UMP Institutional Repository

Prediction of Marine Diesel Engine Performance by Using Artificial Neural Network Model

C. W., Mohd Noor and R., Mamat and G., Najafi and Mohd Hafizil, Mat Yasin and C. K., Ihsan and M. M., Noor (2016) Prediction of Marine Diesel Engine Performance by Using Artificial Neural Network Model. Journal of Mechanical Engineering and Sciences (JMES) , 10 (1). pp. 1917-1930. ISSN 2289-4659 (print); 2231-8380 (online)

[img]
Preview
PDF
Prediction of Marine Diesel Engine Performance by Using Artificial Neural Network Model.pdf
Available under License Creative Commons Attribution.

Download (812kB) | Preview

Abstract

This study deals with an artificial neural network (ANN) modelling of a marine diesel engine to predict the output torque, brake power, brake specific fuel consumption and exhaust gas temperature. The input data for network training was gathered from engine laboratory testing running at various engine speeds and loads. An ANN prediction model was developed based on a standard back-propagation Levenberg–Marquardt training algorithm. The performance of the model was validated by comparing the prediction data sets with the measured experiment data and output from the mathematical model. The results showed that the ANN model provided good agreement with the experimental data with a coefficient of determination (R2) of 0.99. The prediction error of the ANN model is lower than the mathematical model. The present study reveals that the artificial neural network approach can be used to predict the performance of a marine diesel engine with high accuracy

Item Type: Article
Uncontrolled Keywords: Artificial neural network; marine diesel engine; engine performance
Subjects: T Technology > TJ Mechanical engineering and machinery
Faculty/Division: Faculty of Mechanical Engineering
Depositing User: Mrs. Neng Sury Sulaiman
Date Deposited: 08 Nov 2016 03:24
Last Modified: 21 Sep 2018 07:12
URI: http://umpir.ump.edu.my/id/eprint/14441
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item