一种新型三维加速度传感器静态解耦研究  

Studying of a New Kind of three Dimension Acceleration Sensor's Static Decoupling

作　　者：王小燕[1] 

机构地区：[1]安徽工贸职业技术学院机械工程系,安徽淮南232001

出　　处：《电子质量》2014年第6期10-12,19,共4页Electronics Quality

基　　金：安徽省高校省级优秀青年人才基金项目(2012SQRL235)主持人:王小燕

摘　　要：所述新型三维加速度传感器由于受到结构、应变片粘贴、加工等因素的影响,在测量中存在维间耦合,影响测量精度。传统的是利用最小二乘法线性解耦。该文根据BP神经网络的强非线性映射功能研究了其非线性解耦方法。以新型传感器标定实验中的实验数据为对象,分别对其进行了非线性解耦和线性解耦,结果表明解耦精度提高了六倍。Because of the structure and strain gauge paste and processing of new 3d acceleration sensor. Measurement accuracy is affected by the coupling in the measurement.Traditional linear decoupling is used by least square method.Now a nonlinear decoupling method is designed by BP neural network of strongly nonlinear mapping function.Linear and nonlinear decoupling experiments are implemented by using data of calibration experiments of new three-axis acceleration sensor,the experimental results show that the decou- piing precision of BP neural network is increased six times.

关 键 词：三维加速度传感器 静态解耦 神经网络 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]