Robust design optimization for a nonlinear system via Bayesian neural network enhanced polynomial dimensional decomposition

Abstract

Uncertainties such as manufacturing tolerances cause performance variations in complex engineering systems, making robust design optimization (RDO) essential. However, simulation-based RDO faces high computational cost for statistical moment estimation, and strong nonlinearity limits the accuracy of conventional surrogate models. This study proposes a novel RDO method that integrates Bayesian neural networks (BNN) with polynomial dimensional decomposition (PDD). The method employs uncertainty-based active learning to enhance BNN surrogate accuracy and a multi-point single-step strategy that partitions the design space into dynamically adjusted subregions, within which PDD analytically estimates statistical moments from BNN predictions. Validation through a mathematical benchmark and an electric motor shape optimization demonstrates that the method converges to robust optimal solutions with significantly fewer function evaluations. In the thirty-dimensional benchmark, the proposed method achieved a 60.39% mean reduction, while Gaussian process-based approaches failed to locate the global optimum. In the motor design problem, the method reduced cogging torque by 91.89% with only 6702 finite element evaluations, confirming its computational efficiency for high-dimensional, strongly nonlinear engineering problems.