Expensive constraints are commonly seen in real-world engineering design. However, metamodel based design optimization (MBDO) approaches often assume inexpensive constraints. In this work, the situational adaptive Kreisselmeier and Steinhauser (SAKS) method was employed in the development of a hybrid adaptive aggregation-based constraint handling strategy for expensive black-box constraint functions. The SAKS method is a novel approach that hybridizes the modeling and aggregation of expensive constraints and adds an adaptive strategy to control the level of hybridization. The SAKS strategy was integrated with a modified trust region-based mode pursuing sampling (TRMPS) algorithm to form the SAKS-trust region optimizer (SAKS-TRO) for single-objective design optimization problems with expensive black-box objective and constraint functions. SAKS-TRO was benchmarked against five popular constrained optimizers and demonstrated superior performance on average. SAKS-TRO was also applied to optimize the design of an industrial recessed impeller.
An Adaptive Aggregation-Based Approach for Expensively Constrained Black-Box Optimization Problems
Coquitlam, BC V3K 7C1, Canada
Contributed by the Design Automation Committee of ASME for publication in the JOURNAL OF MECHANICAL DESIGN. Manuscript received November 23, 2017; final manuscript received May 29, 2018; published online June 26, 2018. Editor: Wei Chen.
- Views Icon Views
- Share Icon Share
- Search Site
Cheng, G. H., Gjernes, T., and Gary Wang, G. (June 26, 2018). "An Adaptive Aggregation-Based Approach for Expensively Constrained Black-Box Optimization Problems." ASME. J. Mech. Des. September 2018; 140(9): 091402. https://doi.org/10.1115/1.4040485
Download citation file: