研究生: |
蕭傑駿 Chieh-Chun Hsiao |
---|---|
論文名稱: |
運用機器學習於變壓器異常電流類型之辨識 Classification of Transformer Abnormal Current Types Using Machine Learning |
指導教授: |
郭政謙
Cheng-Chien Kuo |
口試委員: |
張宏展
Hong-Chan Chang 陳鴻誠 Hung-Cheng Chen 張建國 Chien-Kuo Chang |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2019 |
畢業學年度: | 107 |
語文別: | 中文 |
論文頁數: | 107 |
中文關鍵詞: | 變壓器 、機器學習 、湧入電流 、離散小波轉換 |
外文關鍵詞: | Transformer, Machine Learning, Inrush Current, Discrete Wavelet Transform |
相關次數: | 點閱:270 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本論文運用機器學習辨識變壓器異常電流類型。當變壓器空載投入系統或外部故障清除後電壓恢復時,因為殘餘磁通導致鐵心的飽和且可能造成一暫態電磁湧入電流,但跟變壓器發生外部故障時的故障電流不同,所以如何辨識異常電流類型,並避免保護電驛誤動作是相當重要的。湧入電流及故障電流擁有不同的特徵,將這些特徵當作類神經網路的輸入資料,類神經網路處理單元的轉移函數採用正切對數雙彎曲函數,並以多層前授型網路為架構,以辨識變壓器異常電流類型。
本論文利用Matlab Simulink來模擬變壓器湧入電流和變壓器發生外部故障的狀況,將模擬後的電流透過離散小波轉換擷取訊號中重要的資訊,再透過計算其統計特徵值當作類神經網路的輸入資料,透過類神經網路的學習與回想,最後可辨識變壓器的異常電流類型。本文所提出的方法確實可行,且辨識結果有不錯的準確度。
This thesis using machine learning to classify the abnormal current types of transformer. When the transformer connect to the power system or when the external faults is cleared, the residual magnetic flux cause the transformer core to saturate and may cause a transient electromagnetic inrush current. The inrush current is different from the external faults current, so how to classify the abnormal current types, and prevent the protection relay to malfunctioning is important. Inrush current and external faults current have different characteristics, and these characteristics are regarded as input data of neural network. The transfer function of neural network processing unit adopts tangent hyperbolic function, and is structured by the multi-layer feedforward network. In order to classify the abnormal current types of the transformer.
This thesis using Matlab Simulink to simulate the inrush current and the external faults of the transformer. The simulated currents using discrete wavelet transform to capture the important data of the signals, and then the statistical features are calculated as the input data of neural network. After the neural network learning and recalling. Finally it can classify the abnormal current types of the transformer. The method proposed in this thesis is feasible, and the classification results have good accuracy.
[1] Ma Jing﹐Zengping Wang﹐‘‘Hierarchical Protection for Smart Grids﹐’’IEEE Press eBook﹐Vol.1﹐pp.1-16﹐2017.
[2] 王進德,「類神經網路與模糊控制理論入門與應用」,全華科技圖書股份有限公司,第一~四章,民國95出版。
[3] 蘇木春、張孝德,「機器學習:類神經網路、模糊系統入門以及基因演算法則」,全華科技圖書股份有限公司,第一¬¬¬~四章,民國93年出版。
[4] J. H. Brunke﹐K. J. Frohlich﹐‘‘Elimination of Transformer Inrush Currents by Controlled Switching-Part I:Theoretical Considerations ﹐’’IEEE Transactions on Power Delivery﹐Vol.16﹐No.2﹐pp.276-280﹐April 2001.
[5] J. H. Brunke﹐K. J. Frohlich﹐‘‘Elimination of Transformer Inrush Currents by Controlled Switching-Part II:Application and Performance Considerations ﹐’’IEEE Transactions on Power Delivery﹐Vol.16﹐No.2﹐pp.281-285﹐April 2001.
[6] A. K. AL-Khalifah﹐E. F. El-Saadany﹐‘‘Investigation of Magnetizing Inrush Current in a Single-Phase Transformer﹐’’Large Engineering Systems Conference on Power Engineering﹐pp.165-171﹐July 2006.
[7] S. K. Agasti﹐R. Naresh﹐N. Ghosh﹐‘‘Investigation of Various Affecting Factors and Reduction Technique of Transformer Magnetizing Inrush Current﹐’’International Conference on Computation of Power﹐Energy Information and Communication﹐ pp. 307-310﹐April 2016.
[8] Yang Long﹐ Ning Jingdong﹐‘‘A Wavelet Transform Based Discrimination Between Internal Faults and Inrush Currents in Power Transformers﹐’’International Conference on Electric Information and Control Engineering﹐pp.1127-1129﹐April 2011.
[9] J. Faiz﹐ S. Lotfi-Fard﹐‘‘A Novel Wavelet-Based Algorithm for Discrimination of Internal Faults From Magnetizing Inrush Currents in Power Transformers﹐’’IEEE Transactions on Power Delivery﹐Vol.21﹐No.4﹐pp.1989-1996﹐October 2006.
[10] 林明河,「以類神經網路為基礎之變壓器數位保護技術研究」,碩士論文,國立台灣大學電機工程學系,2002年。
[11] P. L. Mao﹐R. K. Aggarwal﹐‘‘A Novel Approach to the Classification of the Transient Phenomena in Power Transformers Using Combined Wavelet Transform and Neural Network﹐’’IEEE Transactions on Power Delivery﹐Vol.16﹐No.4﹐pp.654-660﹐October 2001.
[12] S. Sudha﹐A. Ebenezer Jeyakumar﹐‘‘Wavelet and ANN Based Relaying for Power Transformer Protection﹐’’Journal of Computer Science﹐June 2007.
[13] Okan Ozgonenel﹐‘‘Wavelet based ANN Approach for Transformer Protection﹐’’World Academy of Science﹐Engineering and Technology International Journal of Electronics and Communication Engineering﹐Vol.2﹐No.6﹐pp.1277-1284﹐June 2008.
[14] S. K. Nanda﹐S. Gopalakrishna‘‘Virtual Instrument based Fault Classification in Power Transformers using Artificial Neural Networks﹐’’2013 IEEE 1st International Conference on Condition Assessment Techniques in Electrical Systems﹐pp.169-173﹐December 2013.
[15] J. F. Fernandes﹐F. B. Costa﹐R. P. de Medeiros﹐‘‘Power Transformer Disturbance Classification Based on the Wavelet Transform and Artificial Neural Networks﹐’’2016 International Joint Conference on Neural Networks﹐pp.640-646﹐July 2016.
[16] S. Sendilkumar﹐B. L. Mathur﹐Joseph Henry﹐‘‘Differential Protection for Power Transformer Using Wavelet Transform and PNN﹐’’World Academy of Science﹐Engineering and Technology International Journal of Electronics and Computer Engineering﹐Vol.4﹐No.3﹐pp.564-570﹐August 2010.
[17] P. B. Thote﹐M. B. Daigavane﹐‘‘Differential Protection of Three Phase Transformer Using Artificial Neural Network﹐’’World Academy of Science﹐2015 7st International Conference on Emerging Trends in Engineering & Technology﹐pp.76-81﹐November 2015.
[18] Stephen J. Chapman,「電機機械基本原理」,東華書局,第一¬¬¬~二章,民國101年出版。
[19] Dino Zorbas,「電機機械原理、應用與控制」,滄海書局,第一¬¬¬~二章,民國104年出版。
[20] Andreas Ebner﹐‘‘Transient Transformer Inrush Currents due to Closing Time-and Residual Flux Measurement-Deviation if Controlled Switching is used﹐’’Eth Zurich﹐Switzerland﹐2008.
[21] 胡昌華、張軍波、夏軍、張偉,「基於MATLAB的系統分析與設計:小波分析」,西安電子科技大學出版社,第一¬¬¬章,1999年。
[22] 顏奕豪,「應用二維離散小波轉換及類神經網路於多裂縫平板之損傷偵測」,碩士論文,國立成功大學系統及船舶機電工程學系,2013年。
[23] 楊邦樑,「小波轉換應用於平板與樑的雙破損偵測之研究」,碩士論文,國立成功大學系統及船舶機電工程學系,2007年。
[24] 單維彰,「凌波初步」,全華圖書公司,第一章,2000年。
[25] Robi Polikar﹐‘‘The Engineer’s Ultimate Guide To Wavelet Analysis:The Wavelet Tutorial﹐’’Rowan University﹐ College of Engineering Web Servers﹐2006.
[26] Asmaa Hamad﹐E. H. Houssein﹐A. E. Hassanien﹐A. A. Fahmy﹐‘‘Feature Extraction of Epilepsy EEG using Discrete Wavelet Transform﹐’’2016 12th International Computer Engineering Conference﹐pp.190-195﹐December 2016.
[27] Domy Kristomo﹐ Risanuri Hidayat﹐ Indah Soesanti﹐ ‘‘Feature Extraction and Classification of the Indonesian Syllables Using Discrete Wavelet Transform and Statistical Features﹐’’2016 2nd International Conference on Science and Technology-Computer﹐pp.88-92﹐October 2016.
[28] 李德治,「應用統計學」,博碩文化股份有限公司,第三章,民國106年出版。
[29] 黃旻華,「統計學的思路論理與應用」,五南圖書出版公司,第三章,民國106年出版。