Efficient Gaussian Sugeno fuzzy vector with bidirectional lucidity network for gas turbine

In the realm of power generation, the integration of gas turbine technology with complementary components in a combined gas turbine (CGT) plant demands meticulous examination of exergy destruction and NO x reduction to ascertain its pivotal performance metrics.Hence, a novel Gaussian Sugeno vector network with a bidirectional lucidity network has been introduced.In the condenser, azeotropic mixtures in the working fluid reveal different heat-transfer characteristics which affect condenser effectiveness and contribute to higher exergy destruction.Thus, a novel Gaussian-Sugeno-Swarm vector network has been implemented, which mitigates the complexities introduced by azeotropic mixtures, reducing exergy destruction and significantly improving the overall effectiveness of the condenser.Furthermore, selective catalytic reduction (SCR) systems exhibit non-linear behaviour due to catalyst deactivation, causing incomplete NO x reduction due to difficulty in predicting and controlling temperature changes.So, a novel bidirectional niching fuzzy lucidity network has been introduced, which provides a comprehensive solution to address the limitations of current control algorithms, ensuring a complete reduction in NO x emissions in SCR systems.The proposed method demonstrates excellence in condenser and SCR systems by achieving a high prediction accuracy of 0.94, precision of 0.96, NO x reduction of 0.97 and low heat loss of 0.02.