A Secure ANFIS based Relay for Turbo-Generators Phase Backup Protection

This paper presents a new advanced methodology as a solution for the problem due to the current setting of Relay (21) when it is set to provide thermal backup protection for the generator during two common system disturbances, namely a system fault and a sudden application of a large system load. These investigations are carried out using Adaptive Neuro Fuzzy Inference System (ANFIS). The results of the investigations have shown that the ANFIS has a promising effect when applied for turbo-generators phase backup protection. Such an effect varies according to the type of data used for ANFIS testing and validating. The proposed method in this paper proposes the use of two different sets of inputs to the ANFIS, these inputs are the generator terminal impedance measurements (R and X) and the generator three phase terminal voltages and currents (V and I). The dynamic simulations of a test benchmark have been conducted using the PSCAD/EMTDC software. The results obtained from the ANFIS scheme are encouraging.