An adaptive calibration technique for thermistor with varying temperature coefficient and reference resistance

Abstract

Background: A thermistor is a nonlinear sensor requiring a precise calibration technique to achieve accurate temperature measurements. This paper attempts to design a calibration technique employing artificial neural network (ANN) algorithms. The present work fulfills the following objectives: (i) to cover 100% input range in the linearity range measurement; (ii) to make the measurement technique adaptive to variations in reference resistance and thermistor temperature coefficient using a calibration technique. Methods: An ANN-based calibration circuit is cascaded to the data conversion circuit. Optimized ANN is trained with linear data independent of reference resistance and temperature coefficient effects on thermistor output. ANN optimization is performed by comparing various schemes, algorithms, and numbers of hidden layers to achieve a minimum mean square error and a regression close to 1. Results: The proposed technique provides a linear relationship for the system over the entire input range and avoids the requirement of repeated calibrations each time the thermistor is replaced. Practical data are used to validate the proposed measurement technique. Conclusions: The objectives and proposed technique have been demonstrated by results with a root mean square percentage error of 1.8%.