Most factory machines cannot talk to each other, and this project builds the digital wiring to make them communicate in real time. Manufacturing plants today are filled with a mix of old and new equipment, often running on incompatible software from different vendors. This creates a "shop floor to top floor" data gap: production machines cannot feed information directly into business planning systems. The result is wasted time, energy, and materials. This project tackles three specific barriers: the lack of technical standards that would let devices from different makers work together, cybersecurity risks when connecting legacy equipment to the internet, and the difficulty of extracting useful data from older machines that were never designed to share it. If successful, the research will produce a tested toolkit for rapidly connecting factory equipment using open standards rather than expensive proprietary systems. This would allow manufacturers—especially small and medium-sized ones—to adopt artificial intelligence and data analytics without costly custom integration. The potential impact is a step change in industrial productivity: factories that can adjust production in real time, reduce energy use, and cut waste, all without replacing their existing machinery.
View original technical description
Public description Industrial Digital Technologies (IDT's) are disrupting industries across the globe. The breadth and depth of these changes herald the transformation of entire systems of production, management, and governance. There is overwhelming evidence that IDTs can provide a step change in industrial productivity(2). The Smart Connected Factory is central to this goal; it will alter the way production is performed based on smart connected machines/ devices but also smart products. However, the application of these technologies at scale presents many challenges, and there are few examples of Smart factories which provide full real-time data integration from the 'shop floor to the top floor '. These factories tend to operate with single vendor propriety technologies or have undertaken significant investment in creating bespoke integration of multi-vendor solutions. Such approaches are costly to develop and maintain and prevent continuous open innovation. The application of these technologies at scale still presents many challenges such as lack of standards creating technical interoperability issues, cyber threats, high number of legacy assets and constrained devices limiting data exploitation opportunities This proposal delivers solutions for shop floor connectivity including legacy devices, analytics, and integration with the Manufacturing Execution layer of the ISA-95 architecture. It demonstrates how through rapidly maturing and fusing IDT through proof of value projects solutions can be scaled quickly to realise real productivity improvement. It addresses 3 broad innovation challenges :- 1. How to address the technical barriers to IDT introduction? Addressing the challenge of merging IT and OT. In industry 4.0 these entities must act as one to exploit technologies such as AI/ ML, big data etc. 2. How to rapidly mature and deploy IDT to match the exponential pace at which it is being developed? Demonstrate a rapid open innovation methodology to co create IDT solutions tailored for complex Industrial environments based on the 3 key tenets of Invent:- Focus on Open Innovation / design thinking and shared development of common solutions Incubate:- Focuses on the rapid prototyping of solutions to demonstrate Proof of Value Industrialise:- Understanding the route to scale utilizing 4 key methods of Design thinking, Design Sprints, Lean experiments and agile delivery. 3. How to leverage standards to innovate at pace by removing vendor 'lock out' due to the use of proprietary standards? The goal is to develop an Interoperability & standards road map in recognition of the role standards play in accelerating innovation and deployment. (2)made_smarter_review
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know