Ship Operating Conditions Research Articles

Comprehensive evaluation of machine learning models for predicting ship energy consumption based on onboard sensor data

Machine learning models for predicting ship energy consumption are built and their influencing factors are investigated. First, data collected from a real ship is preprocessed. Six machine learning methods are used to establish the prediction models of ship fuel consumption, and the performance of models is evaluated by Mean Absolute Error, Coefficient of Determination and training time. Then, by analysing the correlation and importance of the features, it's studied whether the model established complies with the laws of physics. Finally, the factors affecting the prediction performance of machine learning models are analysed. The results show that Random Forest and Extreme Gradient Boosting are the most suitable algorithms for ship fuel consumption prediction. Data preprocessing, data normalisation, training sample size, model type, ship operating conditions, as well as the thermotechnical parameters of main engine have impact on the prediction performance. In particular, when taking the thermotechnical parameters into consideration, R2 is increased by 0.32%, MAE is reduced by 5.0%.

Characteristics of intermediate volatility organic compounds emitted from inland vessels with different influential factors and implication of reduction emissions

Ships could emit an abundance intermediate volatility organic compounds (IVOCs). In recent years, many studies on the emission characteristics of IVOCs have focused on the burning of heavy fuel oil by ocean-going ships; however, few have focused on inland vessels which have a more significant impact on air quality and human health owing to their closer proximity to cities than ocean-going ships. In this study, the IVOC emission factors (EFIVOCs) of three inland vessels were determined using a dilution sampling system considering different influencing factors (ship age and operating conditions). The results showed that the EFIVOCs values ranged from 869.9 to 7607 mg/kg fuel, with an average of 4128 ± 2703 mg/kg fuel. In addition, the age of the vessel was found to have a dramatic effect on emissions with the average EFIVOCs of inland vessels aged >10 years was 4300 ± 4319, 5769, and 6484 ± 1586 mg/kg fuel under cruising, idling, and maneuvering conditions, respectively, while that of vessels <10 years old was 1180 ± 328.3 mg/kg fuel when maneuvering. The percentages of emission factors for unresolved complex mixture (UCM), normal alkanes (n-alkanes), branched alkanes (b-alkanes), and polycyclic aromatic hydrocarbons (PAHs) from inland vessels were 82.1 ± 2.6 %, 5.2 ± 0.9 %, 10.6 ± 2.0 % and 2.0 ± 0.6 % of the total IVOCs, respectively. The secondary organic aerosols (SOA) production of inland vessels was estimated to be 1212 ± 801.7 mg/kg fuel, which was substantially higher than those of diesel vehicles, non-road construction machinery, and gasoline vehicles reported by other researches. Moreover, based on the ship movement and measured EFIVOCs data, the IVOCs emission inventory of inland vessels in Jiangsu Province and China in 2016 was 4.2 ± 2.8 and 32.0 ± 21.0 Gg respectively, which was comparable to those from diesel vehicle emissions.

Techno-economic optimization of hybrid-electric power plants onboard cruise ships

This work aims at assessing energy, environmental and economic performances of hybrid-electric plants installed onboard large-size cruise vessels fuelled by Liquefied Natural Gas. Specifically, hybrid-electric power plants coupling combined gas electric and steam plants, reciprocating engines and lithium-ion battery pack are considered. By adopting cogeneration efficiency, carbon dioxide emissions, nitrogen oxide emissions and costs as objective functions, optimal performances were assessed by a Mixed Integer Linear Programming code, following a two-step procedure. First, the MILP code has been applied considering 8-days long, phase-mean operating profiles to identify an optimal design of the engine room. Second, power plant performances have been investigated by applying MILP code to hourly demand profiles, in order to provide more detailed insight on working schedule. Overall, as main outcome of the phase-mean analysis, the potential of combined gas electric and steam plants and lithium-ion batteries in promoting a more efficient energy utilization, reduced environmental impact and enhanced cost savings is proved. Specifically, combined gas electric and steam plant was shown to optimize objective functions during navigation and maneuvering, whereas batteries improved energy and environmental performances in the most demanding ship operating conditions. Furthermore, optimal sizing of lithium-ion battery pack was determined at 40 MWh, despite its economic competitiveness resulted to deeply rely on carbon tax. On the other hand, the hourly analysis showed that controlling the combined gas electric and steam plant and batteries according to a mixed spinning reserve-peak shaving strategy optimizes the performance of power plant even in port conditions, with almost no role played by reciprocating engines. In detail, in comparison to a reference non-hybrid electric power plant, batteries are shown to improve cogeneration efficiency and greenhouse gas emission savings by nearly 2%, whereas nitrogen oxide emissions and costs were reduced by 12% and 2%, respectively.

The concept phase design of LNG tank and the fuel supply system on dual-fuel ships

ABSTRACT To reduce pollution, LNG is increasingly used as a fuel in the maritime industry. This paper provides a methodology for the concept phase design of the LNG tank and fuel supply system on a ship. First, constraints of the ship, fuel tank and supply are determined. Next, the simultaneous design and optimisation of the fuel tank and supply system under defined constraints and realistic operating profiles is done. Tank design includes tank type, dimensions, insulation and design pressure analysis and structural strength assessment. Fuel supply system analysis is conducted using the developed dynamic model for comparing system configurations and equipment sizing. The methodology is demonstrated on two dual-fuel cruise ships of different sizes. The influence of ship operating conditions on the tank and fuel supply system and their interdependence is examined. Several candidates for the optimal tank design and fuel supply system are determined based on conflicting design objectives.

Energy, environmental and economic investigations of cruise ships powered by alternative fuels

In recent years, methanol, ammonia and methane–hydrogen blends are currently receiving most of interest as green fuels enabling energy transition in the maritime sector. In this work, the energy, environmental and economic performances offered by these alternative fuels applied to modern large-size cruise ships are investigated. Overall, 5 different routes, three different operating conditions (maneuvering, port and navigation) and summer–winter seasons have been accounted for. Due to the enhanced fuel flexibility of gas turbines, attention is here focused on power configurations integrating combined gas electric and steam plants with reciprocating engines. First, a cogeneration efficiency optimization study has been carried out considering variable ship operating conditions. Interestingly, combined gas steam power plants resulted to cover up to 68% of the overall thermal power request and to provide energy savings when electrical power demand exceeds 15 MW during navigation and maneuvering. Methane–hydrogen blends enabled the highest cogeneration efficiencies (i.e. ≈82%). Successively, environmental impact of power plants is assessed by means of the Energy Efficiency Design Index and Carbon Intensity Indicator, whose attained values have been shown to comply with regulation limits up to 2025 and 2050, respectively, under ammonia and methane–hydrogen feeding conditions. On the contrary, methanol appears a valuable option only for a short-term energy transition perspective, since compliance with regulations lapses before 2028. Finally, investments and operational costs for power plants have been computed to assess their economic viability. In the current scenario, comparable costs result for ammonia and methanol fueled cruise ships, while 40–60 M€increase in operational expenditure is achieved at 25-th year by methane–hydrogen blends due to the high price still affecting green hydrogen.

Assessment of ship manoeuvring safety in waterway systems by relative navigational risk

The safety of vessels navigating in the sea waterway system is ensured by fulfilling the acceptable restrictions called safe ship operation conditions in that system. The assessment of navigation safety is particularly important when the conditions for safe operation of ships in the waterway system are changed concerns increasing the maximum parameters of vessels, increasing the allowable hydrometeorological conditions or changing the minimum tug assistance. The article presents a method for assessing navigation safety when the conditions for the safe operation of vessels in the waterway system get changed. The method uses two indicators, which are difference in navigation risks and relative navigation risk. To determine the navigational risk, algorithms were developed for calculating the probability of accidents caused by the deterioration of navigation conditions and technical failure of ship equipment and tugs. Another algorithm was developed for calculating the consequences of the accidents that involve blocking a waterway by a ship anchoring in an emergency, grounding, impact of the ship against a port structure or moored ship and a collision with another ship in motion. The method developed for assessing navigation safety by means of relative navigation risk can be used in practice when changing the conditions for safe operation of vessels in the waterway system and when the system is modernized. Navigational safety management is a decision process that is implemented in the loop presented in the article. The acceptable risk is determined on the basis of vessel traffic intensity and ship parameters defined by safe operation conditions for a given waterway system. Relative navigational risk may be used in assessment and comparison of various conditions of safe ship operation. The probability of an accident caused by ship's moving outside the available navigable area due to technical failures of ship equipment or tugs is determined, depending on the type of port waterway and the manoeuvres performed.

Ship exhaust emission estimation and analysis using Automatic Identification System data: The west area of Shenzhen port, China, as a case study

In recent years, ship exhaust gases have become an essential source of air pollution. A detailed study of ship exhaust emissions can accurately reflect air pollution intensity in ports with high waterborne traffic. In this paper, ship exhaust emissions in 2018 in the west area of Shenzhen port are estimated based on ship AIS data and fitting results between ship characteristics, including ship length, engines' power, gross tonnage, and maximum speed. This research reveals the emission distributions according to different ship types, months, and operation conditions. The results showed that the contribution rate of exhaust emissions of cargo ships and container ships is at the forefront, In contrast, ship emissions in hotelling and normal cruising are more significant than those in maneuvering and slow steaming conditions. The results presented in this research provide a basis for developing emission reduction measures in port area management and provide relevant experience to other world port areas.

Comparison of Radial and Zonal DC Distribution System for Hybrid-Powered Trimaran Vessels Power Flow Analysis

Two types of power grid structures have been applied to the shipboard, namely the radial and the zonal networks. These two distribution systems have different power characteristics transmitted to the bus panel. The power characteristics affect the power density of each bus at each level. This paper explores the power characteristics of the radial type and the zonal type power grid structures in a DC distribution system. The power flow of both distribution system types has been determined by the Adaptive Newton-Raphson method and simulated based on ship operation conditions using Electrical Power System Analysis Software (ETAP). In determining the power flow for the DC distribution system, one-line diagram modelling is developed in radial type and zonal type. The simulation parameters are adjusted to the operating conditions of the ship, namely sailing, manoeuvring, loading-unloading, and at the port. After that, a power flow simulation has been carried out using ETAP and has showed what had successfully implemented the power flow in the DC distribution system for radial and zonal types. The capacity of Power generation is adequate all through a ship operation. The characteristics of the transmitted power show that the zonal type has a higher efficiency rate than the radial type. The zonal type has a backup bus so that the electrical system's reliability is higher than the radial type. However, the power distributed to the equipment bus from the load bus, both the radial type and the zone type, has the exact power requirements.

13K Chemical Tanker의 기관 제어 불능상태 IMO 2세대 안정성 평가에 관한 실험적 연구

The stability of the existing ships has been evaluated through numerical calculations in the steady-state, but recently the IMO proposed a new stability assessment criteria that the stability is evaluated in the state in which environmental loads from such as waves and wind act like the loads under actual ship operating conditions. In this study, IMO 2nd generation stability assessment method and procedure were summarized for the dead ship condition, and Direct Stability Assessment (DSA) was performed on 13K chemical tanker through basin model test. The model test is performed in the ocean engineering basin to implement wave and wind loads, and environmental conditions for waves were set height and period of the incident wave, considering the regular wave and wind generation range reproducible in the ocean engineering basin. In addition, to consider the effect of wind speed, the Beaufort Scale for wind speed was applied in the model test.

Feasibility study of an integrated COGES-DF engine power plant in LNG propulsion for a cruise-ferry

The feasibility study of an integrated COmbined Gas Electric and Steam-reciprocating engine propulsion plant for a Liquified Natural Gas (LNG) fueled cruise-ferry is assessed in this paper. Specifically, the purpose of this work is to respond to GNV shipowners’ need to equip ships with a propulsion system highly efficient in a wide ship speed range. The issue was addressed through the repowering study of the GNV La Suprema ship. Several power plant configurations based on different dual-fuel (DF) engine and gas turbine combinations have been tested in a cogeneration efficiency maximization study performed over a wide ship speed range. Afterwards, the best power plant was identified. Analysis showed that COmbined Gas Electric and Steam (COGES) plants have a great potential for marine propulsion application due to their benefits in cogeneration efficiency, emissions and required volumes. Furthermore, integrating a COmbined Gas Electric and Steam plant with small size dual-fuel engines revealed high cogeneration efficiency over wide ship operating conditions. The propulsion plant comprising a COmbined Gas Electric and Steam plant based on GE25.1 gas turbine and small size dual-fuel engines was proved to guarantee high cogeneration efficiency (47–52%) over a wide ship speed range (16–26 knots). In particular, a 51% cogeneration efficiency is provided for the current operating condition of GNV La Suprema. Moreover, the energy efficiency design index (EEDI) for the different investigated plants has been also evaluated, to verify their compliance with IMO limits. The selected propulsion plant provides an EEDI margin of 1.42–2.89 gCO2/(t*nm) with respect to the 2025 requirements. Finally, economic analysis was performed for four different ship routes and capital/operational costs have been computed. Overall, the proposed COmbined Gas Electric and Steam-reciprocating engine power plant revealed to be economically feasible over all of the operating conditions accounted for.

Control charts for monitoring ship operating conditions and CO2 emissions based on scalar‐on‐function regression

AbstractTo respond to the compelling air pollution programs, shipping companies are nowadays setting‐up on their fleets modern multisensor systems that stream massive amounts of observational data, which can be considered as varying over a continuous domain. Motivated by this context, a novel procedure is proposed, which extends classical multivariate techniques to the monitoring of multivariate functional data and a scalar quality characteristic related to them. The proposed procedure is shown to be also applicable in real time and is illustrated by means of a real‐case study in the maritime field on the continuous monitoring of operating conditions (ie, the multivariate functional data) and total CO2 emissions (ie, the scalar quality characteristic) at each voyage of a cruise ship. The real‐time monitoring is particularly helpful for promptly supporting managerial decision making by indicating if and when an anomaly occurs during the navigation.

Predicting ships' CO2emissions using feature‐oriented methods

AbstractShipping companies are forced by the current EU regulation to set up a system for monitoring, reporting, and verification of harmful emissions from their fleet. In this regulatory background, data collected from onboard sensors can be utilized to assess the ship's operating conditions and quantify its CO2emission levels. The standard approach for analyzing such data sets is based on summarizing the measurements obtained during a given voyage by the average value. However, this compression step may lead to significant information loss since most variables present a dynamic profile that is not well approximated by the average value only. Therefore, in this work, we test two feature‐oriented methods that are able to extract additional features, namely, profile‐driven features (PdF) and statistical pattern analysis (SPA). A real data set from a Ro‐Pax ship is then considered to test the selected methods. The data set is segregated according to the voyage distance into short, medium, and long routes. Both PdF and SPA are compared with the standard approach, and the results demonstrate the benefits of employing more systematic and informative feature‐oriented methods. For the short route, no method is able to predict CO2emissions in a satisfactory way, whereas for the medium and long routes, regression models built using features obtained from both PdF and SPA improve their prediction performance. In particular, for the long route, the standard approach failed to provide reasonably good predictions.

Experimental testing and simulations of an autonomous, self-propulsion and self-measuring tanker ship model

Improving the energy efficiency of ships has generated significant research interest due to the need to reduce operational costs and mitigate negative environmental impacts. Numerous hydrodynamic energy saving technologies have been proposed. Their overall performance needs to be assessed prior to implementation. A new approach to this evaluation is investigated at model scale which applies an approach comparable to that applied for the performance monitoring of a full scale ship. That is long duration testing that measures power consumption for given environmental and ship operating conditions and can use statistical analysis of the resultant large amount of data to identify performance gains. As a demonstration of the approach, an autonomous, self-propelled and self-measuring free running ship model of an Ice Class tanker is developed. A series of lake based and towing tank tests experiments have been conducted which included bollard pull, shaft efficiency, naked-hull, self-propulsion, and manoeuvrability tests. These investigated the efficiency improvement resulting from changing the ship operational trim and testing different bow designs. An associated mathematical model for the time domain simulation of the autonomous ship model provides an effective tool for data analysis. It has been demonstrated that the use of a suitably instrumented self-propelled autonomous ship model can provide long duration tests that incorporates the influence of varying environmental conditions and thereby identify marginal gains in ship energy efficiency.

Analysis of profiles for monitoring of modern ship performance via partial least squares methods

AbstractShipping operators are nowadays facing the challenge of monitoring ship performance based on operational data. This is triggered by the compelling air pollution regulation EU 2015/757 of the European Parliament, which aims from January 2018 to monitoring, reporting, and verification of all harmful emissions of ships operating in the European Economic Area. On the other hand, the continuous acquisition of operational data, which is performed on most of the modern ships, urgently calls for the application of new and opportune statistical methods able to deal with high‐dimensional data. Ship operating conditions can be in fact described by sensor signals collected throughout each voyage and stored as profiles. In this paper, the latter are analyzed through multiway partial least squares regression of the average fuel consumption per hour over each voyage, which is chosen as scalar performance response, being proportional to harmful emissions. The proposed approach is able to monitor profiles with different length at different voyages. Nevertheless, it is capable of indicating at which instant anomalies may have occurred in ship operating conditions. The proposed approach is shown to be able to furnish clear indications for supporting prognosis of faults. By means of real data acquired from a Ro‐Pax cruise ship owned by the shipping company Grimaldi Group, a different multilinear version that explicitly takes into account the 3‐way structure of the data is also compared with the proposed approach.

Multidisciplinary experiment using steep regular waves to determine ship operating conditions that avoid capsize

This paper explores using steep regular waves to identifying safe operating conditions that avoid capsize. The data is from a multidisciplinary experiment using an autonomous scale-model running a proportional-derivative controller in aft of beam steep regular waves. The test explored relative wave headings from 15 $$^\circ $$ to 75 $$^\circ $$ and speeds from 0.1 to 0.4 Froude number. This effort analyzes the resultant ship trajectories to determine if the model obtained the desired operating conditions during each run. For slow speeds, safe operating conditions could not be identified since the requested headings could not be achieved. For moderate speeds, most requested headings could be achieved. At the highest speeds, only relative wave headings closer to beam seas could be explored as the model capsized in stern quartering waves. Results show that wavelength and wave steepness have minimal effects on the model’s ability to achieve a desired heading. Finally, only a limited number of runs are required to verify a safe operating condition since capsizes appear to be consistently repeatable. This research highlights the usefulness of using steep regular waves for capsize testing but also some of its limitations.

Emissions of NO, NO&amp;lt;sub&amp;gt;2&amp;lt;/sub&amp;gt; and PM from inland shipping

Abstract. Particulate matter (PM) and nitrogen oxides NOx (NOx = NO2+ NO) are key species for urban air quality in Europe and are emitted by mobile sources. According to European recommendations, a significant fraction of road freight should be shifted to waterborne transport in the future. In order to better consider this emission change pattern in future emission inventories, in the present study inland water transport emissions of NOx, CO2 and PM were investigated under real world conditions on the river Rhine, Germany, in 2013. An average NO2 ∕ NOx emission ratio of 0.08 ± 0.02 was obtained, which is indicative of ship diesel engines without exhaust gas aftertreatment systems. For all measured motor ship types and operation conditions, overall weighted average emission indices (EIs), as emitted mass of pollutant per kg burnt fuel of EINOx = 54 ± 4 g kg−1 and a lower limit EIPM1 ≥ 2.0 ± 0.3 g kg−1, were obtained. EIs for NOx and PM1 were found to be in the range of 20–161 and ≥ 0.2–8.1 g kg−1 respectively. A comparison with threshold values of national German guidelines shows that the NOx emissions of all investigated motor ship types are above the threshold values, while the obtained lower limit PM1 emissions are just under. To reduce NOx emissions to acceptable values, implementation of exhaust gas aftertreatment systems is recommended.

Monitoring through T2 Hotelling of cylinder lubrication process of marine diesel engine

Frequently, it can be complex to identify when a process, has a deviation from its normal working conditions, when the process variables are individually monitored. This paper responds to that need.The cylinder lubrication process, of a 2T marine diesel engine, was monitored throughout multivariate control charts, for specific ship operation conditions; the historical data set in control the optimal working process was made and with a new entry of sample n=23, observations out of statistical control were detected using Hotelling’s T2 control charts. The variables that generated the signals in the process were identified through the MYT decomposition technique. This technique could complement and not supplement the systems which monitor the independent variables and have a general vision of the behavior of the complete process.

Investigation of the radial bearing force developed during actual ship operations. Part 2: Unsteady maneuvers

The bearing radial load developed by a propeller during actual ship operating conditions is thoroughly investigated by means of a free running, self-propelled twin screw model at the CNR-INSEAN outdoor maneuvering basin. The present work further broadens the results focused on the quasi-steady conditions (straight ahead motion and steady turning) analyzed in Part I (Ortolani et al., 2015) to transient maneuvers. After the rudder actuation (both at the start of the turning circle and the pull-out phase), peaks 100% higher than the stabilized value have been highlighted, in particular on the internal shaft. To inspect this aspect in depth, the inertial contribution of the propeller mass is reconstructed by the measurement of the 6DoF motion of the model and is removed from the measured force in order to obtain the hydrodynamic force exerted by the propeller. In addition to the turning circles,±10°,±20° and±35° zig–zag maneuvers at three different speeds (FN=0.26,0.32,0.36) were carried out in order to consider the transient effects on the propulsion system during fully unsteady maneuvers. The paper is presented following the same phenomenological style adopted in the previous work in order to clarify the nature of the bearing radial force during transient phases.

Model Reference Robust Control for Marine Propulsion Systems with Model Uncertainty Caused by Hull Deformation

A marine propulsion system can be strongly coupled with the hull deformation in a large-scale ship. The interaction of this coupling dynamics increases the nonlinearity and complexity of the control model. Traditional control method based on the empirical PID (proportion-integration-differentiation) parameters has difficulty in dealing with the model uncertainty caused by the hull deflection. However, up to date, limited work has been done to address the model uncertainty problem of the marine propulsion system. It is therefore imperative to develop feasible and effective control systems that take the model uncertainty into account. In this study, a new method based on the model reference adaptive system (MRAS) has been proposed for the active and accurate control of the marine propulsion system coupling with the hull deformation. A finite element model of the ship shaft line was established to investigate the uncertainty boundaries of the propulsion system. Moreover, the sea trial was carried out on the hydraulic dredge named ”Changjing 2” to measure the main engine power loss under hull deformation. The finite element analysis (FEA) and shipboard measurement results showed a fiducial interval of [0.1% 10%] for the model uncertainty of the marine propulsion system. These uncertainty boundaries were added into the ship speed control system model, and the MRAS controller was designed based on the Lyapunov theory to mitigate the adverse effects of model uncertainty. The stability of the MRAS has been proven by the Lyapunov stability criterion. Numerical evaluations using MATLAB®/ Simulink® software for the ”Changjing 2” ship engine parameters have showed high effectiveness of the MRAS structure for speed tracking under the hull deflection coupling. This study has demonstrated that the newly proposed control system can work stably with various ship operating conditions, and its performance is superior to the traditional PID controller.

Time-domain fatigue assessment of ship side-shell structures

Loads acting on ship side-shell structures are complex and vary randomly over time. The current study proposes a direct calculation procedure for the fatigue assessment of ship side-shell structures. The calculation procedure is characterised by nonlinear time-domain hydrodynamic simulations followed by finite element (FE) analyses. Sensitivity and feasibility analyses of the proposed time-domain procedure were carried out, and the calculated fatigue damages were compared with full-scale measurements made on a container vessel. Fatigue life analyses were carried out by both the spectral method and the time-domain approach. In addition, two approaches for local stress analysis are presented and discussed: an engineering-based definition of the stress concentration factor (SCF) and a proposed local stress factor (LSF) that utilises stress ranges extracted from the stress history. The results from the fatigue analysis using the LSF indicated a shorter fatigue life than the results obtained using the SCF. This difference is observed because the LSF accounts for the effects of wave-induced loads under ship operation conditions in a more realistic manner.