Oct 2026· Machine Learning and Knowledge Extraction· Vol 8, pp. 313· 0 citations· 35 references
TL;DR
Investigating the performance of different combinations of sampling and machine learning methods under varying process characteristics that are previously known to the domain expert suggests that process noise eliminates the predictive quality of standard regression models used in statistical evaluation.
Abstract
To improve physical processes, domain experts use experimental test setups to gather data. After sampling, the data is analysed using a regression model, for example. The objective of this work is to investigate the performance of different combinations of sampling and machine learning methods under varying process characteristics that are previously known to the domain expert. This results in practical recommendations for users with limited expertise in machine learning. A large-scale combinatorial test setup consisting of polynomial surrogates as pseudo processes with the characteristics of variable count, complexity, process noise and position of the optimum was created. The sampling methods (Sobol, random, Bayesian optimisation and response surface methodology with additional G-optimal test points) were compared against twenty-six ML methods. The results indicate that the choice of ML method has a greater influence on global modelling accuracy than the choice of sampling method. However, strong interactions between sampling and ML method demonstrate that they should not be selected independently. Overall, the findings suggest that process noise eliminates the predictive quality of standard regression models used in statistical evaluation. Space-filling sampling methods generally provide reliable performance, while regularised polynomial, kernel-based, and additive models offer strong predictive accuracy across multiple scenarios.
In this work, we present a comparative study on machine-learning-based surrogate modeling for multidisciplinary aerospace applications. The main objective of the work is to demonstrate the predictive capability of traditional machine learning methods, including linear regression, random forest, gradient boosting, extre...
Dilan Kılıç, Melike Nikbay· Journal of Aerospace Informa...· 0 citations
Abstract. This work presents an Adaptive Sampling-based surrogate framework for predicting the accuracy of higher-order beam theories generated within the Carrera Unified Formulation. The objective is to identify the minimal set of generalized displacement variables required to achieve a prescribed accuracy, thereby re...
M. Petrolo· Materials Research Proceedin...· 0 citations
This article reviews ML-based prediction of mechanical properties for crystalline compounds, steels, high-entropy alloys, concrete and architected composites and indicates that tree ensembles and neural networks are applied to composition and processing data and that knowledge-based descriptors can improve on compositi...
Kancharla Bullibabu, Md. Abid Ali, Bhukya Venkanna et al.· Journal of Advanced Material...· 0 citations
Introduction: This paper conducted a comparative study that evaluated classical statistical and modern machine-learning regression models of small sample predictive modeling using the Concrete Compressive Strength (n = 100) data.
Methodology: The current research used a powerful nested cross-validation model which use...
Maria Malik· Precision Journal of Applied...· 6 citations
This study examines the impact of uncertainty propagation and design exploration techniques on robust airfoil optimization processes. The RAE2822 airfoil geometry is selected as the case study and parameterized using the class/shape transformation (CST) method. The functional relationship between design inputs and ou...
G. Demir· Journal of Aerospace Enginee...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.