An EMAT denoising algorithm based on envelope filtering

To reduce the noise in the inspection data from an electromagnetic acoustic transducer (EMAT), the paper proposes a denoising method based on envelope filtering. It uses a cubic polynomial interpolation curve fitting method to obtain the envelope of the original signals, and uses the up envelope and the down envelope separately to modify the original signals according to the given denoising threshold, and then averages the up and down modified signals to get the final result of smoothing the signals and suppressing the clutters. The algorithm can suppress various types of high frequency noises mixed in the signals, without damaging the main feature of the signals. The algorithm was tested by the experiment with surface wave data. The result shows that the denoising algorithm based on envelope filtering can effectively eliminate the clutters and burrs in the inspection data, suppress the noise amplitude, and improve the signal to noise ratio.