The Experts below are selected from a list of 159 Experts worldwide ranked by ideXlab platform
Kazuhiko Hasegawa - One of the best experts on this subject based on the ideXlab platform.
-
Consistently Trained Artificial Neural Network for Automatic Ship Berthing Control
TransNav: International Journal on Marine Navigation and Safety of Sea Transportation, 2015Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract:In this paper, consistently trained Artificial Neural Network controller for automatic ship berthing is discussed. Minimum time course changing manoeuvre is utilised to ensure such consistency and a new concept named ‘virtual window’ is introduced. Such consistent teaching data are then used to train two separate multi-layered feed forward neural networks for command rudder and Propeller Revolution output. After proper training, several known and unknown conditions are tested to judge the effectiveness of the proposed controller using Monte Carlo simulations. After getting acceptable percentages of success, the trained networks are implemented for the free running experiment system to judge the network’s real time response for Esso Osaka 3-m model ship. The network’s behaviour during such experiments is also investigated for possible effect of initial conditions as well as wind disturbances. Moreover, since the final goal point of the proposed controller is set at some distance from the actual pier to ensure safety, therefore a study on automatic tug assistance is also discussed for the final alignment of the ship with actual pier.
-
ICARCV - Artificial neural network based automatic ship berthing combining PD controlled side thrusters — A combined controller for final approaching to berth
2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), 2014Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract:Manoeuvring ship during berthing has always required vast experience, skill and knowledge to provide desired necessary actions. Presence of environmental disturbances as well as decreased manoeuvrability in low speed often makes the whole procedure so sophisticated that even slight mistake may results catastrophic disaster. By knowing the fact that Artificial Neural Network (ANN) has the ability to replicate human brains and good enough for controlling such multi-input multi-out nonlinear system, at the beginning of this research, consistent teaching data are created using Non Linear Programing (NPL) method and a new concept named ‘virtual window’ is introduced. Later on, considering gust wind disturbances, two separate multilayer feed forward networks are trained using back propagation technique for command rudder and Propeller Revolution output. After being successful in simulation works, real time berthing experiments are carried out for Esso Osaka 3-m model where the ship is planned to successfully stop within a distance of 1.5L from actual pier to ensure safety. Finally, as a current status, PD controlled side thrusters are included in order to shake hand with current controller to align the ship with pier considering wind up to 1.5 m/s for model ship.
-
Automatic ship berthing using artificial neural network trained by consistent teaching data using nonlinear programming method
Engineering Applications of Artificial Intelligence, 2013Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract: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.
-
Implementation of Automatic Ship Berthing Using Artificial Neural Network for Free Running Experiment
IFAC Proceedings Volumes, 2013Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract: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 ship's 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.
-
Design Practice for the Horizontal Fin of a Single Screw-Twin Rudder System
Journal of the Japan Society of Naval Architects and Ocean Engineers, 2012Co-Authors: Toshihiko Arii, Kazuyoshi Hosogaya, Kazuhiko HasegawaAbstract:The single-Propeller/twin-rudder system composed of single Propeller and two high-lift rudders of fish-tail type has been installed on many vessels in Japan. With this system, a ship can be maneuvered at any mode including going astern, hovering, dead slow forwarding and turning by means of various rudder angle combination, with Propeller Revolution being kept in the forward direction. To improve propulsive efficiency of the single-Propeller/twin-rudder system, a pair of reaction fins is attached between two rudders where the Propeller slip stream passes. Form, size and setting angle of the fin affect propulsive performance a great deal. A method to determine the setting angle of fin is discussed in this paper. Fundamentally the setting angle is determined by doing model experiment in model basin. As the second method the authors propose to estimate the setting angle based on fluid pattern of stern. A concept of the datum line for evaluation of lift of fin is introduced. A method to determine the representative inflow angle to the fin by the datum line and to determine the optimum setting angle of fin is discussed.
Yaseen Adnan Ahmed - One of the best experts on this subject based on the ideXlab platform.
-
Consistently Trained Artificial Neural Network for Automatic Ship Berthing Control
TransNav: International Journal on Marine Navigation and Safety of Sea Transportation, 2015Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract:In this paper, consistently trained Artificial Neural Network controller for automatic ship berthing is discussed. Minimum time course changing manoeuvre is utilised to ensure such consistency and a new concept named ‘virtual window’ is introduced. Such consistent teaching data are then used to train two separate multi-layered feed forward neural networks for command rudder and Propeller Revolution output. After proper training, several known and unknown conditions are tested to judge the effectiveness of the proposed controller using Monte Carlo simulations. After getting acceptable percentages of success, the trained networks are implemented for the free running experiment system to judge the network’s real time response for Esso Osaka 3-m model ship. The network’s behaviour during such experiments is also investigated for possible effect of initial conditions as well as wind disturbances. Moreover, since the final goal point of the proposed controller is set at some distance from the actual pier to ensure safety, therefore a study on automatic tug assistance is also discussed for the final alignment of the ship with actual pier.
-
ICARCV - Artificial neural network based automatic ship berthing combining PD controlled side thrusters — A combined controller for final approaching to berth
2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), 2014Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract:Manoeuvring ship during berthing has always required vast experience, skill and knowledge to provide desired necessary actions. Presence of environmental disturbances as well as decreased manoeuvrability in low speed often makes the whole procedure so sophisticated that even slight mistake may results catastrophic disaster. By knowing the fact that Artificial Neural Network (ANN) has the ability to replicate human brains and good enough for controlling such multi-input multi-out nonlinear system, at the beginning of this research, consistent teaching data are created using Non Linear Programing (NPL) method and a new concept named ‘virtual window’ is introduced. Later on, considering gust wind disturbances, two separate multilayer feed forward networks are trained using back propagation technique for command rudder and Propeller Revolution output. After being successful in simulation works, real time berthing experiments are carried out for Esso Osaka 3-m model where the ship is planned to successfully stop within a distance of 1.5L from actual pier to ensure safety. Finally, as a current status, PD controlled side thrusters are included in order to shake hand with current controller to align the ship with pier considering wind up to 1.5 m/s for model ship.
-
Automatic ship berthing using artificial neural network trained by consistent teaching data using nonlinear programming method
Engineering Applications of Artificial Intelligence, 2013Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract: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.
-
Implementation of Automatic Ship Berthing Using Artificial Neural Network for Free Running Experiment
IFAC Proceedings Volumes, 2013Co-Authors: Yaseen Adnan Ahmed, Kazuhiko HasegawaAbstract: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 ship's 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.
Shao Yu Chen - One of the best experts on this subject based on the ideXlab platform.
-
Development of an Image Processing Module for Autonomous Underwater Vehicles Through Integration of Object Recognition With Stereoscopic Image Reconstruction
Volume 7B: Ocean Engineering, 2019Co-Authors: Yu Hsien Lin, Shao Yu ChenAbstract:Abstract This study investigated the development of visual recognition and stereoscopic imaging technology, applying them to the construction of an image processing system for Autonomous Underwater Vehicles (AUVs). For the proposed visual recognition technology, an optical flow algorithm was used to detect the linear features and movement speeds of dynamic images; the proposed stereoscopic imaging technique employed a Harris corner detector to estimate the distance of the target. A physical AUV was constructed with a wide-angle lens camera and a binocular vision device mounted on the bow to provide image input. Subsequently, a simulation environment was established in Simscape Multibody and used to control the post-driver system of the stern, which contained horizontal and vertical rudder planes as well as the Propeller. Finally, the dynamic testing results were combined with a fuzzy controller to output the real-time responses of the vehicle regarding the angles, rates of the rudder planes, and the Propeller Revolution speeds at various distances.
-
Development of an image processing module for autonomous underwater vehicles through integration of visual recognition with stereoscopic image reconstruction
Journal of Marine Science and Engineering, 2019Co-Authors: Yu Hsien Lin, Shao Yu Chen, Chia Hung TsouAbstract:This study investigated the development of visual recognition and stereoscopic imaging technology, applying them to the construction of an image processing system for autonomous underwater vehicles (AUVs). For the proposed visual recognition technology, a Hough transform was combined with an optical flow algorithm to detect the linear features and movement speeds of dynamic images; the proposed stereoscopic imaging technique employed a Harris corner detector to estimate the distance of the target. A physical AUV was constructed with a wide-angle lens camera and a binocular vision device mounted on the bow to provide image input. Subsequently, a simulation environment was established in Simscape Multibody and used to control the post-driver system of the stern, which contained horizontal and vertical rudder planes as well as the Propeller. In static testing at National Cheng Kung University, physical targets were placed in a stability water tank; the study compared the analysis results obtained from various brightness and turbidity conditions in out-of-water and underwater environments. Finally, the dynamic testing results were combined with a fuzzy controller to output the real-time responses of the vehicle regarding the angles, rates of the rudder planes, and the Propeller Revolution speeds at various distances.
Yu Hsien Lin - One of the best experts on this subject based on the ideXlab platform.
-
Development of an Image Processing Module for Autonomous Underwater Vehicles Through Integration of Object Recognition With Stereoscopic Image Reconstruction
Volume 7B: Ocean Engineering, 2019Co-Authors: Yu Hsien Lin, Shao Yu ChenAbstract:Abstract This study investigated the development of visual recognition and stereoscopic imaging technology, applying them to the construction of an image processing system for Autonomous Underwater Vehicles (AUVs). For the proposed visual recognition technology, an optical flow algorithm was used to detect the linear features and movement speeds of dynamic images; the proposed stereoscopic imaging technique employed a Harris corner detector to estimate the distance of the target. A physical AUV was constructed with a wide-angle lens camera and a binocular vision device mounted on the bow to provide image input. Subsequently, a simulation environment was established in Simscape Multibody and used to control the post-driver system of the stern, which contained horizontal and vertical rudder planes as well as the Propeller. Finally, the dynamic testing results were combined with a fuzzy controller to output the real-time responses of the vehicle regarding the angles, rates of the rudder planes, and the Propeller Revolution speeds at various distances.
-
Development of an image processing module for autonomous underwater vehicles through integration of visual recognition with stereoscopic image reconstruction
Journal of Marine Science and Engineering, 2019Co-Authors: Yu Hsien Lin, Shao Yu Chen, Chia Hung TsouAbstract:This study investigated the development of visual recognition and stereoscopic imaging technology, applying them to the construction of an image processing system for autonomous underwater vehicles (AUVs). For the proposed visual recognition technology, a Hough transform was combined with an optical flow algorithm to detect the linear features and movement speeds of dynamic images; the proposed stereoscopic imaging technique employed a Harris corner detector to estimate the distance of the target. A physical AUV was constructed with a wide-angle lens camera and a binocular vision device mounted on the bow to provide image input. Subsequently, a simulation environment was established in Simscape Multibody and used to control the post-driver system of the stern, which contained horizontal and vertical rudder planes as well as the Propeller. In static testing at National Cheng Kung University, physical targets were placed in a stability water tank; the study compared the analysis results obtained from various brightness and turbidity conditions in out-of-water and underwater environments. Finally, the dynamic testing results were combined with a fuzzy controller to output the real-time responses of the vehicle regarding the angles, rates of the rudder planes, and the Propeller Revolution speeds at various distances.
Tatsuro Kudo - One of the best experts on this subject based on the ideXlab platform.
-
DESIGN AND EVALUATION OF NEW SUPERCAVITATING Propeller
Journal of the Society of Naval Architects of Japan, 1993Co-Authors: Yoshitaka Ukon, Tatsuro Kudo, Yuzo Kurobe, Tetsuji HoshinoAbstract:This paper firstly describes a new design method of supercavitating (hereafter, SC) Propellers. The circulation distribution of Propeller blades was calculated by a lifting line theory as an existing method, while the hydrodynamic characteristics of blade sections at each radial position were calculated by a nonlinear cavity flow theory based on a higher-order singularity panel method, “Linear Vortex Panel Method ; LVPM”.Three SC Propellers were designed for the same design conditions, that is, the ship speed is 50 kts, the required thrust per shaft is 100 tons and the Propeller immersion is 4 meters. The SSPA SC Propeller was chosen as a target SC Propeller, since reliable design charts were published. The optimum Propeller Revolution rate was determined from the chart under the constrained condition of supercavitation. For the target Propeller, a SSPA Propeller model was made and the hydrodynamic characteristics were measured in the SRI large cavitation tunnel.From the calculated circulation distribution and the assumed blade contour, the design lift coefficient at each radial position and SC section were determined by the iteration so that the strength requirement was satisfied. The lifting surface correction based on Ludwieg-Ginzel's method was applied to the blade profile on the face side of the first designed SC Propeller (SRIJ-I). The efficiency of the SRIJ-I SC Propeller at the design condition (J=1.1) was 0.676 and about 4 % higher than the target Propeller. The measured thrust of the SRIJ-I SC Propeller was 15 % higher than the predicted one and this Propeller emitted relatively higher cavitation noise.Secondly effort was made to improve the performance of the first designed SC Propeller. From the examination by the experiments, inappropriate camber correction was cleared up. Using the load distribution of the SC sections given by the LVPM, the camber distribution at each radial position was calculated by the Propeller design method based on “Quasi-Continuous Method”. The second SC Propeller was tested at the cavitation tunnel. The measured Propeller efficiency at the design condition was 0.720 and the increase of 11 % on the efficiency was obtained against the target Propeller. The obtained thrust was 4 % higher than the predicted one, while the Propeller was fully cavitating. It is concluded that a new favorable SC Propeller could be designed by the present design method.
-
Measurement of Pressure Distribution on a Full Scale Propeller
Journal of the Society of Naval Architects of Japan, 1990Co-Authors: Yoshitaka Ukon, Tatsuro Kudo, Yuzo Kurobe, Hikaru Kamiirisa, Hajime Yuasa, Hironao Kubo, Yoshiki ItadaniAbstract:In the previous paper, authors have developed a new technique to measure the pressure distribution around the blades of a full scale Propeller. The full scale measurements were performed on the conventional Propeller, CP in short, of the training ship “Seiun-Maru”. From the results of full scale measurement, the measured pressure distributions were similar at each Propeller loading condition, except cavitation region. Comparing with an existing Propeller lifting surface theory, good agreements were found at most of the measurement points on the back side except near the Propeller tip. This paper describes the measurement of pressure distribution on a highly skewed Propeller, HSP in short, of the same ship “Seiun-Maru”. First of all, the special pressure pick-up was improved taking account of the experience in the previous measurement. The same measurement instruments were employed. The measurements were also performed with the same procedure as the previous ones under several working conditions of Propeller Revolution rate 70, 90, 110 and 149 rpm. At the Propeller Revolution rates more than 110 rpm, the thrust coefficient KT and the advance coefficient J are 0.190 and 0.66, respectively. The accuracy of the present measurement was estimated to be the same as that of the previous one, i. e, ± 0.03 kg/cm2.The measured pressure distributions were compared with the theoretical one with using an estimated nominal full scale wake distribution. Excellent agreements with the theory were found at most of the measurement points, especially in the fore part of the blades. These results indicate the usefulness of the lifting surface theory and the estimated wake for a highly skewed Propeller in full scale.On the other hand, the following unforeseen findings were obtained. The measured pressure at 90% radial position tends to decrease toward the trailing edge and completely differs from the theory. This suggests us the hydrodynamic load in the vicinity of the trailing edge at 90% radial position was remarkably heavier than that predicted by the theory. This cyclic load might cause the break-off of the Propeller tip due to rapid fatigue crack growth, if a Propeller blade is damaged at the trailing edge.The measured pressure in the region of sheet cavitation on HSP was higher than the vapor pressure while that on CP was equal to or lower than the vapor pressure.The present full scale measurements indicated that there still exist some problems on the existing Propeller theory and some improvements are necessary on the modelling of a Propeller theory including separation vortex from the leading edge.The present measurement of pressure distribution on both Propellers also provides us a number of invaluable standard data to develop and validate a new Propeller theory.
-
MEASUREMENT OF PRESSURE DISTRIBUTION ON A FULL SCALE Propeller - MEASUREMENT ON A CONVENTIONAL Propeller
Naval architecture and ocean engineering, 1990Co-Authors: Yoshitaka Ukon, Tatsuro KudoAbstract:This paper describes the development of a sophisticated pressure measurement technique for a full scale Propeller and the success of the measurement. First of all, the special pressure pick-ups with Helmholtz chamber were designed. The full scale measurements were carried out on the training ship SEIUN-MARU. Six pressure pick-ups were equipped at each of four Propeller blades. The pressure signals were transmitted from the pressure pick-ups on the Propeller blades through slip-rings to FM receivers and analysed using static pressure calibration data obtained in the sock before the voyage. This ship was operated so carefully that the working conditions at each Propeller Revolution rate were kept constant, that is, Kr=0.210. Then, the measured non-dimensionalised pressure distributions were similar at each condition, except cavitation regions. Except the lowest Revolution rate, sheet cavitation or tip vortex cavitation was observed and the influence of cavitation of other blades on the pressure measurement was found out. The present measurement techniques have the accuracy of plus or minus 0.03 kg/cm2. By the pressure coefficient, it amounts to plus or minus 0.3 at 70 RPM and plus or minus 0.7 at 140 RPM, respectively. The measured pressure distributions were compared with the theoretical ones obtained by the existing lifting surface theory. In this calculation, the estimated nominal wake distribution was employed, including the tangential wake based on the measurement in a towing tank. Excellent agreements with theory were found at most of the measurement points, especially the fore part of the blades. These results clearly demonstrate that the use of this estimated wake and the lifting surface theory with the concept of the equivalent two-dimensional profile is quite reasonable for a conventional Propeller principally. Near the angular position of the top, some discrepancies between the measurements and theory were observed probably due to the deformation of the nominal wake and the leading edge separation. The present full scale measurements indicated that there still exist some problems on the lifting-surface theory and the use of nominal wake. These measurements also confirmed that the measured pressure in the sheet cavitation region was nearly equivalent to the vapour pressure at each working condition. The study has provided a number of invaluable standard data to validate the numerical computational techniques on marine Propellers at high Reynolds number.
