Industrial hole wall defect detection system based on AI and identification algorithm

Abstract

The invention relates to the technical field of defect detection, and in particular relates to an industrial hole wall defect detection system based on AI and an identification algorithm. The system comprises a data acquisition unit, a data preprocessing unit, a feature extraction unit, a defect detection unit and a loss function unit; the data acquisition unit is used for converting a shot target into an image signal, the data preprocessing unit is used for carrying out data augmentation on the image signal acquired by the data acquisition unit and subtracting a mean value from images in a training set and a test set, and the feature extraction unit is used for optimizing a weight coefficient and offset of each node by the images; the defect detection unit is used for determining a central point of a defect detection position according to the image features in the feature extraction unit. According to the invention, the position and the type of the defect can be obtained only by converting the picture into the image signal, naked eye observation is liberated, the detection standard is unified, the product quality consistency is ensured, and the detection speed is improved, so that the detection speed of the inner wall defect of an industrial product is improved.

Description

technical field [0001] The present invention relates to the technical field of defect detection, in particular to an AI-based industrial hole wall defect detection system and recognition algorithm. Background technique [0002] At present, most of the detection of defects on the inner wall of industrial products relies on manual work. The detection speed of this scheme is slow. At the same time, the detection results are affected by the experience, proficiency and some subjective factors of the inspectors, lacking consistency and reliability. Traditional detection of inner wall defects of industrial products The technology of this technology mainly uses the ultra-depth-of-field microscope to perform oblique viewing. This method is difficult to automate, and it will cause image distortion, low detection efficiency, and high detection error rate. At present, the deep learning method is used to detect the inner wall defects of industrial products. The method mainly Using a two-...

AI Technical Summary

Problems solved by technology

[0002] At present, most of the detection of defects on the inner wall of industrial products relies on manual work. The detection speed of this scheme is slow. At the same time, the detection results are affected by the experience, proficiency and some subjective factors of the inspectors, lacking consistency and reliability. Traditional detection of inner wall defects of industrial products The technology of this technology mainly uses the ultra-depth-of-field microscope to perform oblique viewing. This method is difficult to automate, and it will cause image distortion, low detection efficiency, and high detection error rate. At present, the deep learning method is used to detect the inner wall defects of industrial products. The method mainly Using a two-stage target detection algorithm, this method first generates a large number of candidate pictures, and then uses a convolutional neural network to classify and regress the pictures. This method is time-consuming. In view of this, we propose an AI-based industrial hole wall defect detection System and Recognition Algorithm

Images