Fault detection of slow speed bearings using an integrated approach

Aye, Sylvester A.; Heyns, P.S.; Thiart, Coenie J.H.

doi:10.1016/j.ifacol.2015.06.344

Cited by 10 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…20 As for statistical methods, Guo et al 21 used the matrix decomposition method k -means singular value decomposition for defect detection of wind turbine bearings. Aye et al 22 used the principal component analysis (PCA) approach to gently identify bearing degradation under varied slow-speed situations.…”

Section: Introductionmentioning

confidence: 99%

Wind turbine pitch bearing fault detection with Bayesian augmented temporal convolutional networks

Zhang

2023

Structural Health Monitoring

View full text Add to dashboard Cite

There are few studies on the fault diagnosis of deep learning in real large-scale bearings, such as wind turbine pitch bearings. We present a novel fault diagnosis method, Bayesian augmented temporal convolutional network (BATCN), to filter the raw signal in wind turbine pitch bearing defect detection. This method, which employs temporal convolutional neural networks, is designed to capture the temporal dependencies of the signal, with such a focus on non-stationary relationships in the collected signals. By referring to the thoughts of Bayesian optimization, our approach can spontaneously find the best patch length that influences fault signal extraction during the filtering process, avoiding manual tuning of this hyper-parameter. This BATCN method is first performed on simulation signals and an open-source dataset of general bearings, and then validated on industrial wind turbine pitch bearings both in the lab and in the real wind farm, where the bearings have been operated for over 15 years. The results show that our method can work well for large-scale slow-speed wind turbine pitch bearings.

show abstract

Section: Introductionmentioning

confidence: 99%

Wind turbine pitch bearing fault detection with Bayesian augmented temporal convolutional networks

Zhang

2023

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…Each obtained feature can be sensitive to different fault mode. One main problem of using multiple feature extraction methods is the resulting high amount of data, which is hard to deal with in case of fault diagnostics (Aye, Heyns, & Thiart, 2014). Thus, the need of data reduction methods arises.…”

mentioning

confidence: 99%

Asynchronous Motor Test Bench for the Generation and Current Signal Diagnostics of Accelerated Bearing Damage

2015

View full text Add to dashboard Cite

The data acquisition of run to failure data by means of de- grading components is one of the most delicate tasks in evaluating new diagnostic and prognostic approaches, since it is cost-intensive and time-consuming. Therefore, a test rig for a cost-efficient generation of artificial bearing damages is described below. The test rig is thereby based on an ordinary asynchronous motor. This paper mainly concentrates on the description of the test rig’s setup and first diagnostic findings. One aim of the experiments is the investigation of several variations of the applied loads for the artificially accelerated bearing aging. Thus, radial force and fluting are examined. The latter causes a damage triggered by a current flow through the test bearing. Both load types reduce the overall lifespan of bearings to about few weeks. The generated faults are a broken cage and chattermarks due to a radial force higher than the design point. The bearings are diagnosed by means of frequency analysis of the phase current signal, which is produced in the stator of the motor. Beside the current signal, also temperature, vibration and revolution of the shaft are measured, whereas the vibration signal is used only for the comparison to the current signal. The comprehensive measurement concept allows a performance evaluation of diagnostic and prognostic algorithms based on different physical indicators. It can be shown that especially the current frequency spectrum of a faulty bearing differs significantly from a healthy one. In order to face the high amount of measurement data, the Principal Component Analysis is used for data reduction to generate features for the diagnosis and prognosis. Thus, a classification of different fault modes and loading conditions is possible.

show abstract

A review of failure modes, condition monitoring and fault diagnosis methods for large-scale wind turbine bearings

2020

View full text Add to dashboard Cite

Fault detection of slow speed bearings using an integrated approach

Cited by 10 publications

References 23 publications

Wind turbine pitch bearing fault detection with Bayesian augmented temporal convolutional networks

Wind turbine pitch bearing fault detection with Bayesian augmented temporal convolutional networks

Asynchronous Motor Test Bench for the Generation and Current Signal Diagnostics of Accelerated Bearing Damage

A review of failure modes, condition monitoring and fault diagnosis methods for large-scale wind turbine bearings

Contact Info

Product

Resources

About