A Novel CNN-LSTM Hybrid Model for Prediction of Electro-Mechanical Impedance Signal Based Bond Strength Monitoring

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.

A proof of concept study on reliability assessment of different metal foil length based piezoelectric sensor for electromechanical impedance techniques

“…In impedance based SHM for damage quantification, many statistical indices are being used i.e., root-mean-square deviation (RMSD), mean absolute percentage deviation (MAPD), and correlation coefficient deviation metric (CCDM). The CCDM 5 is commonly used to evaluate changes in signal measurement due to any structural anomaly or any electrical fluctuation. The CCDM index for the piezo-coupled signatures can be expressed by Eq.…”

“…The change in the impedance signature can be used to identify and locate damage, even at the very incipient level 4 . The method of EMI has been successfully demonstrated on diverse types of engineered constructions, including bridges, buildings, aircraft, and pipelines 5 – 7 . The non-destructive and non-invasive nature of the technique makes it particularly attractive for monitoring large and complex structures.…”

Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection

“…This reflects the effectiveness of LSTM and CNN as individual models [ 27 , 28 ]. Moreover, combined with a hybrid model, CNN-LSTM enhances feature extraction and improves disease classification performance in time-series data [ 29 ]. Further, applying wavelet transformation on VOC data in the CNN-LSTM model is expected to enhance the model's accuracy in disease classification [ 23 ].…”

Corrosion inhibitors for enhanced strength, durability, and microstructure of coastal concrete structures

“…The construction industry, which includes the development of high-rise buildings, bridges, and highways, has been a major contributor to the economic growth of the country, owing to rapid urbanization. Concrete, being a reliable and durable material, is extensively used across the globe [1][2][3][4]. Despite its ability to withstand numerous deterioration processes, external factors can impact its overall health.…”