Computational and Artificial Intelligence Study of the Parameters Affecting the Performance of Heat Recovery Wheels

Abstract

Heat recovery wheels represent key components in air handling units (AHU) that can be used in commercial and industrial building airconditioning systems for energy saving. For example, in health facilities, heat transfer process is to be applied in airconditioning systems for heat recovery of the exhaust (return) air from the patient's room without contamination. Thus, heat recovery wheels are much suitable for such applications. Heat recovery wheels are also known as heat conservation wheels. A conservation wheel consists of a rotor with permeable storage mass fitted in a casing, which operates intermittently between two sections of hot and cold fluids. The rotor is driven by a low-speed electric motor. Thus, the two streams of exhaust and fresh air are alternately passed through the wheel. The present investigation considers computationally the different parameters that affect the operation of heat recovery wheels. These parameters signify actual operating conditions such as flow velocity, shape of cross-section of flow path, and wall material. Moreover, both the artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) techniques were utilized to predict the critical characteristics of the heat exchange system. These artificial intelligence techniques use the present computational results as training and verification data.