Online Diagnosis for Transformer Winding Deformation Based on Information Entropy and SVM

Transformer winding may be deformed after suffering short circuit, which brings hidden danger to the operation and control of power system. Existing offline diagnosis methods for winding deformation not only reduce operation efficiency but also impact residents’ life. To improve the accuracy and efficiency of winding deformation diagnosis, an intelligent online diagnosis method for winding deformation based on information entropy and support vector machine is proposed. This method uses permutation entropy, wavelet energy entropy, and expert knowledge to extract the fault feature from online monitoring signals and then uses support vector machine to learn the diagnosis rules from the fault features, thereby reducing the labor cost and improving the diagnosis efficiency. In the experiment part, the real operation data of 29 transformers is used to train and test the online winding deformation diagnosis model. The results show that the diagnosis accuracy of whether the transformer has been deformed is 93.10%, and the diagnosis accuracy of the deformation position is 88.89%, which proves its validity and practicability.

[1]  J. Richman,et al.  Physiological time-series analysis using approximate entropy and sample entropy. , 2000, American journal of physiology. Heart and circulatory physiology.

[2]  G. B. Gharehpetian,et al.  A Feasibility Study on the Application of Radar Imaging for the Detection of Transformer Winding Radial Deformation , 2012, IEEE Transactions on Power Delivery.

[3]  Zhigang Liu,et al.  Wavelet Entropy-Based Traction Inverter Open Switch Fault Diagnosis in High-Speed Railways , 2016, Entropy.

[4]  William Stafford Noble,et al.  Support vector machine , 2013 .

[5]  Julius Georgiou,et al.  Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines , 2012, Expert Syst. Appl..

[6]  Ales Procházka,et al.  Permutation Entropy and Signal Energy Increase the Accuracy of Neuropathic Change Detection in Needle EMG , 2018, Comput. Intell. Neurosci..

[7]  Francisco Herrera,et al.  On the importance of the validation technique for classification with imbalanced datasets: Addressing covariate shift when data is skewed , 2014, Inf. Sci..

[8]  U. Rajendra Acharya,et al.  Automated Diagnosis of Myocardial Infarction ECG Signals Using Sample Entropy in Flexible Analytic Wavelet Transform Framework , 2017, Entropy.

[9]  Fei Cheng-wei.  Rotor vibration fault diagnosis method based on wavelet energy spectrum entropy and SVM , 2011 .

[10]  Shan Suthaharan,et al.  Support Vector Machine , 2016 .

[11]  Jian-Jiun Ding,et al.  Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and Support Vector Machine , 2012, Entropy.

[12]  X. An,et al.  Bearing fault diagnosis of a wind turbine based on variational mode decomposition and permutation entropy , 2017 .

[13]  G. B. Gharehpetian,et al.  Application of Ultra-Wideband Sensors for On-Line Monitoring of Transformer Winding Radial Deformations–A Feasibility Study , 2012, IEEE Sensors Journal.

[14]  Gevork B. Gharehpetian,et al.  A new algorithm for localization of radial deformation and determination of deformation extent in transformer windings , 2008 .

[15]  S M Pincus,et al.  Approximate entropy as a measure of system complexity. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[16]  B. Pompe,et al.  Permutation entropy: a natural complexity measure for time series. , 2002, Physical review letters.

[17]  Dongsheng Yuan,et al.  Cumulative Deformation Analysis for Transformer Winding Under Short-Circuit Fault Using Magnetic–Structural Coupling Model , 2016, IEEE Transactions on Applied Superconductivity.

[18]  Gholamreza Moradi,et al.  A new on-line monitoring method of transformer winding axial displacement based on measurement of scattering parameters and decision tree , 2011, Expert Syst. Appl..

[19]  Marcelo Risk,et al.  Classification of Normal and Pre-Ictal EEG Signals Using Permutation Entropies and a Generalized Linear Model as a Classifier , 2017, Entropy.