Defect Detecting And Classification System Of The Lithium Battery Pole Piece Based On Machine Vision

With the development of the new energy industry,the demand and quality requirement oflithium batteries are getting higher and higher.As an important part of the lithium battery,polepiece quality will affect the performance and service life of lithium battery seriously,and evenlead to safety incidents.It is necessary to detect pole piece defect to avoid these problems,atthe same time,identify the type of defects to adjust the production process in time to preventthe defect from recurring.However,traditional detection method has been unable to meet theneeds of industrial development,so a defect detection and classification system of pole pieceis designed,and it has a great significance to improve the inspection efficiency and reduceproduction costs.In this paper,lithium battery pole piece is taken as the research object.According to themanufacturing process of pole piece,the causes and characteristics of defect are analyzed,adetection and classification system of the pole piece defect is designed in combination withmachine vision technology.According to the system demand,the type of equipment isdetermined to acquire pole piece images.Due to the influence of noise and mechanicalvibration,the preprocessing method of bilateral filter and grayscale transformation is used toimprove the image quality.With the help of Sobel edge detection and adaptive threshold,thepole defect target is isolated,and the image further processed by using morphology,then thedetection is completed by marking defect.In the process of studying defect characteristics,animproved K-means algorithm is applied to complete SURF feature clustering,and it quantifiedas BoF-SURF feature.In order to solve the problem of low classification accuracy caused bythe effect of illumination and the incomplete description of defect by a single feature,theBoF-SURF feature and grayscale feature are weighted fusion.Finally,the fusion feature isused as the input of SVM for defect classification,and an improved particle swarmoptimization method is adopted to optimize the parameters.Experimental results show that theaccuracy of the algorithm in this paper is 94.43%,compared with the two features usedseparately,the accuracy is increased by 5.23%?12.2%,and it has better classificationperformance.The system software is designed on the basis of algorithm research and functionalrequirement,it has functions such as defect detection and classification,result storage,andhistorical query.The verification results show that the system can effectively realize thedetection and classification of pole piece defects and have certain feasibility.