Learning-Based Decision Making for Combustion Phasing Control in Multi-Fuel CI Engines with Latent Fuel Reactivity Estimation
arXiv:2606.18393v1 Announce Type: cross Abstract: Multi-fuel compression-ignition engines offer fuel flexibility but introduce uncertain, time-varying fuel reactivity, represented by cetane number (CN), which complicates cycle-to-cycle combustion-phasing control. This work formulates CA50 regulation under latent CN variation as a partially observable sequential decision problem and systematically evaluates controllers with increasing temporal and representational capacity, including LinUCB, history-augmented contextual bandits, observation-only DDPG, recurrent DDPG, and a proposed GRU-guided R
The increasing complexity of internal combustion engine control, particularly with multi-fuel strategies, necessitates advanced AI/ML solutions for optimizing performance and efficiency under variable conditions.
This research demonstrates how AI can manage dynamic and uncertain variables in complex mechanical systems, potentially leading to more efficient and adaptable engine designs critical for various industrial and transportation applications.
The ability to accurately estimate and manage latent fuel reactivity in real-time through learning-based methods could significantly improve the performance, emissions, and fuel flexibility of compression-ignition engines.
- · AI/ML researchers
- · Engine manufacturers
- · Automotive industry
- · Heavy industry utilizing CI engines
- · Traditional control system designers (without AI integration)
- · Less fuel-flexible engine technologies
Improved fuel efficiency and reduced emissions in multi-fuel CI engines through advanced combustion control.
Accelerated adoption of AI-driven control systems across other complex mechanical and energy systems facing similar uncertainty challenges.
Reduced reliance on single-fuel infrastructure due to enhanced adaptability of multi-fuel engines, contributing to energy resilience.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI