Sykulski, J.K., Al-Khoury, A.H. and Goddard, K.F.
Minimal Function Calls Approach with On-Line Learning and Dynamic Weighting for Computationally Intensive Design Optimisation
Full text not available from this repository.
Design/optimisation processes requiring intensive finite-element computation can be made significantly more efficient, while preserving good accuracy, by combining the Response Surface Methodology with on-line learning and dynamic weighting. The paper presents such a new development and uses the multi-parameter design of a brushless pm motor to illustrate the approach.
Actions (login required)