【作者】 范斌； 杨力； 袁家虎； 曾志革； 李晓今；

【Author】 FAN Bin, YANG Li, YUAN Jia-hu, ZENG Zhi-ge, LI Xiao-jin(Institute of Optics and Electronics, The Chinese Academy of Science, Chengdu, Sichuan 610209 China)

【机构】 中国科学院光电技术研究所；

【摘要】 根据(CMAC)小脑模型处理非线性系统的特点,分析了应力盘系统的结构和盘控系统,引入了CMAC神经网络实现应力盘形变控制的模型。提出了将CMAC神经网络应用于应力盘逆变形智能控制的创意和实现方法,以应力盘面形参数和对应的驱动器电压参数作为样本训练CMAC神经网络,将训练成功的CMAC神经网络作为控制器控制应力盘变形,取得了误差小于5%的计算机仿真结果。更多还原

【Abstract】 The characteristics of stressed-lap structure and control system are analysised .The structure and principle of CMAC neural networks model are introduced. The idea and implementing method of inverse deformation intelligent control for stressed-lap by CMAC neural networks are put forward. The training of the CMAC neural networks according to the parameters of stressed-lap surface deformation and the corresponding voltage of actuators is obtained. The trained CMAC neural networks have been completed.so that it will be able to apply the trained CMAC neural networks as a controller for stressed-lap deformation controlling. The computer simulation of 5% error is achieved.更多还原