Abstract
Rolling element bearings are a vital part of rotating machines and their sudden failure can result in huge economic losses as well as physical causalities. Popular bearing fault diagnosis techniques include statistical feature analysis of time, frequency, or time-frequency domain data. These engineered features are susceptible to variations under inconsistent machine operation due to the non-stationary, non-linear, and complex nature of the recorded vibration signals. To address these issues, numerous deep learning-based frameworks have been proposed in the literature. However, the logical reasoning behind crack severities and the longer training times needed to identify multiple health characteristics at the same time still pose challenges. Therefore, in this work, a diagnosis framework is proposed that uses higher-order spectral analysis and multitask learning (MTL), while also incorporating transfer learning (TL). The idea is to first preprocess the vibration signals recorded from a bearing to look for distinct patterns for a given fault type under inconsistent working conditions, e.g., variable motor speeds and loads, multiple crack severities, compound faults, and ample noise. Later, these bispectra are provided as an input to the proposed MTL-based convolutional neural network (CNN) to identify the speed and the health conditions, simultaneously. Finally, the TL-based approach is adopted to identify bearing faults in the presence of multiple crack severities. The proposed diagnostic framework is evaluated on several datasets and the experimental results are compared with several state-of-the-art diagnostic techniques to validate the superiority of the proposed model under inconsistent working conditions.
Highlights
Rotating machinery is a prevailing component that plays an increasingly significant role in modern industries [1,2]
The main goal of transfer learning (TL) is to transfer knowledge obtained from one task to another task that resembles it closely to improve the diagnostic performance of the new task in a short amount of time [13]
This study presented a bispectrum-aided preprocessing technique, which is combined with a multitask learning–based, fine-tuned transfer learning approach to diagnose bearing faults
Summary
Rotating machinery is a prevailing component that plays an increasingly significant role in modern industries [1,2]. Due to the disparity in the signal amplitude and frequency for several inconsistent working conditions, e.g., variable loads, speeds, different crack severities, and compound faults, these established approaches have failed to generalize the health characteristics To solve these problems, several time-frequency-based analysis techniques have been proposed. In [39], Liu et al introduced a dislocated layer into the CNN architecture to boost the one-dimensional feature analysis performance These methods have two major drawbacks: (a) the lack of proper health state information that is applicable in cross-domain fault diagnosis and (b) weak generalization capabilities because these approaches cannot provide satisfactory results for the fault diagnosis of bearings under inconsistent working conditions (e.g., variable motor speed, variable motor load, multiple crack severities, and compound fault types).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
