Retrofit of a steam power plant using the adaptive neuro-fuzzy inference system in response to the load variation.

Abstract Artificial neuro-fuzzy inference system known as the ANFIS tool was earlier developed by authors [1] for exergoeconomic optimization of an energy system. It was shown that the ANFIS could achieve the optimal solutions of systems with reasonable accuracy, very low computation time, and less dependency on experts' knowledge. This paper aims to test a similar methodology for retrofit and real-time optimization of a large energy system in response to the load variation. A 250 MW unit in a fossil-fueled steam power plant was considered as a case study. The profit of the power plant was estimated using an exergoeconomic analysis, and it was maximized by adjusting flow rates of extracted steams that flow from turbines into feed-water heaters. The ANFIS methodology was developed in detail to optimize the profit of the proposed power plant. The advantage of the ANFIS for this purpose was compared to other alternatives such as genetic algorithm (GA) and fuzzy-inference system (FIS). It was shown that the ANFIS is much faster than the GA and considerably easier than the FIS for real-time optimization energy systems. It was shown that using ANFIS, it is possible to achieve more profit in the proposed power plant up to 320 $.hr−1 by implication control on the flow of extracted steam; however, this figure is different at various loads of the power plant. Highlights • Real-time optimization based on adaptive neuro-fuzzy inference system, ANFIS. • Optimizing extracted steams in response to the load using the ANFIS. • Maximizing the profit of a fossil-fueled steam power plant. • A quite faster optimization methodology in comparison to conventional methods. • Automatic generation of governing fuzzy rules of optimization by the ANFIS. [ABSTRACT FROM AUTHOR]