Show simple item record

contributor authorHan G. Park
contributor authorMichail Zak
date accessioned2017-05-09T00:09:47Z
date available2017-05-09T00:09:47Z
date copyrightSeptember, 2003
date issued2003
identifier issn0022-0434
identifier otherJDSMAA-26320#451_1.pdf
identifier urihttp://yetl.yabesh.ir/yetl/handle/yetl/128122
description abstractWe present a fault detection method called the gray-box. The term “gray-box” refers to the approach wherein a deterministic model of system, i.e., “white box,” is used to filter the data and generate a residual, while a stochastic model, i.e., “black-box” is used to describe the residual. The residual is described by a three-tier stochastic model. An auto-regressive process, and a time-delay feed-forward neural network describe the linear and nonlinear components of the residual, respectively. The last component, the noise, is characterized by its moments. Faults are detected by monitoring the parameters of the auto-regressive model, the weights of the neural network, and the moments of noise. This method is demonstrated on a simulated system of a gas turbine with time delay feedback actuator.
publisherThe American Society of Mechanical Engineers (ASME)
titleGray-Box Approach for Fault Detection of Dynamical Systems
typeJournal Paper
journal volume125
journal issue3
journal titleJournal of Dynamic Systems, Measurement, and Control
identifier doi10.1115/1.1589032
journal fristpage451
journal lastpage454
identifier eissn1528-9028
keywordsNoise (Sound)
keywordsActuators
keywordsDynamic systems
keywordsGas turbines
keywordsAutomobiles
keywordsDelays
keywordsFlaw detection
keywordsFeedforward control
keywordsArtificial neural networks
keywordsFeedback AND Filters
treeJournal of Dynamic Systems, Measurement, and Control:;2003:;volume( 125 ):;issue: 003
contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record