In this article,in order to improve the meta-heuristic algorithm's accuracy and efficiency in seeking optimization for the bridge crane's main girder,an improved rat swarm optimization algorithm(IRSO)is proposed.Hénon chaotic random re-verse learning(HROBL)is used to initialize the rat swarm,so as to improve the algorithm's performance of initial optimization.In the pursuit behavior,the hybrid strategy of random reverse learning and Gaussian mutation is introduced to enhance the algo-rithm's ability of global search.In the fighting behavior,the somersault fighting search strategy is used to update the rat swarm's position and enhance the algorithm's ability of local search.The self-adaptive cosine control factor is introduced into the algo-rithm to achieve the dynamic balance between the control parameters and improve the overall the algorithm's overall ability of see-king optimization.The simulation results show that compared with other algorithms,the IRSO algorithm has better ability of see-king optimization,higher accuracy in convergence,higher stability and stronger robustness.At the same time,the IRSO algo-rithm effectively ensures the lightweight design of the bridge crane's main girder,with its weight reducing by 20.72％,which can be widely applied in the fields of engineering.
关键词
鼠群优化算法/Hénon混沌/随机反向学习/翻筋斗搏斗策略/自适应余弦控制因子/主梁轻量化设计
Key words
rat swarm optimization algorithm/Hénon chaos/random reverse learning/somersault fighting search strategy/self-adaptive cosine control factor/lightweight design of main girder
维普
万方数据