Research On Cylinder Liner Defects' Detection Technology Based On Compressive Sensing

The cylinder liner is an important core component of an automobile engine.In the production process,cylinder liners contain defects such as air holes,cracks,and shrinkage holes due to various reasons.Defective cylinder liners can have unpredictable consequences once they enter the market.Therefore,before the cylinder liner product leaves the factory,it must carry out necessary defect detection.At present,because of the lack of a complete automatic detection system for the detection of cylinder sleeve defects,it is still relying on manual detection.This method is time consuming,laborious and has low detection accuracy.Therefore,it is very necessary to develop an automatic and rapid defect detection system that replaces manual detection.The cylinder sleeve defect detection system of this paper uses X-ray detection principle to design the flow structure of the defect detection system.According to the actual production of the enterprise,a complete set of cylinder sleeve automatic defect inspection line was built,and the selection of major modules in the assembly line was analyzed and discussed.In the detection algorithm,the image of the cylinder liner is firstly acquired by the X-ray imaging system in the protective imaging room;then,the image is denoised and enhanced by multiple frame superposition and histogram equalization;finally,the theory of compressed sensing is used.The defect of the preprocessed cylinder liner image is discriminated.In compression-sensing algorithm,firstly,the improved K-SVD algorithm is used to train the redundant dictionary of the cylinder liner sample image;then,the sample is measured by using the adaptive measurement matrix composed of Walsh-Hadamard matrix to measure the cylinder liner image;For the reconstruction of cylinder liner images,comparing the advantages and disadvantages of the seven mainstream image reconstruction algorithms,the matching tracking algorithm with compressible sampling is used to reconstruct the cylinder liner images and obtain the sparse coefficients.The sparse coefficients in the reconstructed images are used to determine the defect types.Use the assembly line sorting system to sort the cylinder liners with different defects to complete the defect detection.The test results show that the system can realize the automatic,rapid and accurate judgment of cylinder liner defects,and solve the worries of the production enterprises.