Prediction of emissions and exhaust temperature for direct injection diesel engine with emulsified fuel using ANN

Creative Commons License

Kökkülünk G., Akdoğan E., Ayhan V.

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.21, ss.2141-2152, 2013 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 21
  • Basım Tarihi: 2013
  • Doi Numarası: 10.3906/elk-1202-24
  • Dergi Adı: TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED)
  • Sayfa Sayıları: ss.2141-2152
  • Anahtar Kelimeler: Neural networks, emulsified fuel, diesel engine emissions, back propagation, radial basis function, ARTIFICIAL NEURAL-NETWORK, PERFORMANCE, CONSUMPTION
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

Exhaust gases have many effects on human beings and the environment. Therefore, they must be kept under control. The International Convention for the Prevention of Pollution from Ships (MARPOL), which is concerned with the prevention of marine pollution, limits the emissions according to the regulations. In Emission Control Area (ECA) regions, which are determined by MARPOL as ECAs, the emission rates should be controlled. Direct injection (DI) diesel engines are commonly used as a propulsion system on ships. The prediction and control of diesel engine emission rates is not an easy task in real time. Therefore, in this study, an artificial neural network (ANN) structure using the back propagation (BP) learning algorithm and radial basis function (RBF) has been developed to predict the emissions and exhaust temperature for DI diesel engines with emulsified fuel. In order to show the ANN performance, the network outputs and experimental results of the BP and RBF have been compared in this paper. The experimental results were obtained from a real diesel engine. The results showed that the emissions and exhaust temperature were estimated with a very high accuracy by means of the designed neural network structures and the RBF is more reliable than the BP.