No abstract

While automatic controllers are frequently used during transit operations and low-speed maneuvering of ships, ship operators typically perform docking maneuvers. This task is more or less challenging depending on factors such as local environment disturbances, number of nearby vessels, and the speed of the ship as it docks. This paper proposes a tool for onboard support that offers position predictions based on an integration of a supervised machine learning (ML) model of the ship into the ship dynamic model. The ML model is applied as a compensator of the unmodelled behaviour or inaccuracies from the dynamic model. The dynamic model increases the amount of predetermined knowledge about how the vessel is likely to move and thus reduces the black-box factor typically experienced in purely data-driven predictors. A prediction horizon of 30 seconds ahead of real time during docking operations is examined. History data from the 29meter coastal displacement ship RV (Research Vessel) Gunnerus is applied to validate the approach. Results show that the inclusion of the data-based ML model significantly improves the prediction accuracy.

Developing a reliable model to identify the sea state is significant for the autonomous ship. This paper introduces a novel deep neural network model (SeaStateNet) to estimate the sea state based on the ship motion data from dynamically positioned vessels. The SeaStateNet mainly consists of three components: an Long-Short-Term Memory (LSTM) recurrent neural network to capture the long dependency in the ship motion data; a convolutional neural network (CNN) to extract time-invariant features; and a Fast Fourier Transform (FFT) block to extract frequency features. A feature fusion layer is designed to learn the degree affected by each component. The proposed model is applied directly to the raw time series data, without needing of any hand-engineered features. A sensitivity analysis (SA) method is applied to assess the influence of data preprocessing. Through benchmark test and experiment on ship motion dataset, SeaStateNet is verified effective for sea state estimation. The investigation on real-time test further shows the practicality of the proposed model.

No abstract

No abstract

When a ship experiences a loss of position reference systems, the ship's navigation system typically enters a mode known as dead reckoning to maintain an estimate of the position of the ship. Commercial systems perform this task using a state estimator that includes mathematical model knowledge. Such a model is non-trivial to derive and needs tuning if the dynamic properties of the vessel change. To this end we propose to use machine learning to estimate the horizontal velocity of the vessel without the help of position, velocity or acceleration sensors. A simulation study was conducted to show the ability to maintain position estimates during a Global Navigation Satellite System outage. Comparable performance is seen relative to the established Kalman Filter model-based approach.

Researchers have been investigating data-driven modeling as a key way to achieve ship intelligence for years. This paper presents a novel data analysis approach to data-driven modeling of ship motion.We propose a global sensitivity analysis (GSA) approach combining artificial neural network (ANN) and sparse polynomial chaos expansion (SPCE) techniques to accommodate high-dimensional sensor data collected from ship motion. An ANN is constructed as a surrogate model to associate ship sensor data with particular a certain type of ship motion. To account for the computational efficiency of GSA, an SPCE is integrated into the GSA to decrease the need for Monte Carlo (MC) samples generated by the ANN. A probe variable is designed to couple with the MC samples, which plays a role in determining degree of convergence of variable importance. A test on benchmark function demonstrates the efficiency and accuracy of the proposed approach. A case study of ship heading with and without environment effects is conducted. The experimental results show that the proposed approach can identify and rank the most sensitive factors of ship motion. The proposed approach highlights the application of GSA in data-driven modeling for ship intelligence.

Sea State is significant to the operations on the sea. The traditional model-based approaches need lots of knowledge of vessels, which limit the real-world use. This paper proposes a spectrogram-based deep learning model for sea state estimation (SpectralNet). In this model, the ship motion data is converted to spectrogram using short time Fourier transform (STFT). Unlike other methods, the spectrogram of each sensor will be combined to a new image. And then, a 2D convolutional neural network (CNN) is built as the classifier and the sea state can be identified. The experimental results show the proposed approach can achieve higher classification accuracy compared these methods applied directly in raw time series data. Through the comparison results of the proposed approach and the combination of spectrogram of different number of sensors, the proposed approach can achieve highest classification accuracy, and the classification accuracy is growing with the number of combined sensors. The sensitivity analysis finds the classification accuracy is easily influenced by the scale factor of images.