Technology Record - Issue 31: Winter 2023

Manufacturing operations generate vast amounts of data at every step in the process, from the design of products to the performance of assembly lines. It is, therefore, a vast challenge to make sense of this data – turning it into actionable insights that will benefit the business. Significant advances in two areas of technology – digital twins and AI – in manufacturing is releasing some of the constraints that firms faced when trying to use data effectively. “Manufacturers are no strangers to using data in everyday processes and procedures, but often the data is constrained to specific systems or processes – either physically or digitally,” says Simon Floyd, Microsoft’s general manager of manufacturing and mobility in the Americas. “This situation often hinders the manufacturer’s ability to use the data across processes or functions where it has the potential to have the largest impact. “With the rise of generative AI tools, manufacturers are now presented with advanced capabilities that utilise natural language interactivity with the combined knowledge of private and public data sources. This provides an entirely new way of interacting with data and creating content that is easy to use. “The power of the digital twin as the organisational principle for enterprise data is undeniable. By creating a virtual replica of any product, process or machine, manufacturers can simulate specific outcomes and understand their current or future performance. This enables users to train machine learning models to predict failures in specific types of equipment, assess their future performance, and provide opportunities for optimisation and autonomous decision-making.” Floyd notes that the main benefit for designers who are creating new products or engineers looking to optimise operations is that they will have the ability to analyse data with context, create prediction-based outcomes and simulate different scenarios to ensure an optimal solution. “Digital twins can take several forms, and one of the most effective examples we see from leading customers are data-based knowledge graphs,” says Floyd. “These graphs use nodes to represent interactions between different assets or factories, providing a clear and organised way to visualise and understand the relationships and dependencies within a manufacturing system.” By using knowledge graphs, manufacturers can gain visibility and insights into their products or operations in real time. “This approach allows manufacturers to break down data silos and gain a holistic view which leads to improved efficiency and performance,” says Floyd. Generative AI tools can help manufacturers gain deeper insights from data via a conversational interface – accelerating new design and production options – thereby improving industrial processes and achieving a faster time to market. “The use of AI in manufacturing Microsoft’s Simon Floyd explains how the combined power of digital twins and artificial intelligence is helping manufacturers to yield multiple benefits, from reducing waste to improving safety BY RICHARD HUMPHREYS INDUSTRIALS & MANUFACTURING 99