Change search
ReferencesLink to record
Permanent link

Direct link
Big Data Analytics for Fault Detection and its Application in Maintenance
Luleå University of Technology, Department of Civil, Environmental and Natural Resources Engineering, Operation, Maintenance and Acoustics. (eMaintenance)ORCID iD: 0000-0001-7310-5717
2016 (English)Doctoral thesis, comprehensive summary (Other academic)Alternative title
Big Data Analytics för Feldetektering och Applicering inom Underhåll (Swedish)
Abstract [en]

Big Data analytics has attracted intense interest recently for its attempt to extract information, knowledge and wisdom from Big Data. In industry, with the development of sensor technology and Information & Communication Technologies (ICT), reams of high-dimensional, streaming, and nonlinear data are being collected and curated to support decision-making. The detection of faults in these data is an important application in eMaintenance solutions, as it can facilitate maintenance decision-making. Early discovery of system faults may ensure the reliability and safety of industrial systems and reduce the risk of unplanned breakdowns.

Complexities in the data, including high dimensionality, fast-flowing data streams, and high nonlinearity, impose stringent challenges on fault detection applications. From the data modelling perspective, high dimensionality may cause the notorious “curse of dimensionality” and lead to deterioration in the accuracy of fault detection algorithms. Fast-flowing data streams require algorithms to give real-time or near real-time responses upon the arrival of new samples. High nonlinearity requires fault detection approaches to have sufficiently expressive power and to avoid overfitting or underfitting problems.

Most existing fault detection approaches work in relatively low-dimensional spaces. Theoretical studies on high-dimensional fault detection mainly focus on detecting anomalies on subspace projections. However, these models are either arbitrary in selecting subspaces or computationally intensive. To meet the requirements of fast-flowing data streams, several strategies have been proposed to adapt existing models to an online mode to make them applicable in stream data mining. But few studies have simultaneously tackled the challenges associated with high dimensionality and data streams. Existing nonlinear fault detection approaches cannot provide satisfactory performance in terms of smoothness, effectiveness, robustness and interpretability. New approaches are needed to address this issue.

This research develops an Angle-based Subspace Anomaly Detection (ABSAD) approach to fault detection in high-dimensional data. The efficacy of the approach is demonstrated in analytical studies and numerical illustrations. Based on the sliding window strategy, the approach is extended to an online mode to detect faults in high-dimensional data streams. Experiments on synthetic datasets show the online extension can adapt to the time-varying behaviour of the monitored system and, hence, is applicable to dynamic fault detection. To deal with highly nonlinear data, the research proposes an Adaptive Kernel Density-based (Adaptive-KD) anomaly detection approach. Numerical illustrations show the approach’s superiority in terms of smoothness, effectiveness and robustness.

Place, publisher, year, edition, pages
Luleå, Sweden: Luleå University of Technology, 2016. , 72 p.
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
Keyword [en]
Big Data analytics, eMaintenance, fault detection, high-dimensional data, stream data mining, nonlinear data
National Category
Other Engineering and Technologies not elsewhere specified
Research subject
Operation and Maintenance
Identifiers
URN: urn:nbn:se:ltu:diva-60423ISBN: 978-91-7583-769-7ISBN: 978-91-7583-770-3 (pdf)OAI: oai:DiVA.org:ltu-60423DiVA: diva2:1046794
Public defence
2017-01-27, F1031, Luleå University of Technology, 971 87, Luleå, 10:00 (English)
Opponent
Supervisors
Available from: 2016-11-15 Created: 2016-11-15 Last updated: 2016-12-01Bibliographically approved
List of papers
1. An Angle-based Subspace Anomaly Detection Approach to High-dimensional Data: With an Application to Industrial Fault Detection
Open this publication in new window or tab >>An Angle-based Subspace Anomaly Detection Approach to High-dimensional Data: With an Application to Industrial Fault Detection
2015 (English)In: Reliability Engineering & System Safety, ISSN 0951-8320, E-ISSN 1879-0836, Vol. 142, 482–497- p.Article in journal (Refereed) Published
Abstract [en]

The accuracy of traditional anomaly detection techniques implemented on full-dimensional spaces degrades significantly as dimensionality increases, thereby hampering many real-world applications. This work proposes an approach to selecting meaningful feature subspace and conducting anomaly detection in the corresponding subspace projection. The aim is to maintain the detection accuracy in high-dimensional circumstances. The suggested approach assesses the angle between all pairs of two lines for one specific anomaly candidate: the first line is connected by the relevant data point and the center of its adjacent points; the other line is one of the axis-parallel lines. Those dimensions which have a relatively small angle with the first line are then chosen to constitute the axis-parallel subspace for the candidate. Next, a normalized Mahalanobis distance is introduced to measure the local outlier-ness of an object in the subspace projection. To comprehensively compare the proposed algorithm with several existing anomaly detection techniques, we constructed artificial datasets with various high-dimensional settings and found the algorithm displayed superior accuracy. A further experiment on an industrial dataset demonstrated the applicability of the proposed algorithm in fault detection tasks and highlighted another of its merits, namely, to provide preliminary interpretation of abnormality through feature ordering in relevant subspaces.

Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-13556 (URN)10.1016/j.ress.2015.05.025 (DOI)ccb88d21-0f57-4412-9035-a6b9f78de9c7 (Local ID)ccb88d21-0f57-4412-9035-a6b9f78de9c7 (Archive number)ccb88d21-0f57-4412-9035-a6b9f78de9c7 (OAI)
Note
Validerad; 2015; Nivå 2; 20150531 (liazha)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2016-11-15Bibliographically approved
2. Sliding Window-based Fault Detection from High-dimensional Data Streams
Open this publication in new window or tab >>Sliding Window-based Fault Detection from High-dimensional Data Streams
2016 (English)In: IEEE Transactions on Systems, Man & Cybernetics. Systems, ISSN 2168-2216, 7509594Article in journal (Refereed) Epub ahead of print
Abstract [en]

High-dimensional data streams are becoming increasingly ubiquitous in industrial systems. Efficient detection of system faults from these data can ensure the reliability and safety of the system. The difficulties brought about by high dimensionality and data streams are mainly the ``curse of dimensionality'' and concept drifting, and one current challenge is to simultaneously address them. To this purpose, this paper presents an approach to fault detection from nonstationary high-dimensional data streams. An angle-based subspace anomaly detection approach is proposed to detect low-dimensional subspace faults from high-dimensional datasets. Specifically, it selects fault-relevant subspaces by evaluating vectorial angles and computes the local outlier-ness of an object in its subspace projection. Based on the sliding window strategy, the approach is further extended to an online mode that can continuously monitor system states. To validate the proposed algorithm, we compared it with the local outlier factor-based approaches on artificial datasets and found the algorithm displayed superior accuracy. The results of the experiment demonstrated the efficacy of the proposed algorithm. They also indicated that the algorithm has the ability to discriminate low-dimensional subspace faults from normal samples in high-dimensional spaces and can be adaptive to the time-varying behavior of the monitored system. The online subspace learning algorithm for fault detection would be the main contribution of this paper.

National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-12680 (URN)10.1109/TSMC.2016.2585566 (DOI)bd869fb2-6668-49d9-9511-535c94003f4f (Local ID)bd869fb2-6668-49d9-9511-535c94003f4f (Archive number)bd869fb2-6668-49d9-9511-535c94003f4f (OAI)
Note

Upprättat; 2016; 20160713 (liazha)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2016-12-02
3. Adaptive Kernel Density-based Anomaly Detection for Nonlinear Systems
Open this publication in new window or tab >>Adaptive Kernel Density-based Anomaly Detection for Nonlinear Systems
2016 (English)Article in journal (Refereed) Submitted
Abstract [en]

This paper presents an unsupervised, density-based approach to anomaly detection. The purpose is to define a smooth yet effective measure of outlierness that can be used to detect anomalies in nonlinear systems. The approach assigns each sample a local outlier score indicating how much one sample deviates from others in its locality. Specifically, the local outlier score is defined as a relative measure of local density between a sample and a set of its neighboring samples. To achieve smoothness in the measure, we adopt the Gaussian kernel function. Further, to enhance its discriminating power, we use adaptive kernel width: in high-density regions, we apply wide kernel widths to smooth out the discrepancy between normal samples; in low-density regions, we use narrow kernel widths to intensify the abnormality of potentially anomalous samples. The approach is extended to an online mode with the purpose of detecting anomalies in stationary data streams. To validate the proposed approach, we compare it with several alternatives using synthetic datasets; the approach is found superior in terms of smoothness, effectiveness and robustness. A further experiment on a real-world dataset demonstrated the applicability of the proposed approach in fault detection tasks.

Keyword
maintenance modelling, fault detection, unsupervised learning, nonlinear data, kernel density
National Category
Other Engineering and Technologies not elsewhere specified Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
urn:nbn:se:ltu:diva-60425 (URN)
Available from: 2016-11-15 Created: 2016-11-15 Last updated: 2016-11-23

Open Access in DiVA

knbe(8028 kB)1 downloads
File information
File name FULLTEXT01.pdfFile size 8028 kBChecksum SHA-512
cda0656f0716f856bf3b91afc1f30cb804b3acd84a03818b16a883f1e4d356c21c8d8472e11c2ed39b0951c8538e223c517753db893bac7439442a4f8dc22d2f
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Zhang, Liangwei
By organisation
Operation, Maintenance and Acoustics
Other Engineering and Technologies not elsewhere specified

Search outside of DiVA

GoogleGoogle Scholar
Total: 1 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: 44 hits
ReferencesLink to record
Permanent link

Direct link