In this work, effective methods for monitoring friction and wear of journal bearings integrated in future UltraFan^® jet engines containing a gearbox are presented. These methods are based on machine learning algorithms applied to Acoustic Emission (AE) signals. The three friction states: dry (boundary), mixed, and fluid friction of journal bearings are classified by pre-processing the AE signals with windowing and high-pass filtering, extracting separation effective features from time, frequency, and time-frequency domain using continuous wavelet transform (CWT) and a Support Vector Machine (SVM) as the classifier. Furthermore, it is shown that journal bearing friction classification is not only possible under variable rotational speed and load, but also under different oil viscosities generated by varying oil inlet temperatures. A method used to identify the location of occurring mixed friction events over the journal bearing circumference is shown in this paper. The time-based AE signal is fused with the phase shift information of an incremental encoder to achieve an AE signal based on the angle domain. The possibility of monitoring the run-in wear of journal bearings is investigated by using the extracted separation effective AE features. Validation was done by tactile roughness measurements of the surface. There is an obvious AE feature change visible with increasing run-in wear. Furthermore, these investigations show also the opportunity to determine the friction intensity. Long-term wear investigations were done by carrying out long-term wear tests under constant rotational speeds, loads, and oil inlet temperatures. Roughness and roundness measurements were done in order to calculate the wear volume for validation. The integrated AE Root Mean Square (RMS) shows a good correlation with the journal bearing wear volume.

It has been shown that Acoustic Emission (AE) can be used to classify different friction states and identify defects in journal bearings. In addition, it has been demonstrated in experimental setups that AE can be used to estimate the wear volume of sliding lubricated metallic contacts. The aim of our work is to monitor the wear during the operation of a journal bearing. This work deals with the development of a prognosis system for a detection of the wear and its volume by means of AE before an actual fault occurs. For this purpose, a journal bearing test bench was developed, where the oil temperature for the lubrication, load and rotational speed can be set. Experiments were carried out under different operating conditions and lasted up to 20 hours each. To establish a correlation between wear and AE, the wear volume is determined by comparing recorded roundness profiles of the inner race before and after each experiment at multiple positions. The method used is validated by measuring the roughness of the inner race surface, thus confirming the position of the wear. The analysis of the recorded AE signals shows an amplitude modulation as well as bursts. The frequency of the amplitude modulation correlates with the rotational speed even at higher velocities. Bursts in the AE signal are directly related to wear. Various features, e.g. root mean square value and properties of the measured bursts, of the AE signal and their relevance for the prediction of the wear are analyzed. A quantitative estimation of the volume proves to be challenging, while a qualitative estimation of occurrence and severity of wear can be reliably detected.

To develop a system for predicting the remaining useful lifetime of a journal bearing, it is necessary to monitor the progressive wear quantitatively. For this purpose, we create a dataset where the wear volume is tracked throughout several experiments. The roundness profile is used to determine the wear volume over the entire life of the journal bearing. Therefore, a procedure for tracking the wear volume is described. The uncertainty of the procedure is analyzed. It is shown that the procedure has good accuracy and that the uncertainty is induced by the manual setting of the measuring positions. It has been shown that acoustic emission can be used to classify different friction states and identify defects in journal bearings. In addition, it has been demonstrated in experimental setups that it can be used to estimate the wear volume of sliding lubricated metallic contacts. Several experiments were carried out under different operating conditions for the dataset’s creation. Finally, the root mean square value of the acquired acoustic emission signal is used for estimation. Linear regression, random forest regressor, multilayer perceptron, and recurrent neuronal network are applied. The wear volume can be estimated with a root mean square error of 0.32 mm³and a coefficient of determination of 93 %. Neural networks have the distinct advantage of being able to estimate wear at any point during an experiment.

For diagnosis and predictive maintenance of mechatronic systems, monitoring of bearings is essential. An integral component for this is the determination of the bearing friction condition. Hydrodynamic journal bearings experience three basic types of friction states: fluid, mixed and solid friction, whereas the last two types cause mechanical wear.This paper deals with the differentiation of these three basic types of journal bearing friction conditions under several rotational speed, load and oil viscosity combinations based on acoustic emission (AE) signals. The aim of this work is to show that it is possible to detect various oil viscosities under same loads and rotational speeds with AE features. An already developed classifier [1], which is trained and tested under various rotational speed and load combinations, can then be improved by training and testing it under several oil viscosities.Different oil viscosities were generated by varying the oil temperature. A special test environment is introduced for this purpose. The actual friction state was verified by the contact voltage (CV) between shaft and bearing [2].