Improved prediction of oscillatory heat transfer coefficient for a thermoacoustic heat exchanger using modified adaptive neuro-fuzzy inference system

Despite the increasingly rapid advances in the thermoacoustic field, heat transfer process in thermoacoustic-based heat exchangers has not been fully understood yet. In this study, an improved adaptive neuro-fuzzy inference system (ANFIS) based on the crow search algorithm (CSA) is proposed to predict the oscillatory heat transfer coefficient (OHTC). The frequency of the oscillations and the mean pressure are used as inputs to the proposed algorithm, while OHTC is used as the output. To investigate the performance of the proposed method, ANFIS-CSA is compared with traditional ANFIS and the ANFIS based genetic algorithm (ANFIS-GA). The experimental results show the high ability of the proposed ANFIS-CSA model to learn the nonlinear relationship between the inputs and outputs. In addition, it provides higher performance to predict the OHTC value than the other two models in terms of performance measures. (C) 2019 Elsevier Ltd and IIR. All rights reserved.