A knowledge-based geometry repair system for robust parametric CAD models

Abstract

In modern multi-objective design optimization (MDO) an effective geometry engine is becoming an essential tool and its performance has a significant impact on the entire MDO process. Building a parametric geometry requires difficult compromises between the conflicting goals of robustness and flexibility. This article presents a method of improving the robustness of parametric geometry models by capturing and modeling engineering knowledge with a support vector regression surrogate, and deploying it automatically for the search of a more robust design alternative while trying to maintain the original design intent. Design engineers are given the opportunity to choose from a range of optimized designs that balance the ‘health’ of the repaired geometry and the original design intent. The prototype system is tested on a 2D intake design repair example and shows the potential to reduce the reliance on human design experts in the conceptual design phase and improve the stability of the optimization cycle. It also helps speed up the design process by reducing the time and computational power that could be wasted on flawed geometries or frequent human interventions

More information

Identifiers

ORCID for A. Sobester: orcid.org/0000-0002-8997-4375

ORCID for A.J. Keane: orcid.org/0000-0001-7993-1569

Catalogue record

Export record