摘要
舰船辐射噪声特征提取是水下被动声探测装置进行目标识别、分类的关键技术;针对于此,研究了基于功率谱的连续谱、线谱特征实时提取技术和工程实现;该技术以分段拟合为基础,首先提取功率谱中的连续谱特征,再从原始功率谱中减去连续谱得到线谱分布,然后进行线谱特征提取;在此基础上,详细介绍了舰船噪声功率谱特征提取的软、硬件系统设计和实现技术;系统经过实验验证,能有效提取不同类型目标的特征,系统性能良好,可满足新一代水下智能被动探测的要求。
Feature extraction of warship radiated noise is the key technique for underwater passsive detection system to recognize and classify the targets. Aiming for this, this paper studies the technique on the real--time feature extraction of continuous and line spectrums and engineering realization based on the power spectrum of radiated noise. The technique, on the basis of segmented fitting algorithm, firstly extracts the continuous spectrum features and then subtracts the continuous spectrum from the power spectrum, and extracts the line spectrum features from the remainder spectrum. Further more, the technique is applied to a real feature extraction system, and paper details the system＇s software and hardware design and realization. Experimentation results show that the whole designed system performs well and matches the factors which the new generation underwater intelligent passive detection system expects.
出处
《计算机测量与控制》
CSCD
北大核心
2010年第8期1821-1824,共4页
Computer Measurement &Control
基金
国防预研基金资助(4010709010402)
关键词
舰船噪声
特征提取
功率谱
连续谱
线谱
warship noise
feature extraction
power spectrum
continuous spectrum
line spectrum
