Constrained multi-objective optimization of process design parameters in
settings with scarce data: an application to adhesive bonding
- URL: http://arxiv.org/abs/2112.08760v3
- Date: Mon, 10 Apr 2023 12:26:57 GMT
- Title: Constrained multi-objective optimization of process design parameters in
settings with scarce data: an application to adhesive bonding
- Authors: Alejandro Morales-Hern\'andez, Sebastian Rojas Gonzalez, Inneke Van
Nieuwenhuyse, Ivo Couckuyt, Jeroen Jordens, Maarten Witters, and Bart Van
Doninck
- Abstract summary: Finding the optimal process parameters for an adhesive bonding process is challenging.
Traditional evolutionary approaches (such as genetic algorithms) are then ill-suited to solve the problem.
In this research, we successfully applied specific machine learning techniques to emulate the objective and constraint functions.
- Score: 48.7576911714538
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Adhesive joints are increasingly used in industry for a wide variety of
applications because of their favorable characteristics such as high
strength-to-weight ratio, design flexibility, limited stress concentrations,
planar force transfer, good damage tolerance, and fatigue resistance. 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
failures that are adhesion-related), and uncertain (testing the same process
parameters several times may lead to different break strengths). Real-life
physical experiments in the lab are expensive to perform. Traditional
evolutionary approaches (such as genetic algorithms) are then ill-suited to
solve the problem, due to the prohibitive amount of experiments required for
evaluation. Although Bayesian optimization-based algorithms are preferred to
solve such expensive problems, few methods consider the optimization of more
than one (noisy) objective and several constraints at the same time. In this
research, we successfully applied specific machine learning techniques
(Gaussian Process 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
physical experiments).
Related papers
- End-to-End Learning for Fair Multiobjective Optimization Under
Uncertainty [55.04219793298687]
The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality.
This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives.
It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
arXiv Detail & Related papers (2024-02-12T16:33:35Z) - Task-specific experimental design for treatment effect estimation [59.879567967089145]
Large randomised trials (RCTs) are the standard for causal inference.
Recent work has proposed more sample-efficient alternatives to RCTs, but these are not adaptable to the downstream application for which the causal effect is sought.
We develop a task-specific approach to experimental design and derive sampling strategies customised to particular downstream applications.
arXiv Detail & Related papers (2023-06-08T18:10:37Z) - An Empirical Evaluation of Zeroth-Order Optimization Methods on
AI-driven Molecule Optimization [78.36413169647408]
We study the effectiveness of various ZO optimization methods for optimizing molecular objectives.
We show the advantages of ZO sign-based gradient descent (ZO-signGD)
We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
arXiv Detail & Related papers (2022-10-27T01:58:10Z) - Efficiently Controlling Multiple Risks with Pareto Testing [34.83506056862348]
We propose a two-stage process which combines multi-objective optimization with multiple hypothesis testing.
We demonstrate the effectiveness of our approach to reliably accelerate the execution of large-scale Transformer models in natural language processing (NLP) applications.
arXiv Detail & Related papers (2022-10-14T15:54:39Z) - Bayesian optimization with known experimental and design constraints for
chemistry applications [0.0]
We extend our experiment planning algorithms Phoenics and Gryffin such that they can handle arbitrary known constraints.
We illustrate their practical utility in two simulated chemical research scenarios.
arXiv Detail & Related papers (2022-03-29T22:16:54Z) - Tuning Particle Accelerators with Safety Constraints using Bayesian
Optimization [73.94660141019764]
tuning machine parameters of particle accelerators is a repetitive and time-consuming task.
We propose and evaluate a step size-limited variant of safe Bayesian optimization.
arXiv Detail & Related papers (2022-03-26T02:21:03Z) - Golem: An algorithm for robust experiment and process optimization [0.0]
Design of experiment and optimization algorithms are often adopted to solve these tasks efficiently.
Golem is an algorithm that is suboptimal to the choice of experiment planning strategy.
It can be used to analyze the robustness of past experiments, or to guide experiment planning toward robust solutions on the fly.
arXiv Detail & Related papers (2021-03-05T15:00:34Z) - High Dimensional Level Set Estimation with Bayesian Neural Network [58.684954492439424]
This paper proposes novel methods to solve the high dimensional Level Set Estimation problems using Bayesian Neural Networks.
For each problem, we derive the corresponding theoretic information based acquisition function to sample the data points.
Numerical experiments on both synthetic and real-world datasets show that our proposed method can achieve better results compared to existing state-of-the-art approaches.
arXiv Detail & Related papers (2020-12-17T23:21:53Z) - Using models to improve optimizers for variational quantum algorithms [1.7475326826331605]
Variational quantum algorithms are a leading candidate for early applications on noisy intermediate-scale quantum computers.
These algorithms depend on a classical optimization outer-loop that minimizes some function of a parameterized quantum circuit.
We introduce two optimization methods and numerically compare their performance with common methods in use today.
arXiv Detail & Related papers (2020-05-22T05:23:23Z) - Experimental adaptive Bayesian estimation of multiple phases with
limited data [0.0]
adaptive protocols, exploiting additional control parameters, provide a tool to optimize the performance of a quantum sensor to work in such limited data regime.
Finding the optimal strategies to tune the control parameters during the estimation process is a non-trivial problem, and machine learning techniques are a natural solution to address such task.
We employ a compact and flexible integrated photonic circuit, fabricated by femtosecond laser writing, which allows to implement different strategies with high degree of control.
arXiv Detail & Related papers (2020-02-04T11:32:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.