Enhanced Distributed Parallel Firefly Algorithm Based on the Taguchi Method for Transformer Fault Diagnosis

To improve the reliability and accuracy of a transformer fault diagnosis model based on backpropagation (BP) neural network, this study proposed an enhanced distributed parallel firefly algorithm Taguchi method (EDPFA). First, (DPFA) was implemented then used to enhance original communication strategies in DPFA. Second, verify performance EDPFA, compared EDPFA with (FA) DPFA under test suite Congress Evolutionary Computation 2013 (CEC2013). Finally, applied by training initial parameters BP network. The experimental results showed that: (1) effectively EDPFA. Compared FA DPFA, had faster convergence speed better solution quality. (2) improved network (up 11.11%).