Detection of Ships at Mooring Dolphins with Hidden Markov Models

Abstract

IJpalen near the lock in IJmuiden are of great economic value to the Port of Amsterdam. These mooring dolphins have to endure a considerable amount of kinetic forces which can have an impact on the condition of the dolphins. These forces are created by either mooring or already moored ships. Any irregularities taking place at the IJpalen can have disastrous results unless timely addressed. The Port of Amsterdam has attached sensors to the poles and the plates, which measure changes in the dimensions regarding the dolphins. This report explores whether combining sensor data from the IJpalen and automatic identification system (AIS) data can produce beneficial insights into the dolphins’ states. We have used the sensor dataset to build a hidden Markov model (HMM) which predicts whether a ship is moored. We evaluated these results using the AIS data, in which can be discovered when a ship was moored at the IJpalen, producing remarkable results. We analyzed the sensor values using descriptive statistics to discover the normal and problem values. This research has obtained the following findings. First, descriptive statistics indicate a normal value range for the sensor values. Whenever a value out of this range is observed, it could be a problem case. Finally, it is possible to detect whether a ship is moored in the sensor data. An HMM on the z-angle of the plate of the east dolphin produces the best prediction, i.e., the highest accuracy of 90.2% according to the evaluation method, of a moored ship at the IJpalen.