Axlebox bearings are one of the most critical components of a rail vehicle with regard to safety. An axlebox bearing that breaks during operation can be dangerous for the passengers and expensive for the operator. In-service failure of axlebox bearings has been the cause of many catastrophic accidents. Thus, it is of utmost importance to predict bearing failures as early as possible. This will increase reliability and safety of the vehicle as well as reduce the vehicle maintenance cost. Monitoring of roller bearings is an active research eld, and many methods have been proposed by other researchers. Many of these methods employ complex algorithms to make the most use of the given measurements. The algorithms often lack interpretability and have high computational costs, making them dicult to employ in an on-board system. This thesis proposes an interpretable and transparent algorithm that predicts bearing damages with high accuracy. Meanwhile, it tries to retain interpretability as much as possible. The algorithm is based on Empirical Mode Decomposition (EMD) and Singular Value Decomposition (SVD). These two techniques extract essential and meaningful information from the axlebox accelerations. The algorithm is benchmarked on two benchmark datasets, and the results are compared to the respective literature. Then the algorithm is employed on the railway axlebox acceleration measurements that were taken on an axlebox test bench available at SWJTU. The proposed algorithm can be extended to incorporate additional measurements of dierent types, e.g. sound or temperature measurements. The incorporation of other types of measurements will improve the performance of the algorithm even further. ; Axelbox lager är en av de viktigaste komponenterna i ett järnvägsfordon när det berör säkerheten. Ett axelbox lager som havererar under drift kan vara farligt for passagerarna och även dyrt för operatören. Driftfel av lagren har varit orsaken till många katastrofala olyckor. Därför är det av yttersta vikt att förutsäga lagerfel ...


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Fault diagnosis of axlebox roller bearings of high speed rail vehicles based on empirical mode decomposition and machine learning ; Feldiagnos av axelbox rullager i höghastighetstågfordon baserat på Empirical Mode Decomposition och maskininlärning


    Beteiligte:

    Erscheinungsdatum :

    2021-01-01


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Fault Diagnosis of Train Wheels Based on Empirical Mode Decomposition Generalized Energy

    Chen, Yejian / Wang, Xiaolong / Zhang, Yong et al. | British Library Conference Proceedings | 2018




    Empirical mode decomposition on skeletonization pruning

    Krinidis, S. / Krinidis, M. | British Library Online Contents | 2013