Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/40077
Title: | Multi-objective optimization of adhesive bonding process in constrained and noisy settings | Authors: | MORALES HERNANDEZ, Alejandro VAN NIEUWENHUYSE, Inneke ROJAS GONZALEZ, Sebastian JORDENS, Jeroen Witters, Maarten Van Doninck, Bart |
Issue Date: | 2023 | Source: | Bernabe , Dorronsoro; Francisco, Chicano; Danoy, Gregoire; Talbi, El-Ghazali (Ed.). Optimization and Learning - 6th International Conference, OLA 2023, Malaga, Spain, May 3–5, 2023, Proceedings, | Series/Report: | Communications in Computer and Information Science | Series/Report no.: | 1824 | Status: | In press | Abstract: | Finding the optimal process parameters for an adhesive bonding process is challenging: the optimization is inherently multi-objective (aiming to maximize break strength while minimizing cost), constrained (the process should not result in any visual damage to the materials, and stress tests should not result in adhesive failures), and uncertain (mea-suring the same process parameters several times lead to different break strength). Real-life physical experiments in the lab are expensive to perform (∼6 hours of experimentation and subsequent production costs); traditional evolutionary approaches are then ill-suited to solve the problem , due to the prohibitive amount of experiments required for evaluation. In this research, we successfully applied specific machine learning techniques (Gaussian Process Regression and Logistic Regression) to emulate the objective and constraint functions based on a limited amount of experimental data. The techniques are embedded in a Bayesian optimization algorithm, which succeeds in detecting Pareto-optimal process settings in a highly efficient way (i.e., requiring a limited number of experiments). | Keywords: | multi-objective optimization;constrained optimization;machine learning;adhesive bonding | Document URI: | http://hdl.handle.net/1942/40077 | Link to publication/dataset: | https://link.springer.com/conference/ola | ISBN: | 978-3-031-34019-2 | Rights: | The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023 | Category: | C1 | Type: | Proceedings Paper |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
JMLab_OLA_2023.pdf Restricted Access | Early view | 1.68 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.