An implementation of HIA (humoral immune algorithm) PID controller using neural network identifier

In this paper, an adaptive mechanism based on HIA (humoral immune algorithm) is designed. When the HIA is applied to the PID controller, there exists the case that the plant is damaged by the abrupt change of PID parameters since the parameters are adjusted almost randomly. To solve this problem, a neural network is used to model the plant and the parameter tuning of the system is performed by the humoral immune algorithm. After the PID parameters are determined through this off-line manner, these gains are then applied to the plant for the online control using immune adaptive algorithm. Moreover, even though the neural network model may not be accurate enough initially, the weighting parameters are adjusted to be accurate through the online fine tuning. The experiment for the control of the AGV system is performed. The results show that the proposed controller has better performances than other conventional controllers.