Abstract
During the condition monitoring of a planetary gearbox, features are extracted from raw data for a fault diagnosis. However, different features have different sensitivity for identifying different fault types, and thus, the selection of a sensitive feature subset from an entire feature set and retaining as much of the class discriminatory information as possible has a directly effect on the accuracy of the classification results. In this paper, an improved hybrid feature selection technique (IHFST) that combines a distance evaluation technique (DET), Pearson’s correlation analysis, and an ad hoc technique is proposed. In IHFST, a temporary feature subset without irrelevant features is first selected according to the distance evaluation criterion of DET, and the Pearson’s correlation analysis and ad hoc technique are then employed to find and remove redundant features in the temporary feature subset, respectively, and hence, a sensitive feature subset without irrelevant or redundant features is selected from the entire feature set. Further, the k-means clustering method is applied to classify the different kinds of health conditions. The effectiveness of the proposed method was validated through several experiments carried out on a planetary gearbox with incipient cracks seeded in the tooth root of the sun gear, planet gear, and ring gear. The results show that the proposed method can successfully distinguish the different health conditions of a planetary gearbox, and achieves a better classification performance than other methods. This study proposes a sensitive feature subset selection method that achieves an obvious improvement in terms of the accuracy of the fault classification.
Highlights
Owing to its advantages of a compact structure, large transmission ratio, and high load capacity, a planetary gear transmission system is widely used in large-scale and complex mechanical equipment [1, 2], e.g., wind turbines, helicopters, and automobiles.A planetary gearbox typically consists of some key components: a sun gear, planet gear, ring gear, carrier, and bearing, and faults may occur in these components owing to fatigue or tough working conditions
It can be observed that three features (Nos. 19, 20, and 26) with higher mean correlation coefficients in the distance evaluation technique (DET) method are suppressed according to the new distance evaluation criteria β
Twelve sensitive features are selected from the entire feature set using the DET method with a given threshold, Thr(α) = mean(αj), and eight sensitive features are selected using the improved hybrid feature selection technique (IHFST) method with a given threshold, Thr(β) = mean(βj), where j = 1, 2,..., 32 denotes the feature index
Summary
Owing to its advantages of a compact structure, large transmission ratio, and high load capacity, a planetary gear transmission system is widely used in large-scale and complex mechanical equipment [1, 2], e.g., wind turbines, helicopters, and automobiles.A planetary gearbox typically consists of some key components: a sun gear, planet gear, ring gear, carrier, and bearing, and faults may occur in these components owing to fatigue or tough working conditions. In this way, researchers can identify the difference between the spectrum of a normal vibration signal and a fault vibration signal with commonly used methods that include a spectrum-based analysis, resonance demodulation technique, and cepstrum analysis [10,11,12]. Vibrationbased methods have been successfully used in the fault diagnosis and condition monitoring of rotating machinery, the appearance of faults in the analysis results has to be identified artificially, e.g., the identification of a fault characteristic frequency in the spectrum, the determination of a filter sub-band in a demodulation analysis, or the determination of a wavelet type, all of which require considerable of experience and expertise [17,18,19]. It is necessary to develop some intelligent techniques that can automatically determine the health conditions of a planetary gearbox
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
