Some novel classification and learning methods and applications for neural networks - Selected papers from the Second International Conference on Bio-Inspired Computing: Theories and Applications

Xiaopeng Wei, Qiang Zhang, Guangzhao Cui

Abstract: This study presents a novel bio-inspired knowledge system, based on closed loop tuning, for calculating the Proportional-Integral-Derivative (PID) controller parameters of a real combined cycle plant. The aim is to automatically achieve the best parameters according to the work point and the dynamics of the plant. To this end, several typical expressions and systems were taken into account to build the model for this multidisciplinary study. Each of these expressions is appropriated for a particular system. The novel method is empirically verified under a real case study based on an auxiliary steam system of a combined cycle plant.