Energy efficiency of inland ships is significantly influenced by navigational environment, including wind speed and direction as well as water depth and speed. The complexity of the inland navigational environment makes it rather difficult to determine the optimal speeds under different environmental conditions to achieve the best energy efficiency. Route division according to the characteristics of these environmental factors could provide a good solution for the optimization of ship engine speed under different navigational environments. In this paper, the distributed parallel k-means clustering algorithm is adopted to achieve an elaborate route division by analyzing the corresponding environmental factors based on a self-developed big data analytics platform. Subsequently, a ship energy efficiency optimization model considering multiple environmental factors is established through analyzing the energy transfer among hull, propeller and main engine. Then, decisions are made concerning the optimal engine speeds in different segments along the path. Finally, a case study on the Yangtze River is performed to validate the present optimization method. The results show that the proposed method can effectively reduce energy consumption and CO2 emissions of ships.@en

This paper investigates the formation keeping problem of heterogeneous ships with underactuated inputs, uncertain dynamics, and environmental disturbances. The control objective is to make the heterogeneous followers keep the desired formation while tracking a leader. To solve the problem effectively, a novel virtual leader–follower formation scheme considering the ship heterogeneity is proposed by utilizing the backstepping method, adaptive neural network, and adaptive control law. The stability of the formation control system is proved based on Lyapunov's direct method where all tracking errors are guaranteed to be uniformly ultimately bounded. Finally, simulations and comparisons are conducted to verify the effectiveness of the proposed control law.@en

It is of significant importance to optimize the energy consumption of ships in order to improve economy and reduce CO2 emissions. However, the energy use of ships is affected by a series of navigational environmental parameters, which have certain spatial and temporal differences and variability. Therefore, the dynamic collaborative optimization method of sailing route and speed, which fully considers the spatial and temporal distribution characteristics of those factors, is of great importance. In this paper, the spatial and temporal distribution characteristics of the environmental factors and their related ship energy consumption profiles are first analyzed. Subsequently, a ship energy consumption model considering various environmental factors is established to realize the prediction of energy use of ships within the navigation region. Then, a novel dynamic collaborative optimization algorithm, which adopts the Model Predictive Control (MPC) strategy and swarm intelligence algorithm, is proposed, to further improve the ship's energy consumption optimization. Finally, a case study is conducted to demonstrate the effectiveness of the proposed method. The results show that the newly developed dynamic collaborative optimization method, which fully considers the continuously time-varying characteristics of environmental and operational parameters, could effectively reduce the energy consumption in comparison to the original operational mode. In addition, the adoption of the MPC strategy produces better performance results compared to the optimization method without the MPC strategy.@en

The optimization of ship energy consumption is attracting a great deal of attention, as societies seek to save energy and reduce emissions. Shipping companies are more concerned with the energy consumption of a ship fleet, as opposed to that of a single ship. Because the energy consumption of a fleet is influenced by multiple factors including environmental factors, port operations and transport demands, an improvement in a single ship's energy consumption does not necessarily mean that the overall energy consumption of a fleet is good. In addition, those factors are usually varying over time, making it hard to optimize the fleet's energy consumption by methods that do not consider these time-varying factors. Therefore, a bi-level distributed dynamic optimization method based on distributed model predictive control is proposed. Moreover, an upper-level optimization model for fleet operational decision-making and a lower-level dynamic optimization model of fleet energy consumption are established. Based on these, a control algorithm for the dynamic optimization of fleet energy consumption is developed. Finally, a case study is carried out to demonstrate the effectiveness of the method. It can further reduce the energy consumption of each ship by at least 1.1% and about 6.8% for the whole fleet.@en

Energy saving and emission reduction have attracted a great deal of attention in the maritime industry. The optimization of a ship's energy efficiency can reduce energy consumption and CO2 emissions effectively. However, most of the available studies only focus on either the sailing speed or route optimization, and the interaction between speed and route under the influence of multiple environmental factors was not accounted properly. In this paper, a novel joint optimization method of the sailing route and speed, which considers the interaction between route and speed as well as multiple environmental factors, is proposed to fully exploit the energy efficiency's potential. Moreover, a joint optimization model of the sailing route and speed, which is based on an energy consumption model that considers multiple environmental factors, is established. Next, a solution algorithm for the joint optimization model is investigated in order to achieve joint decision-making with regard to the sailing route and speed. Finally, a case study is conducted that demonstrates the effectiveness of the proposed method. The results show that the proposed method can achieve the optimal sailing route and speed under complex environmental conditions, as well as a reduction in fuel consumption and CO2 emissions of about 4%.@en

Nowadays, optimization of ship energy efficiency attracts increasing attention in order to meet the requirement for energy conservation and emission reduction. Ship operation energy efficiency is significantly influenced by environmental factors such as wind speed and direction, water speed and depth. Owing to inherent time-variety and uncertainty associated with these various factors, it is very difficult to determine optimal sailing speeds accurately for different legs of the whole route using traditional static optimization methods, especially when the weather conditions change frequently over the length of a ship route. Therefore, in this paper, a novel dynamic optimization method adopting the model predictive control (MPC) strategy is proposed to optimize ship energy efficiency accounting for these time-varying environmental factors. Firstly, the dynamic optimization model of ship energy efficiency considering time-varying environmental factors and the nonlinear system model of ship energy efficiency are established. On this basis, the control algorithm and controller for the dynamic optimization of ship energy efficiency (DOSEE) are designed. Finally, a case study is carried out to demonstrate the validity of this optimization method. The results indicate that the optimal sailing speeds at different time steps could be determined through the dynamic optimization method. This method can improve ship energy efficiency and reduce CO2 emissions effectively.@en

In the case of the global energy crisis and the higher sound of energy saving and emission reduction, how to take effective management measures of ship energy efficiency to achieve the goal of energy saving and emission reduction, put forward a new challenge for the development of shipping technology. The application of big data technology provides a new idea for the research of ship energy efficiency optimization management. The energy efficiency management level of the operating ship can be improved by the analysis and mining of the big data. In this paper, a big data analysis platform for ship energy efficiency management based on the widely used Hadoop platform architecture is designed. Afterward, due to the huge amount of involved data on the energy efficiency management which has exceeded the processing ability of traditional solutions, the big data analysis method is used to achieve the route division according to environmental factors, thus to lay the foundation for speed optimization in different segments of a route. Finally, a simple decision-making method of optimal engine speed based on the result of route division is proposed, which could improve ship energy efficiency and hence reduce CO2 emission.@en

Human experience is regarded as an indispensable part of artificial intelligence in the process of controlling or decision making for autonomous cargo ships. In this paper, a novel Deep Q-Network-based (DQN) approach is proposed, which performs satisfactorily in controlling a cargo ship automatically without any human experience. At the very beginning, we use the model of KRISO Very Large Crude Carrier (KVLCC2) to describe a cargo ship. To manipulate this ship has to conquer great inertia and relatively insufficient driving force. Subsequently, customary waterways, regulations, conventions are described with Artificial Potential Field and value-functions in DQN. Based on this, the artificial intelligence of planning and controlling a cargo ship can be obtained by undertaking sufficient training, which can control the ship directly, while avoiding collisions, keeping its position in the middle of the route as much as possible. In simulation experiments, it is demonstrated that such an approach performs better than manual works and other traditional methods in most conditions, which makes the proposed method a promising solution in improving the autonomy level of cargo ships.@en

With the further development of marine and information technologies, ship intelligence, green policies and automation will become mainstream with global cargo ships. Ship labor costs increase every year, so for the foreseeable future, the number of experienced crew members will be greatly reduced as smart ship emergence accelerates. At present, there is no mature research system for the human-like piloting of smart ships. In this paper, we use an improved decision tree, which could address problems of fuzziness and uncertainty. This will allow us to study the decision mechanisms of different piloting behaviors in order to realize the automatic acquisition and representation of the pilot's decision-making knowledge in inbound ship analysis as well as the simulated reproduction of the pilot's behavior. The simulation results show that the piloting decision recognition model, based on the fuzzy Iterative Dichotomiser 3 (ID3) decision tree, possesses a high reasoning speed and can accurately identify current piloting behavior. This provides theoretical guidance and a feasibility basis for research into human-like piloting behavior and the realization of automatic smart ship piloting systems.@en

With the further development of marine and information technologies, ship intelligence, green policies and automation will become mainstream with global cargo ships. Ship labor costs increase every year, so for the foreseeable future, the number of experienced crew members will be greatly reduced as smart ship emergence accelerates. At present, there is no mature research system for the human-like piloting of smart ships. In this paper, we use an improved decision tree, which could address problems of fuzziness and uncertainty. This will allow us to study the decision mechanisms of different piloting behaviors in order to realize the automatic acquisition and representation of the pilot's decision-making knowledge in inbound ship analysis as well as the simulated reproduction of the pilot's behavior. The simulation results show that the piloting decision recognition model, based on the fuzzy Iterative Dichotomiser 3 (ID3) decision tree, possesses a high reasoning speed and can accurately identify current piloting behavior. This provides theoretical guidance and a feasibility basis for research into human-like piloting behavior and the realization of automatic smart ship piloting systems.@en