Machine learning algorithms in civil structural health monitoring

This comparison surveys various research papers on the applications of machine learning algorithms in Structural Health Monitoring (SHM). The studies reviewed employ algorithms such as Back Propagation (BP), Support Vector Machines (SVM), Neural Networks (NNs), K-Nearest Neighbors (KNN), and Convolutional Neural Networks (CNNs) for diverse SHM tasks. The research highlights the effectiveness of these algorithms in detecting and diagnosing structural damage, understanding uplift pressure, estimating damage potentials, and assessing leakage flow. Collectively, these studies demonstrate the capabilities of machine learning approaches in detecting damaged joints, locating damage, evaluating long-term structural health, and identifying mass and stiffness degradation, providing a comprehensive overview of their applications and benefits in SHM.