摘要
研究了非线性多变量系统的T S模糊辨识问题.提出一种利用测得的输入输出数据来计算非线性动态模糊模型的方法.使用模糊聚类简化了T S模糊规则及前提参数的生成,采用加权最小二乘算法得出结论参数.将该辨识器用于一类非线性系统的模糊辨识,并与模糊神经网络的辨识结果进行了比较,验证了所提方法的有效性.
Fuzzy method is used as a tool for model identification of a nonlinear and multivariable system.A method puts forward to compute non-linear dynamic fuzzy models from input/output measurement data. In fact, the use of fuzzy clustering facilitates automatic generation of Takagi-Sugeno rules and its antecedent parameters. The consequent parameters of each rule are identified separately by the weighted least square method. At last, the fuzzy identification method is applied to a nonlinear system, and the simulation result is compared with the result of neuro-fuzzy inference system, and it shows the effectiveness of the method.
出处
《兰州交通大学学报》
CAS
2004年第4期58-60,共3页
Journal of Lanzhou Jiaotong University
基金
上海市教育委员会科研项目(03IK09)
上海市教育委员会科研重点项目(04FA02)
关键词
辨识
非线性系统
T-S模糊模型
模糊聚类
加权最小二乘法
identification, nonlinear system
Takagi-Sugeno model
fuzzy clustering
the weighted least square method
