Copper-clad plate surface defect visual online detection method and device based on deep learning

Abstract

The invention relates to a copper-clad plate surface defect visual online detection method based on deep learning, which comprises the following steps: continuously scanning a copper-clad plate passing through a conveyor belt at a constant speed line by line through a linear array scanning camera to complete image acquisition to obtain a complete and clear copper-clad plate image; carrying out defect detection on the acquired copper-clad plate image, if a defect is detected, marking the copper-clad plate as a defective copper-clad plate and giving an alarm, and simultaneously intercepting a defect image in the copper-clad plate; for defect images, adopting a deep neural network learning method, building a TensorFlow framework for defect classification, distinguishing different types of defects, and giving a targeted repair scheme; and displaying defect detection and defect classification results on the display screen, so that field staff can conveniently check the real-time state of the copper-clad plate in time and carry out subsequent processing. The invention further provides a corresponding device, and the problems that an existing copper-clad plate defect classification system is high in dependence on manpower and equipment, low in accuracy and long in consumed time can be solved.

Description

technical field [0001] The invention belongs to the technical field of surface defect detection, and in particular relates to a method and device for visual online detection of surface defects of copper clad laminates based on deep learning. Background technique [0002] Copper-clad laminate is the substrate material in the manufacture of printed circuit boards. With the continuous improvement of technology and the development of electronic information and communication industries, the position of copper-clad laminate in the electronic information industry is becoming more and more important. It involves almost all electronic products. information products. In the production process of copper clad laminates, due to factors such as the production environment and manufacturing industry, different types of defects appear on the surface of copper clad laminates, which directly affect its quality, safety and performance. Classifying the defects on the surface of copper clad lami...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of the above-mentioned prior art, the purpose of the present invention is to provide a method and device for visual online detection of surface defects of copper-clad laminates based on deep learning, so as to solve the problem that the current defect classification system of copper-clad laminates is highly dependent on labor and equipment, and is accurate. The problem of low rate and long time

Images