CN-121073266-B - Lithium battery diaphragm production quality tracing method and system based on Internet of things

CN121073266BCN 121073266 BCN121073266 BCN 121073266BCN-121073266-B

Abstract

The application discloses a lithium battery diaphragm production quality tracing method and system based on the Internet of things, and relates to the field of lithium battery diaphragm production quality tracing; determining key nodes of lithium battery diaphragm production, setting a unique quality safety traceability code for each key node, constructing a quality anomaly knowledge graph by combining historical diaphragm production information and the quality safety traceability codes, inputting real-time diaphragm production information into the quality anomaly knowledge graph to obtain quality anomaly parameters, performing reliability verification on the quality anomaly parameters, determining quality anomaly causes by using a root cause analysis model, generating compensation parameters according to the quality anomaly causes, performing parameter compensation on the quality anomaly parameters based on the compensation parameters, and performing quality traceability in the quality anomaly knowledge graph according to the compensated quality anomaly parameters. The application can effectively improve the management efficiency of lithium battery diaphragm production.

Inventors

WANG CONG
WANG HONGBING
JIANG HUI
BIAN GUANGYU
DU FEIYUE
ZHANG YUE

Assignees

合肥惠强新能源材料科技有限公司

Dates

Publication Date: 20260508
Application Date: 20250710

Claims (7)

1. The lithium battery diaphragm production quality tracing method based on the Internet of things is characterized by comprising the following steps of: Collecting historical diaphragm production information and real-time diaphragm production information; Determining key nodes for lithium battery diaphragm production according to the historical diaphragm production information, and setting a unique quality safety traceability code for each key node; combining the historical diaphragm production information with the quality safety traceability code and constructing a quality anomaly knowledge graph by utilizing a cut Bayesian estimation and prior algorithm; inputting the real-time diaphragm production information into the quality abnormality knowledge graph to obtain quality abnormality parameters; performing credibility verification on the quality anomaly parameters; If the quality anomaly parameters pass the credibility verification, determining quality anomaly causes by utilizing a root cause analysis model, and generating compensation parameters according to the quality anomaly causes; Performing parameter compensation on the quality abnormal parameters based on the compensation parameters, and performing quality tracing in a quality abnormal knowledge graph according to the compensated quality abnormal parameters; The key nodes comprise production quality nodes and production flow nodes, the key nodes for lithium battery diaphragm production are determined according to the historical diaphragm production information, and unique quality safety traceability codes are set for each key node, and the method comprises the following steps: Selecting production parameter data and quality indexes in the historical diaphragm production information; calculating a correlation coefficient between the production parameter data and the quality index by using a pearson correlation coefficient; Taking a production node corresponding to the production parameter data with the association coefficient exceeding a preset association coefficient as a production quality node; Determining the process flow of diaphragm production according to the historical diaphragm production information, wherein each process flow corresponds to a process procedure and a process node; Drawing a process flow chart of each process flow by combining the process procedure corresponding to each process flow and the process node; determining the completion time of each process node; Determining a production flow node according to the process flow chart and the completion time; Distributing unique quality safety traceability codes for each key node; the quality anomaly parameters comprise process anomaly parameters and equipment anomaly parameters, and the reliability verification of the quality anomaly parameters comprises the following steps: when the quality abnormal parameter is the process abnormal parameter, taking the process parameters corresponding to all the key nodes in a preset time stamp and the quality safety traceability code as a process combination parameter set; calculating a sliding window hash value of the process combination parameter set by utilizing a hash function in a preset time period; comparing the sliding window hash value with a reference process hash value, and if the sliding window hash value is not equal to the reference process hash value, determining that the quality anomaly parameter passes the credibility verification; The method further comprises the steps of: when the quality abnormal parameter is the equipment abnormal parameter, determining initial state parameter sets of all lithium battery diaphragm production equipment, and generating initial hash values based on the initial state parameter sets; Calculating an equipment state hash value of an equipment combination parameter set of the lithium battery diaphragm production equipment after each production task is completed through a hash function, wherein the equipment combination parameter set consists of a batch number of the production task and the current equipment state parameter set of the lithium battery diaphragm production equipment; And comparing the equipment state hash value with a reference equipment hash value, and if the equipment state hash value is not equal to the reference equipment hash value, determining that the quality abnormal parameter passes the credibility verification.
2. The method of claim 1, wherein said combining said historical diaphragm production information and said quality security traceback code and utilizing a cut bayesian estimation and prior algorithm to construct a quality anomaly knowledge graph comprises the steps of: extracting a quality abnormality knowledge body from the historical diaphragm production information, and constructing a quality abnormality knowledge base based on the quality abnormality knowledge body; Extracting a quality anomaly subject and a quality anomaly object from the quality anomaly knowledge base by using a preset knowledge extraction model; Storing the quality anomaly subject, the quality anomaly object and the key nodes in a triplet form; Extracting association relations among all triples by using a cut Bayes estimation and priori algorithm to generate association rules; and constructing a quality anomaly knowledge graph by combining the association rule and the triples.
3. The method according to claim 2, wherein the extracting the association relationships between all the triples using a cut bayesian estimation and a priori algorithm, generating association rules comprises the steps of: Converting the triples into transaction data sets, wherein each of the transaction data sets represents each quality anomaly case; forming the transaction data sets into item set elements, wherein each item variable in the item set elements corresponds to each transaction data set; For any item variable, calculating the occurrence times of the item variable in all item set elements to obtain experience probability; calculating the deviation and variance of the experience probability by using a cut Bayesian estimation, and adjusting the experience probability by using the deviation and the variance to obtain a probability estimation value; screening out a plurality of frequent sets by using a priori algorithm in combination with the probability estimation value; Screening out non-empty proper subsets in all the frequent sets, and generating candidate association rules between the frequent sets and the non-empty proper subsets corresponding to the frequent sets; And calculating the confidence coefficient of each candidate association rule through a preset confidence coefficient formula, and taking the candidate association rule with the confidence coefficient larger than or equal to a preset confidence coefficient threshold value as an association rule.
4. The method of claim 1, wherein determining a cause of a quality anomaly using a root cause analysis model and generating compensation parameters based on the cause of the quality anomaly comprises the steps of: Inputting the quality abnormality parameters into a root cause analysis model to determine the quality abnormality cause of the lithium battery diaphragm production; and inputting the quality abnormality cause into a preset compensation model to generate compensation parameters.
5. The method of claim 4, wherein said inputting the quality anomaly parameter into a root cause analysis model determines a quality anomaly cause for the lithium battery separator production comprises the steps of: taking the quality abnormal phenomenon corresponding to the quality abnormal parameter as a top event in the production process of the lithium battery diaphragm; inputting the top event into a fault tree logic chain of the root cause analysis model, and identifying a minimum cut set of the top event by using Boolean algebra, wherein the minimum cut set consists of basic events; Calculating basic event probability of each basic event and minimum cut set probability of each minimum cut set based on a preset probability formula; calculating the probability of occurrence of a top event by utilizing the principle of repulsion and combining the minimum cutset and the probability of the basic event; Calculating the contribution degree of each basic event probability to the occurrence probability of the top event through a preset importance analysis algorithm; And taking the corresponding basic event with the largest contribution degree as the quality abnormality cause.
6. A machine-readable storage medium having stored thereon instructions for causing a machine to perform the method of tracing the production quality of lithium battery separator based on the internet of things according to any one of claims 1 to 5.
7. Lithium battery diaphragm production quality traceability system based on thing networking, its characterized in that includes: A memory configured to store instructions, and A processor configured to recall the instructions from the memory and, when executed, enable the lithium battery separator production quality traceability method based on the internet of things according to any one of claims 1 to 5.

Description

Lithium battery diaphragm production quality tracing method and system based on Internet of things Technical Field The embodiment of the application relates to the field of lithium battery diaphragm production quality tracing, in particular to a lithium battery diaphragm production quality tracing method and system based on the Internet of things. Background The lithium battery is used as a core energy carrier in the fields of new energy automobiles, energy storage equipment, consumer electronics and the like, and the safety, stability and consistency of the lithium battery directly influence the performance of a terminal product. The lithium battery diaphragm is used as a key component in the battery and plays an important role in isolating the anode and the cathode and allowing ions to pass through, and parameters such as thickness uniformity, pore size distribution, mechanical strength and the like play a decisive role in the cycle life, charge and discharge efficiency and safety of the battery. The current lithium battery diaphragm production quality traceability work mainly depends on manual recording and local informatization systems. From the production flow, the production of lithium battery separators encompasses a number of critical processes such as polymerization, extrusion, stretching, coating, slitting, quality inspection, and the like. However, the data of each process is stored independently. The independent storage mode can generate the problem of 'information island', so that the data among lithium battery diaphragm production procedures lack full-chain real-time interconnection. When the production quality of the lithium battery diaphragm is comprehensively analyzed and traced, a complete data chain is difficult to obtain, so that the abnormal position in the production process of the lithium battery diaphragm cannot be accurately positioned, and the management efficiency of the production of the lithium battery diaphragm is further affected. For example, in actual production, temperature changes in the extruder may affect the stretching rate of the subsequent stretching process, which in turn may further affect the coating effect of the coating solution on the separator. Meanwhile, the difference of the components of the coating liquid can be caused by the difference of the material batches, so that the quality of the diaphragm is influenced. However, due to the lack of an effective cross-process correlation analysis mode, when the quality of the diaphragm is abnormal, it is difficult to quickly and accurately locate which process or which parameter has a problem, so that the efficiency of quality tracing is low, and the management efficiency of the production of the lithium battery diaphragm is affected. There is currently no better solution to the above problems. Disclosure of Invention The embodiment of the application provides a lithium battery diaphragm production quality tracing method and system based on the Internet of things, which are used for improving the management efficiency of lithium battery diaphragm production. In order to achieve the above purpose, the embodiment of the present application adopts the following technical scheme: In a first aspect, a method for tracing production quality of a lithium battery diaphragm based on the internet of things is provided, the method comprising: Collecting historical diaphragm production information and real-time diaphragm production information; Determining key nodes for lithium battery diaphragm production according to the historical diaphragm production information, and setting a unique quality safety traceability code for each key node; combining the historical diaphragm production information with the quality safety traceability code and constructing a quality anomaly knowledge graph by utilizing a cut Bayesian estimation and prior algorithm; inputting the real-time diaphragm production information into the quality abnormality knowledge graph to obtain quality abnormality parameters; performing credibility verification on the quality anomaly parameters; If the quality anomaly parameters pass the credibility verification, determining quality anomaly causes by utilizing a root cause analysis model, and generating compensation parameters according to the quality anomaly causes; And carrying out parameter compensation on the quality abnormal parameters based on the compensation parameters, and carrying out quality tracing in a quality abnormal knowledge graph according to the compensated quality abnormal parameters. In a possible implementation manner of the first aspect, the key nodes include a production quality node and a production flow node, the determining key nodes for lithium battery diaphragm production according to the historical diaphragm production information, and setting a unique quality security traceability code for each key node includes the following steps: Selecting production parameter data and quality indexes