Submarine manoeuvring controllers' optimisation using simulated annealing and genetic algorithms

This paper is concerned with non-linear controller parameter optimisation for the diving and heading motions of a submarine model. The structure of the non-linear controllers used for these manoeuvres is derived from Sliding Mode control theory for decoupled single input, single output systems. The performance of these controllers depends on key design parameters. In this comparative study the values of these controller parameters are optimised using three different optimisation techniques. These are simulated annealing, segmented simulated annealing and genetic algorithms. The search properties of these algorithms are defined and compared in terms of simulated time domain results, convergence and saturation properties, These results are used to show the advantages and disadvantages of each optimisation technique. (c) 2005 Elsevier Ltd. All rights reserved.