A5052158680- Neural Networks and Applications
- Structural Health Monitoring Techniques
- Vibration and Dynamic Analysis
- Adversarial Robustness in Machine Learning
- Engineering Applied Research
- Building Energy and Comfort Optimization
- Anomaly Detection Techniques and Applications
Korea Institute of Energy Research
2021
University at Buffalo, State University of New York
2002
New York University
2002
Continuous fatigue information is essential for the structural health monitoring (SHM) of wind turbines. Faults, such as sensor failure, data loss, and cable disconnection, can result in a total loss SHM. To avoid malfunction, machine learning algorithms polynomial curve fitting are suggested to predict missing from otherwise known measurement data. Artificial neural networks showed best prediction performance. Decision trees regularized linear regression also powerful alternatives.
Presents the results of utilizing neural networks to provide an efficient computational model for a dynamical system. Neural are used parameter identification multistorey buildings. The were trained and tested using experimental data measured on building models. measurements consist acceleration time-histories taken at base buildings various floor levels. It is demonstrated that, once initial learning phase completed, network can instantaneous system parameters when presented with different...