一种新填充函数算法优化的小波网络及其应用

A Wavelet Networks Optimized by a New Filled Function Algorithm and Its Application

小波网络的结构及参数的寻优是小波网络应用中的一个关键问题.为达到寻优速度快、优化效果好的目的,提出了一个新的填充函数,把基于此函数的填充函数法与BP算法相结合,提出一种训练小波网络的全局优化新算法.并将由此算法优化得到的小波网络应用于飞控系统的故障诊断中.计算机仿真结果表明,该算法在训练小波网络时,收敛速度优于采用进化规划算法的训练速度,由此得到的小波网络用于飞控系统的故障诊断具有泛化性强、收敛较快、诊断较准确等优点.

It＇s an important problem to optimize the structure and parameters of wavelet network. A new filled function and a novel global optimization technique which combines the filled function and BP algorithm are presented to optimize the wavelet network efficiently. In the algorithm,the BP algorithm finds one of local minimal points, the filled function method finds the point that is lower than the minimal point previously found. By repeating these processes, a global minimal point can be obtained at last. Compared with usual BP training algorithm,this new global optimization algorithm is more efficient and has a higher accuracy in application of three kinds of common faults diagnosis of flight control system.