A Design of Self-Tuning PID Controllers Fused with a Neural Network

In recent years, the structure and the mechanism of the human brain have been clarified partially, and their knowledges are formulated as neural network systems. Furthermore, there have been applications of neural networks to pattern matching problems, pattern recognitions, learning controls and so on. Especially, neural network techniques have widely used in adaptive and learning control schemes for nonlinear systems. However, generally, it costs a lot of time for learning in the case applied in control systems. Furthermore, the physical meaning of neural networks constructed as a result, is not obvious. In this paper, a design method of self-tuning PID controllers is proposed, which has a fusional structure of self-tuning and neural network schemes. This method enables us to understand a physical meaning of the control parameters, and also to adjust PID gains quickly. Finally, in order to show the effectiveness of the proposed self-tuning PID control scheme, a numerical simulation example is illustrated.