Gerico Vidanes

Applied Researcher & Computational Engineer interested in developing technology to enable and accelerate STEM

View My Work

About Me

I'm a PhD candidate at the University of Southampton's Rolls-Royce UTC for Computational Engineering & Design, focusing on geometric deep learning applications at the interface between computer-aided design and engineering/manufacturing.

With a background in aerospace engineering and industry experience in simulation and modeling, I'm passionate about developing innovative computational solutions that bridge the gap between design and practical implementation.

My research interests include machine learning and CAD/CAE integration, with a particular focus on how advanced computational methods can accelerate engineering workflows.

Machine Learning Geometric Deep Learning Python C++ Linux CAD Data Science Git Mathematical Modelling

Past Projects

Neural Networks in Siemens-NX

Implemented point-based NN approach from my PhD directly into the NX CAD environment using PyTorch/libtorch and NX UGOpen C++ APIs. Integrated into an existing proprietary RR C++ codebase.

C++ Python PyTorch CAD

Data Handler DLLs

Implemented a DLL for a background process to be queried by a MATLAB/Simulink model for data, significantly reducing memory and computation overhead. Designed the data structure and implemented in C.

C MATLAB Simulink

6 DoF Missile Dynamics Modelling

Restructured an existing model to modularize it and add functionality, both in Simulink structure and MATLAB code. The model simulated trajectory due to various forces including aerodynamics, inertia, stage separation, and thrust.

MATLAB Simulink Modelling

Virtual SwirlGenerator

Toolkit for creating arbitrary swirling inlet boundary conditions for use with a CFD framework (SU2). Code could also translate contour plot images into velocity values for boundary conditions.

View on GitHub

Python CFD SU2

Fixed Wing UAV

Part of a team which designed, built, and flew a 7kg UAV with a 2kg payload. Designed a 'lifting body' fuselage and main wing, performed CFD analysis, and developed computer vision algorithms for target detection.

Aerospace CFD Python Computer Vision

Publications

Extending Point-Based Deep Learning Approaches for Better Semantic Segmentation in CAD

Computer-Aided Design
2024
Vidanes, G., Toal, D., Zhang, X., Keane, A., Gregory, J., Nunez, M.
Geometry understanding is a core concept of computer-aided design and engineering (CAD/CAE). Deep neural networks have increasingly shown success as a method of processing complex inputs to achieve abstract tasks. This work revisits a generic and relatively simple approach to 3D deep learning – a point-based graph neural network – and develops best-practices and modifications to alleviate traditional drawbacks. It is shown that these methods should not be discounted for CAD tasks; with proper implementation, they can be competitive with more specifically designed approaches. Through an additive study, this work investigates how the boundary representation data can be fully utilised by leveraging the flexibility of point-based graph networks. The final configuration significantly improves on the predictive accuracy of a standard PointNet++ network across multiple CAD model segmentation datasets and achieves state-of-the-art performance on the MFCAD++ machining features dataset. The proposed modifications leave the core neural network unchanged and results also suggest that they can be applied to other point-based approaches.

Experience

PhD Candidate

September 2021 - Present

University of Southampton - Rolls-Royce UTC for Computational Engineering & Design

Researching the application of geometric deep learning to the interface between computer-aided design and computer-aided engineering.

Supporting the delivery of the 'Systems Design and Computing' module involving Arduino, electronics, and C++.

Simulation and Modelling Engineer

September 2019 - June 2020

MBDA UK

Developing hierarchical and modular numerical models for system performance assessment, using MATLAB, Simulink, and C.

Received 'Reward & Recognition Award' for work done towards meeting a key model delivery milestone during the COVID-19 pandemic.

Master of Aerospace Engineering

2021

Queen's University Belfast

First Class Honours.

Get In Touch

I'm always open to discussing research collaborations, technical challenges, or new opportunities.