Combining and comparing various machine‐learning algorithms to improve dissolved gas analysis interpretation

Hybrid Grey Wolf Optimizer for Transformer Fault Diagnosis Using Dissolved Gases Considering Uncertainty in Measurements

“…It can be classified into two main stages: The first stage contains three main processes: A. The original datasets were collected, and new datasets were created based on the expected random uncertainty in the gas concentrations by using (4). Furthermore, the percentages of the dissolved gas concentrations were calculated in each set.…”

“…Therefore, several methods were proposed for accurate fault diagnosis in transformers based on the analysis of insulating oil. Dissolved gas analysis (DGA) is the most used method for fault diagnosis [3], [4]. DGA is based on the correlation between dissolved gases in the oil and corresponding fault type and severity.…”

Overview and Partial Discharge Analysis of Power Transformers: A Literature Review

“…A decision tree had been employed to identify the void size and differentiating the multiple PD sources in power transformers [186]. K-nearest neighbor (KNN) is a simple and non-parametric algorithm that classifies the training sets by recognizing the collection of k objects nearest to test objects and allotting the type through correlation of the respective class in the neighborhood [187].…”

Integrated decision‐making method for power transformer fault diagnosis via rough set and DS evidence theories

“…To address these challenges, many intelligent techniques and machine‐learning algorithms have been applied in the field of transformer fault diagnosis [10, 11]. Li et al [5] and Taha et al [12, 13] combined various data features of the combustible gases in transformers, e.g.…”