Workpiece surface defect detection method and system based on deep learning

Abstract

The invention discloses a workpiece surface defect detection method and system based on deep learning, and the method comprises the steps: obtaining sample pictures of various defect types of a product to generate a training sample set, the defect types at least comprising scratches, rubbing, abrasion, bumping, pits, white dots and watermarks; according to the defect target detection method, a deep learning algorithm based on an image is used for carrying out defect detection on a product of a customer, the target detection algorithm focuses on defects, the morphological contour and characteristics of the target detection algorithm have a certain rule and range on a two-dimensional image, and a sample distribution data set about each defect of an aluminum plate can be established; the feature distribution of the sample sets on the two-dimensional image is studied through a neural network algorithm, a mathematical model can be established, the input of the model is a product image collected by a client on site, and the coordinates of possibly defective points in the image can be output through model calculation. Whether the product has defects or not can be judged by screening the results.

Description

technical field [0001] The invention relates to the technical field of defect detection, in particular to a method and system for detecting surface defects of workpieces based on deep learning. Background technique [0002] With the rapid development of the industry, people pay more and more attention to the quality of products, and the requirements are becoming more and more strict. Because products often have some defects in the production process, these defects have a certain degree of randomness, that is, the defect types, shapes and sizes are different. Therefore, product surface defect detection, as one of the most important processes in the production process, will directly affect the Product quality and user experience. [0003] Previously, most of the defects of industrial parts were detected by manual visual quality inspection. However, this method has the following defects: low efficiency: the efficiency of inspecting parts actually tests a person's proficiency....

AI Technical Summary

Problems solved by technology

However, this method has the following defects: Low efficiency: the efficiency of inspecting parts actually tests a person's proficiency. Longer working hours will have higher detection efficiency, but as working hours increase, personal fatigue and laziness will also increase. increase, which will reduce the detection efficiency of quality inspectors; risk of missed inspection: as the working hours increase, personal attention will also decrease, which will bring the risk of missed inspection, and the machine will not be tired, so there is no such problem; it is difficult to define : Since the size of industrial defects is at the millimeter level, it is difficult to manually identify millimeter-sized defects with the naked eye; quantitative analysis is difficult: manual determination of defects will not be able to carry out data statistics, which will hinder the intelligentization of factories; high labor costs

[0005] However, the existing deep learning algorithms have weak detection ability and slow operation speed. It is easier to deal with relatively simple deep learning problems such as detection, detection number, and defects of regular shape and size. However, in the face of industrial quality inspection field, the accuracy and speed are low when detecting defects on complex surfaces

Images