摘要
下肢自主康复训练机器人中交流伺服电机电流信号噪声严重影响电机力矩辨识精度。为解决非线性非平稳信号的滤波去噪问题,提出一种基于经验模态分解(EMD)的改进阈值小波滤波算法。首先对EMD最佳去噪层数和阈值小波的阈值处理函数进行分析和改进,然后将两种改进方法相结合,最后对Matlab中的Heavy sine信号添加高斯噪声,分别利用改进方法和软、硬阈值等滤波方法进行去噪实验。仿真实验结果表明,改进算法能有效去除非线性非平稳信号中噪声信号。与EMD和阈值小波等其他滤波方法相比,本文滤波算法去噪后信噪比更大,均方根误差更小,滤波效果更好。
In lower limb rehabilitative training robot, the accuracy of the motor torque identification is seriously affected by the noise of AC servo motor current signal. In order to solve the problem of nonlinear and non-stationary noise signal denoising, an improved threshold wavelet filtering method based on Empirical Mode Decomposition （EMD） is proposed in this paper. The EMD denoising layers and the thresholding function of wavelet threshold are improved. The heavy sine signal in Matlab is used to do simulation experiments. The simulation results show that the improved method can effectively remove the noise of non-linear and non-stationary signal. Compared with other filtering methods, such as EMD and wavelet transforms, the improved method can obtain the maximum SNR （signal-to-noise ratio） and the minimum RMSE （root mean square error）, and have better filtering effect.
出处
《机械科学与技术》
CSCD
北大核心
2017年第8期1175-1179,共5页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金重大研究计划项目(91420301)资助
关键词
EMD
小波
阈值函数
信噪比
EMD
threshold function
Matlab
signal-to-noise ratio
wavelet transforms
