基于神经网络的混沌控制原理对切削颤振的模拟控制研究  

Control of Chaotic Systems Based on Neural Network and its Application to Simulant Study of Turning Flutter

作　　者：王新晴[1] 唐建宁[1] 杨小强[1] 王洋[1] 王兰芳[1] 

机构地区：[1]解放军理工大学工程兵工程学院,江苏南京210007

出　　处：《解放军理工大学学报（自然科学版）》2000年第6期63-65,共3页Journal of PLA University of Science and Technology(Natural Science Edition)

摘　　要：在机械加工过程中存在一种以残留振痕作为机械反馈量的自激振荡 ,严重影响了加工质量、车床及刀具的寿命。理论研究与仿真结果表明 ,将人工神经网络理论引入非线性或不稳定系统混沌行为的控制 ,可以有效地减少残留振痕引起的车削颤振 ,提高车削稳定性。As a result of the mechanic feedback, turning flutter resulted from former vibration trace is a kind of self excited oscillation. In this paper a new method of chaotic control with multilayer feed forward neural network is presented. With this method the chaotic behaviors of nonlinear or unstable system are controlled, and the self excited oscillation in turning process is eliminated.

关 键 词：混沌控制原理 切削颤振 模拟控制 车削颤振 神经网络 车削加工 残留振痕 

分 类 号：TG510.1[金属学及工艺—金属切削加工及机床] TP183[自动化与计算机技术—控制理论与控制工程]