APPLYING NEURAL NETWORK IN COMPUTING FILLING COEFFICIENT OF FOUR-STROKE INTERNAL COMBUSTION ENGINE
Keywords:
neural network, supervised training, backpropagation, internal combustion engine, filling coefficientAbstract
Neural networks consist of many simple elements operating in parallel. In supervised training they are capable of finding their own solution to a particular problem, given only examples of proper behavior. It is a very useful method of solving complex, non-linear problems. The following article discusses the usage of artificial neural network to compute the value of filling coefficient of four-stroke internal combustion engines as the function of crankshaft rotational speed and throttle opening angle. The paper presents the idea of a static, two-layer feedforward network trained with the basic backpropagation algorithm in which the weights and biases are updated in the direction of the negative gradient. The article discusses network architecture and data structure, training parameters and result analysis.Downloads
References
Brzózka J., Dorobczyński L. 2008, Matlab. Środowisko obliczeń naukowo-technicznych. Wydawnictwo Naukowe PWN, Warszawa, ISBN 978-83-01-15459-2.
Rokosch U. 2007, Układy oczyszczania spalin i pokładowe systemy diagnostyczne samochodów OBD. Wydawnictwa Komunikacji i Łączności, Warszawa, ISBN 978-83-206-1657-6.
Serdecki W. 2001, Badania silników spalinowych: laboratorium. 2nd ed., Wydawnictwo Politechniki Poznańskiej, Poznań, ISBN 83-7143053-1.
Tadeusiewicz R. 1993, Sieci neuronowe. Akademicka Oficyna Wydawnicza, Warszawa 1993, ISBN 83-85769-03-X.
Zając P., Kołodziejczyk L. M. 2001, Silniki spalinowe. Wydawnictwa Szkolne i Pedagogiczne, Warszawa, ISBN 978-83-02-07987-0.
MathWorks, Neural network toolbox: user's guide (Release 2010b), 2010, http://www.mathworks.com/ (20.12.2010).
Downloads
Published
Issue
Section
License
Remember to download, sign, scan and attach the copyright notice
This file should be uploaded as a Supplementary file (Step 4) of the submission procedure.
