Damage identification using the PZT impedance signals and residual learning algorithm

Damage identification techniques are of essential importance to promote the efficiency, reliability and safety of any structural system. In recent years, many artificial intelligence (AI)-based approaches have been successfully applied to establish damage identification tools using sample structural responses. However, it is generally difficult to fully train a deep neural network, therefore, researchers usually use shallow neural networks, which is limited in terms of performance. Addressing these issues, this paper proposes a novel structural damage identification method based on the raw time-series structural response signals and a deep residual network (DRN). A deep residual network is designed for extracting features of the raw time-domain impedance responses signals that measured from steel beam under different damage conditions. In order to optimize the network’s performance, a residual learning algorithm and the Bayesian optimization algorithm are proposed and implemented. The results show that different structural conditions have been identified accurately. Also, the proposed methodology is suitable for processing structural responses signal with variable sequential length. Reasonable knowledge is required in damage detection and signal processing, which increases the applicability of the established method. Thus, the introduced method offers significant improvement for structural health monitoring (SHM) in terms of different damage sizes and location detection. To the best of our knowledge, this is the first work adopting DRN simultaneously on SHM non-image datasets of electro-mechanical impedance (EMI) signals.

[1]  Xiang Li,et al.  Deep residual learning-based fault diagnosis method for rotating machinery. , 2019, ISA transactions.

[2]  Shamim N. Pakzad,et al.  Localized Structural Damage Detection: A Change Point Analysis , 2014, Comput. Aided Civ. Infrastructure Eng..

[3]  H. Adeli,et al.  Synchrosqueezed wavelet transform-fractality model for locating, detecting, and quantifying damage in smart highrise building structures , 2015 .

[4]  Farqad K. J. Jawad,et al.  Wise-local response convolutional neural network based on Naïve Bayes theorem for rotating machinery fault classification , 2021, Applied Intelligence.

[5]  Huan Zhou,et al.  A Computationally Efficient Algorithm for Real‐Time Tracking the Abrupt Stiffness Degradations of Structural Elements , 2016, Comput. Aided Civ. Infrastructure Eng..

[6]  Hong-ping Zhu,et al.  Experimental investigation of damage identification in beam structures based on the strain statistical moment , 2017 .

[7]  Khalid M. Mosalam,et al.  Deep Transfer Learning for Image‐Based Structural Damage Recognition , 2018, Comput. Aided Civ. Infrastructure Eng..

[8]  Ka-Veng Yuen,et al.  Real‐Time System Identification: An Algorithm for Simultaneous Model Class Selection and Parametric Identification , 2015, Comput. Aided Civ. Infrastructure Eng..

[9]  Wei Zhang,et al.  Unified Vision‐Based Methodology for Simultaneous Concrete Defect Detection and Geolocalization , 2018, Comput. Aided Civ. Infrastructure Eng..

[10]  Hongping Zhu,et al.  Damage Identification in a Plate Structure Based on Strain Statistical Moment , 2014 .

[11]  Patrick M. Pilarski,et al.  First steps towards an intelligent laser welding architecture using deep neural networks and reinforcement learning , 2014 .

[12]  Dimitrios Giagopoulos,et al.  Structural Health Monitoring using deep learning with optimal finite element model generated data , 2020 .

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

[14]  Oral Büyüköztürk,et al.  Structural Damage Detection Using Modal Strain Energy and Hybrid Multiobjective Optimization , 2015, Comput. Aided Civ. Infrastructure Eng..

[15]  Ying Wang,et al.  SHMnet: Condition assessment of bolted connection with beyond human-level performance , 2020, Structural Health Monitoring.

[16]  Jun Shang Kuang,et al.  Equivalent frame analysis for effective wall width of nonplanar beam–wall connections , 2017 .

[17]  V. Sheng,et al.  An abnormal network flow feature sequence prediction approach for DDoS attacks detection in big data environment , 2018 .

[18]  Daniel J. Inman,et al.  An Integrated Health Monitoring Technique Using Structural Impedance Sensors , 2000 .

[19]  Yang Liu,et al.  Statistical Regularization for Identification of Structural Parameters and External Loadings Using State Space Models , 2015, Comput. Aided Civ. Infrastructure Eng..

[20]  Osama Al-Azzawi,et al.  Deep convolution neural network for damage identifications based on time-domain PZT impedance technique , 2021, Journal of Mechanical Science and Technology.

[21]  J. Zhang,et al.  Mobile Impact Testing for Structural Flexibility Identification with only a Single Reference , 2015, Comput. Aided Civ. Infrastructure Eng..

[22]  L. H. Yam,et al.  FEM modeling method of damage structures for structural damage detection , 2006 .

[23]  J. Grover.  An Introduction to Bayes’ Theorem and Bayesian Belief Networks (BBN) , 2013 .

[24]  Min Xia,et al.  Fault Diagnosis for Rotating Machinery Using Multiple Sensors and Convolutional Neural Networks , 2018, IEEE/ASME Transactions on Mechatronics.

[25]  Myeongsu Kang,et al.  Deep Residual Networks With Dynamically Weighted Wavelet Coefficients for Fault Diagnosis of Planetary Gearboxes , 2018, IEEE Transactions on Industrial Electronics.

[26]  Qinkai Han,et al.  Deep residual learning with demodulated time-frequency features for fault diagnosis of planetary gearbox under nonstationary running conditions , 2019, Mechanical Systems and Signal Processing.

[27]  Limao Zhang,et al.  Computational methodologies for optimal sensor placement in structural health monitoring: A review , 2020, Structural Health Monitoring.

[28]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Norris Stubbs,et al.  A new method to extract modal parameters using output-only responses , 2005 .

[30]  Carlos Cabrera,et al.  Analysis of the sources of uncertainty for portfolio‐level earthquake loss estimation , 2012 .

[31]  Oreste S. Bursi,et al.  Capabilities of a Fiber Bragg Grating Sensor System to Monitor the Inelastic Response of Concrete Sections in New Tunnel Linings Subjected to Earthquake Loading , 2015, Comput. Aided Civ. Infrastructure Eng..

[32]  Hui Li,et al.  Sparse Bayesian learning approach for propagation distance recognition and damage localization in plate-like structures using guided waves , 2020 .

[33]  Min Yang,et al.  Real-Time Tunnel Crack Analysis System via Deep Learning , 2019, IEEE Access.

[34]  Armen Der Kiureghian,et al.  A stochastic ground motion model with separable temporal and spectral nonstationarities , 2008 .

[35]  Wang-Ji Yan,et al.  Operational Modal Parameter Identification from Power Spectrum Density Transmissibility , 2012, Comput. Aided Civ. Infrastructure Eng..

[36]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[37]  K. Law,et al.  Time series-based damage detection and localization algorithm with application to the ASCE benchmark structure , 2006 .

[38]  Billie F. Spencer,et al.  Sensor Attitude Correction of Wireless Sensor Network for Acceleration-Based Monitoring of Civil Structures , 2015, Comput. Aided Civ. Infrastructure Eng..

[39]  Sami F. Masri,et al.  Studies into Computational Intelligence and Evolutionary Approaches for Model‐Free Identification of Hysteretic Systems , 2015, Comput. Aided Civ. Infrastructure Eng..

[40]  Hongping Zhu,et al.  Damage identification in beam type structures based on statistical moment using a two step method , 2014 .

[41]  Hojjat Adeli,et al.  A novel machine learning‐based algorithm to detect damage in high‐rise building structures , 2017 .

[42]  José Viterbo Filho,et al.  A New Impedance Measurement System for PZT-Based Structural Health Monitoring , 2009, IEEE Transactions on Instrumentation and Measurement.