|
端磨机器人磨抛性能参数ANN-GA目标优化分析
喻凯 2026/3/10 18:07:36
淮安生物工程高等职业学校，机电工程系，江苏淮安，223200
摘要：机器人辅助在铣削机床上得到广泛应用，表现出来很高的运行稳定性。为了提高端磨机器人磨抛控制效率，设计了一种应用遗传优化神经网络的端磨机器人参数优化方法，并展开磨抛优化案例分析。研究结果表明：随着迭代的进程，工件表面粗糙度呈现持续下降，在迭代20次之后趋于稳定，表现出来很高的计算效率。采用磨抛加工能够达到表面粗糙度调控目标，经ANN-GA优化后获得更高表面粗糙度预测精度，整体耗时大幅减少，提升处理效率。该研究可以有效的提高智能制造效率，也可拓宽到其它的工业机器人领域。
关键词：端磨机器人；磨抛加工；神经网络；表面粗糙度
中图分类号：TH13
ANN-GA Target Optimization Analysis of Grinding and Polishing Performance Parameters of End Grinding robots
Yu Kai
Department of Mechanical and Electrical Engineering, Huai ’an Vocational College of Bioengineering, Huai ’an, Jiangsu 223200
Abstract: Robot-assisted machines have been widely applied in milling machines, demonstrating high operational stability. In order to improve the grinding and polishing control efficiency of the end face grinding robot, a parameter optimization method for the end grinding robot applying genetic optimization neural network was designed, and a case analysis of grinding and polishing optimization was carried out. The research results show that: With the process of iteration, the surface roughness of the workpiece continuously decreases and tends to stabilize after 20 iterations, demonstrating a very high computational efficiency. Grinding and polishing processing can achieve the surface roughness control target. After ANN-GA optimization, higher surface roughness prediction accuracy is obtained. The overall time consumption is significantly reduced and the processing efficiency is improved. This research can effectively enhance the efficiency of intelligent manufacturing and can also be extended to other fields of industrial robots.
Key words: End grinding robot; Grinding and polishing processing; Neural network; Surface roughness
0 引言
对不同打磨工艺建立了仿真模型，同时优化了曲面打磨技术，这些研究成果对改善打磨自动化水平起到了直观重要的效果，并且为建立更完善磨抛技术理论和开展工艺优化建立了重要基础[1]。到目前为止，在建立工艺调控模型方面仍需开展进一步分析，综合分析各类工艺条件下的打磨效果[2]。因此开展端磨机器人参数优化分析是目前研究的热点之一。
在当前磨抛加工领域中，已有较多研究人员报道了磨抛加工技术优化方面的内容。任利娟等[3]设计了一种4+2自由（未完，下一页）
附件下载：端磨机器人磨抛性能参数ANN-GA目标优化分析
|