Detailed Program of the 22nd ISC 2024
Predicting Compatibility of Sealing Material with Bio-Hybrid Fuels: Development and Comparison of Machine Learning Methods
Summary
Bio-hybrid fuels, derived from sustainable raw materials and green energies, offer a promising alternative to conventional fuels made of mineral oil. An advantage of bio-hybrid fuels over other alternative energy sources, such as fuel cells or electrical energy, is the use of existing infrastructure. If bio-hybrid fuels are used as so called “drop-in fuels” in existing combustion engines, a worldwide network of filling stations and petrochemical industry production sites can be used.
Within the cluster of excellence “The Fuel Science Center” at RWTH Aachen bio-hybrid fuels are investigated on a holistic level. Methods are developed to optimize fuel properties, which posts another benefit compared to fossil fuels. One property that is addressed is the compatibility with sealing material. Previous time-consuming experimental investigations revealed that many bio-hybrid fuels show poor material compatibility with conventional elastomer sealing materials (e.g. NBR & FKM) leading to issues such as volume expansion, hardness alteration, or chemical reactions upon immersion. These incompatibilities could result in catastrophic failures during practical applications.
Due to the high number of possible fuels, fuel-mixtures and therefore fuel/seal combinations a solely empirical approach is impractical. Consequently, machine learning methods have been chosen to predict material compatibility. Based on existing experimental data and fluid properties, an analysis of correlation is conducted to identify significant parameters influencing compatibility. Subsequently, machine learning methods suitable for this approach are selected and applied. Their results are compared and discussed critically with particular attention to the limited amount of experimental data. This method aims to assist experimental investigation by previously reducing the number of fuel/seal combinations, thereby minimizing experimental expenses.