A Novel CNN-LSTM Hybrid Model for Prediction of Electro-Mechanical Impedance Signal Based Bond Strength Monitoring
Open accessThe DOI matches its Crossref record; 97 of the 98 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
The recent application of deep learning for structural health monitoring systems for damage detection has potential for improvised structure performance and maintenance for long term durability, and reliable strength. Advancements in electro-mechanical impedance (EMI) techniques have sparked attention among researchers to develop novel monitoring techniques for structural monitoring and evaluation. This study aims to determine the performance of EMI techniques using a piezo sensor to monitor the development of bond strength in reinforced concrete through a pull-out test. The concrete cylindrical samples with embedded steel bars were prepared, cured for 28 days, and a pull-out test was performed to measure the interfacial bond between them. The piezo coupled signatures were obtained for the PZT patch bonded to the steel bar. The damage qualification is performed through the statistical indices, i.e., root-mean-square deviation (RMSD) and correlation coefficient deviation metric (CCDM), were obtained for different displacements recorded for axial pull. Furthermore, this study utilizes a novel Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM)-based hybrid model, an effective regression model to predict the EMI signatures. These results emphasize the efficiency and potential application of the deep learning-based hybrid model in predicting EMI-based structural signatures. The findings of this study have several implications for structural health diagnosis using a deep learning-based model for monitoring and conservation of building heritage.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures


















Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“The problem of data temporal and spatial feature extraction can be solved using a combination of the CNN and RNN methods, such as CNN with GRU [64,109,123], CNN with LSTM [27,178,179,180,181,182], CNN with Auto-encoder and [183], CNN with echo state networks [113], etc.”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [27]
The cited source says what the claim attributes to it.
In the citing paper
“Generally, the training set’s ratio to the test set is 8:2 [27,36,182,198] or 7:3 [15,58,187].”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [27]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
Yu, Y., Si, X., Hu, C., & Zhang, J. (2019) · Neural Computation · doi:10.1162/neco_a_01199 · Cited by 5,591 · cited 1×
“The hybrid model used in this study is a combination of long short-term memory (LSTM) [81] and CNN [82], found to be suitable for the prediction of sequence data.”
MethodUnderstanding of a convolutional neural network
Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017) · 2017 International Conference on Engineering and Technology (ICET) · doi:10.1109/icengtechnol.2017.8308186 · Cited by 3,986 · cited 1×
“The hybrid model used in this study is a combination of long short-term memory (LSTM) [81] and CNN [82], found to be suitable for the prediction of sequence data.”
MethodDeep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks
Cha, Y., Choi, W., & Büyüköztürk, O. (2017) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12263 · Cited by 3,295 · cited 1×
“These methods can accurately recognize, locate, and visualize cracks and corrosion [66,67].”
MethodReview on Convolutional Neural Networks (CNN) in vegetation remote sensing
Kattenborn, T., Leitloff, J., Schiefer, F., & Hinz, S. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.12.010 · Cited by 1,805 · cited 1×
“It has been employed in numerous fields such as remote sensing [55], image recognition [56], damage detection [57], vibration-based structural state [58], civil infrastructure [59], bolt looseness [60], disease [61], and rock classifications [62].”
MethodCha, Y., Choi, W., Suh, G., Mahmoudkhani, S., & Büyüköztürk, O. (2018) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12334 · Cited by 1,558
Overview of Piezoelectric Impedance-Based Health Monitoring and Path Forward
Park, G., Sohn, H., Farrar, C. R., & Inman, D. J. (2003) · The Shock and Vibration Digest · doi:10.1177/05831024030356001 · Cited by 1,060 · cited 1×
“45 m for reinforced concrete structures [87].”
Convolutional Neural Network (CNN) for Image Detection and Recognition
Chauhan, R., Ghanshala, K. K., & Joshi, R. C. (2018) · 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC) · doi:10.1109/icsccc.2018.8703316 · Cited by 661 · cited 1×
“It has been employed in numerous fields such as remote sensing [55], image recognition [56], damage detection [57], vibration-based structural state [58], civil infrastructure [59], bolt looseness [60], disease [61], and rock classifications [62].”
MethodMishra, M., Lourenço, P. B., & Ramana, G. V. (2022) · Journal of Building Engineering · doi:10.1016/j.jobe.2021.103954 · Cited by 479
A comparison of deep networks with ReLU activation function and linear spline-type methods
Eckle, K., & Schmidt-Hieber, J. (2019) · Neural Networks · doi:10.1016/j.neunet.2018.11.005 · Cited by 409
Crack and Noncrack Classification from Concrete Surface Images Using Machine Learning
Kim, H., Ahn, E., Shin, M., & Sim, S.-H. (2019) · Structural Health Monitoring · doi:10.1177/1475921718768747 · Cited by 315 · cited 1×
“In the field of civil engineering, mostly ML approaches are still scarce and only limited to image classification and digital image correlation [42].”
Background
Research works printed but not linked: 3
- Banerjee T. Parida L. Moharana S. Monitoring and Diagnosis of Thermal Expansion of Rails and Rail Joints Using Piezoelectric Sensor for Electro-Mechanical Impedance Technique Proceedings of the NDE 2019 Conference & Exhibition Bengaluru, India 5–7 December 2019 NDE-India 2019 Volume 3 2012
- Moharana S. Bhalla S. Numerical investigations of shear lag effect on PZT-structure interaction: Review and application Curr. Sci. 2012 103 685 696
- Arun Sundaram B. Ravisankar K. Senthil R. Parivallal S. Wireless sensors for structural health monitoring and damage detection techniques Curr. Sci. 2013 104 1496 1505
Cited by
Jia, J., & Li, Y. (2023) · Sensors · doi:10.3390/s23218824 · Cited by 182
“…and spatial feature extraction can be solved using a combination of the CNN and RNN methods, such as CNN with GRU [64,109,123], CNN with LSTM [27,178–182], CNN with Auto-encoder and [183], CNN with echo state networks [113], etc. Yang et al. [123] proposed a hierarchical CNN and GRU…”
BackgroundMethodKumar, R., Althaqafi, E., Patro, S. G. K., Šimić, V., Babbar, A., Pamucar, D. S., Singh, S. K., & Verma, A. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111956 · Cited by 71
A comprehensive review on piezo impedance based multi sensing technique
Parida, L., & Moharana, S. (2023) · Results in Engineering · doi:10.1016/j.rineng.2023.101093 · Cited by 56
Self-citationJena, T., Raj, A. K., Saravanan, T. J., & Bansal, T. (2024) · Measurement · doi:10.1016/j.measurement.2024.115698 · Cited by 40
Maginga, T. J., Masabo, E., Bakunzibake, P., Kim, K. S., & Nsenga, J. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e26647 · Cited by 31
“Moreover, combined with a hybrid model, CNN-LSTM enhances feature extraction and improves disease classification performance in time-series data [29].”
MethodRamesh, G., Talakokula, V., Jyosyula, S. K. R., & Bansal, T. (2024) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2024.137725 · Cited by 25
Parida, L., & Moharana, S. (2023) · Measurement · doi:10.1016/j.measurement.2023.113592 · Cited by 24
Self-citationParida, L., Moharana, S., Vicente, R., & Ascensão, G. (2024) · Scientific Reports · doi:10.1038/s41598-023-49762-2 · Cited by 21
Self-citationParida, L., & Moharana, S. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2024.111897 · Cited by 21
Self-citationA Review of Hybrid LSTM Models in Smart Cities
Kim, B.-J., & Nam, I. W. (2025) · Processes · doi:10.3390/pr13072298 · Cited by 20
Li, X., Chiabrando, F., & Sammartano, G. (2026) · Remote Sensing · doi:10.3390/rs18040628 · Cited by 20
Parida, L., Moharana, S., & Giri, S. K. (2023) · Materials Today Proceedings · doi:10.1016/j.matpr.2023.03.741 · Cited by 15
Self-citationSubash, S., Parida, L., Singh, U., & Moharana, S. (2023) · Materials Research Express · doi:10.1088/2053-1591/ace75c · Cited by 14
Self-citationIndoor Positioning Method by CNN-LSTM of Continuous Received Signal Strength Indicator
Yoon, J.-H., Kim, H., Lee, D.-S., & Kwon, S.-K. (2024) · Electronics · doi:10.3390/electronics13224518 · Cited by 13
Jena, T., Saravanan, T. J., & Bansal, T. (2025) · Measurement · doi:10.1016/j.measurement.2025.118346 · Cited by 14
Ai, D., & Yang, K. (2025) · Engineering Structures · doi:10.1016/j.engstruct.2025.120787 · Cited by 12
A Real-Time Remaining Fatigue Life Prediction Approach Based on a Hybrid Deep Learning Network
Zhu, Y., Zhang, J., Luo, J., Guo, X., Liu, Z., & Zhang, R. (2023) · Processes · doi:10.3390/pr11113220 · Cited by 11
“For example, Lukesh et al. [16] established a CNN–LSTM model to predict electromechanical impedance signals, and they emphasized the efficiency of their CNN–LSTM model for the problem of time-series prediction regression.”
MethodKamal, M., Parida, L., & Banerjee, S. (2025) · Smart Materials and Structures · doi:10.1088/1361-665x/adb6e3 · Cited by 10
Self-citationAgha, W. A., Pal, S., & Dev, N. (2025) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2025.142296 · Cited by 12
Parida, L., & Moharana, S. (2024) · Smart Materials and Structures · doi:10.1088/1361-665x/ad754f · Cited by 8
“SHM offers substantial advantages in addressing these challenges [10–12].”
Self-citationEarly detection of thermal instability in railway tracks using piezo-coupled structural signatures
Banerjee, T., Moharana, S., & Parida, L. (2023) · Journal of Infrastructure Intelligence and Resilience · doi:10.1016/j.iintel.2023.100063 · Cited by 7
Self-citationParida, L., Banerjee, S., & Moharana, S. (2025) · Structural Concrete · doi:10.1002/suco.70208 · Cited by 6
“Parida et al. 138 investigated using EMI-based active sensing approach for monitoring the pullout behavior of steel – concrete cylindrical specimens.”
Self-citationParida, L., & Moharana, S. (2025) · Journal of Structural Integrity and Maintenance · doi:10.1080/24705314.2025.2485011 · Cited by 5
“EMI techniques provide a unique approach to detect and locate defects and damages in structures at an early stage, which can prevent catastrophic failures and reduce maintenance costs (Parida & Moharana, 2022; Parida et al., 2022, 2023; Tamhane, Banerjee, et al., 2022).”
Self-citationLiao, X., Yan, Q., Qiao, M., Xiong, Z., Li, B., & Zhang, C. (2025) · NDT & E International · doi:10.1016/j.ndteint.2025.103518 · Cited by 5
Raji, R. K., Mahmoud, S. T., Najar, A., Awwad, F. R., & Qamhieh, N. N. (2026) · Chemical Engineering Journal Advances · doi:10.1016/j.ceja.2026.101106 · Cited by 5
Colace, F., Gupta, B. B., Lorusso, A., Troiano, A., Santaniello, D., & Valentino, C. (2023) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-6684-9999-3.ch013 · Cited by 7
Parida, L., Moharana, S., & Sahani, R. (2024) · Engineering Research Express · doi:10.1088/2631-8695/ad885b · Cited by 5
Self-citationMoon, J.-H., Lim, S.-K., Kim, J.-H., Kang, G., & Kim, B.-H. (2024) · Applied Sciences · doi:10.3390/app14177833 · Cited by 4
Nguyen, N. C., & Vu, T. M. (2025) · Engineering Computations · doi:10.1108/ec-08-2024-0714 · Cited by 8
Ping, Y., Yang, X., Yang, Y., Shen, Y., Zeng, S., Dai, S., & Hong, J. (2025) · Machines · doi:10.3390/machines13070556 · Cited by 3
Ohenhen, P. E., Nwaobia, N. K., Nwasike, C. N., Gidiagba, J. O., & Ani, E. C. (2024) · Acta Electronica Malaysia · doi:10.26480/aem.01.2024.11.20 · Cited by 3
Parida, L., & Moharana, S. (2025) · Journal of Failure Analysis and Prevention · doi:10.1007/s11668-025-02214-7 · Cited by 2
“Wang et al. [36] considered a multi-layer perception ANN model using multiple parameters for bond strength assessment.”
Self-citationHolsamudrkar, N., Parida, L., Kamal, M., Joshi, M., & Banerjee, S. (2026) · Structural Health Monitoring · doi:10.1177/14759217261453518 · Cited by 2
Self-citationPatel, A., Parida, L., & Moharana, S. (2024) · Lecture notes in civil engineering · doi:10.1007/978-3-031-62253-3_18 · Cited by 2
Self-citationA-DCLN: Attention Based Deep CNN-LSTM Network for the Classification of Lung Cancer
Giri, S. K., Dash, S., Sahoo, T., & Angami, T. (2025) · Learning and analytics in intelligent systems · doi:10.1007/978-3-031-82706-8_8 · Cited by 2
Self-citationKamal, M., Parida, L., & Banerjee, S. (2025) · SPIE Health Monitoring of Structural and Biological Systems · doi:10.1117/12.3051112 · Cited by 1
“8,9 Liang et al. 10 proposed an EMI analysis methodology for one-dimensional model.”
Self-citationZhang, D., Gu, D., Zhang, Q., Xiao, P., Zhang, Z., & Sun, Q. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2574341 · Cited by 1
“Parida et al. investigated an electro-mechanical impedance (EMI) signal prediction method based on a CNN-LSTM hybrid model for monitoring the bond strength of reinforced concrete [31].”
Parida, L., Moharana, S., & Mishra, A. (2026) · Measurement · doi:10.1016/j.measurement.2026.121021 · Cited by 1
Self-citationNhut, N. M., Quan, D. M., Khanh, L. M. D., & Thuân, N. Đ. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8296-7_29 · Cited by 1
Parida, L., & Moharana, S. (2024) · Lecture notes in civil engineering · doi:10.1007/978-3-031-62253-3_16 · Cited by 1
Self-citationRangwala, H., Vora, T. P., & Baz, A. (2025) · Case Studies in Construction Materials · doi:10.1016/j.cscm.2025.e05430 · Cited by 1
AN OPTIMIZED STRATEGY FOR ESTIMATING THE RATE OF HYDRATION OF CONCRETE USING PZT SENSORS
Parida, L., & Moharana, S. (2023) · ECCOMAS Thematic Conference on Smart Structures and Materials (SMART) · doi:10.7712/150123.9962.454900
Self-citationParida, L., Moharana, S., & Giri, S. K. (2023) · Report · doi:10.2749/newdelhi.2023.0567
Self-citationMaurya, A., Parida, L., & Moharana, S. (2024) · Lecture notes in civil engineering · doi:10.1007/978-3-031-62253-3_17
Self-citationParida, L., & Moharana, S. (2024) · Lecture notes in mechanical engineering · doi:10.1007/978-981-97-1036-2_12
Self-citationParida, L., Moharana, S., & Giri, S. K. (2024) · Lecture notes in mechanical engineering · doi:10.1007/978-981-97-6367-2_11 · Cited by 1
Self-citationSahoo, T., Giri, S. K., Dash, S., & Longkumer, A. (2025) · Learning and analytics in intelligent systems · doi:10.1007/978-3-031-82706-8_13
Self-citationZhao, X., Gao, Z., Li, M., Han, Z., & Zhu, J. (2025) · IEEE Access · doi:10.1109/access.2025.3551508
“…development is the convolutional neural networks Long Short-Term Memory (CNN-LSTM) hybrid model, which combines the spatial feature extraction of CNNs with the temporal sequence learning of LSTMs to predict EMI signals and monitor bond strength in composite structures [23], [24], [25], [26], [27].”
Non-destructive Detection of Bond Slip Failure in Fiber-Reinforced Concrete Using Piezo Sensors
Ramesh, G., Mangalampalli, A. K., Talakokula, V., Jyosyula, S. K. R., Battula, M., & Chellam, S. (2026) · Lecture notes in civil engineering · doi:10.1007/978-981-96-9712-0_20
Agha, W. A., Pal, S., & Dev, N. (2026) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-025-02311-9 · Cited by 1
Elghrabawy, O. (2026) · Earth Science Informatics · doi:10.1007/s12145-026-02098-7
Nithyadevi, S., Farithkhan, A. A., Susila Sakthy, S., & Srimathi, S. (2026) · Mechanics of Advanced Materials and Structures · doi:10.1080/15376494.2026.2665288
Rezzoug, A. (2026) · REVIEWS ON ADVANCED MATERIALS SCIENCE · doi:10.1515/rams-2025-0249
“The utilization of hybrid AI models, including ANFIS-GA and CNN – LSTM, has gained signi fi cant attention due to their ability to capture complex nonlinear relationships and enhance predictive performance in engineering applications [23].”
Machine learning review of composite structural member performance assessment
Iyappan, G. R., Sangeetha, P., & Elango, D. (2026) · Proceedings of the Institution of Civil Engineers - Forensic Engineering · doi:10.1680/jfoen.25.00045
Nguyen, T.-T., Truong, G. T., & Huynh, T. (2026) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-026-01111-3
Ekmekci, D., & Kaplan, E. (2026) · Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering · doi:10.1177/09544089261479940
Pradeepkumar, G., & Kavitha, S. (2026) · Mechanics of Advanced Materials and Structures · doi:10.1080/15376494.2026.2719642
Modeling and Forecasting Piezoelectric Energy Harvesting Using Deep LSTM–ANN Architectures
Oktarina, Y., Dewi, T., Yahya, M. A., Faraquinnsha, A. M., & Juraijin, D. (2026) · EMITTER International Journal of Engineering Technology · doi:10.24003/emitter.v14i1.1002
Sibaroni, Y., Prasetiyowati, S. S., & Puspandari, D. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.4080
M, M. N. I. A., Saravanan, V., Lavanya, N., Soman, S., & Sherin, F. (2026) · Advanced Healthcare Materials · doi:10.1002/adhm.71786
Metadata
- Authors
- Parida, L., Moharana, S., Ferreira, V. M., Giri, S. K., & Ascensão, G.
- Affiliations
- Shiv Nadar University (IN)
- Riscos e Sustentabilidade na Construção (PT)
- Department of CSE, Srinix College of Engineering, Gopalgoan 756003, India
- Corresponding author
- Moharana, Sumedha
- Ascensão, Guilherme
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2022-12-16
- Volume
- 22
- Issue
- 24
- Pages
- 9920
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC9781742
- OpenAlex
- W4312194846
- Cited by
- 58
- References
- 96
- Citations by year
- 2026: 15 · 2025: 17 · 2024: 15 · 2023: 11
- FWCI
- 4.74
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Foundation for Science and Technology (FCT) (FCT/UIDB/ECI/04450/2020)
- Topics
- Physical Sciences › Engineering › Mechanics of Materials › Ultrasonics and Acoustic Wave Propagation
- Physical Sciences › Engineering › Civil and Structural Engineering › Structural Health Monitoring Techniques
- Physical Sciences › Engineering › Civil and Structural Engineering › Structural Engineering and Materials Analysis
- Keywords
- electromechanical impedance, reinforced concrete, pull-out test, piezoelectric sensors, PZT patches, CNN-LSTM hybrid model, structural health monitoring, damage detection, interfacial bonding
- MeSH terms
- Records, Steel, Neural Networks, Computer, Electric Impedance, Memory, Long-Term
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.