用遗传程序设计实现复杂函数的自动建模

The Automatic Modeling of Complex Functions Based on Genetic Programming

采用遗传程序设计的方法实现复杂函数的自动建模,程序中用树的分层结构表示复杂函数,并设计了相应的遗传算子(包括杂交算子和变异算子)以及停机条件。实例测试的结果表明采用遗传程序设计的方法得到的模型比传统的方法得到的模型要好,甚至优于专家设计的一些模型。

In this paper, we apply Genetic Programming to the automatic modeling of complex functions. In our programs the complex functions are expressed by multi-layer trees. The Genetic Operators such as Crossover and Mutation, Termination Conditions are designed respectively. Further more, we give two examples, whose results show that the models set up by Genetic Programming are better than the models set up by classical algorithms, and even better than some models designed by specialists.