检索结果-内蒙古大学图书馆

data-based modelling of arrays of wave energy systems: Experimental tests, models, and validation

CONTROL ENGINEERING PRACTICE 2024年 148卷

作者： Pasta, Edoardo Papini, Guglielmo Pena-Sanchez, Yerai Mosquera, Facundo D. Ferri, Francesco Faedo, Nicolas Politecn Torino Dept Mech & Aerosp Engn DIMEAS Marine Offshore Renewable Energy Lab Corso Duca Degli Abruzzi 24 I-10129 Turin TO Italy Mondragon Univ Fluid Mech Dept Loramendi 4 Arrasate Mondragon 20500 Spain Univ Nacl La Plata Inst Invest Elect Control & Proc Senales Calle 48 & 116CC 91 RA-1900 La Plata Buenos Aires Argentina Aalborg Univ Dept Built Environm Ocean & Coastal Engn Res Grp Thomas Manns Vej 23 1-330 DK-9220 Aalborg Denmark

One of the key steps towards economic feasibility of wave energy conversion technology concerns scaling up to farms of multiple devices, in the attempt to reduce installation costs by sharing infrastructure, and a consequent drop in levelised cost of energy. Moreover, whenever wave energy systems are deployed in proximity (in so-called arrays ), the exploitation of the hydrodynamic interactions between single devices is fully enabled, potentially increasing the final energy outcome. To achieve this in real (operational) time, the employed energy-maximising control strategies require control-oriented array models, able to efficiently describe the dynamics of these interconnected systems in a representative fashion. This can be, nonetheless, a difficult task when considering first principles alone, under small motion assumptions, for modelling purposes. Recognising the uncertainty associated to array numerical models obtained from the linearisation of simplified system equations around their equilibria, this paper presents models of several array configurations identified following a frequency domain approach on the basis of experimental data. Tailored tests on laboratory-scale devices have been designed and conducted in the Aalborg University (Denmark) wave tank facility, with the purpose of performing representative system identification of the wave energy systems arrays. The obtained models are validated on different representative sea states configurations, in controlled and uncontrolled motion operational conditions. The validation results are fully discussed and analysed in terms of standard error measures and time lag, while the obtained models are made freely accessible via a linked repository (named OCEAN ), in the attempt to openly provide validated models for different array configurations.

关键词： Wave energy Wave energy arrays System identification data-based modelling Control oriented models Experimental validation

来源：评论

学校读者我要写书评

暂无评论

data-based modelling of ship emissions and fuel oil consumption for transient engine operation

Data-based modelling of ship emissions and fuel oil consumpt...

引用

OCEANS - Marseille Conference

作者： Schaub, Michele Finger, Georg Riebe, Tino Dahms, Felix Hassel, Egon Baldauf, Michael Wismar Univ Appl Sci Fac Engn Wismar Germany Rostock Univ Fac Mech Engn & Ship Engn Rostock Germany

ISBN: (纸本)9781728114507

Marine pollution has many origins and numerous facets. One of the origins is the global vessel traffic. Shipping pollution is regulated in the IMO International Convention for the Prevention of Pollution from Ships (MARPOL). Its Annex VI focusses on air pollution which will be considered in this paper. Air pollution accrues mainly from energy conversion in combustion engines especially during transient engine operation. Manoeuvring is essential and indispensable when entering or leaving a port. Ports use to be in areas where many people live and work and will be affected directly by air pollution. A conscious handling of resources during manoeuvring is even more important if internal or external engine measures for more sustainable operation are either not available or impracticable for the specific vessel. This paper focusses on the data-based modelling of emissions in order to predict them online when manoeuvring with a ship.

关键词： diesel engines operation environmental protection monitoring prediction fast-time simulation data-based modelling artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative and performative investigation of various data-based and conventional theoretical methods for modelling heat pipe solar collectors

引用

SOLAR ENERGY 2020年第0期198卷 212-223页

作者： Shafieian, Abdellah Parastvand, Hossein Khiadani, Mehdi Edith Cowan Univ Sch Engn 270 Joondalup Dr Perth WA 6027 Australia

Solar collector, as the key component of any solar system, has always been the focal point of research in the field of solar energy. based on the literature, data-based methods, which have been proven to be promising in accurate modelling of solar collectors, have not been used for modelling heat pipe solar collectors (HPSCs). At the same time, accurate equations relating the thermal efficiency of solar collectors to the operational and climatic conditions have not been obtained for HPSCs. Therefore, in this study, various data-based and energy balancebased modelling methods were proposed, and based on different accuracy criteria, their precisions were compared in predicting the performance of HPSCs. First, an experimental rig was manufactured and the operational data of the system was recorded throughout a year. The recorded experimental data was used to train and validate various modelling approaches. Then, the accuracies of the proposed models were analysed and assessed. The evaluated models included Artificial Neural Network (ANN), Thermal Resistance Network (TRN), Artificial Neuro Fuzzy Inference System (ANFIS), and Fuzzy methods. Among different modelling approaches, ANN had the best performance which was followed by the ANFIS and TRN methods. The Fuzzy method was not recommended due to its poor accuracy. In addition, the optimum equations relating the outlet temperature of HPSCs to the operational conditions of the solar water heating systems as well as the climatic conditions were obtained and verified.

关键词： Solar water heating data-based modelling Heat pipe solar collector Energy balance modelling

来源：评论

学校读者我要写书评

暂无评论

Adaptive model based on ESN for anomaly detection in industrial systems

引用

EVOLVING SYSTEMS 2025年第1期16卷 1-16页

作者： Rodriguez-Ossorio, Jose Ramon Moran, Antonio Fuertes, Juan J. Prada, Miguel A. Diaz, Ignacio Dominguez, Manuel Univ Leon Escuela Ingn SUPPRESS Res Grp Campus Vegazana Leon 24007 Spain Univ Oviedo Elect Engn Dept Edif Departamental Oeste 2 Campus Viesques s-n Oviedo 33204 Spain

Modeling real industrial systems is a challenging task due to the complex nature of process data. data-driven models commonly employ machine learning algorithms, but they often lack the ability to adapt to changes in the system over time. This paper proposes a method that uses Echo State Networks (ESN), a simplified version of Recurrent Neural Networks (RNN), to model an industrial plant. The ESN model incorporates online adaptation to system changes and enables the visualisation of deviations or errors in the operation of the plant. This adaptive model acknowledges acceptable changes within the original system while identifying potential problems or errors. The advantage of this approach is that the same model can be applied to other systems with the same design, eliminating the need for algorithm retraining. Firstly, its successful offline application in visualising anomalies applied to the reference plant is assessed. Secondly, the model is tested for online adaptation to changes in another plant with an identical design but slight differences, while still observing the generated faults. Residual colour maps are used for the visualisation of anomalies.

关键词： Echo state networks Dynamics data-based modelling Visual information Online learning

来源：评论

学校读者我要写书评

暂无评论

SWELL: An open-access experimental dataset for arrays of wave energy conversion systems

引用

RENEWABLE ENERGY 2023年第1期212卷 699-716页

作者： Faedo, Nicolas Pena-Sanchez, Yerai Pasta, Edoardo Papini, Guglielmo Mosquera, Facundo D. Ferri, Francesco Politecn Torino Dept Mech & Aerosp Engn Marine Offshore Renewable Energy Lab Turin Italy Univ Basque Country Dept Math Bilbao Spain Univ Nacl La Plata Inst Invest Elect Control & Proc Senales Buenos Aires Argentina Aalborg Univ Dept Built Environm Aalborg Denmark

Achieving large-scale commercial exploitation of ocean wave energy inherently encompasses the design and deployment of arrays of wave energy converters (WECs), in an effort to reduce the associated levelised cost of energy. In this context, understanding the interactions between devices in a controlled WEC array is hence essential to achieve optimal layout configurations, as well as to provide guidance on the area required for array installation, reliability, life-time, and overall cost of the farm. Successful achievement of these vital objectives for the wave energy industry has been constantly aided by the use of appropriate numerical models. Regardless of the specific modelling approach adopted, model reliability is always a major concern: Numerical models need to able be to represent reality to be useful in supporting the different stages of development, hence providing significant results for decision making. To test reliability of a model, experimental results are an invaluable asset for *** the striking absence of real-world data concerning arrays of WEC systems, and its inherent value for model validation and data-based modelling purposes, we present, in this paper, an experimental campaign fully conducted with the sole objective of generating and providing an open-access dataset on WEC farms: SWELL (Standardised Wave Energy converter array Learning Library). The generated dataset, included alongside this manuscript, comprises an approximate total of similar to 3000 variables and more than similar to 108 datapoints, for up to 5 devices in 9 diverse WEC array layouts with different levels of interaction, and 19 carefully selected operating conditions. Four different categories of tests are considered, providing measures of key variables required for model validation and data-based modelling tasks. As such, SWELL provides a crucial resource to achieve confidence in numerical modelling, helping towards creating reliable tools for decision mak

关键词： Wave energy Wave energy converters Array Farm Model validation data-based modelling

来源：评论

学校读者我要写书评

暂无评论

Deep Echo State Networks for modelling of Industrial Systems 25th

Deep Echo State Networks for Modelling of Industrial Systems

引用

25th International Conference on Engineering Applications of Neural Networks (EANN)

作者： Ramon Rodriguez-Ossorio, Jose Gallicchio, Claudio Moran, Antonio Diaz, Ignacio Fuertes, Juan J. Dominguez, Manuel Univ Leon Escuela Ingn SUPPRESS Res Grp Campus Vegazana Leon 24007 Spain Univ Pisa Dept Comp Sci Largo Bruno Pontecorvo 3 I-56127 Pisa Italy Univ Oviedo Elect Engn Dept Edif Departamental Oeste 2Campus Viesques S-N Gijon 33204 Spain

ISBN: (纸本)9783031624940;9783031624957

In the industrial field, the modelling of complex systems is a relevant task to understand their evolution, to infer their most representative characteristics, or to detect anomalous situations. Nevertheless, this modelling is notably challenging within the industrial environment, with large amounts of data to be processed but several difficulties in extracting knowledge from these data. In this paper, we work with an industrial plant with four water tanks, focusing on estimating the levels of two sequentially connected tanks. For this purpose, Deep Echo State Networks (Deep ESNs), within the framework of Reservoir Computing (RC), are used, representing an increasingly popular methodology for efficient learning to modelling systems with diverse time-scale dynamics. Specifically, we have designed a learning system that makes use of a dedicated Deep ESN module for the prediction of the level of each tank. We conducted numerical experiments to examine how the performance of the predictions is affected by the number of layers. Our findings indicate that increasing the number of recurrent layers leads to better predictions, and also highlight noteworthy differences in the dynamics of the upper and lower tanks.

关键词： Reservoir Computing Echo State Networks Deep Echo State Networks Dynamics data-based modelling

来源：评论

学校读者我要写书评

暂无评论

Echo State Networks for anomaly detection in industrial systems 22

Echo State Networks for anomaly detection in industrial syst...

引用

22nd World Congress of the International Federation of Automatic Control (IFAC)

作者： Rodriguez-Ossorio, Jose Ramon Moran, Antonio Alonso, Serafin Perez, Daniel Diaz, Ignacio Dominguez, Manuel Univ Leon SUPPRESS Res Grp Escuela Ingn Campus Vegazana Leon 24007 Spain Univ Oviedo Dept Elect Engn Edif Dept Oeste 2Campus Viesques S-N Gijon 33204 Spain

ISBN: (纸本)9781713872344

In the field of industrial engineering, it is extremely interesting and useful to develop models that faithfully represent the behaviour of real physical systems, which allow to understand their dynamics, to optimise them or to detect anomalous or faulty situations. This paper proposes the modelling of the dynamics of water tanks within an industrial plant with real instrumentation, using Echo State Networks. The developed models have been used to explore the detection of anomalies in the system by analysing the differences between the estimated system state and the actual state after the introduction of faults. Copyright (c) 2023 The Authors.

关键词： Echo-state Networks Visual information Dynamics Transfer function Scale systems data-based modelling

来源：评论

学校读者我要写书评

暂无评论

Mathematical modelling of a TENG-Powered data Buoy

Mathematical Modelling of a TENG-Powered Data Buoy

引用

OCEANS Conference

作者： McLeod, Iain Clemente, Daniel Santos, Paulo Rosa Pinto, Francisco Taveira Rosati, Marco Ringwood, John V. Maynooth Univ Dept Elect Engn Ctr Ocean Energy Res Maynooth Kildare Ireland Univ Porto FEUP Fac Engn CIIMAR Interdisciplinary Ctr Marine & Environm R Porto Portugal

ISBN: (纸本)9798350332261

Triboelectric nanogenerators, or TENGs, are prominent among power take off (PTO) systems being researched for use in specifically small scale wave energy converters (WECs). The low power requirements, and modest size of data buoys, suggests TENGs as an ideal PTO for this small-scale wave energy application. However, a physics-based model of the relationship between the movement of the buoy and the performance of the onboard TENG is difficult, particularly for rolling-ball-type TENGs. This paper develops three multiple input single output system identification (SI), black-box models for a rolling-ball-type TENG. The SI models are identified, and validated, using input-output data gathered from real wave tank tests on a 1:8 Froude-scaled model of a navigation buoy. The models described in this paper, relate the TENG's current output to the displacement, in 6 degrees of freedom (DoFs), of the buoy to which it is mounted, across a range of wave conditions. The SI models used include linear autoregressive with exogenous input (ARX), and nonlinear Kolmogorov-Gabor polynomial (KGP).

关键词： navigation buoy wave energy converter triboelectric nanogenerator TENG parameterization data-based modelling linear ARX model nonlinear KGP model system identification

来源：评论

学校读者我要写书评

暂无评论

Adaptive Model for Industrial Systems Using Echo State Networks 1

引用

24th International Conference on Engineering Applications of Neural Networks (EANN)

作者： Rodriguez-Ossorio, Jose Ramon Moran, Antonio Fuertes, Juan J. Prada, Miguel A. Diaz, Ignacio Dominguez, Manuel Univ Leon Escuela Ingn SUPPRESS Res Grp Campus Vegazana Leon 24007 Spain Univ Oviedo Dept Elect Engn Edif Dept Oeste 2Campus Viesques S-N Gijon 33204 Spain

ISBN: (数字)9783031342042

ISBN: (纸本)9783031342035;9783031342042

When a model of an industrial system is developed, it is expected that this model performs consistently when applied to other identically designed systems. However, different operating hours, degradation or maintenance, among other circumstances, cause a change in the dynamics of the system and result in the model not performing as expected. For this reason, it is necessary to build a model that continuously adapts to changes in the dynamics of the system, in order to handle such deviations and thus reduce the estimation error. This paper proposes the development of an adaptive model based on Echo State Networks to estimate the level of a water tank. For this purpose, two identically designed industrial pilot plants are used, taking one of them as a reference for the parameterization, training and validation of the model, and applying the developed model to the other one in order to evaluate the adaptation to changes in the dynamics of the system.

关键词： Echo State Networks Dynamics data-based modelling Online Learning

来源：评论

学校读者我要写书评

暂无评论

Application of data-based solar field models to optimal generation scheduling in concentrating solar power plants

引用

MATHEMATICS AND COMPUTERS IN SIMULATION 2021年 190卷 1130-1149页

作者： Vasallo, Manuel Jesus Cojocaru, Emilian Gelu Gegundez, Manuel Emilio Marin, Diego Univ Huelva Sci & Technol Res Ctr Huelva Huelva Spain

This paper proposes several data-based models for solar fields (SF) of concentrating solar power (CSP) plants. The proposed models estimate SF thermal output from solar resource data and aim to replace first-principles-based SF models typical in CSP generation schedulers. The advantages of the first models as opposed to the second ones are the ease in their development and their adaptability to changes in the plant, facilitating the forecast of SF thermal output. This information is very useful in order to take advantage of the operational flexibility of CSP plants, which is the main attribute that differentiates them from other renewable sources. The applicability of these models is studied in the optimal generation self-scheduling problem of a CSP plant participating in a day-ahead energy market. A simulation-based economic study has been performed using realistic data, where several scheduling strategies are evaluated in a 50 MW parabolic-trough plant with thermal storage. The scheduling strategies differ only in the model used for the SF. The study shows that the data-based models provide results very similar to those obtained with a first-principles-based SF model. Therefore, they can be used as a viable alternative, while significantly simplifying the design and development of the generation scheduler. (C) 2021 International Association for Mathematics and Computers in Simulation (IMACS). Published by Elsevier B.V. All rights reserved.

关键词： Concentrating solar power data-based modelling Power output forecasting Optimal generation scheduling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：