DNA immune algorithm and its application

An approach was proposed to combine T-S fuzzy model with RBF neural network for constructing T-S fuzzy RBF neural network And the method based on the DNA biology mechanism and structure was studied for optimizing the coefficient of the consequence of T-S fuzzy RBF neural network via the DNA immune algorithm. In this method, the adjusting mechanism based on antibody concentration updating strategy kept the antibody diversity and avoided the premature convergence. At last it was used in Soft sensing modeling of acrylonitrile yield, the experimental simulation results showed that DNA immune algorithm is effective in the optimizing design ofT-S fuzzy neural network system, and high accuracy model could be obtained.