基于GRNN网络自适应滤波的钻具加速度去噪  

Drilling Tool Acceleration Denoising Based on GRNN Network Adaptive Filtering

作　　者：仝小森 杨金显[1] TONG Xiaosen;YANG Jinxian(School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo 454000,China)

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454000

出　　处：《电子科技》2022年第7期46-51,共6页Electronic Science and Technology

基　　金：国家自然科学基金(41672363,U1404510,61440007);河南省高等学校青年骨干教师培养计划(2018GGJS061);河南省创新型科技人才队伍建设工程(CXTD2016054);河南理工大学青年骨干教师资助计划(2017XQG-07)。

摘　　要：针对随钻测量过程中钻具底部振动噪声引起重力加速度信息严重失真的问题,文中提出一种将广义回归神经网络和改进的递推最小二乘相结合的方法来去除噪声。应用自适应噪声相互抵消的原理,以加速度计测量信号与钻具振动信号作为主噪声模型,将经过广义回归神经网络处理后的钻具振动信号作为副噪声模型。采用递推最小二乘法滤波处理,进而提高钻具加速度计测量精度,解算实时钻进的姿态信息。仿真实验结果表明,文中所提算法能有效去除钻具加速度计振动噪声,提高姿态测量精度。去噪后解算的井斜角误差在1.45°之内,工具面角误差在1.65°之内。In view of the problem of serious distortion of gravitational acceleration information caused by bottom-hole vibration and noise during measurement while drilling,a method that combines generalized regression neural network and improved recursive least squares is proposed to remove noise.Using the principle of mutual cancellation of adaptive noise,the accelerometer measurement signal and drilling tool vibration signal are used as the main noise model,and the drilling tool vibration signal processed by the generalized regression neural network is used as the auxiliary noise model.Recursive least squares filter processing is used to improve the accuracy of drilling tool accelerometer measurement and calculate real-time drilling attitude information.The simulation results show that the proposed algorithm can effectively remove the vibration and noise of the drilling tool accelerometer and improve the attitude measurement accuracy.After denoising,the calculated deviation angle error is within 1.45°,and the tool face angle error is within 1.65°.

关 键 词：随钻测量 自适应噪声对消 重力提取 广义回归神经网络 递推最小二乘算法 加速度计去噪 自适应滤波 姿态解算 

分 类 号：TN713[电子电信—电路与系统] TN99