Radial basis function (RBF) neural network (NN) is powerful computational tools that have been used extensively in the areas of pattern recognition, systems modeling and identification. This paper proposes an adaptive PID control method based on RBF neural network identification. This approach can on-line identify the controlled plant with the RBF neural network identifier and the weights of the adaptive PID controller are adjusted timely based-on the identification of the plant and self-learning capability of RBFNN. Simulation result shows that the proposed controller has the adaptability, strong robustness and satisfactory control performance in the nonlinear and time varying system