Search

In the present work, Artificial Neural Network (ANN) has been used to predict the thermal performance of unidirectional flow porous bed solar air heater. The ANN model was structured on the basis of data sets obtained from experiments and values of thermal efficiency of solar air heater. Four types of training functions are used in ANN model for training process with feed forward learning procedure. The aim of this work is to examine the performance and comparison of four training functions (TRAINCGP, TRAINSCG, TRAINLM and TRAINOSS) applied in training process of neural model. A comparison was based on the RMSE and R 2 . It was found that training function TRAINLM exhibits optimal result with the experimental data. [ABSTRACT FROM AUTHOR]

This paper presents an investigation on optimal thermohydraulic performance of a solar air heater having arc-shaped wire rib roughness on underside of the absorber plate. The use of artificial roughness on the absorber plate of a solar air heater causes enhancement in rate of the heat transfer between absorber plate and flowing air, by creating turbulence, however, there is substantial increase in the frictional resistance which leads to more pumping power consumption. The effective efficiency is evaluated on the basis of useful thermal energy gain minus equivalent thermal energy to the power required to propel the air through solar air heaters. A mathematical model and procedure for prediction of effective efficiency of an arc shaped wire rib roughened absorber plate solar air heater has been presented and the effects of roughness and various geometrical and operating parameters on effective efficiency have been worked out. The effective efficiency of the roughened absorber plate solar air heater has also been compared with smooth absorber plate solar air heater operating under similar conditions. It is observed that effective efficiency of a roughened solar air heater has an optimum value corresponding to a certain Reynolds number and specific values of operating and geometrical conditions. A correlation between system and operating parameters that delivers optimum effective efficiency has been developed and presented, which can be used for optimal design of such systems. [ABSTRACT FROM AUTHOR]