摘要
TIG(TungstenInertGas)焊接过程是一个高度非线性、强耦合、时变的系统 ,针对这一特点 ,本文设计了单层神经网络模糊控制器 ,给出了学习算法。该控制器可以自动学习模糊控制规则 ,并随系统的变化自动调节模糊控制规则。采用普通CCD(ChargedCoupleDevice)摄像机拍摄熔池的正面图像 ,提取出熔池正面几何参数 ,利用熔池正面几何参数与背面熔宽的关系模型 ,对背面熔宽进行实时控制。仿真及试验结果表明 。
Since TIG welding process has the characteristics of long time lag, time-dependence and nonlinearity, an one-layer neuro-fuzzy controller is designed and a learning algorithm is developed for it. The controller can learn and adjust the fuzzy rules with the change of system automatically. In the system, topside images of weld pool are captured by commercial CCD camera, thus online control of back weld width can be realized, based on the model of topside weld pool geometrical parameters and back weld width. The simulation and test results show that the controller has good control performance and control effect.
出处
《焊接学报》
EI
CAS
CSCD
北大核心
2001年第5期5-8,共4页
Transactions of The China Welding Institution
基金
国家自然科学基金资助项目 ( 5 9875 0 5 3)
