Abstract
After long-term operation, the electrical performance of UHV transmission line insulator string decreases and zero-value insulators are prone to occur. The existence of zero-value insulators leads to the flashover of insulator strings, which causes large-scale power outages in serious cases. In order to improve the power quality and detect the zero-value insulators of transmission lines more timely and efficiently, the influence of zero-value insulators on the electric field distribution of insulator strings is simulated and calculated by finite element method. At the same time, taking the grounding current of insulator string as the cut-in point, the principal component analysis method is used to screen the effective characteristic quantities, and then as the input of artificial neural network, and the fault area of insulator string is determined by the neural network. The simulation results show that the recognition accuracy of artificial neural network based on insulator string grounding current is high, and it has certain engineering application value.
Author contribution: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Research funding: None declared.
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
Probabilistic neural network training samples.
| Actual fault area | The result of insulator fault location diagnosis is based on PNN | Diagnostic fault area | ||
|---|---|---|---|---|
| 1 | 0.000265 | 0.000003 | 1.02326 | 1 |
| 1 | 0.000652 | −0.000059 | 0.995214 | 1 |
| 1 | 0.000102 | 1.365942 | 1.00559 | 3 |
| 2 | 0.000139 | 1.02695 | 0.000269 | 2 |
| 2 | 0.000231 | 0.89255 | 0.00952 | 2 |
| 2 | 0.000005 | 0.96224 | 0.00074 | 2 |
| 3 | 0.000365 | 1.78562 | 1.00055 | 3 |
| 3 | 0.000236 | 0.993658 | 0.999595 | 3 |
| 3 | 1.259562 | 0.000009 | 1.06526 | 5 |
| 4 | 1.00078 | 0.000189 | 0.000065 | 4 |
| 4 | 1.000082 | 0.000075 | 0.000639 | 4 |
| 4 | 0.000059 | 0.000926 | 1.02659 | 1 |
| 5 | 1.632629 | 0.000082 | 1.265959 | 5 |
| 5 | 1.055998 | 0.000159 | 0.855965 | 5 |
| 5 | 0.635823 | 0.000841 | 0.952552 | 5 |
| 6 | 0.985622 | 0.755623 | 0.000049 | 6 |
| 6 | 1.285658 | 1.154873 | 0.000002 | 6 |
| 6 | 1.362148 | 1.522154 | 0.000081 | 6 |
Predictive model of zero-value insulator location.
| Training sample number | Zero-value insulator location | Average value of rectification | Standard deviation | Impulse factor |
|---|---|---|---|---|
| 1 | 4th | 0.814 | 0.90863 | 3.519 |
| 2 | 5th | 0.810 | 0.90634 | 3.3431 |
| 3 | 6th | 0.793 | 0.90863 | 3.411 |
| 4 | 7th | 0.792 | 0.89998 | 3.4681 |
| 5 | 8th | 0.758 | 0.89118 | 3.5104 |
| 6 | 9th | 0.754 | 0.88662 | 3.3182 |
| 7 | 13th | 0.734 | 0.87646 | 3.8967 |
| 8 | 14th | 0.734 | 0.87665 | 3.6159 |
| 9 | 15th | 0.733 | 0.87562 | 3.5143 |
| 10 | 16th | 0.730 | 0.87428 | 3.9144 |
| 11 | 17th | 0.728 | 0.87244 | 3.7039 |
| 12 | 18th | 0.728 | 0.87196 | 4.0009 |
| 13 | 22nd | 0.720 | 0.86862 | 3.428 |
| 14 | 23rd | 0.713 | 0.8682 | 3.4988 |
| 15 | 24th | 0.710 | 0.86458 | 3.4004 |
| 16 | 25th | 0.711 | 0.86445 | 3.5325 |
| 17 | 26th | 0.712 | 0.86205 | 3.555 |
| 18 | 27th | 0.711 | 0.86121 | 3.6289 |
| 19 | 31st | 0.702 | 0.85504 | 3.4601 |
| 20 | 32nd | 0.700 | 0.85578 | 3.7586 |
| 21 | 33rd | 0.709 | 0.85018 | 3.5276 |
| 22 | 34th | 0.691 | 0.84382 | 3.5407 |
| 23 | 35th | 0.697 | 0.84214 | 3.4162 |
| 24 | 36th | 0.694 | 0.84116 | 3.7979 |
| 25 | 40th | 0.689 | 0.83648 | 3.9474 |
| 26 | 41st | 0.682 | 0.83640 | 3.6679 |
| 27 | 42nd | 0.690 | 0.83586 | 3.4684 |
| 28 | 43rd | 0.682 | 0.83205 | 3.6167 |
| 29 | 44th | 0.685 | 0.83063 | 3.3395 |
| 30 | 45th | 0.681 | 0.82716 | 3.3835 |
| 31 | 49th | 0.669 | 0.81041 | 3.4735 |
| 32 | 50th | 0.651 | 0.80968 | 4.246 |
| 33 | 51st | 0.657 | 0.80998 | 4.0145 |
| 34 | 52nd | 0.632 | 0.80659 | 3.7044 |
| 35 | 53rd | 0.630 | 0.80521 | 3.9978 |
| 36 | 54th | 0.632 | 0.80117 | 3.4833 |
References
1. Rahbari, O, Mayet, C, Omar, N, van Mierlo, J. Battery aging prediction using input time-delayed based on an adaptive neuro-fuzzy inference system and a group method of data handling techniques. Appl Sci 2018;8:1301. https://doi.org/10.3390/app8081301.Search in Google Scholar
2. Bin, ZH. Current study situation of faulty insulator detection method home and abroad. Power Syst Technol 2006;30:275–8. http://doi.org/10.13335/j.1000-3673.pst.2006.s1.073.Search in Google Scholar
3. Feng, L, Zhang, X, Xie, F, Xv, C, Wang, D. EMTP-based distributed simulation of 330kV voltage insulator strings. J Shanghai Univ Electr Power 2015;4:525–8. http://doi.org/10.3969/j.issn.1006-4729.2015.06.005.Search in Google Scholar
4. Yang, YH, Wang, L. The design of online detection system of faulty insulator. Electron Test 2013;21:11–16. https://doi.org/10.1109/icsai.2014.7009281.Search in Google Scholar
5. Gao, B, Yan, Z, Zhao, Y, Tan, C, Rong, F, Hu, J. Study on the effect of ceramic microstructure on mechanical properties and temperature resistance of suspended porcelain insulators. Insul Surge Arresters 2019;5:255–61. https://doi.org/10.16188/j.isa.1003-8337.2019.05.042.Search in Google Scholar
6. Zeng, S, Zhang, Y, Wang, Z, Yin, Y, Yin, Y. Condition diagnosis of oil-paper insulation during the accelerated electrical aging test based on polarization and depolarization current [C]. In: 2015 IEEE 11th international conference on the properties and applications of dielectric materials (ICPADM) [S.l.]. IEEE, Sydney, Australia; 2015. 448–51.10.1109/ICPADM.2015.7295305Search in Google Scholar
7. Fu, W, Wang, W, Dong, J, Liu, Y, Zhang, K. Study on the applicability of detecting deterioration insulator based on infrared thermal image. High Volt Appar 2018;54:110–14+20. https://doi.org/10.13296/j.1001-1609.hva.2018.02.018.Search in Google Scholar
8. Palangar, MF, Mirzaie, M. Diagnosis of porcelain and glass insulators conditions using phase angle index based on experimental tests. IEEE Trans Dielectr Electr Insul 2016;23: 1460–6. https://doi.org/10.1109/TDEI.2015.005586.Search in Google Scholar
9. Li, J, Dong, Z, Qu, K. Calculation of the voltage distribution of insulator strings in 500kV lines based on the combination of electrical field and road. High Volt Appar 2018;54:21–6. https://doi.org/10.13296/Fj.1001-1609.hva.2018.08.004.Search in Google Scholar
10. Le, Z, Wang, W, Zhao, W, Yang, G, Fu, C, Liu, H, et al. Grounding current characteristic study of 35kV composite insulator under pollution condition. Insul Mater 2012;45:65–9. http://doi.org/10.16790/j.cnki.1009-9239.im.2012.06.017.Search in Google Scholar
11. Kowalski, PA, Kusy, M. Sensitivity analysis for probabilistic neural network structure reduction. IEEE Trans Neural Netw Learn Syst 2018;29:1919–32. https://doi.org/10.1109/tnnls.2017.2688482.Search in Google Scholar PubMed
12. Zhang, ZY, Yan, K, Wang, FC, Yang, SJ, Li, NC. Insulator hydrophobic identification method based on image feature extraction and BP neural network. High Volt Eng 2014;40:1446–52. https://doi.org/10.13336/1003-6520.hve.2014.05.022.Search in Google Scholar
13. Li, JY, Sun, CX, Sebo, SA. Humidity and contaminati on severity impact on the grounding currents of porcelain insulators. IET Gener Transm Distrib 2011;5:19–28. https://doi.org/10.1049/iet-gtd.2009.0559.Search in Google Scholar
14. Yao, CH, Dehua, Z, Jie, N, Luo, R, Tang, X. The impact of zero and low resistance insulator on potential and electric field distribution of long insulator strings in the 500kV transmission line. Insul Surge Arresters 2015;3:29–34. http://doi.org/10.16188/j.isa.1003-8337.2015.03.006.Search in Google Scholar
15. Bensheng, Q. Research on fault diagnosis of high-voltage circuit breaker based on the improved BP neural network. In: The 2nd international conference on information science and engineering. IEEE, Hangzhou, China; 2010.1460–3.Search in Google Scholar
16. Yang, L, Zhu, Y. High voltage circuit breaker fault diagnosis of probabilistic neural network. Power Sys Protect Contr 2015;43:62–7. http://doi.org/10.7667/j.issn.1674-3415.2015.10.010.Search in Google Scholar
17. Subba Reddy, B, Verma, AR, Satish Naik, B. Performance analysis of 1200kV porcelain disc insulator string under normal and faulted conditions. Energy Procedia 2015;75:1114–19. https://doi.org/10.1016/j.egypro.2015.07.522.Search in Google Scholar
18. Chong, Ma, Zheng, Du. Reason analysis on ceramic isolators deteriorating on transmission lines. North China Electric Power 2006;7:51–4. http://doi.org/10.16308/j.cnki.issn1003-9171.2006.07.016.Search in Google Scholar
19. Jiang, J, Wen, Z, Zhao, M, Bie, Y, Li, C, Tan, M, et al. Series arc detection and complex load recognition based on principal component analysis and support vector machine. IEEE Access 2019; 7: 47221–9. https://doi.org/10.1109/access.2019.2905358.Search in Google Scholar
20. Han, W, Mao, D-J, Qi-min, Y. Induced draft fan fault and multivariate state warning based on PCA estimation technique. J Eng Therm Energy Power 2020;35:91–7. http://doi.org/10.16146/j.cnki.rndlgc.2020.01.014.Search in Google Scholar
21. Yan, C, Chen, Y, Zheng, J. An improved data preprocessing method based on PCA. Appl Electron Tech 2020;46:96–9. http://doi.org/10.16157/j.issn.0258-7998.190773.Search in Google Scholar
22. Dobrzycki, A, Mikulski, S, Opydo, W. Using ANN and SVM for the detection of acoustic emission signals accompanying epoxy resin electrical treeing. Appl Sci 2019; 9: 1523. https://doi.org/10.3390/app9081523.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
