NTT DATA and lift truck manufacturer, Hyster-Yale Materials Handling, have announced a breakthrough application of physical AI that embeds intelligence directly into manufacturing processes, leveraging sensor data to enable machines and systems to perceive, understand and act in realtime within real-world operations.
Bringing this capability into practice introduces AI-driven quality assurance directly into HYMH’s manufacturing operations. This co-developed approach represents a first-of-its-kind use case of how physical AI can be applied in an industrial assembly environment by embedding intelligence into production workflows, helping to safeguard that products are built to consistently high standards.
NTT DATA designed and developed the solution at HYMH’s manufacturing facility in Berea, KY, integrating vision sensors, edge AI that processes data on-site and advanced analytics into a critical assembly workflow.
With manufacturing contributing approximately 13% to South Africa’s GDP and supporting more than 1,6-million jobs, the sector remains vital to the country’s economic growth. As manufacturers accelerate their digital transformation efforts, Physical AI offers new opportunities to improve quality, productivity, and operational resilience by embedding intelligence directly into manufacturing processes.
“Physical AI is helping manufacturers move beyond traditional automation by embedding intelligence directly into production environments,” says Vinesh Maharaj, director: Smart Manufacturing at NTT DATA South Africa. “This collaboration shows how AI can deliver measurable improvements in quality, productivity and operational performance, while accelerating the adoption of Industry 4.0 across South Africa’s manufacturing sector.”
Together with partner Archetype AI, NTT DATA, in collaboration with HYMH, adapted a physical AI model that analyses assembly activity against expected production steps, validating that all parts are installed and that assembly stages are completed, flagging deviations before the product moves to the next stage. By validating quality throughout the assembly process, the solution helps identify and address potential issues before products leave the factory floor.
This initiative demonstrates a step-change in how AI can be applied in manufacturing environments.
Combined with edge computing, the solution can run locally so all processing happens on-site, enabling faster rollout and quicker time-to-value. Early results showed that physical AI cuts deployment timelines from months to weeks when compared with legacy techniques, accelerating adoption and iteration across manufacturing operations.
“Our confidence in physical AI continues to grow, and we’re starting to see the countless benefits that AI can bring to our global manufacturing operations,” says Barbara Binda, director of Global Manufacturing Innovation at Hyster-Yale Materials Handling. “Working with NTT DATA allows us to leverage how physical AI can help our production teams maintain high-quality standards and deliver the most reliable products to our clients.”
Shahid Ahmed, global head of Edge Services at NTT DATA, adds: “This deployment shows what physical AI looks like in real production environments, not as a concept, but with tangible impact on the factory floor. By combining real production data with physical AI models at the edge, we’re helping leading manufacturers like HYMH deliver high-quality products, support frontline workers, and apply AI in ways that deliver real-world outcomes.”