Real-time neural network based semiactive model predictive control of structural vibrations

被引:4
|
作者
Yu, Tianhao [1 ]
Mu, Zeyu [1 ,2 ,3 ]
Johnson, Erik A. [1 ]
机构
[1] Univ Southern Calif, Sonny Astani Dept Civil & Environm Engn, Los Angeles, CA 90089 USA
[2] Univ Virginia, Link Lab, Charlottesville, VA 22904 USA
[3] Univ Virginia, Dept Engn Syst & Environm, Charlottesville, VA 22904 USA
基金
美国国家科学基金会;
关键词
Model predictive control; Neural network; Real-time control; Semiactive control; MULTICLASS; SYSTEMS;
D O I
10.1016/j.compstruc.2022.106899
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Semiactive model predictive control (sMPC) can be very effective, but its computational cost due to the inherent mixed-integer quadratic programming (MIQP) optimization precludes its use in real-time vibra-tion control. This study proposes training neural networks (NNs) to predict in real-time only the MIQP's integer variables' values, called a strategy, for a given structure state. Because the number of strategies is exponential in the number of sMPC horizon steps, the resulting NN can be massive. This study proposes to reduce the NN dimension by exploiting the homogeneity-of-order-one nature of this control problem and, using state vector statistics, to efficiently choose training samples. The single large NN is proposed to be split into several much smaller NNs, each predicting a strategy grouping, that together uniquely and efficiently predict the strategy. Given the strategy's integer values, the MIQP optimization reduces to a quadratic programming (QP) problem, solved using a fast QP solver with proposed adaptations: exploit-ing optimization efficiencies and bounding sub-optimality; using several NN predictions; and reverting to a simpler (suboptimal) semiactive control algorithm upon occasional incorrect NN predictions or QP sol-ver nonconvergence. Shear building examples demonstrate significant online computational cost reduc-tions with control performance comparable to the conventional MIQP-based control.(c) 2022 Elsevier Ltd. All rights reserved.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] Integration of real-time optimization and model predictive control
    Adetola, V.
    Guay, M.
    JOURNAL OF PROCESS CONTROL, 2010, 20 (01) : 125 - 133
  • [22] Real-time control of AHU based on a neural network assisted cascade control system
    Guo, CY
    Song, Q
    Cai, WJ
    2004 IEEE CONFERENCE ON ROBOTICS, AUTOMATION AND MECHATRONICS, VOLS 1 AND 2, 2004, : 964 - 969
  • [23] Model predictive control-based feedback scheduling for real-time control systems
    Dept. of Automation, Shanghai Jiaotong Univ., Shanghai 200030, China
    Shanghai Jiaotong Daxue Xuebao, 2006, 5 (838-842+847):
  • [24] Model Predictive Control for Real-time Simulation of a Network-controlled Vehicle Drivetrain
    Caruntu, Constantin Florin
    Onu, Doina
    Braescu, Florin Catalin
    Lazar, Corneliu
    2011 2ND EASTERN EUROPEAN REGIONAL CONFERENCE ON THE ENGINEERING OF COMPUTER BASED SYSTEMS (ECBS-EERC), 2011, : 115 - 123
  • [25] Development of deep artificial neural network controller based on non-linear model predictive control data for real-time autonomous driving
    Lee T.
    Kang Y.
    Journal of Institute of Control, Robotics and Systems, 2020, 26 (05) : 302 - 311
  • [26] Real-Time Adaptive Control of Robot Manipulator Based on Neural Network Compensator
    Cong-Nguyen, Huu
    Lee, Woo-Song
    Lee, Dong-Han
    Han, Sung-Hyun
    2008 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS, VOLS 1-4, 2008, : 2240 - +
  • [27] AGC real-time control strategy based on LSTM recurrent neural network
    Li B.
    Wang J.
    Liang S.
    Wei C.
    Dianli Zidonghua Shebei/Electric Power Automation Equipment, 2022, 42 (03): : 128 - 134
  • [28] Real-Time Model Predictive Control of Human Bodyweight Based on Energy Intake
    Fernandez, Alberto Pena
    Youssef, Ali
    Heeren, Charlotte
    Matthys, Christophe
    Aerts, Jean-Marie
    APPLIED SCIENCES-BASEL, 2019, 9 (13):
  • [29] Real-Time Model Predictive Control Based on Prediction-Correction Algorithms
    Paternain, Santiago
    Morari, Manfred
    Ribeiro, Alejandro
    2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC), 2019, : 5285 - 5291
  • [30] Real-time microgrid economic dispatch based on model predictive control strategy
    Du, Yan
    Pei, Wei
    Chen, Naishi
    Ge, Xianjun
    Xiao, Hao
    JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, 2017, 5 (05) : 787 - 796