Accurate modelling of the performance of a yacht in varying environmental conditions can significantly improve a yachts performance. However, a racing yacht is a highly complex multi-physics system meaning that real-time performance prediction tools are always semi-empirical, leaving significant room for improvement. In this paper we first use unsupervised machine learning to analyse full-scale yacht performance data. The widely documented ORC VPP (ORC, 2015) and the commercial Windesign VPP are compared to the data across a range of wind conditions. The data is then used to train machine learning models. A number of machine learning regression algorithms are explored including Neural Networks, Random Forests and Support Vector Machines and improvements of 82% are obtained compared to the commercial tools. The use of physics- based learning models (Weymouth and Yue, 2013) is explored in order to reduce the amount of data required to achieve accurate predictions. It is found that machine learning models can outperform empirical models even when predicting performance in environmental conditions that have not been supplied to the model as part of the training dataset.
{"title":"Using Machine Learning To Model Yacht Performance","authors":"C. Byrne","doi":"10.2218/marine2021.6837","DOIUrl":"https://doi.org/10.2218/marine2021.6837","url":null,"abstract":"Accurate modelling of the performance of a yacht in varying environmental conditions can significantly improve a yachts performance. However, a racing yacht is a highly complex multi-physics system meaning that real-time performance prediction tools are always semi-empirical, leaving significant room for improvement. In this paper we first use unsupervised machine learning to analyse full-scale yacht performance data. The widely documented ORC VPP (ORC, 2015) and the commercial Windesign VPP are compared to the data across a range of wind conditions. The data is then used to train machine learning models. A number of machine learning regression algorithms are explored including Neural Networks, Random Forests and Support Vector Machines and improvements of 82% are obtained compared to the commercial tools. The use of physics- based learning models (Weymouth and Yue, 2013) is explored in order to reduce the amount of data required to achieve accurate predictions. It is found that machine learning models can outperform empirical models even when predicting performance in environmental conditions that have not been supplied to the model as part of the training dataset.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127879416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
. Coupled mooring analysis using CFD with dynamic mooring models is becoming an established field. This is an important step for better predictions of responses of moored marine structures in extreme sea states and also for capturing the low-frequency response correctly. The coupling between the CFD and mooring solvers are most often carried out by exchanging the fairlead/anchor points and fairlead forces. In this paper we will discuss effects of using (i) viscous fluid flow on a mooring component level (submerged buoys and clump weights) and (ii) the fluid-structure coupling between the viscous fluid solver and the mooring system.
{"title":"Developments in Coupled High-Fidelity Simulations of Moored Marine Structures","authors":"C. Eskilsson, Johannes Palm","doi":"10.2218/marine2021.6806","DOIUrl":"https://doi.org/10.2218/marine2021.6806","url":null,"abstract":". Coupled mooring analysis using CFD with dynamic mooring models is becoming an established field. This is an important step for better predictions of responses of moored marine structures in extreme sea states and also for capturing the low-frequency response correctly. The coupling between the CFD and mooring solvers are most often carried out by exchanging the fairlead/anchor points and fairlead forces. In this paper we will discuss effects of using (i) viscous fluid flow on a mooring component level (submerged buoys and clump weights) and (ii) the fluid-structure coupling between the viscous fluid solver and the mooring system.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129073638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Pellegrini, J. Wackers, A. Serani, M. Visonneau, M. Diez
. The performance of surrogate-based optimization is highly affected by how the surrogate training set is defined. This is especially true for multi-fidelity surrogate models, where different training sets exist for each fidelity. Adaptive sampling methods have been developed to improve the fitting capabilities of surrogate models, avoiding to define an a priori design of experiments, adding training points only where necessary or most useful (i.e., providing the highest knowledge gain) to the optimization process. Nevertheless, the efficiency of the adaptive sampling is highly affected by its initialization. The paper presents and discusses a novel initialization strategy with a limited training set for adaptive sampling. The proposed strategy aims to reduce the computational cost of evaluating the initial training set. Furthermore, it allows the surrogate model to adapt more freely to the data. In this work, the proposed approach is applied to single- and multi-fidelity stochastic radial basis functions for an analytical test problem and the shape optimization of a NACA hydrofoil. Numerical results show that the results of the surrogate-based optimization are improved, thanks to a more effective and efficient domain space exploration and a significant reduction of high-fidelity evaluations.
{"title":"TOWARDS AUTOMATIC PARAMETER SELECTION FOR MULTI-FIDELITY SURROGATE-BASED OPTIMIZATION","authors":"R. Pellegrini, J. Wackers, A. Serani, M. Visonneau, M. Diez","doi":"10.2218/marine2021.6862","DOIUrl":"https://doi.org/10.2218/marine2021.6862","url":null,"abstract":". The performance of surrogate-based optimization is highly affected by how the surrogate training set is defined. This is especially true for multi-fidelity surrogate models, where different training sets exist for each fidelity. Adaptive sampling methods have been developed to improve the fitting capabilities of surrogate models, avoiding to define an a priori design of experiments, adding training points only where necessary or most useful (i.e., providing the highest knowledge gain) to the optimization process. Nevertheless, the efficiency of the adaptive sampling is highly affected by its initialization. The paper presents and discusses a novel initialization strategy with a limited training set for adaptive sampling. The proposed strategy aims to reduce the computational cost of evaluating the initial training set. Furthermore, it allows the surrogate model to adapt more freely to the data. In this work, the proposed approach is applied to single- and multi-fidelity stochastic radial basis functions for an analytical test problem and the shape optimization of a NACA hydrofoil. Numerical results show that the results of the surrogate-based optimization are improved, thanks to a more effective and efficient domain space exploration and a significant reduction of high-fidelity evaluations.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128426927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
. To withstand harsh sea states, fish cages can be immersed during critical sea state conditions. In this paper, we present the numerical modelling of water ballast in flexible pipe. According to our results, we consider this modelling to be easy to implement, easy to use, and numerically efficient. We use the finite element method, in which the pipes are modelled using bar elements. The volume of the ballast tank is distributed over the extremities of the bar elements and is represented as cubes. Once the volume of water ballast has been determined, the altitude of the free surface of the ballast is calculated by dichotomy in the cubes. The force on the extremities of the bar elements is calculated using the resulting altitude. Comparison of the present numerical modelling with an analytical method shows that for a vertical tube, the present modelling is robust and realistic. Through the modelling we have assessed the behaviour of a fish cage using ballast: We analysed the shape of the cage during the different phases (immersed, emerged, ballasting, unballasting), the tension in mooring lines, and in the floating part of the cage.
{"title":"Numerical modelling of water ballast. Application to fish cages.","authors":"D. Priour","doi":"10.2218/marine2021.6839","DOIUrl":"https://doi.org/10.2218/marine2021.6839","url":null,"abstract":". To withstand harsh sea states, fish cages can be immersed during critical sea state conditions. In this paper, we present the numerical modelling of water ballast in flexible pipe. According to our results, we consider this modelling to be easy to implement, easy to use, and numerically efficient. We use the finite element method, in which the pipes are modelled using bar elements. The volume of the ballast tank is distributed over the extremities of the bar elements and is represented as cubes. Once the volume of water ballast has been determined, the altitude of the free surface of the ballast is calculated by dichotomy in the cubes. The force on the extremities of the bar elements is calculated using the resulting altitude. Comparison of the present numerical modelling with an analytical method shows that for a vertical tube, the present modelling is robust and realistic. Through the modelling we have assessed the behaviour of a fish cage using ballast: We analysed the shape of the cage during the different phases (immersed, emerged, ballasting, unballasting), the tension in mooring lines, and in the floating part of the cage.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"246 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114217115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Andersson, Robin Gustafsson, Rikard Johansson, R. Bensow
. A CFD study in both model and ship-scale is conducted to compare the in-behind performance of an ice classed to a conventional propeller. In ship-scale the performance degradation of the ice classed propeller in-behind is less than in open water. Through evaluation of the blades performance tangentially and radially in the wake it is observed that the ice classed blade is superior at very low load, the blunter profiles is less sensitive to negative angles of attack. Contrary, in model-scale a larger difference in performance is noted between the propellers in-behind than expected from open water performance. This is most probably related to differences in Reynolds number between model-scale open water and self-propulsion tests, the thicker profiles of the ice classed propeller makes it additionally punished by the low Reynolds numbers of the self-propulsion tests.
{"title":"In-behind Performance of an Ice Classed Propeller in Model and Ship-Scale","authors":"J. Andersson, Robin Gustafsson, Rikard Johansson, R. Bensow","doi":"10.2218/marine2021.6805","DOIUrl":"https://doi.org/10.2218/marine2021.6805","url":null,"abstract":". A CFD study in both model and ship-scale is conducted to compare the in-behind performance of an ice classed to a conventional propeller. In ship-scale the performance degradation of the ice classed propeller in-behind is less than in open water. Through evaluation of the blades performance tangentially and radially in the wake it is observed that the ice classed blade is superior at very low load, the blunter profiles is less sensitive to negative angles of attack. Contrary, in model-scale a larger difference in performance is noted between the propellers in-behind than expected from open water performance. This is most probably related to differences in Reynolds number between model-scale open water and self-propulsion tests, the thicker profiles of the ice classed propeller makes it additionally punished by the low Reynolds numbers of the self-propulsion tests.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127482005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, offshore wind power and aquaculture industry have developed rapidly and expanded. Considering the sea-use conflict between offshore wind power and aquaculture as well as the development needs, a new designed structure that integrated the floating wind turbine and the fish cage is proposed in this study. This new structure can effectively use the ocean space and achieve a win-win situation between the modern marine aquaculture industry and the renewable energy industry, which is of great significance to both social, economic development and environmental protection. The characteristic of the windenergie-aquaculture integrated structure in this study is that the tower of the wind turbine is connected to the top center of the frame structure of a hexagonal semi-submersible fish cage, and the side columns are as ballast compartments for adjusting the draft and provide sufficient buoyancy. The mooring system is tensioned which is suitable for the deep sea which can mitigate the first order heave, surge and pitch motions. A finite element numerical model is established based on the Morison equation and the mesh grouping method. The dynamic response of the overall structure under wave action is studied. This study has significant reference for ensuring the safe operation of the whole windenergie-aquaculture integrated structure and the efficient utilization of marine space resources.
{"title":"Numerical analysis of the dynamic response of an integrated structure of the floating wind turbine and the fish cage to regular waves","authors":"Hui Su, Chunwei Bi, Yun-Peng Zhao","doi":"10.2218/marine2021.6796","DOIUrl":"https://doi.org/10.2218/marine2021.6796","url":null,"abstract":"In recent years, offshore wind power and aquaculture industry have developed rapidly and expanded. Considering the sea-use conflict between offshore wind power and aquaculture as well as the development needs, a new designed structure that integrated the floating wind turbine and the fish cage is proposed in this study. This new structure can effectively use the ocean space and achieve a win-win situation between the modern marine aquaculture industry and the renewable energy industry, which is of great significance to both social, economic development and environmental protection. The characteristic of the windenergie-aquaculture integrated structure in this study is that the tower of the wind turbine is connected to the top center of the frame structure of a hexagonal semi-submersible fish cage, and the side columns are as ballast compartments for adjusting the draft and provide sufficient buoyancy. The mooring system is tensioned which is suitable for the deep sea which can mitigate the first order heave, surge and pitch motions. A finite element numerical model is established based on the Morison equation and the mesh grouping method. The dynamic response of the overall structure under wave action is studied. This study has significant reference for ensuring the safe operation of the whole windenergie-aquaculture integrated structure and the efficient utilization of marine space resources.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122141567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Z. Moscicki, T. Dewhurst, Michael MacNicoll, Peter S. Lynn, C. Sullivan, M. Chambers, I. Tsukrov, R. Swift, Beth Zotter
A dynamic numerical modeling approach was used to inform the design process and economic analysis for an offshore kelp farm with a modular structure designed to scale to 1,000 hectares. This modeling approach incorporated finite-element representations of kelp aggregates and was implemented using the software OrcaFlex. А sequence of dynamic loading scenarios corresponding to extreme events observed in the Gulf of Maine (North Atlantic) was developed and implemented in numerical simulations. The simulations were used to predict the overall dynamic response of the considered modular offshore kelp farm and estimate the highest tensions in various farm components including the anchor lines. Both regular and random wave loadings were considered. It was shown that utilization of regular (monochromatic) wave model can lead to significant overprediction of expected tensions and overdesign of the structure under investigation. Identification of the appropriate worst-case loading scenarios allowed for the well justified specification of the farm components and a subsequent techno-economic analysis.
{"title":"Using Finite Element Analysis for the Design of a Modular Offshore Macroalgae Farm","authors":"Z. Moscicki, T. Dewhurst, Michael MacNicoll, Peter S. Lynn, C. Sullivan, M. Chambers, I. Tsukrov, R. Swift, Beth Zotter","doi":"10.2218/marine2021.6855","DOIUrl":"https://doi.org/10.2218/marine2021.6855","url":null,"abstract":"A dynamic numerical modeling approach was used to inform the design process and economic analysis for an offshore kelp farm with a modular structure designed to scale to 1,000 hectares. This modeling approach incorporated finite-element representations of kelp aggregates and was implemented using the software OrcaFlex. А sequence of dynamic loading scenarios corresponding to extreme events observed in the Gulf of Maine (North Atlantic) was developed and implemented in numerical simulations. The simulations were used to predict the overall dynamic response of the considered modular offshore kelp farm and estimate the highest tensions in various farm components including the anchor lines. Both regular and random wave loadings were considered. It was shown that utilization of regular (monochromatic) wave model can lead to significant overprediction of expected tensions and overdesign of the structure under investigation. Identification of the appropriate worst-case loading scenarios allowed for the well justified specification of the farm components and a subsequent techno-economic analysis.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129662470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. Marimon Giovannetti, F. Gerhardt, M. Kjellberg, M. Alexandersson, S. Werner
Hybrid testing is an experimental technique that can be used to test ships and marine structures when both hydrodynamic and aerodynamic effects are important, for example for wind powered or wind assisted ships and sailing vessels. SSPA is currently developing an experimental method using hybrid testing involving fan forces added to ship decks to simulate sails to assess the course keeping, seakeeping and manoeuvring performance of a wind powered ship. For conventional motor ships there are well established test methods and knowledge on how to scale the results from model to full-scale. For a wind propelled ship however, the driving force is no longer located at the propeller shaft but high above deck and at another longitudinal position that could vary with true wind angle and speed. Moreover, there is a large side force coming from the aerodynamic forces of the wingsails that needs to be counteracted with lifting surfaces underwater. The side-force and yaw moment are much more prominent than in conventional vessels. The combination of those factors will influence the manoeuvrability and course keeping, especially in waves. Having built up the research tools for predicting and simulating the behaviour of a full-scale vessel, making the model sail in a similar way as predicted for the full-scale vessel remains a challenge because of the difference between Froude scaling and Reynolds scaling applicable for the hull and lifting surfaces respectively. Using Computational Fluid Dynamics (CFD) to understand the scale effects in model tests for a wind powered ship and developing a methodology for determining the fan parameters that correctly model the ships behaviour and performance are the key objectives of the research study. The art of model testing encompasses the need to learn from different techniques to ultimately achieve the best agreement between model tests and full-scale results in terms of accuracy, repeatability, cost, and speed. Learning from preliminary experimental tests, through studies on CFD and ultimately paving the way to new testing methodologies is the main aim of the current paper.
{"title":"The art of model testing: Using CFD to adapt traditional tank testing techniques to a new era of wind propelled shipping","authors":"L. Marimon Giovannetti, F. Gerhardt, M. Kjellberg, M. Alexandersson, S. Werner","doi":"10.2218/marine2021.6815","DOIUrl":"https://doi.org/10.2218/marine2021.6815","url":null,"abstract":"Hybrid testing is an experimental technique that can be used to test ships and marine structures when both hydrodynamic and aerodynamic effects are important, for example for wind powered or wind assisted ships and sailing vessels. SSPA is currently developing an experimental method using hybrid testing involving fan forces added to ship decks to simulate sails to assess the course keeping, seakeeping and manoeuvring performance of a wind powered ship. For conventional motor ships there are well established test methods and knowledge on how to scale the results from model to full-scale. For a wind propelled ship however, the driving force is no longer located at the propeller shaft but high above deck and at another longitudinal position that could vary with true wind angle and speed. Moreover, there is a large side force coming from the aerodynamic forces of the wingsails that needs to be counteracted with lifting surfaces underwater. The side-force and yaw moment are much more prominent than in conventional vessels. The combination of those factors will influence the manoeuvrability and course keeping, especially in waves. Having built up the research tools for predicting and simulating the behaviour of a full-scale vessel, making the model sail in a similar way as predicted for the full-scale vessel remains a challenge because of the difference between Froude scaling and Reynolds scaling applicable for the hull and lifting surfaces respectively. Using Computational Fluid Dynamics (CFD) to understand the scale effects in model tests for a wind powered ship and developing a methodology for determining the fan parameters that correctly model the ships behaviour and performance are the key objectives of the research study. The art of model testing encompasses the need to learn from different techniques to ultimately achieve the best agreement between model tests and full-scale results in terms of accuracy, repeatability, cost, and speed. Learning from preliminary experimental tests, through studies on CFD and ultimately paving the way to new testing methodologies is the main aim of the current paper.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128096094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
When dealing with maintenance in ships engine room, the space available around machinery and systems (clearance) plays an important role and may significantly affect the cost of the maintenance intervention. In a first part of a current research study (Gualeni et al., 2021), a quantitative relation between the maintenance costs increment due to the clearance reduction is determined, using a Bayesian approach to General Linear Model (GLM), with reference to a single item/component of a larger system (Sánchez-Herguedas, 2021). This paper represents the second part of the activity and it enforces a systemic view over the whole machinery or system (Sanders et al., 2012). The aim is to identify not only the relation between maintenance costs and clearance reduction, but how the clearance reductions of the single components/items interact and affect the whole system/machinery accessibility and maintainability, meant as relevant emerging properties. The system emerging properties are investigated through the design and application of a Hidden Markov Model (Salvatier et al., 2016); i.e., the system is modelled by a Markov process with unobservable states. The sequence of states is the maintainability of the system (which incorporates each one of the single components) while the evidence is the increase in cost of maintenance related to the space reduction. By predicting a sequence of states, it is therefore possible to predict the interactions between the system components clearances and determine how the emerging maintainability property is affected by the engine room design.
在船舶机舱进行维修时，机器和系统周围的可用空间(间隙)起着重要的作用，并可能对维修干预的成本产生重大影响。在当前研究的第一部分(Gualeni et al.， 2021)中，使用通用线性模型(GLM)的贝叶斯方法，参考大型系统的单个项目/组件，确定了由于间隙减少而导致的维护成本增量之间的定量关系(Sánchez-Herguedas, 2021)。本文代表了活动的第二部分，它对整个机器或系统进行了系统的观察(Sanders等人，2012)。其目的不仅是确定维护成本和间隙减少之间的关系，而且确定单个部件/项目的间隙减少如何相互作用并影响整个系统/机械的可及性和可维护性，即相关的新特性。通过隐马尔可夫模型的设计和应用来研究系统的新兴属性(Salvatier等人，2016);也就是说，系统是由一个状态不可观察的马尔可夫过程来建模的。状态的顺序是系统的可维护性(它包含了单个组件中的每一个)，而证据是与空间减少相关的维护成本的增加。通过预测一系列状态，可以预测系统组件间隙之间的相互作用，并确定正在出现的可维护性如何受到机舱设计的影响。
{"title":"Accessibility for maintenance in engine room: a prediction tool for operational costs estimation during the design process","authors":"P. Gualeni, T. Vairo","doi":"10.2218/marine2021.6798","DOIUrl":"https://doi.org/10.2218/marine2021.6798","url":null,"abstract":"When dealing with maintenance in ships engine room, the space available around machinery and systems (clearance) plays an important role and may significantly affect the cost of the maintenance intervention. In a first part of a current research study (Gualeni et al., 2021), a quantitative relation between the maintenance costs increment due to the clearance reduction is determined, using a Bayesian approach to General Linear Model (GLM), with reference to a single item/component of a larger system (Sánchez-Herguedas, 2021). This paper represents the second part of the activity and it enforces a systemic view over the whole machinery or system (Sanders et al., 2012). The aim is to identify not only the relation between maintenance costs and clearance reduction, but how the clearance reductions of the single components/items interact and affect the whole system/machinery accessibility and maintainability, meant as relevant emerging properties. The system emerging properties are investigated through the design and application of a Hidden Markov Model (Salvatier et al., 2016); i.e., the system is modelled by a Markov process with unobservable states. The sequence of states is the maintainability of the system (which incorporates each one of the single components) while the evidence is the increase in cost of maintenance related to the space reduction. By predicting a sequence of states, it is therefore possible to predict the interactions between the system components clearances and determine how the emerging maintainability property is affected by the engine room design.","PeriodicalId":367395,"journal":{"name":"The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)","volume":"594 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116070702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：