In contemporary industrial applications, predictive models have been pivotal in bolstering production efficiency, product quality, scalability, and cost-effectiveness while promoting sustainability. These predictive models can be constructed solely based on domain-specific knowledge, exclusively on observational data, or by amalgamating both approaches. They are commonly referred to as Full-, Zero-, or Partial-knowledge-based predictive models, respectively. Full-knowledge based models are highly explainable, point-wise accurate, data efficient, computationally demanding in the prediction phase to achieve high accuracy. Zero-knowledge based models are poorly explainable, data hungry, highly accurate on average, computationally demanding in the construction phase but inexpensive the prediction phase. Partial-knowledge based models focus on taking the best of the two worlds. To maintain a focused scope and avoid redundancy with existing literature, our review will primarily delve into the key industrial applications within a narrow context, encompassing sectors such as extraction, chemical processes, manufacturing, transportation, energy, and construction. Our approach entails several steps. Initially, we conducted a meta-review to pinpoint gaps in previously published surveys on Full-, Zero-, and Partial-knowledge-based predictive models for industrial applications. Subsequently, we present a formal analysis of the subject matter, supplemented with illustrative examples to offer valuable insights. The core of our work comprises a review of existing research categorized by specific industrial applications. Finally, we outline the unresolved challenges and future prospects in this burgeoning field of research. We contend that our work serves as a valuable resource, catering to the needs of both young researchers seeking a solid foundation for their studies, industrial practitioners aiming to grasp core concepts and applications, and senior researchers seeking potential real-world applications for their findings.@en

The global installed capacity of floating offshore wind turbines is projected to increase by at least 100 times over the next decades. Station-keeping of floating offshore renewable energy devices is achieved through the use of mooring systems. Mooring systems are exposed to a variety of environmental and operational conditions that cause corrosion, abrasion, and fatigue. Regular physical in-service inspections of mooring systems are the golden standard for monitoring their health status. This approach is often expensive, inefficient, and unsafe, and for this reason, researchers are focusing on developing tools for digital solutions for real-time monitoring. Floating offshore renewable energy devices are usually equipped with a wide range of sensors, some low-cost, low/zero maintenance, and easily deployable (e.g., accelerometers on the tower), contrary to others (e.g., direct tension mooring line measurements), producing real-time data streams. In this paper, we propose exploiting the data coming from the first type of sensors for mooring systems health status nowcasting. In particular, we will first rely on state-of-the-art supervised shallow and deep learning models for predicting the health status of the different sections of the mooring lines. Then, since these supervised models require types and amount of data that are seldom available, we will propose new shallow and deep weekly supervised models that require a very small amount of data regarding worn mooring lines. Results will show that these last models can potentially have practical applicability and impact for real-time monitoring of mooring systems in the near future. In order to support our statements, we will make use of data generated with a state-of-the-art digital twin of the mooring system, OrcaFlex, for a floating offshore wind turbine reproducing the physical mechanism of the mooring degradation under different loads and environmental conditions. Results will show errors around 1% in the simplest scenario and errors around 4% in the most challenging one, confirming the potentiality of the proposed approaches.

@en

To ensure that future autonomous surface ships sail in the most sustainable way, it is crucial to optimize the per-formance of the Energy and Power Management (EPM) system. However, marine EPM systems are complex and often coordinate various distributed energy resources, energy storage systems, and power grids to ensure reliable and safe power delivery. Traditional control methods for marine EPM systems are limited by evaluating processes using simplified component models over a short time horizon, or relying on historical insights gained from earlier journeys, and are not the optimal approach for complex hybrid marine EPM systems. Advanced control strategies, such as Model Predictive Control (MPC), offer a promising control method that considers predicted future system responses over an extended time horizon to determine the best control input, making them an effective strategy for optimizing the performance of hybrid marine EPM systems. However, to learn the onboard energy profiles based on component behavior in a hybrid system from past experiences is not a trivial task, and one of the primary barriers to implementing MPC for marine EPM control. For this reason, in this work, we address the challenge of learning energy profiles for a marine EPM system by utilizing shallow and deep machine learning for total power demand forecasting. The forecast is an essential reference for an MPC-based controller and will enable this control strategy to provide reliable and safe power delivery for hybrid marine EPM systems. The proposed approach compares state-of-the-art machine learning models to identify the best-performing algorithm, considering accuracy and computational requirements. We illustrate the potential of the proposed approach by using real world operational data from a vessel with a hybrid marine EPM system. Results indicate that shallow models, trained on engineered features handcrafted with classical signal processing techniques, allow forecasting the total power demand up to a horizon of 5min with minimal loss in accuracy and a negligible computational burden.

@en

Shape optimization of vessel hulls and airfoils is crucial for achieving optimal performance and minimizing environmental impact. Typically, these designs are adaptations of existing ones, not fully optimized for specific Key Performance Indicators (KPIs) such as drag or lift, and their optimization often relies on a mix of human experience and numerical approaches. The current state-of-the-art approach leverages Computational Fluid Dynamics (CFD) Data-Driven Surrogate (DDS) models in a four-step process. First, a shape design space is created through parametrization, involving varying levels of human input. Accurate KPI estimation using CFD is computationally intensive, preventing direct optimization. Thus, in the second step, representative shapes are selected from the design space, and evaluated for their KPIs using CFD. Next, a DDS model is constructed from the generated data, which, although costly to develop, allows for efficient KPI prediction. This model is then integrated into an optimization loop to identify optimal geometries on the Pareto front. Finally, these results are validated through CFD to ensure physical plausibility. This review sets focuses on recent advances in DDS models for shape optimization of hulls and airfoils since 2015, an area not thoroughly covered in previous surveys. We systematically examine the four-step optimization process in recent studies, highlighting the evolution and deeper integration of DDS models with CFD. Additionally, we critically assess unresolved issues and gaps in current methodologies, exploring future research directions such as the application of machine learning for shape optimization. These elements highlight the novelty of our work by synthesizing recent technological advances and proposing pathways for future developments, bridging the gap between traditional methods and future possibilities in shape optimization, with implications for both academic research and industrial practice.@en

Due to increasing environmental concerns and global energy demand, the development of Floating Offshore Wind Turbines (FOWTs) is on the rise. FOWTs offer a promising solution to expand wind farm deployment into deeper waters with abundant wind resources. However, their harsh operating conditions and lower maturity level compared to fixed structures pose significant engineering challenges, notably in the design phase. A critical challenge is the time-consuming hydromechanics analysis traditionally done using computationally intensive Computational Fluid Dynamics (CFD) models. In this study, we introduce Artificial Intelligence-based surrogate models using state-of-the-art Machine Learning algorithms. These surrogate models achieve CFD-level accuracy (within 3% difference) while dramatically reducing computational requirements from minutes to milliseconds. Specifically, we build a surrogate model for characterizing the hydrodynamic response of a floating spar-type offshore wind turbine (including added mass, radiation damping matrices, and hydrodynamic excitation) using computationally efficient shallow Machine Learning models, optimizing the trade-off between computational efficiency and accuracy, based on data generated by a cutting-edge potential-flow code.

@en

Optimizing vessel hull resistance is pivotal for enhancing maritime performance and minimizing environmental impacts. Traditional methods combine expert intuition with Data-Driven Models (DDMs), relying on parametrization to predict and optimize hull geometries using Experimental Fluid Dynamics (EFD) or Computational Fluid Dynamics (CFD) data. However, these conventional approaches are hampered by several limitations: they require significant human input, are computationally intensive and costly, and lack flexibility in adapting to new families of geometries or parameters beyond predefined ranges. Addressing these challenges, our research introduces a novel method that significantly reduces the need for human intervention, computational resources, and costs, while also improving the model's adaptability. By proposing a new a parametrization technique that accurately encompasses the Delft Systematic Yacht Hull Series (DSYHS), we demonstrate that DDMs can be effectively trained directly on EFD datasets. This eliminates the dependency on extensive CFD simulations or the generation of new EFD data tailored to a specific investigation. Our approach matches the performance of leading-edge CFD models, even in extrapolating conditions, with physical plausibility and minimal human oversight. The validation of our method under various and increasingly complex extrapolating scenarios, employing statistical analyses on the DSYHS EFD dataset and comparisons with state-of-the-art CFD models, underscores the effectiveness of our proposal. Furthermore, we demonstrated that our model can successfully optimize hull resistance when navigating geometric parameters outside the confines of the DSYHS validating our results through leading-edge CFD simulations. This work addresses the limitations of existing methodologies by offering a novel approach more accurate, efficient, cost-effective, flexible, automated, and robust to extrapolation for hull resistance optimization.

@en

Seismic events in Italy and worldwide have highlighted the high vulnerability of unreinforced masonry (URM) structures in small historical centres. A key feature of these settlements is to be mostly composed of buildings in aggregate, i.e., interconnected by a more or less structurally effective connection. The seismic assessment of such buildings is quite debated in the literature and no shared tools procedures are currently available. The difficulty of standardization derives from the fact that structural units can be characterized by multiple features and configurations that determine a vast number of vulnerability factors, whose interdependency is not straightforward to be identified. The paper addresses this issue by combining evidence-based damage data with the potential offered by Machine Learning (ML) technique. Real data are used in combination with state-of-the-art ML algorithms carefully tuned via an advanced statistical procedure for two main purposes. The first one will be able to predict possible URM damages based on the vulnerability factor in both interpolation and extrapolation scenarios. The second purpose of the ML-based techniques will be to predict the most important vulnerability factors in making these predictions, namely to make the ML-based model explainable and informative about the underlying phenomena and not just predictive. The small historic centre of Casentino, hit by the 2009 L'Aquila earthquake, is adopted in the paper as the first test case study. A large amount of data was collected after the earthquake through in-situ surveys made by the Universities of Genova, Catania and Rome. Data include both geometric and structural factors, i.e., the input data supplied to the ML algorithm, as well as the actual seismic damage mechanisms, i.e., the output data expected to be predicted by the ML algorithm. As first application, ML techniques are applied only to data acquired on out-of-plane mechanisms.

@en

The prediction of ship motions and quiescent periods, is of paramount importance for the maritime industry. The capability to predict these events sufficiently in advance has the potential to improve the safety and efficiency of several marine operations, such as landing and take-off on aircraft carriers, transfer of cargo, and mating operations between ships. Several models have been proposed in the literature for the prediction of ship motions and quiescent period. This work will review them by first grouping them into three main categories (i.e., physical, data-driven, and hybrid models) and then by detailing the most recent and relevant ones describing the advantages and disadvantages of each approach. Review concludes with the open problems and future perspectives of this important field of research.

@en

For propeller-driven vessels, cavitation is the most dominant noise source producing both structure-borne and radiated noise impacting wildlife, passenger comfort, and underwater warfare. Physically plausible and accurate predictions of the underwater radiated noise at design stage, i.e., for previously untested geometries and operating conditions, are fundamental for designing silent and efficient propellers. State-of-the-art predictive models are based on physical, data-driven, and hybrid approaches. Physical models (PMs) meet the need for physically plausible predictions but are either too computationally demanding or not accurate enough at design stage. Data-driven models (DDMs) are computationally inexpensive ad accurate on average but sometimes produce physically implausible results. Hybrid models (HMs) combine PMs and DDMs trying to take advantage of their strengths while limiting their weaknesses but state-of-the-art hybridisation strategies do not actually blend them, failing to achieve the HMs full potential. In this work, for the first time, we propose a novel HM that recursively correct a state-of-the-art PM by means of a DDM which simultaneously exploits the prior physical knowledge in the definition of its feature set and the data coming from a vast experimental campaign at the Emerson Cavitation Tunnel on the Meridian standard propeller series behind different severities of the axial wake. Results in different extrapolating conditions, i.e., extrapolation with respect to propeller rotational speed, wakefield, and geometry, will support our proposal both in terms of accuracy and physical plausibility.

@en

Accurately forecasting vessel motions is a critical step towards achieving fast and accurate intelligent vessel control systems. Intelligent vessel control relies on accurate predictions of vessel motion to make informed decisions regarding control, maneuvering, and positioning, particularly during times of exogenous loading caused by adverse weather conditions. Hence, by accurately forecasting vessel motion accurately, the control system can anticipate potential issues (i.e., excessive trim or roll) and prescribe corrective actions before they become problematic. In this study, the authors propose two approaches to address the problem of vessel motion forecasting. The first approach relies on classical shallow learning models, whereas the second approach involves the use of state-of-the-art deep learning models for improved accuracy at further forecast horizons. Unlike shallow models, deep models can learn the required features directly from the data and therefore do not require a priori knowledge or additional features engineering. By leveraging deep learning models, the authors show that vessel motions can be forecasted further into the future without a significant loss in accuracy, thereby improving the overall effectiveness of the intelligent vessel control system. To support their statements, the authors use real operational data and compare the performance of the shallow and deep learning models. The results show that deep learning outperforms shallow learning models in terms of accuracy without a significant increase in the computational demand. Additionally, the authors demonstrate that their models remain accurate even under adverse weather conditions, indicating that they have practical applicability for vessel motions forecasting and can potentially improve the overall effectiveness of intelligent vessel control systems.@en

In this paper, for the first time, a three-step approach for the optimal design of stiffened panels accounting for the ultimate limit state due to welding residual stress is developed. First, authors rely on state-of-the-art analytical approaches coupled with recently data-driven nonlinear finite element methods surrogates characterized by functional which are computationally expensive to build but computationally inexpensive to use. Then, surrogates are used within a design optimization loop to find new optimal designs since nonlinear finite element methods are too computationally demanding for this purpose. Finally, the new designs are reassessed with the original nonlinear finite element methods to verify that substituting them with their surrogates in the optimization loop actually leads to better designs. Results obtained optimizing a series of parameters of a commonly used stiffened panel geometry under different scenarios will support the authors’ novel approach.

@en

The last decade has seen significant changes in the power grid complexity due to the increased integration of multiple heterogeneous distributed energy resources. Accurate and fast power flow analysis tools have then become essential to guarantee grid stability, reliable operation, strategic planning, and market strategies. State-of-the-art approaches to power flow analysis are based on iterative numerical techniques which exhibit high accuracy but slow-, or even no-, convergence. For this reason, researchers have investigated the use of data-driven techniques that, while exhibiting lower accuracy with respect to iterative numerical ones, have the advantage of being extremely fast. To address the lack of accuracy, physics-informed data-driven techniques, i.e., techniques that leverage both the data and domain knowledge to generate simultaneously fast and accurate models, have been proposed. Nevertheless, these works exhibit two main limitations: i) they do not fully leverage the physical knowledge, and ii) they do not fairly compare the different approaches. In this paper, we propose a novel physics informed data-driven model able to address both limitations by fully leveraging the physical knowledge into the data-driven, i.e., constraining the model and augmenting the available data, and proposing a framework able to fairly compare the different approaches proving the actual effectiveness of the proposal. Results on the IEEE 57 realistic power network will support the proposal.@en

The development of fast and accurate intelligent vessel control systems is a necessary milestone on the path toward operating autonomous marine vehicles effectively in harsh environments and complex mission settings. One of the main problems of existing control systems is the disparity between the forecasted behaviour and how the vessel actually responds to its environment. This disparity can be partly attributed to the dependency on physics-based methods to model the response of the vessel and the fact that accurate high-fidelity physical models are too computationally expensive to be utilized in real time. One promising solution to this problem is to integrate the dynamic environmental conditions such as sea states, winds, and currents to model the response of the vessel. However, this may not be feasible with the existing physics-based controller strategies due to the high computational requirements. Instead, we propose using Artificial Intelligence (AI) based methods, which leverage Data Mining and Machine Learning, to enable fast and accurate short-term motions forecasting for autonomous marine vehicles. The AI-based approach is extremely time-aware in the forecasting phase since it does not rely on solving the physics behind the phenomenon but rather learns a phenomenon from historical examples, linking the vessel's motions to a holistic view of its real-time environment.To test our hypothesis, we will develop state-of-the-art AI-based models for the short-term motions forecasting of the roll and trim of a twin-engine commercial vessel using real-world operational data and leverage statistical methods to validate our results.@en

The potential impact of underwater radiated noise from maritime operations on marine fauna has become an important issue. The most dominant noise source on a propeller-driven vessel is propeller cavitation, producing both structure-borne and radiated noise, with a broad spectrum that covers a wide range of frequencies. To ensure acceptable noise levels for sustainable shipping, accurate prediction of the noise signature is essential, and procedures able to provide a reliable estimate of propeller cavitation noise are becoming a fundamental tool of the design process. In this work, we investigate the potential of using computationally cheap methods for the prediction of underwater radiated noise from cavitating marine propellers. We compare computational and experimental results on a subset of the Meridian standard propeller series, behind different severities of axial wake, for a total of 432 experiments. The results indicate that the approaches employed can be a convenient solution for noise analysis during the design process.

@en

Accurate, reliable, and computationally inexpensive models of the dynamic state of combustion engines are a fundamental tool to investigate new engine designs, develop optimal control strategies, and monitor their performance. The use of those models would allow to improve the engine cost-efficiency trade-off, operational robustness, and environmental impact. To address this challenge, two state-of-the-art alternatives in literature exist. The first one is to develop high fidelity physical models (e.g., mean value engine, zero-dimensional, and one-dimensional models) exploiting the physical principles that regulate engine behaviour. The second one is to exploit historical data produced by the modern engine control and automation systems or by high-fidelity simulators to feed data-driven models (e.g., shallow and deep machine learning models) able to learn an accurate digital twin of the system without any prior knowledge. The main issues of the former approach are its complexity and the high (in some case prohibitive) computational requirements. While the main issues of the latter approach are the unpredictability of their behaviour (guarantees can be proved only for their average behaviour) and the need for large amount of historical data. In this work, following a recent promising line of research, we describe a modelling framework that is able to hybridise physical and data driven models, delivering a solution able to take the best of the two approaches, resulting in accurate, reliable, and computationally inexpensive models. In particular, we will focus on modelling the dynamic state of a four-stroke diesel engine testing the performance (both in terms of accuracy, reliability, and computational requirements) of this solution against state-of-the-art physical modelling approaches on real-world operational data.

@en

The purpose of this chapter is to provide an overview of the state-of-the-art and future perspectives of Data Science and Advanced Analytics for Shipping Energy Systems. Specifically, we will start by listing the different static and dynamic data sources and knowledge base available in this particular context. Then we will review the Data Science and Advanced Analytics technologies that can leverage these data to extract and synthesize new additional actionable information, suggestions, and actions. We will then review the current exploitation strategies of these technologies aiming at improving the current Shipping Energy Systems. In conclusion, we will depict our vision on the future perspectives of the application and adoption of Data Science and Advanced Analytics for shaping the next generations of Shipping Energy Systems.

@en

Deterministic models based on the laws of physics, as well as data-driven models, are often used to assess the current state of vessels and their systems, as well as predict their future behaviour. Predictive maintenance methodologies (i.e., Condition Based Maintenance) and advanced control strategies (i.e., Model Predictive Control) are built upon the use of such numerical tools to identify ensuing performance shifts. In fact, forecasting near-future performance can substantially contribute to enhancing operational efficiency and enabling advanced system control. Data from modern sensor technology, which has become more readily available, combined with automatic control systems capable of prescribing optimal control strategies, can improve vessel operation and reduce energy consumption. A data-driven model that relies on recent advances in Artificial Intelligence, Machine Learning, and Data Mining, leveraging historical observations is employed to forecast a vessel’s onboard power generation trends as a function of the past, present, and future behaviour of a ship and its systems. To prove the framework, the proposed methodology is tested on real data collected from the Integrated Platform Management System of an Oceangoing Patrol Vessel of the Royal Netherlands Navy. The developed data-driven model is achieves high forecasting accuracy in the near-term. The authors foresee that the proposed methodology could be used as part of an electric energy control strategy, within a more integrated and intelligent mission planning framework.

@en

Ultimate limit state (ULS) assessment examines the maximum load-carrying capacity of structures considering inelastic buckling failure. Contrary to the traditional allowable stress principle which is mainly based on experiences, the ULS assessment focuses on explicitly evaluating the structural safety margin and thus enables a consistent level of safety/risk between conventional and novel structural designs. Modern structures are usually designed as a network of plates and stiffeners (e.g., ship structures, offshore and onshore wind turbine, and land-based bridge) joined by welding which induces a residual stress field. Hence, predicting the ultimate strength reduction of stiffened panels caused by welding residual stress is a crucial problem addressed by many scholars with different approaches, among which the Nonlinear Finite Element Method (NLFEM) is the prevailing approach within the community of structural engineering. Unfortunately, the NLFEM has a high computational requirement which prevents its use in the design, appraisal, and optimisation phases of stiffened panels. To well approximate the nonlinear finite element method, a data-driven method is proposed in this paper, with a functional which is computationally expensive to build but computationally inexpensive to use allowing its application at design stage. Results obtained in different (i.e., interpolation and extrapolation) scenarios using data generated by a state-of-the-art NLFEM on a series of stiffened panels will support the proposed method.

@en

Monitoring and evaluating the biofouling state and its effects on the vessel's hull and propeller performance is a crucial problem that attracts the attention of both academy and industry. Effective and reliable tools to address this would allow a timely cleaning procedure able to trade off costs, efficiency, and environmental impacts. In this paper, the authors carry out a critical review, accompanied with summary tables, of the biofouling problem with a particular focus on the shipping industry and the state-of-the-art techniques for monitoring and evaluating the biofouling state and its effects on the vessel's hull and propeller performance. In particular, different techniques are grouped according to the three main families of numerical models that have been designed and exploited in the literature: Physical Models (i.e., models relying on the mechanistic knowledge of the phenomena), Data-Driven Models (i.e., models relying on historical data about the phenomena together with Artificial Intelligence), and Hybrid Models (i.e., a hybridisation between Physical and Data-Driven Models). A conclusion from the performed review, open problems, and future direction of this field of research is detailed at the end of the review.

@en

In offshore maritime operations, automated systems capable of maintaining the vessel's position and heading using its own propellers and thrusters to compensate exogenous disturbances, like wind, waves, and currents, are referred to as marine dynamic positioning (DP) systems. DP systems play a central role in several marine operations, such as drilling, pipe-laying, coring, and ocean observation. These operations are the primary cause of fuel consumption, having a strong impact on the overall footprint of the vessel. For this reason, we will face the problem of optimal thrust allocation of an over-actuated vessel to maintain position and heading with minimal fuel consumption. State-of-the-art approaches simplify this problem by roughly approximating it and obtain a simple, mostly convex, optimization problem that can be solved in near-real time by the automation system. In this article, we improve current approaches with the following contributions. We will exploit a higher fidelity representation of the physical system, and we will manipulate the resulting optimization problem accordingly, to allow for near-real-time solutions on conventional computing platforms on-board. We evaluate the quality of the proposal with a case study on a drilling unit equipped with six thrusters. The results will show that it is possible to achieve up to 5% of fuel savings with respect to conventional approaches. Note to Practitioners - This article was motivated by the problem of minimizing fuel consumption in thrust allocation of DP systems. The current approaches simplify this issue by adopting simpler, yet related, optimization problems as surrogates, keeping the problem tractable for near-real-time control. We propose, instead, to solve the original problem with state-of-the-art modelization of the physical system and exploit reasonable and theoretical proprietaries to achieve optimal solutions in near-real-time. The results on a drilling unit will show additional fuel savings of up to 5% with respect to alternative state-of-the-art approaches.

@en