Skip to main content
European Commission logo
English English
CORDIS - EU research results
CORDIS
CORDIS Web 30th anniversary CORDIS Web 30th anniversary

Hyperconnected Architecture for High Cognitive Production Plants

Periodic Reporting for period 3 - HyperCOG (Hyperconnected Architecture for High Cognitive Production Plants)

Reporting period: 2022-03-01 to 2023-08-31

EU manufacturing companies are facing increasingly competitive and dynamic markets. To compete in the modern world, companies in the process industry need highly flexible manufacturing environments, capable of continuously adapting to changing conditions by means of advanced technologies and decision-making processes that take advantage of big data in real-time. Enterprises need to harness the knowledge held within their data streams to become more energy and resource efficient while improving safety and lowering their environmental impact.

The HyperCOG project aims to show that cyber-physical systems (CPS) and data analytics can be used to drive transformation within the European process industry, improving efficiency and competitiveness by harnessing the power of data.

The CPS architecture developed by HyperCOG enables the concept of cognitive manufacturing, combining cognitive computing techniques (such as artificial intelligence), the Industrial Internet of Things, and advanced data analytics to optimise manufacturing processes.

HyperCOG architecture has been validated in three use cases of process industry (steel, cement and chemical) showing benefits in terms of environmental aspects (reduction of waste, CO2, and raw materials mainly) and productivity. Transferability of the solutions has also been demonstrated to other industries such as glass manufacturing. Training for workers helped the adoption of the solution.
The HyperCOG project initially identified the existing state-of-the-art digital solutions in smart manufacturing to develop the HyperCOG elements, including frameworks for suitable use cases, assure ethical, legal, privacy and security requirements as well as Cyber-Physical System architecture concepts. Based on the requirements obtained, the design and development of an innovative Industrial Cyber-Physical System based on a intercommunicated network of digital nodes was performed and validated in industrial production. This system is defined as a composition of nodes running in devices that communicate with each other without hierarchical layers or the requirement of neither gateways nor message brokers. So, this innovative approach, starting from the Reference Architecture Model for Industry 4.0 (RAMI 4.0) breaks down with the traditional hierarchical information systems, given the hyperconnecting capabilities. Through this system, the nodes can acquire outstanding streams of data in real-time, which together with the high computing capabilities, provide sensing, knowledge and cognitive reasoning, making companies robust in the face of variant scenarios. For this, a set of nodes have been developed, in order to be able to acquire information in real time from data provided by a physical sensor connected to a PLC or other acquisition device or system, collect historic data, record data, compute models or algorithms or check the status of the system, among others. For that a middleware has been use to abstract the communications in a distributed system, as a CPS, composed of several connected devices. Also, a standard Functional Mock up Interface has been implemented to be able the interoperability between the different software languages that can be part of the algorithm models developed.

HyperCOG is deeply grounded in the last advances in AI such as modelling for twin factories, decision-support systems for human-machine interaction. As a first step, industrial data was collected, in order to investigate data analysis methods that distill knowledge hidden in the data and make it usable for optimizing processes that occur in the three use cases (steel, cement and chemical). Models and optimization algorithms have been developed for the production planning optimization of the use cases. A monitoring tool has been developed with the aim of monitoring the acquired data, analysing the correct communication between the different nodes or the status of these nodes, reporting logs with the indication of possible mistake, showing them in a colour scale in function of the level of the error. Also, with this tool it is possible to verify the value of data and to estimate the correct operation of the system. Additionally, a blockchain tool for supply chain management and traceability has been developed to use steel manufacturing waste as raw material in cement manufacturing site. LCA concept was integrated in the HyperCOG solution by developing Dynamic LCA approach and a LCA node that was tested as a proof-of-concept in the steel use case.

The human perspective was integrated by identifying the existing competence gaps in the workers, creating ad-hoc training content and training a total of 20 workers in the three sites. Moreover, training material on CPS for Master degree students was prepared.

The following KPIs were obtained:
-Steel use case: reduction of 14% waste, 3,752 ton CO2 and 189 ton of raw materials
-Cement use case: reduction of 2,8 tons/h water, 1,69 kWh/ ton energy, and 2.820 ton CO2
-Chemical use case: use of 50% less solvent

As a result 2 market-ready key exploitable results were obtained (A software suite for implementing industrial cyber-physical system, blockchain tool for supply chain management and traceability), which were included in the Innovation Radar, plus an additional exploitable result (hyperspectral camera system for white slags chemical characterization). A business plan has been defined for them.

Several dissemination activities were carried out: 15 papers published, 15 workshops/conferences/fairs, 5 films, 14 newsletters, presence in magazines and press, 461 followers in social media, and clustering activities.
The project provided the following results:

1. Development of a platform that converts manufacturing industries into more flexible environments
2. Implementation of advanced data analytics for extracting knowledge from production databases
3. Development of a decision support system to make the best possible decision in a specific situation.
4. Leverage cybersecurity concerns about cyber-physical systems and Internet of Things devices as a business enabler
5. Development of strategies for training and re-skilling human resources.
6. Integration of LCA aspects in the software architecture

Potential impacts:

As a result of the implementation of its technical objectives, HyperCOG contributes to the digitalisation of process industry towards better productivity and less environmental impact. Society will get profit of this project not only throughout the environmental impact, but through the lifelong learning of workers and vocational training for digitisation.
Solvay drift detection dashboard: if green values turn into red, there is a drift
Node configurator by MSI: each small box is a node and each arrow is a connection between nodes