Integrating PZT-enabled active sensing with deep learning techniques for automatic monitoring and assessment of early-age concrete strength

Compressive strength of concrete is one of the key indicators to evaluate the quality of concrete materials. Real-time monitoring of the compressive strength development during the concrete curing process can effectively guide the staged construction and ensure the safety and stability of engineering structures. In this paper, a novel method is proposed to monitor and evaluate the early-age concrete strength development by integrating PZT-enabled active sensing and deep learning (DL) techniques. First of all, the stress wave signals were continuously captured during the concrete curing process using PZT-enabled active sensing, and then the time-frequency diagrams were generated from the collected signals through the continuous wavelet transform (CWT). After that, an innovative DL-based framework named concrete early-age strength monitoring network (CESMonitorNet) was developed to automatically learn optimal features from the CWT spectrum and ultimately quantify the early-age concrete strength. Finally, experiments on laboratory-cast concrete specimens were conducted to verify the effectiveness of the proposed method. A comprehensive comparison analysis with the widely used machine learning-based methods and convolutional neural network (CNN) was also performed. The results show that the proposed method can accurately predict the concrete strength development and has superior performances over other methods, indicating its great potential for real-time monitoring and rapid evaluation of the strength development of early-age concrete.