英语小论文翻译.doc

一、英文原文 Compensation of temperature drift of MEMS  gyroscope using BP neural network Qintuo Zhang， Zhenfan Tan， Lidong Guo College f Automation Harbin Engineering university Nantong Street 145，Harbin，Heilongjiang,China Abstract:In order to solve the temperature change on the impact of MEMS gyroscope output, through self-development MEMS IMU temperature test, we used BP neural network to predict the temperature drift of MEMS gyroscope and compensation it. After using BP neural network to compensate three gyroscopes, we compared the results with the traditional least-squares method that the output error variance respectively reduced from 0.4242, 0.3506 and 0.4335 to 0.0758, 0.1024 and 0.1122. The results indicate the correctness and validity of the method, so as to offer a new method to improve the performance of MEMS gyroscope . Keywords:MEMS Gyroscope; BP Neural Network; Temperature Drift I. INTRODUCTION In recent years, a promising technology, micro-electromechanical systems (MEMS) based inertial sensors has been developed[9], however, due to the small size and weight of it, the performance characteristics are highly dependent on the temperature variations[1]. Due to the production process and other reasons, the gyroscope frequency or AGC are tested to simulate MEMS gyroscope temperature changes, which inevitably bring additional error [2-3]. We researched on ADXL150 MEMS gyroscope made by Analog Devices Inc, and which can give the temperature information of it, the temperature coefficient is 8.4mv/°, while its sensitivity is only 12.5mv/°/s. Therefore, it’s necessary and practical to compensate temperature drift through temperature test. Some researchers focuses on the impact of temperature on the MEMS gyroscope zero bias, in which the zero bias voltage is converted to angular rate value, but it is not clear how to select the scale factor with temperature changes[4]; Reference[5] shows temperature impact on