Digital Innovation Hubs


DIH Profile


Hub Information

Hub Name
Local Name
Evolutionary Stage
Fully operational
Geographical Scope


Formerly ADISIF Interface, SynHERA is the network of 19 University Colleges (UC) and their associated research centres in the Wallonia-Brussels Federation. It supports the University Colleges and their associated research centres in order to valorise their research projects and to match skills between the University Colleges and the Walloon, Brussels and international research stakeholders. In addition, SynHERA is willing to offer University Colleges’ researchers a space for sharing and reflexion.

SynHERA est le réseau des 19 Hautes Ecoles et des Centres de recherche Associés en Fédération Wallonie Bruxelles.SynHERA les supporte dans la recherche et les aides à valoriser les résultats de recherche dans le sens demandé par les parties subsidiantes. De plus, SynHERA offre des services aux chercheurs faisant partie de son réseau, comme par exemple, la mise en réseau, la formation, etc...

Contact Data

SynHERA networks
Year Established
rue des pieds d'alouettes 39, 5100, Naninne (Belgium)
Social Media
Contact information
Sabine Dossa,director ; Yves Laccroix, coordinator ;
+32 (0) 81 41 38


Organizational form
(part of) Public organization (part of RTO, or university)
Number of employees


  • Sensory systems
  • Photonics and imaging technologies
  • Robotics
  • Internet of things
  • Artificial intelligence
  • Mobility & Location based technologies
  • Interaction technologies
  • Cyber security
  • Advanced, or high performance computing
  • Big data, data analytics, data handling
  • Virtual, augmented and extended reality
  • Simulation, modelling and digital twins
  • Gamification
  • Additive manufacturing
  • Logistics

The activities of the hub are well aligned with the Belgian national initiative for digitising industry, MADE DIFFERENT – Factories of the future.

Market and Services


  • Agriculture and food
  • Energy and utilities
  • Transport and logistics
  • Education
  • Life sciences & healthcare

TRL Focus

  • TRL3 - Analytical and experimental critical function and/or characteristic proof of concept
  • TRL4 - Component and/or breadboard validation in laboratory environment
  • TRL5 - Component and/or breadboard validation in relevant environment
  • TRL6 - System/subsystem model or prototype demonstration in a relevant environment
  • TRL7 - System prototype demonstration in an operational environment

Services provided

  • Collaborative Research
  • Concept validation and prototyping
  • Testing and validation
  • Education and skills development

Service Examples

Feasibility study and training

Client needs:
In classical predictive maintenance, vibration sensors are placed on customers engines and they acquire vibrations of the latter. The acquired vibrations waveforms are then analyzed by a condition monitoring expert and a report is sent to the customer.
In the new context of Industry 4.0, all sensors installed on a customers site acquire a lot of data. All these data need to be processed. And due to the amount of data, it is not possible for a condition monitoring expert to analyze every single one of them.

Provided solution: Therefore it is needed to be able to process these data automatically. The goal of the project was to develop a tool to process this vibration data and automatically diagnose defects present on the engines. To achieve this objective, it was necessary to extract features from these data, and validate them on historical data. Then train a machine learning algorithm to classify these data according to the diagnosis.

Services provided:

  • Research and development activities
  • The first service provided to the industrial partner of the project was to explore the feasibility of automatic diagnosis in condition monitoring. This is why we have selected a subset of industrial engines (in our case HVAC engines only), and a reduced number of defects.
  • The second service provided was to help the industrial partner, because at the time he had no experience in machine learning.

Relation with digitization:
This project was developed to meet the needs of Industry 4.0 and BigData to analyze a large amount of data. This was done using machine learning algorithm, for a certain types of engines and a reduced number of defects. It can be easily extend to a larger number of defects and also to other types of engines.

Name customer, contact details
Rue Ren Descartes, 18
7000 Mons (Belgium)

Development of control interfaces

The project ""Automated application of control of structural equipment in clean room"" done for the company BECARV.

This study lead to the development of control interfaces, based on the necessary requirements for controlling equipment to limit development time. Thus, the company BECARV is now able to integrate a very
simplified automation with pre-packaged hardware and software objects that are assembled according to the type of project to carry out.

Concept validation and prototyping

Client needs:
The need that has been solved is the lack of a low-cost and non-intrusive system that collects and analyses ergonomic data. The main goal of developing such an environment is giving to ergonomists and prevention advisers a guide and a tool that help them diagnose repetitive strain injury that affects musculoskeletal and nervous system. This environment had to be flexible and adaptable to different scenarios, like a supermarket cashier, a secretary

Services provided:
Concept validation and prototyping is the service that Cerisic provided. The concept that needed to be validated is the use of Kinect 3D cameras to track body movements, then calculate the kinematic indicators of those movements, and compare them to the observations of an experimented physiotherapist.

Based on this validation, we prototyped a system that tracks body joints and calculates kinematic indicators based on the cords of those joints, and then delivers an automatic analysis of the indicators and the dangerousness of the repetitive strain injury.

Relation with digitization:
TRACKTMS was developed to digitize and automate the procedure of detecting either the presence or not of the repetitive strain injury and its severity. Those analysis are done thanks to human observation, which brings errors and imprecision. By the use of our tool, we gain in precision, and thus in the quality of the analysis.

Name customer, contact details:
Venelle le Phare, 10
1400 Nivelles (Belgique)
067 84 44 54


  • European Social Fund
  • National basic research funding
  • Regional funding


Number of customers annually
Type of customers
  • Start-up companies
  • SMEs (<250 employees)
  • MidCaps (between €2-10 billion turnover)
  • Partners

    • Université de Liège (ULg)
    • SEE Telecom
    • SKYWin
    • Haute Ecole Libre De Bruxelles Ilya Prigogine
    • Modyva
    • BElourthe
    • Icare
    • Averbode
    • Université libre de Bruxelles (ULB)
    • SPW DGO4
    • Université de Mons (UMons)
    • Université de Louvain (UCL)
    • TerrEye
    • Logistics In Qallonia
    • Odometric
    • BELSPO
    • SPW DGO3
    • Mecatech
    • SPW DGO6
    • Agoria - Technology industry
      Industry association
    Last updated: 08/09/18 11:39