نوع مقاله : مقاله پژوهشی
نویسندگان
استادیار، دانشگاه امام علی (ع)، تهران، ایران
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
The experimental data of fluid mechanics is one of the main important tools for flow study and also an evaluation criterion of some methods such as the numerical methods. Thus, it is important that the quality of the data, measured in the laboratory be acceptable. One of the important properties of any flow is the fluid velocity field that is measured by different instruments. One of those tools is the SPIV tool. This tool provides sheet information from the flow velocity components. Generally, the data extracted from this tool would have big errors in some points of the velocity field, for various reasons and laboratory conditions, and the values obtained in these points known as gappy points, are eliminated. Therefore, some methods are needed to reconstruct the velocity field at these gaps. For this purpose, in the present study we have used artificial neural networks, such as MLP and CNN. The optimization of the number of neurons in the MLP network has been performed by the mean error of the test data and the matching of the images. The final error has been obtained for each of the methods, and considering the errors and taking into account the accommodation between the reconstructed velocity field and the experimental data, the results indicate that for both velocity components, the CNN neural network has had the best performance.
کلیدواژهها [English]