Thermal Analysis and Optimization of MEMS Temperature Sensor for Food Detection

In order to improve the sensitivity of MEMS temperature sensor, this paper proposes an efficient and robust structural optimum design method for the sensor structure. Based on thermal analysis of software ANSYS, the thermal deformation and distribution of temperature field can be obtained clearly. A predictive model for thermal deformation is established using artificial neural network and the sample for neural network model is designed by using orthogonal experimental method. In the model, the structure parameters of sensor are treated as design variables and the objective is to obtain the maximum deformation. Optimization of structure parameters for sensor was conducted by introducing artificial neural network prediction models into genetic algorithm. The results indicate that the optimization method based on artificial neural network and the genetic algorithm is feasible for improve the sensitivity of chemical sensor.