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
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
ISBN: 9783031340192
DOI: 10.1007/978-3-031-34020-8_16
ISI #: WOS:001481371300016
Rights: The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023
Category: C1
Type: Proceedings Paper
Validations: vabb 2025
Appears in Collections:Research publications

Files in This Item:
File Description SizeFormat 
Pages from 978-3-031-34020-8.pdf
  Restricted Access
Published version418.93 kBAdobe PDFView/Open    Request a copy
Show full item record

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.