Fault Diagnosis Method for Power Transformers Based on Improved Golden Jackal Optimization Algorithm and Random Configuration Network

The problem of the low accuracy Dissolved Gas Analysis (DGA) in diagnosing transformer faults is addressed by proposing an Improved Golden Jackal Optimization (IGJO) based Stochastic Configuration Network (SCN) method. method fault diagnosis on IGJO optimized SCN proposed. Firstly, Kernel Principal Component (KPCA) used to reduce dimensionality gas data and extract effective feature quantities. Secondly, L2 parametric penalty term introduced into improve generalisation ability practical applications. elite backward learning golden sine algorithms are incorporated jackal algorithm, performance tested using 13 typical test functions, demonstrating that has greater stability merit-seeking capability. coefficient C optimised develop a model with algorithm Random (IGJO-SCN). Finally, quantities extracted KPCA as input set different models simulated validated. results show IGJO-SCN higher compared other models.