Change search
ReferencesLink to record
Permanent link

Direct link
A Self-Organized Fault Detection Method for Vehicle Fleets
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
2016 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

A fleet of commercial heavy-duty vehicles is a very interesting application arena for fault detection and predictive maintenance. With a highly digitized electronic system and hundreds of sensors mounted on-board a modern bus, a huge amount of data is generated from daily operations.

This thesis and appended papers present a study of an autonomous framework for fault detection, using the data gathered from the regular operation of vehicles. We employed an unsupervised deviation detection method, called Consensus Self-Organising Models (COSMO), which is based on the concept of ‘wisdom of the crowd’. It assumes that the majority of the group is ‘healthy’; by comparing individual units within the group, deviations from the majority can be considered as potentially ‘faulty’. Information regarding detected anomalies can be utilized to prevent unplanned stops.

This thesis demonstrates how knowledge useful for detecting faults and predicting failures can be autonomously generated based on the COSMO method, using different generic data representations. The case study in this work focuses on vehicle air system problems of a commercial fleet of city buses. We propose an approach to evaluate the COSMO method and show that it is capable of detecting various faults and indicates upcoming air compressor failures. A comparison of the proposed method with an expert knowledge based system shows that both methods perform equally well. The thesis also analyses the usage and potential benefits of using the Echo State Network as a generic data representation for the COSMO method and demonstrates the capability of Echo State Network to capture interesting characteristics in detecting different types of faults.

Place, publisher, year, edition, pages
Halmstad: Halmstad University Press, 2016. , 116 p.
Series
Halmstad University Dissertations, 27
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:hh:diva-32489ISBN: 978-91-87045-57-8ISBN: 978-91-87045-56-1OAI: oai:DiVA.org:hh-32489DiVA: diva2:1049704
Presentation
2016-12-16, Halda, Kristian IV:s väg 3, 301 18 Halmstad, Halmstad, 10:00 (English)
Opponent
Supervisors
Projects
In4Uptime
Funder
VINNOVA
Available from: 2016-11-28 Created: 2016-11-25 Last updated: 2016-11-28Bibliographically approved
List of papers
1. Using Histograms to Find Compressor Deviations in Bus Fleet Data
Open this publication in new window or tab >>Using Histograms to Find Compressor Deviations in Bus Fleet Data
2014 (English)In: The SAIS Workshop 2014 Proceedings, Swedish Artificial Intelligence Society (SAIS) , 2014, 123-132 p.Conference paper (Refereed)
Abstract [en]

Cost effective methods for predictive maintenance are increasingly demanded in the automotive industry. One solution is to utilize the on-board signals streams on each vehicle and build self-organizing systems that discover data deviations within a fleet. In this paper we evaluate histograms as features for describing and comparing individual vehicles. The results are based on a long-term field test with nineteen city buses operating around Kungsbacka in Halland. The purpose of this work is to investigate ways of discovering abnormal behaviors and irregularities between histograms of on-board signals, here specifically focusing on air pressure. We compare a number of distance measures and analyze the variability of histograms collected over different time spans. Clustering algorithms are used to discover structure in the data and track how this changes over time. As data are compared across the fleet, observed deviations should be matched against (often imperfect) reference data coming from workshop maintenance and repair databases.

Place, publisher, year, edition, pages
Swedish Artificial Intelligence Society (SAIS), 2014
Keyword
Predictive maintenance, Diagnostics, Deviation detection
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-26572 (URN)
Conference
The Swedish AI Society (SAIS) Workshop 2014, Stockholm, Sweden, May 22-23, 2014
Available from: 2014-09-24 Created: 2014-09-24 Last updated: 2016-11-28Bibliographically approved
2. Evaluation of Self-Organized Approach for Predicting Compressor Faults in a City Bus Fleet
Open this publication in new window or tab >>Evaluation of Self-Organized Approach for Predicting Compressor Faults in a City Bus Fleet
2015 (English)In: Procedia Computer Science, ISSN 1877-0509, E-ISSN 1877-0509, Vol. 53, 447-456 p.Article in journal (Refereed) Published
Abstract [en]

Managing the maintenance of a commercial vehicle fleet is an attractive application domain of ubiquitous knowledge discovery. Cost effective methods for predictive maintenance are progressively demanded in the automotive industry. The traditional diagnostic paradigm that requires human experts to define models is not scalable to today's vehicles with hundreds of computing units and thousands of control and sensor signals streaming through the on-board controller area network. A more autonomous approach must be developed. In this paper we evaluate the performance of the COSMO approach for automatic detection of air pressure related faults on a fleet of city buses. The method is both generic and robust. Histograms of a single pressure signal are collected and compared across the fleet and deviations are matched against workshop maintenance and repair records. It is shown that the method can detect several of the cases when compressors fail on the road, well before the failure. The work is based on data from a three year long field study involving 19 buses operating in and around a city on the west coast of Sweden. © The Authors. Published by Elsevier B.V.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2015
Keyword
Vehicle diagnostics, predictive maintenance, fault detection, self-organizing systems
National Category
Signal Processing Information Systems
Identifiers
urn:nbn:se:hh:diva-29240 (URN)10.1016/j.procs.2015.07.322 (DOI)000360311000051 ()2-s2.0-84939156791 (ScopusID)
Conference
INNS Conference on Big Data, San Francisco, CA, USA, 8-10 August, 2015
Projects
In4Uptime
Funder
VINNOVA
Available from: 2015-08-19 Created: 2015-08-19 Last updated: 2016-11-28Bibliographically approved
3. Incorporating Expert Knowledge into a Self-Organized Approach for Predicting Compressor Faults in a City Bus Fleet
Open this publication in new window or tab >>Incorporating Expert Knowledge into a Self-Organized Approach for Predicting Compressor Faults in a City Bus Fleet
2015 (English)In: Frontiers in Artificial Intelligence and Applications, ISSN 0922-6389, E-ISSN 1879-8314, Vol. 278, 58-67 p.Article in journal (Refereed) Published
Abstract [en]

In the automotive industry, cost effective methods for predictive maintenance are increasingly in demand. The traditional approach for developing diagnostic methods on commercial vehicles is heavily based on knowledge of human experts, and thus it does not scale well to modern vehicles with many components and subsystems. In previous work we have presented a generic self-organising approach called COSMO that can detect, in an unsupervised manner, many different faults. In a study based on a commercial fleet of 19 buses operating in Kungsbacka, we have been able to predict, for example, fifty percent of the compressors that break down on the road, in many cases weeks before the failure.

In this paper we compare those results with a state of the art approach currently used in the industry, and we investigate how features suggested by experts for detecting compressor failures can be incorporated into the COSMO method. We perform several experiments, using both real and synthetic data, to identify issues that need to be considered to improve the accuracy. The final results show that the COSMO method outperforms the expert method.

Place, publisher, year, edition, pages
Amsterdam: IOS Press, 2015
Keyword
Vehicle diagnostics, Predictive maintenance, Fault detection, Receiver Operating Characteristic curve, Expert knowledge
National Category
Computer and Information Science
Identifiers
urn:nbn:se:hh:diva-29809 (URN)10.3233/978-1-61499-589-0-58 (DOI)2-s2.0-84963636151 (ScopusID)
Conference
The 13th Scandinavian Conference on Artificial Intelligence (SCAI), Halmstad University, Halmstad, Sweden, 5-6 November, 2015
Projects
In4Uptime
Funder
VINNOVAKnowledge Foundation
Note

ISBN: 978-1-61499-588-3 (print) | 978-1-61499-589-0 (online)

Editor: Sławomir Nowaczyk

Available from: 2015-11-24 Created: 2015-11-24 Last updated: 2016-11-28Bibliographically approved
4. Predicting Air Compressor Failures with Echo State Networks
Open this publication in new window or tab >>Predicting Air Compressor Failures with Echo State Networks
2016 (English)In: PHME 2016: Proceedings of the Third European Conference of the Prognostics and Health Management Society 2016 / [ed] Ioana Eballard, Anibal Bregon, PHM Society , 2016, 568-578 p.Conference paper (Refereed)
Abstract [en]

Modern vehicles have increasing amounts of data streaming continuously on-board their controller area networks. These data are primarily used for controlling the vehicle and for feedback to the driver, but they can also be exploited to detect faults and predict failures. The traditional diagnostics paradigm, which relies heavily on human expert knowledge, scales poorly with the increasing amounts of data generated by highly digitised systems. The next generation of equipment monitoring and maintenance prediction solutions will therefore require a different approach, where systems can build up knowledge (semi-)autonomously and learn over the lifetime of the equipment.

A key feature in such systems is the ability to capture and encode characteristics of signals, or groups of signals, on-board vehicles using different models. Methods that do this robustly and reliably can be used to describe and compare the operation of the vehicle to previous time periods or to other similar vehicles. In this paper two models for doing this, for a single signal, are presented and compared on a case of on-road failures caused by air compressor faults in city buses. One approach is based on histograms and the other is based on echo state networks. It is shown that both methods are sensitive to the expected changes in the signal's characteristics and work well on simulated data. However, the histogram model, despite being simpler, handles the deviations in real data better than the echo state network.

Place, publisher, year, edition, pages
PHM Society, 2016
Keyword
predictive maintenance, fault detection, Vehicle diagnostics, reservoir model, echo state network
National Category
Vehicle Engineering
Identifiers
urn:nbn:se:hh:diva-31644 (URN)978-1-936263-21-9 (ISBN)
Conference
Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016
Projects
In4Uptime
Funder
VINNOVA
Available from: 2016-07-14 Created: 2016-07-14 Last updated: 2016-11-28Bibliographically approved
5. Evaluation of Micro-flaws in Metallic Material Based on A Self-Organized Data-driven Approach
Open this publication in new window or tab >>Evaluation of Micro-flaws in Metallic Material Based on A Self-Organized Data-driven Approach
2016 (English)In: 2016 IEEE International Conference on Prognostics and Health Management (ICPHM), IEEE conference proceedings, 2016Conference paper, Poster (Refereed)
Abstract [en]

Evaluating the health condition of a material that could potentially contain micro-flaws is a common and important application within the field of non-destructive testing. Examples of such micro-defects include dislocation, fatigue cracks or impurities and are often hard to detect. The ability to precisely measure their type, size and position is a prerequisite for estimating the remaining useful life of the component. One technique that was shown successful in the past is based on traditional ultrasonic testing methods. In most cases, inner micro-flaws induce slight changes of acoustic wave spectrum components. However, these changes are often difficult to detect directly, as they tend to exhibit features that are most naturally analyzed using statistical and probabilistic methods. In this paper we apply Consensus Self-Organizing Models (COSMO) method to detect micro-flaws in metallic material. This approach is essentially an unsupervised deviation detection method based on the concept of "wisdom of the crowd". This method is used to analyze the spectrum of acoustic waves received by the transducer attached on the surface of material being analyzed. We have modeled a steel board with micro-cracks and collected time-series of acoustic echo response, at different positions on material's surface. The experimental results show that the COSMO method is able to detect and locate micro-flaws. © 2016 IEEE

Place, publisher, year, edition, pages
IEEE conference proceedings, 2016
Keyword
Non-destructive testing, ultrasonic, micro-defects
National Category
Other Medical Engineering
Identifiers
urn:nbn:se:hh:diva-31646 (URN)10.1109/ICPHM.2016.7542868 (DOI)978-1-5090-0382-2 (ISBN)
Conference
2016 IEEE International Conference on Prognostics and Health Management, Carleton University, Ottawa, ON, Canada, June 20-22, 2016
Available from: 2016-07-14 Created: 2016-07-14 Last updated: 2016-11-28Bibliographically approved

Open Access in DiVA

fulltext(12180 kB)13 downloads
File information
File name FULLTEXT01.pdfFile size 12180 kBChecksum SHA-512
796e62f9a14752aa90e9835fcb015837bd52326e43ab647d23c7592c1ac85701a61124c40a32a5715a190b00fb56795a2053edac5716d6528e42e0b0cadd1c04
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Fan, Yuantao
By organisation
CAISR - Center for Applied Intelligent Systems Research
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 13 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 24 hits
ReferencesLink to record
Permanent link

Direct link