Istraživanje mogućnosti primjene neuronske mreže u dijagnostici četverotaktnog benzinskog motora pomoću sadržaja čestica trošenja

Lisjak, Dragutin and Marić, Gojko and Štefanić, Nedeljko (2012) Istraživanje mogućnosti primjene neuronske mreže u dijagnostici četverotaktnog benzinskog motora pomoću sadržaja čestica trošenja. = Studying the possibility of neural network application in the diagnostics of a small four-stroke petrol engine by wear particle content. Tehnički vjesnik : znanstveno-stručni časopis tehničkih fakulteta Sveučilišta u Osijeku, 19 (4). pp. 857-862. ISSN 1330-3651. Vrsta rada: ["eprint_fieldopt_article_type_article" not defined]. Kvartili JCR: Q3 (2012). Točan broj autora: 3.

[img]
Preview
Text
tv_19_2012_4_857_862.pdf - Published Version Jezik dokumenta:English

Download (1MB) | Preview
Official URL: http://hrcak.srce.hr/93559

Abstract

This paper presents the application of artificial neural network (ANN) in engine diagnostics. One-layer feed-forward neural network which is trained using a back-propagation algorithm that updates the weights and biases values according to Levenberg-Marquardt algorithm has been established to predict the Wear Particle Content (WPC) using the number of working hours of the motor engine as input parameter. The generalization property of the developed ANN is very high, which is confirmed by a very good match between the predicted and the targeted values on a new data set that was not included in the training data set.

Item Type: Article (["eprint_fieldopt_article_type_article" not defined])
Keywords (Croatian): Data sets; Engine diagnostics; Generalization properties; Input parameter; Levenberg-Marquardt algorithm; Motor engines; Neural network application; Petrol engine; Training data sets; Wear particles; Working hours; Backpropagation algorithms; Maintenance; Motors; Neural networks
Subjects: TECHNICAL SCIENCE
Divisions: 1000 Department of Materials > 1010 Chair of Materials and Tribology
700 Department of Industrial Engineering > 720 Chair of Production Control
Indexed in Web of Science: Yes
Indexed in Current Contents: No
Citations JCR: 0 (16.01.2018.)
Quartiles: Q3 (2012)
Citations SCOPUS: 0 (16.01.2018.)
Date Deposited: 30 Apr 2015 11:27
Last Modified: 16 Jan 2018 13:18
URI: http://repozitorij.fsb.hr/id/eprint/3883

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year