Hybrid data fusion approach for fault diagnosis of fixed-axis gearbox

Abstract

Intelligent fault diagnosis system based on condition monitoring is expected to assist in the prevention of machine failures and enhance the reliability with lower maintenance cost. Most machine breakdowns related to gears are a result of improper operating conditions and loading, hence leads to failure of the whole mechanism. With advancement in technology, various gear fault diagnosis techniques have been reported which primarily focus on vibration analysis with statistical measures. However, acoustic signals posses a huge potential to monitor the status of the machine but a few studies have been carried out till now. This article describes the implementation of Teager–Kaiser energy operator and empirical mode decomposition methods for fault diagnosis of the gears using acoustic and vibration signals by extracting statistical features. A cross-correlation-based fault index that assists the automatic selection of the sensitive Intrinsic Mode Function (IMF) containing fault information has also been described. The features extracted by all combinations of signal processing techniques are sorted by order of relevance using floating forward selection method. The effectiveness is demonstrated using the results obtained from the experiments. The fault diagnosis is performed with k-nearest neighbor classifier. The results show that the hybrid of empirical mode decomposition–Teager–Kaiser energy operator techniques employs the advantages traits of one or the other technique to generate overall improvement in diagnosing severity of local faults.

Applications of machine learning to machine fault diagnosis: A review and roadmap

“…6, the majority label of the 𝑘𝑘 samples will be assign to the unlabeled sample as its predicted result. The kNN has been concerned in the research of IFD, especially for fault diagnosis of rolling element bearings [266][267][268][269][270][271][272][273], gears [274][275][276][277], and motors [278].…”

Learning Attention Representation with a Multi-Scale CNN for Gear Fault Diagnosis under Different Working Conditions

“…We fused these manual features at the feature level for improving the representation of the fault information. Then, we fed it into several classic machine learning classifiers [40][41][42][43][44][45] that are widely used in fault diagnosis tasks for comparison. The end-to-end model that we proposed in a previous work [34] used time and frequency signals as raw input signals to detect the gear fault patterns.…”

Data fusion approaches for structural health monitoring and system identification: Past, present, and future

“…Although the ANFIS method requires longer training time, it achieves comparable performances with the ANN and has higher interpretability over ANN. In Vanraj and Pabla, 168 the KNN classifier is used to perform fault diagnosis of a fixed-axis gearbox. Features extracted from the vibration and sound signals are fed into the KNN classifier to discriminate the normal and faulty conditions.…”