Neural Network Approach to Railway Stand Lateral Skew Control
This work addresses a specific control problem in railway engineering, but it appears incremental as it applies existing neural network techniques to a new experimental setup.
The paper tackled lateral skew control in a railway stand by using neural networks for modeling and control, achieving experimental results through various neural architectures and training methods.
The paper presents a study of an adaptive approach to lateral skew control for an experimental railway stand. The preliminary experiments with the real experimental railway stand and simulations with its 3-D mechanical model, indicates difficulties of model-based control of the device. Thus, use of neural networks for identification and control of lateral skew shall be investigated. This paper focuses on real-data based modeling of the railway stand by various neural network models, i.e; linear neural unit and quadratic neural unit architectures. Furthermore, training methods of these neural architectures as such, real-time-recurrent-learning and a variation of back-propagation-through-time are examined, accompanied by a discussion of the produced experimental results.