Renewal of LMS algorithm and its application in measurement

被引:0
|
作者
Zhu, ZW [1 ]
Wang, CM [1 ]
机构
[1] Nanjing Univ, Sch Mech Engn, Dept Precis Instrument & Control, Nanjing 210008, Peoples R China
关键词
LMS algorithm; error-adjustment; steepest-descendent method; signal processing;
D O I
暂无
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
LMS algorithm is one of key algorithm in signal detection and processing. Though many researches have been done on it, there still exist work to do. There is a epsilon - curve surface in LMS algorithm. This curve surface is protruding downward. According to this property, a new method estimating the minimum point of the epsilon - curve surface has been proposed in this paper. In continuous iteration steps, the descendant direction of the objective function is calculated with steepest descendant method. Then a parabola is determined through fitting algorithm. The coefficients of the curved surface are got using the minimum square error method. The minimum point of the paraboloid is then the minimum estimation of objective function through analysis method. The new method has been used in signal detection. and processing the pressure variation inside a gas pipe, the calculation efficiency and the accuracy of the new method are satisfactory.
引用
收藏
页码:1323 / 1326
页数:4
相关论文
共 50 条
  • [41] COMPLEX LMS ALGORITHM
    WIDROW, B
    MCCOOL, J
    BALL, M
    PROCEEDINGS OF THE IEEE, 1975, 63 (04) : 719 - 720
  • [42] Application of modified LMS algorithm to induction motor bearing fault diagnosis
    Chen, Kai
    Xu, Boqiang
    Li, Heming
    Duan, Xiangying
    Dianli Zidonghua Shebei / Electric Power Automation Equipment, 2008, 28 (09): : 77 - 81
  • [43] A TENSOR LMS ALGORITHM
    Rupp, Markus
    Schwarz, Stefan
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 3347 - 3351
  • [44] APPLICATION OF ORTHONORMAL TRANSFORMS TO IMPLEMENTATION OF QUASI-LMS NEWTON ALGORITHM
    FARHANGBOROUJENY, B
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1993, 41 (03) : 1400 - 1405
  • [45] INFLUENCE OF MEASUREMENT NOISE ON THE PERFORMANCE AND CONVERGENCE OF THE FILTEREDX LMS ALGORITHM; THEORY AND SIMULATIONS
    Larsson, Martin
    Johansson, Sven
    Claesson, Ingvar
    Hakansson, Lars
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONGRESS ON SOUND AND VIBRATION, 2010,
  • [47] Superior step-size theorem and its application - Parallel variable step-size LMS filters algorithm
    Gu, YT
    Tang, K
    Cui, HJ
    SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES, 2004, 47 (02): : 151 - 160
  • [48] Combined regularization parameter for normalized LMS algorithm and its performance analysis
    Shi, Long
    Zhao, Haiquan
    Wang, Wenyuan
    Lu, Lu
    SIGNAL PROCESSING, 2019, 162 : 75 - 82
  • [49] Variable step size LMS adaptive filtering algorithm and its analysis
    Gao, Ying
    Xie, Sheng-Li
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2001, 29 (08): : 1094 - 1097
  • [50] A consideration on the modified block LMS-Newton algorithm and its performance
    Kimoto, M
    Furukawa, T
    ISCAS 96: 1996 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS - CIRCUITS AND SYSTEMS CONNECTING THE WORLD, VOL 3, 1996, : 154 - 157