Self-adaptive firefly algorithm with neural network for design modelling and optimization of boiler plants

Abstract

Recently, the introduction of advanced approach for designing boiler become mandatory. The main challenges in designing the boiler is considered to be the energy saving and reduction of emission. Thus the need of optimization algorithms in this field is high to overcome this. The efficient boiler design has been accomplished by diverse researchers as reported in the literature. Further, the neural network has been utilized for designing boiler, which is the non-linear system. This paper proposes a self-adaptive scheme for firefly (FF) algorithm and combines with Artificial Neural Network (ANN) called as Self-Adaptive firefly-Neural Model (SAFF-NM) to design an effective boiler. Further, the analysis of the Type I and II error functions with conventional methods validate the performance of the proposed method. The Type I and II error functions are determined for several parameters like steam flow, temperature outlet, electrical power, steam pressure, feed water flow, steam pressure in drum, spray water flow, steam pressure in throttle, water level in drum and steam temperature. This analysis described the superiority of the SAFF-NM against the conventional methods like Neural Model (NM) and Firefly-Neural Model (FF-NM).