5G has been built on the foundation of innovation and creativity. Since its inception, 5G has been continuously investing in research and technology to build "alpha" (that removes technology risks) and "beta" (that removes commercial risks) prototypes of new and innovative technologies in the areas of digital automation. As part of the alpha research initiatives, 5G has recently entered into a research collaboration with Durham University and University of Northumbria - two leading universities in the UK.
The research with Durham University is in the area of Machine Learning of Process/Production Monitoring Rules. The research study focuses on generation of an automated rule base for the adoption of predictive and preventative maintenance, in order to achieve Reliability Excellence within an organization. This includes research on the application of AI techniques such as model based reasoning and/or learning algorithms for achieving context sensitive rule generation from real time production data.
The research with University of Northumbria shall deliver "energy optimised" production continuously, and in real time, in manufacturing enterprises by integrating : (a) a technique for real time predictive fault identification in equipment from power quality measurements and (b) amethodology for real time abstraction of the raw values of process variables in a manufacturing enterprise. By connecting to the individual pieces of equipment in order to capture the dynamics of process variables on one side, and correlating the process values with an independent real time measurement of the power quality on the other, a central "intelligent" controller will continuously create opportunities (through "learning") to optimise energy consumption for meeting the production demand. The potential energy saving that shall be realised from early identification and rectification of equipment faults while they are still operational (preceding a failure) is a very useful by-product of this technology, while the core mandate would concentrate on tracking the minima for energy consumption for every unit of the product produced by the manufacturing enterprise.