Prediction by Artificial Neural Network Techniques to Determine Energy gap of Carbon Reinforced with Nano (Copper oxide and Nickel oxide)

Nano-coating of (CuO:NiO/C) has been prepared to achieve high selective surfaces for solar energy enhancement. Different concentration percentages of CuO and NiO were doped carbon (fuel ash) to obtain nanocomposite. The energy gap of nano coating is predicted by using an artificial neural network (ANN). Generally, the relation between energy gap and the wavelength features are discussed to obtain the best values. Therefore, these values were taken from the experimental tests and empirically result dependent on the wavelength range (250- nm) at room temperature by ANN. The achievement of the energy gap for this coating wasinvestigated, to generate optimal energy gap from ANN for these nanocomposites and compared with the experimental results. The ANN model has been presented from the experimental test. Two-layer has been used to predict the energy gap value. these tests were trained to predict and assess their capability in various numbers of neural cells. Due to the complexity of the system, all the tests results were processed as a database for ANN and inspected through the algorithm of neurons network by MATLAB program. The results shown an acceptable coincidence with experimental data within the final model for the nan coating. The acquired efficiency between experimental and theoretical results was 99% which is a good agreement to reach this value. However, the results obtained show that the energy gap has a value ranging from 3.1 and 3.7 eV, this result conform that this type of nano coating must be the best coating for solar energy absorbance in spectrally surfaces applications.