Nonlinear Modeling and Inverse Modeling of Sensor Using Adaptive Network-based Fuzzy Inference Systems

摘要：

Aiming at nonlinear modeling and the nonlinear calibration for the output characteristic of sensor in course of measurement, a novel modeling method using adaptive network-based fuzzy inference system (ANFIS) is presented, which is computationally efficient universal nonlinear function approximators. By using a hybrid learning procedure, the ANFIS can construct an input-output mapping based on both human knowledge in the form of fuzzy if-then rule and stipulated input-output data pairs. Experimental results show that the nonlinear modeling or inverse modeling of sensor using the ANFIS is superior to the existing neural networks or fuzzy modeling techniques.

关键词： sensor modeling inverse modeling Adaptive neuro-fuzzy systems hybrid learning algorithm

作者: LI Jun ZHANG Youpeng

作者单位: School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, 730070

会议类型: 国际会议

会议名称: 第七届国际测试技术研讨会

会议地点: 北京

会议语种:英文

在线出版日期: 2007-08-05（万方平台首次上网日期，不代表论文的发表时间）