IEEE Transactions on Dielectrics and Electrical Insulation · 2018 · 127 citations · 50 references
EngineeringComputer ScienceElectrical EngineeringArtificial Intelligence In EducationDiagnostic ReasoningThermal AnalysisDiagnosisDiagnosticsElectrical System DiagnosticsFault DetectionFault DiagnosisDowntime CostElectrical Power SystemsEnergyFibrous InsulationIncipient Fault DetectionInsulation Fault DiagnosisPower System Fault AnalysisTransformer Insulation
Transformers are vital components of power systems as they are situated between energy generation and consumers and their failure disrupts the use of electrical energy. Therefore, diagnosing an incipient fault is essential in avoiding hazardous operating conditions and minimizes downtime cost. In transformers, faults take place due to electrical or thermal stresses that cause insulation decomposition in transformers. In oil-filled transformers, insulations are cellulose and oil, and the products of the insulation decomposition are gases which can be dissolved in the oil. Therefore, dissolved gas analysis (DGA) can be used for fault diagnosis in oil filled transformers. In this paper, DGA interpretation methods, conventional and intelligence, are investigated and compared. For evaluating consistency and accuracy of the methods, "No Result" cases are not considered. It can help the newcomers to this field to have access to a comprehensive comparison about the application of computational intelligence and conventional methods in transformer fault detection using DGA.
50
An Artificial Neural Network Approach to Transformer Fault Diagnosis
Yuxin Zhang, Xuewen Ding, Yike Liu et al. · IEEE Power Engineering Review · 1996 · 262 citations · Full text
Computing, Electrical Engineering, Artificial Intelligence +15
Jinzhong Li, Qiaogen Zhang, Ke Wang et al. · IEEE Transactions on Dielectrics and Electrical Insulation · 2016 · 235 citations