Surveillance intelligente des défauts d'un compresseur d'air bassé sur les signaux acoustiques

Abstract

Abstract This thesis includes a literature review on acoustic signal analysis, the main faults of internal combustion engines, an explanation of the most commonly used signal processing techniques for diagnostics, and an introduction to classification methods using pattern recognition. Then, it presents a detailed description of the database used for our work, followed by the classification results using the SVM method to diagnose air compressor faults. The thesisconcludeswith a general conclusion.