HyperCOG’s new coordinator, Beatriz Chicote of LORTEK, outlined the progress being made in the test phase of the project during a recent webinar, which took place on January 24th, 2022.
The clustering event brought together six projects involved in the SPIRE 2030 call “Digital technologies for improved performance in cognitive production plants” to explore the progress each is making towards the development of innovative approaches to cognitive production plants.
The projects joining HyperCOG – COGNIPLANT, Capri, COGNITWIN, Inevitable and FactLog – are each at the testing phase of their technology development. By sharing information about each approach, the projects are hoping to engage with manufacturers across the spectrum of size and processes and broaden their understanding of what technologies will best fit their individual needs.
Chicote began her talk by introducing HyperCOG’s innovative node architecture, which breaks from the traditional layered approach of the Reference Architectural Model Industrie 4.0 (RAMI 4.0) and enables every aspect of the manufacturing process to interact and communicate with each other in real time to aid intelligent decision making and cognitive systems and to provide interconnectivity and interoperability.
HyperCOG has developed 11 node types so far, which are being implemented in SIDENOR. These include:
• Acquisition nodes, which extract values and information from various devices being used in the process
• Collector nodes, which are used to collect historical data and statistical measurements from a database
• Recorder nodes, which are able to save the data and information collected on the other nodes
• Executor nodes, which support decision making, through algorithms or models, by using the data gathered from other nodes in the process. This node also integrates a Functional Mock-Up Interface (FMI) which allows for interoperability between the different algorithms developed in different environments.
• Human-machine interface nodes (HMI), which allows human-machine interaction for operating staff working on the process.
The HyperCOG nodes are designed to optimise the plant’s scheduled production process by automating how on-line production planning problems caused by unexpected events are solved, a job currently done by humans at the plant.
Chicote continued her presentation by explaining the current steel-making process at Sidenor and how the HyperCOG architecture is being applied.
The process, she explained is now carried out in several steps, starting with the raw material (scrap), through an electric arc furnace, then into a ladle before secondary metallurgy and grading, casting and then product formation. Planning the sequences of these stages is currently done offline by humans and determined by available heat and changing from one sequence to another leads to down time where production is stopped. Long sequences are therefore planned to minimise material processing time. Problems often occur during these stages, however, often due to quality requirements, and it becomes necessary to schedule on-line planning and these issues can often arise at the change of a sequence or in the middle of a sequence. It is necessary, therefore, to monitor the status of each stage of production to be able to make the necessary changes to the process online as each stage is related.
HyperCOG’s node architecture is now being used in this process to demonstrate how it can be optimised, solving both the offline and online production planning problems. The idea is to create a digital twin of the process to model effective interventions in real time.
There are now no layers. Instead, the information and data is gathered by several sensors and cameras along the process and, combined with historic data, dynamic models are created. The whole process is monitored by a human operator through the human-machine interfaces and the data and solution saved in the database. All the node actions are interconnected and able to interact with each other in the network and the digital twin of the process is created, which can be used to model interventions enabling the whole process to be controlled by advanced computational intelligence in real time.
A monitoring tool is being developed at the pilot scheme at SIDENOR which is being used to configure and verify this HyperCOG architecture. The tool allows the partners to monitor the state of the nodes, the communication between them and the data being collected. This enables the configuration of the nodes along the process and the creation of new nodes where necessary. Dynamic modelling of the process is underway and algorithms are being developed.
Chicote concluded by outlining the next phase of the project and how it will be applied across other industries. She explained that while this activity is focused on a large steel-making facility, the HyperCOG solution is flexible and can be adapted for any external system of any size, being modular and scalable. The project will now continue integrating the solution at SIDENOR and will start applying it at a chemical plant and a cement processing plant, using lessons learned at SIDENOR to adapt the architecture for the specific needs of those plants. This in turn will enable the development of effective, cyber-physical systems to be developed for across the industrial spectrum delivering process efficiency, cost savings and increased sustainability. The project is also developing suitable business models to enable industry to integrate HyperCOG technology into their processes.