Temperature compensation of micromachined silicon hot wire sensor using ANN technique

Temperature is one of the most important factors influencing accurate silicon sensor devices and is one of the largest sources of error in measurement. In this paper, a model based on Neural Networks (NN), has been implemented to generate fluid velocity data, knowing fluid temperature measurements. The proposed model based on neural networks can provide the calibrated response characteristics irrespective of change in the sensor characteristics due to change in ambient temperature. The NN-based sensor model automatically calibrates and compensates with high accuracy for the nonlinear response characteristics and nonlinear dependency of the sensor characteristics on the environmental parameters. Through extensive simulated experiments, we have shown that the NN-based silicon hot wire sensor model can provide flow speed readout with a maximum full-scale error of only 1.5% over a temperature range from 0 to 40°C for nonlinear dependencies.