[HTML][HTML] Physics-informed machine learning for system reliability analysis and design with partially observed information

Y Xu, P Bansal, P Wang, Y Li - Reliability Engineering & System Safety, 2025 - Elsevier
Constructing a high-fidelity predictive model is crucial for analyzing complex systems,
optimizing system design, and enhancing system reliability. Although Gaussian Process …

Multi-Task Learning for Design Under Uncertainty With Multi-Fidelity Partially Observed Information

Y Xu, H Wu, Z Liu, P Wang, Y Li - Journal of …, 2024 - asmedigitalcollection.asme.org
The assessment of system performance and identification of failure mechanisms in complex
engineering systems often requires the use of computation-intensive finite element software …

Multi-Task Multi-Fidelity Machine Learning for Reliability-Based Design With Partially Observed Information

Y Xu, H Wu, Z Liu, P Wang - … and Information in …, 2023 - asmedigitalcollection.asme.org
In complex engineering systems, assessing system performance and underlying failure
mechanisms with respect to uncertain variables requires repeated testing, which is often …

Hierarchical surrogate modeling with multiple order partially observed information

Y Xu, P Wang - International Design Engineering …, 2022 - asmedigitalcollection.asme.org
Understanding the input and output relationship of a complex engineering system is an
essential task that attracts widespread interests in engineering design fields. To investigate …

Efficient and robust optimal design for quantile regression based on linear programming

C Peng, DP Kouri, S Uryasev - Computational Statistics & Data Analysis, 2024 - Elsevier
When informing decisions with experimental data, it is often necessary to quantify the
distribution tails of uncertain system responses using limited data. To maximize the …

Risk averse constrained blackbox optimization under mixed aleatory/epistemic uncertainties

C Audet, J Bigeon, R Couderc… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper addresses risk averse constrained optimization problems where the objective
and constraint functions can only be computed by a blackbox subject to unknown …

Physics-constrained machine learning for reliability-based design optimization

Y Xu, P Wang - 2023 Annual Reliability and Maintainability …, 2023 - ieeexplore.ieee.org
Summary & ConclusionsTo aid and improve the reliability of product designs, repeated
safety tests are required to find out the safety performance of the product with respect to …

Reliability-Based Optimization of Offshore Salt Caverns for CO2 Abatement

Z Zheng, Y Xu, B Hamdan… - International …, 2022 - asmedigitalcollection.asme.org
In recent years, projects have been proposed to utilize salt caverns as a storage method for
supercritical CO2 (s-CO2) and have been carried out around the world, which can effectively …

Peregrination through blackbox optimization: multimodality, stochasticity and risk aversion.

R Couderc - 2023 - theses.hal.science
To tackle blackbox optimization, this thesis consists of three contributions, designed around
a single notion: Gaussian exploration of space. This exploration consists of sampling points …

Reliability Analysis Using Multi-Fidelity Physics-Informed Machine Learning with Partially Observed Information

K Babski-Reeves, B Eksioglu, D Hampton - search.proquest.com
Reliability analysis of complex engineering systems requires repeated testing to determine
system performance and underlying failure mechanisms with respect to a number of …