We present a CFD-driven surrogate modeling framework that integrates a Convolutional Autoencoder (CAE) with a Deep Neural Network (DNN) for the rapid prediction of urban wind environments and their subsequent use in UAV trajectory planning. A Reynolds-Averaged Navier–Stokes (RANS) CFD database is generated, parameterized by boundary-condition descriptors, to train the surrogate for velocity magnitude and turbulent kinetic energy (TKE). The CAE compresses horizontal flow fields into a low-dimensional latent space, providing an efficient representation of complex flow structures. The DNN establishes a mapping from input descriptors to the latent space, and flow reconstructions are obtained through the frozen decoder. Validation against CFD demonstrates that the surrogate captures velocity gradients and TKE distributions with mean absolute errors below 1% in most of the domain, while residual discrepancies remain confined to near-wall regions. The approach yields a computational speed-up of approximately 4000× relative to CFD, enabling deployment on embedded or edge hardware. For path planning, the domain is discretized as a k-Non-Aligned Nearest Neighbors (k-NANN) graph, and an A* search algorithm incorporates heading constraints and surrogate-based TKE thresholds. The integrated pipeline produces turbulence-aware, dynamically feasible trajectories, advancing the integration of high-fidelity flow predictions into urban air mobility decision frameworks.

Turbulence and wind gusts pose significant risks to the safety and efficiency of UAVs (uncrewed aerial vehicles) in urban environments. In these settings, wind dynamics are strongly influenced by interactions with buildings and terrain, giving rise to small-scale phenomena such as vortex shedding and gusts. These wind speed oscillations generate unsteady forces that can destabilise UAV flight, particularly for small vehicles. Additionally, predicting their formation requires high-resolution Computational Fluid Dynamics (CFD) models, as current weather forecasting tools lack the resolution to capture these phenomena. However, such models require 3D representations of study areas with high geometric consistency and detail, which are not available for most cities. To address this issue, this work introduces an automated methodology for urban CFD mesh generation using open-source data. The proposed method generates error-free meshes compatible with OpenFOAM and includes tools for geometry modification, enhancing solver convergence and enabling adjustments to mesh complexity based on computational resources. Using this approach, CFD simulations are conducted for the city of Ourense, followed by an analysis of their impact on UAV operations and the integration of the system into a trajectory optimisation framework. The CFD model is also validated using experimental anemometer measurements.

Innovative approaches in hot forging, such as the use of floating dies, which aim to minimise burr formation by controlling material flow, require precise management of die geometry distortions. These distortions, primarily caused by thermal gradients, must be tightly controlled to prevent malfunctions during production. This study introduces a comprehensive thermal analysis framework that captures the complete forging cycle—from billet transfer and die closure to forging, spray-cooling, and lubrication. Two advanced heat transfer models were developed: a pressure- and lubrication-dependent contact heat transfer model and a spray-cooling model that simulates fluid dispersion over die surfaces. These models were implemented within the finite element software FORGE-NxT to evaluate the thermal behaviour of dies under realistic operating conditions. These two new models, contact and spray-cooling, implemented within a full-cycle thermal simulation and validated with industrial thermal imaging data, represent a novel contribution. The simulation results showed an average temperature deviation of just 5.8%, demonstrating the predictive reliability of this approach. This validated framework enables accurate estimation of thermal fields in the dies, and offers a practical tool for optimising process parameters, reducing burr formation, and extending die life. Moreover, its structure and methodology can be adapted to various hot forging applications where thermal control is critical to ensuring part quality and process efficiency.

Purpose: This study aims to develop a fast numerical tool for detailed wind flow predictions around offshore wind turbines. The tool is designed to assist in optimizing Unmanned Aerial Vehicle (UAV) flight paths for maintenance operations by providing high-resolution wind and turbulence data in real time. Design/methodology/approach: A Computational Fluid Dynamics (CFD)-generated database is built using a validated Reynolds-Averaged Navier–Stokes model under different wind conditions. Proper Orthogonal Decomposition, namely High Order Singular Value Decomposition, is applied to create a surrogate model. When coupled with site-specific meteorological forecasts, it produces high-resolution wind flow and turbulence maps (spatial resolution of less than 1 m) in less than 1.5 s. These predictions are used within a UAV simulator to assess flight behaviour under realistic turbulence conditions. Findings: This numerical tool speeds up wind predictions by a factor of 2,400 compared to direct CFD calculations while maintaining mean and maximum relative deviations for velocity and turbulence kinetic energy under 2 and 10%, respectively. Its integration with UAV flight assessment tools helps to identify critical regions that may compromise UAV stability, improving operational safety. Originality/value: This tool enables real-time wind predictions (using meteorological data as inputs) and UAV flight analysis, improving UAV-based maintenance operations in offshore wind farms. Its computational efficiency allows real-time use on any computer, supporting pre-flight risk assessment and safe UAV trajectory planning. The integration of the tool into UAV simulators provides a novel approach to enhance the reliability of UAV flights in extreme marine conditions.