An improved hybrid immune algorithm for mechanism kinematic chain isomorphism identification in intelligent design

摘要

In intelligent mechanism design, isomorphism identification of mechanism kinematic chains (IIMKC) is aimed at avoiding repeated mechanism design and is proved to be an NP-complete problem. In this paper, kinematic chains are represented by graphs. An improved hybrid immune algorithm, which integrates the clonal selection immune algorithm with genetic algorithm and the local search algorithm, is proposed to solve IIMKC problem. Moreover, the novel saving and updating operator is proposed to save the best antibodies and maintain a diverse repertoire of antibodies for improving performance of clonal selection. In addition, the pseudo-crossover operator is introduced to enhance the efficiency of genetic algorithm. Simulation results validate the high efficiency and robustness of the hybrid immune algorithm.