Search

Artificial neural networks (ANNs) is an adaptive system that has the ability to predict the relationship between the input and output parameters without defining the physical and operation conditions. In this study, some queries about using ANN methodology are simply clarified especially about the neurons number and their relationship with input and output parameters. In addition, two ANN models are developed using MATLAB code to predict the power production of a polycrystalline PV module in the real weather conditions of Iraq. The ANN models are then used to optimize the neurons number in the hidden layers. The capability of ANN models has been tested under the impact of several weather and operational parameters. In this regard, six variables are used as input parameters including ambient temperature, solar irradiance and wind speed (the weather conditions), and module temperature, short circuit current and open circuit voltage (the characteristics of PV module). According to the performance analysis of ANN models, the optimal neurons number is 15 neurons in single hidden layer with minimum Root Mean Squared Error (RMSE) of 2.76% and 10 neurons in double hidden layers with RMSE of 1.97%. Accordingly, it can be concluded that the double hidden layers introduce a higher accuracy than the single hidden layer. Moreover, the ANN model has proven its accuracy in predicting the current and voltage of PV module. [ABSTRACT FROM AUTHOR]

Phase change materials (PCM) in the construction industry became attractive because of several interesting attributes, such as thermo-physical parameters, open air atmospheric condition usage, cost and the duty structure requirement. Thermal performance optimization of PCMs in terms of proficient storage of a large amount of heat or cold in a finite volume remains a challenging task. Implementation of PCMs in buildings to achieve thermal comfort for a specific climatic condition in Iraq is our main focus. From this standpoint, the present paper reports the experimental and numerical results on the lowering of heat flux inside a residential building using PCM, which is composed of oil (40%) and wax (60%). This PCM (paraffin), being plentiful and cost-effective, is extracted locally from waste petroleum products in Iraq. Experiments are performed with two rooms of identical internal dimensions in the presence and absence of PCM. A two-dimensional numerical transient heat transfer model is developed and solved using the finite difference method. A relatively simple geometry is chosen to initially verify the numerical solution procedure by incorporating in the computer program two-dimensional elliptic flows. It is demonstrated that the heat flux inside the room containing PCM is remarkably lower than the one devoid of PCM. [ABSTRACT FROM AUTHOR]