Peter Mark Benes, Matous Cejnek, Jan Kalivoda and Ivo Bukovsky, Czech Technical University, Czech Republic

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 modelling 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.

Roller Rig, Linear Neural Unit, Quadratic Neural Unit, Real-Time-Recurrent-Learning (RTRL), Back-Propagation-Through-Time (BPTT)