Research On The Technology Of Automatic Classification Of X-ray Cylinder Liner Defect Based On Grey Theory

Cylinder liner as a key component of internal combustion engine,domestic and foreign manufacturers and users of their production quality put forward strict requirements.At present,the common methods for detecting cylinder liner defects are eddy current testing and X-ray inspection.However,due to skin effect eddy current method can only detect the cylinder liner surface or near surface defects,while the deep defects is difficult to detect.After the eddy current testing of the cylinder liner may be hidden into the subsequent assembly of the internal combustion engine production.Currently,X-ray detection methods rely mostly on human eye recognition.In the face of mass production of cylinder liner products,human eye interpretation method is not only slow to detect,high labor costs,and susceptible to subjective factors,reliability is not high,is not conducive to the late analysis of defects and casting technology and technology improve.Based on the above background,this paper presents an automatic detection technology of X-ray cylinder liner based on gray theory.In view of the difficult problem of defect feature extraction,this paper first uses the simplified B-type correlation to detect the edge of the cylinder liner and defect small pieces.Then,the edge of the cylinder liner is filled with the boundary filling method,and the defective small pieces are extracted.Finally,the defective small pieces are pretreated by morphological swelling and the defects in the cylinder liner are extracted.The difficulty of defect feature extraction is how to extract defective small pieces.In this paper,we analyze the defective region belongs to the high frequency component,first calculate the mean value of the center pixel and the neighborhood of the 8 neighborhood pixels to construct a new sub-image matrix,and then enhance the high frequency component,and then use the matrix mean operator and simplify the B Associative degree of the combination of the method to detect the edge of the cylinder liner and defect small pieces,accurate extraction of the cylinder liner defects.Defect detection of products on the one hand to ensure the quality of the product,on the other hand,the classification of waste defects will help identify the cause of defects,improve the cylinder liner casting production process,improve product qualification rate.In this paper,the fuzzy fuzzy identification method is used to classify the defects.Based on the characteristic attributes of defects,the membership thresholds of stomachs,shrinkage,shrinkage and crack are discriminated and compared,and the categories of defects are judged.The experimental results show that the method proposed in this paper realizes the X-ray automatic detection and identification of the cylinder liner defect,and can quickly and accurately extract the defects of the cylinder liner and realize the rapid classification of the defect category.The research of related technology in this paper is helpful to the development of X-ray automatic recognition technology in China.