Search

The opportunities of impedance-based condition monitoring for rolling bearings have been shown earlier by the authors: Changes in the impedance signal and the derived features enable the detection of pitting damages. Localizing and measuring the pitting length in the raceway direction is possible. Furthermore, the changes in features behavior are physically explainable. These investigations were focused on a single bearing type and only one load condition. Different bearing types and load angles were not considered yet. Thus, the impedance signals and their features of different bearing types under different load angles are investigated and compared. The signals are generated in fatigue tests on a rolling bearing test rig with conventional integrated vibration analysis based on structural borne sound. The rolling bearing impedance is gauged using an alternating current measurement bridge. Significant changes in the vibration signals mark the end of the fatigue tests. Therefore, comparing the response time of the impedance can be compared to the vibration signal response time. It can be shown that the rolling bearing impedance is an instrument for condition monitoring, independently from the bearing type. In case of pure radial loads, explicit changes in the impedance signal are detectable, which indicate a pitting damage. Under combined loads, the signal changes are detectable as well, but not as significant as under radial load. Damage-indicating signal changes occur later compared to pure radial loads, but nevertheless enable an early detection. Therefore, the rolling bearing impedance is an instrument for pitting damage detection, independently from bearing type and load angle. [ABSTRACT FROM AUTHOR]

The engineering challenge of rolling bearing condition monitoring has led to a large number of method developments over the past few years. Most commonly, vibration measurement data are used for fault diagnosis using machine learning algorithms. In current research, purely data-driven deep learning methods are becoming increasingly popular, aiming for accurate predictions of bearing faults without requiring bearing-specific domain knowledge. Opposing this trend in popularity, the present paper takes a more traditional approach, incorporating domain knowledge by evaluating a variety of feature engineering methods in combination with a random forest classifier. For a comprehensive feature engineering study, a total of 42 mathematical feature formulas are combined with the preprocessing methods of envelope analysis, empirical mode decomposition, wavelet transforms, and frequency band separations. While each single processing method and feature formula is known from the literature, the presented paper contributes to the body of knowledge by investigating novel series connections of processing methods and feature formulas. Using the CWRU bearing fault data for performance evaluation, feature calculation based on the processing method of frequency band separation leads to particularly high prediction accuracies, while at the same time being very efficient in terms of low computational effort. Additionally, in comparison with deep learning approaches, the proposed feature engineering method provides excellent accuracies and enables explainability. [ABSTRACT FROM AUTHOR]

Condition monitoring of technical systems has increasing importance for the reduction of downtimes based on unplanned breakdowns. Rolling bearings are a central component of machines because they often support energy-transmitting elements like shafts and spur gears. Bearing damages lead to a high number of machine breakdowns; thus, observing these has the potential to reduce unplanned downtimes. The observation of bearings is challenging since their behavior in operation cannot be investigated directly. A common solution for this task is the measurement of vibration or component temperature, which is able to show an already occurred bearing damage. Measuring the electrical bearing impedance in situ has the ability to gather information about bearing revolution speed and bearing loads. Additionally, measuring the impedance allows for the detection and localization of damages in the bearing, as early research has shown. In this paper, the impedance signal of five fatigue tests is investigated using individual feature selection. Additionally, the feature behavior is analyzed and explained. It is shown that the three different bearing operational time phases can be distinguished via the analysis of impedance signal features. Furthermore, some of the features show a significant change in behavior prior to the occurrence of initial damages before the vibration signals of the test rig vary from a normal state. [ABSTRACT FROM AUTHOR]

Rolling bearings are frequently subjected to high stresses within modern machines. To prevent bearing failures, the topics of condition monitoring and predictive maintenance have become increasingly relevant. In order to efficiently and reliably maintain rolling bearings in a predictive manner, an estimate of the remaining useful life (RUL) is of great interest. The RUL prediction quality achieved when using machine learning depends not only on the selection of the sensor data used for condition monitoring, but also on its preprocessing. In particular, the execution of so-called feature engineering has a major impact on prediction quality. Therefore, in this paper, various methods of feature engineering are presented based on rolling–bearing endurance tests and recorded structure-borne sound signals. The performance of these methods is evaluated in the context of a regression-based RUL model. Furthermore, the way in which the quality of RUL prediction can be significantly improved is demonstrated, by adding further processed, time-considering features. [ABSTRACT FROM AUTHOR]