Design Under Uncertainty and Health Prognostics

Catalog description

Explores probabilistic machine learning methods for engineering design and health prognostics. Provide students with a hands-on experience applying these methods to analyze and improve the reliability of engineered systems; applications of probabilistic machine learning methods to engineering design and health prognostics; hands-on learning of various probabilistic design methods, such as surrogate modeling, uncertainty quantification, reliability-based design, and robust design. Real-world examples of using probabilistic machine learning methods for fault diagnostics and health prognostics in two industrial applications: prognostics of implantable-grade Li-ion battery and deep learning and Industrial Internet of Things (IIoT) for predictive maintenance of industrial equipment.