hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Predicting Air Compressor Failures Using Long Short Term Memory Networks
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.ORCID iD: 0000-0003-3272-4145
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.ORCID iD: 0000-0002-3034-6630
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.ORCID iD: 0000-0002-7796-5201
2019 (English)In: Progress in Artificial Intelligence: 19th EPIA Conference on Artificial Intelligence, EPIA 2019, Vila Real, Portugal, September 3–6, 2019, Proceedings, Part I / [ed] Paulo Moura Oliveira, Paulo Novais, Luís Paulo Reis, Cham: Springer, 2019, p. 596-609Conference paper, Published paper (Refereed)
Abstract [en]

We introduce an LSTM-based method for predicting compressor failures using aggregated sensory data, and evaluate it using historical information from over 1000 heavy duty vehicles during 2015 and 2016. The goal is to proactively identify trucks that will require maintenance in the near future, so that component replacement can be scheduled before the failure happens, translating into improved uptime. The problem is formulated as a classification task of whether a compressor failure will happen within the specified prediction horizon. A recurrent neural network using Long Short-Term Memory (LSTM) architecture is employed as the prediction model, and compared against Random Forest (RF), the solution used in industrial deployment at the moment. Experimental results show that while Random Forest slightly outperforms LSTM in terms of AUC score, the predictions of LSTM stay significantly more stable over time, showing a consistent trend from healthy to faulty class. Additionally, LSTM is also better at detecting the switch from faulty class to the healthy one after a repair. We demonstrate that this stability is important for making repair decisions, especially in questionable cases, and therefore LSTM model is likely to lead to better results in practice. © Springer Nature Switzerland AG 2019

Place, publisher, year, edition, pages
Cham: Springer, 2019. p. 596-609
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 11804
Keywords [en]
Fault detection, Predictive maintenance, Recurrent neural networks, Long-short term memory
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:hh:diva-41366DOI: 10.1007/978-3-030-30241-2_50Scopus ID: 2-s2.0-85072895300ISBN: 978-3-030-30240-5 (print)ISBN: 978-3-030-30241-2 (electronic)OAI: oai:DiVA.org:hh-41366DiVA, id: diva2:1384811
Conference
19th EPIA Conference on Artificial Intelligence (EPIA 2019), Vila Real, Portugal, September 3–6, 2019
Available from: 2020-01-10 Created: 2020-01-10 Last updated: 2020-01-14Bibliographically approved
In thesis
1. Wisdom of the Crowd for Fault Detection and Prognosis
Open this publication in new window or tab >>Wisdom of the Crowd for Fault Detection and Prognosis
2020 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Monitoring and maintaining the equipment to ensure its reliability and availability is vital to industrial operations. With the rapid development and growth of interconnected devices, the Internet of Things promotes digitization of industrial assets, to be sensed and controlled across existing networks, enabling access to a vast amount of sensor data that can be used for condition monitoring. However, the traditional way of gaining knowledge and wisdom, by the expert, for designing condition monitoring methods is unfeasible for fully utilizing and digesting this enormous amount of information. It does not scale well to complex systems with a huge amount of components and subsystems. Therefore, a more automated approach that relies on human experts to a lesser degree, being capable of discovering interesting patterns, generating models for estimating the health status of the equipment, supporting maintenance scheduling, and can scale up to many equipment and its subsystems, will provide great benefits for the industry. 

This thesis demonstrates how to utilize the concept of "Wisdom of the Crowd", i.e. a group of similar individuals, for fault detection and prognosis. The approach is built based on an unsupervised deviation detection method, Consensus Self-Organizing Models (COSMO). The method assumes that the majority of a crowd is healthy; individual deviates from the majority are considered as potentially faulty. The COSMO method encodes sensor data into models, and the distances between individual samples and the crowd are measured in the model space. This information, regarding how different an individual performs compared to its peers, is utilized as an indicator for estimating the health status of the equipment. The generality of the COSMO method is demonstrated with three condition monitoring case studies: i) fault detection and failure prediction for a commercial fleet of city buses, ii) prognosis for a fleet of turbofan engines and iii) finding cracks in metallic material. In addition, the flexibility of the COSMO method is demonstrated with: i) being capable of incorporating domain knowledge on specializing relevant expert features; ii) able to detect multiple types of faults with a generic data- representation, i.e. Echo State Network; iii) incorporating expert feedback on adapting reference group candidate under an active learning setting. Last but not least, this thesis demonstrated that the remaining useful life of the equipment can be estimated from the distance to a crowd of peers. 

Place, publisher, year, edition, pages
Halmstad: Halmstad University Press, 2020. p. 87
Series
Halmstad University Dissertations ; 67
National Category
Information Systems
Identifiers
urn:nbn:se:hh:diva-41367 (URN)978-91-88749-43-7 (ISBN)978-91-88749-42-0 (ISBN)
Public defence
2020-01-31, J102 Wigforss, Kristian IV:s väg 3, Halmstad, 13:00 (English)
Opponent
Supervisors
Available from: 2020-01-14 Created: 2020-01-10 Last updated: 2020-01-14Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Chen, KunruPashami, SepidehFan, YuantaoNowaczyk, Sławomir

Search in DiVA

By author/editor
Chen, KunruPashami, SepidehFan, YuantaoNowaczyk, Sławomir
By organisation
CAISR - Center for Applied Intelligent Systems Research
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 2 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf