Application of Artificial Neural Network for Predicting Water-Drag of the N219 Aircarft Floater Sigit Tri Atmaja (a), Rizqon Fajar (b*), Sayuti (b), Sutiyo (c)
a) The Centre of Technology for Thermodynamics, Engines and Propulsion (BT2MP-BPPT), Build 230 Puspiptek, South Tangerang, Banten 15314
b) Center of Technology for System and Infrastructure of Transportation (PTSPT-BPPT), Build Teknologi 2 Lt 3 Puspiptek, South Tangerang, Banten 15314.
*rizqon.fajar[at]bppt.go.id
c) Department of Marine Engineering, Faculty of Engineering and Marine Science, Hang Tuah University, Jl. Arif Rahman Hakim 150, Surabaya
Abstract
Indonesia is an archipelagic country that needs cheap and fast transportation facilities. One solution is a modified small aircraft with the addition of a pair of floaters for the purpose to float and glide in the waters. At the time of take-off, the aircraft encounters a water-drag that will prevent the aircraft from accelerating, thereby preventing the aircraft from taking off. The purpose of this research is to predict the water-drag of the floater using machine learning, artificial intelligence (ANN). Prediction results are used for the analysis of the thrust required for the aircraft to take off. The ANN architecture used consists of one hidden layer, the activation function used is sigmoid with Adam^s optimization method. The ANN algorithm is run using python-libraries. Water-drag calculation using the ANN model on three floaters with different dimensions shows that the predicted value is close to the target value, obtained from the CFD calculation, where the regression-coefficient is close to 1 with the error approaching 0. Prediction results on water-drag using the ANN model produce accurate values. The use of machine learning ANN in calculating water-drag has also proven to be very fast, thus saving research time and costs.
Keywords: floater, water-drag, ANN, hyperparameter, regression-coefficient
Topic: Symposium on Advance of Sustainable Engineering
