PROJECTS

Centiloc, a pioneering hardware innovation startup, proposes a solution aimed to develop a Digital Twin “on the shelf'” for chemical inventories, using Centiloc’s NFC microgeolocation and filling-level sensors. This technology will provide real-time tracking and data analytics, improving production efficiency, quality control, workforce optimization, waste reduction (15-30%), and worker safety. Key representative industrial partners will test and implement the solution ensuring practical validation and business expansion:

• One of the biggest watch manufacturer represented by its integrator SOLID, that uses chemicals for watch manufacturing and quality control
• Thinkin, an Italian based company specialized in creating Digital Twins through IoT technologies for shop floor operations management and optimization

TEC Eurolab’s role will be to represent the chemical lab which faces chemical storage issues and tests the Digital Twin

The DSRRD (DataSpace for Rapid R&D) project is a cutting-edge initiative aimed at improving the traceability of components during the development, design, and testing phases. This project focuses on the abstraction of data related to the aerospace components that Collins Aerospace intends to develop, using the dataspace provided by IndustryApps. TEC Eurolab will be responsible for testing the physical components once they are produced by Collins Aerospace. The test results will be sent to the IndustryApps platform, where they will be processed through an artificial intelligence model developed by SUPSI. This AI model will suggest new optimal design parameters based on the collected data.

The Structurescope EG + Artificial Intelligence (SSEGAI) technology is designed to determine by eddy current (EC) non-destructive testing (NDT) methods the chemical-physical, mechanical properties of electrically conductive, mostly metal alloys, carbon-fiberreinforced polymers (SRFP) and metal ceramics, semiconductor materials in the Industrial 4.0/Industrial 5.0 paradigm. The technology consists of the Qu-Scope measuring device and the Nanoinspect AI Solution sotware suite.

The Energy Master project represents a significant advancement in energy efficiency and sustainability. By leveraging AI technology, the project aims to optimize the self-consumption of energy generated by TEC Eurolab’s rooftop solar panels. The AI system will precisely predict power usage and production, aligning the operation of high-energy-consuming machinery with peak solar production periods. This strategic synchronization enhances the utilization of solar energy, thereby advancing TEC Eurolab’s sustainability goals and reducing reliance on external energy sources. This innovative approach not only maximizes the benefits of renewable energy but also significantly contributes to the company’s overarching objectives of environmental responsibility and operational efficiency.

Predictive Q+ is an advanced software platform for streamlined production processes. Originating from the automotive and steel wire industries, it serves as a comprehensive process control station, monitoring, detecting, and predicting operational and quality issues. Developed by the startup PredictiveDataScience in collaboration with industry partners and powered by AI, it offers tools for detailed analytics, disruption prediction, and optimization, enhancing quality and resource efficiency. Its versatile interface accommodates diverse data sources, catering to any manufacturing enterprise. Collaborating with partners within the consortium, Predictive Q+ expands its capabilities to other industries. TEC Eurolab leverages the platform for enhanced predictive maintenance of tomographs. NV Bekaert SA benefits from predictive maintenance for patenting and galvanizing lines and systems and quality control of wire products. INNOVAPLAST will use the platform for optimizing the process parameters in production of the ria-based bioplastic raw materials. Through collaborations, Predictive Q+ demonstrates its ability to drive innovation and address industry-specific challenges. Its versatile and powerful features, combined with a user-friendly interface, empower manufacturing enterprises to achieve agility, efficiency, and competitiveness. It enables companies to optimize their production processes, respond to market demands, and remain competitive in a dynamic economic environment.

Many industrial processes are difficult to optimize due to the lack of performance index definition, unavailability of sensors (and, indeed, measurements), and difficulties in setting up objective functions. In such scenarios, expert operators’ knowledge drives the tune-up phase of the industrial processes/applications. Indeed, a programming-free approach to transfer such human knowledge to the production plant can be implemented to allow any operator to naturally/intuitively transfer his/her expertise to the target machine/robot.

The Kick-off Meeting of the CAMPRES Industrial Research Project was conducted as part of the “Call for strategic industrial research projects aimed at the priority areas of the Smart Specialization Strategy 2023-2024”, Action 1.1.2 “Support for collaborative research of research laboratories and universities with companies” of the Emilia-Romagna Region (PR-FESR EMILIA ROMAGNA 2021-2027).

CAMPRES focuses on the development of a family of innovative composite materials for the containment of battery elements for static and/or portable energy storage suitable for mass production with advanced injection molding technologies.

The development of innovative alloys with high-temperature resistance properties remains imperative in the field of materials engineering research. Since they are intended for use in the construction of turbine components, these alloys must exhibit high fatigue, creep, oxidation, and corrosion resistance at extreme temperatures. The new generation of high entropy alloys shows potential for achieving optimal performance in such components. These alloys are based on five or more main elements, forming stable solid solution structures at elevated temperatures. To date, components made from high entropy alloys are mostly produced using conventional techniques, which require additional post-fabrication treatments.

GIMCANA is a European Union co-funded project that will develop a new multi-material joining technology, to be applied to a wide range of structural components in any industrial sector, in order to promote the substitution of metal in favor of a fiber-reinforced polymer (PFR) and the resulting extreme weight reduction. The innovative technology, namely SLIM2CORE (Standalone Lattice Insert for Metal-COmposite COnnection REinforcement), is based on inserts made by low-cost, high-value Additive Manufacturing (AM), which will enable a stronger connection between metal and PFR. The project covers the entire value chain of the innovative technology, from materials, design, manufacturing, testing and quality control, evaluating its potential on a use case and the great impact of its adoption. GIMCANA will also be developed consistent with Circular Economy principles, showing how a high-performance metal-PFR component can be achieved by using recycled carbon fibers for the latter, and performing a life cycle analysis (LCA). The project has a duration of 30 months.

X-rAI is a European co-funded project with a contribution of €1.148.723 by EIT Manufacturing. TEC Eurolab, together with other participants Volkswagen AG, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V., Loamics, Technische Universität Braunschweig and Tvarit GmbH, will be working on the optimization of the casting process by using X-ray inspection to determine product quality. 

The foundry industry is one of the most energy-intensive industries in Germany. Therefore, the optimization of the processes with a resulting reduction of production defects is essential for a sustainable development of the industry. One way to optimize the casting processes is the use of digital tools to identify the non-linear and multicriterial dependencies in the processes, which significantly complicate the optimization. To derive these non-linear and multicriterial dependencies data analysis tools to analyze the data from the production process and the data from quality inspections are necessary.