Welding robot control system based on AI vision

Through the welding robot control system based on AI vision, the energy and material consumption during the welding process is monitored and optimized in real time, the serious problem of resource waste in existing welding technology is solved, and the unity of weld quality stability and green manufacturing is achieved.

CN120533688AActive Publication Date: 2025-08-26ANHUI GAMMA ROBOT TECHNOLOGY CO LTD
7 Cites 0 Cited by

Patent Information

Application Number
CN202510615435.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-14
Publication Date
2025-08-26
Estimated Expiration
2045-05-14

AI Technical Summary

Technical Problem

The existing welding technology research focuses on the quality and strength of weld forming, and rarely pays attention to energy and material losses, resulting in serious waste of resources in the production process, which is not conducive to green and low-carbon manufacturing and sustainable development.

Method used

The welding robot control system based on AI vision obtains the melt pool image through the acquisition module, the analysis module calculates the width-depth ratio and marks abnormalities, optimizes the module to build a sample set and obtains feature importance scores, and the control module implements energy and material control strategies to achieve dynamic balance between energy and material.

Benefits of technology

Significantly improve the consistency and process stability of weld formation, reduce rework and scrapping rates, optimize energy and material consumption, and support the long-term and stable operation of flexible production and intelligent manufacturing scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of AI vision, and particularly discloses a welding robot control system based on AI vision, which comprises an acquisition module, an analysis module, an optimization module and a control module, and is characterized in that the acquisition module is used for acquiring a molten pool image, preprocessing the molten pool image to obtain a target image, and extracting the edge of a molten pool in the target image based on the AI vision; the analysis module is used for acquiring the actual width A1 of the molten pool based on the edge, acquiring the actual depth A2 of the molten pool, calculating the width-depth ratio, and when the width-depth ratio does not belong to a preset safety range, marking as an abnormal condition; the optimization module is used for acquiring features in real time in a preset acquisition period when an abnormal condition occurs, constructing two sample sets based on the features, and acquiring importance scores of the features based on the sample sets; and the control module is used for executing a preset control strategy based on the important score. Energy and welding material consumption can be reduced, and green and efficient welding manufacturing is assisted.
Need to check novelty before this filing date? Find Prior Art