小波方法光顺的B样条模糊系统及其应用

为了减少不准确数据对模糊系统的影响, 本文利用准均匀B样条小波方法光顺了B样条模糊系统. 首先将B样条模糊系统的多分辨率表示转化为准均匀B样条函数的多分辨率表示, 接着利用准均匀B样条小波分解方法对相应的准均匀B样条函数进行分解就得到了一系列光顺性逐渐增强、规则个数逐渐减少的模糊系统, 即基于小波方法的光顺B样条模糊系统. 最后, 仿真结果表明, 小波方法光顺的B样条模糊系统构造的模糊控制器在改善原来B样条模糊系统构造的模糊控制器性能的同时, 大大提高了原来控制器的运行效率.

B-spline fuzzy systems faired by wavelet method and its applications

The B-spline fuzzy systems (B-FSs) are faired by using the quasi-uniform B-spline wavelet decomposition method to reduce adverse effects of the inaccurate data. First, the multi-resolution of B-FSs is transformed to the multiresolution of quasi-uniform B-splines; and then, the corresponding quasi-uniform B-splines are decomposed by using the quasi-uniform B-spline wavelet method to produce a series of fuzzy systems with gradually increasing fairness and gradually decreasing number of rules. Those fuzzy systems are called faired B-spline fuzzy systems by wavelet method. Simulation results show that fuzzy controllers constructed from faired B-FSs by wavelet method surpass in performances the fuzzy controllers by the original B-FSs, while consuming considerably less running time.