A Neuro-Fuzzy Model of Evaporator in Organic Rankine Cycle

Abstract

The Organic Rankine Cycle (ORC) is a propitious waste heat recovery (WHR) technology that allows recovery of wasted energy from low to medium temperature sources. This WHR method needs to be adopted as an Internal Combustion Engine (ICE) bottoming technology to mitigate its environmental effects and fulfil exhaust gas emission regulations. The evaporator is the most decisive element of the ORC cycle due to its high nonlinear behaviour and high thermal inertia. In this study, a neuro-fuzzy model of the evaporator is presented based on the data obtained from Finite Volume (FV) model of the evaporator. The simulation results are compared in terms of RMSE, error mean and standard deviation. The data obtained from ANFIS model reached a promising agreement with FV model. F or prediction of the evaporator outlet temperature, RMSEs of 0.152 and 1.33 obtained for the training and test data, res pectively. Furthermore, the ANFIS model was successfully able to predict the evaporator power with RMSE of 0.035 for the training and 0.2 for the test data. In addition, the ANFIS model compared to the FV model with twenty control volumes enhanced the simu lation time significantly. This clearly indicates the great potential of employing ANFIS model for real-time applications.

A Control-Oriented ANFIS Model of Evaporator in a 1-kWe Organic Rankine Cycle Prototype

“…Khosravi et al [30] used ANFIS-PSO algorithm for thermodynamic modelling of geothermal based ORC equipped with solar system. Authors, in previous studies [27,31], have developed ANFIS models based on the available data from FV evaporator models that offer reduced complexity, high accuracy and lower computational burden for prediction of the working-fluid and heat-source outlet temperatures. This paper investigates the application of neuro-fuzzy techniques for modelling a plate evaporator using time-resolved high-fidelity experimental data obtained on a 1-kWe ORC prototype.…”