An intelligent temperature measurement technique using J type thermocouple with an optimal neural network

This paper aims at designing an intelligent temperature measurement technique using J type thermocouple with an optimized neural network model. The objectives of this work are to (i) extend the linearity range of measurement to 100 % of the full scale, (ii) make the measurement system adaptive of variation in temperature coefficients and (iii) to achieve (i) and (ii) using optimal neural network. The output of thermocouple is in mV range. A suitable data conversion circuit is used to convert mV to voltage and to overcome the problem of interference of noise and open thermocouple detection. A suitable optimal Artificial Neural Network (ANN) block is added in cascade to data conversion unit. This arrangement helps to linearise the overall system and make it adaptive of variations in temperature coefficients. Since, the proposed intelligent temperature measurement technique produces adaptive of variation in physical properties of thermocouple. It avoids the requirement of repeated calibrations every time the thermocouple is replaced. Simulation results show that proposed measurement technique satisfies the objectives.