The objective of this research is to diagnose an inaccessible rolling bearing by indirect vibration measurement. In this study, a shaft supported with several bearings is considered. It is assumed that the vibration for at least one bearing is not recordable. The purpose is to diagnose inaccessible bearing by the recorded data from the sensors located on the other bearings. To achieve this goal, the continuous wavelet transform is used to detect weak signatures in the available vibration signals. A new criterion for adjusting the scale parameter of continuous wavelet transform is proposed based on the amplitude of the bearing characteristic frequencies. In this criterion, the optimal scale is selected to maximize the amplitude of bearing characteristic frequencies in comparison with the amplitude of the other frequencies. The results of the proposed method are compared with a popular method, energy-to-entropy ratio criterion, using two different sets of run-to-failure experimental data. Results indicate that the proposed method in this article is more effective and efficient for extracting the weak signatures and diagnosing inaccessible bearings from the recorded vibration signals.
Intelligent fault classification of rolling element bearings (REBs) using machine learning (ML) techniques increases the reliability of industrial assets. One of the main issues associated with ML model development is the lack of training data and, most importantly, the ability of models
to be used for applications without specific training data, ie the generalisation capability of models. This study investigates the feasibility of using multinomial logistic regression (MLR) as generalised ML models for rolling element bearing fault classification without the requirement of
training data for new bearing designs and varied machine operations. This has been achieved by using bearing characteristic frequencies (BCFs) as inputs to the MLR models extracted by a newly developed hybrid method. The new method combines cepstrum pre-whitening (CPW) and full-band enveloping,
which can effectively identify the BCFs in vibration data from various machines. This paper presents the methods of the feature extraction and the development of generalised ML models for REBs based on data from the EU Clean Sky 2 I2BS project1. This model is then validated
by data from Case Western Reserve University (CWRU) and the Society for Machinery Failure Prevention Technology (MFPT), available in the public domain without further training.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.