Analysis of inland waterway ship performance in ice: Operation Time Window

Inland waterway (IWW) shipping is a sustainable opportunity to reduce traffic on, in many times very congested, roads and railways. This is especially true for cities and urban areas. However, for an operator, the ship Oper-ation Time Window (OTW) is important in order to predict possible business cases, especially for regions with long-term winter seasons with icy conditions. The OTW indicates the probable number of navigable days for the ship. The operability is in relation with ship speed, ice thickness, whereas the ship resistance is of significant relevance. This study proposes a model to investigate the possibility of a certain operating condition for ice-going ships based on an Artificial Neural Network (ANN) model and a statistical model. To demonstrate the proposed method for calculating the ship OTW of an IWW, a case study is performed. Ice condition in Lake Ma center dot laren (in Sweden) and an IWW ship designed to maximise its dimension restrictions are used for this case. The Radial Basis Function-Particle swarm optimization (RBF-PSO) ANN model is used to predict ice resistance in level ice con-ditions. Given the ice resistance prediction, a statistical analysis is further conducted regarding to the ice thickness distribution and the operational ship speed distribution to obtain ship OTW. Comparisons are made between semi-empirical ice resistance prediction methods and the ANN model. The influence of different ship speed distribution profiles is investigated by performing a parametric study. The OTW model can be used to evaluate ship operational scenarios in ice-covered waters for ship designers and owners.

Automated summary

Inland waterway shipping is a sustainable solution to reduce traffic congestion in cities. This study proposes a model based on artificial neural networks and statistical analysis to evaluate the operational possibilities of ice-going ships. The results can be used to assess ship operations in icy conditions.