Acoustic Emission Denoising Based on Bio-inspired Antlion Optimization: A Novel Technique for Structural Health Monitoring

Acoustic emission (AE) is a widely used non-destructive testing (NDT) technique for materials and structures, particularly for damage detection and health monitoring of structures. The interference of noise signals with the damage-related AE signals is one of the elements impacting the performance of the AE approach used for real-time monitoring of structures, leading to erroneous inspection findings.

This article addresses the problem of noise reduction in AE signals by proposing a unique technique based on the bio-inspired Antlion Optimization (ALO) algorithm.

The ALO algorithm is based on the hunting instincts of antlions. In this research, ALO is used to reduce the adaptive filter's error fitness in an adaptive noise cancellation (ANC) setup, and the suggested method is used to filter AE signals generated during concrete compression and composite drilling tests.

The performance of the ALO-based ANC is assessed quantitatively using the signal to noise ratio (SNR), peak signal to noise ratio (PSNR), and mean square error (MSE), as well as qualitatively through visual inspection of spectrograms and waveforms. The results are compared to those obtained using the gradient-based recursive least squares technique (RLS).

The ALO-based technique is of great significance to reduce the noise in AE signals by dramatically lowering the MSE and increasing the SNR when compared to the gradient-based approach RLS.