Multi-speed gearbox design using multi-objective evolutionary algorithms

作     者：Deb, K Jain, S 

作者机构：Indian Inst Technol Dept Mech Engn Kanpur Genet Algorithms Lab Kanpur 208016 Uttar Pradesh India 

出 版 物：《JOURNAL OF MECHANICAL DESIGN》 (美国机械工程师学会汇刊: 机械设计杂志)

年 卷 期：2003年第125卷第3期

页      面：609-619页

核心收录：

学科分类：08[工学] 0802[工学-机械工程] 

主　　题：Errors design engineering Optimization optimisation Design evolutionary computation Mechanical drives mechanical engineering Evolutionary algorithms Gears Gear teeth 

摘      要：Optimal design of a multi-speed gearbox involves different types of decision variables aid objectives. Due to lack of efficient classical optimization techniques, such problems are usually decomposed into tractable subproblems and solved. Moreover, in most cases the explicit mathematical expressions of the problem formulation is exploited to arrive tit the optimal solutions. In this paper, we demonstrate the use of a multi-objective evolutionary algorithm, which is capable of solving the original problem involving mixed discrete and real-valued parameters aid more than one objectives, and is capable of finding multiple nondominated solutions in a single simulation run. On a number of instantiations of the gearbox design problem having different complexities, the efficacy of NSGA-II in handling different types a decision variables, constraints, mid multiple objectives are demonstrated. A highlight of the suggested procedure is that a post-optimal investigation of the obtained solutions allows a designer to discover important design principles which are otherwise difficult to obtain using other means.