Development of a wind turbine gearbox virtual load sensor using multibody simulation and artificial neural networks

A current development trend in wind energy is characterized by the installation of wind turbines (WT) with increasing rated power output. Higher towers and larger rotor diameters increase rated power leading to an intensification of the load situation on the drive train and the main gearbox. However, current main gearbox condition monitoring systems (CMS) do not record the 6‑degree of freedom (6-DOF) input loads to the transmission as it is too expensive. Therefore, this investigation aims to present an approach to develop and validate a low-cost virtual sensor for measuring the input loads of a WT main gearbox. A prototype of the virtual sensor system was developed in a virtual environment using a multi-body simulation (MBS) model of a WT drivetrain and artificial neural network (ANN) models. Simulated wind fields according to IEC 61400‑1 covering a variety of wind speeds were generated and applied to a MBS model of a Vestas V52 wind turbine. The turbine contains a high-speed drivetrain with 4‑points bearing suspension, a common drivetrain configuration. The simulation was used to generate time-series data of the target and input parameters for the virtual sensor algorithm, an ANN model. After the ANN was trained using the time-series data collected from the MBS, the developed virtual sensor algorithm was tested by comparing the estimated 6‑DOF transmission input loads from the ANN to the simulated 6‑DOF transmission input loads from the MBS. The results show high potential for virtual sensing 6‑DOF wind turbine transmission input loads using the presented method.

[1]  B. Jonkman.  Turbsim User's Guide: Version 1.50 , 2009 .

[2]  Georg Jacobs,et al.  Analysis of Wind-Turbine Main Bearing Loads Due to Constant Yaw Misalignments over a 20 Years Timespan , 2019, Energies.

[3]  Ralf Tönjes,et al.  Virtual Sensor Creation to Replace Faulty Sensors Using Automated Machine Learning Techniques , 2020, 2020 Global Internet of Things Summit (GIoTS).

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  I. A. Chaikovsky,et al.  Terminology for model credibility , 1979 .

[6]  J. Sola,et al.  Importance of input data normalization for the application of neural networks to complex industrial problems , 1997 .

[7]  Mehmet Özçalici,et al.  Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction , 2016, Expert Syst. Appl..

[8]  Sung-Hoon Ahn,et al.  Condition monitoring and fault detection of wind turbines and related algorithms: A review , 2009 .

[9]  Robert G. Sargent,et al.  Verification and validation of simulation models , 2009, IEEE Engineering Management Review.

[10]  Geoffrey I. Webb,et al.  Encyclopedia of Machine Learning , 2011, Encyclopedia of Machine Learning.

[11]  Gunnar Abrahamson,et al.  Terminology for model credibility , 1980 .

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  R. Wiser,et al.  The hidden value of large-rotor, tall-tower wind turbines in the United States , 2020, Wind Engineering : The International Journal of Wind Power.

[14]  Wolf Fichtner,et al.  Key challenges and prospects for large wind turbines , 2016 .

[15]  M. Bampton,et al.  Coupling of substructures for dynamic analyses. , 1968 .

[16]  Tiedo Tinga,et al.  Calculating wind turbine component loads for improved life prediction , 2020 .

[17]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[18]  Averill M. Law,et al.  Simulation Modeling and Analysis , 1982 .

[19]  Hermann Winner,et al.  Validation of vehicle dynamics simulation models – a review , 2014 .

[20]  Sasu Tarkoma,et al.  Intelligent Calibration and Virtual Sensing for Integrated Low-Cost Air Quality Sensors , 2020, IEEE Sensors Journal.

[21]  Paul Fleming,et al.  Use of SCADA Data for Failure Detection in Wind Turbines , 2011 .

[22]  Yaoyu Li,et al.  A review of recent advances in wind turbine condition monitoring and fault diagnosis , 2009, 2009 IEEE Power Electronics and Machines in Wind Applications.

[23]  Georg Jacobs,et al.  Modelling of Wind Turbine Loads nearby a Wind Farm , 2017 .

[24]  Poul Henning Kirkegaard,et al.  Cost‐effective shaft torque observer for condition monitoring of wind turbines , 2013 .

[25]  Guido Van Rossum,et al.  Python Tutorial , 1999 .

[26]  Yingning Qiu,et al.  Wind turbine condition monitoring: technical and commercial challenges , 2014 .

[27]  Francesco Braghin,et al.  6D Virtual Sensor for Wrench Estimation in Robotized Interaction Tasks Exploiting Extended Kalman Filter , 2020, Machines.

[28]  Georg Jacobs,et al.  Dynamic simulation of full-scale nacelle test rig with focus on drivetrain response under emulated loads , 2015 .

[29]  Michael M. Tiller.  Verification and Validation of Physical Plant Models , 2009 .

[30]  J. Tinsley Oden,et al.  Verification and validation in computational engineering and science: basic concepts , 2004 .

[31]  Michael N Kotzalas,et al.  Tribological advancements for reliable wind turbine performance , 2010, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[32]  Mikhail A. Semenov,et al.  Canopy temperature for simulation of heat stress in irrigated wheat in a semi-arid environment: a multi-model comparison , 2017 .

[33]  J.S. Carson,et al.  Model verification and validation , 2002, Proceedings of the Winter Simulation Conference.

[34]  N. Nagelkerke,et al.  A note on a general definition of the coefficient of determination , 1991 .

[35]  Adnan M. Abu-Mahfouz,et al.  Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor , 2020, J. Sens. Actuator Networks.