Automation of knowledge extraction for degradation analysis

Sri Addepalli; Tillman Weyde; Bernadin Namoano; Oluseyi Ayodeji Oyedeji; Tiancheng Wang; John Ahmet Erkoyuncu; Rajkumar Roy

doi:10.1016/j.cirp.2023.03.013

Automation of knowledge extraction for degradation analysis

Sri Addepalli
, Tillman Weyde
, Bernadin Namoano
, Oluseyi Ayodeji Oyedeji
, Tiancheng Wang
, John Ahmet Erkoyuncu
, Rajkumar Roy

School of Technology

Research output: Contribution to Journal › Article › peer-review

Abstract

Degradation analysis relies heavily on capturing degradation data manually and its interpretation using knowledge to deduce an assessment of the health of a component. Health monitoring requires automation of knowledge extraction to improve the analysis, quality and effectiveness over manual degradation analysis. This paper proposes a novel approach to achieve automation by combining natural language processing methods, ontology and a knowledge graph to represent the extracted degradation causality and a rule based decision-making system to enable a continuous learning process. The effectiveness of this approach is demonstrated by using an aero-engine component as a use-case.

Original language	English
Pages (from-to)	33-36
Number of pages	4
Journal	CIRP Annals - Manufacturing Technology
Volume	72
Issue number	1
Early online date	15 Jun 2023
DOIs	https://doi.org/10.1016/j.cirp.2023.03.013
Publication status	Published - 13 Jul 2023

Keywords

Knowledge management
Decision making
Knowledge graph

Access to Document

10.1016/j.cirp.2023.03.013Licence: CC BY

Addepalli_et_al_2023_Automation_of_knowledge_extraction_for_degradation_analysisFinal published version, 1.1 MBLicence: CC BY

Cite this

@article{8d4aba7633a54f5bb0d0c7c4801014ff,

title = "Automation of knowledge extraction for degradation analysis",

abstract = "Degradation analysis relies heavily on capturing degradation data manually and its interpretation using knowledge to deduce an assessment of the health of a component. Health monitoring requires automation of knowledge extraction to improve the analysis, quality and effectiveness over manual degradation analysis. This paper proposes a novel approach to achieve automation by combining natural language processing methods, ontology and a knowledge graph to represent the extracted degradation causality and a rule based decision-making system to enable a continuous learning process. The effectiveness of this approach is demonstrated by using an aero-engine component as a use-case.",

keywords = "Knowledge management, Decision making, Knowledge graph",

author = "Sri Addepalli and Tillman Weyde and Bernadin Namoano and Oyedeji, \{Oluseyi Ayodeji\} and Tiancheng Wang and Erkoyuncu, \{John Ahmet\} and Rajkumar Roy",

year = "2023",

month = jul,

day = "13",

doi = "10.1016/j.cirp.2023.03.013",

language = "English",

volume = "72",

pages = "33--36",

journal = "CIRP Annals - Manufacturing Technology",

issn = "0007-8506",

publisher = "Elsevier Inc.",

number = "1",

}

TY - JOUR

T1 - Automation of knowledge extraction for degradation analysis

AU - Addepalli, Sri

AU - Weyde, Tillman

AU - Namoano, Bernadin

AU - Oyedeji, Oluseyi Ayodeji

AU - Wang, Tiancheng

AU - Erkoyuncu, John Ahmet

AU - Roy, Rajkumar

PY - 2023/7/13

Y1 - 2023/7/13

N2 - Degradation analysis relies heavily on capturing degradation data manually and its interpretation using knowledge to deduce an assessment of the health of a component. Health monitoring requires automation of knowledge extraction to improve the analysis, quality and effectiveness over manual degradation analysis. This paper proposes a novel approach to achieve automation by combining natural language processing methods, ontology and a knowledge graph to represent the extracted degradation causality and a rule based decision-making system to enable a continuous learning process. The effectiveness of this approach is demonstrated by using an aero-engine component as a use-case.

AB - Degradation analysis relies heavily on capturing degradation data manually and its interpretation using knowledge to deduce an assessment of the health of a component. Health monitoring requires automation of knowledge extraction to improve the analysis, quality and effectiveness over manual degradation analysis. This paper proposes a novel approach to achieve automation by combining natural language processing methods, ontology and a knowledge graph to represent the extracted degradation causality and a rule based decision-making system to enable a continuous learning process. The effectiveness of this approach is demonstrated by using an aero-engine component as a use-case.

KW - Knowledge management

KW - Decision making

KW - Knowledge graph

U2 - 10.1016/j.cirp.2023.03.013

DO - 10.1016/j.cirp.2023.03.013

M3 - Article

SN - 0007-8506

VL - 72

SP - 33

EP - 36

JO - CIRP Annals - Manufacturing Technology

JF - CIRP Annals - Manufacturing Technology

IS - 1

ER -

Automation of knowledge extraction for degradation analysis

Abstract

Keywords

Access to Document

Fingerprint

Cite this