模拟非线性网络离散型混合模型辨识及多重预置模型比较故障诊断方法  

The Discrete Hybrid Model Identification And Fault Diagnosis Method by Comparing with Preset Models for Nonlinear Analog Network

作　　者：谢长焱[1] 刘蓉[1] 彭卫韶[2] 

机构地区：[1]长沙医学院计算机系,湖南长沙410219 [2]中南大学信息科学与工程学院,湖南长沙410083

出　　处：《长沙医学院学报》2005年第1期48-51,54,共5页Journal of Changsha Medical University

基　　金：国家自然科学基金(NO:50277010)

摘　　要：本文采用方波脉冲函数变换(BPFT)对非线性动态网络的混合模型进行了辨识,推导出了计算混合模型的相关公式和网络响应的伏特劳级数解在方波域内的离散递推算式,提出了一种多重预置模型的非线性网络的故障诊断方法,该法极大地减轻了在线计算工作量,可实现在线故障诊断。The idntification is made for the hybrid model of nonlinear dynamic network through the block-pulse fuctions transforn (BPFT).And the identification formulas has been developed to determine model of nonlinear dynamic network and to set some useful recursive formulas for computer network response in domain of bloek-pulse.A new fault diagnosis method based on multiple preset models for nonlinear dynamic network has also been proposed.This method can largely reduce the computational cost on line,so the fault diagnosis can be realized on line.

关 键 词：方波脉冲函数变换 模型辨识 递推计算 多重预置模型 故障诊断 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]