scholarly journals Unsupervised Damage Detection for Offshore Jacket Wind Turbine Foundations Based on an Autoencoder Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3333
Author(s):  
Maria del Cisne Feijóo ◽  
Yovana Zambrano ◽  
Yolanda Vidal ◽  
Christian Tutivén

Structural health monitoring for offshore wind turbine foundations is paramount to the further development of offshore fixed wind farms. At present time there are a limited number of foundation designs, the jacket type being the preferred one in large water depths. In this work, a jacket-type foundation damage diagnosis strategy is stated. Normally, most or all the available data are of regular operation, thus methods that focus on the data leading to failures end up using only a small subset of the available data. Furthermore, when there is no historical precedent of a type of fault, those methods cannot be used. In addition, offshore wind turbines work under a wide variety of environmental conditions and regions of operation involving unknown input excitation given by the wind and waves. Taking into account the aforementioned difficulties, the stated strategy in this work is based on an autoencoder neural network model and its contribution is two-fold: (i) the proposed strategy is based only on healthy data, and (ii) it works under different operating and environmental conditions based only on the output vibration data gathered by accelerometer sensors. The proposed strategy has been tested through experimental laboratory tests on a scaled model.

Author(s):  
Thanh Dam Pham ◽  
Junbae Kim ◽  
Byoungcheon Seo ◽  
Rupesh Kumar ◽  
Youngjae Yu ◽  
...  

Abstract A pilot floating offshore wind turbine project of Korea was proposed for installing in the East Sea of Korea. The prototype is a semisubmersible platform supporting a 750-kW wind turbine. A scaled model was tested in the basin tank of the University of Ulsan at scale ratio 1:40. The 750-kW floating offshore wind turbine was modeled by using the NREL-FAST code. Numerical results were validated by comparing with those of the test model. This paper analyzes dynamic responses and loads of the wind turbine system under extreme environmental conditions. Extreme environmental conditions based on metocean data of East Sea Korea. Extreme responses and extreme loads are important data for designing the structure of the 750 kW semi-submersible floating offshore wind turbine.


Author(s):  
Wenhua Wang ◽  
Zhen Gao ◽  
Xin Li ◽  
Torgeir Moan ◽  
Bin Wang

In the last decade the wind energy industry has developed rapidly in China, especially offshore. For a water depth less than 20m, monopile and multi-pile substructures (tripod, pentapod) are applied widely in offshore wind farms. Some wind farms in China are located in high seismicity regions, thus, the earthquake load may become the dominant load for offshore wind turbines. This paper deals with the seismic behavior of an offshore wind turbine (OWT) consisting of the NREL 5MW baseline wind turbine, a pentapod substructure and a pile foundation of a real offshore wind turbine in China. A test model of the OWT is designed based on the hydro-elastic similarity. Test cases of different load combinations are performed with the environmental conditions generated by the Joint Earthquake, Wave and Current Simulation System and the Simple Wind Field Generation System at Dalian University of Technology, China, in order to investigate the structural dynamic responses under different load conditions. In the tests, a circular disk is used to model the rotor-nacelle system, and a force gauge is fixed at the center of the disk to measure the wind forces during the tests. A series of accelerometers are arranged along the model tower and the pentapod piles, and strain gauges glued on the substructure members are intended to measure the structural dynamic responses. A finite element model of the complete wind turbine is also established in order to compare the theoretical results with the test data. The hydro-elastic similarity is validated based on the comparison of the measured dynamic characteristics and the results of the prototype modal analysis. The numerical results agree well with the experimental data. Based on the comparisons of the results, the effect of the wind and sea loads on the structural responses subjected to seismic is demonstrated, especially the influence on the global response of the structure. It is seen that the effect of the combined seismic, wind, wave and current load conditions can not be simply superimposed. Hence the interaction effect in the seismic analysis should be considered when the wind, wave and current loads have a non-negligible effect.


Author(s):  
Tomoaki Utsunomiya ◽  
Shigeo Yoshida ◽  
Hiroshi Ookubo ◽  
Iku Sato ◽  
Shigesuke Ishida

This paper is concerned with the development of a Floating Offshore Wind Turbine (FOWT) utilizing spar-type floating foundation. In order to design such a structure, it is essential to evaluate the dynamic response under extreme environmental conditions. In this study, therefore, a dynamic analysis tool has been developed. The dynamic analysis tool consists of a multi-body dynamics solver (MSC.Adams), aerodynamic force evaluation library (NREL/AeroDyn), hydrodynamic force evaluation library (In-house program named SparDyn), and mooring force evaluation library (In-house program named Moorsys). In this paper, some details of the developed dynamic analysis tool are given. In order to validate the program, comparison with the experimental results, where the wind, current and wave are applied simultaneously, has been made. The comparison shows that satisfactory agreements between the simulation and the experimental results are obtained. However, when VIM (Vortex Induced Motion) occurs, the current loads and cross flow responses (sway and roll) are underestimated by the simulation since the simulation code does not account for the effect of VIM.


2012 ◽  
Vol 226-228 ◽  
pp. 772-775
Author(s):  
Yu Chen ◽  
Chun Li ◽  
Wei Gao ◽  
Jia Bin Nie

Offshore wind turbine is a novel approach in the field of wind energy technology. With the rapid development of coastal wind farms, it is the trend to move them outward to deep-water district. However, the cost of construction rises significantly with the increase in water depth. Floating wind turbine is one of the efficient methods to solve this problem. The early history, current status and cutting-edge improvements of overseas offshore floating wind turbine as well as the shortcomings shall be presented. The concept designs, international standards, fully coupled model simulations and hydrodynamic experiments will be illustrated and discussed together with the development of the theory and the related software modules. Thus a novel researching method and concept shall be presented to provide reference for future researches


Author(s):  
Xiaolu Chen ◽  
Zhiyu Jiang ◽  
Qinyuan Li ◽  
Ye Li

Abstract Evaluation of dynamic responses under extreme environmental conditions is important for the structural design of offshore wind turbines. Previously, a modified environmental contour method has been proposed to estimate extreme responses. In the method, the joint distribution of environmental variables near the cut-out wind speed is used to derive the critical environmental conditions for a specified return period, and the turbulence intensity (TI) of wind is assumed to be a deterministic value. To address more realistic wind conditions, this paper considers the turbulence intensity as a stochastic variable and investigates the impact on the modified environmental contour. Aerodynamic simulations are run over a range of mean wind speeds at the hub height from 9–25 m/s and turbulence levels between 9%–15%. Dynamic responses of a monopile offshore wind turbine under extreme conditions were studied, and the importance of considering the uncertainties associated with wind turbulence is highlighted. A case of evaluating the extreme response for 50-year environmental contour is given as an example of including TI as an extra variant in environmental contour method. The result is compared with traditional method in which TI is set as a constant of 15%. It shows that taking TI into consideration based on probabilistic method produces a lower extreme response prediction.


Author(s):  
David Barreto ◽  
Abdolmajid Moghtadaei ◽  
Madjid Karimirad ◽  
Arturo Ortega

Abstract In the field of stochastic dynamics of marine structures, environmental conditions play a vital role. Considering wind and waves as random processes, determining the environmental parameters which correspond to an annual exceedance probability for a certain structural concept is of vital importance for the respective assessment of the loads and their effects. The accuracy in predicting the conditions, especially those corresponding to the sea, is of a great relevance when a probabilistic design is performed in order to ensure the structural integrity of an offshore wind turbine. In particular, models are not always completely perfect and accurate data is not always available. The Environmental Contour Method (ECM), which is based on the IFORM methodology, is one of the most popular methods in the offshore industry when determining the environmental conditions, for a given annual exceedance probability, is required. The ECM allows analysing proper sea states for operational and extreme conditions with lower computational efforts than the most accurate method (Full Long-Term Analysis). In the present study, effects of progressive variations (uncertainties) of the sea states parameters (i.e. significant wave height, spectral peak period) on the dynamic response of a Monopile Wind Turbine (NREL 5MW) are analysed. Two operative conditions are considered: rated wind and cut-out wind speed. In each case, the 50-year environmental contour (EC) is plotted for a site located in the North Sea. Some sea states are selected from the EC (base cases) and then derived cases with percentage variations are generated. All the cases are simulated in FAST (NREL) and the standard deviations of the time series are compared with its respective values of base cases. The results for the dynamic responses at mudline (e.g. overturning moments and shear forces) are presented as the most important parameters governing the design of the monopile. In this analysis, the wave height shows more influence on the response variation percentage than the peak period. This work shows the importance of accurately setting up the input parameters and their impact on the calculation of the dynamic responses.


Sign in / Sign up

Export Citation Format

Share Document