Nonlinear Stochastic Model Predictive Control with Generative Uncertainty in Homogeneous Charge Compression Ignition

TL;DR

This paper presents a nonlinear stochastic model predictive control method for homogeneous charge compression ignition engines that explicitly models uncertainty distributions, improving combustion stability and load tracking.

Contribution

It introduces a novel control approach that incorporates learned uncertainty models and distribution-based cost functions for robust engine control.

Findings

Achieved over 28% reduction in combustion phasing variation.

Improved load tracking accuracy by more than 26%.

Demonstrated effectiveness of distribution-level performance metrics.

Abstract

This work addresses the challenge of ignition timing and load control in homogeneous charge compression ignition engines operating subject to uncertainty from complex combustion dynamics and external disturbances. To handle this issue, we propose a nonlinear stochastic model predictive control approach explicitly incorporating distributional information of uncertainties. Specifically, we integrate an uncertainty model learned from empirical residual data to capture realistic probabilistic characteristics and handle the nonlinear additive uncertainty propagation within the prediction horizon based on polynomial chaos expansion. Additionally, we introduce a novel cost function based on maximum mean discrepancy, enabling direct penalization of the discrepancy between predicted and desired distributions of combustion indicators. The simulation results demonstrate that our proposed method achieves over a 28 \% reduction on combustion phasing variation and more than a 26 \% improvement in load tracking accuracy compared to traditional nonlinear and Gaussian-based predictive control strategies. These findings indicate the effectiveness of explicitly modeling uncertainty distributions and highlight the advantages of distribution-level performance index in robust combustion control.