Transient response prediction of randomly excited vibro-impact systems via RBF neural networks

被引:18
|
作者
Qian, Jiamin [1 ,2 ]
Chen, Lincong [1 ,2 ,4 ]
Sun, Jian-Qiao [3 ]
机构
[1] Huaqiao Univ, Coll Civil Engn, Xiamen 361021, Peoples R China
[2] Huaqiao Univ, Key Lab Intelligent Infrastructure & Monitoring Fu, Jimei Ave 668, Xiamen 361021, Fujian, Peoples R China
[3] Univ Calif Merced, Sch Engn, Dept Mech Engn, Merced, CA 95343 USA
[4] Huaqiao Univ, Key Lab Intelligent Infrastructure & Monitoring Fu, Jimei Ave 668, Xiamen 361021, Fujian, Peoples R China
基金
中国国家自然科学基金;
关键词
Transient response; Vibro-impact system; RBF neural networks; Short-time Gaussian approximation; PATH-INTEGRAL SOLUTIONS; DATA APPROXIMATION SCHEME; FOKKER-PLANCK EQUATIONS; NUMERICAL EVALUATION; DYNAMICS; MULTIQUADRICS; TIME;
D O I
10.1016/j.jsv.2022.117456
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Systems exposed to random excitations may fail long before stationarity is achieved, which necessitates consideration of the transient responses of the system. On the other hand, the transient response prediction of non-smooth systems may face more obstacles than that of smooth systems. One of the foremost challenges lies in the handling of vector fields with singularities in non-smooth systems. In this work, the radial basis function neural networks (RBFNN) is utilized for the first time to analyze the transient response of randomly excited vibro-impact systems (VIS), a class of typical non-smooth systems. The solution of the system response is expressed in terms of a serious of Gaussian activation functions (GAFs) with time-dependent weights. These time-dependent weights are determined by minimizing a loss function, which involves the residual of the differential equations and constraint conditions. To avoid the singularity of the initial condition being a Dirac delta function, a strategy of short-time Gaussian approximation is presented to obtain the initial weights. Two typical VISs exposed to stochastic excitations are presented to verify the suggested scheme. Appropriate comparisons to the data obtained by digital simulation show that the method yields reliable results even for strongly nonlinear systems. With the merits of high computational accuracy and satisfactory efficiency, this approach is expected to be an effective method for solution of random vibration problems of high-dimensional complex non-smooth systems.
引用
收藏
页数:21
相关论文
共 43 条
  • [31] Nonlinear dynamic response of the vibro-impact systems subjected to harmonic ground motion under conditions of uncertainty on the gap size
    Pagano, Domenico
    Perna, Giuseppe
    De Angelis, Maurizio
    Andreaus, Ugo
    INTERNATIONAL JOURNAL OF NON-LINEAR MECHANICS, 2024, 165
  • [32] Response prediction of nonlinear hysteretic systems by deep neural networks
    Kim, Taeyong
    Kwon, Oh-Sung
    Song, Junho
    NEURAL NETWORKS, 2019, 111 : 1 - 10
  • [33] Response probability estimation for randomly excited quasi-linear systems using a neural network approach
    Cai, GQ
    PROBABILISTIC ENGINEERING MECHANICS, 2003, 18 (03) : 235 - 240
  • [34] Influence of the characteristics of isolation and mitigation devices on the response of single-degree-of-freedom vibro-impact systems with two-sided bumpers and gaps via shaking table tests
    Andreaus, Ugo
    De Angelis, Maurizio
    STRUCTURAL CONTROL & HEALTH MONITORING, 2020, 27 (05):
  • [35] Learning Structural Uncertainties of Nonlinear Systems with RBF Neural Networks via Persistently Exciting Control
    Bechlioulis, Charalampos P.
    Rovithakis, George A.
    2013 21ST MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED), 2013, : 1532 - 1537
  • [36] Prediction of the Impact of Approximate Computing on Spiking Neural Networks via Interval Arithmetic
    Saeedi, Sepide
    Carpegna, Alessio
    Savino, Alessandro
    Di Carlo, Stefano
    2022 23RD IEEE LATIN-AMERICAN TEST SYMPOSIUM (LATS 2022), 2022,
  • [37] Fault detection and diagnosis for non-Gaussian stochastic distribution systems with time delays via RBF neural networks
    Qu Yi
    Li Zhan-ming
    Li Er-chao
    ISA TRANSACTIONS, 2012, 51 (06) : 786 - 791
  • [38] Response estimation and system identification of dynamical systems via physics-informed neural networks
    Marcus Haywood-Alexander
    Giacomo Arcieri
    Antonios Kamariotis
    Eleni Chatzi
    Advanced Modeling and Simulation in Engineering Sciences, 12 (1)
  • [39] P4: Phase-Based Power/Performance Prediction of Heterogeneous Systems via Neural Networks
    Kim, Yeseong
    Mercati, Pietro
    More, Ankit
    Shriver, Emily
    Rosing, Tajana
    2017 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD), 2017, : 683 - 690
  • [40] ON THE IMPACT OF USING X-RAY ENERGY RESPONSE IMAGERY FOR OBJECT DETECTION VIA CONVOLUTIONAL NEURAL NETWORKS
    Bhowmik, Neelanjan
    Galls, Yona Falinie A.
    Breckon, Toby P.
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 1224 - 1228