Search Results

Predicting and preventing combustion anomalies leads to safe and efficient operation of the hydrogen internal combustion engine. This research presents the application of three machine learning (ML) models – K-Nearest Neighbors (KNN), Random Forest (RF) and Logistic Regression (LR) – for the prediction of combustion anomalies in a hydrogen internal combustion engine. A small experimental dataset was used to train the models and posterior experiments were used to evaluate their performance and predicting capabilities (both in operating points -speed and load- within the training dataset and operating points in other areas of the engine map). KNN and RF exhibit superior accuracy in classifying combustion anomalies in the training and testing data, particularly in minimizing false negatives, which could have detrimental effects on the engine.

Economy decarbonization will be one of the main goals for the following years. Research efforts are being focused on reducing carbon-based emissions, by increasing the efficiency of the transport power plants while developing new fuel production methods that reduce the environmental footprint of the refinement process. Consequently, the depletion of conventional fuels derived from petroleum with high carbon content, such as gasoline and diesel, motivated the development of propulsive alternatives for the transportation sector. In this paradigm, methane (CH4) fuel appears as a mid-term solution due to its low carbon content, if compared with traditional fuels, and the low CO2 emissions during its production from renewable sources. However, the intrinsic properties of methane compromise the combustion process, subsequently increasing the emission of CO2.

In order to face the new challenges, spark ignition engines are evolving by following some strategies and technologies. Among them, alternative combustion processes based on the dilution of the homogeneous mixture, either with fresh air or with Exhaust Gas Recirculation (EGR), are being explored. In a higher or lower extent, these changes modify in-cylinder thermodynamic conditions during the engine operation (pressure, temperature and gas composition) thus conditioning the spark ignition system requirements that will have to evolve to become more reliable and powerful. In this framework, an experimental study on the effect of the key in-cylinder conditions on the ignition system performance has been carried out in a single-cylinder spark-ignition (SI) research engine. The study includes EGR, lambda and energizing time sweeps to assess the behavior of the engine in different operating conditions.