Intelligent Techniques based Power Transformer Health Monitoring Index using Dissolved Gas Analyser

Diagnosis of power transformer faults is essential for the stable operation of an electrical power system. Dissolved gas analysis is a prevalent method used for this purpose, which assesses the transformer oil quality and analyses the gases liberated during continuous transformer operation. The proposed work uses a support vector machine (SVM) optimized firefly algorithm for transformer fault diagnosis. This algorithm optimizes the SVM hyperparameters and reduces k-fold loss, improving the model’s accuracy and fault prediction capability. The SVM’s radial basis function (RBF) kernel helps handle the non-linearly separable data. The results showed that the accuracy obtained after incorporating the optimization algorithm is comparatively high, evidencing increased performance of the model in predicting transformer faults. The approach provides a reliable way for quick and early detection of transformers’ inherent faults, facilitating improved maintenance strategies and reduced equipment downtime.