In recent years, the manufacturing landscape has undergone a profound transformation driven by artificial intelligence. At the heart of this transformative shift are digital twins — sophisticated virtual replicas of real-world objects, systems and processes, enabling businesses to explore "what-if" scenarios and carry out performance analyses.
Digital twins have especially been used to manage operations of physical assets and processes to keep huge facilities, such as power plants and global manufacturing factories, running. To maximise the operability of digital twins to optimise workflows, digital twins need to be structured intuitively and more so, the relationships and the context between assets in systems and processes need to be established thoroughly.
Digital twins mirror systems and networks that include assets such as sensors, valves, pumps, and engines to show how they behave as they do in real life. The data from these real-world networks are processed and analysed by digital twins and these analytics are fed back into the networks. However, when it comes to extensive networks and systems, it becomes difficult to navigate the massive amounts of data and apply expert knowledge seamlessly across the digital system.
Imagine temperature sensors, air conditioning units, and radiators in a room. Mapping out this network is simple enough, where these temperature sensors are dependent on whether the AC and radiators in the room are turned on or off. What happens when you’d want to take this a step further, and automate temperature conditions so that anybody that walks in is comfortable? As humans, we would simply walk into a room and turn on the radiator if it feels cold, but automating this logic requires the incorporation of human reasoning into machines.
Rules-based AI or Knowledge Representation and Reasoning (KRR) establishes nuanced relationships and dependencies within and across systems and gives them context, just as humans do. The components and systems that connect them are represented within a knowledge graph and with the addition of a reasoning layer, these systems are enriched with context to automate expert knowledge.
In the context of the example above, KRR can account for the past readings of the sensor, its’ position in a room, the location of the room in a building, and other characteristics that normally isn’t established within a digital twin — giving meaning to every component within a network. With this, businesses can identify any problems within their systems with their established interconnectivity and elevate their operational maturity.
As the only enterprise-grade knowledge graph implementing rules-based AI, RDFox structures digital twins and offer context-aware intelligent insights in one go. RDFox carries out reasoning incrementally, making digital twins responsive to real-time changes in a dynamic environment. Born out of decades of University of Oxford research and already adopted by some of the world’s largest companies, RDFox is the solution that can be used now, later, and forever.
The team behind Oxford Semantic Technologies started working on RDFox in 2011 at the Computer Science Department of the University of Oxford with the conviction that flexible and high-performance reasoning was a possibility for data-intensive applications without jeopardising the correctness of the results. RDFox is the first market-ready knowledge graph designed from the ground up with reasoning in mind. Oxford Semantic Technologies is a spin-out of the University of Oxford and is backed by leading investors including Samsung Venture Investment Corporation (SVIC), Oxford Sciences Enterprises (OSE) and Oxford University Innovation (OUI).