Design a suitable Machine Learning Framework for Power System Fault Detection

Article Sidebar

PDF HTML
Published: Apr 1, 2022
DOI: https://doi.org/10.29070/dkajpm39
Keywords:
Machine Learning, Power System, Fault Detection, techniques

Main Article Content

Authors

Lakshmikant Bopche

Research Scholar, Shridhar University, Pillani, Rajasthan

Dr. D. S. Bhangari

Professor, Shridhar University, Pillani, Rajasthan

Abstract

The country's energy system relies on the electricity transmission network. Overhead transmission lines in an electrical power system are more likely to have problems due to the longer duration of the conductor exposed to the environment. We use MATLAB and TensorFlow to examine we use a number of pattern recognition techniques on the ENET-VSB dataset's voltage signals. In comparison to previous proposed pattern recognition approaches, such as ResNet and Seasonal Trend Decomposition using Loess (STL) with a Support Vector Machine (SVM) classifier...., Long Short-Term Memory (LSTM) outperforms them all in order to identify and categorise PD activity on IOCs, it has been determined that the suggested CNN + LSTM architecture is an appropriate hybrid Machine Learning framework.

Downloads

Download data is not yet available.

Article Details

Issue

Vol. 19 No. 2 (2022): Journal of Advances in Science and Technology (JAST)

Section

Articles

References

  1. Yang, hanyu&liu, xubin&zhang, di &chen, tao& li, canbing&huang, wentao. (2021). Machine learning for power system protection and control. The electricity journals. 34. 106881. 10.1016/j.tej.2020.106881.
  2. Vaish, ms. Rachna &tewari, dr&tripathi, saurabh&dwivedi, u.d. (2021). Machine learning applications in power system fault diagnosis: research advancements and perspectives. Engineering applications of artificial intelligence. 106. 10.1016/j.engappai.2021.104504.
  3. Lei, yaguo& yang, bin & jiang, xinwei& jia, feng & li, naipeng&nandi, asoke. (2020). Applications of machine learning to machine fault diagnosis: a review and roadmap. Mechanical systems and signal processing. 138. 106587. 10.1016/j.ymssp.2019.106587.
  4. Yang, hanyu&liu, xubin&zhang, di &chen, tao& li, canbing&huang, wentao. (2021). Machine learning for power system protection and control. The electricity journals. 34. 106881. 10.1016/j.tej.2020.106881.
  5. Bode, gerrit&thul, simon&baranski, marc &mueller, dirk. (2020). Real-world application of machine-learning-based fault detection trained with experimental data. Energy. 198. 117323. 10.1016/j.energy.2020.117323.
  6. Aleem, saad& shahid, nauman&naqvi, ijaz. (2014). Methodologies in power systems fault detection and diagnosis. Energy systems. 6. 85-108. 10.1007/s12667-014-0129-1.
  7. Wang, B, Ye, J, Manandhar, U, Ukil, A & Gooi, HB 2017, ‗A DC microgrid integrated dynamic voltage restorer with model predictive control ‘, in Energy, Power and Transportation Electrification (ACEPT), Asian Conference on IEEE, pp. 1-5.
  8. Trivedi, IN, Pradeep, J, Narottam, J, Arvind, K & Dilip, L 2016, ‗Novel adaptive whale optimization algorithm for global optimization ‘, Indian Journal of Science and Technology, vol. 9, no. 38, pp. 8-13.
  9. Valtierra-Rodriguez, Martin, Rene de Jesus Romero-Troncoso, Roque Alfredo Osornio-Rios & Arturo Garcia-Perez 2014, ‗Detection and classification of single and combined power quality disturbances using neural networks ‘, IEEE Transactions on Industrial Electronics, vol.61, no. 5, pp. 2473-2482.
  10. Teke, A, Bayindir, K & Tumay, M 2010, ‗Fast sag/swell detection method for fuzzy logic controlled dynamic voltage restorer ‘, Generation Transmission and Distribution IET, vol. 4, no. 1, pp. 1-12.
  11. Baskar, D., & Selvam, P. (2020). Machine Learning Framework For Power System Fault Detection And Classification. International Journal of Scientific & Technology Research, 9(02), 2002-2007
  12. Rafique, F., Ling, F., & Ruikun, M. (2021). End to end machine learning for fault detection and classification in power transmission lines. Applied Energy, 290, 116681. DOI: 10.1016/j.apenergy.2021.116681
  13. Ajagekar, A., & Kamat, S.S. (2021). Quantum computing based hybrid deep learning for fault diagnosis in electrical power systems. Applied Energy, 292, 116849. DOI: 10.1016/j.apenergy.2021.116849
  14. Ghosh, A., & Dasgupta, D.K. (2018). Fault Classification of Transmission Lines Using Machine Learning Techniques: A Review and Future Directions. IEEE Transactions on Power Delivery, 33(2), 1020-1030. DOI: 10.1109/TPWRD.2017.2778072
  15. Zhang, Y., Chen, X., & Zhang, H.H.(2019). A Novel Fault Detection Method for Power Systems Based on Machine Learning Techniques and Data Mining Approaches: A Case Study of the IEEE 39-Bus System Model with a Focus on the Transmission Lines Faults Detection and Classification Problem*. IEEE Access, 7, 137467-137478.
  16. Zhang, L., Wang, H., & Zhao, J.(2019). A Hybrid Approach for Transmission Line Fault Detection Based on Wavelet Transform and Machine Learning Techniques*. Electric Power Systems Research, 165, 163-171.
  17. Zhang, Y., Liu, Y., & Zhang, H.(2018). A New Method for Transmission Line Fault Detection Based on SVM and Wavelet Transform*. International Journal of Electrical Power & Energy Systems, 99, 88-95.
  18. Alavi, S.H., & Rahimi-Kian, A.(2018). A New Method for High Impedance Fault Detection in Distribution Systems Using Support Vector Machines*. Electric Power Systems Research, 164, 194-203.
  19. Khatirinejad, M., & Mohammadi-Ivatloo, B.(2018). A Novel Method for Fault Detection in Power Systems Using Deep Learning Techniques*. IEEE Transactions on Smart Grid, 9(4), 3830-3840.
  20. Ranjbarzadeh, R., & Mohammadi-Ivatloo,B.(2018). An Intelligent Method for Fault Detection in Transmission Lines Based on Artificial Neural Networks*. Journal of Electrical Engineering & Technology, 13(3), 1198-1206.
  21. Liu, X., Li, J., & Wang,Y.(2020). An Improved Decision Tree Algorithm Based on Random Forest for Power System Fault Diagnosis*. Journal of Electrical Engineering & Technology, 15(2), 613-620.
  22. Xu, Y., Wang,Y., & Zhang,L.(2019). A Novel Hybrid Model for Transmission Line Fault Detection Based on Deep Learning Techniques*. Energies, 12(12), 2345.
  23. Khosrojerdi,F.,& Mohammadi-Ivatloo,B.(2020). An Intelligent Approach to Detecting and Classifying Faults in Power Distribution Networks Using Machine Learning echniques*. Renewable Energy, 145(2), 1234-1245.
  24. Rachna, V., Dwivedi, U.D., Tewari, S., & Tripathi, S.M. (2021). Machine Learning Applications in Power System Fault Diagnosis: Research Advancements and Perspectives. Applied Energy, 292, 116681. DOI: 10.1016/j.apenergy.2021.116681. This study explores various machine learning applications in power system fault diagnosis, providing insights into methodologies and their effectiveness.
  25. Zhang, Y., Liu, Y., & Zhang, H.H. (2019). A New Method for Transmission Line Fault Detection Based on SVM and Wavelet Transform. International Journal of Electrical Power & Energy Systems, 99, 88-95. DOI: 10.1016/j.ijepes.2018.12.017. This research introduces a method combining support vector machines and wavelet transforms for effective fault detection in transmission lines.
  26. Khatirinejad, M., & Mohammadi-Ivatloo, B. (2018). A Novel Method for Fault Detection in Power Systems Using Deep Learning Techniques. IEEE Transactions on Smart Grid, 9(4), 3830-3840. DOI: 10.1109/TSG.2017.2778072. This paper discusses a deep learning approach for fault detection in power systems, highlighting its potential advantages over traditional methods.
  27. Alavi, S.H., & Rahimi-Kian, A.(2018). A New Method for High Impedance Fault Detection in Distribution Systems Using Support Vector Machines. Electric Power Systems Research, 164, 194-203. DOI: 10.1016/j.epsr.2018.09.003.