A5066144866- Structural Health Monitoring Techniques
- Infrastructure Maintenance and Monitoring
- Concrete Corrosion and Durability
- Fatigue and fracture mechanics
- Ultrasonics and Acoustic Wave Propagation
- Non-Destructive Testing Techniques
- Electric Power Systems and Control
- Structural Integrity and Reliability Analysis
- Fuzzy Logic and Control Systems
- Water Systems and Optimization
- Probabilistic and Robust Engineering Design
- Electric Motor Design and Analysis
- Magnetic Bearings and Levitation Dynamics
- Statistical Methods and Applications
Universidade Estadual Paulista (Unesp)
2021-2024
Classifiers based on machine learning algorithms trained through hybrid strategies have been proposed for structural health monitoring (SHM) of bridges. Hybrid use numerical and data together to improve the process algorithms. The models, such as finite-element (FE) are used augmentation assumption existence limited experimental sets. However, a model might fail in providing reliable data, its parameters not share same underlying operating conditions observed real situations. Meanwhile,...
Machine learning methods used in Structural Health Monitoring applications still have generalization difficulties among structures, even when structures are nominally and topologically similar. The data sets present divergences between their probability distributions that do not allow the model’s for damage detection. This issue is more complex situations where one wants to quantify levels through collected from different structures. Transfer offer a solution overcome those limitations,...
Bridges are built to last more than 100 years, spanning many human generations. Throughout their lifetime, service requirements may change, or they age and often suffer a material degradation process that can lead the need of retrofitting. In bridge engineering, retrofitting refers strengthening existing structures make them resistant increase lifespan bridges. Retrofitting normally increases stiffness components, which cause significant changes in global modal properties. context structural...
Bridges are crucial transportation infrastructures with significant socioeconomic impacts, necessitating continuous assessment to ensure safe operation. However, the vast number of bridges and technical financial challenges maintaining permanent monitoring systems in every single bridge make implementation structural health (SHM) difficult for authorities. Unsupervised transfer learning, which reuses experimental or numerical data from well-known detect damage on other limited response data,...
Abstract This paper investigates how to improve the performance of a classifier tightening torque in bolted joints by applying transfer learning. The procedure uses vibration measurements extract features and train using Gaussian mixture model (GMM). key enhancing surrogate for loss detection is considering joint structures with more qualitative quantitative knowledge as source domain, where labels are known trained. After domain adaptation method, it possible reuse this trained target i.e.,...