Abstract: A method is proposed to design a fuzzy classification system with immune principle.Based on the clonal selection and hypermutation principle of biological immune system,the algorithm evolves a population of antibodies to optimize the fuzzy classification rule set.The shape of membership functions,the rule set,and the number of rules inside the rule set can be determined at the same time.Simulation experiments are made on some benchmark data sets,and the results demonstrate that the proposed algorithm is effective.