Applying cognitive computing to maintainer-collected data

Thomas M. Smoker, Tim French, Wei Liu, Melinda R. Hodkiewicz

Research output: Chapter in Book/Conference paperConference paper

1 Citation (Scopus)

Abstract

Companies are investing heavily in predictive maintenance algorithms without considering how the predictions will be validated. When components are removed, the observations of the maintenance technicians about their state (failed or not) and the failure mode are crucial to this validation process and to developing accurate component reliability distributions. Despite years of effort to get maintenance technicians to collect data that is usable and useful to engineers, either by trying to enforce the use of codes or apply management controls, little progress has been made. Advances in cognitive computing processes such as text mining, natural language processing and knowledge representation hold the key to solving this problem. The purpose of this paper is to explain key concepts in text mining, knowledge representation and ontology development in a way that is accessible to reliability and maintenance engineers. We illustrate, using a conveyor system as an example, how these concepts can be applied. Our aim is to convince the reader of the value of investing time to understand and develop cognitive computing methods. Sooner, rather than later, these concepts will be used to translate manually entered maintenance work order data to support validation of condition based maintenance predictions and generation of near real time reliability distributions.

Original languageEnglish
Title of host publication2017 2nd International Conference on System Reliability and Safety, ICSRS 2017
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages543-551
Number of pages9
Volume2018-January
ISBN (Electronic)9781538633229
DOIs
Publication statusPublished - 29 Jan 2018
Event2nd International Conference on System Reliability and Safety, ICSRS 2017 - Milan, Italy
Duration: 20 Dec 201722 Dec 2017

Conference

Conference2nd International Conference on System Reliability and Safety, ICSRS 2017
CountryItaly
CityMilan
Period20/12/1722/12/17

Fingerprint

Maintenance
Computing
Text Mining
Knowledge Representation
Knowledge representation
Condition-based Maintenance
Computing Methods
Prediction
Failure Mode
Engineers
Natural Language
Ontology
Failure modes
Concepts
Processing
Industry

Cite this

Smoker, T. M., French, T., Liu, W., & Hodkiewicz, M. R. (2018). Applying cognitive computing to maintainer-collected data. In 2017 2nd International Conference on System Reliability and Safety, ICSRS 2017 (Vol. 2018-January, pp. 543-551). USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICSRS.2017.8272880
Smoker, Thomas M. ; French, Tim ; Liu, Wei ; Hodkiewicz, Melinda R. / Applying cognitive computing to maintainer-collected data. 2017 2nd International Conference on System Reliability and Safety, ICSRS 2017. Vol. 2018-January USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 543-551
@inproceedings{6bca89c49f8d42e49f0a3643a31cae48,
title = "Applying cognitive computing to maintainer-collected data",
abstract = "Companies are investing heavily in predictive maintenance algorithms without considering how the predictions will be validated. When components are removed, the observations of the maintenance technicians about their state (failed or not) and the failure mode are crucial to this validation process and to developing accurate component reliability distributions. Despite years of effort to get maintenance technicians to collect data that is usable and useful to engineers, either by trying to enforce the use of codes or apply management controls, little progress has been made. Advances in cognitive computing processes such as text mining, natural language processing and knowledge representation hold the key to solving this problem. The purpose of this paper is to explain key concepts in text mining, knowledge representation and ontology development in a way that is accessible to reliability and maintenance engineers. We illustrate, using a conveyor system as an example, how these concepts can be applied. Our aim is to convince the reader of the value of investing time to understand and develop cognitive computing methods. Sooner, rather than later, these concepts will be used to translate manually entered maintenance work order data to support validation of condition based maintenance predictions and generation of near real time reliability distributions.",
keywords = "asset management, cognitive computing, maintenance, natural language processing, ontology, text processing, work management",
author = "Smoker, {Thomas M.} and Tim French and Wei Liu and Hodkiewicz, {Melinda R.}",
year = "2018",
month = "1",
day = "29",
doi = "10.1109/ICSRS.2017.8272880",
language = "English",
volume = "2018-January",
pages = "543--551",
booktitle = "2017 2nd International Conference on System Reliability and Safety, ICSRS 2017",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Smoker, TM, French, T, Liu, W & Hodkiewicz, MR 2018, Applying cognitive computing to maintainer-collected data. in 2017 2nd International Conference on System Reliability and Safety, ICSRS 2017. vol. 2018-January, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 543-551, 2nd International Conference on System Reliability and Safety, ICSRS 2017, Milan, Italy, 20/12/17. https://doi.org/10.1109/ICSRS.2017.8272880

Applying cognitive computing to maintainer-collected data. / Smoker, Thomas M.; French, Tim; Liu, Wei; Hodkiewicz, Melinda R.

2017 2nd International Conference on System Reliability and Safety, ICSRS 2017. Vol. 2018-January USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 543-551.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Applying cognitive computing to maintainer-collected data

AU - Smoker, Thomas M.

AU - French, Tim

AU - Liu, Wei

AU - Hodkiewicz, Melinda R.

PY - 2018/1/29

Y1 - 2018/1/29

N2 - Companies are investing heavily in predictive maintenance algorithms without considering how the predictions will be validated. When components are removed, the observations of the maintenance technicians about their state (failed or not) and the failure mode are crucial to this validation process and to developing accurate component reliability distributions. Despite years of effort to get maintenance technicians to collect data that is usable and useful to engineers, either by trying to enforce the use of codes or apply management controls, little progress has been made. Advances in cognitive computing processes such as text mining, natural language processing and knowledge representation hold the key to solving this problem. The purpose of this paper is to explain key concepts in text mining, knowledge representation and ontology development in a way that is accessible to reliability and maintenance engineers. We illustrate, using a conveyor system as an example, how these concepts can be applied. Our aim is to convince the reader of the value of investing time to understand and develop cognitive computing methods. Sooner, rather than later, these concepts will be used to translate manually entered maintenance work order data to support validation of condition based maintenance predictions and generation of near real time reliability distributions.

AB - Companies are investing heavily in predictive maintenance algorithms without considering how the predictions will be validated. When components are removed, the observations of the maintenance technicians about their state (failed or not) and the failure mode are crucial to this validation process and to developing accurate component reliability distributions. Despite years of effort to get maintenance technicians to collect data that is usable and useful to engineers, either by trying to enforce the use of codes or apply management controls, little progress has been made. Advances in cognitive computing processes such as text mining, natural language processing and knowledge representation hold the key to solving this problem. The purpose of this paper is to explain key concepts in text mining, knowledge representation and ontology development in a way that is accessible to reliability and maintenance engineers. We illustrate, using a conveyor system as an example, how these concepts can be applied. Our aim is to convince the reader of the value of investing time to understand and develop cognitive computing methods. Sooner, rather than later, these concepts will be used to translate manually entered maintenance work order data to support validation of condition based maintenance predictions and generation of near real time reliability distributions.

KW - asset management

KW - cognitive computing

KW - maintenance

KW - natural language processing

KW - ontology

KW - text processing

KW - work management

UR - http://www.scopus.com/inward/record.url?scp=85046689127&partnerID=8YFLogxK

U2 - 10.1109/ICSRS.2017.8272880

DO - 10.1109/ICSRS.2017.8272880

M3 - Conference paper

VL - 2018-January

SP - 543

EP - 551

BT - 2017 2nd International Conference on System Reliability and Safety, ICSRS 2017

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

ER -

Smoker TM, French T, Liu W, Hodkiewicz MR. Applying cognitive computing to maintainer-collected data. In 2017 2nd International Conference on System Reliability and Safety, ICSRS 2017. Vol. 2018-January. USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 543-551 https://doi.org/10.1109/ICSRS.2017.8272880