Hierarchical learning-based cascaded adaptive filtering for nonlinear system identification

被引:0
|
作者
Le, Dinh Cong [1 ]
Phan, Van Du [1 ]
机构
[1] Vinh Univ, Sch Engn & Technol, 182 Le Duan, Vinh 43108, Nghe An, Vietnam
关键词
Nonlinear adaptive filter; Hierarchical; Cascade; Functional links artificial neural networks; Legendre neural networks; NEURAL-NETWORK FILTER; VOLTERRA FILTER;
D O I
10.1016/j.dsp.2025.105031
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
To enhance the dynamic performance of point-wise nonlinear expansion-based filters, such as the functional links artificial neural networks (FLANN) and Legendre neural networks (LNN), a novel cascaded filter in a hierarchical design fashion between FLANN and LNN, has been introduced in this paper. The proposed filter comprises two layers: the first layer consists of small-sized FLANN modules nested in a pipelined fashion to extract features from the input data efficiently; the second layer is an LNN transversal filter whose task is to further process the output data from the first layer. A nonlinear activation function is implemented between the two layers to ensure stability in Legendre functional expansion. The adaptive weights of the layers are updated based on a modified hierarchical learning algorithm to avoid the cost of computing the backpropagation error. Furthermore, the proposed filter is computationally efficient, thanks to small-sized FLANN modules and a parallel processing architecture. Besides, the study has analyzed the stability and convergence conditions of the algorithm. Experimental results have shown that the proposed filter performs better in nonlinear dynamic system identification scenarios than FLANN, LNN, and other cascaded FLANN-LNN filters.
引用
收藏
页数:10
相关论文
共 50 条
  • [41] Adaptive learning-based optimal tracking control system design and analysis of a disturbed nonlinear hypersonic vehicle model
    An, Kai
    Wang, Zhenguo
    Huang, Wei
    SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2024, 67 (06) : 1893 - 1906
  • [42] Deep learning-based indirect bridge damage identification system
    Hajializadeh, Donya
    STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2023, 22 (02): : 897 - 912
  • [43] Adaptive learning-based optimal tracking control system design and analysis of a disturbed nonlinear hypersonic vehicle model
    AN Kai
    WANG ZhenGuo
    HUANG Wei
    Science China(Technological Sciences), 2024, 67 (06) : 1893 - 1906
  • [44] On the Vulnerability of Graph Learning-based Collaborative Filtering
    Xu, Senrong
    Li, Liangyue
    Li, Zenan
    Yao, Yuan
    Xu, Feng
    Chen, Zulong
    Lu, Quan
    Tong, Hanghang
    ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2023, 41 (04)
  • [45] PatchRNN: A Deep Learning-Based System for Security Patch Identification
    Wang, Xinda
    Wang, Shu
    Feng, Pengbin
    Sun, Kun
    Jajodia, Sushil
    Benchaaboun, Sanae
    Geck, Frank
    2021 IEEE MILITARY COMMUNICATIONS CONFERENCE (MILCOM 2021), 2021,
  • [46] Applying adaptive recursive filtering to system identification
    Wang, FL
    An, LL
    An, LN
    Xu, YX
    ICSP '96 - 1996 3RD INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, PROCEEDINGS, VOLS I AND II, 1996, : 250 - 253
  • [47] MACHINE LEARNING BASED NONLINEAR RESONATOR SYSTEM IDENTIFICATION
    Jain, Pavitra
    Gupta, Garvit
    Kwon, Hyun-Keun
    Vukasin, Gabrielle D.
    Chandorkar, Saurabh A.
    2024 IEEE 37TH INTERNATIONAL CONFERENCE ON MICRO ELECTRO MECHANICAL SYSTEMS, MEMS, 2024, : 541 - 544
  • [48] Machine learning-based adaptive model identification of systems: Application to a chemical process
    Bhadriraju, Bhavana
    Narasingam, Abhinav
    Kwon, Joseph Sang-Il
    CHEMICAL ENGINEERING RESEARCH & DESIGN, 2019, 152 : 372 - 383
  • [49] Nonlinear Adaptive Control of Maglev System Based on Parameter Identification
    Qiang, Haiyan
    Qiao, Sheng
    Huang, Hengyue
    Cheng, Ping
    Sun, Yougang
    ACTUATORS, 2025, 14 (03)
  • [50] A Nonlinear System Identification Method Based on Adaptive Neural Network
    Sun J.
    Lin L.
    Journal of Computing and Information Technology, 2020, 28 (02) : 111 - 123