Human-computer interaction safety early warning and control method based on digital twinning

Abstract

The invention provides a human-computer interaction safety early warning and control method based on digital twinning. The method comprises the following steps: identifying a worker in an image shot by a binocular camera and a human body key point position of the worker based on a deep learning algorithm; adhering a label to a moving joint of the robot, and identifying the position of the label inthe image through Canny edge detection and Hough circle detection algorithms to obtain the position of the robot; based on a binocular vision distance measurement principle, measuring space coordinates of key points and labels of a human body of a worker, and calculating a distance between the worker and the robot; building a man-machine interaction safety early warning twinning system, achievinginteraction co-fusion and iterative optimization of a man-machine interaction physical scene and a virtual scene, and visually monitoring the safety of the man-machine interaction process online in real time. The man-machine interaction safety early warning twinning system is driven by real-time data, the optimal work space can be optimized, the safety of the man-machine interaction process is guaranteed, and the man-machine cooperative work efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of intelligent manufacturing, human-computer interaction and safety control, in particular to a method for human-computer interaction safety early warning and control based on digital twins, especially to realize the digital twin environment based on deep learning and multi-eye vision. A security control method for human-computer interaction. Background technique [0002] Smart manufacturing will bring a new manufacturing model, which requires a high degree of automation to achieve fast and low-cost production, as well as highly flexible and intelligent production. By combining the performance of the robot system with the flexibility, agility and intelligence of humans, the flexibility and intelligence of the production line can be significantly improved in some production processes, thereby improving production efficiency. However, when humans and robots work in the same working environment, the sa...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the technical problems of poor adaptability, large amount of calculation, and high cost in the existing human-computer interaction control in a dynamic environment, the present invention proposes a human-computer interaction safety early warning and control method based on digital twins, based on deep learning and multi-eye vision Combined, the distance between man-machine is calculated, the model of man-machine distance measurement is simplified, the real-time performance of detection is improved, the efficiency of man-machine collaboration is improved, and the whole process of man-machine interaction can be monitored online in real time. process safety

Images