Search

The increasing demand for vehicles is leading to a rise in pollutant emissions across the world. This decline in air quality is significantly impacting public health, with internal combustion engines being a major contributor to this concerning trend. Ever-stringent regulations demand high engine efficiency and reduced pollutant emissions. Therefore, every automobile company requires rigorous methods for accurately estimating engine emissions. The implementation of advanced technologies, including machine learning methods, has proven to be a promising solution. The present work aims to develop an artificial intelligence-based model to estimate the pollutant emissions produced by an internal combustion engine under varying operating conditions. Experimental activities have been conducted on a single-cylinder spark ignition research engine with gasoline port fuel injection under both stationary and dynamic operating conditions. This work explores different artificial intelligence architectures and compares their performance in order to determine the best approach for the presented task. These structures have been trained and tested based on data obtained from the engine control unit and fast emission analyzer. The main target is to evaluate the possibility of applying the presented artificial intelligence predictive model as an on-board virtual tool in the estimation of emissions in real driving conditions.

The automotive industry is increasingly challenged to develop cleaner, more efficient solutions to comply with stringent emission standards. Hydrogen (H2)-powered internal combustion engines (ICEs) offer a promising alternative, with the potential to reduce carbon-based emissions and improve efficiency. However, hydrogen combustion presents two main challenges related to the calibration process: emissions control and measurement of the air excess coefficient (λ). Traditional lambda sensors struggle with hydrogen’s combustion dynamics, leading to potential inefficiencies and increased pollutant emissions. Consequently, the determination of engine performance could also be compromised. This study explores the feasibility of using machine learning (ML) to replace physical lambda sensors with virtual ones in hydrogen-fueled ICEs. The research was conducted on a single-cylinder spark-ignition (SI) engine, collecting data across a range of air excess coefficients from 1.6 to 3.0. An advanced hybrid model combining long short-term memory (LSTM) networks and convolutional neural networks (CNNs) was developed and fine-tuned to accurately predict the air–fuel ratio; its predictive performance was compared to that obtained with the backpropagation (BP) architecture. The optimal configuration was identified through iterative experimentation, focusing on the neuron count, number of hidden layers, and input variables. The results demonstrate that the LSTM + 1DCNN model successfully converged without overfitting; it also showed better prediction ability in terms of accuracy and robustness when compared with the backpropagation approach.

Hydrogen fuel is gaining particular attention in internal combustion engines. In addition to zero-carbon emissions, major advantages relate to its combustion characteristics, which allow a significant increase in thermal efficiency under ultra-lean operation and with very low NOx levels. The ignition system is one of the main technology enablers, as it determines the capability to control ultra-lean operations, avoid backfire phenomena, and/or reduce the risks of abnormal combustions. The latter results from hydrogen’s low ignition energy and it is associated with factors like high-temperature residuals, hot spots, and irregular spark plug discharge. The ACIS gen 2-Barrier Discharge Igniter excels in accelerating the initial flame growth speed by the generation of non-equilibrium low-temperature plasma, a strong ignition promoter for the combined action of kinetic and thermal effects. Moreover, its volumetric discharge facilitates combustion initiation on a wide region, in contrast to the localized ignition of traditional spark systems. In this work we present for the first time, to the best of our knowledge, experimental results showing the performance of a hydrogen engine with a low-temperature plasma discharge. Tests were conducted on a single-cylinder research engine, achieving ultra-lean conditions with cycle-to-cycle variability results below 2.5%. The analysis indicates that the H2-BDI combined solution is capable of accelerating the evolution of the flame front compared to traditional spark plugs, leading to a significant reduction in the cycle-to-cycle variability. A meticulous adjustment of the BDI control parameters further enhances igniter performance and contributes to a deeper understanding of the innovative approach proposed in this study.