COGNITIVE PLANTS THROUGH PROACTIVE SELF-LEARNING HYBRID DIGITAL TWINS

COGNITIVE PLANTS THROUGH PROACTIVE SELF-LEARNING HYBRID DIGITAL TWINS

While the concept of digitalisation and Industry 4.0 is making rapid inroads into the European manufacturing sector, there are several aspects that can be still incorporated into the system which can strengthen the goal of optimal process operations. One such aspect to the digitalisation vision is the "cognitive element", where the process plants can learn from historical data and adapt to changes in the process while also being able to predict unwanted events in the operation before they happen. Through this project, COGNITWIN (Cognitive digital Twin), we aim to add the cognitive element to the existing process control systems and thus enabling their capability to self-organise and offer solutions to unpredicted behaviours. To achieve the objectives of the project, we have partnered with six industries and seven research groups from seven European nations, each of whom will bring their expertise in data analytics and pattern recognition which are going to be at the heart of the COGNITWIN solution platform. The set-up of the platform includes a sensor network that will continuously monitor and collect data from various plant processes and assets which will be stored at a database. This data will be used to develop a digital twin of the process and will also be used to develop models with cognitive capability for self-learning and predictive maintenance which will lead towards optimal plant operations. The project builds on ideas and technologies that have been validated in controlled environments (TRL 5) to arrive at prototype demonstrations in operational environments (TRL 7). The COGNITWIN project results will be implemented to our industrial partner's processes to demonstrate the transition from TRL 5 to TRL 7. TRL – Technology Readiness Level