R&D Area 03

Scientific Computing and Computational Engineering

The strongest capability area: scientific computing and computational engineering that bridge physical models, multiphysics and multiscale modelling, numerical simulation, AI, experimental data and deployable engineering systems.

INTELLIGENT COMPUTATIONAL STACKComputing, AI & Digital Systems

01DATA SOURCEinstrument / sensor / simulation

02MODEL DESIGNfeatures / representations / data pipelines

03AI / ML / DLsupervised / unsupervised / NLP

04SCIENTIFIC CODEPython / MATLAB / CUDA / GPU

05DEPLOYembedded / full stack / digital twin / XR

06VALIDATEmetrics / experiments / real-case feedback

Engineering data moves through scientific computation, learning algorithms, validation and physical or digital deployment.

10 primary systems

Problems, Methods and Outcomes

Scientific computing, computational engineering, FEM/FEA, RVE, resistor networks, DEM wear modelling, multiphysics, multiscale modelling, Python, MATLAB, Julia, CST, HFSS, COMSOL, ANSYS, Abaqus, SolidWorks, AI/ML/DL, computer vision, NLP, XR, scientific code and digital systems.

P112020-2024

Computational Multiphysics and Experimental Validation

Problem: No single model explains how nanoscale morphology, transport, mechanics and electromagnetic response combine in a sensing material.
Solution: A computational stack that moves between RVE, resistor-network, diffusion, mechanical and electromagnetic models and closes the loop with experiments.
Evidence / result: Physics-to-instrument reasoning

FEM/FEARVEresistor networkdiffusion

View system

P092020-2024

CNT Conductivity, Percolation and Network Models

Problem: Conductive nanocomposite design depends on predicting when random CNT networks establish electron transport and how tunnelling distance affects conductivity.
Solution: Parallel three-dimensional resistor-network and finite-element models validated against electrical measurements.
Evidence / result: around 2 wt% reported percolation threshold

MATLABresistor networkDIGIMATFEM

View system

P242025

Backhoe Teeth Wear Prediction with DEM

Problem: Earthmoving components experience wear that affects maintenance, replacement planning and operating cost.
Solution: A discrete-element simulation approach for predicting backhoe-teeth wear under representative interaction conditions.
Evidence / result: Industrial predictive method

DEMwear predictionindustrial simulation

View system

P232025

Autonomous Mobile-Robot Logistics

Problem: Autonomous logistics platforms require motion-planning methods that connect perception and computation with safe mobile-system behaviour.
Solution: A deep motion-planning research workflow developed around autonomous mobile-robot logistics.
Evidence / result: Accepted research output

mobile roboticsmotion planningdeep learningsimulation

View system

P272024-2026

Applied AI, Machine Learning and Deep Learning for Mechatronics

Problem: Mechatronics students and engineering teams need to move beyond isolated algorithms and connect data, learning models, software and physical systems in realistic applications.
Solution: A project-based artificial-intelligence and digital-systems practice spanning supervised and unsupervised learning, deep learning, NLP, scientific programming, embedded implementation and full-stack system integration.
Evidence / result: AI integrated into mechatronics practice

machine learningdeep learningPython / MATLABembedded AI

View system

P292024-2026

Deep Learning Cycling Posture and Sports Computer Vision

Problem: Sports posture and movement assessment can be costly or difficult to scale when it depends on specialized equipment or manual observation.
Solution: A computer-vision and deep-learning workflow for analysing cycling posture and movement patterns from visual data.
Evidence / result: 90% reported cost reduction

deep learningcomputer visionposture analysissports analytics

View system

P142025-2026

NVIDIA Digital Twins, Simulation and Physical AI

Problem: Engineering education and prototype development needed a shared simulation-to-embedded stack for robotics, digital twins and AI-enabled systems.
Solution: Deployment of NVIDIA Omniverse, Isaac Sim and Jetson across simulation, workshops, supervised projects and collaboration as the first official NVIDIA University Ambassador in Ecuador.
Evidence / result: 3 NVIDIA platforms deployed

OmniverseIsaac SimJetsondigital twins

View system

P152020-Present

Smart Realities: Spatial Computing and Connected Systems

Problem: Emerging-technology concepts often fail to connect interactive software, physical hardware, learning content and a practical delivery strategy.
Solution: An independent R&D initiative integrating sensors, embedded systems, data processing, spatial interfaces and web-based engineering applications.
Evidence / result: 4 cross-functional teams led

XR/ARIoTembedded systemsweb systems

View system

P162020-Present

NanoXR: Nanoscale Spatial Computing Initiative

Problem: Nanoscale structures and multiphysics relationships are difficult to communicate through flat diagrams alone.
Solution: NanoXR applies spatial-computing and AR/XR capability to interactive nanotechnology visualization and engineering communication.
Evidence / result: Cross-disciplinary R&D direction

NanoXRXR/ARscientific visualizationtechnology transfer

View system

P252020-Present

AR-Enabled Educational Publication

Problem: Static educational publishing offers limited interaction for explaining spatial or technical ideas.
Solution: A bilingual publication augmented with interactive digital content and an end-to-end production workflow.
Evidence / result: 50% reported cost reduction

augmented realitypublishinginteraction designdelivery

View system

Cross-Disciplinary Connections

Connected Work

Related work in which this area provides a supporting method, technology or scientific context.

P01Portable Microwave and Passive Wireless Sensing PlatformAn integrated RF instrument connecting resonant sensing structures, VNA acquisition, electromechanical positioning and Python analysis.P03VNA/NanoVNA Measurement and Python Processing ToolchainA complete experimental workflow from RF acquisition and positioning to repeatable processing and engineering interpretation.P08Temperature-Dependent Nanocomposite MechanicsRVE and finite-element models predicted temperature-dependent viscoelastic response and were validated against dynamic mechanical analysis.P10Non-Contact Structural-Health-Monitoring MethodsA technology study comparing vision, radar, laser, wireless, embedded and hybrid methods for structural condition assessment.P13Multidisciplinary Mechatronics Project DevelopmentTechnical direction and hybrid delivery across wireless sensing, simulation, AI, robotics, nanotechnology and embedded projects.P18Remote Monitoring for Elevator Service ResponseEmbedded remote monitoring used to improve fault visibility and reduce emergency-response time.P21Telecommunications Programme and Laboratory ModernizationCurriculum, laboratory and industry-partnership development across wireless sensing, embedded systems, digital twins, mechatronics and AI.P22Wireless Sensor Networks for Agricultural MonitoringA connected-sensing research contribution focused on epidemic monitoring in agricultural environments.P28Sand-Walking Robotic Turtle PrototypeA conservative mechatronics concept/prototype for terrain mobility using bio-inspired turtle locomotion on sand.P30Cathodic Protection Sensor DesignSensor-design work for cathodic-protection monitoring through instrumentation, electromagnetism and embedded/mechatronic integration.