Cycle-Time Estimation for Forming Curved Plates Using Neural Networks

Abstract

This article introduces an artificial neural network (ANN) model to determine cycle-times for forming curved hull plates when the target shape is known. The proposed model aids shipbuilding companies in predicting the cycle-times required for ship fabrication. The input parameters are geometric information extracted from the target shape (curvedness, Gaussian curvature, width, and height of the hull plate), and the output parameter is the heating duration per unit area. The structure of the proposed model, which predicts cycle-times for line heating after the cold forming case, consists of two hidden layers. The proposed model is convenient to use and flexible because it only requires retraining when the dataset is changed. The performance of the proposed model was analyzed by five-fold cross-validation and compared with that of a mathematical model obtained from the linear regression analysis method and predefined formulas. The results show that the ANN model is reliable and accurate for the cycle-time prediction of curved hull plates in shipbuilding applications. Shipbuilding companies generally estimate the production cost of a ship based on their previous ships for various purposes before the production planning department begins to optimize the fabrication process. They use the estimated value to refine the overall fabrication process or improve it by reducing unnecessary tasks and maximize the overall production efficiency.