kth.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
Unsupervised rail vehicle running instability detection algorithm for passenger trains (iVRIDA)
KTH, School of Engineering Sciences (SCI), Engineering Mechanics. KTH, School of Engineering Sciences (SCI), Centres, The KTH Railway Group.ORCID iD: 0000-0001-5644-248x
KTH, School of Engineering Sciences (SCI), Engineering Mechanics. KTH, School of Engineering Sciences (SCI), Centres, The KTH Railway Group.ORCID iD: 0000-0002-0875-3520
KTH, School of Engineering Sciences (SCI), Centres, The KTH Railway Group. KTH, School of Engineering Sciences (SCI), Engineering Mechanics.ORCID iD: 0000-0002-2571-4662
2023 (English)In: Measurement, ISSN 0263-2241, E-ISSN 1873-412X, Vol. 216, p. 112894-112894, article id 112894Article in journal (Refereed) Published
Abstract [en]

Intelligently identifying rail vehicle faults instigating running instability from carbody floor acceleration is essential to ensure operational safety and reduce maintenance costs. However, the vehicle-track interaction's nonlinearities and scarcity of running instability occurrences complicate the task. The running instability is an anomaly in the vehicle-track interaction. Thus, we propose unsupervised anomaly detection and clustering algorithms based iVRIDA framework to detect and identify running instability and corresponding root cause. We deploy and compare the performance of the PCA-AD (baseline), Sparse Autoencoder (SAE-AD), and LSTM-Encoder-Decoder (LSTMEncDec-AD) model to detect the running instability occurrences.

Furthermore, we deploy a k-means algorithm on latent space to identify clusters associated with root causes instigating instability. We deployed the iVRIDA framework on simulated and measured accelerations of European high-speed rail vehicles where SAE-AD and LSTMEncDec-AD models showed 97% accuracy. The proposed method contributes to smart maintenance by intelligently identifying anomalous vehicle-track interaction events.

Place, publisher, year, edition, pages
Elsevier, 2023. Vol. 216, p. 112894-112894, article id 112894
Keywords [en]
Vehicle hunting; unsupervised machine learning; Sparse Autoencoder; LSTM Encoder Decoder; worn wheel; failed yaw damper
National Category
Vehicle and Aerospace Engineering
Research subject
Vehicle and Maritime Engineering
Identifiers
URN: urn:nbn:se:kth:diva-326371DOI: 10.1016/j.measurement.2023.112894ISI: 000990508000001Scopus ID: 2-s2.0-85153567490OAI: oai:DiVA.org:kth-326371DiVA, id: diva2:1753927
Projects
PIVOT2
Funder
Swedish Transport Administration, Research Excellence Area IEuropean Commission, European Union’s Horizon 2020 research and innovation programme under Grant Agreement No 881807 (PIVOT II)
Note

QC 20230607

Available from: 2023-05-02 Created: 2023-05-02 Last updated: 2025-02-14Bibliographically approved
In thesis
1. Onboard condition monitoring of vehicle-track dynamic interaction using machine learning: Enabling the railway industry’s digital transformation
Open this publication in new window or tab >>Onboard condition monitoring of vehicle-track dynamic interaction using machine learning: Enabling the railway industry’s digital transformation
2023 (English)Doctoral thesis, comprehensive summary (Other academic)
Alternative title[sv]
Tillståndsövervakning ombord av dynamisk interaktion mellan fordon och spår med hjälp av maskininlärning : Möjliggörande av järnvägsbranschens digitala transformation
Abstract [en]

The railway sector’s reliability, availability, maintainability, and safety (RAMS) can significantly improve by adopting condition based maintenance (CBM). In the CBM regime, maintenance decisions are driven by condition monitoring (CM) of the asset. This thesis proposes machine learning (ML) based onboard CM (OCM) algorithms for CM of vehicle-track dynamic interaction via vehicle response (VR). More specifically, the algorithms are developed to monitor track irregularities (TI) and vehicle running instability incidences (VRII) via VR.

CM of TI from onboard accelerations is a cost-effective method for daily surveillance of tracks. Most of the latest research is focused on monitoring vertical irregularity via vertical accelerations. Less attention is given to monitoring alignment level (AL) and cross level (CL) track irregularities. The PhD thesis proposes an ML based OCM algorithm to identify track sections with AL and CL  track irregularities exceeding maintenance thresholds via bogie frame accelerations (BFAs). In this thesis, the OCM algorithm’s supervised ML models are trained on BFAs’ datasets synthesized with multibody simulation (MBS) of a high-speed diagnostic vehicle. Furthermore, the trained ML models and OCM algorithm are validated with measurements acquired by the same high-speed vehicle. The proposed OCM algorithm shows excellent performance in track quality surveillance only from BFAs. 

OCM of vehicle running instability (VRI) is important to ensure safety and onboard ride comfort. The latest research focuses on designing OCM algorithms for detecting VRI, but these OCM algorithms lack fault diagnosis (FD) of detected VRII. The PhD thesis proposes various OCM algorithms under an "intelligent vehicle running instability detection algorithm" (iVRIDA) umbrella to detect VRII and diagnose corresponding root causes via carbody accelerations. The occurrence of VRI during regular operation across a whole train fleet is an anomaly. Thus, an unsupervised anomaly detection (AD) based iVRIDA algorithm is proposed and later extended as iVRIDA-fleet for vehicle fleetwide application. The proposed OCM algorithms iVRIDA and iVRIDA-fleet are verified by onboard measurements of a European high-speed vehicle and the Swedish X2000 vehicle fleet.

The thesis contributes towards the digitalization of vehicle and track maintenance by enabling adaptation of the CBM regime.

Abstract [sv]

Järnvägssektorns tillförlitlighet, tillgänglighet, underhållsmässighet och säkerhet (RAMS) kan förbättras avsevärt genom att införa tillståndsbaserat underhåll (CBM). I CBM-regimen drivs underhållsbeslut av tillståndsövervakning (CM) av tillgången. Denna avhandling föreslår maskininlärning (ML) baserade omboard CM (OCM) algoritmer för CM av fordon-spår dynamisk interaktion via fordonsrespons (VR). Mer specifikt utvecklas algoritmerna för att övervaka spårlägesfel (TI) och fordonsinstabilitets (VRII) via VR.

CM av TI från accelerationer ombord är en kostnadseffektiv metod för daglig övervakning av spår. Det mesta av den senaste forskningen är inriktad på att övervaka vertikal oregelbundenhet via vertikala accelerationer. Mindre uppmärksamhet ägnas åt övervakning av oegentligheter i lateralled (AL) och rälsförhöiningsfel (CL). Doktorsavhandlingen föreslår en ML-baserad OCM-algoritm för att identifiera spårsektioner med AL- och CL-spåroregelbundenheter som överskrider underhållströsklar via boggiramaccelerationer (BFA). I denna avhandling tränas OCM-algoritmens övervakade ML-modeller på BFAs' data syntetiserade med flerkropps-simulering (MBS) av ett höghastighetsfordon. Dessutom valideras de tränade ML-modellerna och OCM-algoritmen med mätningar som erhållets från samma höghastighetsfordon. Den föreslagna OCM-algoritmen visar utmärkt prestanda vid övervakning av spårkvalitet endast från BFA.

OCM för fordonets gånginstabilitet (VRI) är viktigt för att säkerställa säkerhet och komfort. Den senaste forskningen fokuserar på att designa OCM-algoritmer för att upptäcka VRI, men dessa OCM-algoritmer saknar feldiagnos (FD) av detekterad VRII. Doktorsavhandlingen föreslår olika OCM-algoritmer under ett "intelligent vehicle running instability detection algorithm" (iVRIDA) paraply för att upptäcka VRII och diagnostisera motsvarande grundorsaker via korgsaccelerationer. Förekomsten av VRI under regelbunden drift över en hel tågflotta är en anomali. Således föreslås en oövervakad anomalidetektering (AD) baserad iVRIDA algoritm och utvidgas senare som iVRIDA-fleet för fordonsparksomfattande applikation.

De föreslagna OCM-algoritmerna iVRIDA och iVRIDA-fleet verifieras genom mätningar ombord av ett europeiskt höghastighetsfordon och den svenska fordonsflottan X2000.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2023. p. 1-95
Series
TRITA-SCI-FOU ; 2023:19
Keywords
Active preventive maintenance, intelligent fault diagnosis, anomaly detection, vehicle fleet, track irregularities, vehicle hunting, wheel-rail interface.
National Category
Vehicle and Aerospace Engineering
Research subject
Vehicle and Maritime Engineering
Identifiers
urn:nbn:se:kth:diva-326616 (URN)978-91-8040-542-3 (ISBN)
Public defence
2023-06-01, https://kth-se.zoom.us/j/68259826119, F3, Lindstedtsvägen 26, Stockholm, 10:00 (English)
Opponent
Supervisors
Funder
EU, Horizon 2020, Shift2Rail Projects IN2TRACK2, IN2TRACK3, PIVOT2Swedish Transport Administration, Research Excellence Area 1 and RV-29 via the KTH Railway Group
Available from: 2023-05-10 Created: 2023-05-09 Last updated: 2025-02-14Bibliographically approved

Open Access in DiVA

iVRIDA_published(8115 kB)164 downloads
File information
File name FULLTEXT01.pdfFile size 8115 kBChecksum SHA-512
5986c8b9d9e022c7c171ff7f90fe471c5865bdd59a178bc7d1669cc5c786a9af6508428be4c89bb76443eadd669133f9a5b77214e3d78e19b40cab1e1828a7d8
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopushttps://www.sciencedirect.com/science/article/pii/S026322412300458X

Authority records

Kulkarni, RohanQazizadeh, AlirezaBerg, Mats

Search in DiVA

By author/editor
Kulkarni, RohanQazizadeh, AlirezaBerg, Mats
By organisation
Engineering MechanicsThe KTH Railway Group
In the same journal
Measurement
Vehicle and Aerospace Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 165 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

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 588 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