Plastic pipe surface defect detection method and system and computer readable storage medium

Abstract

The invention discloses a plastic pipe surface defect detection method, system and equipment and a computer readable storage medium. The method comprises the steps that surface defect features corresponding to the surface image of a plastic pipe to be detected are acquired so as to obtain the defect features to be detected; and the defect features to be detected are inputted to a pre-created trained model so as to obtain the surface defect types outputted by the trained model, wherein the trained model is the model obtained by training the model to be trained created on the basis of a BP neural network algorithm by using training samples in advance, and the training samples include the historical surface defect features and the corresponding surface defect types. The highly nonlinear mapping relation of the input and the output of the BP neural network and the great fault tolerance capability, the classification capability and the self-learning capability are utilized so that the detection accuracy of the plastic pipe surface defects can be enhanced, a lot of labor resources can be saved and the detection efficiency can be greatly enhanced.

Description

technical field [0001] The invention relates to the technical field of defect detection, in particular to a method, system and equipment for detecting defects on the surface of plastic pipes, and a computer-readable storage medium. Background technique [0002] With the continuous advancement of urbanization and new industrialization, there are more and more types of plastics, and the plastic production technology is also improving. The application fields of plastic pipes are becoming more and more extensive. At the same time, the requirements for the performance and quality of plastic pipes in various fields Also getting higher and higher. However, in the injection molding process, due to poor control of injection molding conditions such as pressure, temperature, and time, changes in the rubber material, and mold damage, various defects on the surface of the plastic pipe will occur. [0003] At present, most plastic pipe manufacturers use manual visual inspection or tradit...

AI Technical Summary

Problems solved by technology

[0004] Manual visual inspection not only has a heavy workload, but also the human eye is prone to fatigue after long-term work. At the same time, it is easily affected by the subjective factors of the inspectors, and it is easy to cause missed inspection of product surface defects, which greatly reduces the surface quality of the product, so that the detection accuracy cannot be guaranteed. efficiency and precision

The traditional non-destructive testing technology is limited by the limitations of its testing principle, the defect quantitative description parameters are extremely limited, and the types of defects that can be detected are few, resulting in low detection accuracy. In addition, it is necessary to further analyze the detected defects during the detection process Only by analyzing the data can the corresponding surface defect detection results be obtained, and the traditional non-destructive testing technology cannot accurately classify the defects, so it is impossible to comprehensively evaluate the surface quality of the product

Images