Abstract

Predictive models are essential in dam safety assessment. Both deterministic and statistical models applied in the day-to-day practice have demonstrated to be useful, although they show relevant limitations at the same time. On another note, powerful learning algorithms have been developed in the field of machine learning (ML), which have been applied to solve practical problems. The work aims at testing the prediction capability of some state-of-the-art algorithms to model dam behaviour, in terms of displacements and leakage. Models based on random forests (RF), boosted regression trees (BRT), neural networks (NN), support vector machines (SVM) and multivariate adaptive regression splines (MARS) are fitted to predict 14 target variables. Prediction accuracy is compared with the conventional statistical model, which shows poorer performance on average. BRT models stand out as the most accurate overall, followed by NN and RF. It was also verified that the model fit can be improved by removing the records of the first years of dam functioning from the training set.

Abstract

The high-level objective of MARS project was to understand the formation and behaviour of turbulent structures which affects the Reynolds stress and skin friction. The aim was, once understood, to apply flow control techniques in order to control these structures and reduce the overall drag derived from the Reynolds stress and mainly from the skin friction. Active flow control devices were the main interest; DBD plasma, Synthetic jets, Micro Blowing and Suction, Moving Surfaces were included on the list. To test all these devices, two test cases were defined, and a database and file repository were established in the project webserver. The present chapter is aimed to describe the test cases, including the set-up of the flow control devices, as well as to describe the file repository were all the data was stored.