Active vibration control of structural systems with a preview of a future seismic waveform generated by remote waveform observation data and an artificial intelligence–based waveform estimation system
Restricted accessResearch articleFirst published online September, 2020
Active vibration control of structural systems with a preview of a future seismic waveform generated by remote waveform observation data and an artificial intelligence–based waveform estimation system
We propose a new active vibration control strategy of structural systems based on the information of future seismic waveform observed in remote observation sites. The observed waveform information of the remote site is transmitted by a waveform transmission network to the structure under control. The waveform transmission network is realized by interconnecting multiple controlled structures and observation sites. By using the remote waveform containing the future information of the disturbance at the location of the controlled structure, we propose an active control method that achieves fairly higher control performance over conventional methodologies. A preview control consisting of the state-feedback and feedforward control (preview action) is adopted as the control law. For the preview action, a future seismic waveform in some time interval is needed. Because the future seismic waveform is not available, the preview action contributing the performance improvement is generally impossible. To get over this difficulty, an artificial intelligence–based waveform estimation system to estimate the future seismic waveform is proposed. The core of the wave estimation system is a multi-layered artificial neural network. Through a small-scale simulation study with a recorded seismic event in Japan, we show that the proposed control method achieves much higher control performance over the optimized state-feedback control law.
AkbariALohmannB (2010) Output feedback H∞/GH2 preview control of active vehicle suspensions: a comparison study of LQG preview. Vehicle System Dynamics48(12): 1475–1494.
2.
Bani-HaniKGhaboussiJ (1998) Neural networks for structural control of a benchmark problem, active tendon system. Earthquake Engineering & Structural Dynamics27(11): 1225–1245.
3.
BirlaNSwarupA (2015) Optimal preview control: a review. Optimal Control Applications and Methods36: 241–268.
4.
ChenHM,TsaiKH,QiGZ, et al. (1995) Neural network for structure control. Journal of Computing in Civil Engineering9(2): 168–176.
5.
De OliveiraMC,GeromelJCBernussouJ (2002) Extended H2 and H∞ norm characterizations and controller parametrizations for discrete-time systems. International Journal of Control75(9): 666–679.
6.
DykeSJ,SpencerBF,SainMK, et al. (1996) An experimental study of MR dampers for seismic protection. Smart Materials and Structures7: 693–703.
7.
FuY,MechitovK,HoangT, et al. (2019) Development and full-scale validation of high-fidelity data acquisition on a next-generation wireless smart sensor platform. Advances in Structural Engineering22: 3512–3533.
8.
GhaboussiJJoghataieA (1995) Active control of structures using neural networks. Journal of Engineering Mechanics121(4): 555–567.
9.
GravesAJaitlyN (2014) Towards end-to-end speech recognition with recurrent neural networks. In: 31st international conference on machine learning, Beijing, China, 21–26 June 2014.
10.
HamadaY (2016) Discrete-time preview feedforward design via linear matrix inequality. Transactions of the Society of Instrument and Control Engineers52(8): 446–452(in Japanese).
11.
HiramotoK,MatsuokaTSunakodaK (2016) Semi-active vibration control of structural systems based on a reference active control law: output emulation approach. Structural Control and Health Monitoring23: 423–445.
12.
HirataN,SakaiS,SatoH, et al. (2009) An outline of the special project for earthquake disaster mitigation in the Tokyo metropolitan area–subproject I: characterization of the plate structure and source faults in and around the Tokyo metropolitan area. Bulletin of the Earthquake Research Institute, University of Tokyo84: 41–56(in Japanese).
KatayamaT,OhkiT,InoueT, et al. (1985) Design of an optimal controller for a discrete-time system subject to previewable demand. International Journal of Control41(3): 677–699.
15.
KrizhevskyA,SutskeverIHintonGE (2012) ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems25: 1097–1105.
16.
KuyukHSMotosakaM (2009) Forward spectral forecasting of ground motion with the information of earthquake early warning systems for structural control. Journal of Japan Association for Earthquake Engineering9(3): 14–27.
17.
MarzbanradJ,AhmadiGJhaR (2004) Optimal preview active control of structures during earthquakes. Engineering Structures24: 1437–1471.
18.
MohamedA,DahlGHintonG (2009) Deep Belief Networks for phone recognition. In: NIPS workshop on deep learning for speech recognition and related applications, Vancouver, Canada, 6–10 December 2009. Available atwww.cs.utoronto.ca/gdahl/papers/dbnPhoneRec.pdf.
19.
NagashimaIMasekiR (2012) Study on feed-forward control of base-isolated buildings using predicted propagation of seismic waves. In: 15th world conference on earthquake engineering, Lisbon, Portugal, 24–28 September 2012, pp. 9820–9820.
20.
NakamuraY,FukukitaA,TamuraK, et al. (2014) Seismic response control using electromagnetic inertial mass dampers. Earthquake Engineering & Structural Dynamics43: 507–527.
21.
National Research Institute for Earth Science and Disaster Resilience (1996) Realtime ground-motion monitoring system. Available at: www.kmoni.bosai.go.jp (accessed 1 June 2019).
22.
RumelhartDE,HintonGEWilliamsRJ (1986) Learning representations by back-propagating errors. Nature323(6088): 533–536.
23.
SakaiSHirataN (2009) Distribution of the metropolitan seismic observation network. Bulletin of the Earthquake Research Institute, University of Tokyo84: 57–69(in Japanese).
24.
SchnabelPB,LysmerJSeedHB (1972) Shake A Computer Program for Earthquake Response Analysis of Horizontally Layered Sites. Report no. EERC72-12. Berkeley, CA: University of California.
SunZ,LiB,DykeSJ, et al. (2016) Benchmark problem in active structural control with wireless sensor network. Structural Control and Health Monitoring23: 20–34.
27.
TateisiANishiokaT (2002) Control of structural response by using information on predicted external force. Journal of Japan Society of Civil Engineers1–58(696): 21–29(in Japanese).
28.
TomizukaMRosenthalDE (1979) On the optimal digital state vector feedback controller with integral and preview actions. Journal of Dynamic Systems, Measurement, and Control101(2): 172–178.
29.
TsujiT,NakamuraH,KagimuraS (2012) Studies on an active preview control of structures and applicability of predicted earthquake motions. Journal of Japan Society of Civil Engineers, Series A1 (Structural Engineering & Earthquake Engineering (SE/EE)68(1): 110–123(in Japanese).
30.
United States Geological Survey (2016) ShakeAlert: an earthquake early warning system for the west coast of the United States. Available at: www.shakealert.org/ (accessed 1 June 2019).
31.
WaheebW,GhazaliRHerawanT (2016) Ridge polynomial neural network with error feedback for time series forecasting. PLOS One11(12): e0167248.
32.
WangNAdeliH (2015) Self-constructing wavelet neural network algorithm for nonlinear control of large structures. Engineering Application of Artificial Intelligence41: 249–258.
