An Approach to Generate Fuzzy Rules based on Rough Set and Fuzzy Neural Network

A new approach to get fuzzy rules based on rough set theory and fuzzy neural network is proposed in this paper. First, it uses the powerful capability of qualitative analysis of rough set theory to get a set of fuzzy rules from the given training data; then it constructs the fuzzy neural network model according to these rules; and then it uses the approaching and self-learning capability of neural network to optimize the rules´ parameters. Theory analysis and simulation results have shown that this method is superior to conventional method based on RS theory, and it can automatically adjust the gotten rules´ parameters, and we can obtain a set of optimum control rules