基于双维度变化的形态学多重分形的战场声目标识别

摘要
图/表
参考文献(16)
相关文章 (15)

全文: PDF (2010 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对战场声目标识别的多重分形特性，提出了基于双维度变化的数学形态学多重分形计算方法。该方法定义了基于双维度变化的配分函数(DDCDF)，同时引入回归分析对分形尺度与配分函数进行高精度拟合，确保采用两点式斜率计算作为分形维数的准确性；以运算速度与识别率为标准，筛选出最优尺度组合，并计算多重分形维数。通过半实物仿真对比试验验证了所提算法的运算效率较现有的形态学多重分形维数算法有明显提升；此外，将多重分形维数作为特征输入，使用支持向量机进行声目标识别，识别结果显示了该算法所提取的多重分形维数特征具有更好的区分度，其识别率比现有算法提升了23.5%，为战场声目标的非线性特征快速识别提供了一种有效的技术手段。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张坤1
	邸忆1
	2
	顾晓辉1

关键词 ：数学形态学, 多重分形, 回归分析, 快速算法, 声目标识别

Abstract：An acoustic recognition method based on morphological multifractal of double dimensions changed was proposed according to the multifractal characteristics of the battlefield acoustic target.The method defined double dimensions changed distributed function.Regression analysis was used to show that the accuracy of fitting with the function was high and the slope of two points could be used as the fractal dimension.Based on speed and recognition rate, the best scale group was selected.The simulation results show that the algorithm is faster than the traditional method of measurement in morphological multifractal obviously.The multifractal dimension calculated by them was used as the feature input.The support vector machine was used for acoustic target recognition, and also the acoustic target recognition rate is increased by 23.5% compared with the existed method.Therefore, the method proposed in this work can be a better choice for battlefield acoustic target recognition using the nonlinear characteristic of the signal.

Key words： morphology multifractal regression analysis fast algorithm acoustic recognition

收稿日期: 2018-04-28 出版日期: 2019-12-15

引用本文:

张坤1，邸忆1,2，顾晓辉1. 基于双维度变化的形态学多重分形的战场声目标识别[J]. 振动与冲击, 2019, 38(24): 203-208.
ZHANG Kun1,DI Yi1,2,GU Xiaohui1. Recognition of battlefield acoustic target based on morphological multifractal of double changed dimensions. JOURNAL OF VIBRATION AND SHOCK, 2019, 38(24): 203-208.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2019/V38/I24/203

[1] 邸忆, 顾晓辉, 龙飞. 一种基于声阵列信息融合及改进EEMD的信号降噪方法[J]. 振动与冲击, 2017, 36(15):133-141.
   Di Y, Gu X, Long F. A signal de-noising method for multi-microphone array based on information fusion and improved EEMD[J]. Journal of Vibration & Shock, 2017, 36(15):133-141.
[2] 褚青青, 肖涵, 吕勇,等. 基于多重分形理论与神经网络的齿轮故障诊断[J]. 振动与冲击, 2015,34(21):15-18.
   Chu Q Q, Han X, Yong L, et al. Gear fault diagnosis based on multifractal theory and neural network[J]. Journal of Vibration & Shock, 2015，34(21):15-18.
[3] Xia Y, Feng D D, Zhao R. Morphology-based multifractal estimation for texture segmentation[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2006, 15(3):614-623.
[4] Li B, Zhang P L, Wang Z J, et al. A weighted multi-scale morphological gradient filter for rolling element bearing fault detection[J]. Isa Transactions, 2011, 50(4):599-608.
[5] Frecon J, Pustelnik N, Wendt H, et al. Multivariate optimization for multifractal-based texture segmentation[C]. IEEE   International Conference on Image Processing. IEEE,015:4957-4961.
[6] 李兵, 张培林, 任国全,等. 基于数学形态学的分形维数计算及在轴承故障诊断中的应用[J]. 振动与冲击, 2010, 29(5):191-194.
   Li B, Zhang P L, Ren G Q, et al. Mathematic morphology-based fractal dimension calculation and its application in fault diagnosis of roller bearings[J]. Journal of Vibration & Shock, 2010, 29(5):191-194.
[7] 丁庆海, 庄志洪. 混沌,分形和小波理论在被动声信号特征提取中的应用[J]. 声学学报, 1999,24(2):197-203.
   Ding Q, Zhuang Z, Zhu L, et al. Application of the chaos, fractal and wavelet theories to the feature extraction of passive acoustic signal[J]. Acta Acustica, 1999，24(2):197-203
[8] 丁凯, 方向, 张卫平,等. 基于声信号多重分形和支持向量机的目标识别研究[J]. 兵工学报, 2012, 33(12):1521-1526.
   Ding K, Fang X, Zhang W P, et al. Target identification of acoustic signals based on multifractal analysis and support vector machine[J]. Acta Armamentarii,2012, 33(12):1521-1526.
[9] Shen C, He Q, Kong F, et al. A fast and adaptive varying-scale morphological analysis method for rolling element bearing fault diagnosis[J]. Proceedings of Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science, 2013, 227(6):1362-1370.
[10] 李兵, 张培林, 米双山等. 齿轮故障信号多重分形维数的形态学计算方法[J]. 振动、测试与诊断, 2011, 31(4):450-453.
    Bing L, Zhang P, Mi S, et al. Mathematical Morphology Based on Multifractal Dimensions for Gear Fault Diagnosis[J]. Journal of Vibration Measurement & Diagnosis, 2011, 31(4):450-453.
[11] 王冰, 李洪儒, 许葆华. 数学形态学分形维数广义估算方法及其应用[J]. 振动工程学报, 2014, 27(6):951-959.
    Wang B, Li H R, Xu B H. Generalized estimation method of fractal dimension based on mathematical morphology and its application in bearing degradation status identification[J]. journal of Vibration Engineering, 2014, 27(6):951-959.
[12] Hu Z, Wang C, Zhu J, et al. Bearing fault diagnosis based on an improved morphological filter[J]. Measurement,2016, 80(2):163-178.
[13] Yu D, Wang M, Cheng X. A method for the compound fault diagnosis of gearboxes based on morphological component analysis[J]. Measurement, 2016, 91(9):519-531.
[14] Li B, Zhang P L, Liu D S, et al. Classification of time-frequency representations based on two-direction 2DLDA for gear fault diagnosis [J]. Applied Soft Computing, 2011, 11(8):5299-5305.
[15] Maragos P, Sun F K. Measuring the Fractal Dimension of Signals: Morphological Covers and Iterative Optimization[J]. IEEE Transactions on Signal Processing, 1993, 41(1):108-121.
[16] Yang L, Liu S, Tsoka S, et al. Mathematical programming for piecewise linear regression analysis[J]. Expert Systems with Applications An International Journal, 2016, 44(C):156-167.