齿轮机器人复杂装配过程在线建模与参数优化

Online Modeling and Parameter Optimization Method for Robotic Complex Assembly Process of Gear

以缓速器装配生产线齿轮装配工位为研究背景,提出一种复杂机器人装配过程在线建模学习与参数优化方法,解决当前离线方法装配成功率低和效率低的问题。针对复杂多变的机器人齿轮装配过程,基于高斯过程回归建立机器人接触状态与机器人动作的动态模型,提出一种新的基于生成对抗的粒子群优化算法用于在线学习,生成装配关键参数优化策略,并采用支持向量数据描述对新颖装配数据进行检测,最终实现装配过程在线建模与参数优化。齿轮与花键轴机器人装配实验结果表明,基于生成对抗粒子群-高斯过程回归的装配方法在装配成功率与效率上均优于人工和离线方法,可以对生产线不同批次和规格的齿轮进行在线装配,满足缓速器装配生产线的实际生产需求。

Taking the gear assembly station of the retarder assembly line as a research background,an online modeling learning and parameter optimization method for complex robot assembly process is proposed to solve the problems of low assembly success rate and low efficiency using current offline methods.For the complex and changeable robotic assembly process of gear,the dynamic model of contact states and robot motion is established based on Gaussian process regression(GPR).A new particle swarm optimization algorithm based on generative adversarial algorithm(GAPSO)is proposed for online learning to generate optimization strategy of assembly key parameters.Support vector data description(SVDD)is utilized to detect the new assembly data.The method finally realizes the online modeling and parameter optimization of the assembly process.Experiment results of the gear and spline shaft show that the GAPSO-GPR method is superior to the manual and offline methods in assembly success rate and efficiency,and can be used for online assembly of gears with different batches and specifications,which can meet the actual production demand of the retarder assembly line.