A bearing vibration data analysis based on spectral kurtosis and ConvNet

2018 ◽  
Vol 23 (19) ◽  
pp. 9341-9359 ◽  
Author(s):  
Sandeep S. Udmale ◽  
Sangram S. Patil ◽  
Vikas M. Phalle ◽  
Sanjay Kumar Singh
Keyword(s):  
Data Analysis ◽  
Spectral Kurtosis ◽  
Vibration Data ◽  
Bearing Vibration

scholarly journals Vibration analysis based on the spectrum kurtosis for adjustment and monitoring of ball bearing radial clearance

2018 ◽  
Vol 211 ◽  
pp. 06006 ◽  
Author(s):  
Anthimos Georgiadis ◽  
Xiaoyun Gong ◽  
Nicolas Meier
Keyword(s):  
Signal Analysis ◽  
Vibration Signal ◽  
Radial Clearance ◽  
Spectral Kurtosis ◽  
Vibration Data ◽  
Bearing Clearance ◽  
Bearing Condition Monitoring ◽  
Bearing Vibration ◽  
Vibration Signal Analysis

Vibration signal analysis is a common tool to detect bearing condition. Effective methods of vibration signal analysis should extract useful information for bearing condition monitoring and fault diagnosis. Spectral kurtosis (SK) represents one valuable tool for these purposes. The aim of this paper is to study the relationship between bearing clearance and bearing vibration frequencies based on SK method. It also reveals the effect of the bearing clearance on the bearing vibration characteristic frequencies This enables adjustment of bearing clearance in situ, which could significantly affect the performance of the bearings. Furthermore, the application of the proposed method using SK on the measured data offers useful information for predicting bearing clearance change. Bearing vibration data recorded at various clearance settings on a floating and a fixed bearing mounted on a shaft are the basis of this study

Monitoring Offshore Pipelines Using Forced Transverse Vibration: Data Analysis

1995 ◽  
Author(s):  
Hugh E. M. Hunt
Keyword(s):  
Fluid Flow ◽  
Data Analysis ◽  
Transverse Vibration ◽  
Vibration Amplitude ◽  
Support Condition ◽  
Offshore Pipelines ◽  
Vibration Data ◽  
Wavelet Methods

Abstract Vibration methods are used to identify faults, such as spanning and loss of cover, in long off-shore pipelines. A pipeline ‘pig’, propelled by fluid flow, generates transverse vibration in the pipeline and the measured vibration amplitude reflects the nature of the support condition. Large quantities of vibration data are collected and analysed by Fourier and wavelet methods.

scholarly journals Fault Diagnosis of Industrial Gear Hobbing Machine

2020 ◽  
Vol 9 (3) ◽  
pp. 2039-2043
Keyword(s):  
Fault Diagnosis ◽  
Low Cost ◽  
Market Competition ◽  
Vibrational Analysis ◽  
High Quality ◽  
Mems Accelerometer ◽  
Spectral Kurtosis ◽  
Vibration Data ◽  
Gear Hobbing ◽  
Dynamic Time

The aim of this paper is to develop a fault diagnosis algorithm by vibrational analysis for an industrial gear hobbing machine. Gear Hobbing is the most dominant and profitable process for manufacturing high quality gears. In order to sustain the market competition gear manufacturers, need to produce high quality gears with minimum possible cost. However, catastrophic failures do occur in gear hobbing process which causes unexpected machine down time and revenue loss. These failures can be avoided by using condition monitoring approaches. In the proposed approach vibration data during different faults such as lubrication error, excessive feed rate, loose bearing error is collected from an industrial gear hobbing machine using three axis MEMS accelerometer. The collected data is analyzed and classified with spectral kurtosis and Dynamic Time Warping algorithm. The efficiency of the proposed approach is 90 percent as determined by experimental results. The proposed approach can provide a low-cost solution for predictive maintenance for gear hobbing industries..

Development of Structural Identification Accuracy Indicators Using Fuzzy Logic

1997 ◽  
Author(s):  
Stanley E. Woodard ◽  
Richard S. Pappa
Keyword(s):  
Data Analysis ◽  
Expert System ◽  
Structural Damage ◽  
Identification Accuracy ◽  
Fuzzy Expert System ◽  
Eigensystem Realization Algorithm ◽  
Automatic Control Systems ◽  
Vibration Data ◽  
Fuzzy Membership Functions ◽  
Degree Of Confidence

Abstract A fuzzy expert system was developed for autonomous in-space identification of spacecraft modal parameters. The in-space identification can be used to validate analytical predictions, detect structural damage, or tune automatic control systems as required. A fuzzy expert system determines accuracy of vibration data analysis performed autonomously using the Eigensystem Realization Algorithm. Evaluation of the data analysis output is imprecise and somewhat subjective. The expert system was developed using the knowledge provided the co-developer of the Eigensystem Realization Algorithm. The accuracy indicator represents the analyst’s degree of confidence in the analysis results. The fuzzy membership functions of the expert system were parameterized and tuned using numerical optimization.

Diagnostics of Fatigue Crack in the Shaft Using Spectral Kurtosis

2019 ◽  
Author(s):  
Sagi Rathna Prasad ◽  
A. S. Sekhar
Keyword(s):  
Fatigue Crack ◽  
Crack Detection ◽  
Fatigue Cracks ◽  
Processing Technique ◽  
Rotating Machinery ◽  
Operating Conditions ◽  
Laser Vibrometer ◽  
Signal Processing Technique ◽  
Spectral Kurtosis ◽  
Vibration Data

Abstract Rotating machinery components like shafts subjected to continuous fluctuating loads are prone to fatigue cracks. Fatigue cracks are severe threat to the integrity of rotating machinery. Therefore it is indispensable for early diagnostics of fatigue cracks in shaft to avoid catastrophic failures. From the literature, it is evident that the spectral kurtosis (SK) and fast kurtogram were used to detect the faults in bearings and gears. The present study illustrates the use of SK and fast kurtogram for early fatigue crack detection in the shaft using vibration data. To perform this study, experiments are conducted on a rotor test rig which is designed and developed according to the function specification proposed by ASTM E468-11 standard. Fatigue crack is developed, on three shaft specimens, each seeded with the same circumferential V-Notch configuration, by continuous application of stochastic loads on the shaft using electrodynamic shaker in addition to the unbalance forces that arise in normal operating conditions. Vibration data is acquired from various locations of the rotor, using different sensors like miniature accelerometers, laser vibrometer and wireless telemetry strain gauge, till the shaft specimen develops fatigue crack. The analysis results show that the combination of SK and fast kurtogram is an effective signal processing technique for detecting the fatigue crack in the shaft.

A Study on Applicability of Predictive Maintenance and Vibration Data Analysis by Fast Fourier Transform into Major Equipment of Submarine

2021 ◽  
Vol 4 (1) ◽  
pp. 14-21
Author(s):  
Donghoon Kim ◽  
Sang Woo Kang ◽  
Ji Hoon Lee ◽  
Kyung Mo Nam ◽  
Seong Hun Seong ◽  
...  
Keyword(s):  
Fourier Transform ◽  
Data Analysis ◽  
Fast Fourier Transform ◽  
Predictive Maintenance ◽  
Vibration Data ◽  
Major Equipment

Collection and processing of bearing vibration data for their technical condition classification by machine learning methods

2021 ◽  
pp. 10-15
Author(s):  
Ruslan Babudzhan ◽  
Kostiantyn Isaienkov ◽  
Danylo Krasii ◽  
Ruben Melkonian ◽  
Oleksii Vodka ◽  
...  
Keyword(s):  
Machine Learning ◽  
Technical Condition ◽  
Machine Learning Techniques ◽  
Rolling Bearings ◽  
Control Block ◽  
Vibration Data ◽  
Learning Techniques ◽  
Emergency Stop ◽  
Bearing Vibration ◽  
To Receive

An experimental research facility has been developed to receive vibration signals from mechanisms with installed rolling bearings. A control block for all equipment has been created. For the repeatability of the experiment, an external microcontroller with a programmed proportional-integral-derivative regulator was used. Experiments were carried out to obtain initial data for different types of bearings. The processed data were grouped and made publicly available for further research. It is proposed to solve the problem of emergency stop of the generator, arising during operation due to bearings worn, by recognizing the pre-emergency conditions of rotary rig based on the use of advanced machine learning techniques: to highlight the signs of vibration and build clusters according to the degree of worn.

Sign in / Sign up

Export Citation Format

Share Document