Luis Alberto Bedriñana

Accurate crack width measurement is essential for the condition assessment of reinforced concrete (RC) bridges, yet most unmanned aerial vehicle (UAV) inspections remain limited to pixel-level observations that cannot be converted into reliable metric units without an external scale reference. This paper presents a lightweight, drone-agnostic UAV-mounted metrology system that enables standards-aligned metric crack width measurement directly from inspection imagery. The payload integrates a focusable diffractive optical element (DOE) red laser that projects a cross pattern of known angular geometry, three TF-Luna time-of-flight (ToF) distance sensors, and an ESP-WROOM-32 microcontroller that provides dual-rate sampling, Bluetooth Low Energy (BLE) streaming, and on-board logging. A two-stage calibration links the synchronized distance measurements to the physical length of the projected cross, yielding an image-specific pixel-to-millimeter scale that is applied to pixel-level crack widths obtained from a vision-based segmentation pipeline. The system is field-deployed on the Puente Huamani Bridge in Pisco, Peru, where measurements of 39 cracks classified under AASHTO MBEI condition states are compared against independent manual measurements by six inspectors. The proposed system reduces measurement variability across all condition states (CS), lowering the average coefficient of variation from 0.36 to 0.10 for fine CS1 cracks, from 0.27 to 0.11 for CS2, and from 0.22 to 0.07 for CS3. Cross-platform adaptability is demonstrated through an additional deployment on a DJI Matrice 350 RTK at the Low Level Bridge in Edmonton, Canada. The results indicate that the system provides a practical, low-cost, and scalable solution for repeatable, standards-aligned UAV-based bridge crack assessment.

In different countries with seismic active zones such as Peru, Japan and the USA, seismic isolation have been used in buildings to improve their seismic resilience. Nonetheless, several devices have been operating for over ten years, possibly showing signs of deterioration. Due to their critical role in the seismic response, an efficient inspection system is important to ensure proper isolation conditions. In this context, international standards about the inspection of Lead Rubber Bearings (LRB) have been proposed, as well as more sophisticated noninvasive methods. After reviewing proposed methods, three limitations were identified: a) the lack of a detailed inspection protocol can cause biased and uncertain assessments, b) there is not clear deterioration levels of seismic isolators with parameter thresholds, and c) non-invasive methods are laborious, time consuming and costly for implementation in operational isolators. This study integrates ambient vibration signals with Neural Networks to propose an agile, accurate and cost-effective seismic isolator inspection system. The system is trained and developed with real data from existing LRBs. To this end, 14 LRB isolators from a case study, with nearly 11 years in operation, were inspected using traditional methods. Additionally, a four-level deterioration matrix was proposed. Then, ambient vibration signals were locally recorded using microtremors and relevant features were extracted for each isolator. Consequently, a Fully Connected Deep Neural Network (FCDNN) was trained with signal windows and other relevant variables. After training and hyperparameter tuning, the proposed FCDNN achieved an Accuracy and a ?1????? of 0.93 and 0.94 on the test set, respectively. Using the trained FCDNN and SHAP-based explanation, the following conclusions were drawn: a) the geometric and mechanical parameters of the LRB isolators define the susceptibility and ease of a device to maintain or change from a mild to severe level of deterioration; and b) the signal features define vibration patterns in the temporal and spectral domain in specific levels of deterioration. Finally, a web GUI is developed to predict the level of deterioration of a device after measuring ambient vibrations. The proposed system has the potential to revolutionize the frequent inspection and monitoring of isolation devices.

Reinforced Concrete (RC) bridges are prone to deterioration throughout their service life, which can compromise their structural integrity. Among the visible indicators of deterioration, cracks are particularly significant, underscoring the need for their early detection. Traditional inspections, primarily based on visual inspection, face challenges such as restricted access to certain bridge areas, complex logistics, and excessive operational costs and time. To address these challenges, the engineering community is working toward implementing more efficient technologies for bridge inspection. This paper proposes an automatic deep learning-based system for the segmentation and quantification of surface cracks in RC bridges using images captured by unmanned aerial vehicles (UAVs). The proposed framework combines patch-based and pixel-level segmentation using binary image classification and crack segmentation models. Additionally, an alternative method based on a laser module with a diffractive optical element (DOE) was implemented to obtain an automatic scale factor, enabling the conversion of pixel-level information into metric measurements for damage quantification. Experimental results show that the binary classification model achieved an F1-score of 0.93 on the test set, while the segmentation model achieved an F1-score of 0.83. Overall system performance yielded a coefficient of determination (R²) of 0.70 and an average inference time of 2.32 seconds per high-resolution image. Through integrating UAVs, lasers, and deep learning, the proposed approach offers an alternative for bridge inspections, reducing cost and time while supporting the rapid generation of preliminary reports.

This research discusses the viability of the next-generation novel materials, e.g., titanium alloy bars (TiABs) and ultra-high-performance concrete (UHPC) that have potential to be utilized in civil infrastructures, e.g., bridges, in combination with machine learning (ML) techniques. Since UHPC and TiABs have been demonstrated to be a realistic alternative to traditional construction materials for civil infrastructures, it is important to characterize bond performance of reinforcing, i.e., TiABs embedded in UHPC. The research utilizes improvement of ML techniques, e.g., transfer learning (TL) to predict the bond strength of TiABs in UHPC.

The shear behavior of prestressed concrete (PC) beams is a complex problem because there are many influential parameters involved. Currently, the code-based shear strength of PC beams is primarily based on empirical equations, which tend to be overconservative and are unable to generalize to different cases (e.g., beams with or without stirrups). This paper presents a framework to develop an explainable, data-driven model for the shear design of PC beams over a wide range of parameters. To this end, a comprehensive data set was assembled, consisting of 670 experiments of PC beams with and without stirrups. Different machine-learning (ML) techniques, including Random Forest, AdaBoost, and XGBoost, were evaluated to define a predictive model for the data set. Then, the most accurate model (based on XGBoost) was optimized to achieve high accuracy (with a coefficient of determination of 0.98 for the testing set). Moreover, the Shapley Additive exPlanations technique was used to explain and evaluate the importance of different parameters on the output of the predictive model. The predictive model was shown to be largely more accurate and more generalizable than current design equations and advanced finite-element analysis. In addition, reliability-based shear strength reduction factors were derived for the proposed ML model. These reduction factors allowed the application of the proposed ML model in the code-compliant shear design of PC beams.

This paper presents an analytical procedure to assess the monotonic (envelope) force-deformation response (capacity curve) of unbonded post-tensioning precast concrete (UPT) walls with internal and external replaceable dampers. This procedure, which can also be used to design UPT walls, was compared and validated against experimental evidence. A close agreement (strength discrepancies of 2% on average) was found between the response predictions and experimental results. This agreement was maintained until peak strength was achieved. Moreover, fiber-based models were implemented to further study the cyclic behavior of UPT walls designed according to the proposed analytical procedure. The numerical models were accurate in representing the global cyclic behavior of UPT walls in terms of strength, displacement capacity, and energy dissipation; nonetheless, these models showed some discrepancies in capturing the residual drifts of some UPT walls with internal dampers. A parametric analysis was also conducted to explore the influence of some design parameters on the deformation capacity and energy dissipation of UPT walls. It was found that the ratio of damper reinforcement is critical for the energy dissipation and self-centering capacity of UPT walls, so ratios of 0.10 to 0.25 should be provided to follow the limit states indicated in this paper. Based on the results, the analytical procedure and limit states presented in this paper are considered suitable for UPT walls with external replaceable dampers under total axial load ratios equal or lower than 0.125.

This paper presents the results of an experimental investigation on the performance of half-scale, unbonded, post-tensioning, precast concrete walls subjected to fully reversed cyclic loads. Moreover, this paper discusses the damage progression and failure mechanism of each specimen, associated with their construction details (damper types and confinement details of the boundary elements). Five isolated walls were tested, each consisting of precast concrete panels joined only by unbonded post-tensioning strands. The bottom joint of the walls featured two kinds of dampers: Three specimens had mild steel reinforcement, crossing the bottom joint, and the other two specimens had external replaceable hysteretic dampers, attached to the wall sides. Different types of confinement details at the boundary elements were used among the specimens. Steel fibers were mixed into the concrete of one specimen. The prestressing load ratio was 0.05 in most of the specimens. An additional axial load of 468.5 kN was applied to each specimen (additional axial load ratio of about 0.04), before any lateral loading. Quasi-static, displacement-controlled loads were applied to the specimens until a significant strength reduction was observed. Although only moderate axial loads were applied, most of the specimens sustained drifts above 3% while maintaining their lateral strength, gravity load stability, and self-centering. A better performance was observed in the specimens with external dampers, with drifts above 4%, less residual drifts and less cover concrete spalling, particularly in the specimen with steel fibers. The external dampers were very effective in dissipating energy before fracture, until 3% drifts. On the other hand, the specimens with internal dampers sustained unexpected damage at their bottom joint, after reaching their peak strength. For instance, the gravity load-carrying capacity of one specimen with internal dampers was compromised after 4% drifts. Then, the use of external replaceable dampers provided higher performance and post-earthquake recovery for unbonded post-tensioned precast walls. Additional design recommendations are provided based on the test results.