Jiangsu University of Science and Technology

Southeast University

Na Su

Jie Zhu

Jiayou Wang

Wenhang Li

Maosen Yang

Hua Zhang

Junbo Wang

Cai Zhang

The present invention discloses an intention-driven reinforcement learning-based path planning method, including the following steps: 1: acquiring, by a data collector, a state of a monitoring network; 2: selecting a steering angle of the data collector according to positions of surrounding obstacles, sensor nodes, and the data collector; 3: selecting a speed of the data collector, a target node, and a next target node as an action of the data collector according to an ε greedy policy; 4: determining, by the data collector, the next time slot according to the selected steering angle and speed; 5: obtaining rewards and penalties according to intentions of the data collector and the sensor nodes, and updating a Q value; 6: repeating step 1 to step 5 until a termination state or a convergence condition is satisfied; and 7: selecting, by the data collector, an action in each time slot having the maximum Q value as a planning result, and generating an optimal path. The method provided in the present invention can complete the data collection path planning with a higher probability of success and performance closer to the intention.

Intention-driven reinforcement learning-based path planning method

Disclosed are an adaptive control method and equipment of arc swing in narrow gap welding. The control equipment is composed of an infrared camera system, a computer image processing system, an arc swing parameter control system, a bent-conducting-rod-type swing arc torch and the like. The infrared camera system acquires, in an external triggering manner, an infrared image of welding area when an arc is deviated towards the left or the right side wall groove, extracts information about the width of the groove in real time after image processing by a computer, and calculates an arc swing angle target value. The arc swing parameter control system controls a motor drive mechanism to rotate a bent conducting rod, and drives the welding arc to conduct circular arc swing according to the swing angle target value, thereby realizing the adaptive control for the arc swing angle according to changes of the groove width.

Adaptive control method and equipment of arc swing in narrow gap welding

An infrared vision sensing detection method and device for narrow-gap weld seam deviation are provided. The device includes a shaking (or rotating) arc narrow-gap welding torch, an arc current sensor, a computer image processing system, and an infrared photographing system. The infrared photographing system includes an infrared camera which acquires an infrared image of a welding region in an external triggering manner when an arc shakes (or rotates) to a position closest to the left side wall or right side wall of a groove. After computer image processing, a welding wire position and a groove edge information is extracted in real time, and a weld seam deviation is calculated according to position changes of a welding wire relative to the left side wall and the right side wall of the groove, and the weld seam deviation is output. During pulsed arc welding, a signal in a base value period of the arc current pulse is detected by using the current sensor, thereby realizing welding image acquisition synchronized with the base value current period of the pulsed arc.

Infrared vision sensing detection method and device for narrow-gap weld seam deviation

Growing community of inventors

Jiangsu, China

Na Su