GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades

Liu, Zheng; Liu, Xin; Wang, Kan; Liang, Zhongwei; Correia, José A.F.O.; Jesus, Abílio M.P. De

doi:10.3390/en12061026

Cited by 43 publications

(28 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BP neural network uses the gradient search technique to continuously correct the weights in the network according to the deviation e(k) between the expected and actual values of the system, until the deviation e(k) reaches the minimum value [25]. Through its self-learning and weighting coefficient correction, BP neural network adjusts the parameters of the PID controller in real time to achieve the optimal combination of PID parameters.…”

Section: A Design Of Wind Turbine Pitch Controller For Bp-pidmentioning

confidence: 99%

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

et al. 2020

View full text Add to dashboard Cite

When wind speeds are above the rated speed of variable speed variable pitch wind turbines, pitch angles are changed to keep output powers and rotor speeds at their rated values. For wind turbines with nonlinear and complex structure, conventional PID variable pitch controller is difficult to achieve precise control. In this paper, a variable pitch controller combining back-propagation(BP) neural network with PID (BP-PID) is proposed. By real-time detecting the deviation of the rotor speeds, the BP neural network with self-learning and weighting coefficient correction capability is used to adjust the PID parameters online and further to achieve the optimal combination of the PID parameters. Considering various uncertain disturbances and parameter changes on the mechanical components of the wind turbines, an active disturbance rejection pitch controller of the wind turbines is designed based on BP-PID algorithm. Combined with a tracking differentiator, an extended state observer (ESO) is employed to observe the state and disturbance of the system. In addition, in order to compensate the BP-PID variable pitch controller, nonlinear state error feedback control laws are designed by configuring nonlinear structures according to the state deviation between the extended state observer and the tracking differentiator. The simulation results show that the variable pitch active disturbance rejection control (ADRC) based on BP-PID can effectively estimate the system states and disturbances. And the proposed controller has good dynamic performance and strong robustness. INDEX TERMS Wind turbine, pitch control, BP-PID, active disturbance rejection control, extended state observer.

show abstract

Section: A Design Of Wind Turbine Pitch Controller For Bp-pidmentioning

confidence: 99%

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Genetic algorithms (GA) feature excellent global search ability [46] and are used to optimize the initial connection weights and thresholds of BPANN (hereinafter, GA-BPANN) in order to avoid falling into a local optimum and improve its training speed and modelling ability [42,47]. erefore, GA-BPANN has been applied in many fields of natural and social sciences for complex nonlinear modelling and prediction, showing excellent performance over other BPANN models optimized by different algorithms [48][49][50][51]. Currently, however, there are very few reports on the use of GA-BPANN for spatial interpolation, especially for the interpolation of Antarctic temperatures.…”

Section: Introductionmentioning

confidence: 99%

A GA-Based BP Artificial Neural Network for Estimating Monthly Surface Air Temperature of the Antarctic during 1960–2019

Fang

2021

Advances in Meteorology

View full text Add to dashboard Cite

The spatial sparsity and temporal discontinuity of station-based SAT data do not allow to fully understand Antarctic surface air temperature (SAT) variations over the last decades. Generating spatiotemporally continuous SAT fields using spatial interpolation represents an approach to address this problem. This study proposed a backpropagation artificial neural network (BPANN) optimized by a genetic algorithm (GA) to estimate the monthly SAT fields of the Antarctic continent for the period 1960–2019. Cross-validations demonstrate that the interpolation accuracy of GA-BPANN is higher than that of two benchmark methods, i.e., BPANN and multiple linear regression (MLR). The errors of the three interpolation methods feature month-dependent variations and tend to be lower (larger) in warm (cold) months. Moreover, the annual SAT had a significant cooling trend during 1960–1989 (trend = −0.07°C/year; p = 0.04 ) and a significant warming trend during 1990–2019 (trend = 0.06°C/year; p = 0.05 ). The monthly SAT did not show consistent cooling or warming trends in all months, e.g., SAT did not show a significant cooling trend in January and December during 1960–1989 and a significant warming trend in January, June, July, and December during 1990–2019. Furthermore, the Antarctic SAT decreases with latitude and the distance away from the coastline, but the eastern Antarctic is overall colder than the western Antarctic. Spatiotemporal inconsistencies on SAT trends are apparent over the Antarctic continent, e.g., most of the Antarctic continent showed a cooling trend during 1960–1989 (trend = −0.20∼0°C/year; p = 0.01 ∼ 0.27 ) with a peak over the central part of the eastern Antarctic continent, while the entire Antarctic continent showed a warming trend during 1990–2019 (trend = 0∼0.10°C/year; p = 0.04 ∼ 0.42 ) with a peak over the higher latitudes.

show abstract

“…The statistical method establishes a relationship between historical data and forecasted variables based on data-driven formulations such as regression models [5,6], time series [7], and cluster analysis of clearness index [8,9]. For AI methods, there are artificial neural network (ANN) [10][11][12][13], support vector machine (SVM) [14], and fuzzy logic. A hybrid approach is a mixture of the above approaches.…”

Section: Introductionmentioning

confidence: 99%

Optimal Kernel ELM and Variational Mode Decomposition for Probabilistic PV Power Prediction

et al. 2020

View full text Add to dashboard Cite

A probabilistic prediction interval (PI) model based on variational mode decomposition (VMD) and a kernel extreme learning machine using the firefly algorithm (FA-KELM) is presented to tackle the problem of photovoltaic (PV) power for intra-day-ahead prediction. Firstly, considering the non-stationary and nonlinear characteristics of a PV power output sequence, the decomposition of the original PV power output series is carried out using VMD. Secondly, to further improve the prediction accuracy, KELM is established for each decomposed component and the firefly algorithm is introduced to optimize the penalty factor and kernel parameter. Finally, the point predicted value is obtained through the summation of predicted results of each component and then using the nonlinear kernel density estimation to fit it. The cubic spline interpolation algorithm is applied to obtain the shortest confidence interval. Results from practical cases show that this probabilistic prediction interval could achieve higher accuracy as compared with other prediction models.

show abstract

GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades

Cited by 43 publications

References 21 publications

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

A GA-Based BP Artificial Neural Network for Estimating Monthly Surface Air Temperature of the Antarctic during 1960–2019

Optimal Kernel ELM and Variational Mode Decomposition for Probabilistic PV Power Prediction

Contact Info

Product

Resources

About