The “InCop” project
As part of the FAIR – “Industry 5.0 Collaborative Platform” initiative, Revelis has developed a platform for Industry 5.0 with the aim of connecting people, processes, information and objects in a single and interoperable ecosystem, offering decision-making support in the creation of products and services tailored to each customer and supporting personnel in the execution of tasks, through personalized indications and suggestions to optimize the execution of their tasks, reduce working times and improve operational efficiency with a decrease in production costs.
Project type: Public call for the selection of project proposals, aimed at granting funding for activities consistent with the program using the resources of the National Recovery and Resilience Plan (PNRR) mission 4, “Education and Research” – Component 2, “from research to business” – investment line 1.3, financed by the European Union – nextgenerationeu”, project “Future Artificial Intelligence Research – FAIR” PE0000013, Spoke 9 CUP H23C22000860006.
Project objectives
The main objectives of the InCoP project are the following:
– Develop a versatile and scalable technological platform, capable of supporting Industry 5.0 principles in different industrial sectors. The platform is modular and adaptable, and allows the integration of new functionalities and technologies.
– Validate the platform in a real context, initially at Target S.p.A., a company specialized in the production of baked goods in the Catanzaro area. The long-term goal is to extend the validation to other sectors.
– Improve the efficiency and flexibility of the production process through detailed analysis of the activities and the design of solutions based on Machine Learning (ML), Deep Learning (DL) and Reasoning. The intent is to create a smarter and more adaptable production system.
– Enable mass customization of products thanks to a specific module of the platform, responding to individual customer needs
Distinctive features
The main characteristics of the InCoP project include:
– The use of the Internet of Everything (IoE) paradigm to connect people, processes and data in a single and interoperable ecosystem.
– The development of a module for the intelligent execution of tasks, to support workers and their safety.
– The creation of a mass customization module for the benefit of the customer and the reduction of resource waste.
– The use of advanced scientific methodologies for feasibility analysis, data analysis (such as CRISP-DM and Answer Set Programming – ASP modeling) and design (such as Design Thinking and the Agile approach).
– The forecast of a significant increase in operational efficiency of 40% and a reduction in production costs per product of 20% for the experimenting company
The use case
The InCop platform is based on AI-based methodologies, Internet of Everything (IoE) and intelligent industrial automation and has been validated in Target S.p.A., a company specialized in the production of baked products such as bread, pizza, focaccia and snacks.
The State of the Art techniques used in the project fall into the areas: Internet of Everything, Machine Learning and Deep Learning, Automatic Reasoning.
Internet of Everything
Evolution of the IoT, aiming to connect people, processes, information and objects in a single and interoperable ecosystem. The complexity and heterogeneity of resources in the IoE require architectures capable of managing interoperability at the technical, syntactic, semantic and structural levels. Data repositories, based on NoSQL technologies, store heterogeneous data in a common and accessible format. Such architectures also support the analysis and extraction of useful information for decision-making.
Automatic reasoning
The use of logic programs and Answer Set Programming techniques will support Target staff in the execution of tasks, through personalized indications and suggestions to optimize the execution of their tasks, reducing working times, improving operational efficiency and decreasing production costs as well as the risk of accidents at work.
Machine Learning e Deep Learning
Through descriptive and predictive algorithms for mass customization, Target will receive decision-making support in creating products and services tailored to each customer.
Activity Plan
The activities for the creation of the InCop platform are organised into 3 macro-phases
Feasibility Analysis
Analysis of the production process and manual activities
Verification of the applicability of the WP9.6 framework with respect to the analyzed production process.
Use Case Specification
Definition of expected results, metrics to evaluate them and quantification of the potential impact
Design of ML techniques for mass-personalization, and (Stream) Reasoning techniques to support personnel in the execution of tasks
Design of the platform for the use case
Platform development and validation
Module for intelligent task execution, based on employee behavior analysis
Module for mass product customization, to ensure organizational efficiency
