Flow-sensorless control valve: Neural computing approach

Abstract

Flow measurements using conventional flow meters for feedback on the flow-control loop cause pressure drop in the flow and in turn lead to the usage of more energy for pumping the fluid. This paper presents an alternative approach for determining the flow rate without flow meters. The restriction characteristics of the flow-control valve are captured by a neural network (NN) model. The relationship between the flow rate and the physical properties of the flow as well as flow-control valve, that is, pressure drop, pressure, temperature, and flow-control valve coefficient (valve position) is found. With these accessible properties, the NN model yields the flow rate of fluid across the flow-control valve, which acts as a flow meter. The viability of the methodology proposed is illustrated by real flow measurements of compressed air which is widely used in pneumatic systems. © 2003 Elsevier Ltd. All rights reserved.