Identifying faults contributing to unsafe conditions, such as a high-speed rail vehicle running instability, is crucial to ensuring operational safety. But the occurrence of vehicle running instability during regular operation across the whole vehicle fleet is a rare anomaly. An unsupervised anomaly detection (AD) based iVRIDA-fleet framework is therefore proposed to detect vehicle running instability and identify its root cause. The performance of Principal Component Analysis (PCA-AD, baseline model), Sparse Autoencoder (SAE-AD), and LSTM Encoder Decoder (LSTMEncDec-AD) models are evaluated to detect the occurrence of vehicle running instability. A k-means algorithm is then applied to latent space representations to identify various clusters associated with different root causes of observed vehicle running instability. The effectiveness of the proposed iVRIDA-fleet framework is demonstrated using onboard accelerations measured on a Swedish X2000 vehicle fleet. The probability of vehicle running instability occurrence is observed to be only 0.35% of onboard accelerations corresponding to 827,467 km travel distance. Furthermore, the root causes identified by the iVRIDA-fleet framework are validated by investigating the maintenance records of the vehicles and track. It is identified that heavily worn wheels were the primary root cause of observed vehicle running instability, but the track (actual gauge and rail profiles) was also a contributing factor. The proposed algorithm contributes towards the digitalisation of vehicle and track maintenance by intelligently identifying anomalous events of the vehicle–track dynamic interaction.

    Abbreviations: AD: Anomaly Detection; AL: Alignment Level (Lateral); BDL: TrackSection Id; D1: 3–25 m; wavelength rate of track irregularity; FRA: Federal Railroad Administration (USA); IN2TRACK3: Research into enhanced track and switchand crossing system 3; iVRIDA: Intelligent Vehicle Running Instability Detection Algorithm; iVRIDA-fleet: iVRIDA for fleet; LSTMEncDec: LSTM Encoder Decoder Network; LSTMEncDec-AD: LSTM Encoder Decoder Anomaly Detection; PCA-AD: Principal Component Analysis – Anomaly Detection; SAE-AD: Sparse Autoencoder-Anomaly Detection; TG: Track Gauge; VFI: Vehicle Fault Identification; VFIA: VFIAccuracy; VRID: Vehicle Running Instability Detection; Wz: Wertungszahl Ride Index.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    iVRIDA-fleet: unsupervised rail vehicle running instability detection algorithm for passenger vehicle fleet


    Weitere Titelangaben:

    VEHICLE SYSTEM DYNAMICS
    R. KULKARNI ET AL.


    Beteiligte:
    Kulkarni, Rohan (Autor:in) / Berg, Mats (Autor:in) / Qazizadeh, Alireza (Autor:in) / Söderström, Pör (Autor:in) / Wheelwright, Hugh (Autor:in) / Vincent, David (Autor:in) / Li, Martin (Autor:in)

    Erschienen in:

    Vehicle System Dynamics ; 63 , 2 ; 277-307


    Erscheinungsdatum :

    01.02.2025


    Format / Umfang :

    31 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Unsupervised rail vehicle running instability detection algorithm for passenger trains (iVRIDA)

    Kulkarni, Rohan / Qazizadeh, Alireza / Berg, Mats | BASE | 2023

    Freier Zugriff

    Selecting vehicle for job -- Passenger car fleet

    Mathews, H.O. | Engineering Index Backfile | 1960


    SELECTING THE VEHICLE FOR THE JOB PASSENGER CAR FLEET

    MATHEWS, H. O. | SAE Technical Papers | 1960


    Method for controlling fleet, guiding vehicle, following vehicle and fleet

    KAMPERT DAVE / QIU ZHIHONG / FRANGEN JOACHIM et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    ENERGY OPTIMISATION DURING OPERATION OF A RAIL VEHICLE FLEET

    AUFDERHEIDE HELGE / SIVALINGAM UDHAYARAJ | Europäisches Patentamt | 2025

    Freier Zugriff