Estimation of the COVIMEP variation in a HCCI engine

Creative Commons License

Polat S., Solmaz H., Calam A., Yılmaz E.

Politeknik Dergisi, vol.23, no.3, pp.721-727, 2020 (ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 23 Issue: 3
  • Publication Date: 2020
  • Doi Number: 10.2339/politeknik.567865
  • Journal Name: Politeknik Dergisi
  • Journal Indexes: Emerging Sources Citation Index (ESCI), TR DİZİN (ULAKBİM)
  • Page Numbers: pp.721-727
  • Hakkari University Affiliated: Yes


In this study, variation of the COVIMEP was tried to be predicted by using the artificial neural network method for 4-stroke, 4-cylinder, direct injection and supercharged HCCI engine experimental data obtained by using n-heptane fuel at 60 oC intake airtemperature, 1000 rpm engine speed at different inlet air intake pressure. Intake air inlet pressure and lambda were used as inputdata in artificial neural network model. The COVIMEP value was used as the target. Three layers and five neurons were used toconstruct the network using the Levenberg-Marquardt algorithm. Correlation between targets and outputs for teaching, accuracyand testing were obtained as 0.97989, 0.9504 and 0.91644, respectively. Total correlation factor was found as 0.96983. As a resultof the study, it was seen that the stored data and the estimated COVIMEP data were compatible.