Feature Denoising and Nearest–Farthest Distance Preserving Projection for Machine Fault Diagnosis

Li, Weihua; Zhang, Shaohui; Rakheja, S.

doi:10.1109/tii.2015.2475219

Cited by 98 publications

(25 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further test the utilities of the proposed method, the vibration data sets for 6205-2RS JEM of Svenska Kullager-Fabriken (SKF) deep-groove ball bearings from the website database of the Case Western Reserve University (CWRU) Bearing Data Center (http://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearin g-data-center-website) are used [8,23,25,29,30]. These data are acceleration signals in the vertical directions on the housing of drive end (DE) bearing and on the fan end (FE) bearing housing, respectively.…”

Section: Case 2: Standard Reference Data Sets In the Cwru Bearing Datmentioning

confidence: 99%

“…These results demonstrate that fault bearings have a great impact on other bearings Besides, the data in the CWRU database have been widely investigated. In the previous studies, the classification features were often high-dimensional in order to get high accuracy rates [23,25,29,30,50]. By comparison, the low-dimensional features based on SymEn estimate can effectively detect the faults of rolling bearings for the data used in [23,25,29,30,50].…”

Section: Fault Detection Of Vibration Signals For the Rolling Bearingmentioning

confidence: 99%

See 1 more Smart Citation

Fault Detection for Vibration Signals on Rolling Bearings Based on the Symplectic Entropy Method

Lei

Meng

Dong

2017

Entropy

View full text Add to dashboard Cite

Abstract:Bearing vibration response studies are crucial for the condition monitoring of bearings and the quality inspection of rotating machinery systems. However, it is still very difficult to diagnose bearing faults, especially rolling element faults, due to the complex, high-dimensional and nonlinear characteristics of vibration signals as well as the strong background noise. A novel nonlinear analysis method-the symplectic entropy (SymEn) measure-is proposed to analyze the measured signals for fault monitoring of rolling bearings. The core technique of the SymEn approach is the entropy analysis based on the symplectic principal components. The dynamical characteristics of the rolling bearing data are analyzed using the SymEn method. Unlike other techniques consisting of high-dimensional features in the time-domain, frequency-domain and the empirical mode decomposition (EMD)/wavelet-domain, the SymEn approach constructs low-dimensional (i.e., two-dimensional) features based on the SymEn estimate. The vibration signals from our experiments and the Case Western Reserve University Bearing Data Center are applied to verify the effectiveness of the proposed method. Meanwhile, it is found that faulty bearings have a great influence on the other normal bearings. To sum up, the results indicate that the proposed method can be used to detect rolling bearing faults.

show abstract

Section: Case 2: Standard Reference Data Sets In the Cwru Bearing Datmentioning

confidence: 99%

Section: Fault Detection Of Vibration Signals For the Rolling Bearingmentioning

confidence: 99%

Fault Detection for Vibration Signals on Rolling Bearings Based on the Symplectic Entropy Method

Lei

Meng

Dong

2017

Entropy

View full text Add to dashboard Cite

show abstract

“…Qualitative and quantitative analysis are made with C++ in the platform software .Net. Reference [16] explains complexity fault detection process to detect fault of rotating machine because its non-stationery character and non-linear vibration since its operated. Then, machine fault detection which is can extract and classified fault character is proposed.…”

Section: Introductionmentioning

confidence: 99%

Analog tachometer as an indicator motorcycle machine wearing based on moving coil

2018

View full text Add to dashboard Cite

As an increasing highly mobility and high traffic, the necessary of motorcycle is highly increasing. The condition makes user ride motorcycle with highly speed in highly frequency. Then, these conditions make motorcycle machine reliability is highly decreasing. Finally, it made machine is run to damage and maintenance cost to be high. Analog tachometer is an electronic instrumentation that proposed to solve these problems. Actually, instrumentation system of tachometer is an electromechanical system. A wire in a control unit is embedded into shaft of crank. Then, magnet in control unit will convert rotary machine energy into electrical energy with d’Arsonval meter. Current sensor and small variable resistor are the kind of sensor that are used in tachometer. Small variable resistor is used for tuning and recalibration. Utilization small variable resistor in tachometer circuit is make calibration and recalibration current sensing of electrical current that rectified by diode. Tachometer for counting rotation per minute (RPM) motorcycle machine is built up. The tachometer has capability to count RPM motorcycle machine 1,000 – 13.000 RPM. The range is reliable as an indicator for user to minimize motorcycle machine wearing.

show abstract

“…Many studies reveal that manifold learning geometrically motivated can well handle the high-dimensional nonlinear samples and exploit the inherent low-dimensional manifold structure [16][17][18]. Some recent investigations have demonstrated that manifold learning methods can extract the sensitive low-dimensional manifold characteristics beneficial to pattern classification for bearing fault diagnosis [19][20][21][22]. As one of the representative manifold learning techniques, marginal Fisher analysis (MFA) [23] algorithm was successfully applied to face recognition [23,24] and gait recognition [25].…”

Section: Introductionmentioning

confidence: 99%

Modified Kernel Marginal Fisher Analysis for Feature Extraction and Its Application to Bearing Fault Diagnosis

Jiang

Guo

2016

Shock and Vibration

View full text Add to dashboard Cite

The high-dimensional features of defective bearings usually include redundant and irrelevant information, which will degrade the diagnosis performance. Thus, it is critical to extract the sensitive low-dimensional characteristics for improving diagnosis performance. This paper proposes modified kernel marginal Fisher analysis (MKMFA) for feature extraction with dimensionality reduction. Due to its outstanding performance in enhancing the intraclass compactness and interclass dispersibility, MKMFA is capable of effectively extracting the sensitive low-dimensional manifold characteristics beneficial to subsequent pattern classification even for few training samples. A MKMFA- based fault diagnosis model is presented and applied to identify different bearing faults. It firstly utilizes MKMFA to directly extract the low-dimensional manifold characteristics from the raw time-series signal samples in high-dimensional ambient space. Subsequently, the sensitive low-dimensional characteristics in feature space are inputted into K-nearest neighbor classifier so as to distinguish various fault patterns. The four-fault-type and ten-fault-severity bearing fault diagnosis experiment results show the feasibility and superiority of the proposed scheme in comparison with the other five methods.

show abstract

Feature Denoising and Nearest–Farthest Distance Preserving Projection for Machine Fault Diagnosis

Cited by 98 publications

References 21 publications

Fault Detection for Vibration Signals on Rolling Bearings Based on the Symplectic Entropy Method

Fault Detection for Vibration Signals on Rolling Bearings Based on the Symplectic Entropy Method

Analog tachometer as an indicator motorcycle machine wearing based on moving coil

Modified Kernel Marginal Fisher Analysis for Feature Extraction and Its Application to Bearing Fault Diagnosis

Contact Info

Product

Resources

About