Key Takeaways & Executive Findings
- •• Neural Physics, a CNN-based approach with weights from classical discretisation, enables high-fidelity train aerodynamic simulations on GPUs and AI processors with high speed and accuracy. • The method integrates implicit large eddy simulation with a non-linear Petrov-Galerkin scheme and uses ConvFEM for higher-order finite elements, simplifying implementation. • First application of ConvFEM to high-speed fluid flow in complex geometries, demonstrated on a freight Locomotive Class 66 and a partially loaded freight train with and without crosswind. • Validated results show good agreement with existing numerical and experimental data for pressure and velocity distributions, indicating potential for efficient predictive frameworks in train-environment interaction studies.
Abstract
This paper presents the application of a novel AI-based approach, Neural Physics, to produce high-fidelity simulations of train aerodynamics. Neural Physics is built upon convolutional neural networks (CNNs), where the weights are explicitly determined by classical numerical discretisation schemes rather than by training. By leveraging the power of AI technology, this recent approach results in code that can run easily on GPUs and AI processors, achieving high computational speed without sacrificing accuracy. The approach uses an implicit large eddy simulation method based on a non-linear Petrov-Galerkin method to model the unresolved turbulence. Furthermore, for higher-order finite elements, the convolutional finite element method (ConvFEM) is used, which greatly simplifies the implementation of higher-order elements within the NN4DPEs approach. We demonstrate the capability of Neural Physics by simulating a freight Locomotive Class 66 and a partially loaded freight train operating in an open field environment with and without cross wind. This is the first time that ConvFEM has been applied to high-speed fluid flow problems in complex geometries. The results are validated against existing numerical results and experimental measurements, and show good agreement in terms of pressure and velocity distributions around the train body.
1. Introduction
Railway transportation is increasingly recognized for its potential to offer both energy efficiency and environmental sustainability. In the United Kingdom, for instance, the government has set an ambitious goal to double the volume of rail freight cargo by 2030 [1]. One strategy to achieve this is the introduction of dedicated high-speed freight services, offering potentially faster delivery and improved network capacity. However, raising the operational speeds of freight trains imposes additional aerodynamic demands, including enhanced slipstream effects that could pose safety risks to passengers on platforms and trackside workers [2, 3]. Building on this, recent investigations have examined slipstream characteristics and near-body flow features around trains with varying nose lengths and operational configurations [4], as well as the influence of the Reynolds number and air compressibility [5].
Besides, recent studies have extensively investigated the aerodynamic influences of high-speed trains on their surroundings, including transient pressures on trackside and overhead structures, wind-induced responses of nearby infrastructures, and pressure fluctuations on noise barriers under various wind conditions [6 −16]. These works collectively demonstrate that passing trains can generate significant unsteady aerodynamic loads, vibrations, and even structural fatigue, reinforcing the need for efficient predictive frameworks for train-environment interaction studies. Furthermore, both aerodynamic drag and the amplitude of pressure changes increase roughly in proportion to the square of the train’s speed, magnifying the energy requirements for propulsion and exacerbating any safety concerns [17]. These challenges indicate the need for refined aerodynamic solutions that are both reliable and computationally efficient.
Recent studies have proposed various geometric optimisation strategies to effectively reduce aerodynamic drag and enhance operational efficiency [18, 19]. However, investigations into the aerodynamic behaviour of freight trains under different operational and environmental conditions continue revealing complex flow phenomena. Freight trains already present complex aerodynamic issues due to their bluff body geometries, diverse loading configurations and large inter-car gaps [20−22]. As speeds increase, the significance of these complexities grows, leading to augmented flow separation, vortex shedding, and higher levels of unsteady turbulence around the freight train. Wind tunnel experiments and full-scale measurement
Loading authentic research manuscript (Pages 1–5)...
CHEN Bo-yang, LIU Zhen, GUO Zi-jian, HEANEY Claire E, PAIN Christopher C (2025). Accelerated physics-based simulations of train aerodynamics using machine learning libraries. Journal of Central South University. https://doi.org/10.1007/s11771-025-6155-4
Research & Educational Purpose Only:The translations, structured abstracts, analytical annotations, and data reports provided by SinoTechIntel are intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoTechIntel claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is Neural Physics and how does it differ from traditional AI-based simulation methods?
Neural Physics is a novel AI-based approach that uses convolutional neural networks (CNNs) where the weights are explicitly determined by classical numerical discretisation schemes rather than by training. This allows the method to leverage AI hardware (GPUs, AI processors) for high computational speed while maintaining accuracy, unlike traditional data-driven neural networks that require extensive training data.
What is the significance of using ConvFEM in this study?
ConvFEM (convolutional finite element method) simplifies the implementation of higher-order finite elements within the Neural Physics framework. This is the first time ConvFEM has been applied to high-speed fluid flow problems in complex geometries, enabling efficient and accurate simulations of train aerodynamics.
How was the Neural Physics approach validated?
The approach was validated by simulating a freight Locomotive Class 66 and a partially loaded freight train in an open field with and without crosswind. The results were compared against existing numerical results and experimental measurements, showing good agreement in pressure and velocity distributions around the train body.
What are the potential applications of this research?
This research provides an efficient predictive framework for train-environment interaction studies, which is crucial for assessing aerodynamic loads, vibrations, and safety risks associated with high-speed freight trains. It can aid in optimizing train designs and operational strategies to reduce drag and enhance safety.
What are the computational benefits of using Neural Physics?
Neural Physics code runs easily on GPUs and AI processors, achieving high computational speed without sacrificing accuracy. This makes it suitable for large-scale simulations that would be computationally expensive with traditional methods.
Related Technical Papers & Translations
Direct Repair of the Crystal Structure and Coating Surface of Spent LiFePO4 Materials Enables Superfast Li-Ion Migration
The rapid accumulation of spent LiFePO4 (LFP) cathodes from retired lithium-ion batteries necessitates the development of effective and environmental-friendly recycling strategies. In this context, direct regeneration has emerged as a promising approach for reclaiming LFP cathode materials, offering a streamlined pathway to restore their electrochemical functionality. We report an integrated regeneration protocol that simultaneously repairs the degraded crystal structure and reconstructs the damaged carbon coating in spent LFP. The regenerated cathode material had superfast lithium-ion diffusion kinetics and a stable cathode–electrolyte interface, giving a remarkable rate capability with specific capacities of 122 mAh g−1 at 5C and 106 mAh g−1 at 10C (1C = 170 mA g−1). It also maintained capacities of 110.7 mAh g−1 (5C) and 84.1 mAh g−1 (10C) after 400 cycles. It could be used in harsh environments and could be stably cycled at subzero temperatures (−10 and −20 °C) and in solid-state electrolyte batteries. Life cycle assessment combined with economic evaluation using the EverBatt model reveals that this direct regeneration approach has high economic and environmental benefits.
Oxide Semiconductor for Advanced Memory Architectures: Atomic Layer Deposition, Key Requirement and Challenges
Oxide semiconductors (OSs), introduced by the Hosono group in the early 2000s, have evolved from display backplane materials to promising candidates for advanced memory and logic devices. The exceptionally low leakage current of OSs and compatibility with three-dimensional (3D) architectures have recently sparked renewed interest in their use in semiconductor applications. This review begins by exploring the unique material properties of OSs, which fundamentally originate from their distinct electronic band structure. Subsequently, we focus on atomic layer deposition (ALD), a core technique for growing excellent OS films, covering both basic and advanced processes compatible with 3D scaling. The basic surface reaction mechanisms—adsorption and reaction—and their roles in film growth are introduced. Furthermore, material design strategies, such as cation selection, crystallinity control, anion doping, and heterostructure engineering, are discussed. We also highlight challenges in memory applications, including contact resistance, hydrogen instability, and lack of p-type materials, and discuss the feasibility of ALD-grown OSs as potential solutions. Lastly, we provide an outlook on the role of ALD-grown OSs in memory technologies. This review bridges material fundamentals and device-level requirements, offering a comprehensive perspective on the potential of ALD-driven OSs for next-generation semiconductor memory devices.
Laser powder bed fusion of biodegradable Zn-4Cu alloy: Processing, microstructure and properties
Zn's natural degradability and biocompatibility make it a promising candidate for implants, however, its mechanical properties remain insufficient for bone applications. In this study, the performance of Zn was enhanced by developing Zn-Cu alloys via laser powder bed fusion (LPBF). Optimal LPBF parameters for forming stable tracks were achieved by adjusting laser power and scanning speed. Under optimized conditions of 100 W and 100 mm/s, high-density (99.58%) Zn-Cu alloys with improved hardness (68.2HV) and yield strength (160 MPa) were achieved. These improvements are attributed to solid solution strengthening, segregation strengthening, and grain refinement. The Zn-Cu alloys also demonstrated favorable degradation behavior, with a rate of 0.16 mm/year. This degradation is primarily driven by micro-galvanic corrosion between the CuZn5 phase and Zn matrix, along with refined grains and increased grain boundary density. This work demonstrates a viable strategy for fabricating Zn-based implants with enhanced structural integrity and mechanical performance via LPBF.