Tire wear is one of the largest sources of microplastics in the environment, yet it has long remained difficult to measure accurately under real-world conditions. Project KI-RAM is changing that. By combining smart sensor technology with artificial intelligence, the initiative enables continuous monitoring of tire abrasion directly during vehicle operation. Among the project partners is DENKweit an startup alumni of the SpinLab. Together with research institutions and industry partners, the company contributes advanced data analytics and AI expertise to help make tire wear measurable, predictable, and ultimately reducible.
When vehicles drive, small particles are continuously worn off from their tires. These particlescomposed of synthetic rubber and additives are classified as microplastics. They accumulate in soil and water systems and are transported via runoff into rivers and oceans. In Germany alone, estimates suggest that tire wear contributes tens of thousands of tons of microplastics annually. Despite its environmental relevance, tire abrasion has traditionally been assessed using standardized road tests or laboratory simulations. While useful, these approaches cannot fully replicate real-life driving conditions, where variables such as road surface, temperature, tire pressure, load, and driving behavior significantly influence wear rates.
Tire wear results from a complex interaction of mechanical, environmental, and behavioral variables. Capturing this complexity requires more than isolated measurements. Project KI-RAM therefore integrates a retrofit-capable sensor embedded in the tire tread with advanced AI-based analytics. The sensor continuously measures changes in tread depth during operation, generating real-time data directly from the road. This data is then combined with contextual information such as vehicle dynamics and environmental conditions and analyzed using machine learning models.
Artificial intelligence enables the system to identify patterns within this multidimensional dataset and calculate precise wear trends. Instead of relying on generalized assumptions, KI-RAM provides context-specific forecasts of remaining tire life. This marks a transition from static testing toward dynamic, data-driven evaluation under real operating conditions.
Project KI-RAM brings together expertise from applied research, industry, and startups:
This interdisciplinary collaboration demonstrates how research institutions and agile technology companies can jointly develop scalable solutions for environmental challenges.
The continuous measurement of tire wear under real-world conditions creates tangible advantages across the value chain. Fleet operators can optimize maintenance planning, reduce unexpected downtime, and avoid premature tire replacement. Data-based insights enable more efficient resource use while lowering operational costs.
For tire manufacturers, real-world performance data offers valuable feedback for material development and product optimization. Instead of relying solely on laboratory environments, design decisions can be informed by operational insights.
More reliable measurement methods may also support policymakers and regulatory bodies in developing evidence-based environmental standards for non-exhaust emissions such as tire abrasion.