一种基于正态分布的滑动平均滤波法

Moving Average Filtering Method Based on Normal Distribution

六维力传感器在采集力数据时,不可避免地会受到外界噪声的干扰。为了消除外界噪声对传感器输出信号的影响,针对偶然出现的过高或过低的噪声,提出了一种基于正态分布的滑动平均滤波法。算法根据正态分布的特性对不符合要求的数据进行剔除,从而减少噪声对滤波曲线的影响,最后与普通滑动平均滤波法及去除最大值最小值的滑动平均滤波法进行分析比对。实验结果表明,相比于普通滑动平均滤波法与去除最大值与最小值的滑动平均滤波法,基于正态分布的滑动平均滤波法可以有效抑制过高或过低的噪声,并且平滑度也得到了提高。

Six-dimensional force sensors will inevitably be disturbed by external noise when collecting force data.In order to eliminate the influence of external noise on the sensor output signal,a moving average filtering method based on a normal distribution is proposed for occasionally excessively high or low noise.According to the characteristics of normal distribution,the algorithm can eliminate the data that does not meet the requirements,so as to reduce the impact of noise on the filtering curve.Finally,it is compared with the ordinary moving average filtering method and the moving average filtering method with the maximum and minimum values removed.The experimental results show that compared with the common moving average filtering method and the moving average filtering method,the moving average filtering method based on the normal distribution can effectively suppress the high or low noise and improve the smoothness.