شبکه های عصبی مصنوعی برای ارزیابی عملکرد بندر
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|52492||2015||11 صفحه PDF||سفارش دهید||محاسبه نشده|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Ocean Engineering, Volume 109, 15 November 2015, Pages 298–308
Waves are one of the main factors that can disturb port operations, from berthing to cargo loading and unloading. Wave heights within port basins are typically assessed by means of numerical models based on the outer (offshore) wave conditions, the bathymetry and the port layout. The aim of this work is to implement an artificial neural network (ANN) model which, upon training and validation, will be capable of determining wave agitation within a port basin based on deep-water wave buoy observations alone. In the training the ANN model acquires knowledge on the problem from a series of examples, and thereafter applies this self-acquired knowledge to other (new) cases. To select the ANN architecture most appropriate for this task a comparative study involving 65 options is carried out using the k-fold cross-validation technique. Upon validation, the ANN model is used to carry out a sensitivity analysis in which the influence of the different input variables on the wave parameters in the basin is quantified. Finally, the model is applied to a case study—the Exterior Port of Ferrol—in order to evaluate wave agitation inside the basin and its influence on port operations.