Performance of lognormal probability distribution in crossover operator of NSGA-II algorithm
SEAL'10 Proceedings of the 8th international conference on Simulated evolution and learning
| Hi-index | 0.00 |
This paper presents the method of selecting an optimum design of turbo-alternator using Multi-objective Differential Evolution-I (MODE-I) algorithm and comparing the optimum design obtained using non-dominated sorting genetic algorithm (NSGA-II). In this paper a real-life problem of turbo-alternator design is considered. Initially the complete design of turbo-alternator is worked out by conventional procedure. In the next stage, the optimization is obtained by using the MODE-I algorithm. This optimum design is compared with the optimum design obtained by the NSGA-II algorithm with simulated binary crossover operator with lognormal distribution (SBX-LN). From the set of results, the suitable optimum design of turbo-alternator is chosen. These results are also verified with the actual parameters of the turbo-alternator design. The results obtained are near global optimum solutions.