Detectivity: A combination of Hjorth’s parameters for condition monitoring of ball bearings

2022 ◽  
Vol 164 ◽  
pp. 108247
Author(s):  
Marco Cocconcelli ◽  
Matteo Strozzi ◽  
Jacopo Cavalaglio Camargo Molano ◽  
Riccardo Rubini
Keyword(s):  
Condition Monitoring ◽  
Ball Bearings

scholarly journals Fault Detection and Severity Identification of Ball Bearings by Online Condition Monitoring

2019 ◽  
Vol 66 (10) ◽  
pp. 8136-8147 ◽  
Author(s):  
Osama Abdeljaber ◽  
Sadok Sassi ◽  
Onur Avci ◽  
Serkan Kiranyaz ◽  
Abdelrahman Aly Ibrahim ◽  
...  
Keyword(s):  
Fault Detection ◽  
Condition Monitoring ◽  
Ball Bearings

Condition monitoring studies on ball bearings considering solid contaminants in the lubricant

2010 ◽  
Vol 224 (8) ◽  
pp. 1727-1748 ◽  
Author(s):  
V Hariharan ◽  
P S S Srinivasan
Keyword(s):  
Particle Size ◽  
Condition Monitoring ◽  
Experimental Tests ◽  
Solid Particles ◽  
Contaminant Concentration ◽  
Ball Bearings ◽  
Rolling Element Bearings ◽  
Rolling Bearings ◽  
Rolling Element ◽  
Vibration Signatures

Rolling element bearings are common in any rotating machinery. They are subject to failure under continuous running. Therefore they have received a great deal of attention in the field of condition monitoring. In rolling element bearings, contamination of lubricant grease by solid particles is one of the several reasons for an early bearing failure. In this context, this article investigates the effect of contamination of lubricant by solid particles on the dynamic behaviour of rolling bearings. Silica powder at three concentration levels and different particle sizes was used to contaminate the lubricant. Experimental tests have been performed on the ball bearings lubricated with grease, and the trends in the amount of vibration affected by the contamination of the grease were determined. The contaminant concentration as well as the particle size is varied. Vibration signatures were analysed in terms of root mean square (RMS) values. From the results, some fruitful conclusions are made about the bearing performance. The effects of contaminant and the bearing vibration are studied for both good and defective bearings. The results show significant variation in the RMS velocity values on varying the contaminant concentration and particle size.

scholarly journals Experimental Evidence of the Speed Variation Effect on SVM Accuracy for Diagnostics of Ball Bearings

Machines ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 48
Author(s):  
Jacopo Cavalaglio Camargo Molano ◽  
Riccardo Rubini ◽  
Marco Cocconcelli
Keyword(s):  
Machine Learning ◽  
Condition Monitoring ◽  
Learning System ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Ball Bearings ◽  
Variable Speed ◽  
Learning Techniques ◽  
Stationary Conditions ◽  
Mechanical Components

In recent years, we have witnessed a considerable increase in scientific papers concerning the condition monitoring of mechanical components by means of machine learning. These techniques are oriented towards the diagnostics of mechanical components. In the same years, the interest of the scientific community in machine diagnostics has moved to the condition monitoring of machinery in non-stationary conditions (i.e., machines working with variable speed profiles or variable loads). Non-stationarity implies more complex signal processing techniques, and a natural consequence is the use of machine learning techniques for data analysis in non-stationary applications. Several papers have studied the machine learning system, but they focus on specific machine learning systems and the selection of the best input array. No paper has considered the dynamics of the system, that is, the influence of how much the speed profile changes during the training and testing steps of a machine learning technique. The aim of this paper is to show the importance of considering the dynamic conditions, taking the condition monitoring of ball bearings in variable speed applications as an example. A commercial support vector machine tool is used, tuning it in constant speed applications and testing it in variable speed conditions. The results show critical issues of machine learning techniques in non-stationary conditions.

Bispectrum: A Tool for Distinguishing Different Faults in Rotating Machine

2012 ◽  
Author(s):  
Keri Elbhbah ◽  
Jyoti K. Sinha
Keyword(s):  
Fault Diagnosis ◽  
Condition Monitoring ◽  
State Of The Art ◽  
Ball Bearings ◽  
Rotating Machines ◽  
Rotating Machine ◽  
Current State ◽  
The Future ◽  
Experimental Rig ◽  
Initial Results

The current state-of-the-art in vibration-based condition monitoring of rotating machines requires a number of vibration transducers at each bearing pedestal of a rotating machine to identify any faults, in the machine. In this paper, the use of the bispectrum has been proposed for fault diagnosis in rotating machines. The reason for this is that it may reduce the number of vibration transducers at each bearing pedestal in rotating machines in the future. The paper presents a comparison of the bispectrum results for four cases, namely; Healthy, Misaligned shaft, Crack Shaft and Shaft Rub on an experimental rig consisting of two rigidly coupled shafts supported through 4 ball bearings. Only one accelerometer has been used for this purpose at each bearing and the initial results observed are encouraging.

Sign in / Sign up

Export Citation Format

Share Document