Design and Analysis of an Intelligent Flow Transmitter Using Artificial Neural Network

This paper presents an intelligent flow transmitter using rotameter as a primary sensor. The float movement of the rotameter is converted into an electrical signal so that one can monitor it and control it at a remote location in industries. A Hall probe sensor is used to convert the float movement into Hall voltage, but various parameters like temperature, liquid density, viscosity etc., affect the Hall voltage measurement. The change of Hall voltage with respect to temperature is nonlinear in nature. In this respect, back propagation algorithm of the artificial neural network (ANN) is used to compensate the nonlinearity and inaccuracy of Hall probe sensor due to change in temperature. The proposed measurement system, experimental results, and testing results of the ANN are reported in this paper.