一种求解有约全局优化问题的新型混合方法

通过将模拟退火算法与非线性规划神经网络适当结合，本文提出一种求解有约束全局优化问题的新型混合方法．为了使该方法尽可能保持一般模拟退火算法通用性强的优点，在每一次迭代中不是采用非线性规划神经网络直接求原问题的局部最优解，而是通过求解一个辅助优化问题得到原问题的可行解．数值计算结果表明，与使用罚函数方法处理约束的模拟退火算法相比，本文提出的混合方法不仅可靠性高，而且可以显著地提高计算效率．

A New Hybrid Method for Constrained Global Optimization

By combining properly the simulated annealing algorithm and the nonlinear programming neural network, a new hybrid method for comtrained global optimization is proposed in this paper. To maintain the applicability of the simulated annealing algorithm used in the hybrid method as general as possible, the nonlinear programming neural network is employed at each iteration to find only a feasible solution to the original constrained problem rather than a local optimal solution. Such a feasible solution is obtained by solving an auxiliary optimization problem with a new objective function. The computational results for two numerical examples indicate that the proposed hybrid method for constrained global optimization is not only highly reliable but also much more effcient than the simulated annealing algorithm using the penalty function method to deal with the constraints.