Skip to main content

Data innovation

Potential of data innovation within manufacturing

Contrary to the hype of (big) data and the bright future of Industry 4.0 applications, there is still little understanding of the technological challenges which need to be overcome first in order to realise such applications. It is not simply collecting large amounts of diverse production data and applying intelligent algorithms out of the box, it will require the availability of representative historical data carefully curated by domain experts, creativity to derive additional insights about manufacturing processes by linking different data sources and the acquisition of a new technical skillset enabling the identification of the right data-driven business question in a given context.


During the networking event ABISS on 4 October the EluciDATA Innoation Lab presented the  challenges and opportunities related to the realisation of data innovation within manufacturing.

Data Innovation and new insights based on data science

Data science - the science involved in the smart use of digital data - is not just reserved to Internet giants such as Google, Amazon and Facebook, but can also be of value to innovation processes in various industries, even for SMEs. Data science allows insight based on experimental data, profiling products and customers, optimising production processes and predicting machine failures.


The Sirris Data Innovation Team is organising a master class that sheds light on the various aspects of data innovation within the context of the EluciDATA project. Every session starts with a pragmatic industry-oriented introduction to data-driven innovation after which a specific topic is discussed. Each training course can be attended separately.


In 2017, four topics were discussed during the sessions, attended by 69 participants in total: 'the art of feature engineering', 'the importance of data exploration and hypothesis building',  'the art of formulating a data science task' and 'the importance of data exploration and hypothesis building'.

Analyses of a fleet of industrial machines for data-driven optimisation of operation and maintenance tasks

More and more companies are starting proactive or predictive maintenance projects and are looking for ways to optimise the operation of their machines by making better use of the large quantity of data they collect. They mainly, however, focus on the separate machine level when carrying out the analyses, which means that the potential of analysing the fleet of industrial machines as a whole remains unused.


On 13 December 2017, Sirris in cooperation with project partners, VUB, imec, the University of Antwerp and KU Leuven, organised the second edition of the ’Analysis of a fleet of industrial machines for data-driven optimisation of operation and maintenance’ seminar on this topic within the framework of the HYMOP (Hypermodelling strategies for operational optimisation) project. 


The seminar focused on the challenges connected to the optimisation of the operation and maintenance of a fleet of industrial machines based on data analysis and hybrid modelling strategies. With about 70 participants from the academic and industrial world, the event demonstrated the increasing benefits of and interest in the analyses of a fleet of industrial machines for data-driven optimisation.  

Timely preparation for GDPR consequences for data processing activities

In May 2018, the General Data Protection Regulation (GDPR) will enter into force, which will have a substantial impact on companies collecting and processing personal data. This new legislation reinforces the data subject’s rights and privacy when it comes to the processing of personal data. This will change how we innovate with data. 


On 26 June, Sirris and Agoria organised an event on the GDPR and the effect on algorithms and security. The Sirris Data Innovation team presented how the GDPR can influence a company’s data processing activities from a business and technological point of view.