Free digital report focuses on FAIR data principles, simulation and interoperable data systems as artificial intelligence moves into lubricant research and product development.

Artificial intelligence is beginning to influence lubricant formulation, tribology research and product development, but the quality and compatibility of industry data may determine how quickly those tools can deliver reliable results.

A new special report from the Society of Tribologists and Lubrication Engineers examines how digitalization, simulation-driven engineering and FAIR data principles—making data findable, accessible, interoperable and reusable—can provide the foundation for artificial-intelligence and machine-learning applications in tribology.

The report, Building the Foundation for Artificial Intelligence in Tribology, is available as a free digital download at stle.org/aitribology. It includes contributions from experts across the industry, including original equipment manufacturers.

Building a Stronger Data Foundation

The report focuses on a practical opportunity for the lubricants industry: improving how technical data is collected, documented, structured and used so that artificial-intelligence and machine-learning tools can produce more reliable and useful results.

Tribology generates large volumes of valuable information through laboratory testing, lubricant development, equipment monitoring, field performance and simulation. Bringing more consistency and interoperability to those data environments could allow researchers and companies to compare results more efficiently, identify patterns more quickly and accelerate product-development work.

FAIR principles—developed in the research and data-science communities and increasingly applied in industrial settings—provide a framework for that effort. Data that is findable, accessible under appropriate controls, interoperable and reusable can be applied more effectively than information stored in isolated systems, inconsistent formats or poorly documented records.

The emphasis on accessibility does not necessarily mean making proprietary information public. Rather, it can include creating data systems that allow authorized users and tools to locate, understand and reuse information while maintaining appropriate confidentiality, security and commercial protections.

For lubricant formulators, additive companies, OEMs, testing laboratories and equipment-condition-monitoring specialists, the report offers a forward-looking message: decisions made now about how data is collected, stored, governed and shared will influence the capabilities available to the industry as AI technologies continue to mature.

Why This Matters Now

The current combination of supply disruption, changing base-oil availability and increasingly demanding lubricant specifications adds urgency to the issue. As blenders qualify alternative base oils, reformulate products and respond to new OEM requirements, the ability to move more efficiently through development, validation and testing cycles has direct commercial value.

AI-assisted formulation, simulation, predictive testing and equipment-condition analysis could help shorten those timelines, improve the use of existing technical knowledge and support more informed decision-making. Realizing those benefits, however, will depend on having data that is sufficiently organized, documented and compatible for reliable use.

“As AI and ML move from concept to practice in our industry, the data foundation we build today will determine how much value we can unlock tomorrow,” said STLE Executive Director Rebecca Lintow. “This report gives our members a clear, practical roadmap for adopting FAIR data principles now, so they’re ready to lead as these technologies mature.”