algorithms

Article
A Machine Learning Framework for Condition-Based
Maintenance of Marine Diesel Engines: A Case Study
Francesco Maione 1,† , Paolo Lino 1,† , Guido Maione 1,∗,† and Giuseppe Giannino 2,†

1 Department of Electrical and Information Engineering, Politecnico di Bari, 70125 Bari, Italy;
[email protected] (F.M.); [email protected] (P.L.)
2 Isotta Fraschini Motori S.p.A., 70132 Bari, Italy; [email protected]
* Correspondence: [email protected]
† These authors contributed equally to this work.

Abstract: The development of artificial intelligence-based tools is having a big impact on industry. In
this context, the maintenance operations of important assets and industrial resources are changing,
both from a theoretical and a practical perspective. Namely, conventional maintenance reacts to faults
and breakdowns as they occur or schedules the necessary inspections of systems and their parts
at fixed times by using statistics on component failures, but this can be improved by a predictive
maintenance based on the real component’s health status, which is inspected by appropriate sensors.
In this way, maintenance time and costs are saved. Improvements can be achieved even in the marine
industry, in which complex ship propulsion systems are produced for operation in many different
scenarios. In more detail, data-driven models, through machine learning (ML) algorithms, generate
the expected values of monitored variables for comparison with real measurements on the asset, for
a diagnosis based on the difference between expectations and observations. The first step towards
realization of predictive maintenance is choosing the ML algorithm. This selection is often not the
consequence of an in-depth analysis of the different algorithms available in the literature. For that
reason, here the authors propose a framework to support an initial implementation stage of predictive
maintenance based on a benchmarking of the most suitable ML algorithms. The comparison is tested
to predict failures of the oil circuit in a diesel marine engine as a case study. The algorithms are
Citation: Maione, F.; Lino, P.; Maione, compared by considering not only the mean squared error between the algorithm predictions and
G.; Giannino, G. A Machine Learning the data, but also the response time, which is a crucial variable for maintenance. The results clearly
Framework for Condition-Based indicate the framework well supports predictive maintenance and the prediction error and running
Maintenance of Marine Diesel
time are appropriate variables to choose the most suitable ML algorithm for prediction. Moreover,
Engines: A Case Study. Algorithms
the proposed framework can be used to test different algorithms, on the basis of more performance
2024, 17, 411. https://doi.org/
indexes, and to apply predictive maintenance to other engine components.
10.3390/a17090411

Academic Editors: Mateus Mendes Keywords: condition-based maintenance; predictive maintenance; failure detection; machine learning;
and Balduíno Mateus diesel engine simulation
Received: 10 July 2024
Revised: 4 September 2024
Accepted: 11 September 2024
Published: 14 September 2024 1. Introduction
1.1. Background
In recent years, new technologies have radically changed industry such that the
concept of Industry 4.0 has been coined, meaning the pervasive introduction of information
Copyright: © 2024 by the authors.
technologies that create networks in which machines communicate with each other [1].
Licensee MDPI, Basel, Switzerland.
Many sectors have been affected by this deep change, including the maritime sector. In fact,
This article is an open access article
the term Shipping 4.0 has been introduced next to Industry 4.0 to refer to “smart ships”,
distributed under the terms and
namely, fully interconnected and potentially autonomous vessels [2]. To make this scenario
conditions of the Creative Commons
Attribution (CC BY) license (https://
possible, it is important to design suitable devices able to communicate information to the
creativecommons.org/licenses/by/
outside world, that is, all the infrastructure correlated to the maritime world, not only the
4.0/). ships. For that reason, the term “smart ship” has been expanded to “smart ports” and

Algorithms 2024, 17, 411. https://doi.org/10.3390/a17090411 https://www.mdpi.com/journal/algorithms

Algorithms 2024, 17, 411 2 of 17

“smart transportation” [3]. However, the development of autonomous and smart plants
has opened new challenges. An example is given in the maritime sector by the necessity
to update the dock-to-dock operations [4]. In this context, a virtual counterpart of the
physical asset, namely, a so-called digital twin (DT), is often used for different purposes,
i.e., maintenance or design. In fact, implementing the physical laws in cyberspace gives
the possibility to create both a copy of the whole ship [5] or only a single component, such
as the main engine [6]. An important observation is that Industry 4.0 and Shipping 4.0 do
not forget that humans are the core of the change in paradigm. In fact, technicians can be
involved in new activities if equipped with new smart devices, such as augmented reality
instruments [7].

1.2. The Shift to Proactiveness in Maintenance

This revolution has influenced many fields and applications, among which mainte-
nance has radically changed. Maintenance is defined as “any activity carried out on an
asset in order to ensure that the asset continues to perform its intended functions, or to
repair the equipment” [8].
Many types of maintenance strategies have been proposed in the literature. Some
are comparable, some have similarities, some are clearly distinct. Moreover, different
authors may define the same strategy differently. In general, maintenance is classified as
reactive (also called passive or corrective) or (pro)active (which is sometimes indicated as
preventive) [9–13].
Reactive maintenance (RM) is applied once a complete failure occurs, after breakdown,
and requires fixing equipment problems and repairing faults as they arise; this is also
described in software and automation systems [14].
In more detail, industry can define it as breakdown maintenance if an asset is not
working anymore and needs to be repaired; as run-to-failure maintenance if an asset is
used until it breaks down or requires replacement or repair; as corrective maintenance if it
provides a temporary solution; or as emergency maintenance if a sudden failure occurs
in a critical asset which needs to be repaired as soon as possible, which makes this type
of maintenance expensive. The approach of RM is simple, with no costs for planning
and scheduling regular maintenance tasks. However, especially in the maritime industry,
long-term costs are high because of the emergency repairs and related expensive rush
charges for parts and because of the downtime, which is unpredictable. Moreover, RM
decreases the equipment lifespan, can introduce safety risks, and determines a poorer asset
utilization with reduced performance. So, RM is considered for non-essential equipment,
when the replacement cost is low, and when the equipment is close to its end of life.
Proactive maintenance prevents failures. The terms proactive and preventive are often
used as synonyms, but there are differences. Proactive maintenance aims to anticipate
failures or faults and stop them before they occur. It consists in periodic rigorous inspections
and condition monitoring, in collecting data from sensors, and in replacements at scheduled
intervals, regardless of whether a failure has occurred. Then, it considers data to determine
when maintenance should occur. Basically, proactive actions try to remove the root causes
of failure (wrong or degraded materials, unexpected operations, human errors, etc.) to
extend the equipment life and let it function at its best without unexpected breakdown.
Proactive maintenance can save costs by avoiding unnecessary maintenance (e.g., repairs
or replacements when nothing is wrong), so it can be convenient with respect to preventive
maintenance, which is defined below. However, it requires monitoring technology and
data analysis. Finally, if the equipment is proactively kept safe, then the risk of accidents is
reduced as well as the consequent cost of repairs or replacements.
Preventive maintenance (PvM) schedules audits, inspections, and replacements to
guarantee the continuous operation of the asset, with the purpose to prevent failures be-
fore their occurrence [15,16]. The aim is to reduce the chances of equipment failure and
unplanned downtime and to increase safety. Regular and routine inspections are scheduled
with periodicity on a time basis or on the basis of the equipment’s iterative utilization,
Algorithms 2024, 17, 411 3 of 17

according to a pre-established plan of tasks, while the equipment is still working to prevent
unexpected breakdowns. This maintenance approach has advantages (reduced down-
time, extended equipment life, saving costs due to emergency situations, improved safety,
increased efficiency, and energy saving) but also presents various drawbacks and prob-
lems (initial investment costs, unnecessary maintenance with waste of time and resources,
dedicated personnel, pause of equipment operation, complex scheduling of maintenance
tasks). In summary, it is somewhere between RM and predictive maintenance, which is the
latest trend based on emergent digital technologies (Internet of Things, cloud computing,
data analytics).
One particular form of prevention is what some researchers and practitioners call
planned maintenance or scheduled maintenance [17–21], which some authors consider the
most common onboard a ship [19].
It requires planning, documentation, and scheduling. The concept of planned main-
tenance is much used in industry, and is classically conceived to reduce the unexpected
downtime by making all resources available as much as possible, according to a pre-defined
strategy. Namely, regularly scheduled maintenance identifies and solves the issues that
could become major problems. This is based on statistical observations such that, based on
similar applications, maintenance is planned before the failure is likely to happen. Since the
scheduled maintenance can be planned in advance, the need to react to breakdowns is quite
uncommon. Moreover, the maintenance operations are faster and safer, because technicians
know the procedures, the best practices, the parts to fix, etc. In this way, industry may
optimize the running conditions and extend the lifespan of the equipment. However,
the main challenge of planned maintenance is the costs associated with labor, potential
downtime, parts, and the budgetary constraints.
Moreover, it can lead to audits and operations that are not really required, increas-
ing idle time and wasting money. Finally, note that the terms planned and preventive
maintenance are often used interchangeably, but refer to two different things. PvM is the
foundation for a planned maintenance strategy. Planned maintenance allows proactive
management of facilities by encompassing both RM and PvM such that reliance on RM
is reduced. It is often required for critical systems (e.g., regular inspection of a fire safety
system) and many times is a condition to attaining permissions to operate.
Until recently, maintenance operations, especially in shipping, were mainly performed
by RM and PvM [22–25].
Although many industrial manufacturers decide to use RM because maintenance is
perceived as a negative necessary cost and investments in PvM are not seen as profitable,
RM is today considered outdated. Namely, it was already found that an emergency repair
costs three times and takes ten times longer than a scheduled maintenance task [26], and
many industries are developing digital tools, automated systems, and prevention strategies
to be competitive [27–29]. At the same time, PvM is widely used in the specific field of
maritime applications, as recognized by experts in the field who discourage use of broken
equipment on ships, also for safety reasons, as well as repairing broken machinery [27].
In detail, maintenance on ships or on shore is performed in three ways: (1) Emergency
maintenance, only to repair equipment breakdowns, usually not at sea; (2) scheduled
maintenance, especially on board ships, with periodic inspections and replacements, but
highly expensive; (3) preventive maintenance, with various tasks and analysis of equipment
conditions. Moreover, experts are in favor of early detection of failures and defects, which
demands predictive maintenance. They also highlight that this new tool can be cost-
effective with respect to preventive maintenance and can help in deciding (predicting) the
next maintenance required for machines in service.

1.3. Leveraging Data to Predict Maintenance

In this context, a new kind of maintenance has been introduced, predictive main-
tenance (PdM) [30–32], which is perceived as a groundbreaking approach for maritime
operations, in which RM and PvM are no longer sufficient [25,28]. In this case, the aim
Algorithms 2024, 17, 411 4 of 17

is to predict failures by using sensors that are installed onboard. Some authors prefer
using the prognostic and health management (PHM) definition [23]. The medical term
“prognostic” highlights that it is not only necessary to provide information on the health
status of machines but also to predict incoming failures. Some authors also call PdM
condition-based maintenance (CBM) [32,33]. In shipping, one of the main problems of CBM
is to guarantee continuous data storage and communication between the ship and onshore
operators. To address this issue, a Hierarchical Data Format version 5 was proposed to store
a large amount of data [34]. Herein, the authors will use the acronym PdM to refer to both
PHM and CBM. The advantage of the PdM approach is to give information about when
components and machines actually need maintenance. In this way, the audit timetable
is not fixed in advance but depends on the current, real machinery health status. This
approach reduces the idle time and wasted money for unnecessary inspection. Moreover,
an intelligent and continuous parameter monitoring allows us to decrease sudden failures,
thereby increasing the safety for ships, transported goods, and passengers.
To be more specific, PdM can be performed in two different ways, depending on how
data are collected:
(a) Offline monitoring: Data are acquired when the machinery is not in service or at
regular time intervals using measurement systems that are not integrated with the
equipment. Examples are vibration analysis [35], oil analysis [36], and ultrasound
monitoring [37]. Many times, offline predictive maintenance demands industry
professionals to perform data collection manually. In [35], a comprehensive anal-
ysis of the importance of vibration analysis for diagnostic purposes of an internal
combustion engine is outlined. In [36], the authors find the best oil analysis interval
scheme for a marine engine to investigate the degradation trends from off-line oil
samples. In [37], once the engine is not in service, wave spectrum analysis through
ultrasonic signals is used as a condition-based technique to analyze the health status
of the engine. The main advantage of this technique is to provide very precise and
helpful information on the engine’s health status; nevertheless, the engine needs to
be out of service, thus limiting the applicability of the approach, because failures
can happen during working hours, e.g., when ships are sailing.
(b) Online monitoring: Data are collected during machinery operations [38]. Companies
of the Industry 4.0 movement tend to combine IoT sensors installed in the machines
with artificial intelligence, and collect data automatically, 24 h a day, every day.
Examples are given in [39,40], where the main approach consists in training the
predictive algorithm on previously acquired data, and then, applying it during the
operation of the monitored device. The main advantage of this method is that it
provides information on the engine’s health status continuously. In this way, it
is easier to catch failures earlier. However, issues related to interruption of data
acquisition and noise may have to be addressed.
It is important to be aware of the differences between the two methods and to use valid
reasoning to select the best for monitoring industrial assets. A well-motivated decision
determines good asset maintenance and has an impact on costs and profitability. In
offline monitoring, the collection of data requires a significant amount of time and expert
technicians as well as a measurement plan, and sometimes assets are difficult to access,
posing possible risks for the technicians. The method is simple but requires high expertise
and care.
In online monitoring, equipment sensors allow data to be collected in real time, maybe
stored on the cloud, with no time or effort from humans. The whole data collection
process works automatically and remotely, including data processing and analysis by a
platform based on artificial intelligence tools. The output is sent to managers who may have
information and insights on the equipment’s health status. So, equipment monitoring is
possible by remote networked digital devices. Another reason to prefer online monitoring is
because providing engine status information continuously is the best way to catch sudden
Algorithms 2024, 17, 411 5 of 17

failures in time, avoiding catastrophic accidents (see the Baltimore bridge collapse after
cargo-ship power loss in March 2024).
This paper contributes to online monitoring methods by a framework based on predic-
tive algorithms. This framework consists in an easy-to-implement procedure supporting
an initial-stage CBM. Namely, to perform online monitoring in an effective way, the first
necessary step is to choose the most suitable predictive algorithm. As highlighted in the
following sections, the motivation for the choice of the predictive algorithm is often omitted
or underestimated or is not the consequence of a comparative analysis. So, to the best of
the authors’ knowledge, the novelty of the present study is a framework for an initial and
quick benchmarking among three different machine learning (ML) algorithms that can be
easily developed and implemented. The analysis compares the three ML algorithms based
on their time response and predictive error, which, in the authors’ opinion, are the most
important variables to assess the algorithmic performance. Namely, the response time is
crucial in maritime applications because giving failure information on time is necessary
to guarantee the safety of the machinery, passengers, and crew. On the other hand, the
predictive error must be low to have a reliable prediction.
The paper is divided as follows. Section 2 gives an overview of the literature on the
predictive maintenance approach based on efficient and profitable use of data. Section 3
shows the proposed framework to select the best algorithm for CBM. Section 4 synthetically
describes the simulation model of the engine, in particular of the significant oil filter circuit,
used as a case study for applying the framework strategy. Section 5 shows and briefly
discusses the simulation results. Finally, Section 6 draws the conclusions.

2. Predictive Maintenance
2.1. Predictive Maintenance by Data-Driven Models
Once the monitoring strategy is chosen, the next step is to select the failure detec-
tion and prediction model. The available models are classified based on the diagnostic
strategy [41].
(a) Data-driven models: These typically apply machine learning (ML) or deep learning
(DL) algorithms. An example is given in [42], where the authors compared the
prediction of the ship speed loss due to fouling by two completely different methods:
the ISO 19030 standard [43,44] procedure and a data-driven digital twin. The results
clearly showed the data-driven model had better prediction capability than the
ISO 19030 standard. In general, the main advantage of data-driven models is a
better determination of the time between overhauls (i.e., the time between two
maintenance actions).
(b) Physics-based models: In this case, the outputs from the real asset are compared to
those given by a physical model that can be developed to represent the system under
maintenance. An example is given in [45], where the authors proposed an adaptive
extended Kalman filter for estimating the fault magnitude in an autonomous surface
vehicle. In this case, a digital twin was developed to implement all the mathematical
modeling equations which represent the autonomous vessel’s physics. The main
advantage of this approach is independence from the amount of collected data,
differently from the data-driven model, but a substantial limiting drawback is the
mathematical approximation, which can reduce the method’s reliability.
(c) Knowledge-based models: These try to mimic an expert’s reasoning; the main
advantage is that complex physical models are not needed. An example is given
in [36], where the authors analyzed the deterioration of a marine engine lubrica-
tion system using a dynamic Bayesian network (dBN). The model was realized
by using both the real data provided by the shipping company and the experts’
background knowledge. The latter was used to assess the cost of the risk model of
the dBN (condition monitoring cost, maintenance expenses, repair expenses and
failure expenses).
Algorithms 2024, 17, 411 6 of 17

Although all the aforementioned models are valid for diagnosis, the authors focus on
online monitoring by data-driven models.
Data-driven models are linked to the current technology development, especially in the
maritime sector regarding propulsive systems. In fact, the objectives that must be reached
by the 2030 Agenda and Paris Agreement 2050 determine a high interest for investigating
new fuels for marine propulsion, such as hydrogen fuel cells [46] and ammonia engines [47].
For that reason, physical models or experts’ knowledge are often not available. Instead,
data-driven models do not require the implementation of physical laws, which gives high
flexibility to the detection and prediction algorithms, such that they can be applied to
different engines without deep changes to the algorithmic structure.

2.2. A Bird’s-Eye View of Prediction Models

Data-driven models have been widely investigated in the literature and applied to
different diagnosis problems. They can be used as classifiers and as predictors. In both
cases, the aim is to answer three fundamental maintenance questions:
(1) Will there be a failure or fault?
(2) Where will the failure or fault be?
(3) When will the failure or fault occur?
Answering all the questions is necessary to apply the PdM in a good way. In fact, it is
possible to know which component to maintain and when the failure or fault is predicted to
occur. Focusing the attention on the maritime sector, anticipating a failure occurrence may
allow the ship owner to manage the maintenance and order the spare parts. The difference
between classifiers and predictors is the way in which they are applied.
A classifier is trained to compare new data with data from the different engine behav-
iors it was trained on. Then, it assigns a score to each comparison, and finally, outputs
the behavior with the highest score that matches the data best. Examples of PdM by
classification are given in [32,48,49].
On the contrary, predictors are trained to predict the expected values of engine vari-
ables. They are then compared with the outputs from the real asset. An example is given
in [50], where an artificial neural network (ANN) evaluates the expected values of parame-
ters that are identified as failure indicators. It is remarked that finding failure indicators
is decisive in diagnostic and prognostic models. In fact, reducing the computational cost
is important to realize an intelligent diagnostic tool that could be installed onboard. For
that reason, as concluded by [51], modeling and simulation can be used to overcome the
poor availability of faulty data. Synthetic data produced by simulation make it possible to
compare healthy with faulty behaviors, hence to find the most suitable failure indicators.
Other neural networks were implemented in [52,53]. Moreover, random forests can be
applied for maintenance purposes [49,54], and finally, some authors propose the application
of so-called ensemble neural networks [55,56].
In this innovative context, the main research gap is that frequently it is not well
explained how the algorithms used for diagnostic purposes are chosen, which may affect
the predictive maintenance success and cost, as also discussed in Section 1.3. To provide
a more robust motivation and prevent unreliable predictions, some authors propose a
benchmarking between algorithms, as shown in [22,31], but neither of the mentioned
two analysis techniques are definitively the best choice for predictive maintenance. For
that reason, the aim of this work is to propose an easy-to-use framework to select the
best algorithm for an initial stage of CBM implementation in marine industrial settings.
A procedure is developed to easily find the best algorithm for each component of the
system that is subject to faults and is fundamental for a marine engine’s operation. In
all cases, the procedure marks the best algorithm. The novelty of the current study is to
realize an effective comparison by the response time and the prediction error, and by a
formula evaluating a performance index that weights the two previous time and error
indexes. In the authors’ opinion, these two indexes are the most suitable ones to evaluate
Algorithms 2024, 17, 411 7 of 17

the performance of a predictive algorithm. It is remarked that, differently from [31], the
authors also consider the time variable, which is crucial for maintenance purposes.
Finally, once all the components have been analyzed, the algorithm which is marked
the most number of times is chosen as the predictive algorithm to be used in the online
monitoring system.

3. Proposed Framework
In this section, we describe the proposed strategy for data-driven predictive main-
tenance. Industrial machinery has different numbers and types of sensors installed on
it. The aim of the sensors is to monitor the health status of the main components contin-
uously. These components are those more sensitive to failure or those necessary for the
good operation of the entire machinery. In the case of a marine diesel engine, we take
the oil circuit as an example, since filtering the impurities is important. Namely, both a
non-optimal filtering operation and excessive clogging can cause an unhealthy engine
status. The consequence of this is the reduction of the engine life and, in catastrophic
situations, it can lead to dangerous conditions for the ship crew and passengers. So, it
is extremely important for the engine status to monitor the oil filter, and the associated
pressure drop must be measured by sensors to detect clogging. Similar considerations can
be made for other engine components.
Assuming that m is the number of sensors in the machinery, let us indicate as
[ x1 , x2 , ..., xm ] all the monitored variables. Then, [u1 , u2 , ..., ur ] are the variables chosen
as inputs to the considered ML algorithms, which are trained to provide the predictions
[ x̂1 , x̂2 , ..., x̂m ] by processing the employed inputs. The predictions give the expected values
in the case of a healthy engine. They are next compared to the real values from the asset,
thus allowing the technicians to take decisions regarding the maintenance plan.
The next step is to standardize the x j variables, for j = 1, ..., m, by the Z-score method
to yield xz j , with j = 1, ..., m, as shown below:

xz j = ( x j − µ j )/σj (1)

where µ j is the mean and σj is the standard deviation.

Now, we may apply k different ML algorithms to the m variables and compute the
mean squared error (MSE), say msei,j for i = 1, ..., k and j = 1, ..., m, between the predictions
and the real experimental values.
The MSE is given by
1 m
m j∑
MSE = ( xz j − x̂z j )2 (2)
=1

where xz j is the real standardized value and x̂z j the predicted standardized value. For each
algorithm, the necessary time t pr for obtaining the predicted value is also measured. In this
way, a performance index J = f ( MSE, t pr ) is evaluated: the higher J is, the better the algo-
rithm’s performance. Then, for each variable xz j , the algorithm number i j , 1 ≤ i j ≤ k, with
the highest J, i.e., Ji j ,j , is chosen. Finally, algorithm number i∗ , which presents the highest
J for the largest number of times, is selected for the overall prediction. The procedure is
summarized in Figure 1.

Figure 1. Proposed framework for choosing the most suitable predictive algorithm.

Figure 1 shows the following: the inputs are the standardized measurements from
sensors; J is computed for each algorithm prediction and for each sensor; the outputs
provide the lowest J for each sensor. The rationale is to select the algorithm which provides
Algorithms 2024, 17, 411 8 of 17

the highest J for the highest number of sensors. This optimal algorithm is used subsequently
for predictive maintenance with all sensors.
The following algorithms were considered for the benchmark after a careful analysis
of the literature:
(1) An artificial neural network (ANN);
(2) An ensemble neural network (ENN), which provides an arithmetical mean of the
outputs from the single neural networks;
(3) An ENN providing the weighted mean of outputs from single neural networks;
(4) A random forest (RF).

3.1. Artificial Neural Network and Ensemble Neural Network

An ANN is an ML algorithm that consists of different interconnected hidden layers,
where neurons process the data to produce an output (Figure 2).

Figure 2. Structure of artificial neural networks.

The inputs to the ANN are represented by numbers, so in the current application
the sensor measurements can be used as inputs to the algorithm. After that, the values
are multiplied by the weights in the hidden layers, which are initialized randomly. The
multiplication results are added together to produce the neuron output. Finally, once the
information arrives at the final layer, the ANN outputs are produced. In the present study,
the outputs are the expected sensor measurements associated with the inputs. This basic
kind of information propagation is called forward propagation. During the training phase,
there is also a second kind of propagation, backward propagation (not shown in Figure 2).
In this case, the error is propagated backwards (from the output to the input) to update the
weight values.
The output can be a regression or a classification. More details can be found in [57].
The algorithm is described by (3)–(7):
!
n
y= f ∑ wi x i + b (3)
i =1

2
f (x) = −1 (4)
1 + e−2x
!
n
hj = f ∑ wij xi + bj (5)
i =1
!
m
yk = f ∑ w jk h j + bk (6)
j =1

∆w jk = ηδk h j (7)
where (3) allows us to compute the output of the neural unit, xi is an input, wi is a weight, b
is the bias, and f is the activation function. In more detail, in (5), wij is the weight associated
with the i-th neuron input xi and the j-th neuron output h j ; b j is the bias of the j-th neuron.
Algorithms 2024, 17, 411 9 of 17

In (6), bk is the bias of the k-th output; w jk is the weight associated with the j-th hidden
layer input and the k-th output. The tanh function in (4) is the activation function used
in the present study and introduces nonlinearity in the system. The computations in (5)
and (6) represent the feedforward operations for the hidden layer and the output layer,
respectively. They describe the propagation of data to compute the output. Here, h j is the
neuron output of the j-th hidden layer; yk is the k-th output. Equation (7) describes the
backpropagation, namely, the error computation to update the weights: η is the learning
rate and δk the error between the network output and real data.
An ENN represents an extension of the previous neural architecture. The ENN output
is obtained by combining the outputs of several ANNs. The authors propose two different
ENNs: the first one generates an output by arithmetically averaging the single neural
network outputs; the second one by computing the output as the weighted mean of the
single neural network outputs. The weights are assigned on the basis of the error made by
each ANN. The ANN with the smallest error has the biggest weight.

3.2. Random Forest

We develop an RF with the same regression purpose. An RF consists of a combination
of decision trees [49].
A single decision tree can be used as a predictive algorithm for classification or
regression. In its structure, the first node (first rectangular box in Figure 3) is called the
root and takes the first action or decision; in the same way, each subsequent internal
node (rectangular box) represents another action or decision; an arc between two nodes
represents the consequent decision flow; finally, a leaf is the node where the final decision
is taken. Each decision is taken by considering a probability distribution. The final result
can be a classification (classification tree) or a regression (regression tree).
The RF is introduced to improve the performance of a single decision tree. To realize
it, the first step is to obtain bootstrap aggregating (bagging) datasets from an initial dataset:
they are obtained by random sampling with replacement. This technique consists of taking
elements from the original dataset and using them for training one of the decision trees
which makes the forest. These elements are then put back in the original dataset. In this
way, they can be used for different trees. For each sampling and replacement operation, a
decision tree is trained. Then, during the learning phase, a second bagging is performed to
find the features (i.e., specific characteristics or variables) that allow the node split: the aim
is to obtain the features that can allow a very reliable prediction to obtain the correct output.
The final output stems from averaging the outputs of the trees or selecting the output from
the highest number of trees.
For example, Figure 3 shows an RF composed of three decision trees: the yellow circle
is the RF input; the yellow rectangle is the root node of the decision trees. Since the input
is the same for all trees, the first node has the same color (yellow). Then, based on the
decision taken by each tree, the internal nodes and the leaves have different colors. Two
out of the three displayed trees produce the same output, the red one, which is chosen as
the global output with the same color (red circle).
The base of the decision process of the single decision tree is the Gini index, given
by (8) below, namely, the evaluation of the probability that a sample belongs to a class.
C
G (t) = 1 − ∑ p2i (8)
i =1

where C is the total number of classes and pi is the fraction of elements belonging to class i
in a specific node. Moreover, the entropy, namely, the “measurement” of the disorder in the
data, is evaluated by
C
H (t) = − ∑ pi log( pi ) (9)
i =1
Algorithms 2024, 17, 411 10 of 17

After every node split, the entropy decreases to have a more homogeneous dataset.
Finally, for a regression problem, with B the total number of trees that compose the
forest, the output is evaluated by
B
1
ŷ =
B ∑ ŷb (10)
b =1

where ŷb is the output of a decision tree in the forest.

Figure 3. Structure of a random forest.

4. Case Study
An engine model was developed using the software GT-Suite (v2024) ® [58]. The
GT-Suite Integrated Multi-Physics Systems simulation software is a package allowing us to
build a virtual prototype system. In this way, we may describe physical phenomena with
great precision and details and accurately simulate the system dynamics.
The GT-Suite® software implements the conservation laws of mass, energy, and mo-
mentum by (11)–(13) to predict the engine performance [51]:

∂ρ ∂v
+ =0 (11)
∂t ∂x

∂ρe ∂ρvh
+ =0 (12)
∂t ∂x

∂ρv ∂ρx ∂p
+v + =0 (13)
∂t ∂x ∂x
where ρ is the fluid density, v the fluid velocity, p the fluid pressure, x the longitudinal
dimension of the flow, h the enthalpy, and e the internal energy. The previous mathematical
modeling equations are taken into account in each component of the engine, such as the
turbine and compressor, air-cooling system, cylinders, and valves. The validity of the
results from this software is testified by the amount of technical publications available [59].
The developed model regards a typical large-sized diesel engine with three different
supercharged systems and sixteen cylinders.
We chose the oil filter as the first element to which to apply the ML algorithms. Figure 4
shows the simplified circuit with the employed sensors: PT is a pressure sensor and TT a
temperature sensor.
Algorithms 2024, 17, 411 11 of 17

Figure 4. Oil filter circuit.

The dashed signal in Figure 4 changes the volumetric flow at the pump inlet. Then, on
the basis of the achieved pressure, measured by PT1 , the pump increases or decreases its
rotational speed, affecting the pressure drop PTin − PTou . The brake-specific fuel consump-
tion may increase because the pump is engaged on the main engine, so a higher energy
is required to compensate a higher pressure drop. To conclude, higher filter clogging
determines a higher consumption and worse engine operation.
Since the pressure drop is a quadratic function of the volumetric flow rate, both
nominal and excessive clogging are simulated by multiplying the function by a coefficient
a f ∈ [1, 5], as shown in Figure 5 and explained in [51].

Figure 5. Simulation of excessive filter clogging.

The simulation by GT-Suite® highlighted that the maximum pressure drop for a f = 4.0
is equal to 1.94 bar. Since the sensor warning starts for a pressure drop equal to 2.0 bar,
the last a f value for which the clogging is considered nominal is a f = 3.7, for which
the maximum pressure drop is 1.7 bar. In this way, we keep a certain distance from the
condition of excessive clogging.

5. Simulation Results
The developed ANN has the characteristics reported in Table 1.
Algorithms 2024, 17, 411 12 of 17

Table 1. Specifications of the artificial neural network.

Inputs PT1 /TT1 and pump rotational speed

Outputs Oil filter pressure drop
No. of hidden layers 2
No. of neurons 24 (1st hidden layer) and 12 (2nd hidden layer)
Training algorithm Levenberg–Marquardt

The results shown in Figures 6 and 7 are obtained by using the pressure given by PT1
(see Figure 4) and the pump rotational speed as inputs. In the figures, the horizontal axis
shows the values of the pressures PTin and PTou predicted by the ANN algorithm; the
vertical axis shows the values of PTin and PTou that were obtained by the simulation.
It can be seen that the trained ANN is able to predict the expected value of the
pressure. Equivalent results were obtained for other combinations of inputs (e.g., using the
temperature given by TT1 ).

Figure 6. Results from the artificial neural network for PTin .

Figure 7. Results from the artificial neural network for PTou .

Since the outputs are the pressures by PTin and PTou , two different random forests
were trained because a single one gives one output only. The parameters were tuned in
MATLAB R2023b ® by using the maximum number of splits in the tree (MaxNumSplit)
and the minimum number of observations required to create a node (MinLeafSize). The
different combinations of parameters are compared based on the MSE, and then, the best
one is chosen. Table 2 reports the specifications for the RF making the PTou prediction, and
Figure 8 shows the results.
Algorithms 2024, 17, 411 13 of 17

Table 2. Specifications of the random forest for PTou .

Inputs PT1 and pump rotational speed

Output PTou
Number of trees 91
MinLeafSize 1
MaxNumSplit 92

Figure 8. Results from the random forest.

The simulation was performed on a computer with an Intel(R) Core(TM) i7-1065G7

CPU processor and 8.00 GB of RAM. Although the results shown in Figures 6–8 may seem
similar, tuning the ANN parameters required less time and effort than the RF. Moreover,
one ANN can provide two different outputs, unlike an RF. For this reason, implementing
two different RFs could require a higher computational cost. Finally, the MSE is lower with
the ANN. See Table 3 for a comparison.

Table 3. Comparison between ANN and RF.

Performance ANN RF
MSE 6.2 × 10−5 3.03 × 10−3 (PTin ) and 7.2 × 10−5 (PTou )
Computation time 12 s 105 s

After comparing the ANN and RF, two different ENNs were developed. A first one
was obtained by training three different ANNs and the final output was the arithmetical
mean of the three ANNs’ outputs. A second ENN was obtained by training three different
ANNs and the final output was calculated as the weighted mean. The weights were
assigned based on the MSE of each ANN during the training, namely, the weight 1.0 was
assigned to the ANN with the lowest MSE and 0.70 was assigned to the other ANNs.
Table 4 shows the characteristics of the ENNs.

Table 4. Specifications of the ensemble neural networks.

Inputs PT1 and pump rotational speed

Outputs Oil filter pressure drop
No. of Neural Networks 3
Output Logic Arithmetic mean and weighted mean
Weight Values 1.0, 0.7, 0.7

The results showed that:

• A well-trained ANN is a good predictor thanks to its simplicity; in fact, it is the best
algorithm for the response time but it shows a higher error than an ENN;
• An RF has the highest error and highest computation time;
Algorithms 2024, 17, 411 14 of 17

• A not well-trained ENN gives better results than a not well-trained ANN;
• An ENN shows a smaller error for a higher number of observations than ANN,
even with a lower number of training epochs (i.e., comparing an ENN trained on
25 epochs and an ANN trained on 50 epochs, the first has a smaller error for 65% of
the observations).
Table 5 shows the performance by the two ENNs and Figure 9 shows the simulation
results from the weighted ENN.

Table 5. Results from the ensemble neural networks.

Performance Arith. Mean ENN Weight. Mean ENN

MSE 2.32 × 10−6 2.93 × 10−6
Computation time 46 s 24 s

Figure 9. Results from weighted ENN on input pressure sensor.

The main conclusion arising from the comparison between the ANN and ENN is that
the higher computational cost of the ENN is motivated by easy tuning and higher accuracy.
This is because multiple ANNs, that is, an ENN, allow us to overcome the weakness of
the individual regressors. For this reason, ENNs are preferred to monitor components
or evaluate physical quantities that are crucial for the engine, when faults can impair
the operation.
Finally, for each ML algorithm, an aggregate and simple performance index J can
combine the values of the MSE and computation time T using (14) below:

MSEbest /MSE + Tbest /T

J= (14)
2
where MSEbest and Tbest are the best values obtained by the three algorithms. The following
results are obtained (higher values of J indicate better performance): J = 0.52 (ANN),
J = 0.07 (RF), J = 0.63 (ENN). This gives a compact, easy-to-interpret indication of the best
ML algorithm for PdM (or CBM) of the oil filter.
The shown simulation results highlighted that the ENN is the best algorithm for
monitoring the oil filter and predicting its sensor measurements for online maintenance.
The proposed framework for benchmarking can be applied to all the most important parts
of the monitored machinery. In this way, by comparison, it is possible to choose the best
algorithm overall. The aim is to increase the safety of the marine engine by ensuring that
the predictive algorithm is chosen accurately and after a comparison with other performing
ones. As previously remarked, the time and the error were chosen as key indicators for the
benchmarking due to their importance. The first indicator is for ensuring that operators
receive information about the engine health status in a timely manner; the second is for
reliable predictions. In future and different applications, new type of algorithms and new
key performance indicators can be included in the framework.
Algorithms 2024, 17, 411 15 of 17

6. Conclusions
Maintenance of marine diesel engines, as with many other industrial processes, is
being affected by the revolution brought about by artificial intelligence. So, a thorough
change in its fundamental principles and its application is necessary. This paper follows the
path highlighted by ML algorithms but contributes to the early-stage engine design, when
the choice of the diagnostic algorithm is decisive for an effective maintenance procedure. To
the best of the authors’ knowledge, the motivation behind the preference of one predictive
algorithm over another is missing in the literature. To overcome this limitation, the authors
proposed a framework to follow in the initial stage of CBM implementation: different
predictive algorithms were considered and compared based on the time response and the
prediction error. The best one was evaluated based on a cost index J weighting the response
time and the MSE as key performance indicators. Although the oil filter was chosen as
case study due to its importance, the framework can be easily extended and applied to
other plant components.
To summarize, this study is helpful to increase the reliability and safety of engine
operation. The best predictive algorithm is selected by a comparative analysis among
different algorithms. This result is crucial to prevent a plant working in faulty conditions
and can avoid a high environmental impact: the engine will not operate under faulty
conditions, thus reducing the polluting emissions by 3% [60].

Author Contributions: Conceptualization, F.M. and G.M.; methodology, F.M., P.L. and G.M.; software,
F.M. and G.G.; validation, F.M., P.L. and G.M.; formal analysis, F.M., P.L. and G.M.; investigation,
F.M., G.M. and G.G.; resources, F.M. and G.G.; data curation, F.M. and G.G.; writing, F.M. and G.M.;
visualization, F.M.; supervision, G.M.; project administration, G.G.; funding acquisition, G.M. and
G.G. All authors have read and agreed to the published version of the manuscript.
Funding: This research was funded by EUROPEAN UNION-NEXTGENERATIONEU, CUP:B19J2300
0680004.
Data Availability Statement: The datasets presented in this article are not readily available due to a
confidential agreement with Isotta Fraschini Motori S.p.A.
Acknowledgments: Activities described in this paper have been developed within Fincantieri project
“Wave 2 the Future” (W2F) funded by the European Union—NextGenerationEU. The W2F project is
part of IPCEI Hy2Tech.
Conflicts of Interest: The authors declare no conflicts of interest. The funders had no role in the design
of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or
in the decision to publish the results.

References
1. Elijah, O.; Ling, P.A.; Rahim, S.K.A.; Geok, T.K.; Arsad, A.; Kadir, E.A.; Abdurrahman, M.; Junin, R.; Agi, A.; Abdulfatah, A.M.Y.
A Survey on Industry 4.0 for the Oil and Gas Industry: Upstream Sector. IEEE Access 2021, 9, 144438–144468. [CrossRef]
2. Angelopoulos, A.; Giannopoulos, A.; Nomikos, N.; Kalafatelis, A.; Hatziefremidis, A.; Trakadas, P. Federated Learning-Aided
Prognostics in the Shipping 4.0: Principles, Workflow, and Use Cases. IEEE Access 2024, 12, 6437–6454. [CrossRef]
3. Aslam, S.; Michaelides, M.P.; Herodotou, H. Internet of Ships: A Survey on Architectures, Emerging Applications, and Challenges.
IEEE Internet Things J. 2020, 7, 9714–9727. [CrossRef]
4. Lexau, S.J.N.; Breivik, M.; Lekkas, A.M. Automated Docking for Marine Surface–A survey. IEEE Access 2023, 11, 132324–132367.
[CrossRef]
5. Hasan, A.; Widyotriatmo, A.; Fagerhaug, E.; Osen, O. Predictive Digital Twins for Autonomous Ships. In Proceedings of the 2023
IEEE Conference on Control Technology and Applications (CCTA), Bridgetown, Barbados, 16–18 August 2023; pp. 1128–1133.
[CrossRef]
6. Bondarenko, O.; Fukuda, T. Development of a Diesel Engine’s Digital Twin for Predicting Propulsion System Dynamics. Energy
2020, 196, 117126. [CrossRef]
7. Laera, F.; Manghisi, V.M.; Evangelista, A.; Uva, A.E.; Foglia, M.M.; Fiorentino, M. Evaluating an Augmented Reality Interface for
Sailing Navigation: A Comparative Study with a Immersive Virtual Reality Simulator. Virtual Real. 2023, 27, 929–940. [CrossRef]
8. Mushiri, T.; Hungwe, R.; Mbohwa, C. An Artificial Intelligence Based Model for Implementation in the Petroleum Storage
Industry to Optimize Maintenance. In Proceedings of the 2017 IEEE International Conference on Industrial Engineering and
Engineering Management (IEEM), Singapore, 10–13 December 2017; pp. 1485–1489. [CrossRef]
Algorithms 2024, 17, 411 16 of 17

9. Gackowiec, P. General Overview of Maintenance Strategies - Concepts and Approaches. Multidiscip. Asp. Prod. Eng. 2019, 2,
126–139. [CrossRef]
10. Sambrekar, A.A.; Vishnu, C.R.; Sridharan, R. Maintenance Strategies for Realizing Industry 4.0: An overview. In Emerging Trends
in Engineering, Science and Technology for Society, Energy and Environment—Proceedings of the International Conference in Emerging
Trends in Engineering, Science and Technology (ICETEST 2018), Thrissur, Kerala, India, 18–20 January 2018; Vanchipura, R., Jiji, K.S.,
Eds.; CRC Press: London, UK, 2018; pp. 341–348. [CrossRef]
11. Shafiee, M. Maintenance Strategy Selection Problem: An MCDM Overview. J. Qual. Maint. Eng. 2015, 21, 378–402. [CrossRef]
12. Velmurugan, R.S.; Dhingra, T. Maintenance Strategy Selection and Its Impact in Maintenance Function: A Conceptual Framework.
Int. J. Oper. Prod. Manag. 2015, 35, 1622–1661. [CrossRef]
13. Pricopie, A.; Frangu, L.; Vilanova, R.; Caraman, S. A Preventive Maintenance Strategy For An Actuator Using Markov Models.
IFAC-PapersOnLine 2020, 53, 784–789. [CrossRef]
14. Reactive Maintenance. The Complete Guide to Reactive Maintenance—Fiix. Available online: https://fiixsoftware.com/
maintenance-strategies/reactive-maintenance/#:~:text=Simply%20put%2C%20reactive%20maintenance%2C%20also,’t%20
fix%20it%22%20approach (accessed on 24 August 2024).
15. Burrell, R. Cost-Benefit Analysis of Preventive Maintenance vs. Reactive Maintenance. 19 December 2023. Available online:
https://www.clickmaint.com/blog/preventive-maintenance-vs-reactive-maintenance-analysis (accessed on 24 August 2024).
16. Cicek, K.; Turan, H.H.; Topcu, I.Y.; Searslan, N.M. Risk-Based Preventive Maintenance Planning Using Failure Mode and Effect
Analysis (FMEA) for Marine Engine Systems. In Proceedings of the 2010 Second International Conference on Engineering System
Management and Applications, Sharjah, United Arab Emirates, 30 March–1 April 2010; pp. 1–6
17. Lind, H.; Muyingo, H. Building Maintenance Strategies: Planning under Uncertainty. Prop. Manag. 2012, 30, 14–28. [CrossRef]
18. Liang, M.; Chen, M. Monitoring the Performance of a Ship’s Main Engine based on Big Data Technology. Pol. Marit. Res. 2022, 29,
128–140. [CrossRef]
19. Kandemir, C.; Celik, M. A Human Reliability Assessment of Marine Auxiliary Machinery Maintenance Operations under Ship
PMS and Maintenance 4.0 Concepts. Cogn. Technol. Work 2020, 22, 473–487. [CrossRef]
20. Geurtsena, M.; Diddena, J.B.H.C.; Adana, J.; Atana, Z.; Adan, I. Production, Maintenance and Resource Scheduling: A Review.
Eur. J. Oper. Res. 2023, 305, 501–529. [CrossRef]
21. DNV. Planned Maintenance System (PMS). ShipManager Technical. 2024. Available online: https://www.dnv.com/services/
planned-maintenance-system-for-technical-ship-management-shipmanager-technical-1509/ (accessed on 24 August 2024).
22. Ellefsen, A.L.; Bjørlykhaug, E.; Æsøy, V.; Zhang, H. An Unsupervised Reconstruction-Based Fault Detection Algorithm for
Maritime Components. IEEE Access 2019, 7, 16101–16109. [CrossRef]
23. Han, P.; Ellefsen, A.L.; Li, G.; Holmeset, F.T.; Zhang, H. Fault Detection with LSTM-Based Variational Autoencoder for Maritime
Component. IEEE Sens. J. 2021, 21, 21903–21912. [CrossRef]
24. Han, P.; Ellefsen, A.L.; Li, G.; Æsøy, V.; Zhang, H. Fault Prognostics Using LSTM Networks: Application to Marine Diesel Engine.
IEEE Sens. J. 2021, 21, 25986–25994. [CrossRef]
25. Zhu, T.; Ran, Y.; Zhou, X.; Wen, Y. A Survey of Predictive Maintenance: Systems, Purposes and Approaches. arXiv 2024,
arXiv:1912.07383v2.
26. Chan, F.T.S.; Lau, H.C.W.; Ip, R.W.L.; Chan, H.K.; Kong, S. Implementation of Total Productive Maintenance: A Case Study. Int. J.
Prod. Econ. 2005, 95, 71–94. [CrossRef]
27. Marine Digital. Predictive Maintenance for Marine Vessels. Available online: https://marine-digital.com/article_predictive_
maintenance_for_marine_vessels (accessed on 24 August 2024).
28. Buzinkay, M. Leveraging Predictive Maintenance: Transforming Maritime Operations. 21 September 2023. Available online:
https://www.identecsolutions.com/news/leveraging-predictive-maintenance-transforming-maritime-operations (accessed on
24 August 2024).
29. Property Meld. 3 Types of Maintenance Strategies: What Type is Yours? 2024. Available online: https://propertymeld.com/blog/
3-types-of-maintenance-strategies/ (accessed on 24 August 2024).
30. Selcuk, S. Predictive Maintenance, Its Implementation and Latest Trends. Proc. Inst. Mech. Eng. Part B J. Eng. Manuf. 2017, 231,
1670–1679. [CrossRef]
31. Einabati, B.; Baboli, A.; Ebrahimi, M. Dynamic Predictive Maintenance in industry 4.0 based on real time information: Case study
in automotive industries. IFAC PapersOnline 2019, 52, 1069–1074. [CrossRef]
32. Susto, G.A.; Schirru, A.; Pampuri, S.; McLoone, S.; Beghi, A. Machine Learning for Predictive Maintenance: A Multiple Classifier
Approach. IEEE Trans. Ind. Inform. 2015, 11, 812–820. [CrossRef]
33. Hashemian, H.M.; Bean, C.W. State-of-Art Predictive Maintenance Techniques. IEEE Trans. Instrum. Meas. 2011, 60, 3480–3492.
[CrossRef]
34. Giannino, G.; Tricarico, M.; Orlando, A. Employing HD5F File Format for Marine Engine System Storage. In Proceedings of the
Twelfth International Conference on Data Analytics, Porto, Portugal, 25–30 September 2023; pp. 13–20.
35. Nithin, S.K.; Hemanth, K.; Shamanth, V. A Review on Combustion and Vibration Condition Monitoring of IC Engine. Mater.
Today Proc. 2021, 2021, 65–70. [CrossRef]
36. Ventikos, N.P.; Sotiralis, P.; Annetis, E. A Combined Risk-Based and Condition Monitoring Approach: Developing a Dynamic
Model for the Case of Marine Engine Lubrication. Transp. Saf. Environ. 2022, 4, tdac020. [CrossRef]
Algorithms 2024, 17, 411 17 of 17

37. Awang, M.N.; Zali, Z.; Mohd Noor, N.A.; Nursal, R.S. Main Propulsion Marine Diesel Engine Condition Based Maintenance
Monitoring Using Ultrasound Signal. In Advancement in Emerging Technologies and Engineering Applications; Lecture Notes in
Mechanical Engineering; Saw, C., Woo, T., Karam Singh, S., Asmara Bin Salim, D., Eds.; Springer: Singapore, 2020; pp. 175–187.
[CrossRef]
38. Cachada, A.; Barbosa, J.; Leitño, P.; Gcraldcs, C.A.S.; Deusdado, L.; Costa, J.; Teixeira, C.; Teixeira, J.; Moreira, A.H.J.; Moreira,
P.M.; et al. Maintenance 4.0: Intelligent and Predictive Maintenance System Architecture. In Proceedings of the 2018 IEEE
23rd International Conference on Emerging Technologies and Factory Automation (ETFA), Turin, Italy, 4–7 September 2018;
pp. 139–146. [CrossRef]
39. Zhou, W.; Hu, L.; Yu, Y. Development of Online Monitoring System for Cylinder Pressure of Marine Low-Speed Engine Based
on Virtual Instrument. In Proceedings of the 2023 IEEE 6th Information Technology, Networking, Electronic and Automation
Control Conference (ITNEC), Chongqing, China, 14–26 February 2023; pp. 1534–1539. [CrossRef]
40. Schoen, R.R.; Lin, B.K.; Habetler, T.G.; Schlag, J.H.; Farag, S. An Unsupervised, On-line System for Induction Motor Fault
Detection Using Stator Current Monitoring. IEEE Trans. Ind. Appl. 1995, 31, 1280–1286. [CrossRef]
41. Cheliotis, M.; Lazakis, I.; Cheliotis, A. Bayesan and Machine Learning-Based Fault Detection and Diagnostics for Marine
Applications. Ships Offshore Struct. 2022, 17, 2686–2698. [CrossRef]
42. Corradu, A.; Oneto, L.; Baldi, F.; Cipollini, F.; Atlar, M.; Savio, S. Data-Driven Ship Digital Twin for Estimating the Speed Loss
Caused by the Marine Fouling. Ocean. Eng. 2019, 186, 106063. [CrossRef]
43. ISO 19030-1; Ships and Marine Technology Measurement of Changes in Hull and Propeller Performance—Part 1: General
Principles. International Organization for Standardization: Geneva, Switzerland, 2016.
44. ISO 19030-3; Ships and Marine Technology Measurement of Changes in Hull and Propeller Performance—Part 3: Alternative
Methods. International Organization for Standardization: Geneva, Switzerland, 2016.
45. Bhagavathi, R.; Kufoalor, D.K.M.; Hasan, A. Digital Twin-Driven Fault Diagnosis for Autonomous Surface Vehicles. IEEE Access
2023, 11, 41096–41104. [CrossRef]
46. Haxhiu, A.; Abdelhakim, A.; Kanerva, S.; Bogen, J. Electric Power Integration Schemes of the Hybrid Fuel Cells and Batteries-Fed
Marine Vessels–An Overview. IEEE Trans. Transp. Electrif. 2022, 8, 1885–1905. [CrossRef]
47. Gallucci, M. The Ammonia Solution: Ammonia Engines and Fuel Cells in Cargo Ships Could Slash Their Carbon Emissions. IEEE
Spectrum 2021, 58, 44–50. [CrossRef]
48. Chengtao, C.; Chuanbin, Z.; Gang, L. A Novel Fault Diagnosis Approach Combining SVM with Association Rule Mining for Ship
Diesel Engine. In Proceedings of the 2016 IEEE International Conference on Information and Automation (ICIA), Ningbo, China,
1–3 August 2016; pp. 130–135. [CrossRef]
49. Bakdi, A.; Kristensen, N.B.; Stakkeland, M. Multiple Istance Learning with Random Forest for Event Logs Analysis and Predictive
Maintenance in Ship ELectric Propulsion system. IEEE Trans. Ind. Inform. 2022, 18, 7718–7728. [CrossRef]
50. Ceglie, M.; Ferrante, F.; Giannino, G. Employing Artificial Neural Network for Process Signal Estimation in the Monitoring of
Smart Shipboard Diesel Engine Systems. In Proceedings of the 13th Symposium on High Speed Marine Vehicles, Naples, Italy,
23–25 October 2023.
51. Rubio, J.A.P.; Vera-García, F.; Grau, J.H.; Cámara, J.M.; Hernandez, D.A. Marine Diesel Engine Failure Simulator Based on
Thermodynamic Model. Appl. Therm. Eng. 2018, 144, 982–995. [CrossRef]
52. Cipollini, F.; Oneto, L.; Corradu, A.; Murphy, A.J.; Anguita, D. Condition-Based Maintenance of Naval Propulsion Systems with
Supervised Data Analysis. Ocean Eng. 2018, 149, 268–278. [CrossRef]
53. Zaccone, R.; Altosole, M.; Figari, M.; Campora, U. Diesel Engine and Propulsion Diagnostics of a Mini-Cruise Ship by Using
Artificial Neural Networks. In Towards Green Marine Technology and Transport; Soares, G., Pavleti, D., Eds.; Taylor & Francis Group:
London, UK, 2015; pp. 593–602. [CrossRef]
54. Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [CrossRef]
55. Radonjic, A.; Vukadinovic, K. Application of Ensemble Neural Networks to Prediction of Towboat Shaft Power. J. Mar. Sci.
Technol. 2015, 20, 64–80. [CrossRef]
56. Kim, D.; Lee, S.; Lee, J. An Ensemble-Based Approach to Anomaly Detection in Marine Engine Sensor Streams for Efficient
Condition Monitoring and Analysis. Sensors 2020, 20, 7285. [CrossRef]
57. Haykin, S. Neural Networks: A Comprehensive Foundation; Macmillan: New York, NY, USA, 1994.
58. Gamma Technologies. GT-SUITE Integrated Multi-Physics Systems Simulation. Available online: https://www.gtisoft.com/gt-
suite/ (accessed on 2 September 2024).
59. Gamma Technologies. Published Papers and Presentations Associated with GT-SUITE. Available online: https://www.gtisoft.
com/gt-suite/publications/ (accessed on 2 September 2024).
60. Lazakis, I.; Ölçer, A. Selection of the Best Maintenance Approach in the Maritime Industry Under Fuzzy Multiple Attributive
Group Decision-Making Environment. Proc. Inst. Mech. Eng. Part M J. Eng. Marit. Environ. 2016, 230, 297–309. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.