Surrogate Model-Based Engineering Design and Optimization

TL;DR: In this paper , a generic data-driven control framework was proposed for predicting nodal temperature profiles in additive manufacturing by using extremely randomized trees and is trained and tested on datasets generated through finite element (FE) simulations.

TL;DR: In this article , the authors provide a structured analysis of current methodologies and discuss systematic approaches toward general optimization work in additive manufacturing and the process parameter optimization of new AM alloys.

TL;DR: In this article , a multidisciplinary optimization design framework is presented for decision-makers to explore the given design space, which takes into account the coupling between the disciplines of hull form, structural design and energy use.

TL;DR: In this article , a framework that integrates machine learning and global sensitivity analysis to calibrate process simulation model of self-piercing rivet (SPR) is presented, where surrogate models are trained to represent the intrinsic numerical relationship between selected model parameters (e.g., material properties, interface frictions, and clamping force) and cross-section dimensions of SPR joint obtained from simulation.

TL;DR: An ensemble of surrogate models (EM) is a surrogate model composed of a series of surrogate model combined through a weighted sum to effectively increase the robustness of the prediction.