摘要
为改善MUSIC类DOA估计算法检测弱信源的性能,提出了一种利用过估计源个数和频域峰值统计信息检测宽带弱信号源的MUSIC类DOA估计算法(OSM)。该算法放宽了MUSIC类DOA估计算法过于依赖信源个数质量的限制,OSM把过估计的信源个数输入给MUSIC,提高了正确检测弱信源的概率,同时也增加了虚警概率,但虚假峰值随窄带的变化呈无规则分布。由PPNN和MNT把这一频率域信息引入到信源检测,抑制了虚假峰,提高了OSM的检测性能。其最小可检测信噪比较传统的MUSIC类DOA估计算法降低了6dB。当带宽较窄时,若信号平稳性较好,适当增加一次快拍的采样长度,可提高窄带数目,亦增加了OSM的稳定性。海上实验数据处理得到了和理论分析一致的结果,该数据处理结果也初步验证了OSM算法的良好检测性能。
An algorithm called OSM （MUSIC with overestimation of source number） is presented in this paper. This is a kind of MUSIC algorithm for DOA estimation appropriate to detect weak wideband source based on overestimation of source number and statistical information peak in the frequency domain. The algorithm loosens the limitation of strong dependence on quality of source number estimation in the MUSIC algorithm, and improves performance of DOA estimation, especially when detecting weak wideband source. It is shown via computer simulation that the minimal detectable SNR of the OSM algorithm is lowered by 6dB compared with the conventional MUSIC, and the results of sea experiments well agree with theoretical analysis.
出处
《声学技术》
CSCD
北大核心
2007年第5期830-834,共5页
Technical Acoustics
基金
声场声信息国家重点实验室基金(200502)
关键词
阵列信号处理
弱信号检测
DOA估计
array signal processing
weak signal detection
DOA estimation
