COMPENSATION OF MEMS SENSORS USING NEURAL NETWORK

Abstract

Microelectromechanical system (MEMS) is a technology that in its most general form can be defined as miniaturized mechanical and electro-mechanical devices and structures that are made using the techniques of microfabrication. MEMS are low-cost, low to medium accuracy inertial sensors that are extensively used in the industrial as well as in the real time applications. Also, they are widely used in the satellite and the navigation field. The real time systems are greatly affected by the conditions of the external surrounding, thus the results or the responses of these systems or applications will be highly noisy signals and readings. The temperature compensation of the sensor data is very important, and can be done with any of the techniques. The classic way is to use the filters. In this work two methods are used for the purpose one is using a filter and Neural Network(NN). The main aim of the work is the temperature compensation. The filter used, the Kalman filter(KF), is an algorithm that provides estimates of some unknown variables given the measurements observed over time and works on updation and prediction method. The other method is neural network technique in which the fitting of the neural network for the noise reduction has been done. By a proper temperature compensation, the noise reduction will also be resulted.