一种无恢复过程的SQP-滤子法

An SQP-Filter Method Without Restoration Process

本文研究非线性不等式约束优化问题,构造一个新的SQP-滤子法.该方法将滤子技术有机融合到简金宝提出的可行SQP方法中,利用转轴运算的思想,产生一个近似积极约束集,当QP子问题不相容时,利用广义投影技术获得可行搜索方向.该算法既能避免罚函数的选择,又能避免常规滤子算法中的恢复算法,一定程度上简化了计算.最后,在合理的条件下,证明了算法的全局收敛性.

In this paper, we consider the nonlinear inequality constrained optimization problem.A new SQP-filter method is presented. In the algorithm, the filter technique is combined to the feasible SQP method which is proposed by Jinbao Jian. An approximate active constraint set is produced by the idea of pivoting operation. When the QP subproblem is incompatible, the feasible direction of search is obtained by generalized gradient projection method. So this method is effective to avoid the restoration algorithm in general filter algorithm and the difficulties in choosing penalty parameter. Therefore, the computational cost is reduced. The theoretical analysis shows that the algorithm is global convergent under some suitable conditions.