Neural network based self-tuning control for overhead crane systems

This paper deals with a neural network based self-tuning controller for an overhead crane. The structure of the controller consists of two components. The first component is a basic controller called state feedback controller designed by Linear Quadratic Regulator (LQR) concept. The second component is an on-line performance tuner, which will tune the basic controller by using the neural network concept. The experimental result shows that the proposed controller can improve the speed of the crane movement toward to the desired position without the swinging of the load at the desired position.