http://repositorio.lnec.pt:8080/jspui/handle/123456789/38 2026-04-04T21:00:38Z 2026-04-04T21:00:38Z Debus, P. Valença, J. http://repositorio.lnec.pt:8080/jspui/handle/123456789/1019001 2025-11-27T12:21:10Z 2025-06-01T00:00:00Z

Computer Vision System for Dimension Control in the Prefabrication of Concrete Panels Debus, P.; Valença, J. This paper presents a computer vision system for dimensional quality control of concrete panel formwork. The methodology combines corner detection with photogrammetric principles to analyse overhead images of formwork assemblies, comparing detected geometries with design specifications. Validation on synthetic images demonstrates high accuracy, with mean absolute errors below 1.12 mm for dimensional and 0.02° for orientation measurements. While application to real-world factory conditions revealed challenges in corner detection requiring future improvements, the established framework provides a foundation for automated quality control in concrete prefabrication, enabling early detection of assembly errors before concrete placement.

2025-06-01T00:00:00Z Debus, P. Valença, J. http://repositorio.lnec.pt:8080/jspui/handle/123456789/1018999 2025-11-27T12:21:05Z 2025-04-01T00:00:00Z

Evaluation of Surface Quality in the Prefabrication of Concrete Panels using Computer Vision Debus, P.; Valença, J. The construction industry increasingly uses prefabrication for the significant advantages in cost-effectiveness, production speed, and environmental sustainability. Achieving high-quality building outcomes demands rigorous quality control of the individual building components. Concrete panel manufacturing presents unique challenges, particularly in surface quality assessment, as the material’s heterogeneity complicates standard evaluation metrics from industries like automotive manufacturing, where computer vision methods are well established. This research addresses these challenges with a robust computer vision-based methodology for surface quality assessment for prefabricated concrete panels, focusing on the detection of visible color differences using the ΔE metric. By recognizing the complex material properties and design requirements — including aesthetic aspects like color and texture — the proposed approach establishes more precise and adaptable evaluation techniques to enhance the overall quality and reliability of prefabricated concrete construction.

2025-04-01T00:00:00Z Valença, J. Oliveira Santos, B. http://repositorio.lnec.pt:8080/jspui/handle/123456789/1018996 2025-11-27T12:20:37Z 2025-11-01T00:00:00Z

Relevant channel selection in hyperspectral imaging to enhance crack segmentation in historic concrete buildings Valença, J.; Oliveira Santos, B. Recent years have been fruitful in the development of computer vision methods for a wide variety of applications. Despite the successful results achieved in the segmentation of cracks on concrete surfaces, poor results are still persisting during onsite application, mainly due to noise caused by biological colonization, which is present in most of historical heritage buildings. The authors have been working on this problematic and developed the SC-Crack method previously, however it still relies on the cumbersome task of acquiring sets of 17 channels images to compose an hyperspectral cube and still requires case-wise hyperparameter optimization. Consequently, it is important to define which spectral information mostly defines the success of the method, enabling to optimize both, the acquisition procedure and model processing. Following, a study aiming at the selection of the more informative channels was carried and the hyperparameter-free model is evaluated. In this scope, images of concrete specimens were acquired sequentially to compose a 17 channel hyperspectral image cube. These were sere compute allowing to define the most informative channels sets that are processed using the SC-Crack+ method, presented in this work. The reduced image cubes of cracking on clean concrete surfaces and on surfaces with biological colonization were processed and analyzed. Relevant and improved results were achieved for crack segmentation, following this SC-Crack+ model. This enables the possibility of mounting cameras with sensors and lenses particularly adapted for prone acquisition targeting only the most relevant hyperspectral information for crack segmentation and still using traditional feature engineering image processing methods.

2025-11-01T00:00:00Z Oliveira, P. Xu, Min Meixedo, A. Calçada, R. http://repositorio.lnec.pt:8080/jspui/handle/123456789/1018758 2025-07-21T13:30:01Z 2025-07-03T00:00:00Z

Damage identification in railway bridges using a novel nonlinear time series analysis methodology with sensor clustering Oliveira, P.; Xu, Min; Meixedo, A.; Calçada, R. Vibration-based methods for damage detection have been widely used, particularly those relying on ambient excitations. These methods are based on the principle that changes in a structure's physical properties, such as mass, stiffness, and damping, will lead to changes in its vibration charac-teristics. A promising area of research focuses on utilizing operational loads, such as vehicular traffic, instead of ambient excitations. Dynamic responses gener-ated by operational loads, such as trains, induce higher levels of vibration compared to those caused by temperature variations or ambient vibrations. The consistent and repeatable nature of this load can also reduce the time required for training predictive models. Furthermore, as vehicles cross the bridge from end to end, structural damage, even if localized, will generate anomalies in the dynamic responses, which may be detectable by sensors in-stalled in the structure. With a higher signal-to-noise ratio, this approach en-ables more efficient and cost-effective monitoring systems. This paper presents a data-driven approach for identifying damage in railway bridges based on train-induced dynamic responses. In this methodology, non-linear autoregressive models with exogenous inputs (NARX) are developed for different sensor clusters, using the structure's free response after train ex-citations. The damage index is defined based on the prediction errors of each NARX. The effectiveness of the proposed methodology is validated using real accel-eration data from a long-span steel-concrete composite bowstring arch rail-way bridge. Changes in the longitudinal stiffness of the bearing devices were identified through acceleration data recorded during the passage of Alfa Pen-dular trains.

2025-07-03T00:00:00Z