Temperature Drift Compensation of MEMS Inertial Sensor Based on IA-BP Algorithm

MEMS inertial devices are important sensors for measuring angle and acceleration. Due to the drift of the gyroscope output caused by temperature, it is difficult to improve the precision of the hemispherical resonator gyroscope, so it is necessary to compensate the error of the gyroscope. Firstly, the mechanism of zero drift is analyzed based on the working principle of HRG. In this paper, we introduce the principle of BP neural network and the advantages of immune algorithm in improving BP neural network. The neural network is trained by the zero point data of MEMS gyroscope at different temperatures, and the error is compensated. The conclusion shows that IA-BP algorithm has shorter training time and better error compensation effect than BP algorithm.