NEURAL NETWORK APPROACH FOR SOLVING THE TRAIN FORMATION PROBLEM

The train formation plan is one of the important elements of railroad system operations. Whereas mathematical programming formulations and algorithms are available for solving the train formation problem (TFP), the long CPU time required for convergence makes it difficult to solve the problems in a reasonably short time. At the same time, shorter decision intervals are becoming necessary, given the highly competitive operating climate of the railroad industry. A novel approach is presented for quickly obtaining good solutions to the TFP. A neural network model is developed for efficiently solving the TFP. Following a training process for neural network development, a testing process indicates that the neural network model will likely be both sufficiently fast and accurate in producing train formation plans under on-line conditions.

Language

  • English

Media Info

  • Features: Figures; References; Tables;
  • Pagination: p. 38-46
  • Monograph Title: Railroad research issues
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 00677725
  • Record Type: Publication
  • ISBN: 0309061016
  • Files: TRIS, TRB
  • Created Date: May 22 1995 12:00AM