Abstract Currently applied on-board diagnostic systems enable to find a simple defect if it exceeds the boundary values. If the damage does not exceed such values, measured with the use of intermediate values, which are the criteria for the assessment of exhaust fumes emission, such damage may remain unidentified by the imperfect model of the system. Preliminary tests show that some mechanical damages even over the admissible sizes do not constitute the basis for the reaction of the diagnostic system. At present, failure symptoms found in the signal, are more and more often studied with the aid of artificial intelligence methods. The major issue referred to in the literature related to methods of artificial intelligence is the method for creating the data used in the process of neural network operations. The ability to set up models is the guarantee for a successful classifying process using neural networks. The paper presents an attempt of detecting disturbances in the ignition system by measuring the engine block accelerations and noise based on these, building patterns for radial artificial neural networks (Radial Basis Function – RBF).
Diagnosing of Disturbances in the Ignition System by Vibroacoustic Signals and Radial Basis Function – Preliminary Research
01.01.2011
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
internal combustion engines , artificial neural networks , diagnostics , on-board diagnostics Computer Science , Computer Communication Networks , Information Systems Applications (incl. Internet) , Information Storage and Retrieval , Database Management , Algorithm Analysis and Problem Complexity , Management of Computing and Information Systems
British Library Conference Proceedings | 2011
|VIBROACOUSTIC DIAGNOSING OF DISTURBANCES IN THE CAR IGNITION SYSTEM BY AMPLITUDE ESTIMATES
DOAJ | 2014
|Diagnosing priori unknown faults by radial basis function neural network
Tema Archiv | 2000
|Construction of fuzzy radial basis function neural network model for diagnosing prostate cancer
BASE | 2021
|