PCA-based feature selection scheme for machine defect classification

By Arnaz Malhi, Robert X. Gao. IEEE Transactions on Instrumentation and Measurement, 2004

562 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Control and Systems Engineering, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/682343b02d255a24576195d9f587c12d7c05b4b4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

In Control and Systems Engineering

In Industrial and Manufacturing Engineering

Citations in the corpus

Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review (2020, methodology): “They implemented the PCA method to verify the ability of the proposed method.”
Bearing performance degradation assessment using locality preserving projections (2011, methodology): “…which features are more sensitive to defect development and propagation in a machine system, as various factors affect the effectiveness of the features, e.g., location of the sensors, time of signal samples, signal-to-noise ratios (SNRs) of the data acquisition system, etc. (Malhi & Gao, 2004).”
Online Fault Diagnosis Method Based on Transfer Convolutional Neural Networks (2020, methodology): “Then, the principal component analysis (PCA), linear discriminant analysis, kernel discriminant analysis, and other dimension reduction methods [13], [14] are used to get rid of useless features and improve the computational efficiency.”
Wavelets for fault diagnosis of rotary machines: A review with applications (2014, unknown): “perceptron neural network for machine defect severity classification [109].”
Deep Learning Algorithms for Bearing Fault Diagnosticsx—A Comprehensive Review (2019, background): “One of the earliest adoption of PCA on bearing fault diagnostics can be found in [39].”
Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks (2018, methodology): “To verify the above statement empirically, we tested our proposed LFGRU under five additional different numbers of segments: T = [5, 10, 50, 100, 200] and our previous setting T = 20 over one tool prediction task C1.”
Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics - A Comprehensive Review (2019, background): “One early implementation of the k -NN classiﬁer on bearing fault diagnosis is found in [42], where k -NN serves as the core algorithm for a data mining based ceramic bearing fault classiﬁer based on acoustic emission signals.”
Remaining useful life estimation based on nonlinear feature reduction and support vector regression (2013, methodology): “[14] proposed a PCAbased feature selection approach for bearing fault classification.”
Energy-Fluctuated Multiscale Feature Learning With Deep ConvNet for Intelligent Spindle Bearing Fault Diagnosis (2017, methodology): “Malhi and Gao [4] proposed a Principal Component Analysis (PCA)-based feature selection scheme, and Van and Kang [5] employed wavelet kernel local fisher discriminant analysis to classify the machine defects.”
Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network (2015, unknown): “A challenge in bearing diagnosis and prognosis is to select the most sensitive parameters for the various types of fault, especially when the characteristics of failures are difficult to detect [17].”