SAE Technical Paper Series 2003
DOI: 10.4271/2003-01-0354
|View full text |Cite
|
Sign up to set email alerts
|

Nonlinear Analysis of Combustion Engine Vibroacoustic Signals for Misfire Detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0
9

Year Published

2004
2004
2021
2021

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 19 publications
(18 citation statements)
references
References 8 publications
0
9
0
9
Order By: Relevance
“…In the area of nonlinear methods [21,23,26] the research showed that the Lyapunov exponents can be considered as the good diagnostic parameter. The dominant Lyapunov exponents were higher for the case of misfire.…”
Section: Experiments Measurements and Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…In the area of nonlinear methods [21,23,26] the research showed that the Lyapunov exponents can be considered as the good diagnostic parameter. The dominant Lyapunov exponents were higher for the case of misfire.…”
Section: Experiments Measurements and Resultsmentioning
confidence: 99%
“…Together with classical Fourier methods, some other more sophisticated methods were used also (short-time analysis, nonlinear methods, wavelets and multiresolution analysis) [8,[21][22][23][24][25][26][27][28].…”
Section: Experiments Measurements and Resultsmentioning
confidence: 99%
“…Jak do tej pory eksperymenty w zakresie monitorowania uszkodzeń i zaburzeń pracy silnika na bazie sygnałów wibroakustycznych zostały przeprowadzone z wykorzystaniem wielu metod analizy sygnałów, w tym obliczanie globalnych statystycznych parametrów takich jak średnia, mediana, odchylenie standardowe itp., analiza nieliniowa z wykorzystaniem metod teorii chaosu deterministycznego, analiza krótkoczasowa, metodę maszyn wektorów wspierających SVM (ang. Support Vector Machines) [2,3,4,5,6,7,8,9,10]. Z praktycznego punktu wodzenia chodzi o znalezienie takich parametrów, które mogą być wprost zastosowane do diagnostyki on-line.…”
Section: Wstępunclassified
“…The choice of false criterion for FNN was performed by using the method described in Chapter 3. The eventually obtained threshold value was usually about 17 [10,11,22]. For signals obtained by Gould recorder the time-delay value was in the range t=12-14 (where t=12.78), and the embedding dimension d ¼ 526 (where d=5.5).…”
Section: Choice Of Time Delay and Embedding Dimensionmentioning
confidence: 99%