抽象的

Data driven PID-type neural network controller design using lazy learning for CSTR

Hongcheng Zhou , Daobo Wang , Dezhi Xu , Qiang Zhang

Since most chemical processes exhibit severe nonlinear and time-varying behavior, the control of such processes is challenging. In this paper, a novel two-layer online adjust algorithm is presented for chemical processes. The lower layer consists of a conventional PID-type neural network (PIDNN) controller and a plant process, while the upper layer is composed of identification and tuning modules. Using a lazy learning algorithm, a local valid linear model denoting the current state of system is automatically exacted for adjusting the PID controller parameters based on input/output data. This scheme can adjust the PIDNN parameters in an online manner even if the system has nonlinear properties. In this online tuning strategy, the BP training algorithm is considered. The simulation results on the dynamic model of Continuous Stirred Tank Reactor (CSTR) are provided to demonstrate the effectiveness of the proposed new control techniques