The Fraunhofer Institute for Microstructure of Materials and Systems IMWS in Halle (Saale), Germany, is collaborating with six partners to develop intelligent algorithms and digital methods that support the development and production of customized rubber compounds optimized for specific industrial applications. The project’s goal is to create software that uses mixing and processing data to generate accurate predictions and optimization strategies for rubber compound manufacturing.
From Experience-Based Production to Data-Driven Optimization
Traditionally, the formulation and process design of new rubber compounds have relied heavily on expert experience and trial-and-error methods, which often limit quality control and slow product innovation. To address these challenges, Fraunhofer IMWS and its partners have launched the “InSuKa” project, which aims to combine databases on formulation, processing, and post-processing with predictive tools powered by intelligent algorithms.
This solution provides early guidance on optimal formulations and processing conditions, simplifying and accelerating the development and manufacturing of rubber products. The project also aims to establish industrial data standards for process and material documentation, leading to the creation of a powerful predictive tool for optimizing both material performance and production efficiency.
AI-Driven Research and Process Analysis
Fraunhofer IMWS contributes its expertise in evaluating and optimizing rubber compounds through internal mixing systems of various sizes (1.5 L and 5 L) at its rubber mixing laboratory in Schkopau. Researchers systematically analyze the relationships between processing conditions, compound formulations, and final material properties to develop optimized rubber compound recipes.
Special attention is given to new analytical methods for quantifying multi-scale filler dispersion in tire tread compounds. The institute employs advanced imaging techniques across different length scales, supported by AI-based image analysis, to obtain reliable insights into how formulation and processing adjustments affect compound characteristics.
Through real-time data collection, quantitative dispersion analysis, and AI-driven interpretation, the project integrates all relevant parameters—such as processing data, filler distribution, and compound properties—into a comprehensive intelligent system. This approach paves the way for a new generation of data-driven rubber formulation technologies, boosting efficiency and sustainability in the rubber industry.