为应对舰船噪声信号环境噪声干扰强问题，研究基于小波变换的舰船噪声特征提取方法。通过高保真采集设备获取连续舰船噪声信号，利用离散小波变换分解为低频近似系数与多层高频细节系数，构建由各层能量占比组成能量特征向量，引入尺度间相关性处理以增强信号主导系数、抑制噪声，计算低频近似系数与增强后高频系数能量分布熵，形成综合反映信号宏观趋势与微观结构二维特征向量。试验表明，该方法特征提取准确度达96.87%，特征稳定性为0.02，在–30～50 dB信噪比范围内能量分布熵变化合理，抗噪能力达0.92，对故障敏感性达97.84%，能有效分离舰船噪声低频主体与高频细节特征，为舰船类型识别与状态监测建立高可靠性特征提取体系。
In order to deal with the problem of strong environmental noise interference of ship noise signal, the method of ship noise feature extraction based on wavelet transform is studied. Continuous ship noise signals are obtained through high-fidelity acquisition equipment. The discrete wavelet transform is utilized to decompose them into low-frequency approximate coefficients and multi-layer high-frequency detail coefficients. An energy feature vector composed of the energy proportions of each layer is constructed. Inter-scale correlation processing is introduced to enhance the signal dominance coefficient and suppress noise. The energy distribution entropy of the low-frequency approximate coefficients and the enhanced high-frequency coefficients is calculated. Form a two-dimensional feature vector that comprehensively reflects the macroscopic trend and microscopic structure of the signal. The experiments show that the feature extraction accuracy of this method reaches 96.87%, the feature stability is 0.02, the energy distribution entropy changes reasonably within the signal-to-noise ratio range of –30 to 50 dB, the anti-noise ability reaches 0.92, the fault sensitivity reaches 97.84%, and it can effectively separate the low-frequency main body and high-frequency detail features of ship noise. Establish a highly reliable feature extraction system for ship type identification and status monitoring.
2026,48(3): 133-137 收稿日期：2025-9-12
DOI：10.3404/j.issn.1672-7649.2026.03.021
分类号：U661
基金项目：国家青年科学基金项目（12001420）
作者简介：伊晓玲(1977-),女,硕士,讲师,研究方向为小波分析理论及应用及运筹与优化理论
参考文献：
[1] 刘夏扬, 李晶, 于华鹏, 等. 基于时频特征与排列熵的船舶噪声信号识别方法的研究[J]. 北京石油化工学院学报, 2022, 30(3): 43-50
LIU X Y, LI J, YU H P, et al. A ship recognition method based on time-frequency characteristics and permutation entropy[J]. Journal of Beijing Institute of Petro-chemical Technology, 2022, 30(3): 43-50
[2] 刘丹, 赵梅, 胡长青. 基于VMD与共振稀疏分解的舰船辐射噪声窄带特征提取[J]. 声学技术, 2024, 43(2): 172-181
LIU D, ZHAO M, HU C Q. Narrow-band feature extraction of ship radiated noise based on VMD and resonance sparse decomposition[J]. Technical Acoustics, 2024, 43(2): 172-181
[3] 郭政, 赵梅, 胡长青, 等. 舰船辐射噪声广义多尺度数学形态学特征提取与应用研究[J]. 振动与冲击, 2022, 41(4): 21-28+100
GUO Z, ZHAO M, HU C Q, et al. A study on feature extraction and application for ship radiated noise's generalized multiscale mathematical morphology feature[J]. Journal of Vibration and Shock, 2022, 41(4): 21-28+100
[4] 潘丁宁, 胡长青, 赵梅, 等. 船舶辐射噪声DEMON线谱相位差特征提取[J]. 声学技术, 2025, 44(2): 171-180
PAN D N, HU C Q, ZHAO M, et al. Study on phase difference extraction of ship radiated noise line spectrum in DEMON spectrum[J]. Technical Acoustics, 2025, 44(2): 171-180
[5] 沈鑫玉, 陈涛, 郭良浩, 等. 遗传算法优化变分模态分解提取舰船辐射噪声特征线谱方法[J]. 应用声学, 2024, 43(1): 1-11
SHEN X Y, CHEN T, GUO L H, et al. Feature line spectrum extraction of ship radiated noise based on variable mode decomposition optimized by genetic algorithm[J]. Journal of Applied Acoustics, 2024, 43(1): 1-11
[6] 童亮, 刘丹, 彭中波, 等. 联合小波阈值和F-NLM去噪的高分辨率SAR舰船检测方法[J]. 中国舰船研究, 2024, 19(6): 275-283
TONG L, LIU D, PENG Z B, et al. Method of joint wavelet thresholding and F-NLM de-noising for high-resolution SAR ship detection[J]. Chinese Journal of Ship Research, 2024, 19(6): 275-283
[7] 洪祥, 张步林, 王学永, 等. 基于小波变换技术的舰船电气设备信号去噪抑制方法[J]. 舰船科学技术, 2023, 45(23): 158-161
HONG X, ZHANG B L, WANG X Y, et al. Method for signal denoising suppression of ship electrical equipment based on wavelet transform technology[J]. Ship Science and Technology, 2023, 45(23): 158-161
