Pump-Valve Combined Control of a HVAC Chilled Water System Using an Artificial Neural Network Model

A chilled water system transports cooling functionality from refrigerators to users via heating, ventilation, and air conditioning (HVAC) systems. This paper investigated an optimal control strategy regulate the volume flow rate of each user branch in a system, considering minimum resistance operation reduce energy consumption. An artificial neural network (ANN) was adopted establish nonlinear relationship between branch, pump frequency, valve opening branch. for HVAC is proposed this article, according pump-valve combined (PVCC) principle ANN model, i.e., using model (PVCC-ANN). series tests were conducted collect data train analyze performance PVCC-ANN experimental system. The results show that trained has good prediction performance. can be achieved independently by model. Moreover, method shows energy-saving systems, which attributed operation. Taking consumption pump’s constant frequency as reference, saving 14.3% 58.6% under 10 operating conditions, reported paper.