Initially, three types of faults are considered, including superelevation, wheel burnt, and normal tracks. Two convolutional neural networks (CNN) models, convolutional 1D and convolutional 2D, and one recurrent neural network (RNN) model, a long short-term memory (LSTM) model, are used in this regard. This study proposes the use of traditional acoustic-based systems with deep learning models to increase performance and reduce train accidents. Currently, in Pakistan, rail tracks are inspected by an acoustic-based manual system that requires a railway engineer as a domain expert to differentiate between different rail tracks’ faults, which is cumbersome, laborious, and error-prone. The periodic inspection of railroad tracks is very important to find structural and geometrical problems that lead to railway accidents.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |