MODELLING ANALYSIS OF MULTIPLE DIESEL INJECTION STRATEGIES WITH ONE-DIMENSIONAL SIMULATION COUPLED WITH ARTIFICIAL NEURAL NETWORKS


Creative Commons License

Özener O., Özkan M., Yüksek L.

THERMAL SCIENCE, cilt.21, sa.1, ss.413-425, 2017 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 21 Sayı: 1
  • Basım Tarihi: 2017
  • Doi Numarası: 10.2298/tsci160504223o
  • Dergi Adı: THERMAL SCIENCE
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.413-425
  • Anahtar Kelimeler: Diesel engine, combustion, 1-D modeling, neural networks, emissions, EXHAUST EMISSIONS, FUEL CONSUMPTION, ENGINE, PERFORMANCE, PARAMETERS, COMBUSTION, RECIRCULATION
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

In the modern Diesel injection systems the phasing of injection in the same cycle gives a high flexibility to engineers from the perspective of engines performance and emission optimization. Basically, the injection is separated in to three phases: the pilot, main, and post injection phases. The focus of this study is based on pilot injection strategy implementation, which can be used for emission control effectively. In this work, reference main and pilot + main injection strategy experiments were realized in a modern Diesel engine. The logged data groups were used to model the engine at 1-D thermodynamic simulation AVL BOOST. In the second stage of this work, the engine operating points which are not realized at test bench are made run at BOOST programme. The new model parameters of simulation are identified with artificial neural network technique. The results showed that the implementation of appropriate mass of pilot injection at the appropriate injection advance will reduce the NO, emissions compared to reference main injection strategy. For reducing CO emissions the pilot injection mass should also be kept in the same range with higher injection pressure that can be achieved. Usage of 1-D simulation programme coupled with artificial neural network was found useful up to a certain extent especially for parametric analyses and optimization problems via with validation of calibration parameters at a huge experimental data.