Artificial Intelligence in Tribology: Design of new dispersants using artificial intelligence tools

CAMPILLO, NURIA E.; TALAVANTE, PABLO; PONZONI, IGNACIO; SOTO, AXEL JUAN; MARTÍNEZ, MARÍA JIMENA; NAVEIRO, ROÍ; GOMEZ-ARRAYAS, RAMÓN; FRANCO, MARIO; MARINAS, VÍCTOR; REVILLA LOPEZ, GUILLERMO; BERNABEI, MARCO

Conferencia; 23rd International Colloquium Tribology; 2022

Dispersants are the main additives in oils and lubricants to help keep engines clean and free of deposits. These polymeric surfactant-like molecules are characterized by at least one hydrophobic, oil soluble ?tail? polymer backbone component, often polyisobutylene (PIB), and at least one hydrophilic, polar ?head? unit that adsorbs onto the carbon deposit precursors (mainly sludge soot particles). An efficient dispersant design requires tailoring the nature of the chemical interactions to meet the performance characteristics of a particular engine, for which a number of parameters need to be fine-tuned. Despite the knowledge available, the chemistry for production of dispersants in use today remains limited. Therefore, there is plenty of room for innovation.The design of dispersants is typically carried out through trial and error, coupled with chemical intuition, but this process is expensive and time-consuming. In sharp contrast, artificial intelligence (AI) has the potential to guide the design of next generation materials, allowing both economic and time savings. Herein we describe a machine learning framework oriented to dispersant design and optimization. Two complementary strategies were developed based on unsupervised and supervised learning, nonlinear dimensionality reduction methods and data visualization approaches. This computational framework allows predicting performance properties of new dispersants as part of virtual screening strategies to identify the most promising candidates.