OPTIMIZATION OF RAILWAY OPERATIONS USING NEURAL NETWORKS

Railroad operations involve complex switching and classification decis ions that must be made in short periods of time. Optimization with res pect to these decisions can be quite difficult due to the discrete and non-linear characteristics of the problem. The train formation plan i s one of the important elements of railroad system operations. While m athematical programming formulations and algorithms are available for solving the train formation problem, the CPU time required for their c onvergence is excessive. At the same time, shorter decision intervals are becoming necessary given the highly competitive operating climates of the railroad industry. The field of Artificial Intelligence (Al) o ffers promising alternatives to conventional optimization approaches. In this paper, neural networks (an empirically-based AI approach) are examined for obtaining good solutions in short time periods for the tr ain formation problem (TFP). Following an overview, and formulation of railroad operations, a neural network formulation and solution to the problem are presented. First a training process for neural network de velopment is conducted followed by a testing process that indicates th at the neural network model will probably be both sufficiently fast, a nd accurate, in producing train formation plans. Copyright (C) 1996 El sevier Science Ltd