A semi-empirical model for online real-time control of NO X generation in diesel engines

Abstract

Diesel NO_X emission control is the main control content of diesel engines. Real-time high-precision NO_X emission prediction model is the basic guarantee for (1) Diesel combustion management, (2) SCR after-treatment control, (3) OBD system. Existing models that rely exclusively on physical processes or data-driven artificial intelligence models fail to meet real-time requirements, while MAP look-up table-based models are poorly adapted and require extensive experiments for calibration. In this study, a new semi-empirical model for NO_X emission prediction was developed, and the variables of the model were identified as exhaust temperature, engine speed, injected fuel mass flow rate, air intake mass flow rate, and exhaust oxygen mass flow rate, taking into account the mechanism of NO_X generation in diesel engines as well as the requirement of real-time and direct measurability of the variables for on-line control. The influence of each variable on NO_X was analyzed, the model structure of the NO_X prediction model was determined, and the parameters of the prediction model were identified by least squares. The model is applied to real operating vehicles for validation and compared with a previous semiempirical model taken from the literature, and the results show that the overall accuracy of the proposed model is improved. Finally, the effect of variable uncertainty on the proposed model was assessed and it was found that the relative uncertainty in predicting NO_X emissions ranged between 0 and 8% for sensor accuracies of $\pm 0.75\%$ and $\pm 1\%$ for exhaust temperature and intake air mass flow, respectively, suggesting that the sensor accuracy has a significant effect on the uncertainty of the model.