Automatic welding and defect detection method based on self-learning

Abstract

The invention discloses an automatic welding and defect detection method based on self-learning. The method provided by the invention comprises the steps that 1 knowledge-based coarse welding spot positioning is used, and the optimal welding path is planned to provide a vision system and a robotic arm with a running direction; 2 fine positioning of welding spots is carried out based on machine vision, and the types of welding spots are judged; the robotic arm is accurately guided to find the location of welding spots, so as to implement targeted automatic welding; and 3 welding spot defect detection based on online deep reinforcement learning is used to automatically detect welding spot defects and determine the type, so as to provide basis and guidance for secondary repair welding at thesame station. According to the invention, a path planning algorithm is used to optimize the welding path of a camera and the robotic arm to improve the production efficiency; a deep neural network which fuses multi-layer features is used to facilitate the detection of many small target scenes with welding spots; for a single type of target, the weight of coordinate loss is improved, and the positioning accuracy is improved; and threshold filtering is carried out on the results, which filters out interference targets, and improves the recognition accuracy.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to an automatic welding and defect detection method based on self-learning. Background technique [0002] The electronics manufacturing industry continues to grow and has become one of the most important strategic industries in the world today. In the information age, electronic products are not only used in small calculators, mobile phones, and notebook computers, but also in large industrial equipment, automobiles, military weapon systems, and aviation equipment. The electronics manufacturing industry has become an important symbol to measure a country's economic development, scientific and technological progress and comprehensive national strength. In recent years, my country's electronic information manufacturing industry has grown at an annual rate of more than 20%, and has become a pillar industry of the national economy. [0003] Surface mount technology (Surface Mount Technol...

AI Technical Summary

Problems solved by technology

Existing welding quality inspection equipment is usually separated from the welding robot arm process and requires manual assistance

This method of judging welding defects through manual visual inspection cannot meet the needs of highly automated, self-learning, and self-evolving intelligent welding production lines

Images