Research Project FACTLOG: Energy-Aware Factory Analytics for Process Industries

FACTLOG meeting

Dynamic twinning process models for an oil refinery and a steel industry

TUC participates in the Research and Innovation Project FACTLOG with indigo team (Industrial and Digital Innovations Research Group) of the School of Production Engineering and Management, with Assistant Professor George Arampatzis as the Principal Investigator. FACTLOG is currently on the second year of its implementation (project duration: 11/2019 – 04/ 2023). The project is funded by the European Commission under the Horizon 2020 Framework Program. The project consortium consists of Academic Institutions, Research Centers, Industries and Enterprises from 11 countries (Italy, Greece, Switzerland, Germany, Turkey, Serbia, United Kingdom, Ireland, Portugal, Slovenia, Romania) and it is coordinated by the Italian company Maggioli SpA.

FACTLOG promotes the transformation of production systems under the concept of Industry 4.0, promoting the idea of the Cognitive Factory in the Process Industry (SPIRE European Association). Industry 4.0 marks a new era for businesses, realizing that knowledge may improve the behaviour of a complex production system. The ability to observe behaviour in combination with modelling and monitoring the production processes through Digital Twins can transform the factory into a flexible system able to automatically optimize its performance. FACTLOG enables the realization of the cognitive factory as an ensemble of independent but intertwined Cognitive Digital Twins that are (i) able to self-learn, and thus to effectively detect and react to anomalies and disruptions but also to opportunities that may arise, (ii) enjoy a local or global view of operations and (iii) are capable for short-, mid- and long-term reasoning and optimization.

By incorporating different pipelines of machine learning and analytical tools at different levels (from machines to process steps and from processes to the whole production plant), FACTLOG enables the realization of the Cognitive Factory as an ensemble of independent but intertwined ECTs, that are (i) able to self-learn, and thus to effectively detect and react to anomalies and disruptions but also to opportunities that may arise, (ii) enjoy a local or global view of operations and (iii) are capable for short-, mid- and long-term reasoning and optimization.

Indigo team works closely with all project partners on topics related to the definition of cognitive ability and how it is achieved through advanced techniques of Dynamic Process Modelling and the creation of Cognitive Digital Twins. It also collaborates the research team of the École Polytechnique Fédérale de Lausanne (EPFL) in the creation of Knowledge Graphs for process modelling.

FACTLOG innovations are deployed, tested and demonstrated in five industrial business cases in the Process Industry: