Kazuhiko Hasegawa

Automatic ship berthing using artificial neural network trained by consistent teaching data using nonlinear programming method

Ship handling during berthing is considered as one of the most sophisticated tasks that a ship master has to face. The presence of current and wind make it even more complicated to execute, especially when ship approaches to a pier in low speed. To deal with such phenomenon, only experienced human brain decides the necessary action taken depending on situation demand. So automation in berthing is still far beyond imagination. But, if the human brain can be replicated by any suitable artificial intelligence technique to perform the same action that human brain does during berthing, then automatic ship berthing is possible. In this research artificial neural network is used for that purpose. To enhance its learnability, consistent teaching data based on the virtual window concept are created to ensure optimal steering with the help of nonlinear programming language (NPL) method. Then instead of centralized controller, two separate feed forward neural networks are trained using Lavenberg-Marquardt algorithm in backpropagation technique for command rudder angle and propeller revolution output respectively. The trained ANNs are then verified for their workability in no wind condition. On the other hand, separate ANNs are trained with reconstructed teaching data considering gust wind disturbances. To deal with any abrupt condition, ANN followed by PD controller is also introduced in case of command rudder angle output whose effectiveness is well verified not only for teaching data but also in case of non-teaching data and different gust wind distributions.

Feasibility Study on Intelligent Marine Traffic System 1

Abstract Four-year research of virtual VTS (Vessel Traffic Service) project will terminate in FY2000 and new five-year project of Marine ITS (Intelligent Transport Systems) is started by Ministry of Transport, Japan from FY2000. The project contains three objects. Automatic colusion and grounding avoidance system, marine traffic control system in congested waterways and berthing/deberthing supporting system. In this paper, the project is briefly explained and some feasibility study of the second item is discussed based on the research done by authors. Some future direction of this area is suggested.

Inland transportation system planning by life cycle impact assessment: a case study

Abstract The comparison of land and inland water transportation from economical and ecological points of view is discussed. Required freight rates for trucks and ships are calculated and compared to find which has economic superiority. From the environmental impacts of these two transportation types, the comparative environmental destruction indices for two different time-durations are estimated. All these investigations were conducted for the Yokohama–Fukuoka route in Japan. Life cycle impact assessment, a very useful tool for quantitatively evaluating the environmental influence of a product, was used to compare the environmental burden imposed by these types of transportation. Finally, the way that these results can be used for inland transportation system planning is discussed.

A microscopic theory of STM-induced CO desorption from Cu(111)

Abstract We propose a microscopic theory to describe the dynamics of STM-induced desorption of CO from Cu(111). In the theory, a single electron initially occupies the CO 2π ∗ orbital, and the CO–Cu stretching vibration, described by a Morse potential, is in the ground state. An excitation of the CO–Cu stretching vibration occurs when this electron subsequently transfers/tunnels from the CO 2π ∗ orbital to the metal. The excitation of the CO–Cu stretching vibration to an unbound state leads to CO desorption from Cu(111). Our calculation results for the desorption probability agree with experimental results, and show the same isotope effects as those observed experimentally.

Some recent developments of next generation's marine traffic systems

Abstract Some recent developments of next generations marine traffic systems from Marine ITS project in Japan are roughly introduced. One is marine traffic simulation utilizing automatic collision avoidance system. It can simulate marine traffic simulation for any interested area based on a given OD tables etc. The safety assessment in congested area and utilization for planning of on-land AIS stations are shown as examples of its applications. The other is automatic berthing system utilizing artificial neural network. A proposal of automatic teaching data creation is introduced. A result of a model ship experiments is shown.

Dynamics of STM-Induced Acetylene Dissociation on Cu(100).

A model is presented to describe the dynamics of an acetylene on Cu(100) induced by STM, where the relation between the change of the corresponding electron system caused by an electron tunneling from an STM tip to the metal substrate via the adsorbed acetylene, and the transition of the vibrational state for the intramolecular motion is taken into account. With this model, we can reproduce the experimentally measured dissociation probability of C 2 H 2 (C 2 D 2 ) into C 2 H(C 2 D) and H(D) when the STM tip is set at a position above the center of the C–C bond of an adsorbed C 2 H 2 (C 2 D 2 ).

Study on manoeuverability and control of an autonomous Wave Adaptive Modular Vessel (WAM-V) for ocean observation

In this paper, we are proposing the use of a catamaran equipped with standard navigational sensors as an autonomous surface vehicle for in situ measurement of oceanographic data or as a complimentary observing system. In this research, we mainly focus on the maneuverability of the Wave Adaptive Modular Vessel (WAM-V). The WAM-V must have ability to cruise on the water with a robust propulsion system which determines its propulsion capability and maneuverability. Firstly, the paper describes the configuration of WAM-V. Secondly the paper deals with mathematical modeling, which describes well physics based dynamics of WAM-V. Demand for WAM-V catamaran is justified to a point for improved manoeuverability and because the motion of the boat is affected by hydrodynamics, so many hydrodynamic parameters including resistance force for Mono hull and twin hull are estimated by towing tank experiment. It is observed from the experiments that at higher velocity (Froud Number (fn) > 0.3) due to interference between the two hulls the hydrodynamic derivatives do not remain same as in the case of a single hull. With the help of the geometrical shape of WAM-V the design ratios are calculated. The Matlab simulation is intended to analyze the different parameters for the effect of changing the propeller revolution which replaces the rudder action. Finally, the paper delineates the simulation results for PID tracking control of WAM-V using the Nomotos response model.

Dynamics of STM-induced acetylene rotation on Cu(100)

Abstract We present a microscopic theory to describe the dynamics of STM-induced C 2 HD rotation on Cu(100). In our model, two intermediate processes, which lead to C 2 HD rotation, are taken into account when an electron initially transfers/tunnels from the STM tip to the adsorbate and then, subsequently, to the metal substrate. In one process, excitation of the hindered rotational mode occurs without CH(D) stretching vibrational excitation. In the other process, excitation of the CH(D) stretching vibrational mode occurs first and then, with the relaxation of the excited stretching vibrational mode, excitation of the hindered rotational mode. C 2 HD rotation to another equilibrium position on Cu(100) occurs when the excitation of the hindered rotational mode exceeds some threshold energy. The calculated rotation probabilities satisfactorily reproduce the experimental results.

Implementation of Automatic Ship Berthing Using Artificial Neural Network for Free Running Experiment

Abstract Ship berthing has always considered as a multiple input multiple output phenomenon. And such controlling action becomes even more sophisticated when the ship approaches to a pier especially in low speed. The current and presence of wind also make the task more complicated. But, if a human brain can be replicated by any artificial intelligence technique to perform the same necessary action that human brain does, then automatic operation during complete berthing process is believed to be possible by many researchers. For that purpose as an initial stage of this research, artificial neural network is chosen as one of AI techniques for automatic berthing and to increase its learnability, concentration is given on the consistency of the teaching data provided. To do that, nonlinear programming method is used where ships actual behavior is predicted using famous manoeuvring mathematical group model. After successfully training, ANN controller is tested for various known and unknown condition including wind disturbances and found good results. Finally, to verify the simulated successful results, the current research is based on execution of free running experiment with the implementation of automatic ship berthing using the same trained ANN where adequate decisions for command rudder and propeller revolution taken are decided automatically depending on real time multiple input parameters.

Low Speed Ship Manoeuvrability: Mathematical Model and its Simulation

In case of offshore support vessels, it is quite important for their behaviours in low speed manoeuvrability. It is not easy to operate offshore support vessels and it raises an importance to train crew by a ship handling simulator. Therefore it is quite hot issue for ship handling simulator vendors to provide mathematical model of support vessels, but from the users’ point-of-view the model used for the simulator is not clear. Up to now some mathematical models are proposed in the literature, but the validation is not yet done carefully. For example, cross flow model is the main part for hydrodynamic force in low speed ship manoeuvring. From model ship experiments of various types of ships and from some comparison study, it is found that further discussion is necessary. In this paper, sway force and yaw moment as well as surge force will be treated in low speed condition with certain sway and yaw motions. There are many experiment results for such hydrodynamic forces and moment, especially for sway force and yaw moment, for sway motion, but those for yaw motion is quite limited.In this paper, such hydrodynamic forces and moment for both sway and yaw motions are calculated and validated with experiment results. Some manoeuvring simulation will also demonstrate which terms and/or expressions in the mathematical model are affecting the motion.Copyright