Analysis of positioning of wayside charging stations for hybrid locomotive consists in heavy haul train operations

Hybrid locomotive concepts have been considered as a step towards converting the railway industry into a green transport mode.One of the challenges in integrating a hybrid locomotive in the train consist is that the battery pack in the locomotive needs to be recharged during a long-haul trip which requires stopping of the train.A typical battery pack requires about 1 h to recharge which is unacceptable.With the improvement in the charging system,it is now possible that the same capacity battery pack could be recharged in 10–12 min which can be a competitive option for the railway companies.This paper proposes a method based on simulation to evaluate the positioning of charging stations on a train network.A typical example of a heavy haul train operation hauled by diesel-electric and hybrid locomotives is used to demonstrate the method by using simulation softwares.The result of the simulation study show that the method developed in this paper can be used to evaluate the state of charge(SoC)status of a hybrid locomotive along the track.It is also shown that the SoC status obtained by the simulation method can be further used to assess the positions of charging stations along the track at the design stage.

A strategy for out-of-roundness damage wheels identification in railway vehicles based on sparse autoencoders

Wayside monitoring is a promising cost-effective alternative to predict damage in the rolling stock. The main goal of this work is to present an unsupervised methodology to identify out-of-roundness(OOR) damage wheels, such as wheel flats and polygonal wheels. This automatic damage identification algorithm is based on the vertical acceleration evaluated on the rails using a virtual wayside monitoring system and involves the application of a two-step procedure. The first step aims to define a confidence boundary by using(healthy) measurements evaluated on the rail constituting a baseline. The second step of the procedure involves classifying damage of predefined scenarios with different levels of severities. The proposed procedure is based on a machine learning methodology and includes the following stages:(1) data collection,(2) damage-sensitive feature extraction from the acquired responses using a neural network model, i.e., the sparse autoencoder(SAE),(3) data fusion based on the Mahalanobis distance, and(4) unsupervised feature classification by implementing outlier and cluster analysis. This procedure considers baseline responses at different speeds and rail irregularities to train the SAE model. Then, the trained SAE is capable to reconstruct test responses(not trained) allowing to compute the accumulative difference between original and reconstructed signals. The results prove the efficiency of the proposed approach in identifying the two most common types of OOR in railway wheels.