基于降维的驾驶员侧约束系统高维目标优化
发布时间：2018-08-10 22:28
【摘要】：为解决将高维目标变为单目标优化时各子目标不能同时较优,而多目标算法直接用于高维目标优化时又存在难以找到一个有代表性的Pareto非劣解集问题,在某轿车驾驶员侧约束系统的优化过程中提出了乘员损伤准则与多目标算法协同优化的方法。在已有相关损伤准则基础上根据最新版的FMVSS 208和ECE R94法规提出了适合研究问题的损伤准则;以提出的损伤准则为媒介,将一个高维目标优化问题降为一个低维目标优化问题,通过灵敏度分析、实验设计、多项式近似模型筛选出优化设计变量并得到近似模型,用多目标算法NSGA-Ⅱ对近似模型进行计算得到Pareto非劣解集,将得到的Pareto非劣解集中的每个解代入损伤准则损伤值计算公式,升序排列得到各子目标同时较优而损伤值最小的优化解。最终的优化结果表明:该方法很好地解决了乘员约束系统的高维目标优化问题,优化效果明显。
[Abstract]:In order to solve the problem that each subobjective can not be optimized simultaneously when the high-dimensional target is transformed into single-objective optimization, there is a problem that it is difficult to find a representative Pareto noninferior solution set when the multi-objective algorithm is directly applied to the high-dimensional objective optimization. In the process of optimization of a car driver side constraint system, a cooperative optimization method of crew damage criterion and multi-objective algorithm is proposed. According to the latest version of FMVSS 208 and ECE R94 regulations, the damage criteria are put forward on the basis of the existing damage criteria, and a high-dimensional objective optimization problem is reduced to a low-dimensional objective optimization problem by using the proposed damage criteria as a medium. Through sensitivity analysis, experimental design and polynomial approximation model, the optimal design variables are selected and the approximate model is obtained. The Pareto noninferior solution set is obtained by using the multi-objective algorithm NSGA- 鈪，
本文编号：2176400
[Abstract]:In order to solve the problem that each subobjective can not be optimized simultaneously when the high-dimensional target is transformed into single-objective optimization, there is a problem that it is difficult to find a representative Pareto noninferior solution set when the multi-objective algorithm is directly applied to the high-dimensional objective optimization. In the process of optimization of a car driver side constraint system, a cooperative optimization method of crew damage criterion and multi-objective algorithm is proposed. According to the latest version of FMVSS 208 and ECE R94 regulations, the damage criteria are put forward on the basis of the existing damage criteria, and a high-dimensional objective optimization problem is reduced to a low-dimensional objective optimization problem by using the proposed damage criteria as a medium. Through sensitivity analysis, experimental design and polynomial approximation model, the optimal design variables are selected and the approximate model is obtained. The Pareto noninferior solution set is obtained by using the multi-objective algorithm NSGA- 鈪，
本文编号：2176400
本文链接：https://www.wllwen.com/kejilunwen/jiaotonggongchenglunwen/2176400.html
