. Institute of Research and Development, Duy Tan University, Da Nang 550000, Vietnam . Faculty of Civil Engineering, Duy Tan University, Da Nang 550000, Vietnam . Bridge and Road Department, Danang Architecture University, Da Nang 550000, Vietnam . Faculty of Civil Engineering and Technology, Dong A University, Da Nang 550000, Vietnam . Industrial Maintenance Training Center, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City 700000, Vietnam
The conventional admittance approach utilizing statistical evaluation metrics offers limited information about the damage location, especially when damage introduces nonlinearities in admittance features. This study proposes a novel automated damage localization method for plate-like structures based on deep learning of raw admittance signals. A one-dimensional (1D) convolutional neural network (CNN)-based model is designed to automate processing of raw admittance response and prediction of damage probabilities across multiple locations in a monitored structure. Raw admittance data set is augmented with white noise to simulate realistic measurement conditions. Stratified K-fold cross-validation technique is employed for training and testing the network. The experimental validation of the proposed method shows that the proposed method can accurately identify the state and damage location in the plate with an average accuracy of 98%. Comparing with established 1D CNN models reveals superior performance of the proposed method, with significantly lower testing error. The proposed method exhibits the ability to directly handle raw electromechanical admittance responses and extract optimal features, overcoming limitations associated with traditional piezoelectric admittance approaches. By eliminating the need for signal preprocessing, this method holds promise for real-time damage monitoring of plate structures.
Fig.1 The illustration of the admittance technique for damage identification in a plate structure: (a) the typical EMA measurement system; (b) the simplified EMA coupling model.
Fig.2 The proposed CNN-based damage identification method for plate structures.
Fig.3 The proposed CNN architecture for deep learning of raw EMA data and damage identification in a plate structure.
Layer
Operator
Output shape
Kernel size a)
Stride
Layer
Operator
Output shape
Kernel size
Stride
1
Input
1 × 301
?
?
6
Convolution
32 × 151
32 × 1 × 32
1
2
Convolution
8 × 301
8 × 1 × 64
1
7
Batch normalization
32 × 151
?
?
3
Batch normalization
8 × 301
?
?
8
ReLU
32 × 151
?
?
4
ReLU
8 × 301
?
?
9
FC
1 × 60
?
?
5
Max-pooling
8 × 151
1 × 2
2
10
Output
1 × 60
?
?
Tab.1 The layer information of the proposed CNN model
Fig.4 The experimental setup: (a) the test plate specimen with added mass as a simulated damage; (b) the EMA analyzer; (c) the EMA transducer at the bottom surface; (d) the grid of damage locations over a quarter of the test plate specimen.
Fig.5 The measured EMA signals: (a) the intact case; (b) the Intact + 60 Damage cases; (c) the significant resonance band in 15–18 kHz.
Fig.6 The quantitative damage evaluation using traditional approaches: (a) RMSD contour; (b) CCD contour; (c) RMSD metric vs damage locations.
Fig.7 The added noises to the EMA signals for data augmentation: (a) 10–25 kHz; (b) 15.75–18.25 kHz.
Fig.8 The distribution of the testing samples in each fold for K-fold cross validation.
Fig.9 The training of the proposed 1D CNN: (a) training loss; (b) training RMSE.
Fig.11 The UCL thresholds for damage detection: (a) the distribution of prediction error; (b) the UCL thresholds.
Fig.12 Some typical prediction results by the proposed method.
Fig.13 Performance evaluation of the model: (a) the testing RMSE of 5 folds; (b) the testing MSE of 5 folds; (c) the testing MAE of 5 folds; (d) the testing accuracies of 5 folds.
Fig.14 Performance comparison between the proposed method and other 1D CNN models: (a) RMSE; (b) MSE; (c) MAE.
Fig.15 The training loss and evaluation results across 5 folds of Ai’s method: (a) the training loss; (b) the magnified loss; (c) the testing RMSE; (d) the testing MSE; (e) the testing MAE.
Fig.16 Some typical damage prediction results by Ai’s method: (a) Test 50 (D15); (b) Test 150 (D27); (c) Test 250 (D38).
Fig.17 The training loss and evaluation results across 5 folds of the Nguyen’s method: (a) the training loss; (b) magnified loss; (c) the testing RMSE; (d) the testing MSE; (e) the testing MAE.
Fig.18 Some typical damage prediction results by Nguyen’s method: (a) Test 50 (D15); (b) Test 150 (D27); (c) Test 250 (D38).
1
G ParkD J Inman. Impedance-based structural health monitoring. In: Proceedings of SPIE. Bellingham: SPIE, 2017
2
Z ChaudhryT JosephF SunC Rogers. Local-area health monitoring of aircraft via piezoelectric actuator/sensor patches. In: Proceedings of SPIE. Bellingham: SPIE, 1995
3
G Park, H H Cudney, D J Inman. Feasibility of using impedance-based damage assessment for pipeline structures. Earthquake Engineering & Structural Dynamics, 2001, 30(10): 1463–1474 https://doi.org/10.1002/eqe.72
4
Y W Yang, Y Y Lim, C K Soh. Practical issues related to the application of the electromechanical impedance technique in the structural health monitoring of civil structures: II. Numerical verification. Smart Materials and Structures, 2008, 17(3): 035009 https://doi.org/10.1088/0964-1726/17/3/035009
5
T C Le, T H T Luu, H P Nguyen, T H Nguyen, D D Ho, T C Huynh. Piezoelectric impedance-based structural health monitoring of wind turbine structures: Current status and future perspectives. Energies, 2022, 15(15): 5459 https://doi.org/10.3390/en15155459
6
T C Nguyen, T C Huynh, J H Yi, J T Kim. Hybrid bolt-loosening detection in wind turbine tower structures by vibration and impedance responses. Wind and Structures, 2017, 24(4): 385–403 https://doi.org/10.12989/was.2017.24.4.385
7
Y Yang, H Liu, V G M Annamdas, C K Soh. Monitoring damage propagation using PZT impedance transducers. Smart Materials and Structures, 2009, 18(4): 045003 https://doi.org/10.1088/0964-1726/18/4/045003
8
T T Nguyen, N D Hoang, T H Nguyen, T C Huynh. Analytical impedance model for piezoelectric-based smart Strand and its feasibility for prestress force prediction. Structural Control & Health Monitoring, 2022, 29(11): e3061
9
G Park, C R Farrar, A C Rutherford, A N Robertson. Piezoelectric active sensor self-diagnostics using electrical admittance measurements. Journal of Vibration and Acoustics, 2006, 128(4): 469–476 https://doi.org/10.1115/1.2202157
10
G Park, H Sohn, C R Farrar, D J Inman. Overview of piezoelectric impedance-based health monitoring and path forward. The Shock and Vibration Digest, 2003, 35(6): 451–463 https://doi.org/10.1177/05831024030356001
11
P Liu, H J Lim, S Yang, H Sohn, C H Lee, Y Yi, D Kim, J Jung, I Bae. Development of a “stick-and-detect” wireless sensor node for fatigue crack detection. Structural Health Monitoring, 2016, 16(2): 153–163 https://doi.org/10.1177/1475921716666532
T T Nguyen, Q B Ta, D D Ho, J T Kim, T C Huynh. A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning. Developments in the Built Environment, 2023, 14: 100122 https://doi.org/10.1016/j.dibe.2023.100122
14
E Madi, K Pope, W Huang, T Iqbal. A review of integrating ice detection and mitigation for wind turbine blades. Renewable & Sustainable Energy Reviews, 2019, 103: 269–281 https://doi.org/10.1016/j.rser.2018.12.019
15
R Perera, A Pérez, M García-Diéguez, J Zapico-Valle. Active wireless system for structural health monitoring applications. Sensors, 2017, 17(12): 2880 https://doi.org/10.3390/s17122880
16
Q Q Pham, Q B Ta, J H Park, J T Kim. Raspberry Pi platform wireless sensor node for low-frequency impedance responses of PZT interface. Sensors, 2022, 22(24): 9592 https://doi.org/10.3390/s22249592
17
J Min, S Park, C B Yun, B Song. Development of a low-cost multifunctional wireless impedance sensor node. Smart Structures and Systems, 2010, 6(5–6): 689–709 https://doi.org/10.12989/sss.2010.6.5_6.689
18
A N Zagrai, V Giurgiutiu. Electro-mechanical impedance method for crack detection in thin plates. Journal of Intelligent Material Systems and Structures, 2001, 12(10): 709–718 https://doi.org/10.1177/104538901320560355
19
V Giurgiutiu, A Zagrai, J Jing Bao. Piezoelectric wafer embedded active sensors for aging aircraft structural health monitoring. Structural Health Monitoring, 2002, 1(1): 41–61 https://doi.org/10.1177/147592170200100104
20
G Park, D J Inman. Structural health monitoring using piezoelectric impedance measurements. Philosophical Transactions—Royal Society. Mathematical, Physical, and Engineering Sciences, 2007, 365(1851): 373–392
21
H A Tinoco, L Robledo-Callejas, D J Marulanda, A L Serpa. Damage detection in plates using the electromechanical impedance technique based on decoupled measurements of piezoelectric transducers. Journal of Sound and Vibration, 2016, 384: 146–162 https://doi.org/10.1016/j.jsv.2016.08.011
22
R Tawie, H B Park, J Baek, W S Na. Damage detection performance of the electromechanical impedance (EMI) technique with various attachment methods on glass fibre composite plates. Sensors, 2019, 19(5): 1000 https://doi.org/10.3390/s19051000
23
B T Le, T T Nguyen, T D N Truong, C T Nguyen, T T V Phan, D D Ho, T C Huynh. Crack detection in bearing plate of prestressed anchorage using electromechanical impedance technique: A numerical investigation. Buildings, 2023, 13(4): 1008 https://doi.org/10.3390/buildings13041008
24
J Zhu, X Qing, X Liu, Y Wang. Electromechanical impedance-based damage localization with novel signatures extraction methodology and modified probability-weighted algorithm. Mechanical Systems and Signal Processing, 2021, 146: 107001 https://doi.org/10.1016/j.ymssp.2020.107001
25
J Min, S Park, C B Yun. Impedance-based structural health monitoring using neural networks for autonomous frequency range selection. Smart Materials and Structures, 2010, 19(12): 125011 https://doi.org/10.1088/0964-1726/19/12/125011
26
T C Huynh, J T Kim. Compensation of temperature effect on impedance responses of PZT interface for prestress-loss monitoring in PSC girders. Smart Structures and Systems, 2016, 17(6): 881–901 https://doi.org/10.12989/sss.2016.17.6.881
27
T C Huynh, N L Dang, J T Kim. Advances and challenges in impedance-based structural health monitoring. Structural Monitoring and Maintenance, 2017, 4(4): 301–329
28
V Jr Lopes, G Park, H H Cudney, D J Inman. Impedance-based structural health monitoring with artificial neural networks. Journal of Intelligent Material Systems and Structures, 2000, 11(3): 206–214 https://doi.org/10.1106/H0EV-7PWM-QYHW-E7VF
29
T C Huynh, J T Kim. RBFN-based temperature compensation method for impedance monitoring in prestressed tendon anchorage. Structural Control and Health Monitoring, 2018, 25(6): e2173 https://doi.org/10.1002/stc.2173
30
H. Guo. , X. Zhuang, and T. Rabczuk, A deep collocation method for the bending analysis of Kirchhoff plate. Computers Materials & Continua, 2019, 59(2): 433–456
31
E Samaniego, C Anitescu, S Goswami, V M Nguyen-Thanh, H Guo, K Hamdia, X Zhuang, T Rabczuk. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 2020, 362: 112790 https://doi.org/10.1016/j.cma.2019.112790
32
X Zhuang, H Guo, N Alajlan, H Zhu, T Rabczuk. Deep autoencoder based energy method for the bending, vibration, and buckling analysis of Kirchhoff plates with transfer learning. European Journal of Mechanics A—Solids, 2021, 87: 104225 https://doi.org/10.1016/j.euromechsol.2021.104225
33
K M Hamdia, H Ghasemi, Y Bazi, H AlHichri, N Alajlan, T Rabczuk. A novel deep learning based method for the computational material design of flexoelectric nanostructures with topology optimization. Finite Elements in Analysis and Design, 2019, 165: 21–30 https://doi.org/10.1016/j.finel.2019.07.001
34
H Guo, X Zhuang, P Chen, N Alajlan, T Rabczuk. Stochastic deep collocation method based on neural architecture search and transfer learning for heterogeneous porous media. Engineering with Computers, 2022, 38(6): 5173–5198 https://doi.org/10.1007/s00366-021-01586-2
35
O Abdeljaber, O Avci, M S Kiranyaz, B Boashash, H Sodano, D J Inman. 1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data. Neurocomputing, 2018, 275: 1308–1317 https://doi.org/10.1016/j.neucom.2017.09.069
36
Y J Cha, W Choi, O Büyüköztürk. Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5): 361–378 https://doi.org/10.1111/mice.12263
37
T C Huynh. Vision-based autonomous bolt-looseness detection method for splice connections: Design, lab-scale evaluation, and field application. Automation in Construction, 2021, 124: 103591 https://doi.org/10.1016/j.autcon.2021.103591
38
T T Nguyen, T Tuong Vy Phan, D D Ho, A Man Singh Pradhan, T C Huynh. Deep learning-based autonomous damage-sensitive feature extraction for impedance-based prestress monitoring. Engineering Structures, 2022, 259: 114172 https://doi.org/10.1016/j.engstruct.2022.114172
39
G Li, M Luo, J Huang, W Li. Early-age concrete strength monitoring using smart aggregate based on electromechanical impedance and machine learning. Mechanical Systems and Signal Processing, 2023, 186: 109865 https://doi.org/10.1016/j.ymssp.2022.109865
40
D Ai, F Mo, Y Han, J Wen. Automated identification of compressive stress and damage in concrete specimen using convolutional neural network learned electromechanical admittance. Engineering Structures, 2022, 259: 11476 https://doi.org/10.1016/j.engstruct.2022.114176
41
D Ai, J Cheng. A deep learning approach for electromechanical impedance based concrete structural damage quantification using two-dimensional convolutional neural network. Mechanical Systems and Signal Processing, 2023, 183: 109634 https://doi.org/10.1016/j.ymssp.2022.109634
42
X Zhang, H Wang, B Hou, J Xu, R Yan. 1D-CNN-based damage identification method based on piezoelectric impedance using adjustable inductive shunt circuitry for data enrichment. Structural Health Monitoring, 2022, 21: 1992–2009 https://doi.org/10.1177/14759217211049720
43
Q B Ta, Q Q Pham, N L Pham, T C Huynh, J T Kim. Smart aggregate-based concrete stress monitoring via 1D CNN deep learning of raw impedance signals. Structural Control and Health Monitoring, 2024, 2024: 5822653
44
M de Oliveira, A Monteiro, J Vieira Filho. A new structural health monitoring strategy based on PZT sensors and convolutional neural network. Sensors, 2018, 18(9): 2955 https://doi.org/10.3390/s18092955
45
S Bhalla, C Kiong Soh. Structural impedance based damage diagnosis by piezo-transducers. Earthquake Engineering & Structural Dynamics, 2003, 32(12): 1897–1916 https://doi.org/10.1002/eqe.307
46
C Liang, F P Sun, C A Rogers. Coupled electro-mechanical analysis of adaptive material systems-determination of the actuator power consumption and system energy transfer. Journal of Intelligent Material Systems and Structures, 1994, 5(1): 12–20 https://doi.org/10.1177/1045389X9400500102
47
S Park, J H Yi, C B Yun, Y R Roh. Impedance-based damage detection for civil infrastructures. KSCE Journal of Civil Engineering, 2004, 8(4): 425–433 https://doi.org/10.1007/BF02829166
48
J T Kim, J H Park, D S Hong, W S Park. Hybrid health monitoring of prestressed concrete girder bridges by sequential vibration-impedance approaches. Engineering Structures, 2010, 32(1): 115–128 https://doi.org/10.1016/j.engstruct.2009.08.021
49
J Min, S Park, C B Yun, C G Lee, C Lee. Impedance-based structural health monitoring incorporating neural network technique for identification of damage type and severity. Engineering Structures, 2012, 39: 210–220 https://doi.org/10.1016/j.engstruct.2012.01.012
50
D Kang, S S Benipal, D L Gopal, Y J Cha. Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning. Automation in Construction, 2020, 118: 103291 https://doi.org/10.1016/j.autcon.2020.103291
51
U R Acharya, H Fujita, S L Oh, Y Hagiwara, J H Tan, M Adam. Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Information Sciences, 2017, 415: 190–198 https://doi.org/10.1016/j.ins.2017.06.027
52
D Singh, B Singh. Investigating the impact of data normalization on classification performance. Applied Soft Computing, 2020, 97: 105524 https://doi.org/10.1016/j.asoc.2019.105524
53
F Mattioli, C Porcaro, G Baldassarre. A 1D CNN for high accuracy classification and transfer learning in motor imagery EEG-based brain-computer interface. Journal of Neural Engineering, 2021, 18(6): 066053 https://doi.org/10.1088/1741-2552/ac4430
54
A F Agarap. Deep learning using rectified linear units (ReLu). 2018, arXiv:1803.08375
55
H GholamalinezhadH Khosravi. Pooling methods in deep neural networks: A review. 2020, arXiv:2009.07485
56
T C Huynh, J T Kim. Quantification of temperature effect on impedance monitoring via PZT interface for prestressed tendon anchorage. Smart Materials and Structures, 2017, 26(12): 125004 https://doi.org/10.1088/1361-665X/aa931b
57
S L Ma, S F Jiang, J Li. Structural damage detection considering sensor performance degradation and measurement noise effect. Measurement, 2019, 131: 431–442 https://doi.org/10.1016/j.measurement.2018.08.040
58
T C Huynh, T D Nguyen, D D Ho, N L Dang, J T Kim. Sensor fault diagnosis for impedance monitoring using a piezoelectric-based smart interface technique. Sensors, 2020, 20(2): 510 https://doi.org/10.3390/s20020510
59
C W Helstrom. The resolution of signals in white, Gaussian noise. In: Proceedings of the IRE, New York: IEEE, 1955, 1111–1118
60
L M Campeiro, R Z M da Silveira, F G Baptista. Impedance-based damage detection under noise and vibration effects. Structural Health Monitoring, 2017, 17(3): 654–667
61
B de Castro, F Baptista, F Ciampa. New imaging algorithm for material damage localisation based on impedance measurements under noise influence. Measurement, 2020, 163: 107953 https://doi.org/10.1016/j.measurement.2020.107953
K D Nguyen, J T Kim. Smart PZT-interface for wireless impedance-based prestress-loss monitoring in tendon-anchorage connection. Smart Structures and Systems, 2012, 9(6): 489–504 https://doi.org/10.12989/sss.2012.9.6.489
64
T C Huynh, K S Lee, J T Kim. Local dynamic characteristics of PZT impedance interface on tendon anchorage under prestress force variation. Smart Structures and Systems, 2015, 15(2): 375–393 https://doi.org/10.12989/sss.2015.15.2.375
65
I Behmanesh, B Moaveni. Probabilistic identification of simulated damage on the Dowling Hall footbridge through Bayesian finite element model updating. Structural Control and Health Monitoring, 2015, 22(3): 463–483 https://doi.org/10.1002/stc.1684
66
P Rajendran, S M Srinivasan. Identification of added mass in the composite plate structure based on wavelet packet transform. Strain, 2016, 52(1): 14–25 https://doi.org/10.1111/str.12154
67
D Ai, F Mo, J Cheng, L Du. Deep learning of electromechanical impedance for concrete structural damage identification using 1-D convolutional neural networks. Construction & Building Materials, 2023, 385: 131423 https://doi.org/10.1016/j.conbuildmat.2023.131423
