A Support Vector Machine Method for SF6 Gas Quality Classification
A Machine Learning Method to Generate Anomaly Identification of SF6 Gas Quality
Keywords:
gas-insulated-switchgear, SF6, machine learning, SVMAbstract
To meet the need for high reliability, increased load demand, and optimal maintenance strategy improvements, a machine learning-based method is introduced as an assessment approach for gas-insulated switchgear (GIS). Using historical data from different time periods, indicators representing the health level of GIS in terms of the quality of Sulphur Hexafluoride (SF6) gas are extracted using the support vector machine (SVM) algorithm. The data imbalance in the sample is normalized using the Synthetic Minority Oversampling Technique (SMOTE) to improve the accuracy of the training data. By combining inspection results and online monitoring data, the operational condition panorama of each GIS compartment is classified as the model output. Based on data obtained from three hundred and twenty-two GIS compartments in the Surabaya area, the method's effectiveness is demonstrated through sample test results.
Downloads
References
Belyadi, H., & Haghighat, A. (2021). Machine Learning Guide for Oil and Gas Using Python. In Machine Learning Guide for Oil and Gas Using Python (p. iii). Elsevier. https://doi.org/10.1016/b978-0-12-821929-4.01001-5
Cho, H., Lee, S., & Lim, S. (2006). Dynamic analysis on the closing resistors of Gas Insulated Switchgear. Journal of Mechanical Science and Technology (KSME Int. J), 20(10), 1607–1613.
Geng, S., & Wang, X. (2020). Research on data-driven method for circuit breaker condition assessment based on back propagation neural network. Computers and Electrical Engineering, 86. https://doi.org/10.1016/j.compeleceng.2020.106732
Harahap, K. F., Aminullah, A., & Priyosulistyo, H. (2022). Artificial Neural Network Approach for Estimating Optimum Dimension and Reinforcement Ratio of Buildings. Inersia, 18(1). https://doi.org/10.21831/inersia.v18i1
Ibrahim, V. M., Abdul-Malek, Z., & Muhamad, N. A. (2017). Status review on gas insulated switchgear partial discharge diagnostic technique for preventive maintenance. Indonesian Journal of Electrical Engineering and Computer Science, 7(1), 9–17. https://doi.org/10.11591/ijeecs.v7.i1.pp9-17
Kurniawati, A. H., Mumtaza Ghalya, A., Gayatri, N. C., Januar, D., & Kusnadi. (2022). SF6 Gas Parameter for Condition Assessment in GIS. Proceedings of the National Seminar on Electrical Engineering, 7.
Panmala, N., Suwanasri, T., & Suwanasri, C. (2023). A Fuzzy Logic Approach to Health Index Determination for a Gas-Insulated Switchgear. Energies, 16(18). https://doi.org/10.3390/en16186605
Purnomoadi, A. P., Mor, A. R., & Smit, J. J. (2020). Health index and risk assessment models for Gas Insulated Switchgear (GIS) operating under tropical conditions. International Journal of Electrical Power and Energy Systems, 117. https://doi.org/10.1016/j.ijepes.2019.105681
Srinuntawong, W., Srangtook, W., Kerdmanee, S., Suwanasri, T., Suwansari, C., Fuangpian, P., Kumpalavalee, S., & Somsak, T. (2019). Data Warehouse and Asset Management Intelligence Architecture for Condition Assessment of Major Equipment in Power Plant. IEEE PES GTD Asia, 532–537.
Wang, Q., He, Z., Lin, S., & Li, Z. (2017). Failure Modeling and Maintenance Decision for GIS Equipment Subject to Degradation and Shocks. IEEE Transactions on Power Delivery, 32(2), 1079–1088. https://doi.org/10.1109/TPWRD.2017.2655010
Zeng, F., Tang, J., Zhang, X., Zhou, S., & Pan, C. (2018). Typical Internal Defects of Gas-Insulated Switchgear and Partial Discharge Characteristics. In Simulation and Modelling of Electrical Insulation Weaknesses in Electrical Equipment. InTech. https://doi.org/10.5772/intechopen.79090
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 ITB Graduate School Conference
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
