Search Results

Machine learning algorithms are effective tools to reduce the number of engine dynamometer tests during internal combustion engine development and/or optimization. This paper provides a case study of using such a statistical algorithm to characterize the heat transfer from the combustion chamber to the environment during combustion and during the entire engine cycle. The data for building the machine learning model came from a single cylinder compression ignition engine (13.3 compression ratio) that was converted to natural-gas port fuel injection spark-ignition operation. Engine dynamometer tests investigated several spark timings, equivalence ratios, and engine speeds, which were also used as model inputs. While building the model it was found that adding the intake pressure as another model input improved model efficiency.

Internal combustion diesel engines with optical access (a.k.a. optical engines) increase the fundamental understanding of combustion phenomena. However, optical access requirements result in most optical engines having a different in-cylinder geometry compared with the conventional diesel engine, such as a flat bowl-in-piston combustion chamber. This study investigated the effect of the bowl geometry on the flow motion and emissions inside a conventional heavy-duty direct-injection diesel engine that can operate in both metal and optical-access configurations. This engine was converted to natural-gas spark-ignition operation by replacing the fuel injector with a spark plug and adding a low-pressure gas injector in the intake manifold for fuel delivery, then operated at steady-state lean-burn conditions. A 3D CFD model based on the experimental data predicted that the different bowl geometry did not significantly affect in-cylinder emissions distribution.

Machine learning models were shown to provide faster results but with similar accuracy to multidimensional computational fluid dynamics or in-depth experiments. This study used a support-vector machine (SVM), a set of related supervised learning methods, to predict the dynamic performance (i.e., engine power and torque) of a heavy-duty natural gas spark ignition engine. The single-cylinder four-stroke test engine was fueled with methane. The engine was operated at different spark timings, mixture equivalence ratios, and engine speeds to provide the data for training and testing the proposed SVM. The results indicated that the performance and accuracy of the built regression model were satisfactory, with correlation coefficient quantities all larger than 0.95 and root-mean-square errors close to zero for both training and validation datasets.

Natural gas is a promising alternative gaseous fuel due to its availability, economic, and environmental benefits. A solution to increase its use in the heavy-duty transportation sector is to convert existing heavy-duty compression ignition engines to spark-ignition operation by replacing the fuel injector with a spark plug and injecting the natural gas inside the intake manifold. The use of numerical simulations to design and optimize the natural gas combustion in such retrofitted engines can benefit both engine efficiency and emission. However, experimental data of natural gas combustion inside a bowl-in-piston chamber is limited. Consequently, the goal of this study was to provide high-quality experimental data from such a converted engine fueled with methane and operated at steady-state conditions, exploring variations in spark timing, engine speed and equivalence ratio.

Natural gas (NG) is an alternative fuel for spark-ignition engines. In addition to its cleaner combustion, recent breakthroughs in drilling technologies increased its availability and lowered its cost. NG consists of mostly methane, but it also contains heavier hydrocarbons and inert diluents, the levels of which vary substantially with geographical source, time of the year and treatments applied during production or transportation. To investigate the effects of NG composition on engine performance and emissions, a 3D CFD model of a heavy-duty diesel engine retrofitted to NG spark ignition simulated lean-combustion engine operation at low speed and medium load conditions. The work investigated three NG blends with similar lower heating value (i.e., similar energy density) but different Methane Number (MN). The results indicated that a lower MN increased flame propagation speed and thus increased in-cylinder pressure and indicated mean effective pressure.