Dimensional synthesis of a five-point double-toggle mould clamping mechanism using a genetic algorithm—differential evolution hybrid algorithm
Wen‐Yi Lin, Shengwen Wang · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · 2009
A hybrid evolutionary algorithm by combining real-valued genetic algorithm (RGA) with differential evolution (DE) has been proposed by the first author. This is termed the ‘GA—DE hybrid algorithm’. The only difference between the GA—DE hybrid algorithm and the RGA is in the content of the crossover. The crossover operation in the RGA is replaced by differential vector perturbation, with the best individual or some excellent individuals as the base vectors. In this work, the GA—DE hybrid evolutionary algorithm and the RGA with arithmetic crossover are employed to solve the optimization problem of the dimensional synthesis of the five-point double-toggle mould clamping mechanism with the performance of thrust saving for the prescribed input and output strokes. The optimization design task is relatively unique, because the number of constraints is considerable and the constraints are uneven. A technique for proper handling of design constraints is presented. The synthesized results are estimated using the solutions obtained by the parametric study based on an exhaustive search. Findings show that the GA—DE hybrid algorithm can successfully find a better objective function value more efficiently than the RGA with arithmetic crossover.