This paper aims to present a path planning method based on equal entropy optimization to mitigate force fluctuations and improve trajectory stability in robotic machining of casting defects resulting from variations in surface topology.
Point cloud data of the casting surface is preprocessed to identify and grade defect regions. This process generates defect severity levels. A full-coverage trajectory is then planned and optimized using equal entropy optimization, constrained by defect boundaries, to ensure precise defect removal and smooth trajectories.
Experimental results demonstrate that the proposed method enhances tool stability and machining quality. The results indicate a significant reduction in overturning torque and pressing force fluctuations, leading to improved machined surface smoothness. These findings validate the effectiveness of the proposed method in reducing force fluctuations and enhancing machining performance.
This method integrates point cloud data and defect recognition technology, addressing limitations of traditional approaches that ignore defect impact on step sizes. It significantly improves casting defect machining quality while reducing tool force fluctuations.
Experimental comparisons with existing methods highlight the proposed method's effectiveness in minimizing force fluctuations, maintaining stable machining speeds and optimizing trajectory planning.
