Damage localization in civil infrastructure, such as large-scale reinforced concrete (RC) pedestrian bridges, is essential for conducting precise maintenance and avoiding catastrophic failures. In this study, multiple one-dimensional convolutional neural networks (1-D CNNs) are developed for automatically extracting implicit damage-sensitive features from the structural raw dynamic responses to localize damage in the pile foundations of pedestrian bridges considering uncertainties such as environmental and operational variations (EOVs) inherent in dynamic responses. For this purpose, transient dynamics numerical computation models are established to simulate the multi-point dynamic response of the structure under different typical damage scenarios, forming the baseline dataset. Then, on-site vibration tests are conducted on the structural prototype. Ambient vibrations of the real intact bridge are considered EOVs and integrated into the baseline dataset, forming the test dataset. Additionally, the intact structural dynamic response with measured EOVs replaces the simulated intact structural dynamic response in the baseline dataset to form a reference dataset. The network architectures based on one-dimensional convolutional layers proposed in this paper are trained on the baseline dataset and reference datasets to obtain baseline and reference models. Subsequently, model performance evaluation is conducted on the test dataset, and the results indicate a significant decrease in the performance of damage models based on a single deep learning when EOVs are present. However, integrating the baseline and reference models achieves zero false negative/positive predictions which is safety-oriented and an exemplary classification accuracy of up to 97.2 %.

@en

This study presents a damage pattern recognition approach for corroded steel beams strengthened by CFRP anchorage system based on acoustic emission clustering analysis. The proposed method includes four steps: acoustic emission signal acquisition, feature extraction, clustering analysis, and damage pattern recognition. Four corroded beams with different corrosion levels and strengthening schemes were tested under four-point bending loading. The acoustic emission signals were collected during the loading process and analyzed using Gaussian mixture model clustering method. The results showed that the collected AE data were analyzed using clustering analysis, successfully distinguishing the distinct damage patterns associated with each mode. The AE signals exhibited distinct characteristics for different damage modes: concrete matrix damage had high-frequency and low-energy characteristics, CFRP-matrix debonding showed intermediate values for all parameters, and CFRP tearing had longer durations, lower peak frequencies, and high-energy characteristics. Besides, the study identified three stages of the damage process: an initial stage with fewer low-intensity AE signals, a damage development stage characterized by an increase in concrete-matrix damage and CFRP – matrix debonding signals, and a continuous damage growth stage with significant AE signals associated with three damage modes. Furthermore, the degree of corrosion significantly influenced the cumulative AE energy of damage modes. Lower degrees of corrosion led to higher cumulative energy from concrete matrix damage and CFRP-matrix debonding. These findings provide valuable insights for understanding the damage evolution and failure mechanisms of CFRP-strengthened corroded beams. The use of AE techniques for damage pattern recognition can enhance the evaluation and design of CFRP anchorage systems, leading to more effective rehabilitation strategies for corroded structures.

@en

Externally bonded (EB) carbon fiber reinforced polymer (CFRP) is widely used in structural strengthening and retrofitting. Premature debonding of the FRP severely limits the efficiency of CFRP utilization. The application of CRRP anchorage system offers a solution to the debonding problem. However, the understanding of damage mode identification of this combined system still remains elusive. Acoustic emission (AE) technique is employed to identify the damage mode of this CFRP anchorage system, due to its high sensitivity and the ability to detect damage in real-time. The objective of the current study is to identify the failure mechanisms of CFRP-strengthened beam by applying advanced pattern recognition techniques to the collected AE data. Firstly, four-point test of CFRP-strengthened beam was carried out until failure with simultaneous recording of AE signals. Then, correlation analysis was adopted to select the AE characteristic parameters, and principal component analysis (PCA) was used for dimensionality reduction. Lastly, the AE signals of the CFRP-strengthened beam was clustered to track the evolutionary behavior of the different damage modes by Gaussian mixture model (GMM) algorithm. Three main damage modes of CFRP-strengthened beam were identified by GMM clustering: concrete cracking, debonding of CFRP sheet and fracture of CFRP sheet. This study explores the damage evolution mechanism of combined system and provides a basis for achieving health monitoring of CFRP-strengthened structures.@en

This study investigated the relationship between the acoustic emission (AE) signals parameter sequence fractal characteristics and the damage evolution information of corroded reinforced concrete (RC) beams under four-point bending. Strength deterioration behavior and AE data can be obtained by coupling the four-point bending test and the AE monitoring. The results show that AE ringing counts of corroded and uncorroded beams had prominent fractal characteristics. The fractal dimension values of corroded RC beams all showed a fluctuating rise to a peak and then a sharp drop before the failure. The damage index corresponding to the peak point decreases with the increase of corrosion degree. Fractal dimension peak point could be used as an early warning point for corroded RC beams' failure. Moreover, the AE fractal dimension analysis can effectively reflect the pattern of crack development, which have an important value for evaluating the process of corroded RC beams rupture.

@en

Vibration-based structural damage detection (SDD) has been a subject of intense research in structural health monitoring (SHM) for large civil engineering structures over the decades. The performance of the conventional SDD approaches predominantly relies on the rational choices of the damage feature and classifier. Hand-crafted features or fixed classifiers would not be the optimal choice for all structural damaged scenarios. This paper proposes a novel, quick and precise real-time SDD framework for high-pile wharf foundations using a combination of finite element modeling and 1D convolutional neural networks (CNNs). The distinct advantage of this method lies in extracting the damage-related features from the raw displacement response directly and automatically, and the computational complexity of the compact 1D CNNs is significantly lower because the data processing involves only simple 1D operations. The results show that the presented 1D CNNs have a superior ability to accurately identify the occurrence and location of damage in real time. In addition, the comprehensive performance of the CNNs trained by the displacement response dataset in component form is significantly better than that based on the dataset in absolute value form. The results also demonstrated that although the proposed CNNs are more sensitive to the longitudinal and lateral displacement responses of the high-pile wharf structure, the vertical component still has a positive effect on the improvement of the generalization and robustness of the CNNs.@en

This paper presents the results of an experimental study on the flexural behavior of carbon fibre reinforced polymer (CFRP) anchorage system strengthened reinforced concrete (RC) beams under the coupled effects of corrosion damage and sustained loading. The test beams were subjected to combined accelerated corrosion in 5% NaCl solution and sustained loads for 25, 50 and 100 days at 0% and 50% load levels of the virgin beam ultimate load capacity. The failure modes, load carrying capacity, deflection, ductility and strain response of the beams were investigated in detail. The results indicated that CFRP anchorage systems enhanced the yield and ultimate load of the corrosion-damaged beams. The use of CFRP anchorage system restored the ultimate load of corroded beams between 87.6% and 104.8% and the yield load between 81.9% and 92.7% with respect to those of the virgin beam. In contrast, the ductility and energy absorption index suffered a decline. CFRP-strengthened beams showed a reduction of 4.5%–28.9% for the ductility index compared with their counterparts without CFRP anchorage system. Sustained loads resulted in more considerable reductions in load-bearing capacity, greater loss of rebars mass, wider width of corrosion cracks, indicating a significant coupling effect between sustained loading and corrosion damage. Three typical failure modes of the CFRP-strengthened beams were observed and explained in the paper, thus revealing the failure mechanism of CFRP-strengthened beams. In the engineering practice of CFRP anchorage system, the coupled effects of corrosion damage and sustained loading on the strengthened systems should be taken into accountant comprehensively.

@en