求解非线性规划全局最优解的单参数T-F函数法

One-parameter T-F Function for Global Optimization

给出了求解一般非线性规划问题全局最优解的含单参数的T-F函数方法,而且讨论了所构造的T-F函数的几个性质,按照其理论性质设计了一个T-F函数算法,并进行了数值试验,数值实验表明,所给的方法是有效的。

An one-parameter T-F function for solving general optimization problems with a general function over box-constrained domain is introduced. A T-F function is constructed at a local minimizer of the objective function such that it achieves local maximum at the current solution. Moreover, a local minimizer of the T-F function leads to a new solution to the original problem with lower objective function value. Iteration follows in this manner to reach a global minimizer. Promising computational results are included and show the efficiency of the T-F function method.