Robust design optimisation via surrogate network model and soft outer array design

Robust design searches for a performance optimum with least sensitivity to variable and parameter variations. Taguchi method applies an inner array for control factors and an outer array for noise factors to estimate the Signal-to-Noise ratio (S/N). However, the cross product arrays impose serious cost concerns for expensive samplings. Also, rigorous control of noise factors to pre-set levels is impractical in industrial applications. This study presents a soft computing-based robust optimisation that merges control and noise factors into a combined experimental design to establish a surrogate using artificial neural network. Genetic algorithm is applied to search in the sub-space of control factors in the surrogate with a soft outer array to estimate the S/N served as the evolution fitness. Performance variations due to the tolerances of control and uncontrollable factors can then be estimated without conducting actual experiments. The verifications of the predicted optima become additional learning samples to refine the surrogate, and the iteration continues until convergence. The robust optimisation of a micro-accelerometer with maximised gain is used as an illustrative example. The proposed algorithm provides a superior robust optimum using a much smaller sample and less controlling cost compared with Taguchi method and a conventional response surface method.