Dam safety monitoring is of vital importance, due to the high number of fatalities and large economic damage that a failure might imply. This, along with the evolution of artificial intelligence, has led to machine learning techniques being increasingly applied in this field. Many researchers have successfully trained models to predict dam behavior, but errors vary depending on the method used, meaning that the optimal model is not always the same over time. The main goal of this paper is to improve model precision by combining different models. Our research focuses on the comparison of two successful integration strategies in other areas: Stacking and Blending. The methodology was applied to the prediction of radial movements of an arch-gravity dam and was divided into two parts. First, we compared the usual method of estimating model errors and their hyperparameters, i.e., Random Cross Validation and Blocked Cross Validation. This aspect is relevant not only for the importance of robust estimates, but also because it is the source of the data sets used to train meta-learners. The second and main research topic of this paper was the comparison of combination strategies, for which two different types of tests were performed. The results obtained suggest that Blocked CV outperforms the random approach in robustness and that Stacking provides better predictions than Blending. The generalized linear meta-learners trained by the Stacking strategy achieved higher accuracy than the individual models in most cases.
Dam safety monitoring is critical due to its social, environmental, and economic implications. Although conventional statistical approaches have been used for surveillance, advancements in technology, particularly in Artificial Intelligence (AI) and Machine Learning (ML), offer promising avenues for enhancing predictive capabilities. We investigate the application of ML algorithms, including Boosted Regression Trees (BRT), Random Forest (RF), and Neural Networks (NN), focussing on their combination by Stacking to improve prediction accuracy on concrete dam deformation using radial displacement data from three dams. The methodology involves training first-level models (experts) using those algorithms, and a second-level meta-learner that combines their predictions using BRT, a Linear Model (LM) and the Greedy Weighted Algorithm (GWA). A comparative analysis demonstrates the superiority of Stacking over traditional methods. The GWA emerged as the most suitable meta-learner, enhancing the optimal expert in all cases, with improvement rates reaching up to 16.12% over the optimal expert. Our study addresses critical questions regarding the GWA’s expert weighting and its impact on prediction precision. The results indicate that the combination of accurate experts using the GWA improves model reliability by reducing error dispersion. However, variations in optimal weights over time necessitate robust error estimation using cross-validation by blocks. Furthermore, the assignment of weights to experts closely correlates with their precision: the more accurate a model is, the more weight that is assigned to it. The GWA improves on the optimal expert in most cases, including at extreme values of error, with improvement rates up to 41.74%. Our findings suggest that the proposed methodology significantly advances AI applications in infrastructure monitoring, with implications for dam safety.
Dams are complex systems that involve both the structure itself and its foundation. Rheological phenomena, expansive reactions, or alterations in the geotechnical parameters of the foundation, among others, result in non-reversible and cumulative modifications in the dam response, leading to trends in the monitoring data series. The accurate identification and definition of these trends to study their evolution are key aspects of dam safety. This manuscript proposes a methodology to identify trends in dam behavioural data series by identifying the influence of the time variable on the predictions provided by the ML models. Initially, ICE curves and SHAP values are employed to extract temporal dependence, and the ICE curves are found to be more precise and efficient in terms of computational cost. The temporal dependencies found are adjusted using a GWO algorithm to different function characteristics of irreversible processes in dams. The function that provides the best fit is selected as the most plausible. The results obtained allow us to conclude that the proposed methodology is capable of obtaining estimates of the most common trends that affect movements in concrete dams with greater precision than the statistical models most commonly used to predict the behaviour of these types of variables. These results are promising for its general application to other types of dam monitoring data series, given the versatility demonstrated for the unsupervised identification of temporal dependencies.
Para superar las limitaciones de la metodología tradicional en la enseñanza de AutoCAD, la Unidad Docente de Expresión Gráfica de la Universidad Politécnica de Madrid está llevando a cabo un Proyecto de Innovación Educativa para implementar una metodología de Aula Invertida (AI) con el apoyo de vídeos educativos. En este trabajo se presentan los resultados de una primera aplicación práctica de la metodología de AI llevada a cabo durante el curso 2016/2017 sobre el tema “La impresión en AutoCAD”. La aplicación de la metodología ha incluido el empleo de un grupo de control y la realización de una prueba objetiva sobre el uso de AutoCAD, la cual ha supuesto un reto organizativo para la Unidad Docente. Los resultados del estudio muestran un mejor rendimiento de los alumnos que han empleado AI. Sin embargo, esta mejora no parece deberse directamente al AI como técnica de enseñanza sino a su aspecto motivador que incide de manera general en el rendimiento de los alumnos. [In order to overcome the limitations of traditional teaching methodologies in AutoCAD classes, the Graphic Expression Teaching Unit of the Technical University of Madrid is carrying out an Innovative Teaching Project to implement a Flipped Classroom (FC) methodology with the support of educational videos. This paper presents the results of a first application of the FC methodology carried out during the academic year 2016/2017 on the topic of “Printing in AutoCAD”. The application of the methodology involved a control group and an exam on the use of AutoCAD, all of which has been an organizational challenge for the Teaching Unit. The results of the study show an improved performance by the students who used FC. However, this improvement does not seem to be due directly to FC as a teaching technique, but rather to its motivating character, which has a general impact on student performance.] Arcos, Antonio; Arcos, José Luis; Fernández-Centeno, Miguel Ángel; González-Galindo, Jesús; Gordo, Carlos; Manget, Cristina; Salazar, Fernando; Senent, Salvador
En este trabajo se presentan dos escape rooms educativos para el aprendizaje de geometría, dentro de una asignatura de Expresión Gráfica en la Ingeniería Civil. Se describen los dos escape room elaborados así como la aplicación práctica de uno de ellos durante el curso 22/23. El primero de ellos cubre contenidos de geometría plana (polígonos, circunferencias y transformaciones) y tiene como hilo conductor las películas de La Guerra de las Galaxias. El segundo trata de resolver el robo de un manuscrito de J.V. Poncelet, incorporando aspectos propios de la Ingeniería Civil. Ambos escape rooms se han implementado en la plataforma Escapp, la cual permite, entre otras funcionalidades, facilitar el progreso en la historia y la obtención de pistas. La aplicación práctica de la metodología mostró, a pesar del reducido efecto en la calificación final frente a la metodología tradicional, el enorme interés de los alumnos en este tipo de actividades. Alonso, Jesús; Arcos, Antonio; Fernández-Centeno, Miguel Ángel; García-Parga, Gabriela; Moreno, Ángela; Senent, Salvador; Zariohi, Abdelali