论文部分内容阅读
针对稳健设计中的约束可行稳健性问题,提出了一种新的稳健优化设计方法。通过分析不确定因素对约束的影响,提出了利用最大波动分析计算在不确定性因素影响下约束的最大波动量,将该变化量作为惩罚项添加到原约束中,构造了两级优化数学模型。顶级优化是在原有常规优化的数学模型基础上添加了稳健可行性的判断指标,次级优化用来判断稳健性指标的值。与其他方法比较,该方法不需要知道不确定因素的概率分布和约束的梯度信息。实例结果证明该方法是可行的。
Aiming at the problem of robustness in the robust design, a new robust optimization method is proposed. By analyzing the influence of uncertain factors on the constraints, we propose to use the maximum fluctuation analysis to calculate the maximum fluctuation of the constraint under the influence of uncertainty factors, and add this variation as a penalty term to the original constraints. A two-level optimization mathematical model . Top-level optimization is based on the original mathematical model of conventional optimization to add a robust and viable judgments, sub-optimization used to determine the value of the robust index. Compared with other methods, this method does not need to know the probability distribution of uncertainties and the gradient information of constraints. The result of the example proves that this method is feasible.