Power Research

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Comparative Study of DGA Based Fault Diagnosis using ANN and Fuzzy Systems


Affiliations
1 Electrical Engineering - HV Lab, IIT Ropar, Rupnagar – 140001, Punjab, India
     

   Subscribe/Renew Journal


Dissolved Gas Analysis (DGA) method for fault detection has been implemented using Artificial Neural Networks (ANN), Fuzzy Logic (FL) and Adaptive Neuro Fuzzy Inference System (ANFIS). Incipient faults can be detected using DGA which provides reasonably good results. We have tried to improve this method in order to surpass its limitations. Comparative analysis using the mentioned methods have been done on IEC 599 standard, Rogers Ratio Method and Doernenburg’s method. Using Fault databases, the training has been done to improve the diagnostic capabilities. The obtained results clearly show the superiority of ANFIS on ANN and FL. Being a combination of both, its degree of accuracy in prediction and ease of use, provides a promising alternative in replacing the conventional methods.

Keywords

Adaptive Neuro Fuzzy Inference Systems, Artificial Neural Networks, Dissolved Gas Analysis, Fuzzy Logic.
User
Subscription Login to verify subscription
Notifications
Font Size

  • Duval M, dePabla A. Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases. IEEE Electrical Insulation Magazine. 2001; 17(2):31–41. https://doi.org/10.1109/57.917529

  • Duval M. A review of faults detectable by gas-in-oil analysis in transformers. IEEE Electrical Insulation Magazine. 2002; 18(3):8–17. https://doi.org/10.1109/MEI.2002.1014963

  • Li X, Wu H, Wu D. DGA interpretation scheme derived from case study. IEEE Transactions on Power Delivery. 2011; 26(2):1292–3. https://doi.org/10.1109/ TPWRD.2010.2091325

  • Abu-Siada A, Islam S. A new approach to identify power transformer criticality and asset management decision based on dissolved gas-in-oil analysis. IEEE Transactions on Dielectrics and Electrical Insulation. 2012; 19(3):1007–12. https://doi.org/10.1109/TDEI.2012.6215106

  • Satyanarayana KV, Reddy CC, Govindan TP, Mandlik M, Ramu TS. Application of artificial intelligence for the assessment of the status of power transformers. Conference Record of the 2008 IEEE International Symposium on Electrical Insulation; 2008. p. 104–7. https://doi.org/10.1109/ELINSL.2008.4570289. PMid:18403785

  • Jang JSR. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 1993; 23(3):665–85. https://doi.org/10.1109/21.256541


Abstract Views: 88

PDF Views: 0




  • Comparative Study of DGA Based Fault Diagnosis using ANN and Fuzzy Systems

Abstract Views: 88  |  PDF Views: 0

Authors

A. Harshith Kumar
Electrical Engineering - HV Lab, IIT Ropar, Rupnagar – 140001, Punjab, India
Birender Singh
Electrical Engineering - HV Lab, IIT Ropar, Rupnagar – 140001, Punjab, India
C. C. Reddy
Electrical Engineering - HV Lab, IIT Ropar, Rupnagar – 140001, Punjab, India

Abstract


Dissolved Gas Analysis (DGA) method for fault detection has been implemented using Artificial Neural Networks (ANN), Fuzzy Logic (FL) and Adaptive Neuro Fuzzy Inference System (ANFIS). Incipient faults can be detected using DGA which provides reasonably good results. We have tried to improve this method in order to surpass its limitations. Comparative analysis using the mentioned methods have been done on IEC 599 standard, Rogers Ratio Method and Doernenburg’s method. Using Fault databases, the training has been done to improve the diagnostic capabilities. The obtained results clearly show the superiority of ANFIS on ANN and FL. Being a combination of both, its degree of accuracy in prediction and ease of use, provides a promising alternative in replacing the conventional methods.

Keywords


Adaptive Neuro Fuzzy Inference Systems, Artificial Neural Networks, Dissolved Gas Analysis, Fuzzy Logic.

References





DOI: https://doi.org/10.33686/prj.v17i1.221841