This paper presents engine gearbox fault diagnosis based on empirical mode decomposition (EMD) and Naïve Bayes algorithm. In this study, vibration signals from a gear box are acquired with healthy and different simulated faulty conditions of gear and bearing. The vibration signals are decomposed into a finite number of intrinsic mode functions using the EMD method. Decision tree technique (J48 algorithm) is used for important feature selection out of extracted features. Naïve Bayes algorithm is applied as a fault classifier to know the status of an engine. The experimental result (classification accuracy 98.88%) demonstrates that the proposed approach is an effective method for engine fault diagnosis.

Purpose Bearings and gears are major components in any rotatory machines and, thus, gained interest for condition monitoring. The failure of such critical components may cause an increase in down time and maintenance cost. Condition monitoring using the machine learning approach is a conceivable solution for the problem raised during the operation of the machinery system. The paper aims to discuss these issues. Design/methodology/approach This paper aims engine gearbox fault diagnosis based on a decision tree and artificial neural network algorithm. Findings The experimental result (classification accuracy 85.55 percent) validates that the proposed approach is an effective method for engine gearbox fault diagnosis. Originality/value This paper attempts to diagnose the faults in engine gearbox based on the machine learning approach with the combination of statistical features of vibration signals, decision tree and multi-layer perceptron neural network techniques.

No abstract

This paper presents an experimental investigation on damage detection of internal combustion (IC) engine gear box using conventional vibration spectrum and cepstrum analysis. Experiment was carried out on two stroke internal combustion engine gearbox without considering the combustion. Vibration signals were collected for healthy as well as defective gear condition. The signals were analysed in time domain, frequency domain and cepstrum plots for fault detection. An experimental result demonstrates the dynamic behaviour in frequency domain, which is dominated by gear mesh frequency (GMF) and its harmonics.Based on the experimental results obtained, spectrum and cepstrum analysis can be effectively used for fault prediction of machine components.