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

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 al-gorithms 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.

Automated summary

Intelligently identifying rail vehicle faults that cause running instability is crucial for safety and cost reduction. However, the complexities of vehicle-track interaction and scarcity of instability occurrences make this task challenging. We propose an unsupervised anomaly detection and clustering algorithm based on the iVRIDA framework to detect and identify running instability and its root cause. We compared the performance of three models (PCA-AD, SAE-AD, LSTMEncDec-AD) for detecting instability and used a k-means algorithm to identify clusters associated with root causes. Our method achieved a 97% accuracy in simulated and measured accelerations of European high-speed rail vehicles, contributing to smart maintenance by intelligently identifying anomalous vehicle-track interaction events.