Determination of outlet flow temperature of a flat plate solar collector with artificial neural network

The objective of this work is to use Artificial Neural Networks (ANN) for the determination of the outlet flow temperature of a flat-plate solar collector. ANN have been developed according to the experimental data, which have been carried out for 16 days in Jun and July under semi-arid weather conditions of Rafsanjan, Iran. A neural network of Levenberge-Marquardtbased based on back propagation (BP) algorithm was developed to determine the outlet flow temperature of a flat plate solar collector. The measured data are used in the design of ANN algorithm. The results obtained when unknown data were presented to the network are very satisfactory and indicate that the proposed method can successfully be used for the determination of the outlet flow temperature, and consequently for thermal performance of flat-plate solar collector. The advantages of this approach compared to the conventional testing methods are speed, simplicity, and the capacity of the network to learn from examples. This is done by embedding experiential knowledge in the network.