MODELLING OF NTC THERMISTOR USING ARTIFICIAL NEURAL NETWORK FOR NONLINEARITY COMPENSATION

This paper investigates modelling of NTC thermistors using Steinhart-Hart equation for generic model generation and then parsing the same through the linearization algorithm based on Levenberg–Marquart back propagation technique with sigmoid activation function. The entire modelling and scripting of the linearization algorithm has been accomplished in the MATLAB paradigm. The results showcase small linearity error optimal in the chebyshev norms. The reported technique has a potential for linearization of other impedance based non-linear sensors as well. Further work is in progress to integrate the algorithm as a soft IP core in a full custom or semi-custom ASIC wherein thermistors are employed as sensors.