IMPROVED OPTIMIZATION METHOD USING GENETIC ALGORITHMS FOR MASS-TRANSIT SIGNALING BLOCK-LAYOUT DESIGN

The application of an improved optimisation technique to an existing b lock-layout design process is proposed for equi-block n-aspect (n grea ter than or equal to 2) mass transit signalling systems. The approach is built upon previous published work by applying genetic algorithms ( GA) in place of conventional gradient search methods. The genetic algo rithms have been proven theoretically and empirically for providing mu ltiple-point search, as well as robust and global convergence in compl ex search spaces. Such characteristics have enabled GAs to simplify th e original approach and to broaden its scope for dealing with either c hanges of the objective function or changes of the signalling scheme. In the proposed formulation, a railway line between two stations is di vided into three sections, namely: a constraint section, a stretchable section and a critical section. Since each of these sections is presc ribed with a different headway design criterion, GA is applied separat ely to each section to optimise the layout of block joints and their p ositions within each section. Train performance simulation is then use d to verify each optimised signalling design against the overall requi rements of mass transit signalling systems operation. It is also used to calculate the objective function for each candidate solution as gen erated by GA. Comparative studies are presented to show improvements m ade by GAs over conventional optimisation techniques.