Research on the damage prediction method of offshore wind turbine tower structure based on improved neural network

Qiu, Bingsen; Lu, Yang; Sun, Liping; Qu, Xianqiang; Yang, Xue; Fu-shan, Tong

doi:10.1016/j.measurement.2019.107141

Cited by 31 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e general regression neural network is highly fault tolerant and robust. At present, it is widely used in processing unstable data [19,20]. e GRNN consists of four layers of neurons, which are the input layer, pattern layer, summation layer, and output layer.…”

Section: General Regression Neuralmentioning

confidence: 99%

Dynamic Modulus Prediction of a High‐Modulus Asphalt Mixture

Wang

Tan

Chen

et al. 2021

Advances in Civil Engineering

View full text Add to dashboard Cite

Dynamic modulus is a key evaluation index of the high-modulus asphalt mixture, but it is relatively difficult to test and collect its data. The purpose is to achieve the accurate prediction of the dynamic modulus of the high-modulus asphalt mixture and further optimize the design process of the high-modulus asphalt mixture. Five high-temperature performance indexes of high-modulus asphalt and its mixture were selected. The correlation between the above five indexes and the dynamic modulus of the high-modulus asphalt mixture was analyzed. On this basis, the dynamic modulus prediction models of the high-modulus asphalt mixture based on small sample data were established by multiple regression, general regression neural network (GRNN), and support vector machine (SVM) neural network. According to parameter adjustment and cross-validation, the output stability and accuracy of different prediction models were compared and evaluated. The most effective prediction model was recommended. The results show that the SVM model has more significant prediction accuracy and output stability than the multiple regression model and the GRNN model. Its prediction error was 0.98–9.71%. Compared with the other two models, the prediction error of the SVM model declined by 0.50–11.96% and 3.76–13.44%. The SVM neural network was recommended as the dynamic modulus prediction model of the high-modulus asphalt mixture.

show abstract

Section: General Regression Neuralmentioning

confidence: 99%

Dynamic Modulus Prediction of a High‐Modulus Asphalt Mixture

Wang

Tan

Chen

et al. 2021

Advances in Civil Engineering

View full text Add to dashboard Cite

show abstract

“…Various designs and techniques have been proposed to reduce the manufacturing and installation cost of the wind turbine tower. For example, Qingxu Jin et al, 2019 [1] assessed the durability of ECC/concrete dual-layer system for tall wind turbine towers; while Binbin Qiu et al, 2019 [2] predicted a method for the damage of Off-shore wind turbine by neural network. In 2018 J.Feliciano et al, [3] generalised an analytical displacement model for wind turbine towers under aerodynamic loading and J.Chou et al, [4] simulated the structural failure of onshore wind turbine under strong winds.…”

Section: Introductionmentioning

confidence: 99%

Analytical Displacement Model of Wind Turbine Towers under Loading Conditions

Raikwar¹,

Ahmed²,

Warudkar³

2021

IRJASH

View full text Add to dashboard Cite

The goal of this work is in twofold: 1) to determine the directional deformation (deflection) and bending stress of 1.25 MW Suzlon wind turbine tower under loading conditions for different cross-sections through finite element analysis method; 2) to develop and validate the analytical model allowing to estimate same for different cross-sections. Wind shear force has been calculated in the prevailing direction of the wind for tower structures through integral equations, are then used as input for 3dimensional finite element model to compute the tower deflection and bending stress. To improve the estimation of tower deflection, a mathematical model is developed based on cantilever beam theory. Results are then compared with those obtained from numerical analysis method. The wind turbine tower deflection is found maximum at the tip of the structure and increasing with the hub height. Results indicate that the square cross-section tower is superior with respect to tower deflection with a maximum deflection of 0.064 mm. Numerical analysis method is used to verify the results of mathematical tower deflection model showing very less percentage of error. Thus, the new mathematical model has the advantage of estimating the tower deflection by just knowing the average wind speed of a wind farm for any wind turbine tower structure.

show abstract

“…They concluded that the effect of the blades rotating on the fatigue life analysis of the tubular towers is significant and the fatigue life can be decreased in the case of neglecting the influence of the wind direction and the low stress range on the fatigue damage of the tubular towers. Qiu et al [9] compared the numerical and experimental results to measure intact steel wind turbine towers with different damage locations and different damage degrees. Abraham et al [10] assessed the influence of nacelle and tower generated flow structures on the near-wake of an operational 2.5 MW wind turbine.…”

Section: Introductionmentioning

confidence: 99%

Study of the Bearing Capacity of Stiffened Tall Offshore Wind Turbine Towers during the Erection Phase

Yang

Baniotopoulos

2020

Energies

View full text Add to dashboard Cite

Offshore wind energy is a rapidly maturing renewable energy technology that is poised to play an important role in future energy systems. The respective advances refer among others to the monopile foundation that is frequently used to support wind turbines in the marine environment. In the present research paper, the structural response of tall wind energy converters with various stiffening schemes is studied during the erection phase as the latter are manufactured in modules that are assembled in situ. Rings, vertical stiffeners, T-shaped stiffeners and orthogonal stiffeners are considered efficient stiffening schemes to strengthen the tower structures. The loading bearing capacity of offshore monopile wind turbine towers with the four types of stiffeners were modeled numerically by means of finite elements. Applying a nonlinear buckling analysis, the ultimate bearing capacity of wind turbine towers with four standard stiffening schemes were compared in order to obtain the optimum stiffening option.

show abstract

Research on the damage prediction method of offshore wind turbine tower structure based on improved neural network

Cited by 31 publications

References 29 publications

Dynamic Modulus Prediction of a High‐Modulus Asphalt Mixture

Dynamic Modulus Prediction of a High‐Modulus Asphalt Mixture

Analytical Displacement Model of Wind Turbine Towers under Loading Conditions

Study of the Bearing Capacity of Stiffened Tall Offshore Wind Turbine Towers during the Erection Phase

Contact Info

Product

Resources

About