The influence of the radial internal clearance on the dynamic response of self-aligning ball bearings

The massive environmental noise interference and insufficient effective sample degradation data of the intelligent fault diagnosis performance methods pose an extremely concerning issue. Realising the challenge of developing a facile and straightforward model that resolves these problems, this study proposed the One-Dimensional Convolutional Neural Network (1D-CNN) based on frequency-domain signal processing. The Fast Fourier Transform (FFT) analysis is initially utilised to transform the signals from the time domain to the frequency domain; the data was represented using a phasor notation, which separates magnitude and phase and then fed to the 1D-CNN. Subsequently, the model is trained with White Gaussian Noise (WGN) to improve its robustness and resilience to noise. Based on the findings, the proposed model successfully achieved 100% classification accuracy from clean signals and simultaneously achieved considerable robustness to noise and exceptional domain adaptation ability. The diagnosis accuracy retained up to 97.37%, which was higher than the accuracy of the CNN without training under noisy conditions at only 43.75%. Furthermore, the model achieved an accuracy of up to 98.1% under different working conditions, which was superior to other reported models. In addition, the proposed model outperformed the state-of-art methods as the Signal-to-Noise Ratio (SNR) was lowered to −10 dB achieving 97.37% accuracy. In short, the proposed 1D-CNN model is a promising effective rolling bearing fault diagnosis.

Section: Background and Related Studiesmentioning

confidence: 99%

Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain

Hakim

Omran

Inayat-Hussain

et al. 2022

“…The same data transformation (Horizontal and Vertical scaling) is conducted in the experiments. The parameter of Horizontal scale p is set to be 16, the value set is {0, 2,4,6,8,11,14,17,20,23,27,31,35,39, 43, 47}. The parameter of vertical scale α is set to be 3, and the value set is {0, 0.3, 0.7}.…”

Section: Model Parameter Settingsmentioning

confidence: 99%

“…Then, time domain, frequency domain or time-frequency domain analysis are performed to extract and compare fault characteristics [ 3 , 4 , 5 ]. Vibration spectra were conducted in [ 6 ] with consideration of a set of different recurrence indicators to describe the response of the bearing to the optimal clearance. Acoustic emission and lubricating oil characteristics are also very helpful for condition monitoring of bearings.…”

Section: Introductionmentioning

confidence: 99%

The Robust Multi-Scale Deep-SVDD Model for Anomaly Online Detection of Rolling Bearings

Kou

Chen

Qin

et al. 2022

Aiming at the online detection problem of rolling bearings, the limited amount of target bearing data leads to insufficient model in training and feature representation. It is difficult for the online detection model to construct an accurate decision boundary. To solve the problem, a multi-scale robust anomaly detection method based on data enhancement technology is proposed in this paper. Firstly, the training data are transformed into multiple subspaces through the data enhancement technology. Then, a prototype clustering method is introduced to enhance the robustness of features representation under the framework of the robust deep auto-encoding algorithm. Finally, the robust multi-scale Deep-SVDD hyper sphere model is constructed to achieve online detection of abnormal state data. Experiments are conducted on the IEEE PHM Challenge 2012 bearing data set and XJTU-TU data set. The proposed method shows much greater susceptibility to incipient faults, and it has fewer false alarms. The robust multi-scale Deep-SVDD hyper sphere model significantly improves the performance of incipient fault detection for rolling bearings.

“…Contrary to the typical slide bearings, in which the lubricating medium is primarily oil, GFBs make use of air to operate [ 3 ]. In addition, the specific properties of GFBs are even more evident when compared to the classical rolling-ball bearings [ 4 , 5 ]. In fact, the rolling-ball bearings are very popular because they are cheap and manufactured on a large scale in a variety of geometries and sizes.…”

Section: Introductionmentioning

confidence: 99%

“…Functioning on the basis of other physical phenomena, compared to the GFBs, they withstand higher load capacities. However, rolling-ball bearings exhibit significant disadvantages related to the limited rotational speed, limited ability to transmit mechanical vibrations, tendency to increase the level of generated noise and rather quick wear [ 5 , 6 ]. It is worth noticing that, in contrast to the above characterized bearings, the GFBs are designed for a specific type of machinery each time from scratch, work better at higher rotational speeds and more effectively suppress mechanical vibrations—not as efficiently, however, as in case of the oil lubricated bearings.…”

Section: Introductionmentioning

confidence: 99%

Thermal Characterization of a Gas Foil Bearing—A Novel Method of Experimental Identification of the Temperature Field Based on Integrated Thermocouples Measurements

Martowicz

Zdziebko

Roemer

et al. 2022

Maintenance of adequate thermal properties is critical for correct operation of a gas foil bearing. In this work, the authors present the results of the experimentally conducted thermal characterization of a prototype installation of the bearing. A novel method of temperature identification, based on integrated thermocouples readings, has been employed to determine the thermal properties of the specialized sensing top foil mounted in the tested bearing. Two measurement campaigns have been subsequently completed, applying freely-suspended and two-node support configurations, to gather complementary knowledge regarding the bearing’s operation. Apart from the rotational speed and temperature field measurements, the authors have also studied the friction torque and the shaft’s journal trajectories based on its radial displacements. The temporal courses for the above-mentioned quantities have enabled inference on the effects present during run-up, run-out and stable state operation at a constant speed. As confirmed, the applied distribution of the integrated sensors allows for temperature readings on the entire outer surface of the foil, and therefore, provides useful data for the bearing characterization. The work is concluded with presentation of the recommended directions regarding future improvements of the proposed measurement technique and more comprehensive study of the bearing’s characteristics.