Deep Learning for Reliability and Risk

Modern engineered systems are generally configured with hardware, software, human, organizations, and their interactions. These features exponentially increase the complexity of systems and, in turn, boosting the possibility of system failure. Proper understanding and modeling of such system behaviors are important and urgent to ensure the reliability and safety of system design and operations. With the rapid advances on the Internet of Things (IoT), modern engineered systems tend to be increasingly instrumented with network-connected devices and massive quantities of multidimensional data have been generated from multi-sensor suites. These big machinery data have been recognized as a valuable resource, based on which one can leverage on deep learning techniques to uncover and explore hidden features to gain insights on a complex system performance. Deep learning has emerged as a powerful approach that enables handling big machinery data and sensor fusion for efficient risk and reliability predictive solutions under uncertainty. CRRE develops research and predictive solutions for the industry that seek to tackle the challenges such as (a) physics-based deep learning, (b) Bayesian deep neural networks, (c) generative models, (d) interpretability and trustworthy deep learning based prognostic solutions, (e) systems of systems fault diagnostics and prognostics.