超精密定位的模糊神经网络控制

Ultra Precision Positioning Control Based on Fuzzy Neural Network

利用激光莫尔技术设计了一种超精密定位装置,系统以工业控制计算机为核心,通过光、机、电的有机结合,可实现高精度位置检测及精密自动定位。针对系统存在非线性,精确控制模型难以建立的缺陷,将模糊神经网络应用于该控制系统中,给出了模糊推理BP网络模型,改造后的模糊控制系统具有了知识自动获取功能,能更好地适应工况环境。实验结果表明使用模糊神经网络控制,控制响应快、稳定性好、鲁棒性强。系统取得了亚微米级的定位精度,对超精密加工具有实用价值。

An ultra - precision positioning set based on laser moiré signals is designed. It can achieve a fully automatic precision position by combination of light, electronic and mechanical technology. But it is difficult to set up accurate control model of precise positioning because of non - linearity of the positioning system. Fuzzy neural network is used in the precise positioning control . BP neural network model is set up. The improved fuzzy control system can obtain corresponding operation knowledge according to working environment. The experimental result shows FNNC can perform excellent control effect, such as good stability and strong robustness. The positioning accuracy of sub- micron order is obtained.