Homogeneous charge compression ignition has the potential to significantly reduce NO _x emissions, while maintaining a high fuel efficiency. Homogeneous charge compression ignition is characterized by compression-induced autoignition of a lean homogeneous air–fuel mixture. Combustion timing is highly dependent on the in-cylinder state including pressure, temperature and trapped mass. To control homogeneous charge compression ignition combustion, it is necessary to have an accurate representation of the gas exchange process. Currently, microprocessor-based engine control units require that the gas exchange process is linearized around a desired operating point to simplify the model for real-time implementation. This reduces the models’ ability to handle disturbances and limits the flexibility of the model. However, using a field programmable gate array, a detailed simulation of the physical gas exchange process can be implemented in real time. This paper outlines the process of converting physical governing equations to an offline zero-dimensional gas exchange model. The process used to convert this model to a field programmable gate array capable model is described. This model is experimentally validated using a single cylinder research engine with electromagnetic valves to record real-time field programmable gate array gas exchange results and comparing to the offline zero-dimensional physical model. The field programmable gate array model is able to accurately calculate the cylinder temperature and cylinder mass at 0.1 °CA intervals during the gas exchange process for a range of negative valve overlaps, boost conditions and engine speeds making the model useful for future real-time control applications.

The internal combustion engine faces increasing societal and governmental pressure to improve both efficiency and engine out emissions. Currently, research has moved from traditional combustion methods to new highly efficient combustion strategies such as Homogeneous Charge Compression Ignition (HCCI). However, predicting the exact value of engine out emissions using conventional physics-based or data-driven models is still a challenge for engine researchers due to the complexity the of combustion and emission formation. Research has focused on using Artificial Neural Networks (ANN) for this problem but ANN’s require large training datasets for acceptable accuracy. This work addresses this problem by presenting the development of a simple model for predicting the steady-state emissions of a single cylinder HCCI engine which is created using an metaheuristic optimization based Support Vector Machine (SVM). The selection of input variables to the SVM model is explored using five different feature sets, considering up to seven engine inputs. The best results are achieved with a model combining linear and squared inputs as well as cross correlations and their squares totaling 26 features. In this case the model fit represented by R² values were between 0.72 and 0.95. The best model fits were achieved for CO and CO₂, while HC and NO_x models have reduced model performance. Linear and non-linear SVM models were then compared to an ANN model. This comparison showed that SVM based models were more robust to changes in feature selection and better able to avoid local minimums compared to the ANN models leading to a more consistent model prediction when limited training data is available. The proposed machine learning based HCCI emission models and the feature selection approach provide insight into optimizing the model accuracy while minimizing the computational costs.

In this paper, a deep neural network (DNN)-based nonlinear model predictive controller (NMPC) is demonstrated using real-time experimental implementation. First, the emissions and performance of a 4.5-liter 4-cylinder Cummins diesel engine are modeled using a DNN model with seven hidden layers and 24,148 learnable parameters created by stacking six Fully Connected layers with one long-short term memory (LSTM) layer. This model is then implemented as the plant model in an NMPC. For real-time implementation of the LSTM-NMPC, an open-source package acados with the quadratic programming solver HPIPM (High-Performance Interior-Point Method) is employed. This helps LSTM-NMPC run in real time with an average turnaround time of 62.3 milliseconds. For real-time controller prototyping, a dSPACE MicroAutoBox II rapid prototyping system is used. A Field-Programmable Gate Array is employed to calculate the in-cylinder pressure-based combustion metrics online in real time. The developed controller was tested for both step and smooth load reference changes, which showed accurate tracking performance while enforcing all input and output constraints. To assess the robustness of the controller to data outside the training region, the engine speed is varied from 1200 rpm to 1800 rpm. The experimental results illustrate accurate tracking and disturbance rejection for the out-of-training data region. At 5 bar indicated mean effective pressure and a speed of 1200 rpm, the comparison between the Cummins production controller and the proposed LSTM-NMPC showed a 7.9% fuel consumption reduction, while also decreasing both nitrogen oxides (${\mathrm{NO}}_{\mathrm{x}}$) and Particle Matter (PM) by up to 18.9% and 40.8%.

Homogeneous charge compression ignition is a part-load combustion method, which can significantly reduce oxides of nitrogen (NO _x) emissions compared to current lean-burn spark ignition engines. The challenge with homogeneous charge compression ignition combustion is the high cyclic variation due to the lack of direct ignition control. A fully variable electromagnetic valve train provides the internal exhaust gas recirculation through negative valve overlap which is required to obtain the necessary thermal energy to enable homogeneous charge compression ignition. This also increases the cyclic coupling as residual gas and unburnt fuel is transferred between cycles through exhaust gas recirculation. To improve combustion stability, an experimentally validated feed-forward water injection controller is presented. Utilizing the low latency and rapid calculation rate of a field programmable gate array, a real-time calculation of residual fuel mass is implemented on a prototyping engine controller. Using this field programmable gate array–based calculation, it is possible to calculate the amount of fuel and the required control interaction during an engine cycle. This controller prevents early rapid combustion following a late combustion cycle using direct water injection to cool the cylinder charge and counter the additional thermal energy from any residual fuel that is transferred between cycles. By cooling the trapped cylinder mass, the upcoming combustion phasing can be delayed to the desired setpoint. The controller was tested at several operating points and showed an improvement in the combustion stability as shown by a reduction in the standard deviation of combustion phasing and indicated mean effective pressure.

One promising approach to reduce carbon foot print of internal combustion engines (ICEs) is using alternative fuels like hydrogen, particularly by converting medium and heavy-duty diesel engines to dual-fuel hydrogen-diesel engines. To minimize elevated NOx emissions from hydrogen-fueled engine, fast and accurate emission models are essential for engine model-based control and for engine calibration and optimization using hardware-in-the-loop (HIL) setups. In this study, a fast-response NOx emissions sensor is used to measure the transient NOx emissions from a dual-fuel hydrogen-diesel engine. Subsequently, steady-state models (SSMs), quasi steady-state models (QSSMs), and transient sequential models (TSMs) in the form of black-box (BB) and gray-box (GB) models are developed for transient NOx emissions prediction. GB models utilize both information from a one dimensional (1D) physical engine model and experimental data for training, while BB models only use experimental data. SSMs are optimized artificial neural networks (ANNs) trained using steady-state data, QSSMs are optimized ANNs trained using transient data, and TSMs are time-series networks trained using transient data. Long short-term memory (LSTM) and gated recurrent unit (GRU) networks are used as the time-series deep learning networks. The results showed that the 1D physical model has the poorest performance with successive model performance improvement from SSM to QSSM and from QSSM to TSM. The developed BB TSM model in this study can predict transient NOx emissions with an R² value greater than 0.96 at 89,000 predictions per second which makes this model suitable for real-time engine model-based control where computational efficiency is crucial. The developed GB TSM model can predict transient NOx emissions with an R² value greater than 0.97 but it is computationally more expensive. The extra accuracy of the GB TSM models makes them the best choice for HIL setups where more computational power is available, and accuracy is more crucial.