Research on six-joint industrial robotic arm positioning error compensation algorithm based on motion decomposition and improved CIWOA-BP neural network

Motion errors in the trajectory of a six-joint industrial robotic arm's end-effector can significantly impact machining precision. Complex milling operations can lead to deviations from the intended path due to the robotic arm's structural characteristics. These errors often exhibit periodic and position-dependent variations, underscoring the need for meticulous control measures. To address this challenge, we propose a novel motion decomposition-based error compensation technique for a six-joint industrial robotic arm. This approach involves breaking down the robot's motion trajectory into distinct components and constructing prediction models for each component using a BP neural network. These models are then optimized using the Whale Optimization Algorithm (CIWOA) and an adaptive chaotic mapping clustering approach to improve efficiency and global optimization. The proposed method is applied to various motion types of the robotic arm, resulting in substantial enhancements in absolute positioning accuracy. Experimental validation confirms the reliability of the CIWOA-BP neural network prediction model and the effectiveness of the nonparametric accuracy compensation method in refining motion planning precision.