关键词: 人工免疫网络，特征数据，RI3F网，函数逼近

Abstract: Artificial immune network, an intelligent information processing model inspired by biological immune system,has been widely studied and applied. In this paper, a modified artificial immune algorithm combined with traditional RBF was used in problem solving. The experimental results show that the modified artificial immune network algorithm can present the functions of reducing data redundancy, smoothing noise and extracting feature data to improve data quality.In the application of combining with RBF network, the speed and functionality of problem solving arc raised effectively.

Key words: Artificial immune network,Feature data,RBF network,Function approximation