Research on six-joint industrial robotic arm positioning error compensation algorithm based on motion decomposition and improved CIWOA-BP neural network
Xuejian Zhang, Xiaobing Hu, Hang Li, Zheyuan Zhang, Haijun Chen
{"title":"Research on six-joint industrial robotic arm positioning error compensation algorithm based on motion decomposition and improved CIWOA-BP neural network","authors":"Xuejian Zhang, Xiaobing Hu, Hang Li, Zheyuan Zhang, Haijun Chen","doi":"10.1177/09544062241264706","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":20558,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1177/09544062241264706","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0
Abstract
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.
六关节工业机器人手臂末端执行器轨迹的运动误差会严重影响加工精度。由于机械臂的结构特性,复杂的铣削操作会导致偏离预定路径。这些误差通常会表现出周期性和位置依赖性变化,因此需要采取细致的控制措施。为了应对这一挑战,我们提出了一种基于运动分解的新型误差补偿技术,用于六关节工业机械臂。这种方法包括将机器人的运动轨迹分解为不同的组件,并使用 BP 神经网络为每个组件构建预测模型。然后使用鲸鱼优化算法(CIWOA)和自适应混沌映射聚类方法对这些模型进行优化,以提高效率和全局优化。所提出的方法适用于机械臂的各种运动类型,从而大大提高了绝对定位精度。实验验证证实了 CIWOA-BP 神经网络预测模型的可靠性,以及非参数精度补偿方法在提高运动规划精度方面的有效性。
期刊介绍:
The Journal of Mechanical Engineering Science advances the understanding of both the fundamentals of engineering science and its application to the solution of challenges and problems in engineering.