구속조건의 가용성을 보장하는 신경망기반 근사최적설계

BPN Based Approximate Optimization for Constraint Feasibility

Given a number of training data, a traditional BPN is normally trained by minimizing the absolute difference between target outputs and approximate outputs. When BPN is used as a meta-model for inequality constraint function, approximate optimal solutions are sometimes actually infeasible in a case where they are active at the constraint boundary. The paper describes the development of the efficient BPN based meta-model that enhances the constraint feasibility of approximate optimal solution. The modified BPN based meta-model is obtained by including the decision condition between lower/upper bounds of a constraint and an approximate value. The proposed approach is verified through a simple mathematical function and a ten-bar planar truss problem.