Condition monitoring of an electrohydraulic position control system using artificial neural networks

K Pollmeier, C R Burrows, K A Edge

Research output: Contribution to conferencePaper

  • 3 Citations

Abstract

This paper investigates the condition monitoring of a servo-valve-controlled linear actuator system using artificial neural networks (NNs). The aim is to discuss techniques for the identification of failure characteristics and their source. It is shown that neural networks can be trained to identify more than one fault but these are larger and require more training patterns than networks for single fault diagnosis. This leads to much longer training times and to problems with scaleability. Therefore a modular approach has been developed. Several networks were trained each to identify an individual fault. The parallel outputs of these nets were then used as inputs to another network. This additional network was able to identify not only the correct faults but also the actual fault levels. Copyright 2004 by ASME

Conference

ConferenceASME International Mechanical Engineering Congress and Exposition
CityChicago, IL.
Period5/11/0610/11/06

Fingerprint

Position control
Condition monitoring
Neural networks
Control systems
Linear actuators
Failure analysis

Cite this

Pollmeier, K., Burrows, C. R., & Edge, K. A. (2004). Condition monitoring of an electrohydraulic position control system using artificial neural networks. 137-146. Paper presented at ASME International Mechanical Engineering Congress and Exposition, Chicago, IL., .

Condition monitoring of an electrohydraulic position control system using artificial neural networks. / Pollmeier, K; Burrows, C R; Edge, K A.

2004. 137-146 Paper presented at ASME International Mechanical Engineering Congress and Exposition, Chicago, IL., .

Research output: Contribution to conferencePaper

Pollmeier, K, Burrows, CR & Edge, KA 2004, 'Condition monitoring of an electrohydraulic position control system using artificial neural networks' Paper presented at ASME International Mechanical Engineering Congress and Exposition, Chicago, IL., 5/11/06 - 10/11/06, pp. 137-146.
Pollmeier K, Burrows CR, Edge KA. Condition monitoring of an electrohydraulic position control system using artificial neural networks. 2004. Paper presented at ASME International Mechanical Engineering Congress and Exposition, Chicago, IL., .
Pollmeier, K ; Burrows, C R ; Edge, K A. / Condition monitoring of an electrohydraulic position control system using artificial neural networks. Paper presented at ASME International Mechanical Engineering Congress and Exposition, Chicago, IL., .10 p.
@conference{414082c2d8ee4a3db31836814c978d99,
title = "Condition monitoring of an electrohydraulic position control system using artificial neural networks",
abstract = "This paper investigates the condition monitoring of a servo-valve-controlled linear actuator system using artificial neural networks (NNs). The aim is to discuss techniques for the identification of failure characteristics and their source. It is shown that neural networks can be trained to identify more than one fault but these are larger and require more training patterns than networks for single fault diagnosis. This leads to much longer training times and to problems with scaleability. Therefore a modular approach has been developed. Several networks were trained each to identify an individual fault. The parallel outputs of these nets were then used as inputs to another network. This additional network was able to identify not only the correct faults but also the actual fault levels. Copyright 2004 by ASME",
author = "K Pollmeier and Burrows, {C R} and Edge, {K A}",
year = "2004",
language = "English",
pages = "137--146",
note = "ASME International Mechanical Engineering Congress and Exposition ; Conference date: 05-11-2006 Through 10-11-2006",

}

TY - CONF

T1 - Condition monitoring of an electrohydraulic position control system using artificial neural networks

AU - Pollmeier,K

AU - Burrows,C R

AU - Edge,K A

PY - 2004

Y1 - 2004

N2 - This paper investigates the condition monitoring of a servo-valve-controlled linear actuator system using artificial neural networks (NNs). The aim is to discuss techniques for the identification of failure characteristics and their source. It is shown that neural networks can be trained to identify more than one fault but these are larger and require more training patterns than networks for single fault diagnosis. This leads to much longer training times and to problems with scaleability. Therefore a modular approach has been developed. Several networks were trained each to identify an individual fault. The parallel outputs of these nets were then used as inputs to another network. This additional network was able to identify not only the correct faults but also the actual fault levels. Copyright 2004 by ASME

AB - This paper investigates the condition monitoring of a servo-valve-controlled linear actuator system using artificial neural networks (NNs). The aim is to discuss techniques for the identification of failure characteristics and their source. It is shown that neural networks can be trained to identify more than one fault but these are larger and require more training patterns than networks for single fault diagnosis. This leads to much longer training times and to problems with scaleability. Therefore a modular approach has been developed. Several networks were trained each to identify an individual fault. The parallel outputs of these nets were then used as inputs to another network. This additional network was able to identify not only the correct faults but also the actual fault levels. Copyright 2004 by ASME

M3 - Paper

SP - 137

EP - 146

ER -