Optimal sensor placement for structural health monitoring based on deep reinforcement learning

다국어 초록 (Multilingual Abstract)

In structural health monitoring of large-scale structures, optimal sensor placement plays an important role because of the high cost of sensors and their supporting instruments, as well as the burden of data transmission and storage. In this study, a vibration sensor placement algorithm based on deep reinforcement learning (DRL) is proposed, which can effectively solve non-convex, high-dimensional, and discrete combinatorial sensor placement optimization problems. An objective function is constructed to estimate the quality of a specific vibration sensor placement scheme according to the modal assurance criterion (MAC). Using this objective function, a DRL-based algorithm is presented to determine the optimal vibration sensor placement scheme. Subsequently, we transform the sensor optimal placement process into a Markov decision process and employ a DRLbased optimization algorithm to maximize the objective function for optimal sensor placement. To illustrate the applicability of the proposed method, two examples are presented: a 10-story braced frame and a sea-crossing bridge model. A comparison study is also performed with a genetic algorithm and particle swarm algorithm. The proposed DRL-based algorithm can effectively solve the discrete combinatorial optimization problem for vibration sensor placements and can produce superior performance compared with the other two existing methods.

참고문헌 (Reference)

1 Zhao, T., "Traffic signal control with deep reinforcement learning" 2019

2 Chenchu Xu, "Synthesis of gadolinium-enhanced liver tumors on nonenhanced liver MR images using pixel-level graph reinforcement learning" Elsevier BV 69 : 101976-, 2021

3 Chalioris, C. E., "Structural health monitoring of seismically vulnerable RC frames under lateral cyclic loading" 19 (19): 29-44, 2020

4 Zhenghao Ding, "Structural damage identification by sparse deep belief network using uncertain and limited data" Hindawi Limited 27 (27): 2020

5 Hossein Hosseini-Toudeshky, "Sensor placement optimization for guided wave-based structural health monitoring" 테크노프레스 8 (8): 125-150, 2021

6 Kammer, D. C., "Sensor placement for on-orbit model identification and correlation of large space structures" 14 (14): 251-259, 1991

7 Sutton, R. S., "Reinforcement Learning: An Introductio"

8 Zhi Wang, "Reinforcement Learning-Based Optimal Sensor Placement for Spatiotemporal Modeling" Institute of Electrical and Electronics Engineers (IEEE) 50 (50): 2861-2871, 2020

9 Huang, Y., "Recovering compressed images for automatic crack segmentation using generative models" 146-, 2021

10 Mnih, V., "Playing atari with deep reinforcement learning"

11 Mosbeh R. Kaloop ; Mohamed Elsharawy ; Basem Abdelwahed ; Jong Wan Hu ; Dongwook Kim, "Performance assessment of bridges using short-period structural health monitoring system: Sungsu bridge case study" 국제구조공학회 26 (26): 667-680, 2020

12 Singh, Y., "Path planning of an autonomous surface vehicle based on artificial potential fields in a real time marine environment" 2017

13 Altunisik, A. C., "Optimal sensor placements for system identification of concrete arch dams" 11 (11): 397-407, 2021

14 Hao Sun, "Optimal sensor placement in structural health monitoring using discrete optimization" IOP Publishing 24 (24): 125034-, 2015

15 Wei Liu, "Optimal sensor placement for spatial lattice structure based on genetic algorithms" Elsevier BV 317 (317): 175-189, 2008

16 Chengyin Liu ; Jun Teng ; Zhen Peng, "Optimal sensor placement for bridge damage detection using deflection influence line" 국제구조공학회 25 (25): 169-181, 2020

17 D. J. Ewins, "Modal Testing: Theory and Practice" ASME International 108 (108): 109-110, 1986

18 Alexander Clegg, "Learning to Collaborate From Simulation for Robot-Assisted Dressing" Institute of Electrical and Electronics Engineers (IEEE) 5 (5): 2746-2753, 2020

19 Yurtsever, E., "Information-driven distributed maximum likelihood estimation based on Gauss-Newton method in wireless sensor networks" IV : 1311-1316, 2020

20 Tong Zhao, "Information-Driven Distributed Maximum Likelihood Estimation Based on Gauss-Newton Method in Wireless Sensor Networks" Institute of Electrical and Electronics Engineers (IEEE) 55 (55): 4669-4682, 2007

21 Krishna, A., "Image synthesis for data augmentation in medical ct using deep reinforcement learning"

22 Volodymyr Mnih, "Human-level control through deep reinforcement learning" Springer Science and Business Media LLC 518 (518): 529-533, 2015

23 Ting-Hua Yi, "Health monitoring sensor placement optimization for Canton Tower using immune monkey algorithm" Hindawi Limited 22 (22): 123-138, 2014

24 Xianrong Qin, "Health monitoring sensor placement optimization based on initial sensor layout using improved partheno-genetic algorithm" SAGE Publications 24 (24): 252-265, 2020

25 Rongrong Hou, "Genetic algorithm based optimal sensor placement forL₁-regularized damage detection" Hindawi Limited 26 (26): e2274-, 2018

26 Shiyin Wei, "General solutions for nonlinear differential equations: a rule-based self-learning approach using deep reinforcement learning" Springer Science and Business Media LLC 64 (64): 1361-1374, 2019

27 Luca Rosafalco, "Fully convolutional networks for structural health monitoring through multivariate time series classification" Springer Science and Business Media LLC 7 (7): 2020

28 Lin, K., "Exploration-efficient deep reinforcement learning with demonstration guidance for robot control"

29 Tao Yin, "Entropy‐Based Optimal Sensor Placement for Model Identification of Periodic Structures Endowed with Bolted Joints" Wiley 32 (32): 1007-1024, 2017

30 Ka-Veng Yuen, "Efficient model updating and health monitoring methodology using incomplete modal data without mode matching" Hindawi Limited 13 (13): 91-107, 2006

31 Vahab Akbarzadeh, "Efficient Sensor Placement Optimization Using Gradient Descent and Probabilistic Coverage" MDPI AG 14 (14): 15525-15552, 2014

32 Darragh Lydon ; S.E. Taylor ; Myra Lydon ; Jesus Martinez del Rincon ; David Hester, "Development and testing of a composite system for bridge health monitoring utilising computer vision and deep learning" 국제구조공학회 24 (24): 723-732, 2019

33 Paolo Borlenghi ; Carmelo Gentile ; Antonella Saisi, "Detecting and localizing anomalies on masonry towers from low-cost vibration monitoring" 국제구조공학회 27 (27): 319-333, 2021

34 Ruhua Wang, "Densely connected convolutional networks for vibration based structural damage identification" Elsevier BV 245 : 112871-, 2021

35 Van Hasselt, H., "Deep reinforcement learning with double q-learning" 2016

36 Raed J. AlSaleh ; Clemente Fuggini, "Combining GPS and accelerometers’ records to capture torsional response of cylindrical tower" 국제구조공학회 25 (25): 111-122, 2020

37 Said Quqa ; Pier Francesco Giordano ; Maria Pina Limongelli ; Luca Landi ; Pier Paolo Diotallevi, "Clump interpolation error for the identification of damage using decentralized sensor networks" 국제구조공학회 27 (27): 351-363, 2021

38 Yong Huang, "Bayesian system identification based on hierarchical sparse Bayesian learning and Gibbs sampling with application to structural damage assessment" Elsevier BV 318 : 382-411, 2017

39 Chen Yang, "An interval effective independence method for optimal sensor placement based on non-probabilistic approach" Springer Science and Business Media LLC 60 (60): 186-198, 2016

40 Oh, J., "Action-conditional video prediction using deep networks in Atari games" 2 : 8-, 2015

41 Che-Cheng Chang, "Accuracy Improvement of Autonomous Straight Take-off, Flying Forward, and Landing of a Drone with Deep Reinforcement Learning" Springer Science and Business Media LLC 13 (13): 914-, 2020

42 Wen-Hwa Wu ; Jhe-Wei Jhou ; Chien-Chou Chen ; Gwolong Lai, "A novel recursive stochastic subspace identification algorithm with its application in long-term structural health monitoring of office buildings" 국제구조공학회 24 (24): 459-474, 2019

43 Gauri Kalnoor, "A Review on Applications of Markov Decision Process Model and Energy Efficiency in Wireless Sensor Networks" Elsevier BV 167 : 2308-2317, 2020

44 Can He, "A New Optimal Sensor Placement Strategy Based on Modified Modal Assurance Criterion and Improved Adaptive Genetic Algorithm for Structural Health Monitoring" Hindawi Limited 2015 : 1-10, 2015

45 Carne, T. G., "A Modal Test Design Strategy for Model Correlation (No. SAND-94-2702C; CONF- 950240-4)"

46 P. C. Shah, "A Methodology for Optimal Sensor Locations for Identification of Dynamic Systems" ASME International 45 (45): 188-196, 1978