The potential of artificial intelligence (AI) application for prediction of internal combustion engine performance is assessed in this paper. A literature survey on this subject is first reviewed, in which previous researches utilized the advance of artificial neural networks (ANN) as one type of AI. Previous works commonly obtained the data from experimental engine tests. Under the same engines, they varied the fuel compositions or the engine operating conditions. Whereas in this study, an ANN model is developed to calculate the inputs from an engine simulation software package database and to predict the engine performance based on the simulation software outputs as the ANN target outputs. Results from the ANN model in the “learning” step indicates good agreement with the software simulation outputs. Improvement and development of the program are required, including optimation of the ANN model architecture, such as the choice of activation function, the number of neurons in the hidden layer, and the number of iterations, as well as the number and option of input engine parameters. The ANN model seems promising to predict engine performance, with root mean square errors in the range of 0.4-1.8%.
Keywords: Artificial Intelligence; Neural Networks; Engine Performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.