Feature extraction and classification method for switchgear faults based on sample entropy and cloud model

This study proposes a fault diagnosis method for extracting and classifying the fault features of switchgears in accordance with the monitoring data of three-phase voltage and current, temperature, humidity, and flashing from the smart breaker and sensors. The fault features are calculated using multivariate multiscale sample entropy (MMSE) for the data mining of multivariate monitoring process. The similarity measure of the composite delay vectors of multivariate time series in MMSE is improved by introducing a cloud model to soften the similar tolerance criterion. The modified MMSE is defined as multivariate multiscale cloud sample entropy (MMCSE). The MMCSE features of switchgear monitoring data can be achieved in different time scales in describing various switchgear faults. Subsequently, a classification method based on fuzzy support vector machine (FSVM) is further adopted to identify different types of switchgear faults using the MMCSE features. In addition, a dropping semi-normal membership cloud model is applied to modify the uncertainty quantification of the relationship among fault samples in FSVM. The effectiveness of the proposed method is validated with the monitoring data in a 10 kV switchboard.

[1]  Chih-Chuan Chen,et al.  A Regularized Monotonic Fuzzy Support Vector Machine Model for Data Mining With Prior Knowledge , 2015, IEEE Transactions on Fuzzy Systems.

[2]  Ujjwal Maulik,et al.  Predicting Protein-Protein Interaction Sites with a Novel Membership Based Fuzzy SVM Classifier , 2015, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[3]  Kai Xu,et al.  An image segmentation approach based on histogram analysis utilizing cloud model , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[4]  Francesco Carlo Morabito,et al.  Entropic Measures of EEG Complexity in Alzheimer's Disease Through a Multivariate Multiscale Approach , 2013, IEEE Sensors Journal.

[5]  Chun-Yao Lee,et al.  Optimal Feature Selection for Power-Quality Disturbances Classification , 2011, IEEE Transactions on Power Delivery.

[6]  Danilo P. Mandic,et al.  Multivariate Multiscale Entropy Analysis , 2012, IEEE Signal Processing Letters.

[7]  Danilo P Mandic,et al.  Multivariate multiscale entropy: a tool for complexity analysis of multichannel data. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  Hak-Keung Lam,et al.  Stability and Stabilization Analysis of Positive Polynomial Fuzzy Systems With Time Delay Considering Piecewise Membership Functions , 2017, IEEE Transactions on Fuzzy Systems.

[9]  Chen Lu,et al.  Health assessment for rolling bearing based on local characteristic-scale decomposition — Approximate entropy and manifold distance , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).

[10]  Long Zhang,et al.  Generalized Transmissibility Damage Indicator With Application to Wind Turbine Component Condition Monitoring , 2016, IEEE Transactions on Industrial Electronics.

[11]  Li Hesong,et al.  Computation on Attribute Importance of Classification Based on Cloud Model , 2008, CIMCA 2008.

[12]  Sheng-De Wang,et al.  Fuzzy support vector machines , 2002, IEEE Trans. Neural Networks.

[13]  Matti Lehtonen,et al.  The Smart Solution for the Prediction of Slowly Developing Electrical Faults in MV Switchgear Using Partial Discharge Measurements , 2013, IEEE Transactions on Power Delivery.

[14]  Guo-Liang Tian,et al.  A new fuzzy support vector machine based on mixed kernel function , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[15]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[16]  Ahmet Burak Can,et al.  Action recognition based on feature extraction from time series , 2014, 2014 22nd Signal Processing and Communications Applications Conference (SIU).

[17]  Pere Caminal,et al.  Refined Multiscale Entropy: Application to 24-h Holter Recordings of Heart Period Variability in Healthy and Aortic Stenosis Subjects , 2009, IEEE Transactions on Biomedical Engineering.

[18]  Xiuping Jia,et al.  Using Hurst and Lyapunov Exponent For Hyperspectral Image Feature Extraction , 2012, IEEE Geoscience and Remote Sensing Letters.

[19]  Zhi-Hua Zhou,et al.  Learning Imbalanced Multi-class Data with Optimal Dichotomy Weights , 2013, 2013 IEEE 13th International Conference on Data Mining.

[20]  V. Ajjarapu,et al.  PMU-Based Model-Free Approach for Real-Time Rotor Angle Monitoring , 2015, IEEE Transactions on Power Systems.

[21]  V. Poghosyan,et al.  Numerical study of the correspondence between the dissipative and fixed-energy Abelian sandpile models. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  Okan Ozgonenel,et al.  A Novel Selection Algorithm of a Wavelet-Based Transformer Differential Current Features , 2014, IEEE Transactions on Power Delivery.

[23]  Kazunori Matsumoto,et al.  Classification system for time series data based on feature pattern extraction , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[24]  Rangarao Muralishankar,et al.  Differential Entropy-Driven Spectrum Sensing Under Generalized Gaussian Noise , 2016, IEEE Communications Letters.

[25]  Jing Zhang,et al.  A Fast Parameters Selection Method of Support Vector Machine Based on Coarse Grid Search and Pattern Search , 2013, 2013 Fourth Global Congress on Intelligent Systems.

[26]  Hui Ma,et al.  Investigation of feature selection techniques for improving efficiency of power transformer condition assessment , 2014, IEEE Transactions on Dielectrics and Electrical Insulation.

[27]  Yang Yang,et al.  Chirplet Path Fusion for the Analysis of Time-Varying Frequency-Modulated Signals , 2017, IEEE Transactions on Industrial Electronics.