Prediction of oil whirl initiation in journal bearings using multi-sensors data fusion

Safizadeh, Mir Saeed; Golmohammadi, A.

doi:10.1016/j.measurement.2019.107241

Cited by 19 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alves et al [6] used a convolutional neural network algorithm to diagnose ovalized journal bearings. Using the information provided by proximity probes and a mini piezoelectric load cell at the hydrodynamic bearing, Safizadeh and Golmohammadi [7] proposed a data fusion method to predict oil-whirl and oil-whip. Yang et al [8] showed the importance of analyzing the sub-and super harmonics for fault identification (rotor crack).…”

Section: Introductionmentioning

confidence: 99%

A parametric model to identify hydrodynamic bearing wear at a single rotating speed

Alves

Fieux

Machado

et al. 2021

Tribology International

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

A parametric model to identify hydrodynamic bearing wear at a single rotating speed

Alves

Fieux

Machado

et al. 2021

Tribology International

View full text Add to dashboard Cite

“…Hiremath and Reddy [ 29 ] judge the wear of the outer race of the roller bearing through the degradation of grease and analysis of vibration signals and temperature. Safizadeh and Golmohammadi [ 30 ] use multi-sensor data to detect the pressure distribution change of journal bearing caused by oil whirl.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis for Abnormal Wear of Rolling Element Bearing Fusing Oil Debris Monitoring

Zhao

Wang

Han

et al. 2023

Sensors

View full text Add to dashboard Cite

The abnormal wear of a rolling element bearing caused by early failures, such as pitting and spalling, will deteriorate the running state and reduce the life. This paper demonstrates the importance of oil debris monitoring and its effective feature extraction for bearing health assessment. In this paper, a rolling bearing-rotor test rig with forced lubrication is set up and the nonferrous contaminants with higher hardness were introduced artificially to accelerate the occurrence of pitting and spalling. The early failure and abnormal wear of rolling bearings cannot be effectively detected only through the vibration signal; the temperature and oil debris monitoring data are also collected synchronously. Two features regarding the ferrous particle size distribution are extracted and fused with vibration based-features to form a feature set. The sensitive features are extracted from the features set using the Neighborhood Component Analysis method to avoid feature redundancy. Finally, the importance of the oil debris based-features for the diagnosis of abnormal bearing wear is analyzed with different machine learning algorithms. Taking SVM classifier as an example, the experiment results show that the introduction of oil debris based-features increases the diagnostic accuracy by 15.7%.

show abstract

“…Nowadays, journal bearings have been widely used in rotating machinery due to superior durability and load-carrying capacities [1][2][3], such as wind turbines, transmissions and compressors. The dynamic coefficients of journal bearings directly affect the stability performance and unbalance responses of the whole rotor system, including the four stiffness coefficients and four damping coefficients.…”

Section: Introductionmentioning

confidence: 99%

Model updating for rotor-discs system and its application in dynamic coefficients identification of journal bearings

et al. 2021

View full text Add to dashboard Cite

An accurate finite element (FE) model of the rotor-discs system is essential on the field identification of dynamic coefficients for journal bearings. This paper proposes a novel model updating method using the measured modal parameters. In this method, system mass and stiffness matrices were firstly updated by the particle swarm optimization (PSO) algorithm, in which the sensitivity analysis was used to select the appropriate variables to be optimized. Based on the updated results, the damping matrix defined as an improved Rayleigh Damping was then determined according to the experimental modal frequencies and damping ratios. To evaluate the effectiveness of this method, the FE model of a dual rotor-discs system was updated. The frequencies responses predicted by the updated model perform a good agreement with that from measured. Moreover, to validate the reliability of the updated model, the identifications of the dynamic coefficients were conducted on the flexible rotor test rig experimentally. The results demonstrated that the updated model has higher accuracy in field identification of dynamic coefficients than the original model, especially the system under critical speed.This study provides a feasibility strategy for updating the rotor-discs system and thereby establishes a foundation for further parameters identification and dynamic analysis.

show abstract

Prediction of oil whirl initiation in journal bearings using multi-sensors data fusion

Cited by 19 publications

References 22 publications

A parametric model to identify hydrodynamic bearing wear at a single rotating speed

A parametric model to identify hydrodynamic bearing wear at a single rotating speed

Fault Diagnosis for Abnormal Wear of Rolling Element Bearing Fusing Oil Debris Monitoring

Model updating for rotor-discs system and its application in dynamic coefficients identification of journal bearings

Contact Info

Product

Resources

About