Framework for Mitigation of Welding Induced Distortion Through Response Surface Method and Reinforcement Learning

Welding induced distortion causes dimensional inaccuracies in parts being produced and assembly fit-up problems during manufacturing. In this study, a framework is proposed to mitigate weld distortion at the design stage. A sequential approach is adopted to optimize the welding process. In the first phase, welding process parameters are optimized through the response surface method. The effect of these parameters on the overall distortion of the welded part is observed by a simulation of the welding process. In the second phase, the weld sequence is optimized using the optimum weld parameters. A reinforcement learning-based Q-learning technique is used to select the optimum welding path by sequential observation of weld distortion at each segment being welded. The optimum process parameters and weld path sequence have been selected for 3 mm steel plates having a lap joint configuration and a 2 mm vent panel with a butt joint configuration. It is concluded that the combination of the optimum welding parameters and welding sequence yields minimum distortion. By applying this framework, a reduction of 19% is observed in overall welding induced distortion.

Improved Continuum Joint Configuration Estimation Using a Linear Combination of Length Measurements and Optimization of Sensor Placement

This paper presents methods for placing length sensors on a soft continuum robot joint as well as a novel configuration estimation method that drastically minimizes configuration estimation error. The methods utilized for placing sensors along the length of the joint include a single joint length sensor, sensors lined end-to-end, sensors that overlap according to a heuristic, and sensors that are placed by an optimization that we describe in this paper. The methods of configuration estimation include directly relating sensor length to a segment of the joint's angle, using an equal weighting of overlapping sensors that cover a joint segment, and using a weighted linear combination of all sensors on the continuum joint. The weights for the linear combination method are determined using robust linear regression. Using a kinematic simulation we show that placing three or more overlapping sensors and estimating the configuration with a linear combination of sensors resulted in a median error of 0.026% of the max range of motion or less. This is over a 500 times improvement as compared to using a single sensor to estimate the joint configuration. This error was computed across 80 simulated robots of different lengths and ranges of motion. We also found that the fully optimized sensor placement performed only marginally better than the placement of sensors according to the heuristic. This suggests that the use of a linear combination of sensors, with weights found using linear regression is more important than the placement of the overlapping sensors. Further, using the heuristic significantly simplifies the application of these techniques when designing for hardware.