Dynamic model of manoeuvrability using recursive neural networks

Moreira, L.; Soares, C. Guedes

doi:10.1016/s0029-8018(02)00147-6

Cited by 101 publications

(36 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…System identification requires knowledge of at least some of these derivatives and in the present model it is obviously acceleration derivatives (first order) which are relatively easy to estimate. Therefore in this work we have chosen a model for system identification where the three linear hydrodynamic derivatives and their water depth dependent corrections alone are assumed known as given in (10)- (12). Thus, this model requires knowledge of three acceleration derivatives Xu, Yv and Nṙ and their corrections due to water depth, i.e.…”

Section: Model For Neural Networkmentioning

confidence: 99%

“…Suppose the training time series data of u, v, r,u,v,ṙ and δ are known either from experiments or from simulation, then one can obtain the time series of the functions g 1 , g 2 and g 3 from (10)- (12). Representing the discrete time series at the time instances t n (n = 1, 2, .…”

Section: Neural Network Formulationmentioning

confidence: 99%

“…In recent times, various approaches and techniques of system identification that have been used in the area of ship hydrodynamics are Markov process theories, statistical linearization techniques [8] and reverse multiple input-single output methods [9,10]. Recently, the neural network based identification has drawn attention in ship maneuvering [11][12][13]. The mathematical model of the neural network is so called because it mimics the learning process of * Corresponding author.…”

Section: Introductionmentioning

confidence: 99%

“…Whereas neural network based identification in ship maneuvering has been treated in the literature in a preliminary way [11][12][13], all the studies consider the classical Abkowitz model [7] of nonlinear maneuvering and its variants. This class of maneuvering models hold good for cargo ships but are quite inadequate for large tankers.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

System identification for nonlinear maneuvering of large tankers using artificial neural network

Rajesh

Bhattacharyya

2008

Applied Ocean Research

View full text Add to dashboard Cite

Section: Model For Neural Networkmentioning

confidence: 99%

Section: Neural Network Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

System identification for nonlinear maneuvering of large tankers using artificial neural network

Rajesh

Bhattacharyya

2008

Applied Ocean Research

View full text Add to dashboard Cite

“…Moreira and Soares [4] used data for a series of manoeuvres with varying rudder de�ection angles and approach speeds to train and validate a recursive neural network (RNN) manoeuvring simulation model for surface ships to predict tactical circles and zigzags.…”

Section: Introductionmentioning

confidence: 99%

Nomoto Indices for Constant-Depth Zigzag Manoeuvres of an Autonomous Underwater Vehicle

Azarsina

Williams

2013

ISRN Oceanography

View full text Add to dashboard Cite

A two-dimensional simulation code is used to study the characteristics of constant-depth zigzag manoeuvres of the axisymmetric autonomous underwater vehicle (AUV) MUN Explorer. Sea trials data for several manoeuvres with the AUV have been reported during the past four years; however, to obtain a more complete understanding of the vehicle's hydrodynamics, additional towing tank tests and computer simulation were performed. e present work, based on the towing tank test results and sea-trials data, utilizes computer simulations to predict the performance of the MUN Explorer AUV during horizontal zigzag manoeuvres. Next, the Nomoto indices for this AUV during constant-depth zigzag manoeuvres are estimated using the simulation results, and, then, Nomoto's �rst-order model for the rate of turn of the vehicle during horizontal zigzag manoeuvres in response to a square-wave input for the rudder de�ection angle is analytically solved. e paper investigates the validity of the simpli�ed yaw equation to predict a zigzag manoeuvre. Results of this research are a �rst step to understand the details of zigzag manoeuvres of an AUV such as duration of the �rst execute, yaw-checking ability, and duration of the overshoot.

show abstract

Maneuvering and Coursekeeping Characteristics

Molland

Hudson

2017

Encyclopedia of Maritime and Offshore Engineering

View full text Add to dashboard Cite

For a ship to operate safely it must have adequate control capability to be able to maintain and alter course at its service speed and to maneuver satisfactorily at slow speeds. The principal maneuvering and coursekeeping characteristics of ships are described. Directional stability is described, together with a description of rudder action, including the forces acting on a turn and the heel angle due to the rudder. The equations of motion representing the horizontal motion of the ship when coursekeeping or maneuvering are described. Methods of assessing maneuverability are described, including the turning circle, zig‐zag, spiral, and pull‐out tests. A description is given of the methods of predicting maneuvering characteristics and experimental and numerical simulations, together with an outline of the International Maritime Organization required standards for maneuverability.

show abstract

Dynamic model of manoeuvrability using recursive neural networks

Cited by 101 publications

References 2 publications

System identification for nonlinear maneuvering of large tankers using artificial neural network

System identification for nonlinear maneuvering of large tankers using artificial neural network

Nomoto Indices for Constant-Depth Zigzag Manoeuvres of an Autonomous Underwater Vehicle

Maneuvering and Coursekeeping Characteristics

Contact Info

Product

Resources

About