ANN-based nonlinear time series models in fault detection and prediction

被引：0

作者：

Tang, TH ^{[1
]}

Xiong, M ^{[1
]}

Liu, YJ ^{[1
]}

Li, JR ^{[1
]}

机构：

[1] Shanghai Maritime Univ, Merchant Marine Coll, Shanghai 200135, Peoples R China

来源：

CONTROL APPLICATIONS IN MARINE SYSTEMS (CAMS'98) | 1999年

关键词：

nonlinear time series; neural networks; parameter identification; adaptive prediction;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper nonlinear time series models based on neural networks are introduced to forecast faults. A feedforward neural network prediction method with single sample adaptive learning algorithm and a recurrent neural network prediction method with adaptive learning algorithm are presented to implement system modeling, parameter correcting and trend forecasting on line. Copyright (C) 1998 IFAC.

引用

页码：297 / 302

页数：6

共 9 条

[1] A NEURAL NETWORK APPROACH TO REAL-TIME CONDITION MONITORING OF INDUCTION-MOTORS [J].

CHOW, MY ;

MANGUM, PM ;

YEE, SO .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1991, 38 (06) :448-453

[2] RECURRENT NEURAL NETWORKS AND ROBUST TIME-SERIES PREDICTION [J].

CONNOR, JT ;

MARTIN, RD ;

ATLAS, LE .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :240-254

[3] USING A NEURAL FUZZY SYSTEM TO EXTRACT HEURISTIC KNOWLEDGE OF INCIPIENT FAULTS IN INDUCTION-MOTORS .1. METHODOLOGY [J].

GOODE, PV ;

CHOW, M .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1995, 42 (02) :131-138

[4]

LAPEDES A, 1987, UR872662 LOS AL NAT

[5]

TANG TH, 1995, T SYSTEM THEORY APPL, V1, P279

[6]

TANG TH, 1997, IFAC TS 97 CHAN GREE, V2, P691

[7]

TONB H, 1983, THRESHOLD MODELS NON

[8]

WATANABE K, 1991, P IECON 91, V3, P1550

[9] An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories [J].

Williams, Ronald J. ;

Peng, Jing .

NEURAL COMPUTATION, 1990, 2 (04) :490-501

← 1 →