Neural network predictive control of a heat exchanger
PEER_stage2_10.1016%2Fj.applthermaleng.2011.01.026.pdf (PDF) 297.9Kb
Abstract The study attempts to show that using the neural network predictive control (NNPC) structure for control of thermal processes can lead to energy savings. The advantage of the NNPC is that it is not a linear-model-based strategy and the control input constraints are directly included into the synthesis. In the designed approach, the neural network is used as a nonlinear process model to predict the future behaviour of the controlled process with distributed parameters. The predictive control strategy is used to calculate optimal control inputs. The efficiency of the described control approach is verified by simulation experiments and a tubular heat exchanger is chosen as a controlled process. The control objective is to keep the temperature of the heated outlet stream at a desired value and minimize the energy consumption. The NNPC of the heat exchanger is compared with classical PID control. Comparison of the simulation results obtained using NNPC and those obtained by classical PID control demonstrates the effectiveness and superiority of the NNPC because of smaller consumption of heating medium.
Affiliation:Institute of Information Engineering - Automation--> , and Mathematics--> , Faculty of Chemical and Food Technology--> , Slovak University of Technology in Bratislava--> , Radlinskeho 9--> , 812 37 Bratislava--> - SLOVAKIA (Vasickaninova, Anna)
Institute of Information Engineering - Automation--> , and Mathematics--> , Faculty of Chemical and Food Technology--> , Slovak University of Technology in Bratislava--> , Radlinskeho 9--> , 812 37 Bratislava--> - SLOVAKIA (Bakosova, Monika)
SLOVAKIA (Bakosova, Monika)
Institute of Engineering Studies of the Slovak University of Technology - Vazovova 5--> , 812 43 Bratislava--> - SLOVAKIA (Meszaros, Alojz)
Centre for Process Integration and Intensification ? CPI2, Research Institute of Chemical and Process Engineering, Faculty of Information Technology, University of Pannonia - Egyetem u. 10--> , 8200 Veszprem--> - HUNGARY (Jaromir Klemes, Jiri)