POR FESR Piemonte 2014/2020

Multiple Innovation and digital transformation projects enhancing research and technological development

POR FESR is a Regional Operational Programs financed with the European Regional Development Fund aimed at financing actions on the regional territory and are therefore owned by the Regions or Autonomous Provinces, with the aim of subsidizing infrastructure or productive investments capable of creating employment, in particular by favoring small businesses. Other areas considered to be of particular value and potentially suitable for benefiting from the POR FESR are innovation, research and the digital agenda.


The research and innovation project BIOENPRO4TO - Smart Solutions for Smart Communities was co-funded by the 2014/2020 POR FESR Piemonte, Action I.1b.2.2. Bioeconomy Technology Platform.

BIOENPRO4TO aims to transform residual materials generated by communities in West Turin, such as organic waste, biomass and sewage sludge into bioenergy and new bio products. A solution based on the Distributed Ledger Technologies and Edge Computing has been designed to improve transparency in the bioproducts transformation and supply chains and to increase accuracy and reliability of life cycle assessments.


The DTWIN research project was co-funded by POR FESR Piemonte 2014/2020, Axis I - Action I.1 b.1.2, call PRISM-E. In the project, an integrated software and hardware solution was developed to advance preventive conservation of the artistic heritage by leveraging innovative monitoring methods and tools.

The solution developed is a 'Digital Twin' that enables a detailed and dynamic representation of the physical spaces, artworks and furnishings of historic mansions. IoT, Data analytics and Machine Learning technologies allow understanding the impact of environmental variables and use the knowledge for conservation improvement. You can find more information on the project site.


The TransfoClean-4OT research project was co-funded by POR FESR Piemonte 2014/2020, Axis I - Action I.1 b.1.2, call PRISM-E, Polo Energy and Clean Technologies.

By applying Industry4.0 technologies and principles, the project developed an integrated software and hardware solution that enables improved monitoring of industrial oils and electrical transformers, expanded inferences diagnostics, ensuring greater reliability.

SALS – Food safety management along the supply chain: advanced tools

The SALS research project was carried out thanks to the co-financing of the POR FESR Piedmont 2014/2020, Axis I – Action I.1 b.1.2, PRISM-E tender, Polo Agrifood, and has the objective of extending the safety control for the food production process from the single node of the supply chain of a food production to the entire supply chain, going beyond the concept of track and trace process.

The implemented approach allows to compensate the following problems:
• Ensuring food safety in more extensive and globalized supply chains
• Have an extended vision and not limited to the single node of the supply chain, allowing more timely interventions and waste reduction
• Investigate the logical and operational link between risk assessment and compensation measures, analyzing in detail their effectiveness for the hazelnut supply chain, a Piedmont excellence

The project is funded with PON Research and Innovation 2014-2020 and FSC funds.

ICS-MSC - Industry 4.0 Complex Solution for Manufacturing Supply Chain

The ICS-MSC research project was carried out thanks to the co-financing of the POR FESR Piedmont 2014/2020, PiTeF Supply Chain Technological Platform Tender - Support for cooperative research and development projects aimed at production chains.

The ICS-MSC project aims to create a flexible platform for hosting Digital Twins that can represent products and/or production processes in real time using data from production systems and provided by sensors and IoT gateways and analyzing behavior with Artificial Intelligence techniques in order to predict any deviations, drops in performance and product quality problems.
ICS-MSC allows the creation of models based on neural networks "pulled" by positive and negative examples that train the model by knowledge that human operators possess. This practice will allow, once the model is built and running, to intervene in a preventive manner before the equipment breaks.