A new filtering-based actuator fault diagnosis approach based on NN models of PDFs

Yu Min Zhang; Ling Yao Wu; Lei Guo; Cheng Liang Liu

A new filtering-based actuator fault diagnosis approach based on NN models of PDFs

Yu Min Zhang
, Ling Yao Wu
, Lei Guo^*
, Cheng Liang Liu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In many practical processes, the measured information is the stochastic distribution of the system output rather than its value. In this paper, following the new development for the fault diagnosis (FD) problem of stochastic processes (see [6]), an improved FD method with H_∞ performance optimization is considered by using the output stochastic distributions. A multi-layer perceptron (MLP) neural network is adopted to approximate the probability density function (PDF) of the system outputs. For an identified discrete-time dynamic model with nonlinearities and time delays, the concerned FD problem is investigated. The measure of estimation errors represented by the distances between two output PDFs, will be optimized to find the diagnosis filter gain. Simulation example is given for the weighting dynamics to demonstrate the effectiveness of the proposed method.

Original language	English
Title of host publication	Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Pages	1849-1853
Number of pages	5
State	Published - 2005
Externally published	Yes
Event	2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05 - Beijing, China Duration: 13 Oct 2005 → 15 Oct 2005

Publication series

Name	Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Volume	3

Conference

Conference	2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Country/Territory	China
City	Beijing
Period	13/10/05 → 15/10/05

Cite this

Zhang, Y. M., Wu, L. Y., Guo, L., & Liu, C. L. (2005). A new filtering-based actuator fault diagnosis approach based on NN models of PDFs. In Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05 (pp. 1849-1853). Article 1614986 (Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05; Vol. 3).

@inproceedings{9eed377c014944eaa7da20e9464ed01b,

title = "A new filtering-based actuator fault diagnosis approach based on NN models of PDFs",

abstract = "In many practical processes, the measured information is the stochastic distribution of the system output rather than its value. In this paper, following the new development for the fault diagnosis (FD) problem of stochastic processes (see [6]), an improved FD method with H∞ performance optimization is considered by using the output stochastic distributions. A multi-layer perceptron (MLP) neural network is adopted to approximate the probability density function (PDF) of the system outputs. For an identified discrete-time dynamic model with nonlinearities and time delays, the concerned FD problem is investigated. The measure of estimation errors represented by the distances between two output PDFs, will be optimized to find the diagnosis filter gain. Simulation example is given for the weighting dynamics to demonstrate the effectiveness of the proposed method.",

author = "Zhang, \{Yu Min\} and Wu, \{Ling Yao\} and Lei Guo and Liu, \{Cheng Liang\}",

year = "2005",

language = "英语",

isbn = "0780394224",

series = "Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05",

pages = "1849--1853",

booktitle = "Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05",

note = "2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05 ; Conference date: 13-10-2005 Through 15-10-2005",

}

Zhang, YM, Wu, LY, Guo, L & Liu, CL 2005, A new filtering-based actuator fault diagnosis approach based on NN models of PDFs. in Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05., 1614986, Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05, vol. 3, pp. 1849-1853, 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05, Beijing, China, 13/10/05.

A new filtering-based actuator fault diagnosis approach based on NN models of PDFs. / Zhang, Yu Min; Wu, Ling Yao; Guo, Lei et al.
Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05. 2005. p. 1849-1853 1614986 (Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A new filtering-based actuator fault diagnosis approach based on NN models of PDFs

AU - Zhang, Yu Min

AU - Wu, Ling Yao

AU - Guo, Lei

AU - Liu, Cheng Liang

PY - 2005

Y1 - 2005

N2 - In many practical processes, the measured information is the stochastic distribution of the system output rather than its value. In this paper, following the new development for the fault diagnosis (FD) problem of stochastic processes (see [6]), an improved FD method with H∞ performance optimization is considered by using the output stochastic distributions. A multi-layer perceptron (MLP) neural network is adopted to approximate the probability density function (PDF) of the system outputs. For an identified discrete-time dynamic model with nonlinearities and time delays, the concerned FD problem is investigated. The measure of estimation errors represented by the distances between two output PDFs, will be optimized to find the diagnosis filter gain. Simulation example is given for the weighting dynamics to demonstrate the effectiveness of the proposed method.

AB - In many practical processes, the measured information is the stochastic distribution of the system output rather than its value. In this paper, following the new development for the fault diagnosis (FD) problem of stochastic processes (see [6]), an improved FD method with H∞ performance optimization is considered by using the output stochastic distributions. A multi-layer perceptron (MLP) neural network is adopted to approximate the probability density function (PDF) of the system outputs. For an identified discrete-time dynamic model with nonlinearities and time delays, the concerned FD problem is investigated. The measure of estimation errors represented by the distances between two output PDFs, will be optimized to find the diagnosis filter gain. Simulation example is given for the weighting dynamics to demonstrate the effectiveness of the proposed method.

UR - https://www.scopus.com/pages/publications/33847100448

M3 - 会议稿件

AN - SCOPUS:33847100448

SN - 0780394224

SN - 9780780394223

T3 - Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05

SP - 1849

EP - 1853

BT - Proceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05

T2 - 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05

Y2 - 13 October 2005 through 15 October 2005

ER -

A new filtering-based actuator fault diagnosis approach based on NN models of PDFs

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this