Bearing Fault Severity Analysis on A Multi-stage Gearbox Subjected to Fluctuating Speeds
- PDF / 2,740,327 Bytes
- 12 Pages / 595.224 x 790.955 pts Page_size
- 20 Downloads / 157 Views
RESEARCH PAPER
Bearing Fault Severity Analysis on A Multi-stage Gearbox Subjected to Fluctuating Speeds Vamsi Inturi1 · Sabareesh G.R.1 · P.K. Penumakala1 Received: 18 November 2019 / Accepted: 24 March 2020 © The Society for Experimental Mechanics, Inc 2020
Abstract Early detection of bearing defects may prevent the occurrence of catastrophic failures of the whole associated system. Condition monitoring strategies such as vibration and acoustic signal analyses are employed for incipient fault diagnosis of bearings. The current investigation attempts to compare the fault diagnostic capabilities in terms of their effectiveness in early detection of local bearing defects. Experiments are performed on a three-stage gearbox under constant and fluctuating operating conditions of speed. Wavelet coefficients are achieved from the acquired raw signals by discrete wavelet transform and various statistical features are obtained. Most contributing features among them are chosen by decision tree. Further, the extracted features are classified based on their fault severity levels using support vector machine algorithm. The experimental investigation revealed that vibration signal analysis outperformed the acoustic signal analysis under the experimental operating conditions. Keywords Ball bearing · Condition monitoring · Fluctuating speed · Multi-stage gearbox
Introduction Generally, gearboxes are subjected to fluctuating operating conditions which make them susceptible to incipient failures yielding to unexpected break down of the entire system. Earlier reports suggest that, more than 40% failures in rotating machinery take place as a consequence of bearing failure [1]. Defects present in the bearings could lead to generate vibration and noise [2]. Localized defects such as slots, spall on rollers and are often seen on inner/outer race facilitate a series of transient vibrations when they come in contact with roller. The probability of transition of these defects being transitioned into next level of damage is always high if early diagnosis is neglected. Hence, incipient diagnosis level of localized defects becomes a crucial aspect to avoid unexpected break down events and bring down maintenance economy. Condition monitoring (CM) is an extensively implemented maintenance strategy for incipient anomalies detection.
Vamsi Inturi
[email protected] 1
Department of Mechanical Engineering, BITS Pilani, Hyderabad Campus, Hyderabad, India
Among the various CM strategies, the implementation of vibration and acoustic signal analyses are extensive in the fault diagnostics of bearings. Hizarci et al. [3] have monitored the pitting damage of helical and worm gearboxes by examining the acquired vibration signatures. Karacay and Akturk [4] performed statistical analysis on the vibration signals to ascertain the defects that are present in the bearings. Further, the vibration spectra were examined to locate the fault present on the bearings. Sugumaran et al. [5] executed pattern recognition algorithm to extract the statistical i
Data Loading...
