Robust Bayesian target value optimization

Article Chemistry, Multidisciplinary

Gaussian Process Surrogates for Modeling Uncertainties in a Use Case of Forging Superalloys

Johannes G. Hoffer et al.

Summary: The avoidance of scrap and adherence to tolerances are important goals in manufacturing. Researchers propose a simulation method using Gaussian Process surrogate model that considers real manufacturing process uncertainties, acting as a substitute for expensive and computationally intensive finite element method (FEM) simulation, resulting in a fast and robust method to adequately depict reality.

APPLIED SCIENCES-BASEL (2022)

Add to Collection

Article Mathematics, Applied

BAYESIAN OPTIMIZATION WITH EXPENSIVE INTEGRANDS

Saul Toscano-Palmerin et al.

Summary: Nonconvex derivative-free time-consuming objectives are often optimized using black-box optimization, and a novel Bayesian optimization algorithm leveraging structure is developed to improve performance. The algorithm achieves one-step optimality by solving a challenging value of information optimization problem, providing a novel efficient computational method. Numerical experiments show significant improvements in a wide range of problems, especially when evaluations are noisy or variables vary smoothly.

SIAM JOURNAL ON OPTIMIZATION (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Bayesian optimization for a multiple-component system with target values

Jihwan Jeong et al.

Summary: This paper introduces a method for optimizing multi-component systems by aggregating the squared errors from target values to generate an objective function, which allows for retention of a learned model when changing system components to improve efficiency.

COMPUTERS & INDUSTRIAL ENGINEERING (2021)

Add to Collection

Article Physics, Multidisciplinary