CN118863929B - A production quality traceability method for new energy batteries with embedded RFID - Google Patents
A production quality traceability method for new energy batteries with embedded RFID Download PDFInfo
- Publication number
- CN118863929B CN118863929B CN202411345815.3A CN202411345815A CN118863929B CN 118863929 B CN118863929 B CN 118863929B CN 202411345815 A CN202411345815 A CN 202411345815A CN 118863929 B CN118863929 B CN 118863929B
- Authority
- CN
- China
- Prior art keywords
- internal resistance
- cluster
- abnormal
- resistance data
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
- G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Manufacturing & Machinery (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Networks & Wireless Communication (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to the technical field of electrical performance test, and provides a production quality tracing method of an embedded RFID new energy battery, which comprises the steps of obtaining the internal resistance data, the temperature data and LOF outlier factors of the internal resistance data of all lithium batteries in the same batch with the lithium battery with quality problem; screening and clustering the internal resistance data, obtaining cluster clusters, obtaining the concentration degree of the density center of the internal resistance data, determining the concentration degree of the cluster clusters, determining the internal resistance data without quality problems and the suspected abnormal internal resistance data, obtaining the abnormal consistency index of the suspected abnormal internal resistance, determining the first abnormal internal resistance data according to the abnormal consistency index, clustering the first abnormal internal resistance data, determining the quality problem clusters, obtaining the inter-cluster difference degree of the quality problem clusters, determining the final quality problem clustering result according to the inter-cluster difference degree, and finishing the production quality tracing of the lithium battery embedded with the RFID. The invention aims to solve the problem of low traceability efficiency of battery production quality.
Description
Technical Field
The invention relates to the technical field of electrical performance testing, in particular to a production quality tracing method of an embedded RFID new energy battery.
Background
RFID is a wireless communication technology for wireless identification and tracking of objects. The RFID tag is embedded in the battery, unique identification and data transmission of an object can be realized by utilizing a radio frequency signal, important data in a production process are recorded, and the quality of the battery is convenient to trace. The important data in the production flow comprises production date, production process parameters, raw material information, test data, quality detection results, factory batch and the like. When a problem occurs in a certain battery, the battery which may have the same problem can be traced back quickly and comprehensively through the data.
At present, quality monitoring of batteries is limited to testing performance of single batteries, when quality problems of the batteries are found, the batteries in the same batch are required to be detected sequentially and one by one in a quality tracing process, whether the quality problems are common problems in the same batch or not is judged, and further production links are traced, so that the problems can be found and solved in time. However, the workload of sequentially and individually detecting the batteries in the same batch is large, so that the efficiency of production quality tracing is not high.
Disclosure of Invention
The invention provides a production quality tracing method of an embedded RFID new energy battery, which aims to solve the problem of low efficiency of production quality tracing caused by neglecting the correlation between battery data in the process of battery production quality tracing, and adopts the following specific technical scheme:
the embodiment of the invention provides a production quality tracing method of an embedded RFID new energy battery, which comprises the following steps:
Obtaining the internal resistance data, the temperature data and LOF outlier factors of the internal resistance data of all lithium batteries in the same batch with the lithium batteries with quality problems according to the lithium batteries with quality problems detected in the sampling inspection process;
screening and clustering the internal resistance data according to LOF outliers of the internal resistance data, obtaining clusters, determining the radius of the clusters, obtaining the density center aggregation degree of the internal resistance data according to the internal resistance data contained in the clusters and the radius of the clusters, determining the density concentration degree of the clusters, determining the internal resistance data without quality problems according to the density concentration degree, and determining the suspected abnormal internal resistance data;
Obtaining neighborhood data of suspected abnormal internal resistance, obtaining an internal resistance distance sequence and a temperature distance sequence of the suspected abnormal internal resistance, obtaining a temperature association degree of the suspected abnormal internal resistance, obtaining a variation coefficient of a density center aggregation degree of the suspected abnormal internal resistance, obtaining local abnormal consistency indexes of the suspected abnormal internal resistance according to the temperature association degree of the suspected abnormal internal resistance and the variation coefficient of the density center aggregation degree of the suspected abnormal internal resistance, obtaining abnormal consistency indexes of the suspected abnormal internal resistance according to the local abnormal consistency indexes of all the suspected abnormal internal resistances, and determining first abnormal internal resistance data according to the abnormal consistency indexes;
Clustering the first abnormal internal resistance data, determining a quality problem cluster, determining an adjacent quality problem cluster according to the quality problem cluster, determining an evaluation data set according to the quality problem cluster and the first abnormal internal resistance data contained in the adjacent quality problem cluster, determining the division independence degree of the quality problem cluster according to the first abnormal internal resistance data contained in the evaluation data set, acquiring the inter-cluster difference degree of the quality problem cluster according to the division independence degree of the quality problem cluster and the first abnormal internal resistance data contained in the quality problem cluster, determining a final quality problem clustering result according to the inter-cluster difference degree, and finishing the lithium battery production quality traceability of the embedded RFID.
Further, the screening and clustering are carried out on the internal resistance data according to LOF outlier factors of the internal resistance data to obtain clustered clusters, and the specific method comprises the following steps:
removing internal resistance data with LOF outlier factors larger than a first preset threshold, taking the variance of the residual internal resistance data as a cut-off distance, and clustering the residual internal resistance data by using a density peak clustering algorithm to obtain a cluster.
Further, the determining the radius of the cluster, and obtaining the concentration degree of the density center of the internal resistance data according to the internal resistance data contained in the cluster and the radius of the cluster, includes the following specific steps:
the average value of Euclidean distances from all internal resistance data contained in the cluster to a cluster center is recorded as the radius of the cluster;
the product of Euclidean distance between the internal resistance data and cluster centers of the cluster where the internal resistance data is located and the radius of the cluster where the internal resistance data is located is recorded as a first distance;
And recording the ratio of the number of the internal resistance data contained in the cluster where the internal resistance data are located to the first distance as the concentration degree of the density center of the internal resistance data.
Further, the determining the density concentration of the cluster, determining the internal resistance data without quality problems according to the density concentration, and determining the suspected abnormal internal resistance data comprises the following specific methods:
taking the average value of the concentration degree of the density centers of all the internal resistance data contained in the cluster as the density concentration degree of the cluster;
taking the internal resistance data contained in the cluster with the largest density concentration as the internal resistance data without quality problems;
Internal resistance data which is not free of quality problems is recorded as suspected abnormal internal resistance data.
Further, the method for obtaining the neighborhood data of the suspected abnormal internal resistance comprises the following specific steps:
and recording second preset threshold value internal resistance data with the minimum Euclidean distance with the internal resistance data of the suspected abnormal internal resistance in the cluster where the suspected abnormal internal resistance is located as neighborhood data of the suspected abnormal internal resistance.
Further, the method for obtaining the internal resistance distance sequence and the temperature distance sequence of the suspected abnormal internal resistance and obtaining the temperature association degree of the suspected abnormal internal resistance comprises the following specific steps:
sequencing the internal resistance data of the suspected abnormal internal resistance and the neighborhood data of the suspected abnormal internal resistance according to the sequence from small to large of the Euclidean distance between the internal resistance data of the suspected abnormal internal resistance and the internal resistance data of the suspected abnormal internal resistance, and obtaining an internal resistance distance sequence of the suspected abnormal internal resistance;
Arranging temperature data corresponding to the internal resistance data contained in the internal resistance distance sequence to obtain a temperature distance sequence of suspected abnormal internal resistance;
And (3) counting the Pearson phase relation number between the internal resistance distance sequence and the temperature distance sequence of the suspected abnormal internal resistance as the temperature association degree of the suspected abnormal internal resistance.
Further, the method for obtaining the local abnormal consistency index of the suspected abnormal internal resistance according to the temperature association degree of the suspected abnormal internal resistance and the variation coefficient of the density center aggregation degree of the suspected abnormal internal resistance, and obtaining the abnormal consistency index of the suspected abnormal internal resistance according to the local abnormal consistency indexes of all the suspected abnormal internal resistances comprises the following specific steps:
The ratio of the temperature association degree of the suspected abnormal internal resistance and the variation coefficient of the density center aggregation degree of the suspected abnormal internal resistance is recorded as a local abnormal consistency index of the suspected abnormal internal resistance;
and (3) marking the ratio of the local abnormal consistency index of the suspected abnormal internal resistance to the maximum value of the local abnormal consistency indexes of all the suspected abnormal internal resistances as the abnormal consistency index of the suspected abnormal internal resistance.
Further, the method for determining the first abnormal internal resistance data according to the abnormal consistency index comprises the following specific steps:
and recording the lithium battery internal resistance data with the abnormal consistency index smaller than the first abnormal threshold value as first abnormal internal resistance data.
Further, the determining the adjacent quality problem cluster according to the quality problem cluster, and determining the evaluation data set according to the quality problem cluster and the first abnormal internal resistance data contained in the adjacent quality problem cluster, includes the following specific methods:
Marking the quality problem cluster with the closest cluster center Euclidean distance between the cluster center and the quality problem cluster as an adjacent quality problem cluster;
The set of the quality problem cluster and all the first abnormal internal resistance data contained in the adjacent quality problem cluster is recorded as an evaluation data set.
Further, the method for determining the final quality problem clustering result and finishing the tracing of the production quality of the lithium battery embedded with the RFID according to the inter-cluster difference comprises the following specific steps:
Combining the quality problem clusters with the inter-cluster difference less than the first difference threshold with the adjacent quality problem clusters determined by the quality problem clusters to obtain a final quality problem clustering result;
taking the cluster center of the quality problem cluster with the largest concentration degree of the density center as the cluster center of the combined quality problem cluster, checking the production process of the lithium battery corresponding to the cluster center of each quality problem cluster in the final quality problem clustering result, and determining the problem link in the production process of the lithium battery;
All the lithium batteries corresponding to the first abnormal internal resistance data contained in the quality problem cluster have the same problems in the corresponding links, and the lithium batteries with the same problems are recalled and processed in a centralized manner.
The beneficial effects of the invention are as follows:
The method comprises the steps of clustering internal resistance data of a battery through different quality problems, obtaining concentration degree of a density center according to the size of the cluster and the distance from the internal resistance data contained in the cluster to a cluster center, distinguishing the internal resistance data of a normal battery and abnormal internal resistance data through the concentration degree of the density center, obtaining an abnormal consistency index according to consistency between concentration degree of the density center of neighborhood data of suspected abnormal internal resistance and correlation between the battery temperature through analysis of influence of the battery temperature on change of the internal resistance data of the battery, eliminating abnormal internal resistance data of the battery due to temperature influence through the abnormal consistency index, determining a quality problem cluster, evaluating a clustering result of the abnormal data according to difference between the different quality problem clusters, merging the quality problem clusters with small difference, preventing division redundancy of the quality problem clusters, finally determining a final quality problem clustering result according to the merged quality problem cluster, completing production quality of the lithium battery with embedded RFID, solving the problem that the production quality is not high due to the fact that the correlation between the battery data is ignored in the process of the production quality of the battery is traced back, and improving the production quality.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for tracing production quality of an embedded RFID new energy battery according to an embodiment of the present invention;
Fig. 2 is a flowchart of the first abnormal internal resistance data acquisition.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a method for tracing production quality of an embedded RFID new energy battery according to an embodiment of the invention is shown, and the method comprises the following steps:
and S001, acquiring the internal resistance data, the temperature data and LOF outliers of the internal resistance data of all lithium batteries in the same batch with the lithium batteries with the quality problems according to the lithium batteries with the quality problems detected in the sampling inspection process.
The new energy batteries are various in variety, and in this embodiment, lithium batteries are taken as an example for analysis.
In the production process of the lithium battery, an RFID tag is embedded in the lithium battery, and internal resistance data and lithium battery temperature data of the lithium battery in the production process are recorded through the RFID tag.
In the lithium battery manufacturing process, it is generally necessary to perform sampling inspection on the manufactured lithium battery, and perform charge-discharge cycle test on the sampled lithium battery, that is, detect the internal resistance of the lithium battery, so as to evaluate whether the performance and the service life of the lithium battery meet the requirements. When the lithium batteries with quality problems are found in the sampling detection process, the RFID tag is used for acquiring the internal resistance data and the temperature data of all lithium batteries in the same batch with the lithium batteries with quality problems.
When the production link has problems, the partial internal resistance data of the lithium batteries in the same batch have larger difference, the numerical distribution of the internal resistances of the lithium batteries is more chaotic, and the fluctuation is larger. For example, materials with different components have different internal resistance rates, and if the quality of part of raw materials is uneven or impurities exist, the material components of the positive and negative electrodes in different lithium batteries in the same batch are inconsistent, so that larger difference in internal resistance data occurs.
Therefore, the LOF outlier factor of each internal resistance data can be obtained by using the LOF anomaly detection algorithm to perform anomaly detection on the internal resistance data of all lithium batteries in the same batch of lithium batteries with quality problems according to the characteristic that the production quality problems of the lithium batteries change the stability of the internal resistance data. The LOF outlier factor is an index calculated by the LOF algorithm and is used for representing the abnormal degree of the data relative to the adjacent points, when the LOF outlier factor is larger, the abnormal degree of the internal resistance data is larger, and the LOF abnormality detection algorithm is a known technology and is not repeated.
So far, obtaining the internal resistance data, the temperature data and the LOF outlier factor of the internal resistance data of all lithium batteries in the same batch with the lithium batteries with quality problems.
Step S002, screening and clustering the internal resistance data according to LOF outlier factors of the internal resistance data, obtaining a cluster, determining the radius of the cluster, obtaining the density center aggregation degree of the internal resistance data according to the internal resistance data contained in the cluster and the radius of the cluster, determining the density concentration degree of the cluster, determining the internal resistance data without quality problems according to the density concentration degree, and determining the suspected abnormal internal resistance data.
In order to prevent the lithium battery with the quality problem from affecting the lithium battery production quality traceability result, which is inevitably caused in the production process, the internal resistance data with the LOF outlier factor larger than a first preset threshold value is removed, and analysis is not performed in the subsequent steps. Wherein the first preset threshold has an empirical value of 0.8.
When a problem occurs in a certain production link of the lithium battery in a period of time, the internal resistance data of the lithium battery produced in the period of time generally fluctuates in a data distribution range, and the local density of the internal resistance data of the lithium battery is higher in the data distribution range, so that the abnormal internal resistance data cannot be screened out only by using an abnormal detection algorithm, and the abnormal data with higher local density is easy to be misjudged as normal data.
And clustering the rest internal resistance data by using a density peak value clustering algorithm, and taking the variance of the removed internal resistance data as the cutoff distance of the density peak value clustering algorithm to obtain a clustering cluster. The clustering cluster is obtained by using a density peak clustering algorithm, which is a known technology and will not be described in detail.
And recording the average value of Euclidean distances from all internal resistance data contained in the cluster to the cluster center as the radius of the cluster.
And acquiring the concentration degree of the density center of the internal resistance data according to the internal resistance data contained in the cluster and the radius of the cluster.
Wherein, Is the firstInternal resistance data of individual lithium batteriesIs the degree of concentration of density centers; Is internal resistance data Cluster whereThe number of internal resistance data contained therein; Is internal resistance data And (3) withCluster in which to locateIs a cluster core of (2)A Euclidean distance between them; Is internal resistance data Cluster whereIs set, and the radius of (a) is set.
When the number of the internal resistance data contained in the cluster where the internal resistance data is located is larger and the radius of the cluster is smaller, the density center aggregation degree of the internal resistance data is larger if the cluster where the internal resistance data is located is denser, and at the moment, the reliability of the clustering result of the internal resistance data is higher, and the possibility that the lithium battery corresponding to the internal resistance data has no quality problem is higher.
So far, the concentration degree of the density centers of all the internal resistance data in all the cluster clusters is obtained.
In order to facilitate distinguishing the internal resistance data of the lithium battery without quality problems and with quality problems, the average value of the concentration degree of the density centers of all the internal resistance data contained in the cluster is taken as the density concentration degree of the cluster.
The internal resistance data contained in the cluster with the largest density concentration is taken as the internal resistance data without quality problems, and the internal resistance data not without quality problems is recorded as suspected abnormal internal resistance data.
So far, the density center aggregation degree of all the internal resistance data in all the clusters, the internal resistance data without quality problems and the suspected abnormal internal resistance data are obtained.
Step S003, obtaining neighborhood data of suspected abnormal internal resistances, obtaining an internal resistance distance sequence and a temperature distance sequence of the suspected abnormal internal resistances, obtaining a temperature association degree of the suspected abnormal internal resistances, obtaining a variation coefficient of a density center aggregation degree of the suspected abnormal internal resistances, obtaining local abnormal consistency indexes of the suspected abnormal internal resistances according to the temperature association degree of the suspected abnormal internal resistances and the variation coefficient of the density center aggregation degree of the suspected abnormal internal resistances, obtaining abnormal consistency indexes of the suspected abnormal internal resistances according to the local abnormal consistency indexes of all the suspected abnormal internal resistances, and determining first abnormal internal resistance data according to the abnormal consistency indexes.
After the lithium battery is manufactured, quality detection of the lithium battery is required. In the quality detection of lithium batteries, in order to detect the internal resistance of lithium batteries, the lithium batteries need to be subjected to tests such as a charge-discharge cycle test, a high-rate charge-discharge test, a high-temperature test and the like. The tests all relate to the processes of chemical reaction, physical change, energy conversion and the like, so that the lithium battery subjected to quality detection can generate heat release phenomena of different degrees, the temperature of the lithium battery is increased, the internal resistance of the test is changed, the abnormal degree judgment of the internal resistance of the lithium battery is affected, and the quality tracing of the lithium battery is further affected.
And acquiring the number of the suspected abnormal internal resistance data.
There is a correlation between the resistance and the temperature of a lithium battery, and when the temperature of the lithium battery is low, the internal resistance of the lithium battery generally increases, and when the temperature of the lithium battery is high, the internal resistance of the lithium battery generally decreases.
Based on the correlation between the resistance and the temperature, the second preset threshold value internal resistance data with the minimum Euclidean distance from the internal resistance data of the suspected abnormal internal resistance in the cluster where the suspected abnormal internal resistance is located is recorded as neighborhood data of the suspected abnormal internal resistance. Wherein the empirical value of the second preset threshold is 5.
Sequencing the internal resistance data of the suspected abnormal internal resistance and the neighborhood data of the suspected abnormal internal resistance according to the sequence from small to large of the Euclidean distance between the internal resistance data of the suspected abnormal internal resistance and the internal resistance data of the suspected abnormal internal resistance, and obtaining an internal resistance distance sequence of the suspected abnormal internal resistance. And arranging the temperature data of the suspected abnormal internal resistance and the temperature data corresponding to the neighborhood data of the suspected abnormal internal resistance according to the same sequence to obtain a temperature distance sequence of the suspected abnormal internal resistance.
And (3) counting the Pearson phase relation number between the internal resistance distance sequence and the temperature distance sequence of the suspected abnormal internal resistance as the temperature association degree of the suspected abnormal internal resistance.
When the temperature association degree of the suspected abnormal internal resistance is larger, the correlation between the internal resistance data corresponding to the neighborhood data of the suspected abnormal internal resistance and the lithium battery temperature is higher, and the possibility that the suspected abnormal internal resistance is the lithium battery internal resistance data affected by the temperature is higher.
The density center aggregation degree of the lithium battery internal resistance data with the same kind of problems should have larger consistency, so when the density center aggregation degree of the neighborhood data with the suspected abnormal internal resistances is more similar, the suspected abnormal internal resistances are more likely to be the lithium battery internal resistance data with the same kind of quality problems.
And obtaining a variation coefficient of the density center aggregation degree of the suspected abnormal internal resistance according to the suspected abnormal internal resistance and the density center aggregation degree of the neighborhood data of the suspected abnormal internal resistance. The method for calculating the coefficient of variation is a well-known technique and will not be described in detail.
When the variation coefficient of the density center aggregation degree of the suspected abnormal internal resistance is larger, the numerical distribution of the density center aggregation degree of the suspected abnormal internal resistance and the neighborhood data is more discrete, and the probability that the suspected abnormal internal resistance and the suspected abnormal internal resistance corresponding to the neighborhood data are abnormal in the lithium battery internal resistance data caused by the same type of problem is smaller.
Obtaining local abnormal consistency indexes of the suspected abnormal internal resistances according to the temperature association degree of the suspected abnormal internal resistances and the variation coefficient of the density center aggregation degree of the suspected abnormal internal resistances, and obtaining the abnormal consistency indexes of the suspected abnormal internal resistances according to the local abnormal consistency indexes of all the suspected abnormal internal resistances.
Wherein, Is suspected of abnormal internal resistanceIs a local abnormal consistency index of (2); Is suspected of abnormal internal resistance A coefficient of variation of the degree of density center aggregation; Is suspected of abnormal internal resistance Temperature-related degree of (2); Is suspected of abnormal internal resistance Abnormal consistency index of (2); is the maximum value of the local abnormal consistency indexes of all suspected abnormal internal resistances.
When the temperature association degree of the suspected abnormal internal resistance is larger and the variation coefficient of the density center aggregation degree of the neighborhood data of the suspected abnormal internal resistance is smaller, the local abnormal consistency index of the suspected abnormal internal resistance is larger, and the suspected abnormal internal resistance is more likely to be normal data which is divided into abnormal data under the influence of the temperature.
When the local abnormal consistency index of the suspected abnormal internal resistance is larger than the maximum value of the local abnormal consistency indexes of all the suspected abnormal internal resistances, the larger the abnormal consistency index of the suspected abnormal internal resistance is, namely the more possible the suspected abnormal internal resistance is the abnormal data obtained after being influenced by temperature, the more possible the lithium battery corresponding to the suspected abnormal internal resistance is normal and has no production quality problem.
And setting a first abnormal threshold value, and recording lithium battery internal resistance data with the abnormal consistency index smaller than the first abnormal threshold value as first abnormal internal resistance data. Wherein the empirical value of the first anomaly threshold value is 0.7. The first abnormal internal resistance data acquisition flowchart is shown in fig. 2.
So far, the first abnormal internal resistance data is obtained.
Step S004, clustering the first abnormal internal resistance data, determining a quality problem cluster, determining an adjacent quality problem cluster according to the quality problem cluster, determining an evaluation data set according to the quality problem cluster and the first abnormal internal resistance data contained in the adjacent quality problem cluster, determining the division independence degree of the quality problem cluster according to the first abnormal internal resistance data contained in the evaluation data set, obtaining the inter-cluster difference degree of the quality problem cluster according to the division independence degree of the quality problem cluster and the first abnormal internal resistance data contained in the quality problem cluster, determining a final quality problem clustering result according to the inter-cluster difference degree, and finishing the production quality tracing of the lithium battery embedded with RFID.
When different abnormal problems occur in different production links in the process of manufacturing the lithium battery, the lithium battery has quality problems of different degrees and different characteristics, and the abnormal value fluctuation degree and fluctuation direction of the internal resistance data of the lithium battery are different. Therefore, when the first abnormal internal resistance data are clustered, the first abnormal internal resistance data corresponding to the lithium batteries with different quality problems are divided into different clusters.
Clustering the first abnormal internal resistance data by using a density peak clustering algorithm, and taking the variance of the first abnormal internal resistance data as the cutoff distance of the density peak clustering algorithm to obtain a cluster. And respectively marking each cluster with the contained data as the first abnormal internal resistance data as a quality problem cluster. The clustering using the density peak clustering algorithm is a known technique, and will not be described in detail.
In order to prevent the division redundancy of quality problem clusters, a plurality of quality problem clusters are corresponding to one quality problem, and the cluster result is evaluated by using a Rand index.
First, cluster centers and quality problems are clusteredThe cluster center of the cluster closest to the nearest quality problem cluster is marked as a neighboring quality problem cluster. When a plurality of cluster centers and quality problem clusters are containedWhen the cluster center of the cluster is closest to the nearest quality problem cluster, only the quality problem cluster with the smallest cluster radius is marked as the adjacent quality problem cluster。
Clustering quality problemsAnd (3) withThe set of all the first abnormal internal resistance data contained in the table is recorded as an evaluation data set.
Respectively by quality problem clustersAnd (3) withThe cluster center of the cluster is the initial cluster center of the cluster, all first abnormal internal resistance data contained in the evaluation data set are clustered by using a K-means clustering algorithm, the first abnormal internal resistance data are clustered into two types, and a reference cluster is obtained,. Computing quality problem clustersAndClustering results with referenceAndRand index between. The Rand index between two independent clustering results is calculated as a known technology, and is not described in detail.
The Rand index may reflect the similarity between the two sets of clustering results, the greater the Rand index, the more similar the two sets of clustering results divide the data.
Clustering quality problemsAndClustering results with referenceAndRand index between are quality problem clustersDegree of independence of division of (a)。
So far, the division independence degree of the quality problem clusters is obtained.
And acquiring the inter-cluster difference degree of the quality problem clusters according to the partition independence degree of the quality problem clusters and the first abnormal internal resistance data contained in the quality problem clusters.
Wherein, Is a quality problem clusterIs a cluster-to-cluster degree of difference; Is a quality problem cluster The degree of independence of the partitions; Is a quality problem cluster Information entropy of first abnormal internal resistance data contained in the first abnormal internal resistance data; is an exponential function based on natural constants.
When the information entropy of the first abnormal internal resistance data contained in the quality problem cluster is larger, the first abnormal internal resistance data contained in the quality problem cluster is more disordered, the difference degree between the quality problem cluster and the clusters adjacent to the quality problem cluster is smaller, the aggregation degree between the quality problem cluster and the clusters adjacent to the quality problem cluster is lower, the difference degree between different quality problem clusters is lower, and the clustering result is more unreliable.
Combining quality problem clusters with the inter-cluster difference less than a first difference threshold with adjacent quality problem clusters determined by the quality problem clusters in sequence, taking the cluster center of the quality problem cluster with the largest concentration degree of the density center as the cluster center of the combined quality problem cluster, and obtaining a final quality problem clustering result. Wherein the first difference threshold has an empirical value of 0.5.
And checking the production process of the lithium battery corresponding to the cluster center of each quality problem cluster in the final quality problem cluster result to determine the problem links in the production process of the lithium battery. All lithium batteries corresponding to the first abnormal internal resistance data contained in the quality problem cluster have the same problems in the corresponding links, and the lithium batteries are recalled and processed in a centralized manner.
Thus, the production quality tracing of the lithium battery embedded with the RFID is completed.
The foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411345815.3A CN118863929B (en) | 2024-09-26 | 2024-09-26 | A production quality traceability method for new energy batteries with embedded RFID |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411345815.3A CN118863929B (en) | 2024-09-26 | 2024-09-26 | A production quality traceability method for new energy batteries with embedded RFID |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118863929A CN118863929A (en) | 2024-10-29 |
| CN118863929B true CN118863929B (en) | 2024-12-03 |
Family
ID=93177477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411345815.3A Active CN118863929B (en) | 2024-09-26 | 2024-09-26 | A production quality traceability method for new energy batteries with embedded RFID |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118863929B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115902675A (en) * | 2022-11-25 | 2023-04-04 | 中国汽车工程研究院股份有限公司 | Power battery risk tracing method based on equivalent internal resistance consistency |
| CN116703287A (en) * | 2023-06-16 | 2023-09-05 | 深圳市汇和通传感技术有限公司 | Ultra-high temperature material traceability system based on radio frequency identification technology |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112858919B (en) * | 2021-01-18 | 2022-04-01 | 北京理工大学 | A method and system for on-line fault diagnosis of battery system based on cluster analysis |
| CN116502112B (en) * | 2023-06-29 | 2023-10-24 | 深圳市联明电源有限公司 | New energy power supply test data management method and system |
| CN116628617B (en) * | 2023-07-25 | 2023-09-22 | 值数科技(北京)有限公司 | Method for realizing miniature strain monitoring based on nanocomposite |
| CN117805629A (en) * | 2024-01-02 | 2024-04-02 | 中国电力科学研究院有限公司 | Energy storage system lithium-ion battery abnormality identification method, system, equipment and media |
-
2024
- 2024-09-26 CN CN202411345815.3A patent/CN118863929B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115902675A (en) * | 2022-11-25 | 2023-04-04 | 中国汽车工程研究院股份有限公司 | Power battery risk tracing method based on equivalent internal resistance consistency |
| CN116703287A (en) * | 2023-06-16 | 2023-09-05 | 深圳市汇和通传感技术有限公司 | Ultra-high temperature material traceability system based on radio frequency identification technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118863929A (en) | 2024-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913B (en) | A method and device for diagnosing anomalous household-substation relations in a station area | |
| CN116502112B (en) | New energy power supply test data management method and system | |
| CN113406502B (en) | Defective battery screening method, apparatus and medium based on machine learning | |
| CN114114039B (en) | A method and device for evaluating the consistency of single cells of a battery system | |
| CN117313016B (en) | New energy power transaction spot electricity price difference data processing method | |
| CN112327189B (en) | Comprehensive judging method for health state of energy storage battery based on KNN algorithm | |
| CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
| CN102749585A (en) | Multi-layer SVM (support vector machine) based storage battery on-line monitoring method | |
| CN117113235B (en) | Cloud computing data center energy consumption optimization method and system | |
| CN117872159B (en) | Lithium battery cell charge and discharge abnormality detection method and system based on data analysis | |
| CN112287980B (en) | Power battery screening method based on typical eigenvectors | |
| CN118033427A (en) | A battery pack inconsistency diagnosis method | |
| CN117805649A (en) | Method for identifying abnormal battery cells based on SOH quantized battery capacity attenuation | |
| CN112305442A (en) | Power battery SOH rapid estimation method based on kmeans clustering | |
| CN118863929B (en) | A production quality traceability method for new energy batteries with embedded RFID | |
| CN117619764A (en) | Lithium ion battery screening and analyzing method based on formation curve | |
| CN118503894B (en) | Lithium battery quality detection system based on process index data analysis | |
| CN117649059B (en) | Result evaluation optimization method for digital breeding process | |
| CN113204894A (en) | Construction method and application of electric energy metering abnormity diagnosis model | |
| CN118068192A (en) | Battery running state evaluation method based on large amount of data of energy storage system | |
| CN113705920B (en) | Method and terminal equipment for generating water consumption data sample set of thermal power plant | |
| CN118296557B (en) | Water ecology intelligent monitoring method and system based on distributed sensing unit | |
| CN118965825B (en) | AGM separator thermal stability monitoring method and system | |
| CN118568455B (en) | Network security big data state evaluation method based on pattern recognition | |
| CN116577685B (en) | Health detection method, data processing method, related device, equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |