Standardized Non-Intrusive Reduced Order Modeling Using Different Regression Models With Application to Complex Flow Problems

Abstract

In recent years, numerical methods in industrial applications have evolved from a pure predictive tool towards a means for optimization and control. Since standard numerical analysis methods have become prohibitively costly in such multi-query settings, a variety of reduced order modeling (ROM) approaches have been advanced towards complex applications. In this context, the driving application for this work is twin-screw extruders (TSEs): manufacturing devices with an important economic role in plastics processing. Modeling the flow through a TSE requires non-linear material models and coupling with the heat equation alongside intricate mesh deformations, which is a comparatively complex scenario. We investigate how a non-intrusive, data-driven ROM can be constructed for this application. We focus on the well-established proper orthogonal decomposition (POD) with regression albeit we introduce two adaptations: standardizing both the data and the error measures as well as -- inspired by our space-time simulations -- treating time as a discrete coordinate rather than a continuous parameter. We show that these steps make the POD-regression framework more interpretable, computationally efficient, and problem-independent. We proceed to compare the performance of three different regression models: Radial basis function (RBF) regression, Gaussian process regression (GPR), and artificial neural networks (ANNs). We find that GPR offers several advantages over an ANN, constituting a viable and computationally inexpensive non-intrusive ROM. Additionally, the framework is open-sourced to serve as a starting point for other practitioners and facilitate the use of ROM in general engineering workflows.

References in corpus (11)

• Scikit-learn: Machine Learning in Python
• An overview of gradient descent optimization algorithms
• Tune: A Research Platform for Distributed Model Selection and Training
• Finite volume POD-Galerkin stabilised reduced order methods for the parametrised incompressible Navier-Stokes equations
• An artificial neural network framework for reduced order modeling of transient flows
• On the Computational Efficiency of Training Neural Networks
• Learning Neural Networks with Two Nonlinear Layers in Polynomial Time
• Application of machine learning to viscoplastic flow modeling
• Complexity of Training ReLU Neural Network
• Boundary-Conforming Finite Element Methods for Twin-Screw Extruders using Spline-Based Parameterization Techniques
• An eigenanalysis of data centering in machine learning

Cited by in corpus (4)

• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• Spatio-Temporal Surrogates for Interaction of a Jet with High Explosives: Part I -- Analysis with a Small Sample Size
• A non-intrusive reduced-order modelling for uncertainty propagation of time-dependent problems using a B-splines Bézier elements-based method and Proper Orthogonal Decomposition: application to dam-break flows