Projects | Camilo Velázquez-Rodríguez

RAASCEMAN

Sun, 01 Nov 2026 00:00:00 +0000

About the project

Supply chain disruptions can stop production across entire networks of factories. RAASCEMAN aims to mitigate and prevent these disruptions and to help manufacturers and suppliers adapt quickly to change. It does this within the Manufacturing-as-a-Service (MaaS) paradigm, where factories offer their production capabilities as services.

The project connects factories into networks using digital twins and AI. It is developing:

a tool that quantifies the likelihood and impact of unexpected production events;
a recommendation engine that generates supply chains dynamically;
an audit tool that matches service providers' capabilities to new product requests;
a digital platform for exchanging information within factories and across supply chains.

The results are validated in pilots in the automotive and bike industries and on interconnected pilot lines.

Key facts
Programme	Horizon Europe (grant agreement 101138782)
Duration	3 years
Budget	€4.6 million
Coordinator	DFKI, Germany
Consortium	9 partners: universities, research and technology organisations, and industry, including Flanders Make

My contributions

I lead a large part of the technical work in the Flanders Make pilot, from definition and implementation to deployment and testing:

Standardised digital twins of production assets using the Asset Administration Shell (AAS), designed to be reused across projects.
Deployment and integration of the project’s interoperability middleware in a real production environment.
Tools for testing and demonstration that allow the full solution to be validated continuously under realistic production conditions.

Related publication: Accelerating the Adoption of Asset Administration Shells through AI Agents (INTELLI 2026).

Technologies: Asset Administration Shell (IDTA templates), industrial middleware, digital twins, edge deployment.

UniMaaS

Sat, 31 Oct 2026 00:00:00 +0000

About the project

UniMaaS is building a platform for flexible, agile and decentralised manufacturing based on the Manufacturing-as-a-Service (MaaS) paradigm. Production resources are modelled in a unified way and scheduled automatically across sites.

The platform is demonstrated in four pilots:

aircraft maintenance;
automotive seat manufacturing;
3D construction printing;
logistics and warehouse management.

Key facts
Programme	Horizon Europe, European Partnership Made in Europe (grant agreement 101177842)
Consortium	17 partners from research and industry across Europe and Canada, including Flanders Make

My contributions

I lead a large part of the technical work in the Flanders Make pilot, from definition and implementation to deployment and testing:

Process modelling and semantic integration of production capabilities using ontologies.
Scaling from a single production cell to multi-cell scenarios in a real production environment.
Cloud-based monitoring services, containerised and validated on both historical and real-time production data.

Technologies: process modelling, ontologies, Asset Administration Shell, Docker, cloud monitoring.

EMPOWER

Fri, 30 Oct 2026 00:00:00 +0000

About the project

EMPOWER develops alternative equipment and processes across the photovoltaic (PV) value chain, from silicon wafers to finished modules. The goal is to reduce capital and operating costs and so lower the cost of solar electricity in Europe. The project also aims for higher throughput and yield, and for lower energy and raw-material use.

The work covers direct wafering, metallisation with less silver, edge passivation, and fast interconnection and lamination. It also includes digitalisation with Industry 4.0 methods, including a virtual, vertically integrated PV production line.

Key facts
Programme	Horizon Europe, Innovation Action (grant agreement 101172767)
Duration	December 2024 – May 2028
Budget	€14.6 million (EU contribution €12.0 million)
Coordinator	Institutt for Energiteknikk (IFE), Norway
Consortium	18 partners, including Fraunhofer, Forschungszentrum Jülich, CEA and Flanders Make

My contributions

I develop AI-assisted tools for visual quality inspection of PV modules:

A web-based annotation platform that makes labelling inspection images faster and more consistent, designed together with its users and adopted across several use cases.
Integration with industrial imaging set-ups in collaboration with other teams.
Data analysis that turns inspection results into actionable insights for project partners.

Dissemination: Accelerating EL Defect Annotation in PV Modules via a Web-Based, AI-Assisted Workflow, presented at the 43rd European Photovoltaic Solar Energy Conference and Exhibition (EU PVSEC).

Technologies: computer vision, AI-assisted labelling, electroluminescence (EL) imaging, web development.

WellFiciency

Thu, 29 Oct 2026 00:00:00 +0000

About the project

Manufacturing is paying more and more attention to human centricity and the quality of working life. WellFiciency develops a methodology to monitor operator well-being continuously and to balance it with production efficiency.

Holistic measurement: physical measures, such as postural ergonomics and joint torques, are combined with cognitive measures, such as cognitive load, stress and engagement, at task level. Job-level and personal characteristics are added. Real-time sensor data is linked with feedback from short surveys and questionnaires.
A digital twin of operator well-being, built with privacy and ethics safeguards. It supports role-specific dashboards for operators, team leads and prevention advisors, and helps optimise task allocation and scheduling.
Validation with stakeholders throughout the project, using validation cases that reproduce real industrial challenges.

Key facts
Programme	Flanders Make SBO project
Duration	April 2023 – March 2027
Partners	Flanders Make, HIVA – KU Leuven and others

My contributions

I am responsible for the end-to-end data pipeline for fatigue estimation and recovery recommendations, based on data collected from wearable sensors:

Integration of the team’s components into a single, operational pipeline.
Science-based well-being metrics that turn sensor and task data into practical recommendations.
Validation in near-industrial settings, preparing the solution for use with industrial partners.

Technologies: data pipelines, sensor data processing, ergonomics and human-factors analytics.

KNODI

Wed, 28 Oct 2026 00:00:00 +0000

About the project

Manufacturers collect huge amounts of data through Industrial Internet of Things (IIoT) technologies, but turning it into value is still hard. Production involves many interrelated steps, with variation in products, processes and context. Data from production planning, sensors and operator records has to be combined. Today, answering a single business question can keep a team of experienced data scientists and domain experts busy for 3 to 6 months. An example of such a question is “What factors determine the energy consumption for this specific product?"

KNODI studies how state-of-the-art language-processing AI, combined with structured knowledge representations, can extract, store and use company knowledge. The goal is to support complex production data analyses in two areas: energy consumption and root-cause analysis of product quality. In-house data users can then explore a rich data context and answer complex questions much more efficiently. Answering such questions with less effort is key to reducing energy use, improving efficiency and eliminating scrap.

Key facts
Industrial partners	Bekaert, Materialise, Timeseer
Research partners	Flanders Make, KU Leuven

My contributions

Document analytics that turn company documents into curated, analysis-ready knowledge.
Time-series analytics for anomaly detection and root-cause analysis in production data.
Integration of both into a single analytics pipeline.

Technologies: large language models, knowledge representation, time-series anomaly detection, root-cause analysis.