基于赛利斯模型和分数阶微分的兰姆波信号消噪

Noise suppression for Lamb wave signals by Tsallis mode and fractional-order differential

为降低噪声对超声兰姆波检测信号的影响,提高信噪比和增加特征提取的精度,提出了一种赛利斯模型下分数阶微分方法用于超声兰姆波信号去噪.该方法对含噪声的兰姆波信号幅值谱进行各阶分数微分,用赛利斯分布作为待处幅值谱的模型,提出了幅值谱分数阶微分最大值和过零点与微分阶数的拟合三次关系式,建立了幅值谱特征参数的计算式来提取特征参数和重建原始信号的幅值谱,并结合相位谱重构去噪后的兰姆波信号.仿真结果表明,该方法可以有效地提高兰姆波信号甚至微弱兰姆波信号的信噪比,同时降低均方误差和平滑度.实验结果显示,与小波去噪和集合经验模态去噪方法相比,该方法在没有信号先验知识的情况下,可以更有效地去除兰姆波信号的噪声,同时更好地保留主信号的细节特征.因此,本文提出的方法可以有效地去除兰姆波检测信号中混入的噪声.

To suppress the noise and increase the accuracy of feature extraction for ultrasonic Lamb wave signals, we present a new method based on the Tsallis mode and the fractional-order differential in this paper. Firstly, the fractional-order differentials of the amplitude spectrum of the noisy Lamb signal at different orders are obtained by using the fractional differential theory. Then, the cubic polynomial between the peak amplitude and the derivative order, and that between the peak frequency and the derivative order are proposed based on the Tsallis mode. The characteristic parameters of the amplitude spectrum are extracted with the developed equations. Finally, the Lamb signal without the noise is restored by combining the amplitude spectrum with the phase spectrum. Simulated and experimental results show that the proposed method can improve the performance parameters such as mean square error, r, and signal-to-noise ratio. Consequently, the new method based on the Tsallis mode and the fractional-order differential has the effective noise suppression performance for Lamb wave signals.