Predicting the Dynamic Behaviour of a Concrete Dam using Statistical and Machine Learning Models

• Author(s): Pereira, S ; Mata, J ; Magalhães, F ; Gomes, J ; Cunha, A.
• Date: 2024
• Persistent ID: https://hdl.handle.net/10216/166623
• Origin: Repositório Aberto da Universidade do Porto
• Document Type: Book
• Language: English

Description

Operational Modal Analysis is a reliable methodology for the assessment of civil engineering structures, allowing for the accurate definition of their dynamic behaviour. Additionally, since it does not require the use of artificial excitation, it becomes a cost-effective choice for the performance of singular tests, as well as a consistent option for the long-term continuous monitoring of structures. Nevertheless, the modal characteristics of structures are affected by environmental and operational conditions, concealing the variations that could emerge due to abnormal behaviour. With respect to concrete dams, factors such as temperature and the reservoir water level variations exert a pronounced influence in the evolution of natural frequencies. In this context, the current study seeks to examine the ability of statistical and machine learning tools in characterizing the effects of external conditions on the modal properties of concrete dams, specifically natural frequencies. To achieve this objective, the efficiency of methods incorporating measurements of variables impacting the structure, such as Multiple Linear Regressions and Neural Networks, is compared to that of a tool not needing these inputs, as is the case of the Minimum Mean Square Error estimator. Experimental data obtained during the continuous dynamic monitoring of a concrete dam under exploitation in Portugal is used as case study. (c) 2024 11th European Workshop on Structural Health Monitoring, EWSHM 2024. All rights reserved.