Please use this identifier to cite or link to this item: https://dspace.upt.ro/xmlui/handle/123456789/3822
Title: Knock detection based on neural networks [articol] /
Authors: Lăzărescu, Dan
Ungureanu, Mihaela G.
Subjects: Neural networks
Features extraction
Hopfield algorithm
Knock detection
Issue Date: 2004
Publisher: Timişoara : Editura Politehnica
Citation: Lăzărescu, Dan. Knock detection based on neural networks. Timişoara: Editura Politehnica, 2004
Series/Report no.: Buletinul ştiinţific al Universităţii „Politehnica” din Timişoara, România. Seria electronică şi telecomunicaţii, Tom 49(63), fasc. 1 (2004), p. 253-255
Abstract: The paper presents a new method for knock detection based on two neural networks. First a discrete Hopfield network extracts features from the structural vibration signal. Then the first and the forth coefficients of the autoregressive model and the maximal and minimal value of the signal are applied to a feedforward neural network in order to detect the knock. Once a cycle has been detected as a knock containing one, for the next cycle the engine can be protected in order to avoid further appearances of knock. For the feedforward neural network it was experimentally determined that four neurons in the hidden layer is the best solution for the knock detection.
URI: http://primo.upt.ro:1701/primo-explore/search?query=any,contains,Knock%20detection%20based%20on%20neural%20networks&tab=default_tab&search_scope=40TUT&vid=40TUT_V1&lang=ro_RO&offset=0 Link Primo
Appears in Collections:Articole științifice/Scientific articles

Files in This Item:
File Description SizeFormat 
BUPT_ART_Lazarescu_f.pdf335.08 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.