The automotive and off-road industries are heavily investing in R&D to improve both physical and virtual verification and validation techniques. Recent software and hardware advancements have extended these techniques from simple component evaluations to complex system assessments such as involving multi-physics scenarios. Despite the benefits of virtual validation tools like structural analysis and CFD, they often come with high development costs, particularly in CFD applications.
Virtual verification methodology, especially when combined with data science, offer significant advantages over traditional physical methods by enhancing CAE efficiency and reducing resource consumption which can greatly improve product design and validation efficiency across many industries.
The success of machine learning applications depends on effective data processing, adequate computational resources, and the right algorithm selection. Key machine learning techniques impacting the CFD field include data analytics, PBML reduced-order models, geometry deep learning, and physics-informed neural networks (PINN).
This study explores the application of Machine Learning (ML) in the Computational Fluid Dynamics (CFD) domain, specifically targeting exhaust-driven aspiration and aftertreatment systems. By leveraging numerical data-driven techniques such as data analytics and Parametric-Based Machine Learning (PBML), the research demonstrates how ML can effectively predict quantitative outcomes based on parametric input variables. A key focus is placed on the importance of selecting appropriate regression models, as different techniques significantly influence the quality of design decisions. The study evaluates multiple regression approaches to identify optimal solutions for predicting system performance metrics.
The proposed PBML framework offers a scalable and efficient alternative to traditional CFD methods, particularly in applications where outcomes are heavily dependent on design and simulation parameters—such as intake systems, tailpipe configurations, and cooling systems. By reducing computational demands and accelerating analysis, this approach supports faster and more informed decision-making in early-stage design processes.