Join for free Login

Advertisement

Figure 2 - available via license: Creative Commons

Attribution 4.0 International
Content may be subject to copyright.

Download View publication

Vessels motions along the three axes.

Source publication

+5

Machine Learning Based Moored Ship

Movement Prediction
Article Full-text available
Jul 2021
Alberto Alvarellos · Andres Figuero ·
Humberto Carro · [...] · Juan R. Rabuñal
Several port authorities are involved in the
R+D+i projects for developing port management
decision-making tools. We recorded the
movements of 46 ships in the Outer Port of
Punta Langosteira (A Coruña, Spain) from 2015
until 2020. Using this data, we created neural
networks and gradient boosting models that
predict the six degrees of freedom of a m...

Cite Download full-text

Citations

... With regard to the requirements of port

handlings, and the ability of terminals to
respond to emergency needs, Li et al. [3]
presented twin yard crane scheduling; they
considered the dynamic cut-off time and the
non-crossing constraints of yard cranes in
order to enhance the flexibility of container
yard handling. Machine learning was used
by Alvarellos et al. [4] to predict moored
ship movement. With the movement data of
46 ships recorded in the Outer Port of
Punta Langosteira (A Coruña, Spain) from
2015 until 2020, they created neural
networks and gradient-boosting models that
predict the six degrees of freedom of a
moored vessel using ocean meteorological
data and ship characteristics. ...

Coastal Engineering: Sustainability and New

Technologies
Article Full-text available
Aug 2023
M. Dolores Esteban · José-Santos López-
Gutiérrez · Vicente Negro · M. Graça Neves
Coastal engineering is a constantly evolving
discipline, in which it is essential to seek a balance
between the natural character of the coastal zon…
and the integration, to a greater or lesser extent, of
View
human activities in that space [...]

... These limits are used in the assessment

of downtime with respect to the behavior of
a particular vessel berthed in a specific port
[10][11][12]. For this reason, the response
of the ship-lines-fenders system is
sometimes simulated with a numerical
model and recently additionally through
machine-learning tools [13, 14]. 445 m has
a depth of 15 m (zone Z3), and there is an
intermediate draft transition zone of 16.5 m
(A2 dock). ...

A Decision-Making Tool for Port Operations

Based on Downtime Risk and Met-Ocean…
Conditions including Infragravity Wave
Article Full-text available
Forecast
Mar 2023
Raquel Costas · Humberto Carro · Andrés
Figuero · Enrique Peña · José Sande
Port downtime leads to economic losses and
reductions in safety levels. This problem is
generally assessed in terms of uni-variable…
thresholds, despite its multidimensional nature.
View
The aim of the present study is to develop a
downtime probability forecasting tool, based on
real problems at the Outer Port of Punta
Langosteira (Spain), and including infragravity
wave prediction. The combination of
... The conventional nonlinear marine
measurements from three pressure sensors and a
dynamics [8] utilized machine learning and
tide gauge, together with machine-learning
deep learning [9] . However, each ML and
techniques, made it possible to generate long
DL strategy has different benefits and
wave prognostication at different frequencies. A
applications. ...
fitting correlation of 0.95 and 0.9 and a root mean
squared error (RMSE) of 0.022 m and 0.012 m
... Outliers were removed using the IQR
were achieved for gravity and infragravity waves,
(interquartile range), which is the difference
respectively. A wave hindcast in the berthing
between the values in the top 75% and
areas, met-ocean forecast data, and information
bottom 25% of the quartile. Equations (8)
on 15 real operational problems between 2017
and (9) are expressions for calculating
and 2022, were all used to build a classification
outliers using IQR. ...
model for downtime probability estimation. The
proposed use of this tool addresses the problems
that arise when two consecutive sea states have
An Efficient Feature Augmentation and LSTM-
thresholds above 3.97%. This is the limit for
Based Method to Predict Maritime Traffic…
guaranteeing the safety of port operations and has
Conditions
aArticle Full-text
cost of just available interruptions of
0.6 unnecessary
operations
Feb 2023 per year. The methodology is easily
exportable to other facilities for an adequate
Eunkyu
assessment Lee ·of downtime
Junaid Khan
risks.· Woo-Ju Son ·
Kyungsup Kim
The recent emergence of futuristic ships is the
result of advances in information and
communication technology, big data, and artifici…
intelligence. They are generally autonomous,
View
which has the potential to significantly improve
safety and drastically reduce operating costs.
However, the commercialization of Maritime
Autonomous Surface Ships requires the
development of appropriate technologies,
... Vessel six degrees of freedom
including intelligent navigation systems, which
(after [65] ). ...
involves the identification of the current maritime
traffic conditions and the prediction of future
maritime traffic conditions. This study aims to
Wireless Link Selection Methods for Maritime
develop an algorithm that predicts future maritime
Communication Access Networks—A Deep…
traffic conditions using historical data, with the goal
Learning Approach
ofArticle
enhancing Full-text
the performance
available of autonomous
ships. Using several datasets, we trained and
Dec 2022 · SENSORS-BASEL
validated an artificial intelligence model using long
Michal Hoeft
short-term memory · and Krzysztof
evaluated Gierlowski
the ·
performance
Jozef Wozniak by considering several features such
as the maritime
In recent years, traffic
we have volume,
been maritime
witnessing traffic
a
congestion
growing interest fluctuation
in the range,
subjectfluctuation rate, etc.at
of communication
The
sea. algorithm
One of thewas able to identify
promising solutions features
to enable… for
predicting
widespread maritime
access traffic
to dataconditions.
transmission The obtained
View
results indicated that the highest performance of
capabilities in coastal waters is the possibility of
the model with
employing a valid loss
an on-shore of 0.0835
wireless accesswas
observed under
infrastructure. the scenario
However, suchwith all trends andis a
an infrastructure
predictions.
heterogeneous Theone,maximum
managed values for 3, 6, 12, and
by many
24 days and the
independent congestion
operators of the gate
and utilizing lines of
a number
... Основываясь
around на данных оa погоде и
differentthe analysis point
communication showed
technologies. significant
If a moving
зарегистрированных
effect on performance. The перемещениях
results of this study
sea vessel is to maintain a reliable communication
can судов
besuch с 2015
used по 2020 theг.,performance
Альварельос и
within ato improve
system, it needs to employ aofset of
др. [25]
situation предложили
recognition systems искусственные
in autonomous ships
network mechanisms dedicated for this purpose.
and нейронные
can be applied сетиtoиmaritime
дерево принятия
In this paper, we provide a shorttraffic condition
overview of such
решений
recognition по повышению
technology for градиента
coastal ships (англ.
that
requirements and overall characteristics of
Gradient Boosting
navigate Decision Tree, GBDT) to
maritime more complex
communication, sea
butroutes
our maincompared
focus is on
shipsдля прогнозирования
navigating the ocean. перемещений
the link selection procedure—an element of critical
судов. ...
importance for the process of changing the
device/system which the mobile vessel uses to
retain communication with on-shore networks. The
Machine learning models and methods for
paper presents the concept of employing deep
solving optimization and forecasting proble…
neural networks for the purpose of link selection.
of the work of seaports
The
Article
proposedFull-text
methods available
have been verified using
propagation models dedicated to realistically
Nov 2022
represent the environment of maritime
M. N. Lukashevich
communications and· M. Y. Kovalyov
compared to a number of
currently popular solutions.
Machine learning techniques The
haveresults
made of
evaluation indicate a and
significant advances significant
expanded gainapplication
in both
accuracy
sphere over of predictions
the past decade and reduction
to includeofproblem…
the
amount of test traffic
of port operations. which
This needs to
happened due betogenerated
the
View
for measurements.
growing amount of data available cargo ports. We
review the literature on models and methods of
machine learning and their application to
optimization of port operations. A special attention
is paid to the port planning and development a
... Although certain simplifications are also
wide range of topics in port operations, including
assumed, physical models provide valuable
port planning and development, their safety and
results often used as a complement to
security, water and land port operations.
numerical modeling to calibrate, validate,
and/or refine the numerical results
[9,20,25,30,31]. Finally, the third approach
is the analysis of the berthed ship system
response based on prototype measured
data obtained from monitoring campaigns
[32] [33] [34][35][36]. These measured data
can be considered the real behavior of the
system. ...

... Specifically, different cases of AI

techniques applied in harbor operability
assessment, both in terms of wave agitation
[38][39][40][41][42] and moored ship
motions [32, 33, 36], can be found in the
literature. Using inference models, relations
between variables have been established,
allowing conclusions to be deduced from an
initial multivariate database. ...

... For example, a linear regressionbased

model for the prediction of moored ships'
motions from different met-ocean and
vessel size input parameters is presented in
[32]. In [33] , a prediction model for moored
ships' responses based on gradient
boosting algorithms can be found. In both
cases, different instrumental data obtained
from several field campaigns developed in
the Outer Port of Punta Langosteira (A
Coruña, Spain) were used to fit/train the
inference models. ...

A Semi-Supervised Machine Learning Model to

Forecast Movements of Moored Vessels
Article Full-text available
Aug 2022
Eva Romano-Moreno · Antonio Tomás ·
Gabriel Diaz-Hernandez · Javier L. Lara ·
Javier García-Valdecasas
The good performance of the port activities in
terminals is mainly conditioned by the dynamic
response of the moored ship system at a berth. …
adequate definition of the highly multivariate
View
processes involved in the response of a moored
ship at a berth is crucial for an appropriate
characterization of port operability. The availability
of an efficient forecast system of the movements
of moored ships is essential for the planning,
... Therefore, reliable prediction of the
performance, and safety of the development of
moored vessel movements could increase
port operations. In this paper, an inference model
the safety level of the port. Accordingly,
to predict moored ship motions, based on a semi-
Alvarellos et al. (2021) proposed ANN and
supervised Machine Learning methodology, is
GBDT methods to predict movements using
presented. A comparison with different supervised
weather data and recorded movements of
and unsupervised Machine Learning techniques,
46 ships at Port of Punta Langosteria from
as well as with existing Deep Learning-based
2015 to 2020. ANN achieved the best
models for predicting moored ship motions, has
performance in terms of RMSE and the
been performed. The highest performance of the
coefficient of determination. ...
semi-supervised Machine Learning-based model
has been obtained. Additionally, the influence of
infragravity wave parameters introduced as
Applications of machine learning methods in
predictor variables in the model has been
port operations – A systematic literature…
analyzed and compared with the typical ocean
review
waves,
Article wind, and sea level as predictor variables.
The prediction model has been developed and
Apr 2022 · TRANSPORT RES E-LOG
validated with an available dataset of measured
dataSiyavash Filom
from field ·
campaignsAmir M Amiri
in the Outer· PortSaiedeh
of
Punta
N RazaviLangosteira (A Coruña, Spain).
Ports are pivotal nodes in supply chain and
transportation networks, in which most of the
existing data remain underutilized. Machine…
learning methods are versatile tools to utilize and
View
harness the hidden power of the data. Considering
ever-growing adoption of machine learning as a
data-driven decision-making tool, the port industry
is far behind other modes of transportation in this
transition. To fill the gap, we aimed to provide a
... The prediction methods of the ship
comprehensive systematic literature review on this
motion and attitude are mainly divided into
topic to analyze the previous research from
three categories: mathematical model,
different perspectives such as area of the
statistical model, and machine learning
application, type of application, machine learning
model [5] . Ghadimi and Tavakoli [6]
method, data, and location of the study. Results
proposed a mathematical model which
showed that the number of articles in the field has
used the asymmetric 2D + T theory to
been increasing annually, and the most prevalent
predict the attitude of the planning craft. ...
use case of machine learning methods is to
predict different port characteristics. However,
there are emerging prescriptive and autonomous
Ship Attitude Prediction Model Based on
use cases of machine learning methods in the
Cross-Parallel Algorithm Optimized Neural…
literature. Furthermore, research gaps and
Network
challenges
Article Full-text
are identified,
available
and future research
directions have been discussed from method-
Jan 2022
centric and application-centric points of view.
Yanshu Jiang · Mingqi Jia · Biao Zhang · Liwei
Deng
In recent years, with the development of modern
technology and industrialization, the shipbuilding
industry has become an essential field in a…
country. Offshore operations, such as helicopter
View
take-off and landing, and ship-to-ship cargo
replenishment, need an accurate prediction of ship
motion attitude, not only to improve efficiency but
also to protect study
crew members’ lives. However,
Experimental of multi-buoy-assisted
using theship
single modelat has limited influence on
moored motion open berth
prediction. Therefore, this paper proposed a
Article
Cross-Parallel optimization algorithm framework,
which made MAR
full use of the development ability of
Nov 2023 · STRUCT
the Harris Hawk Optimization algorithm (HHO) and
the Hongjie
searchingWen · Gancheng
ability Zhu ·
of the Sine-Cosine Bing Ren ·
Algorithm
Xuefeng
(SCA). InChang · Yongxue
this paper, we useWangRosenbrock and
Rastrigin functions for testing. The results show
View
that the Cross-Parallel optimization algorithm has
faster search speed and stronger optimization
capability. The optimization algorithm is used to
optimize the hyperparameters of Long Short-Term
Motion estimation and system identification of
Memory (LSTM) neural networks. It improves the
a moored buoy via physics-informed neural…
network’s training ability to predict the ship’s
network
Article The proposed method in this paper is
attitude.
compared
Sep 2023 with 9 models such as BP, LSTM, GRU,
· APPL OCEAN RES
BILSTM and TCN. It is tested with three degrees
He-Wen-Xuan
of freedom Li ·
under different Lin
seaLustates.
· Qianying
MAE Cao
and
RMSE are used as the evaluation indexes of this
View
paper. In the six sets of experimental results,
compared with the other nine models, the method
in this paper can reduce the MAE by up to 9.2%,
7.2%, 4.7%, 5.4%, 6.4%, and 6.8%, respectively. Show more
When using RMSE as the evaluation index, the
decrease was at most 10.1%, 8.7%, 5.6%, 7.1%,
7.5%, and 8.2%. The experimental results show
that the method in this paper has the highest
prediction accuracy.
Join ResearchGate to find the people and research
you need to help your work

25+ million members

160+ million publication pages
2.3+ billion citations

Join for free

Company Support

About us Help Center

News

Careers

Business solutions

Advertising

Recruiting

© 2008-2024 ResearchGate GmbH. All rights reserved.

Advertisement
Terms · Privacy · Copyright · Imprint