Swarm Heuristic for Identifying Preferred Solutions in Surrogate-Based Multi-Objective Engineering Design

Abstract

Exploring the entire Pareto frontier of high-fidelity multidisciplinary problems can be prohibitive due to the excessive number of expensive evaluations required. The use of surrogate models offers promise toward managing such problems, which are restricted by a computational budget. In this paper, the kriging-assisted user-preference multi-objective particle swarm heuristic is presented, in which less accurate but inexpensive surrogate models are used cooperatively with the precise but expensive objective functions to alleviate the computational burden. A userpreference module is integrated into the optimization framework, which guides the swarm toward preferred regions of the Pareto frontier, thereby focusing all computing effort on identifying only solutions of interest to the designer. While providing a logical criterion to prescreen candidates for precise evaluation, the additional guidance provided by user-preferences guarantees an accelerated convergence rate. To depict the proficiency of the proposed framework, a suite of test problems, including the multidisciplinary cross-sectional design of a semimonocoque fuselage enclosing a pressurized cabin and payload bay, is presented. A parametric model is described that is capable of generating a broad range of double-lobe fuselage designs. The superiority of the kriging-assisted user-preference multi-objective particle swarm optimization algorithm over more traditional search methods to efficiently manage high-fidelity discontinuous design problems is highlighted.

Double surrogate modeling usage in PSO

“…Lots of surrogate-model based optimization algorithms were implemented in genetic algorithm (GA) literature (Glaz et al , 2009). Besides them, there are similar studies from PSO literature (Praveen and Duvigneau, 2009; Singh and Grandhi, 2010; Carrese et al , 2011; Yuanfu et al , 2013, Fang et al , 2014; Passos et al , 2015; Mehmani et al , 2015; Tan et al , 2015). In addition to a conventional surrogate modeling approach, another methodology called a hybrid approach was also used in GA and PSO.…”

Evolutionary optimization of transonic airfoils for static and dynamic trim performance

“…The Kriging user preference multi-objective particle swam optimization algorithm (KUPMOPSO) is described comprehensively in previous publications, including a discussion on the swarm dynamics and topology, as well as metrics on the performance of the algorithm (Carrese and Li, 2015;Carrese et al, 2011). For the present article, the discussion is limited to the important components of the algorithm.…”

“…After directly simulating the initial population, a prescreening criterion is applied after each pseudo time-step which ranks each candidate point and decides whether it is suitable for direct simulation or should be rejected Emmerich and Naujoks (2006);So´bester et al (2005). In the present paper, the KUPMOPSO algorithm (Carrese et al, 2011) is employed to investigate a multi-disciplinary optimization problem including objective functions which span across the three aforementioned disciplines. The Isogai model (Isogai, 1979(Isogai, , 1981, a widely studied benchmark for aeroelastic predictions, is considered as the reference shape.…”

Development of a computational system to design a helical spring

“…The use of computational systems in the design of engineering systems has significantly increased recently. Engineers will employ numerical modelling with a high level of accuracy to simulate, to a reasonable degree of precision, how a complex system will operate [5]. As a consequence of this, computer-aided design, often known as CAD, is frequently used in engineering practice, particularly for mechanical analysis, design, optimizing, and drawing.…”