Convolutional Neural Networks for Real-Time and Wireless Damage Detection

Structural damage detection methods available for structural health monitoring applications are based on data preprocessing, feature extraction, and feature classification. The feature classification task requires considerable computational power which makes the utilization of centralized techniques relatively infeasible for wireless sensor networks. In this paper, the authors present a novel Wireless Sensor Network (WSN) based on One Dimensional Convolutional Neural Networks (1D CNNs) for real-time and wireless structural health monitoring (SHM). In this method, each CNN is assigned to its local sensor data only and a corresponding 1D CNN is trained for each sensor unit without any synchronization or data transmission. This results in a decentralized system for structural damage detection under ambient environment. The performance of this method is tested and validated on a steel grid laboratory structure.

[1]  D. Inman,et al.  Concept and model of eddy current damper for vibration suppression of a beam , 2005 .

[2]  Onur Avci,et al.  Design of Experiments Study to Obtain a Robust 3D Computational Bridge Model , 2012 .

[3]  Tim Verbelen,et al.  Fatigue life assessment of three offshore wind turbines , 2016 .

[4]  Onur Avci,et al.  Modal Parameter Variations due to Joist Bottom Chord Extension Installations on Laboratory Footbridges , 2015 .

[5]  Panos J. Antsaklis,et al.  Wireless Sensor Networks for Structural Health Monitoring: A Multi-Scale Approach , 2006 .

[6]  James Demmel,et al.  Wireless sensor networks for structural health monitoring , 2006, SenSys '06.

[7]  Onur Avci,et al.  Damage detection using enhanced multivariate statistical process control technique , 2016, 2016 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA).

[8]  Moncef Gabbouj,et al.  Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Industrial Electronics.

[9]  Onur Avci,et al.  Sensing and Monitoring for Stadium Structures: A Review of Recent Advances and a Forward Look , 2017, Front. Built Environ..

[10]  Daniel J. Inman,et al.  Vibration with Control: Inman/Vibration with Control , 2006 .

[11]  Daniel J. Inman,et al.  A survey of damping matrix identification , 1998 .

[12]  Onur Avci,et al.  Observations from Vibration Testing of In-Situ Structures , 2006 .

[13]  Onur Avci,et al.  Self-Organizing Maps for Structural Damage Detection: A Novel Unsupervised Vibration-Based Algorithm , 2016 .

[14]  D. Inman.  Vibration control , 2018, Advanced Applications in Acoustics, Noise and Vibration.

[15]  Onur Avci,et al.  Simplified vibration response prediction for slender monumental stairs , 2014 .

[16]  Daniel J. Inman,et al.  Development of a New Passive-Active Magnetic Damper for Vibration Suppression , 2006 .

[17]  Ann Nowé,et al.  Decentralized Learning in Wireless Sensor Networks , 2009, ALA.

[18]  Onur Avci,et al.  Active vibration control of flexible cantilever plates using piezoelectric materials and artificial neural networks , 2016 .

[19]  Moncef Gabbouj,et al.  Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks , 2017 .

[20]  Onur Avci,et al.  Novel Framework for Vibration Serviceability Assessment of Stadium Grandstands Considering Durations of Vibrations , 2018 .

[21]  Onur Avci,et al.  Vibrations Assessment of a Hospital Floor for a Magnetic Resonance Imaging Unit (MRI) Replacement , 2013 .

[22]  Vistasp M. Karbhari,et al.  Structural health monitoring of civil infrastructure systems , 2009 .

[23]  Eleni Chatzi,et al.  Vibration monitoring via spectro-temporal compressive sensing for wireless sensor networks , 2017, Life-Cycle of Structural Systems.

[24]  Onur Avci,et al.  Structural Damage Detection in Real Time: Implementation of 1D Convolutional Neural Networks for SHM Applications , 2017 .

[25]  Onur Avci,et al.  A Comparative Assessment of Nonlinear State Estimation Methods for Structural Health Monitoring , 2015 .

[26]  Onur Avci,et al.  Iterated square root unscented Kalman filter for nonlinear states and parameters estimation: three DOF damped system , 2015 .

[27]  Boualem Boashash,et al.  1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data , 2018, Neurocomputing.

[28]  Onur Avci,et al.  Dynamic Forces Induced by a Single Pedestrian: A Literature Review , 2017 .

[29]  Onur Avci,et al.  Optimization of chiral lattice based metastructures for broadband vibration suppression using genetic algorithms , 2016 .

[30]  Onur Avci,et al.  Simplified Vibration Serviceability Evaluation of Slender Monumental Stairs , 2015 .

[31]  Anne S. Kiremidjian,et al.  Modular, wireless network platform for monitoring structures , 1998 .

[32]  Onur Avci,et al.  Wireless and real-time structural damage detection: A novel decentralized method for wireless sensor networks , 2018, Journal of Sound and Vibration.

[33]  Onur Avci,et al.  Genetic Algorithm use for Internally Resonating Lattice Optimization: Case of a Beam-Like Metastructure , 2016 .

[34]  Onur Avci,et al.  Quantification of Structural Damage with Self-Organizing Maps , 2016 .

[35]  Onur Avci,et al.  Recent Issues on Stadium Monitoring and Serviceability: A Review , 2016 .

[36]  Daniel J. Inman,et al.  Dynamics of Asymmetric Nonconservative Systems , 1983 .

[37]  Jae-Sung Bae,et al.  Vibration suppression of a cantilever beam using eddy current damper , 2005 .

[38]  Onur Avci,et al.  Dynamic Testing of a Laboratory Stadium Structure , 2016 .

[39]  Onur Avci,et al.  A Study on Effective Mass of One Way Joist Supported Systems , 2015 .

[40]  Onur Avci,et al.  Vibration suppression in metastructures using zigzag inserts optimized by genetic algorithms , 2017 .

[41]  Onur Avci,et al.  Vibration Testing of Joist Supported Footbridges , 2010 .

[42]  Michael I. Friswell,et al.  Structural health monitoring using shaped sensors , 2009 .

[43]  Onur Avci,et al.  Nonlinear Damping in Floor Vibrations Serviceability: Verification on a Laboratory Structure , 2017 .

[44]  Jae-Sung Bae,et al.  Improved Concept and Model of Eddy Current Damper , 2006 .

[45]  Vasilis K. Dertimanis,et al.  Experimental validation of spectro-temporal compressive sensing for vibration monitoring using wireless sensor networks; The Fifth International Symposium on Life-Cycle Civil Engineering (IALCCE 2016); Life-Cycle of Engineering Systems: Emphasis on Sustainable Civil Infrastructure: Proceedings of th , 2016 .

[46]  Onur Avci,et al.  Amplitude-Dependent Damping in Vibration Serviceability: Case of a Laboratory Footbridge , 2016 .

[47]  Jerome P. Lynch,et al.  A wireless structural health monitoring system with multithreaded sensing devices: design and validation , 2007 .

[48]  Onur Avci,et al.  Vibrations Serviceability of a Medical Facility Floor for Sensitive Equipment Replacement: Evaluation with Sparse In Situ Data , 2019, Practice Periodical on Structural Design and Construction.

[49]  Onur Avci,et al.  Nonparametric structural damage detection algorithm for ambient vibration response: utilizing artificial neural networks and self-organizing maps , 2016 .