Data-driven Control with Real-time Uncertainty Compensation for Multi-Fuel Engines
Researchers have developed a new data-driven control framework for multi-fuel compression ignition (CI) engines to address challenges in achieving consistent combustion phasing. The system utilizes Gaussian Process Regression (GPR) to model engine behavior and incorporates a real-time uncertainty compensation mechanism. This approach allows for dynamic adaptation of control inputs to mitigate deviations caused by modeling inaccuracies and varying operating conditions, with theoretical guarantees for finite-time convergence. AI
IMPACT This research could lead to more efficient and adaptable engine control systems by leveraging AI for real-time uncertainty compensation.