State Evaluation of Electrical Equipment in Substations Based on Data Mining
Source abstract
Abstract
This paper explores the combination of a data mining-based state evaluation method for electrical equipment in substations, analyzing the effectiveness and accuracy. First, a Gaussian mixture model is applied to fit all raw data of electrical equipment. The Expectation Maximization algorithm summarizes the data distribution characteristics and identifies outliers. The a priori algorithm is then employed for data mining to derive frequent itemsets and association rules between equipment quality and measurement data. For new equipment samples, conditional probabilities of each feature are independently calculated and combined to classify and evaluate equipment quality. The results suggest that equipment reliability in smart substations can be inferred from historical and real-time operational data using improved association rule algorithms and Naive Bayes classifiers. Finally, the proposed method was applied to analyze statistical data from a 110 kV substation of a power supply company. The states prediction accuracy exceeded 95% when compared with actual equipment quality. The effectiveness evaluation metrics demonstrated that this method outperforms single-category algorithms in terms of accuracy and discrimination ability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Decision-Making Techniques · Advanced Computational Techniques and Applications · Rough Sets and Fuzzy Logic
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Energy Electrical Engineering, Woosuk University, Jeonju 55338, Republic of Korea
References (35)
Show source-provided references
1. Suan, A.B., Al-Amer, B., and Assiri, I.A. (2022, January 12–14). Multi-Variate, Recurrent Neural Network in a Short-Term Time-Series Substation Demand Forecasting. Proceedings of the 2022 Saudi Arabia Smart Grid (SASG), Riyadh, Saudi Arabia.10.1109/SASG57022.2022.10200117 ↗
2. Condition monitoring and predictive maintenance methodologies for hydropower plants equipment10.1016/j.renene.2021.02.102 ↗
3. Guo, Z., Ma, H., and Liu, W. (2023, January 3–5). Cause Analysis of Substation Faults Based on Multimodal Fusion Detection and Knowledge Graph. Proceedings of the 2023 10th International Forum on Electrical Engineering and Automation (IFEEA), Nanjing, China.10.1109/IFEEA60725.2023.10429117 ↗
4. Existing developments in adaptive smart grid protection: A review10.1016/j.epsr.2020.106901 ↗
5. Machine learning for predictive maintenance scheduling of distribution transformers10.1108/JQME-06-2021-0052 ↗
6. Min, Z., Jian, S., Li, C., Bin, Z., Liang, Z.S., and Zhe, H. (2019, January 21–22). Status evaluation of smart substation measurement and control device. Proceedings of the IOP Conference Series: Materials Science and Engineering, Jakarta, Indonesia.10.1088/1757-899X/563/4/042077 ↗
7. Real-time life-cycle assessment of high-voltage circuit breakers for maintenance using online condition monitoring data10.1109/TIA.2018.2878746 ↗
8. Fu, D., Wang, F., Yuan, S., Wang, G., and Shao, M. (2019, January 20–22). Fuzzy Comprehensive Evaluation Method for On-Line Monitoring Data Quality of Substation Equipment. Proceedings of the 2019 6th International Conference on Information Science and Control Engineering (ICISCE), Shanghai, China.
9. Yang, L., Li, W., Zhang, S., Wan, J., and Zhao, H. (2023, January 23–24). Application of Big Data and Artificial Intelligence in Substation Operation and Maintenance. Proceedings of the Journal of Physics: Conference Series, Bengaluru, India.10.1088/1742-6596/2555/1/012002 ↗
10. Panoramic Assessment Method of Substation Equipment Health Status Based on Multisource Monitoring and Deep Convolution Neural Network under Edge Computing Architecture
11. Gao, Q., Zhong, C., Wang, Y., Wang, P., Yu, Z., and Zhang, J. (2021, January 24–25). Defect analysis of the same batch of substation equipment based on big data analysis algorithm. Proceedings of the IOP Conference Series: Earth and Environmental Science, Surakarta, Indonesia.10.1088/1755-1315/651/2/022093 ↗
12. Agrawal, R., and Srikant, R. (1994, January 12–15). Fast algorithms for mining association rules. Proceedings of the 20th International Conference on Very Large Data Bases, VLDB, San Francisco, CA, USA.
13. An improved association rule mining algorithm for large data
14. Yuan, C., Xu, J., Zhou, J., and Liu, L. (2023, January 27–30). Correlation Analysis of Electrical Equipment Defects Based on Association Rule Algorithm and Big Data. Proceedings of the 2023 Panda Forum on Power and Energy (PandaFPE), Chengdu, China.10.1109/PandaFPE57779.2023.10141015 ↗
15. Shopping and Basket Analysis by Using an Improved Apriori Algorithm in WEKA10.53898/josse2021126 ↗
16. K-means and alternative clustering methods in modern power systems10.1109/ACCESS.2023.3327640 ↗
17. Medical data stream distribution pattern association rule mining algorithm based on density estimation10.1109/ACCESS.2019.2943817 ↗
18. Martinez-Arroyo, M., and Sucar, L.E. (2006, January 20–24). Learning an optimal naive bayes classifier. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.10.1109/ICPR.2006.748 ↗
19. Yang, T., Qian, K., Lo, D.C.-T., Xie, Y., Shi, Y., and Tao, L. (2016, January 9–10). Improve the prediction accuracy of Naïve Bayes classifier with association rule mining. Proceedings of the 2016 IEEE 2nd International Conference on Big Data Security on Cloud (BigDataSecurity), IEEE International Conference on High Performance and Smart Computing (HPSC), and IEEE International Conference on Intelligent Data and Security (IDS), New York, NY, USA.10.1109/BigDataSecurity-HPSC-IDS.2016.38 ↗
20. Research on status information monitoring of power equipment based on Internet of Things10.1016/j.egyr.2022.01.018 ↗
21. Research on fault diagnosis method of 750kV substation based on Bayesian network and fault recording information fusion10.1088/1742-6596/1550/5/052020 ↗
22. Hu, B., Guo, Q., and Zhu, Y. (2020). Key Constraint Variable Identification, Transient Stability Assessment and Feasible Region Generation of Power Grid Operation Based on Machine Learning Method. Proceedings of the PURPLE MOUNTAIN FORUM 2019-International Forum on Smart Grid Protection and Control: Volume II, 2020, Springer.10.1007/978-981-13-9783-7_49 ↗
23. Ma, J., Zhang, G., Zhao, Y., and Jin, L. (2020, January 12–14). Design of the state simulation for the primary equipment of smart substation. Proceedings of the 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China.10.1109/ITOEC49072.2020.9141703 ↗
24. Condition monitoring of high voltage circuit breakers: Past to future
25. Meng, X.-K., Jia, Y.-B., Liu, Z.-H., Yu, Z.-Q., Han, P.-J., Lu, Z.-M., and Jin, T. (2022). High-Voltage Cable Condition Assessment Method Based on Multi-Source Data Analysis. Energies, 15.10.3390/en15041369 ↗
26. Delalleau, O., Courville, A., and Bengio, Y. (2012). Efficient EM training of Gaussian mixtures with missing data. arXiv.
27. Sms classification based on naive bayes classifier and apriori algorithm frequent itemset10.7763/IJMLC.2014.V4.409 ↗
28. A methodological approach for mining the user requirements using apriori algorithm10.4018/JCIT.2020100101 ↗
29. Research and case analysis of apriori algorithm based on mining frequent item-sets
30. An overview of association rule mining algorithms
31. Kazerooni, M., Zhu, H., and Overbye, T.J. (March, January 28). Literature review on the applications of data mining in power systems. Proceedings of the 2014 Power and Energy Conference at Illinois (PECI), Champaign, IL, USA.10.1109/PECI.2014.6804567 ↗
32. Morais, J., Klautau, A., Cardoso, C., and Pires, Y. (2024, July 01). An Overview of Data Mining Techniques Applied to Power Systems. Available online: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=0a255dbf8bebd476ede2bab9995949265c6f7ecf.
33. Xie, J., Shu, H., Zhang, W., Song, Q., and Luo, L. (2018, January 6–8). Evaluation algorithm of high voltage switchgear based on bayesian fusion. Proceedings of the 2018 International Conference on Power System Technology (POWERCON), Guangzhou, China.10.1109/POWERCON.2018.8602161 ↗
34. (2024, July 10). Available online: https://woosuk-my.sharepoint.com/:u:/g/personal/dangjong_stu_woosuk_ac_kr/EUamKUZ9FyZGnrSpWVmZ0rMBzgZmQ19F2VWBZqDG4544fQ?e=ZeWzQH.
35. A review on evaluation metrics for data classification evaluations10.5121/ijdkp.2015.5201 ↗