Yu Yongsheng, Hu Yongwen, Wang Yingming, Cai Zhuoran
State Key Laboratory of Silicate Materials for Architecture, Wuhan University of Technology, Wuhan 430070, China.
School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430070, China.
Sensors (Basel). 2024 Aug 9;24(16):5146. doi: 10.3390/s24165146.
The detection of gas leaks using acoustic signals is often compromised by environmental noise, which significantly impacts the accuracy of subsequent leak identification. Current noise reduction algorithms based on non-negative matrix factorization (NMF) typically utilize the Euclidean distance as their objective function, which can exacerbate noise anomalies. Moreover, these algorithms predominantly rely on simple techniques like Wiener filtering to estimate the amplitude spectrum of pure signals. This approach, however, falls short in accurately estimating the amplitude spectrum of non-stationary signals. Consequently, this paper proposes an improved non-negative matrix factorization (INMF) noise reduction algorithm that enhances the traditional NMF by refining both the objective function and the amplitude spectrum estimation process for reconstructed signals. The improved algorithm replaces the conventional Euclidean distance with the Kullback-Leibler (KL) divergence and incorporates noise and sparse constraint terms into the objective function to mitigate the adverse effects of signal amplification. Unlike traditional methods such as Wiener filtering, the proposed algorithm employs an adaptive Minimum Mean-Square Error-Log Spectral Amplitude (MMSE-LSA) method to estimate the amplitude spectrum of non-stationary signals adaptively across varying signal-to-noise ratios. Comparative experiments demonstrate that the INMF algorithm significantly outperforms existing methods in denoising leakage acoustic signals.
利用声学信号检测气体泄漏常常受到环境噪声的影响，这对后续泄漏识别的准确性产生了显著影响。当前基于非负矩阵分解（NMF）的降噪算法通常使用欧几里得距离作为目标函数，这可能会加剧噪声异常。此外，这些算法主要依靠诸如维纳滤波等简单技术来估计纯信号的幅度谱。然而，这种方法在准确估计非平稳信号的幅度谱方面存在不足。因此，本文提出了一种改进的非负矩阵分解（INMF）降噪算法，该算法通过优化目标函数和重构信号的幅度谱估计过程来改进传统的NMF。改进后的算法用库尔贝克-莱布勒（KL）散度取代了传统的欧几里得距离，并将噪声和稀疏约束项纳入目标函数，以减轻信号放大的不利影响。与维纳滤波等传统方法不同，该算法采用自适应最小均方误差对数谱幅度（MMSE-LSA）方法，在不同信噪比下自适应地估计非平稳信号的幅度谱。对比实验表明，INMF算法在对泄漏声学信号进行去噪方面明显优于现有方法。
