Welding seam defect identification method based on improved LeNet-5 model

Abstract

The invention discloses a welding seam defect identification method based on an improved LeNet-5 model. Firstly, input of traditional convolution kernel channels of the LeNet-5 model is improved for the welding seam grayscale image, the grayscale image is converted to a color image through pseudo-color enhancement technology, and the obtained color image is used as input of a neural network; thenconvolution kernels of the LeNet-5 model are improved, and convolution kernel channels with Gabor filters are added; features obtained by the multiple channels are fused in a sixth layer of the neuralnetwork to obtain a feature set T; and finally, a SoftMax classifier is used in a seventh layer (output layer) of the neural network to obtain the defect type of a welding seam and probability of each category, to which the same belongs, to use the same to provide a reference for negative-film type determination of a film evaluator and site rework scheme formulation. According to the method, feature extraction capability of the neural network is improved, and thus a correctness rate of defect identification is improved; and an identification result is given in a form of the probability of thecertain categories to which a defect belongs, and more sufficient reference information is provided for the film evaluator.

Description

technical field [0001] The invention belongs to the technical field of weld defect recognition, and in particular relates to a weld defect recognition method based on an improved LeNet-5 model. Background technique [0002] In the field of automatic identification of weld defects, traditional methods inevitably go through the process of manually selecting features, which is time-consuming and labor-intensive, and whether the selection of features is reasonable is highly subjective, which has a great impact on the accuracy of identification. [0003] The weld seam image is a grayscale image, and the grayscale image is directly input into the neural network, and there is a problem that the original feature representation is not sufficient. [0004] Existing convolutional neural networks often rely on a single type of convolution kernel for the convolution process, which can easily lead to insufficient feature extraction, thereby affecting the accuracy of defect recognition. ...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a method for identifying weld defects based on the improved LeNet-5 model in view of the deficiencies in the prior art above, which avoids the process of manually selecting features in traditional methods; The amount of information input by the neural network is reduced. By adding the convolution channel of the Gabor filter, the improved neural network has both the traditional convolution kernel channel and the Gabor filter channel, which improves the feature extraction ability of the neural network, thereby improving the accuracy of defect identification. Correct rate; the recognition result is given by the probability that the defect belongs to a certain category, which provides more accurate reference information for reviewers

Images