8 June 2026 – By Francesco Pagano, Project Coordinator at TEKNIKER
The future of lubricant design – the strategic role of AI and modelling
The lubricants industry is facing a convergence of challenges that is reshaping both product development and manufacturing strategies. Increasing regulatory scrutiny, growing sustainability expectations, and persistent uncertainty in global supply chains are placing new demands on how lubricants are designed. In this context, conventional formulation approaches based on empirical testing and incremental optimization are no longer sufficient. The integration of advanced simulation tools and artificial intelligence (AI) is emerging as a key enabler for a more predictive, efficient, and resilient development process.
Traditionally, lubricant formulation has relied on iterative laboratory work supported by accumulated expertise and standardised testing procedures. While robust, this approach requires significant time and resources and often limits the exploration of novel chemical spaces. Simulation methods, including molecular modelling and multiscale analysis, now provide the capability to predict the behaviour of candidate molecules under relevant operating conditions before synthesis. When combined with AI techniques capable of extracting patterns from large and diverse datasets, these tools support a transition toward predictive design. This allows the identification and optimization of promising formulations at early stages, reducing both development time and experimental burden.
At the same time, the European Commission is asking to the industry to start aligning with the principles of the Safe and Sustainable by Design (SSbD) framework, which calls for the integration of safety, environmental performance, and technical functionality from the outset of product development. This represents a significant shift from traditional practices, where such considerations were often addressed after performance targets had been achieved. AI and simulation tools play a central role in enabling this transition by allowing the assessment of properties such as toxicity, biodegradability, and environmental persistence at the molecular level. As a result, unsuitable chemistries can be excluded early, focusing development efforts on solutions that are inherently safer and more sustainable while remaining competitive in performance.
The ability to anticipate regulatory evolution has also become a critical factor. The pace at which chemical regulations are updated, particularly in regions with stringent environmental policies, increases the risk that certain substances may become restricted or obsolete. By integrating predictive modelling with knowledge of regulatory trends, it is possible to guide formulation strategies toward chemistries that are more likely to remain compliant over time. This proactive approach reduces the likelihood of costly reformulations and contributes to the long-term stability of product portfolios.
In parallel, AI-driven methodologies are expanding the way formulations are conceived. Instead of relying solely on known combinations of base oils and additives, machine learning models can explore broader design spaces and propose new molecular structures tailored to specific performance requirements. They also provide improved understanding of interactions between formulation components, enabling more efficient use of additives and reducing unnecessary complexity. This leads to formulations that are not only more targeted but also more resource-efficient.
Sustainability considerations are increasingly central to these developments. The need to reduce environmental impact across the entire lifecycle of lubricants, from raw material sourcing to end-of-life, requires careful balancing of multiple factors. Simulation and AI tools support this by enabling systematic evaluation of alternative feedstocks, including bio-based materials, and by facilitating lifecycle-based decision making. This makes it possible to identify solutions that meet environmental objectives without compromising technical performance.
In addition, recent disruptions in global supply chains have highlighted the importance of resilience. Dependence on geographically concentrated or critical raw materials exposes manufacturers to risks associated with geopolitical instability and resource scarcity. LCA can be used to analyze supply chain vulnerabilities and identify alternative sourcing strategies, while simulation tools ensure that potential substitutes meet required specifications. This integrated approach supports the design of formulations that are both robust and adaptable in a rapidly changing global context.
Overall, the integration of AI and advanced modelling is driving a transition toward a more predictive and integrated approach to lubricant development, in which safety, sustainability, performance, and supply security are addressed simultaneously from the earliest stages. Initiatives such as the SiToLub project are at the forefront of this transformation, developing platforms that embed AI and simulation capabilities specifically aimed at enabling SSbD formulation practices. By providing a structured and data-driven framework for lubricant design, such efforts are helping to define the future direction of the industry.