浮式海上风电基础的数字孪生系统研究

海上风电的发展可以在显著提高可持续性能源供给的同时减少环境污 染。为了开发更多的风能，应用于深远海的浮式海上风电得到了快速发展。 但海洋环境的复杂性使得浮式海上风电的运维成本巨大，阻碍了浮式海上 风电的发展。为了及时监测海洋环境的变化，并且预测其对浮式风机，特 别是其六自由度响应造成的影响，本文针对半潜式浮式风机开发了一套数 字孪生系统，通过数字化手段对浮式风机的动态行为进行实时映射。同时， 引入机器学习工具，对浮式风机六自由度运动响应进行预测，对海上风电 的降本增效具有重要意义。 本文以 15 MW 半潜式浮式海上风机为研究对象，根据浮式风电的特征 和数字孪生系统构成确定了本文开发的数字孪生系统设计目标、设计原则、 功能与开发架构，并采取了合适的开发工具，提高了开发速度，增强了系 统兼容性。使用多种三维建模软件与 C#编程语言完成了浮式风机数字化模 型建立与场景搭建工作。结合 OpenFast 数值分析方法和应用神经网络模型 的机器学习方法预测浮式风机六自由度响应。基于 Unity3D 平台对物理世 界进行高真实度、高精准度的数字孪生映射和数据分析结果的可视化。经 过从多个维度评价数字孪生系统模拟作业的验证结果，本文针对浮式风电 数字孪生的研究可以对数值模拟下的浮式海上风电平台运动响应进行可视 化映射和准确率大于 90%的预测。并且能通过数字孪生平台运行 OpenFast 数值分析软件，提高系统数据分析能力。本文的研究可以为数字孪生在浮 式风电的工程应用提供一定的研究基础。

[1] 胡官清. 极端海况下浮式风机运动响应的预报研究[D]. 大连: 大连理工大学, 2021.
[2] 赵静. 海上风力机系统流体动力性能数值模拟与试验研究[D]. 哈尔滨: 哈尔滨工程大学, 2012.
[3] 国家发展改革委, 工业和信息化部, 国家能源局. 中国制造2025——能源装备实施方案[J]. 中国产经, 2016, 185(6): 66-93.
[4] 申桂英. 《"十四五"可再生能源发展规划》发布[J]. 精细与专用化学品, 2022, 30(6): 4.
[5] “十四五”可再生能源发展规划[R]. 北京: 国家发展和改革委员会, 2022.
[6] 李钢, 田杰, 王仙荣, 等. 远海风电送出技术应用现状及发展趋势[J]. 供用电, 2022, 39(11): 2-10.
[7] 董渝瑾, 陆亮, 蔡文琪, 等. 深远海域漂浮式风电基础水下安装机器人的适用性分析[J]. 太阳能, 2018, 290(6): 54-60.
[8] 高伟, 李春, 叶舟. 深海漂浮式风力机研究及最新进展[J]. 中国工程科学, 2014, 16(2): 79-87.
[9] 刘振亚. 浮式海上风电结构动力响应分析与疲劳损伤研究[D]. 青岛: 中国海洋大学, 2015.
[10] 中国科技产业刊综合整理. 立足新发展阶段 贯彻新发展理念 构建新发展格局——《"十四五"规划纲要》亮点解析和专家解读[J]. 中国科技产业, 2021, 383(5): 6-9.
[11] 罗岚. 海洋工程数字孪生开发与应用[D]. 深圳: 南方科技大学, 2022.
[12] JARRET C. The Challenges of Automation in the Oil and Gas Sector[J]. Ocean News & Technology, 2019, 8(30): 30.
[13] RENZI D, MANIAR D, MCNEILL S, et al. Developing a Digital Twin for Floating Production Systems Integrity Management[C]// Otc Brasil, 2017: 24-26.
[14] FERRARA P, MACCARINI G R, POLONI R, et al. Virtual Reality: New Concepts for Virtual Drilling Environment and Well Digital Twin[C]// International Petroleum Technology Conference, F, 2020: 20-31.
[15] HOLBERG G I, GRENNBERG V, MARTENS J. Using Digital Twins for Condition Monitoring of Subsea Mechanical Equipment[C]// SPE Asia Pacific Oil & Gas Conference and Exhibition, F, 2020: 6-16.
[16] PEDERSEN E B, JøRGENSEN D, RIBER H J, et al. True Fatigue Life Calculation Using Digital Twin Concept and Operational Modal Analysis[C]// International Ocean and Polar Engineering Conference, F, 2019: 319-354.
[17] REPALLE N, THETHI R, VIANA P, et al. Application of Machine Learning for Fatigue Prediction of Flexible Risers - Digital Twin Approach[C]// SPE Asia Pacific Oil & Gas Conference and Exhibition, F, 2020: 626-631.
[18] 陶飞. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 249(1): 5-22.
[19] 张宁, 郭君, 尹韶平, 等. 数字孪生技术发展现状及其在水下无人系统中的应用展望[J]. 水下无人系统学报, 2022, 3(2): 27-30.
[20] 任福深, 孙雅琪, 胡庆, 等. 基于Unity3D的水下机器人半实物仿真系统[J]. 系统仿真学报, 2020, 32(8): 2-10.
[21] 蒋爱国, 王金江, 谷明, 等. 数字孪生驱动半潜式钻井平台智能技术应用[J]. 船海工程, 2019, 48(5): 1-5.
[22] 李凯, 钱浩, 龚梦瑶, 等. 基于数字孪生技术的数字化舰船及其应用探索[J]. 船舶, 2018, 29(6): 3-8.
[23] 姚靖维, 周祺, 张刚. 基于数字孪生技术的船舶管件加工智能车间研究[J]. 自动化仪表, 2021, 42(6): 5-12.
[24] FRANCOIS L. E &P Offshore: A New Wind Blows[J]. E &P Plus, 2020, 3(1): 21-33.
[25] GE Renewable Energy Finalizes Supply and Service Contracts for 1.1 GW Ocean Qind Offshore Project in New Jersey[N]. News Bites - Private Companies, 2021-1-29(9).
[26] Hitachi Energy Launches OceaniQ™ – Innovative Solutions for the Offshore Environment [N]. Nasdaq OMX's News Release Distribution Channel, 2022-4-4(1).
[27] 闻力生. 数字孪生是服装智能制造的底座[J]. 中外缝制设备, 2022, 3(6): 1-3.
[28] 廉磊. 基于NX MCD的机器人激光熔覆系统虚拟调试研究[D]. 河北: 燕山大学, 2020.
[29] EIGNER M B. Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems[J]. Zeitschrift Für Wirtschaftlichen Fabrikbetrieb, 2020, 115(1): 3-6.
[30] LEE A, KIM J, JANG I. Movable Dynamic Data Detection and Visualization for Digital Twin City[C]// The 2020 IEEE International Conference on Consumer Electronics - Asia, 2020: 45-57.
[31] SESHADRI B R, KRISHNA M T. Structural Health Management of Damaged Aircraft Structures Using Digital Twin Concept[C]// The 25th AIAA/AHS Adaptive Structures Conference, F, 2017: 36-48.
[32] SCIULLO L, MARCHI A D, TROTTA A, et al. Relativistic Digital Twin: Bringing the IoT to the Future[J] ArXiv, 2023, 23(1): 7-39.
[33] COOREY, GENEVIEVE, FIGTREE , et al. The Health Digital Twin: Advancing Precision Cardiovascular Medicine[J]. Nature Reviews. Cardiology, 2021, 18(12): 803-804.
[34] YU W, PATROS P, YOUNG B, et al. Energy Digital Twin Technology for Industrial Energy Management: Classification, Challenges and Future[J]. Renewable and Sustainable Energy Reviews, 2022, 14(9): 12-18.
[35] BOJE, CALIN, GUERRIERO , et al. Towards a Semantic Construction Digital Twin: Directions for Future Research[J]. Automation in Construction, 2020, 114(1): 1-16.
[36] MARAI O E, TALEB T, SONG J S. Roads Infrastructure Digital Twin: a Step toward Smarter Cities Realization[J]. IEEE Network, 2020, PP(99): 1-8.
[37] TAO F, LIU W, ZHANG M, et al. Five-dimension Digital Twin Model and Its Ten Applications[J]. Computer Integrated Manufacturing Systems, 2019, 25(1): 1-18.
[38] 葛世荣, 王世博, 管增伦, 等. 数字孪生--应对智能化综采工作面技术挑战[J]. 工矿自动化, 2022, 3(7): 29-48.
[39] PHANDEN R K, SHARMA P, DUBEY A. A Review on Simulation in Digital Twin for Aerospace, Manufacturing and Robotics[J]. Materials Today, 2020, 38(9): 1-17.
[40] LIU J, CAO X, ZHOU H, et al. A Digital Twin-driven Approach towards Traceability and Dynamic Control for Processing Quality[J]. Advanced Engineering Informatics, 2021, 50(11): 371-395.
[41] GRIEVES M W. Virtually Intelligent Product Systems: Digital and Physical Twins[M]. Complex Systems Engineering: Theory and Practice, 2019.
[42] MUKHOPADHYAY A, REDDY G R, MUKHERJEE I, et al. Generating Synthetic Data for Deep Learning Using VR Digital Twin[J]. International Conference on Cloud and Big Data Computing, 2021, 34(2): 172-195.
[43] 周盛涛. 基于快速动力响应分析的半潜式风机下部结构主尺寸优化[D]. 哈尔滨: 哈尔滨工业大学, 2021.
[44] ZHANG M, TANG Y, ZHANG H, et al. Parameter Optimization of Spiral Fertilizer Applicator Based on Artificial Neural Network[J]. Sustainability, 2023, 15(1): 301-318.
[45] 刘照, 王安然, 刘东旭. 基于MIV-BP神经网络的河北省城镇失业率预测研究[J]. 智库时代, 2019, 52(39): 2-26.
[46] JAIN A K, MAO J, MOHIUDDIN K M. Artificial neural networks[J]. Computer, 1996, 3(1): 1-17.
[47] Govindaraju R S, Ramachandra A R. Artificial Neural Networks in Hydrology[J]. Journal of Hydrologic Engineering, 2000, 5(2): 124-137.
[48] CADENAS E, RIVERA W. Short Term Wind Speed Forecasting in La Venta, Oaxaca, Mexico, Using Artificial Neural Networks[J]. Renewable Energy, 2009, 7(3): 271-301.
[49] 卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理, 2016, 31(1): 1-17.
[50] 康小歌. 基于视频的人群行为识别技术研究[D]. 湖北: 武汉科技大学, 2021.
[51] XIANG L I, ZENGQIANG C, ZHUZHI Y, et al. Simple Recurrent Neural Network Control for Non-Minimum Phase Nonlinear System[J]. Control Theory & Applications, 2001, 18(3): 456-460.
[52] 苏向敬, 周汶鑫, 李超杰, 等. 基于双重注意力LSTM神经网络的可解释海上风电出力预测[J]. 电力系统自动化, 2022, 46(7): 1-11.
[53] RODDIER D, CERMELLI C, AUBAULT A, et al. WindFloat: A Floating Foundation for Offshore Wind Turbines[J]. Journal of Renewable & Sustainable Energy, 2010, 2(3): 27-53.
[54] 吴洵. 浮式太阳能基座水动力特性及其系泊系统研究[D]. 江苏: 江苏科技大学, 2018.
[55] 李盼雨. 漂浮式海上风力机动态响应及气动特性研究[D]. 吉林: 东北电力大学, 2022.
[56] 牛世奎, 殷丽, 盖明礼. 渤海南部海区风浪推算与分析[J]. 海岸工程, 1999, 18(3): 4-17.
[57] 文圣常. 海浪理论与计算原理[M]. 科学技术出版社, 1984.
[58] SUBRATA K C. Handbook of Offshore Engineering[M]. Elsevier, 2005.
[59] 唐友刚. 海洋工程结构动力学[M]. 天津大学出版社, 2008.
[60] 李少华. 海洋平台水动力系数反演方法及实验研究[D]. 湖南: 湖南大学, 2010.
[61] 华绍曾. 实用流体阻力手册[M]. 国防工业出版社, 1985.
[62] TONY B. 风能技术[M]. 科学出版社, 2014.
[63] 张轲. 浮式风机半潜式平台水动力及其运动响应分析[D]. 大连: 大连理工大学, 2021.
[64] 中国船级社. 《海上移动平台入级与建造规范》(2005)简要说明[J]. 舰船标准化工程师, 2006, 39(2): 1-23.
[65] ALLEN C, ANTHONY V. Definition of the UMaine VolturnUS-S Reference Platform Developed for the IEA Wind 15-Megawatt Offshore Reference Wind Turbine[R] . National Renewable Energy Laboratory, 2020.
[66] EVAN G J R, LATHA S. Definition of the IEA 15-Megawatt Offshore Reference Wind[R]. National Renewable Energy Laboratory, 2020.
[67] 姜磊, 高景晖, 钟力生, 等. 远海漂浮式海上风电平台用动态海缆的发展[J]. 高压电器, 2022, 58(1): 1-11.
[68] NIRANJAN R, RAMISETTI S B. Insights From Detailed Numerical Investigation of 15 MW Offshore Semi-Submersible Wind Turbine Using Aero-Hydro-Servo-Elastic Code[J]. Ocean Engineering, 2022, 5(1): 251-269.
[69] 杜宏祥. 数据驱动的数字孪生模型构建与在线监控应用[D]. 南京: 南京理工大学, 2018.
[70] TANG, YOU G, ZHANG, et al. Development of Study on the Dynamic Characteristics of Deep Water Mooring System[J]. Journal of Marine Science & Application, 2007, 7(3): 34-50.
[71] 柳林燕, 杜宏祥, 汪惠芬, 等. 车间生产过程数字孪生系统构建及应用[J]. 计算机集成制造系统, 2019, 3(6): 1-10.
[72] 李俊. 产品设计结构知识库的设计方案及实现[J]. 福建电脑, 2022, 38(6): 73-77.
[73] 汤健, 欧长伟, 谢能刚, 等. 基于Unity3D康复机器人数字孪生模型的实时驱动[J]. 安徽工业大学学报:自然科学版, 2023, 40(1): 1-6.
[74] 彭远方, 赖真明, 杜光勇, 等. 电力生产实时数据驱动数字水电站研究[J]. 四川水力发电, 2022, 37(1): 27-41.
[75] 宁亚芸. AR技术基于数字孪生在智慧水务日常巡检中的应用[J]. 智能建筑与智慧城市, 2022, 21(7): 36-50.
[76] 李阿乐, 郑晓雯, 辛海林, 等. 基于Unity3D的液压支架运动仿真系统研究[J]. 2022, 13(5): 7-19.
[77] LING G, PENG W, GUOLONG S. Art Product Design and VR User Experience Based on IoT Technology and Visualization System[J]. Journal of Sensors, 2021, 21(11): 27-40.
[78] KERSTEN T, LINDSTAEDT M, MAZIULL L, et al. 3D Recording Modelling and Visualisation of the Fortification Kristiansten in Trondheim (Norway) by Photogrammetric Methods and Terrestrial Laser Scanning in the Framework of Erasmus Programmes[C]//. Virtual Reconstruction and Visualization of Complex Architectures: Avila(ES), 2015: 255-262.
[79] NAJAHI Y. Urbis Terram - Designing and Implementing a Procedural City Generation Tool for Unity3D Game Engine[J]. Masters Theses, 2017, 14(5): 28-42.
[80] JUAN C. MARTINEZ F, DAVID A. Physx as a Middleware for Dynamic Simulations in the Container Loading Problem[J]. Proceedings of the Workshop on Principles of Advanced and Distributed Simulation, 2018, 20(3):2895-2902.
[81] WALTER A, MIKEL D, SAMANTHA L , et al. Physics-based Modeling of Crowd Evacuation in the Unity Game Engine[J]. International Journal of Modeling, Simulation and Scientific Computing, 2018, 9(4):1-31.
[82] 于佳民, 刘玉庆, 周伯河. PhysX物理引擎在航天员虚拟现实训练系统中的应用[J]. 计算机应用, 2011, 31(1): 1-5.
[83] 董小斐. 基于物理引擎和增强现实技术的虚拟机器人系统设计与实现[D]. 成都: 电子科技大学, 2015.
[84] 李卫民, 刘淑芬. 基于Solidworks平台的二次开发技术[J]. 机械制造, 2003, 41(4): 3-9.
[85] DONG, LIQUN, ZHANG, et al. Development of Program-driven Plug-in for Conical Counter-rotating Twin Screw Based on SolidWorks[J]. Journal of Polymer Engineering, 2021, 41(4): 320-328.
[86] ARAS, MOHD S M, ZHE, et al. Design Analysis and Modelling of Autonomous Underwater Vehicle (AUV) Using CAD[J]. Indian Journal of Marine Sciences, 2019, 48(7): 1081-1090.
[87] YILI Z, BOWEN C, QINGQING H, et al. Research on Virtual Driving System of a Forestry Logging Harvester[J]. Wireless Personal Communications, 2018, 102(2): 667-682.
[88] Karli W, Jacob V H, Jon D R, et al. C#入门经典[M]. 清华大学出版社, 2002.
[89] SWAMI A, JAIN R. Scikit-learn: Machine Learning in Python[J]. Journal of Machine Learning Research, 2013, 12(10): 2825-2830.
[90] KADIYALA, AKHIL, KUMAR. Applications of Python to Evaluate the Performance of Bagging Methods[J]. Environmental Progress & Sustainable Energy, 2018, 37(5): 1555-1559.
[91] TIOBE. Index for March 2023 [EB/OL].
[2023-03-27]. https://www.tiobe.com/tiobe-index/.
[92] WANG L, ROBERTSON A, JONKMAN J, et al. OC6 Phase I: Improvements to the OpenFAST Predictions of Nonlinear, Low-Frequency Responses of a Floating Offshore Wind Turbine Platform[J]. Renewable Energy, 2022, 29(3): 187-203.
[93] 谢远春. 基于Kalman滤波海上风机结构健康监测研究[D]. 深圳: 南方科技大学, 2022.
[94] 张礼贤. 风浪联合作用下新型半潜浮式风机全耦合数值分析[D]. 大连: 大连理工大学, 2019.
[95] OSAH, SAMUEL, ACHEAMPONG, AKWASI A , et al. Deep Learning Model for Predicting Daily IGS Zenith Tropospheric Delays in West Africa Using TensorFlow and Keras[J]. Advances in Space Research: The Official Journal of the Committee on Space Research(COSPAR), 2021, 68(3): 1243-1262.
[96] ABADI M, BARHAM P, CHEN J, et al. TensorFlow: A System for Large-scale Machine Learning[J]. Usenix Association, 2016, 37(5): 46-61.
[97] FUKANG N. A Linear Regression Model of TensorFlow Based on Python Language[C]// International Conference on Intelligent Systems Research and Mechatronics Engineering, 2019: 174-177.
[98] HEIDI C, KEVIN H, WILLIE W, et al. Deep Learning and Radiomics: the Utility of Google TensorFlow? Inception in Classifying Clear Cell Renal Cell Carcinoma and Oncocytoma on Multiphasic CT[J]. Abdominal Radiology, 2019, 44(6): 2009-2020.
[99] Facial Emotion Detection Using Modified Eyemap-Mouthmap Algorithm on an Enhanced Image and Classification with Tensorflow[J]. The Visual Computer, 2020, 36(3): 529-539.
[100]DALKIRAN, FATMA Y, TORAMAN, MUSTAFA. Predicting Thrust of Aircraft Using Artificial Neural Networks[J]. Aircraft Engineering and Aerospace Technology, 2021, 93(1): 35-41.
[101]VENKAT, ANAND, RUSIRA, et al. SWIRL: High-performance Many-core CPU Code Generation for Deep Neural Networks[J]. International Journal of High Performance Computing Applications, 2019, 33(6): 1275-1289.
[102]Xu L, Liu Q. Real-time Inextensible Surgical Thread Simulation[J]. International Journal of Computer Assisted Radiology and Surgery, 2018, 13(7): 324-339.
[103]MACKLIN M, MüLLER M, CHENTANEZ N. XPBD: Position-based Simulation of Compliant Constrained Dynamics[C]// The Motion In Games 2016, F, 2016: 75-87.
[104]KUBIAK B, PIETRONI N, GANOVELLI F, et al. A Robust Method for Real-time Thread Simulation[C]// The Acm Symposium on Virtual Reality Software & Technology, F, 2007: 6-13.
[105]张禹, 李佳, 罗丹, 等. 基于位置动力学的软组织建模研究[J]. 北京生物医学工程, 2020, 39(4): 6-15.
[106]蓝磊. 基于位置约束的布料动态模拟研究[J]. 布料模拟, 2015, 41(3): 31-45.
[107]马域人. 基于Unity3D的变形履带移动机器人仿真平台搭建与研究[D]. 江苏: 中国矿业大学(江苏), 2019.
[108]冉光灿, 谢晓尧, 景凤宣. 复杂3D地形的遮挡剔除算法研究[J]. 福建电脑, 2012, 12(8): 13-28.
[109]张叶廷, 朱庆. 基于部件可视锥的复杂目标遮挡剔除方法[J]. 武汉大学学报：信息科学版, 2010, 35(10): 5-14.
[110]波浪和风场数据. [EB/OL].
[2022-12]. https: //mds.nmdis.org.cn/pages/dataViewDetail. html?dataSetId=6
[111]CHEN P, CHEN J, HU Z. Software-in-the-loop Combined Reinforcement Learning Method for Dynamic Response Analysis of FOWTs[J]. Frontiers in Marine Science, 2021, 13(7): 72-91.
[112]田欢, 李红莲, 吕学强, 等. 基于改进BP神经网络的学术活动文本分类[J]. 北京信息科技大学学报: 自然科学版, 2018, 33(5): 7-19.
[113]尹康. 基于多特征融合网络的手势轨迹识别研究[D]. 成都: 电子科技大学, 2019.
[114]LI G. A Credibility Evaluation Method for Complex Simulation Systems Based on Interactive Network Analysis[J]. Simulation Modelling Practice and Theory: International Journal of the Federation of European Simulation Societies, 2021, 110(1): 13-25.
[115]任宇航. 数字孪生系统可信度评估方法研究[D]. 哈尔滨: 哈尔滨工业大学， 2021.
[116]全先江, 邵帅. 基于数字孪生的玻璃磨边运维管理系统研究[J]. 现代信息科技, 2021, 5(17): 158-161.
[117]Jonkman J , Branlard E, Jasa J P . Influence of Wind Turbine Design Parameters on Linearized Physics-Based Models in OpenFAST[J]. Wind Energy Science, 2021, 16(9): 41-54.
[118]张辰源, 陶飞. 数字孪生模型评价指标体系[J]. 计算机集成制造系统, 2021, 27(8): 2171-2186.
[119]EIZE D V. Digital 15MW Turbine Offers Help in Scaling Up[J]. Windpower, 2020, 36(5): 28-39.
[120]Lai J S . Separation of Landslide Source and Run-Out Areas with Machine Learning for Landslide Inventory Refinement[C]// Asian Conference on Remote Sensing, 2019: 510-521.