The conventional PID (proportional-integral derivative) controller is widely applied to industrial automation and process control field because of its simple structure and robustness, but it does not work well for nonlinear system, time-delayed linear system and time varying system. Artificial Neural Network (ANN) can solve great variety of problems in areas of control systems, pattern recognition, image processing and medical diagnostic. A Neural Network is a powerful data-modeling tool that is able to capture and represent complex input/output relationships. This paper represents the advantage of using neural network for PID controller. PID controller for surge tank has been implemented in MATLAB.