K in the step (1). When the DB index obtains the minimum value, the battery sorting result corresponding to the battery number K is the best at the moment, and the current clustering result is output.
The calculation formula of the DB index is as follows:
Figure BDA0003625188560000081
Figure BDA0003625188560000082
in the above formula, K is the current cluster number, D (x, c) i ) For the sample point x in the i-th retired battery to the c-center i Distance of (1), N i Is the total number of sample points, avg (C), in class i decommissioned batteries i ) Average distance of all sample points in the i-th class retired battery to the class center, D (c) i ,c j ) The distance between the centers of the ith and jth classes. The smaller the DB index is, the smaller the distance in the same class is, the larger the distance between classes is, and the better the clustering sorting result is.
The embodiment adopts an improved K-means clustering algorithm, and effectively improves the convergence rate of the algorithm by continuously optimizing the selection of the initial clustering center in the clustering calculation process; in addition, the clustering result is evaluated by means of a clustering comprehensive evaluation index DB index, and the clustering number K is continuously optimized and adjusted, so that the clustering calculation precision is improved. By combining the improvement of the improvement points of the two technologies, the calculation efficiency and the sorting precision can be simultaneously ensured, so that the retired batteries with comprehensive consistency can be quickly and efficiently sorted out.
As one or more embodiments, in step 4, to verify the sorting effect, the method is applied to a group of retired battery test data sets to obtain class labels of the retired batteries, the retired batteries with the same class labels are put together into the same class, and an average (Mean, M) and a Standard Deviation (SD) of each comprehensive characteristic index in the retired batteries of the same class are calculated.
The average value can reflect the overall situation of each type of retired battery comprehensive characteristic index obtained by sorting; the standard deviation is the average value of the distances of all data from the average value, and can reflect the dispersion degree of all comprehensive characteristics in the same type of retired batteries. Here we quantify the degree of dispersion by the size D of the standard deviation of the sample relative to the mean of the sample, i.e.:
Figure BDA0003625188560000083
the smaller the value, the better, generally within 5% indicating a more compact sample feature.
The calculation results of the average value and the standard deviation of the comprehensive characteristic indexes of various retired batteries are shown in table 1, wherein the maximum D value for measuring the dispersion degree of the capacity index in various retired battery samples is 4.9%, the maximum D value for measuring the dispersion degree of the temperature rise index is 2.5%, the maximum D value for measuring the dispersion degree of the voltage platform is 0.4%, and the maximum D value for measuring the dispersion degree of the capacity index is 2.9%. In conclusion, the dispersion degree of all the comprehensive characteristic indexes is within 5%, which also indicates that the numerical values of all the comprehensive characteristics of the sorted retired batteries are distributed compactly in the same class, namely the comprehensive consistency among the retired batteries of the same class is better, so that various problems caused by inconsistency when the retired batteries are recombined for use can be reduced, the safety of gradient utilization is improved, and the service life of the retired batteries is prolonged.
TABLE 1 comprehensive characteristic index of ex-service batteries
Figure BDA0003625188560000091
As one or more embodiments, in step 5, according to specific requirements on capacity, voltage, temperature and the like of the retired batteries in various scenes of actual echelon utilization, corresponding capacity threshold values, temperature rise threshold values, voltage platform threshold values and the like are set, comparison and analysis are performed in combination with the situation of various comprehensive characteristics in each class of retired batteries obtained through calculation, the matching degree between the retired batteries is obtained, then each class of retired batteries obtained through sorting is recombined and applied to a echelon utilization scene with the maximum matching degree, the retired batteries of the same class obtained through sorting have strong comprehensive consistency, the consistency of the performances of the retired batteries in the length and time scale of the echelon utilization process can be ensured, various problems caused by inconsistency are avoided, and the echelon utilization value of the retired batteries is maximized.
Example two
The embodiment provides a retired battery rapid comprehensive sorting system based on a K-means clustering algorithm, which comprises:
the data acquisition module is used for acquiring retired battery test data;
the characteristic data set construction module is used for preprocessing the test data of the retired batteries, establishing a comprehensive characteristic vector of each retired battery and constructing a comprehensive characteristic data set of all the retired batteries;
the sorting module is used for clustering the retired batteries by continuously optimizing and initializing a clustering center based on a retired battery comprehensive characteristic data set and a K-means clustering algorithm, evaluating a clustering result by adopting a clustering comprehensive index, continuously optimizing and adjusting the clustering number to obtain class labels of each retired battery, and classifying the retired batteries with the same class labels into one class;
and the recombination and echelon matching module is used for comparing the matching degree of each characteristic of the same type of retired battery with the requirement in different echelon utilization scenes and the corresponding comprehensive performance, and continuously recombining the battery with the maximum matching degree to obtain a final sorting result and applying the final sorting result to the corresponding echelon utilization scene.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the retired battery rapid integrated sorting method based on the K-means clustering algorithm as described above.
Example four
The embodiment provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps in the retired battery rapid comprehensive sorting method based on the K-means clustering algorithm.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a computer to implement the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. The retired battery rapid comprehensive sorting method based on the K-means clustering algorithm is characterized by comprising the following steps of:
obtaining test data of a retired battery;
preprocessing the test data of the retired batteries, establishing a comprehensive characteristic vector of each retired battery and constructing a comprehensive characteristic data set of all the retired batteries;
based on the retired battery comprehensive characteristic data set and a K-means clustering algorithm, clustering retired batteries by continuously optimizing and initializing a clustering center, evaluating a clustering result by adopting a clustering comprehensive index, continuously optimizing and adjusting the number of clusters to obtain a class label of each retired battery, and classifying the retired batteries with the same class label into one class;
and comparing the matching degree of the characteristics of the same type of retired batteries with the requirements in different gradient utilization scenes and the corresponding comprehensive performance, and continuously recombining the battery with the maximum matching degree to obtain a final sorting result and applying the final sorting result to the corresponding gradient utilization scene.
2. The method for rapidly and comprehensively sorting retired batteries based on K-means clustering algorithm according to claim 1, wherein the comprehensive feature vector of each retired battery comprises: discharge capacity, temperature rise, voltage plateau and voltage drop value under the same discharge capacity.
3. The method for rapidly and comprehensively sorting retired batteries based on K-means clustering algorithm according to claim 1, wherein the preprocessing retired battery test data comprises: and (4) carrying out standardization processing on the data by adopting a maximum and minimum standardization processing method to obtain characteristic data of the discharge capacity, the temperature rise voltage platform and the voltage drop value so as to eliminate dimensional influence among all parameters.
4. The method for rapidly and comprehensively sorting the retired batteries based on the K-means clustering algorithm according to claim 1, wherein the clustering of the retired batteries by continuously optimizing and initializing the clustering centers comprises the following steps:
inputting a decommissioned battery comprehensive characteristic data set X and a battery class number K;
randomly selecting a sample point as a processing clustering center, and calculating the distance D from each sample point in the retired battery data set to the clustering center;
calculating the probability P of each sample point selected as the next clustering center, and selecting the sample point with the highest probability as the next clustering center according to a wheel disc selection method until all the clustering centers are selected;
calculating the distance from each sample point in the retired battery data set to K clustering centers, and dividing the sample points into the class where the nearest clustering center is located;
and calculating the mass center of each class as the clustering center of each class until the clustering is not changed any more, and outputting the class label of each retired battery sample.
5. The method for rapidly and comprehensively sorting retired batteries based on K-means clustering algorithm according to claim 1, wherein the clustering result is evaluated by using a clustering comprehensive index, and the clustering number is continuously optimized and adjusted, specifically: when the DB index obtains the minimum value, obtaining a battery sorting result corresponding to the number of the batteries, wherein the calculation formula of the DB index is as follows:
Figure FDA0003625188550000021
Figure FDA0003625188550000022
in the above formula, K is the current cluster number,D(x,c i ) For the sample point x in the i-th retired battery to the c-center i Distance of (1), N i Is the total number of sample points, avg (C), in class i decommissioned batteries i ) Average distance of all sample points in the i-th class retired battery to the class center, D (c) i ,c j ) The distance between the centers of the ith and jth classes.
6. The method for rapidly and comprehensively sorting retired batteries based on K-means clustering algorithm according to claim 1, wherein the step of sorting retired batteries with consistent comprehensive performance according to various comprehensive characteristic indexes in the same type of retired batteries comprises the following steps: and calculating the average value and the standard deviation of each comprehensive characteristic index in the same type of retired batteries, and analyzing the integral condition and the discrete degree of the retired batteries according to the calculation results of the average value and the standard deviation.
7. Retired battery rapid comprehensive sorting system based on K-means clustering algorithm is characterized by comprising:
the data acquisition module is used for acquiring retired battery test data;
the characteristic data set construction module is used for preprocessing the test data of the retired batteries, establishing a comprehensive characteristic vector of each retired battery and constructing a comprehensive characteristic data set of all the retired batteries;
the sorting module is used for clustering the retired batteries by continuously optimizing and initializing a clustering center based on a retired battery comprehensive characteristic data set and a K-means clustering algorithm, evaluating a clustering result by adopting a clustering comprehensive index, continuously optimizing and adjusting the clustering number to obtain class labels of each retired battery, and classifying the retired batteries with the same class labels into one class;
and the recombination and echelon matching module is used for comparing the matching degree of each characteristic of the same type of retired battery with the requirement in different echelon utilization scenes and the corresponding comprehensive performance, and continuously recombining the battery with the maximum matching degree to obtain a final sorting result and applying the final sorting result to the corresponding echelon utilization scene.
8. The method as claimed in claim 7, wherein the comprehensive feature vector of each retired battery comprises: discharge capacity, temperature rise, voltage plateau and voltage drop value under the same discharge capacity.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for rapid integrated sorting of retired batteries based on K-means clustering algorithm according to any of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for rapid integrated sorting of retired batteries based on K-means clustering algorithm according to any of claims 1 to 7.
CN202210467919.6A 2022-04-29 2022-04-29 Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm Pending CN114818936A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210467919.6A CN114818936A (en) 2022-04-29 2022-04-29 Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210467919.6A CN114818936A (en) 2022-04-29 2022-04-29 Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm

Publications (1)

Publication Number Publication Date
CN114818936A true CN114818936A (en) 2022-07-29

Family

ID=82508667

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210467919.6A Pending CN114818936A (en) 2022-04-29 2022-04-29 Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm

Country Status (1)

Country Link
CN (1) CN114818936A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116562596A (en) * 2023-07-07 2023-08-08 杭州安影科技有限公司 Retired battery processing method and device, retired battery storage vertical warehouse and medium
CN117828378B (en) * 2024-03-04 2024-05-17 北京清水爱派建筑设计股份有限公司 Digital intelligent green building design evaluation method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116562596A (en) * 2023-07-07 2023-08-08 杭州安影科技有限公司 Retired battery processing method and device, retired battery storage vertical warehouse and medium
CN117828378B (en) * 2024-03-04 2024-05-17 北京清水爱派建筑设计股份有限公司 Digital intelligent green building design evaluation method

Similar Documents

Publication Publication Date Title
CN109165687B (en) Vehicle lithium battery fault diagnosis method based on multi-classification support vector machine algorithm
CN109655754B (en) Battery performance evaluation method based on multi-dimensional grading of charging process
CN108490366B (en) Rapid assessment method for state of health of electric automobile retired battery module
CN112630662B (en) Power battery SOH estimation method based on data driving and multi-parameter fusion
CN107024663A (en) The lithium battery screening technique clustered based on charging curve feature KPCA
CN109613440B (en) Battery grading method, device, equipment and storage medium
CN113289931A (en) Lithium ion battery echelon utilization and sorting method
CN112381351B (en) Power utilization behavior change detection method and system based on singular spectrum analysis
Ran et al. Data‐driven fast clustering of second‐life lithium‐ion battery: mechanism and algorithm
CN115248393A (en) Battery consistency sorting method, device, equipment and storage medium
CN116699446A (en) Method, device, equipment and storage medium for rapidly sorting retired batteries
CN114818936A (en) Retired battery rapid comprehensive sorting method and system based on K-means clustering algorithm
CN115061058A (en) Method and system for measuring and calculating gradient utilization residual life of retired power battery
CN116660759A (en) Battery life prediction method and device based on BMS battery management system
CN113945852B (en) Method for evaluating inconsistency of storage battery pack
CN116699407A (en) Power battery safety risk early warning method based on safety entropy
CN112485694B (en) Battery pack detection method and device
CN116068402A (en) New energy automobile lithium battery state prediction method, device, equipment and storage medium
CN115840151A (en) Battery capacity consistency analysis method and device and computer equipment
CN115248394A (en) Dynamic battery sorting method, device, equipment and storage medium
Lin et al. Research on clustering analysis of new energy charging user behavior based on spark
Dongsheng et al. EV battery SOH diagnosis method based on discrete Fréchet distance
CN117706377B (en) Battery inconsistency identification method and device based on self-adaptive clustering
CN116338501B (en) Lithium ion battery health detection method based on neural network prediction relaxation voltage
Hong et al. Lithium battery sorting method for high-rate operating conditions

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