Identifying and Leveraging Promising Design Heuristics for Multi-Objective Combinatorial Design Optimization
Identifying and Leveraging Promising Design Heuristics for Multi-Objective Combinatorial Design Optimization
复制标题
识别和利用有前途的设计启发法进行多目标组合设计优化
DOI：
10.1115/1.4063238
复制
发表时间：
2023
影响因子：
3.3
通讯作者：
Selva, Daniel
中科院分区：
文献类型：
--
作者：
Suresh Kumar, Roshan;Srivatsa, Srikar;Baker, Emilie;Silberstein, Meredith;Selva, Daniel
传统上，设计优化被用作指导设计过程的定性原则，但它们也被用来提高设计优化的效率。使用设计算法作为软约束或搜索算子已经被证明用于某些问题，以减少实现一定程度的收敛所需的函数求值的数量。然而，在其他情况下，强制执行竞争可能会减少多样性并减慢收敛速度。本文研究的问题，何时以及如何一组给定的设计技巧表示在不同的形式（软约束，修复算子，有偏抽样）可以利用自动化的方式来提高效率，为一个给定的设计问题。提出了一种方法，用于确定有前途的启发式算法为一个给定的问题，通过估计的启发式的基础上的探索性筛选研究的总体影响。提出了两个影响指数：加权影响指数和超容量差异指数。使用这种方法，有前途的四个设计问题，识别和选择性地强制执行只有这些有前途的策略，所有可用的策略，而不是强制执行任何策略的效率进行基准测试。在所有的问题中，它被发现，只强制执行有前途的修复算子，使找到好的设计更快，比强制执行所有可用的修复或不强制执行任何修复。强制执行算法作为软约束或有偏采样函数，可以提高某些问题的效率。基于这些结果，指导设计人员有效地利用几何学的设计优化。
Design heuristics are traditionally used as qualitative principles to guide the design process, but they have also been used to improve the efficiency of design optimization. Using design heuristics as soft constraints or search operators has been shown for some problems to reduce the number of function evaluations needed to achieve a certain level of convergence. However, in other cases, enforcing heuristics can reduce diversity and slow down convergence. This paper studies the question of when and how a given set of design heuristics represented in different forms (soft constraints, repair operators, and biased sampling) can be utilized in an automated way to improve efficiency for a given design problem. An approach is presented for identifying promising heuristics for a given problem by estimating the overall impact of a heuristic based on an exploratory screening study. Two impact indices are formulated: weighted influence index and hypervolume difference index. Using this approach, the promising heuristics for four design problems are identified and the efficacy of selectively enforcing only these promising heuristics over both enforcement of all available heuristics and not enforcing any heuristics is benchmarked. In all problems, it is found that enforcing only the promising heuristics as repair operators enables finding good designs faster than by enforcing all available heuristics or not enforcing any heuristics. Enforcing heuristics as soft constraints or biased sampling functions results in improvements in efficiency for some of the problems. Based on these results, guidelines for designers to leverage heuristics effectively in design optimization are presented.