An improved approach for denoising acoustic signals of subsea gas pipeline leak using hybrid algorithms

Abstract

 Detecting leaks in subsea gas pipelines is a complex challenge because ambient noise often compromises the accuracy of detection. Effective noise removal from pipeline leak signals is essential for improving the precision of leak identification in subsea pipelines. In this study, a hybrid intelligent algorithm is designed to enhance the denoising capability of subsea gas pipeline leak signals. The key parameters of the Variational Mode Decomposition (VMD) were optimized using the Archimedes Optimization Algorithm (AOA) to ensure efficient and accurate signal decomposition. The optimized VMD decomposes a noisy signal into multiple Intrinsic Mode Functions (IMFs), each containing distinct signal components. These IMFs were filtered by calculating their correlation with the original signal. The principal components of the leak signal retained after this screening process were reconstructed. The Wavelet Transform (WT) was applied to further eliminate residual noise and enhance the signal quality. The results demonstrate that the optimized VMD significantly improves the decomposition accuracy and efficiency compared to traditional parameter selection methods. Furthermore, the joint AOA-VMD-WT denoising algorithm outperformed the other methods across common denoising metrics, showing superior noise reduction performance.

One sentence summary: This study presents a novel approach to subsea leak signal processing, showing that AOA-VMD-WT boosts acoustic quality, simplifying preprocessing and making reliable signal analysis accessible for real-time pipeline monitoring.