Research Papers: Fuel Combustion

Artificial Neural Network Prediction of Diesel Engine Performance and Emission Fueled With Diesel–Kerosene–Ethanol Blends: A Fuzzy-Based Optimization

[+] Author and Article Information
Subrata Bhowmik, Durbadal Debroy, Abhishek Paul

Department of Mechanical Engineering,
Agartala, Tripura 799046, India

Rajsekhar Panua

Department of Mechanical Engineering,
Agartala, Tripura 799046, India
e-mail: rajsekhar_panua@yahoo.co.in

1Corresponding author.

Contributed by the Internal Combustion Engine Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received August 30, 2016; final manuscript received January 6, 2017; published online February 24, 2017. Assoc. Editor: Stephen A. Ciatti.

J. Energy Resour. Technol 139(4), 042201 (Feb 24, 2017) (10 pages) Paper No: JERT-16-1352; doi: 10.1115/1.4035886 History: Received August 30, 2016; Revised January 06, 2017

The present study explores the impact of ethanol on the performance and emission characteristics of a single cylinder indirect injection (IDI) Diesel engine fueled with Diesel–kerosene blends. Five percent ethanol is added to Diesel–kerosene blends in volumetric proportion. Ethanol addition to Diesel–kerosene blends significantly improved the brake thermal efficiency (BTE), brake specific energy consumption (BSEC), oxides of nitrogen (NOx), total hydrocarbon (THC), and carbon monoxide (CO) emission of the engine. Based on engine experimental data, an artificial neural network (ANN) model is formulated to accurately map the input (load, kerosene volume percentage, ethanol volume percentage) and output (BTE, BSEC, NOx, THC, CO) relationships. A (3-6-5) topology with Levenberg–Marquardt feed-forward back propagation (trainlm) is found to be optimal network than other training algorithms for predicting input and output relationship with acceptable error. The mean square error (MSE) of 0.000225, mean absolute percentage error (MAPE) of 2.88%, and regression coefficient (R) of 0.99893 are obtained from the developed model. The study also attempts to make clear the application of fuzzy-based analysis to optimize the network topology of ANN model.

Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Complete engine experimental setup

Grahic Jump Location
Fig. 2

Variation of BTE with blends

Grahic Jump Location
Fig. 3

Variation of BSEC with blends

Grahic Jump Location
Fig. 4

Variation of NOx emission with blends

Grahic Jump Location
Fig. 5

Variation of THC emission with blends

Grahic Jump Location
Fig. 6

Variation of CO emission with blends

Grahic Jump Location
Fig. 7

General configuration of ANN model

Grahic Jump Location
Fig. 8

(a) and (b) Variation of MSE with number of neurons

Grahic Jump Location
Fig. 9

Overall R values of developed trainlm

Grahic Jump Location
Fig. 10

(a) and (b) Comparison of ANN-predicted BTE with measured BTE

Grahic Jump Location
Fig. 11

(a) and (b) Comparison of ANN-predicted BSEC with measured BSEC

Grahic Jump Location
Fig. 12

(a) and (b) Comparison of ANN-predicted NOx with measured NOx

Grahic Jump Location
Fig. 13

(a) and (b) Comparison of ANN-predicted THC with measured THC

Grahic Jump Location
Fig. 14

(a) and (b) Comparison of ANN-predicted CO with measured CO

Grahic Jump Location
Fig. 15

Membership functions for MPCI

Grahic Jump Location
Fig. 16

Fuzzy rule for membership function for MPCI




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In