Data Mining Based Full Ceramic Bearing Fault Diagnostic System Using AE Sensors

He, David; Li, Ruoyu; Zhu, Junda; Zade, Mikhail

doi:10.1109/tnn.2011.2169087

Cited by 75 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KNN (Altman) is one of the most popular choices for fault classifiers. KNN has been reported as an effective fault classifier for bearing fault diagnosis (He et al …”

Section: Methodsmentioning

confidence: 99%

Vibration‐based wind turbine planetary gearbox fault diagnosis using spectral averaging

Yoon

Hecke

et al. 2015

Wind Energy

View full text Add to dashboard Cite

Planetary gearboxes (PGBs) are widely used in the drivetrain of wind turbines. Any PGB failure could lead to a significant breakdown or major loss of a wind turbine. Therefore, PGB fault diagnosis is very important for reducing the downtime and maintenance cost and improving the safety, reliability, and lifespan of wind turbines. The wind energy industry currently utilizes vibratory analysis as a standard method for PGB condition monitoring and fault diagnosis. Among them, the vibration separation is considered as one of the well-established vibratory analysis techniques. However, the drawbacks of the vibration separation technique as reported in the literature include the following: potential sun gear fault diagnosis limitation, multiple sensors and large data requirement, and vulnerability to external noise. This paper presents a new method using a single vibration sensor for PGB fault diagnosis using spectral averaging. It combines the techniques of enveloping, Welch's spectral averaging, and data mining-based fault classifiers. Using the presented approach, vibration fault features for wind turbine PGB are extracted as condition indicators for fault diagnosis and condition indicators are used as inputs to fault classifiers for PGB fault diagnosis. The method is validated on a set of seeded localized faults on all gears: sun gear, planetary gear, and ring gear. The results have shown a promising PGB fault diagnosis performance with the presented method.

show abstract

“…KNN (Altman) is one of the most popular choices for fault classifiers. KNN has been reported as an effective fault classifier for bearing fault diagnosis (He et al …”

Section: Methodsmentioning

confidence: 99%

Vibration‐based wind turbine planetary gearbox fault diagnosis using spectral averaging

Yoon

Hecke

et al. 2015

Wind Energy

View full text Add to dashboard Cite

show abstract

“…In k-NN classification, the output is the class of an object, which is identified by a majority vote of its k nearest neighbors. One early implementation of the k-NN classifier on bearing fault diagnostics can be found in [43], where k-NN serves as the core algorithm for a data mining based ceramic bearing fault classifier based on acoustic signals. Similarly, other k-NN based papers [44]- [46] employ k-NN to perform a distance analysis on each new data sample and determine whether it belongs to a specific fault class.…”

Section: K-nearest Neighbors (K-nn)mentioning

confidence: 99%

Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review

et al. 2020

View full text Add to dashboard Cite

In this survey paper, we systematically summarize existing literature on bearing fault diagnostics with machine learning (ML) and data mining techniques. While conventional ML methods, including artificial neural network (ANN), principal component analysis (PCA), support vector machines (SVM), etc., have been successfully applied to the detection and categorization of bearing faults for decades, recent developments in deep learning (DL) algorithms in the last five years have sparked renewed interest in both industry and academia for intelligent machine health monitoring. In this paper, we first provide a brief review of conventional ML methods, before taking a deep dive into the state-of-the-art DL algorithms for bearing fault applications. Specifically, the superiority of DL based methods over conventional ML methods are analyzed in terms of fault feature extraction and classification performances; many new functionalities enabled by DL techniques are also summarized. In addition, to obtain a more intuitive insight, a comparative study is conducted on the classification accuracy of different algorithms utilizing the open source Case Western Reserve University (CWRU) bearing dataset. Finally, to facilitate the transition on applying various DL algorithms to bearing fault diagnostics, detailed recommendations and suggestions are provided for specific application conditions such as the setup environment, the data size, and the number of sensors and sensor types. Future research directions to further enhance the performance of DL algorithms on health monitoring are also discussed.

show abstract

“…In addition, studies have developed effective CIs that accomplish bearing fault diagnosis through the quantification of AE signals. 18,19 A significant difference among the available CI feature extraction techniques is in the way the CIs are computed, that is, features can be extracted from both the time and frequency domains. Additionally, features can be extracted from the raw signal or after a signal processing technique such as TSA or spectral averaging.…”

Section: Cis For Bearing Fault Diagnosismentioning

confidence: 99%

Bearing fault diagnosis based on a new acoustic emission sensor technique

Hecke

Qu²,

2014

Proceedings of the Institution of Mechanical Engineers, Part O:

View full text Add to dashboard Cite

The diagnosis of bearing health by quantifying acoustic emission data has been an area of interest for recent years due to the numerous advantages over vibration-based techniques. However, most acoustic emission-based methodologies to date are data-driven technologies. This research takes a novel approach combining a heterodyne-based frequency reduction technique, time synchronous resampling, and spectral averaging to process acoustic emission signals and extract condition indicators for bearing fault diagnosis. The heterodyne technique allows the acoustic emission signal frequency to be shifted from several megahertz to less than 50 kHz, which is comparable to that of vibration-based techniques. Then, the digitized signal is band-pass filtered to retain the information associated with the bearing defects. Finally, the tachometer signal is used to time synchronously resample the acoustic emission data, allowing the computation of a spectral average which in turn enables the extraction and evaluation of condition indicators for bearing fault diagnosis. The presented technique is validated using the acoustic emission signals of seeded fault steel bearings on a bearing test rig. The result is an effective acoustic emission-based approach validated to diagnose all four fault types: inner race, outer race, ball, and cage.

show abstract

Data Mining Based Full Ceramic Bearing Fault Diagnostic System Using AE Sensors

Cited by 75 publications

References 37 publications

Vibration‐based wind turbine planetary gearbox fault diagnosis using spectral averaging

Vibration‐based wind turbine planetary gearbox fault diagnosis using spectral averaging

Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review

Bearing fault diagnosis based on a new acoustic emission sensor technique

Contact Info

Product

Resources

About