舰船电子工程
艦船電子工程
함선전자공정
SHIP ELECTRONIC ENGINEERING
2012年
7期
48-50
,共3页
MUSIC算法%神经网络%迭代算法%DOA估计
MUSIC算法%神經網絡%迭代算法%DOA估計
MUSIC산법%신경망락%질대산법%DOA고계
multiple signal classification algorithm%neural network%iterative algorithm%direction of arrival estimation
MUSIC方法是空间谱估计中经典的子空间方法,这类算法有个共同特点就是要对输出数据的协方差矩阵进行数学分解,其计算量较大,不适合实时处理。因此,文章提出了基于神经网络的高效迭代方法,不需进行数学分解,计算过程相对简单。仿真结果证明了该方法的有效性。
MUSIC方法是空間譜估計中經典的子空間方法,這類算法有箇共同特點就是要對輸齣數據的協方差矩陣進行數學分解,其計算量較大,不適閤實時處理。因此,文章提齣瞭基于神經網絡的高效迭代方法,不需進行數學分解,計算過程相對簡單。倣真結果證明瞭該方法的有效性。
MUSIC방법시공간보고계중경전적자공간방법,저류산법유개공동특점취시요대수출수거적협방차구진진행수학분해,기계산량교대,불괄합실시처리。인차,문장제출료기우신경망락적고효질대방법,불수진행수학분해,계산과정상대간단。방진결과증명료해방법적유효성。
MUSIC algorithm is a classic suhspace method for spatial estimation. The MUSIC as high-resolution spatial estimation algo- rithm need to decompose eovariance matrix of the array output data, which involves large amount of computation and is not suitable for real- time processing. Therefore, a novel MUSIC algorithm based on neural network is proposed in this paper. This algorithm that needs no de- compose covariance matrix of the array, is relatively simple in the calculation process. Simulation results demonstrate the effectiveness of the new method.
