Interpretation of DGA for transformer fault diagnosis with complementary SaE-ELM and arctangent transform
This paper presents a novel approach for power transformer incipient fault diagnosis through the analysis of dissolved gas in oil. The proposed approach is implemented for improving the diagnosis accuracy by dissolved gas analysis (DGA) of power transformer based on the combined use of a multi-classification algorithm self-adaptive evolutionary extreme learning machine (SaE-ELM) and a easy arctangent remodel (AT). On the one hand, the SaE-ELM algorithm has the power to approximate any nonlinear functions with its structure parameters, i.e. hidden node biases and output weights, optimized self-sufficiently. On the other hand, the AT can alter the information structure of the experiment data, that will enhance the generalization capability for SaE-ELM and other machine learning algorithms. So, the combination of SaEELM and AT can complement every alternative and improve the diagnosis accuracy from the facet of both algorithm and knowledge structure. The performances of the proposed approach are compared with that derived from ANN, SVM, and ELM strategies, respectively. Experimental results with each published and power utility provided information indicate that the developed approach will significantly improve the accuracies for power transformer fault diagnosis.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here