Discovery of knowledge from diagnostic databases

Wojciech A. Moczulski; Paweł Kostka

doi:10.1117/12.460221

Discovery of knowledge from diagnostic databases

Wojciech A. Moczulski
, Paweł Kostka

Katedra Podstaw Konstrukcji Maszyn (RMT/RMT6)

Silesian University of Technology

Wyniki badań: Wkład do czasopisma › Artykuł z konferencji › recenzja

Abstrakt

The paper deals with acquisition of diagnostic knowledge that is relevant for detection and isolation of a special class of malfunctions of rotating machinery called "shaft misalignment". To detect a misalignment of the given shaft supported by multiple journal bearings, decision trees have been applied. These trees have been discovered in a database collected in a numerical experiment performed by the well-verified simulation system. A novel approach to definition of classes of misalignment has been introduced. Several new methods of selection of attributes and evaluation of classifier's performance have been suggested and verified. Finally a new method of diagnosing misalignment of rotating machinery has been formulated. This method may be efficiently implemented for real-existing rotating machinery.

Język oryginału	angielski
Strony (od–do)	126-137
Liczba stron	12
Czasopismo	Proceedings of SPIE - The International Society for Optical Engineering
Tom	4730
Identyfikatory DOI	https://doi.org/10.1117/12.460221
Status publikacji	Opublikowano - 2002
Wydarzenie	Data Mining and Knowledge Discovery: Theory, Tools, and Technology IV - Orlando, FL, Stany Zjednoczone Czas trwania: 1 kwi 2002 → 4 kwi 2002

Obszary tematyczne ASJC Scopus

Materiały elektroniczne, optyczne i magnetyczne
Fizyka materii skondensowanej
Zastosowania informatyki
Matematyka stosowana
Inżynieria elektryczna i elektroniczna

Uzyskaj dostęp do dokumentu

10.1117/12.460221

Inne pliki i linki

Link do publikacji w Scopus

Cytowanie

@article{e5d2388619a44b47bee179803ef339ce,

title = "Discovery of knowledge from diagnostic databases",

abstract = "The paper deals with acquisition of diagnostic knowledge that is relevant for detection and isolation of a special class of malfunctions of rotating machinery called {"}shaft misalignment{"}. To detect a misalignment of the given shaft supported by multiple journal bearings, decision trees have been applied. These trees have been discovered in a database collected in a numerical experiment performed by the well-verified simulation system. A novel approach to definition of classes of misalignment has been introduced. Several new methods of selection of attributes and evaluation of classifier's performance have been suggested and verified. Finally a new method of diagnosing misalignment of rotating machinery has been formulated. This method may be efficiently implemented for real-existing rotating machinery.",

keywords = "Diagnostic knowledge, Knowledge discovery, Rotating machinery, Shaft misalignment, Static models",

author = "Moczulski, \{Wojciech A.\} and Pawe{\l} Kostka",

year = "2002",

doi = "10.1117/12.460221",

language = "English",

volume = "4730",

pages = "126--137",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Data Mining and Knowledge Discovery: Theory, Tools, and Technology IV ; Conference date: 01-04-2002 Through 04-04-2002",

}

TY - JOUR

T1 - Discovery of knowledge from diagnostic databases

AU - Moczulski, Wojciech A.

AU - Kostka, Paweł

PY - 2002

Y1 - 2002

N2 - The paper deals with acquisition of diagnostic knowledge that is relevant for detection and isolation of a special class of malfunctions of rotating machinery called "shaft misalignment". To detect a misalignment of the given shaft supported by multiple journal bearings, decision trees have been applied. These trees have been discovered in a database collected in a numerical experiment performed by the well-verified simulation system. A novel approach to definition of classes of misalignment has been introduced. Several new methods of selection of attributes and evaluation of classifier's performance have been suggested and verified. Finally a new method of diagnosing misalignment of rotating machinery has been formulated. This method may be efficiently implemented for real-existing rotating machinery.

AB - The paper deals with acquisition of diagnostic knowledge that is relevant for detection and isolation of a special class of malfunctions of rotating machinery called "shaft misalignment". To detect a misalignment of the given shaft supported by multiple journal bearings, decision trees have been applied. These trees have been discovered in a database collected in a numerical experiment performed by the well-verified simulation system. A novel approach to definition of classes of misalignment has been introduced. Several new methods of selection of attributes and evaluation of classifier's performance have been suggested and verified. Finally a new method of diagnosing misalignment of rotating machinery has been formulated. This method may be efficiently implemented for real-existing rotating machinery.

KW - Diagnostic knowledge

KW - Knowledge discovery

KW - Rotating machinery

KW - Shaft misalignment

KW - Static models

UR - https://www.scopus.com/pages/publications/0036033291

U2 - 10.1117/12.460221

DO - 10.1117/12.460221

M3 - Conference article

AN - SCOPUS:0036033291

SN - 0277-786X

VL - 4730

SP - 126

EP - 137

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Data Mining and Knowledge Discovery: Theory, Tools, and Technology IV

Y2 - 1 April 2002 through 4 April 2002

ER -

Discovery of knowledge from diagnostic databases

Abstrakt

Obszary tematyczne ASJC Scopus

Uzyskaj dostęp do dokumentu

Inne pliki i linki

Fingerprint

Cytowanie