Weld surface defect identification method based on image texture

Abstract

The invention provides a weld surface defect identification method based on image texture. Miniature CCD camera photographing parameters are set according to the acquisition image standard; an acquired true color image is converted into a grey-scale map, and a gray scale co-occurrence matrix is created; 24 characteristic parameters in total, including energy, contrast, correlation, homogeneity, entropy and variance, are respectively extracted in the direction of 0 degree, 45 degrees, 90 degrees and 135 degrees, and normalization processing is performed on the extracted characteristic parameters; a BP neural network is trained by utilizing a training sample image, and the number of neurons of the neural network, a hidden layer transfer function, an output layer transfer function and a training algorithm transfer function are set; test sample characteristic parameters are outputted to the trained BP neural network to perform classification and identification; and the matching degree of the test sample and different types of surface welding quality training samples is calculated so that automatic classification and identification of the test sample surface welding quality can be completed.

Description

technical field [0001] The invention relates to a method for classifying and identifying weld surface defects, in particular to an automatic classifying and identifying method based on a gray scale co-occurrence matrix and a BP neural network. This method is suitable for classification and identification of weld surface defects, and belongs to the field of non-destructive testing. Background technique [0002] Welding technology is widely used in industrial production. At present, large workpieces are mostly completed by automatic welding technology. In the automatic welding process of the production line, it is inevitable that there will be defects such as holes, welding bumps, partial welding and broken welding that affect product quality. The existence of weld surface defects will greatly reduce the safety of welded products during the service period, ranging from product failure to leakage, to serious causes of brittle fracture of the product, causing serious casualties...

AI Technical Summary

Problems solved by technology

[0004] The gray level co-occurrence matrix analysis method is widely used in the detection and classification of geology, agroforestry and medicine, but it has not been applied to the defect identification and detection of welds at present. Soh et al [Texture analysis of SAR sea iceimagery using gray level co- Occurrence matrices[J].Geoscience&Remote SensingIEEE Transactions on,1999,37(2):780-795] studied the texture characteristics of sea ice, determined the gray-level co-occurrence matrix description parameters, direction characteristics and displacement parameters of sea ice shape, and the research results It shows that the surface shape of sea ice can be quantitatively analyzed based on the gray level co-occurrence matrix

Images