Construction of offline predictive controller for wind farm based on CNN–GRNN

Wang, Yu; Wei, Shanbi; Yang, Wei; Chai, Yi; Li, Penghua

doi:10.1016/j.conengprac.2022.105290

Cited by 5 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input layer's dimension matches the number of neurons, while the pattern layer's neurons correspond to individual samples. A Gaussian function is used in the pattern layer, with a smoothing parameter σ influencing the estimation's smoothness [32]:…”

Section: Establishment Of Grnn Modelmentioning

confidence: 99%

Predicting the wear on the non-working side of the rail profile registration method and its validation

Nie,

Li,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Rail cross-section profile detection can assess the wear and tear of measured rails, providing crucial references for railway maintenance and upkeep. It is challenging to use the conventional method to register only the profile of rail head detection accurately. After the rail edge adjustment in some conventional railways, it becomes difficult to determine the base point of rail profile registration. Due to the wear of non-working edge of rail, a rail profile registration method is proposed. Firstly, a wear prediction model based on the generalized regression neural network is constructed by optimizing smoothing parameters through ten-fold cross-validation to achieve the optimal values. This model predicts the wear values on the non-working rail edge, providing reliable coordinates for two wear points as alignment reference points. Secondly, an initial alignment between the measured profile and the target profile is achieved using the nearest point iterative algorithm, which ensures that both profiles are in the same region and oriented similarly. Thirdly, the weight is assigned to the wear measurement points based on their respective wear values. The predicted positions of wear points are applied for calculating the translation and rotation parameters. These parameters could align the measured profile and facilitate the final profile alignment. Lastly, the experimental profiles under rail adjustment conditions were registered, verifying the accuracy of the proposed method. The research results indicate that under rail adjustment conditions, the mean squared error (MSE) between the calculated and actual values of lateral wear is 0.094 mm2, which is lower than the MSE from manual measurements. The calculated lateral wear value for experimental profiles achieved high alignment and calculation accuracy. This method can be applied in practical projects, providing an effective solution for rail head profile alignment and serving as a reference for profile alignment on the non-working rail edge with incomplete measurement data.

show abstract

Section: Establishment Of Grnn Modelmentioning

confidence: 99%

Predicting the wear on the non-working side of the rail profile registration method and its validation

Nie,

Li,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Compared with H ∞ and gain-scheduled PI (GSPI) controllers, the PD-MFAC controller shows improved blade load alleviation. In [26], a stochastic model predictive control, which uses an adaptive scenario generation is proposed for active yaw control for offshore wind farm. The adaptive controller shows improved harvested energy compared with a baseline predictive controller.…”

Section: Introductionmentioning

confidence: 99%

“…The adaptive controller shows improved harvested energy compared with a baseline predictive controller. The adaptive control schemes in [19]- [21], [23], [24], [26] are not robust to modeling errors resulting from model-system mismatch and inherent WT nonlinearities due operating point changes occasioned by wind variability.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Robust Observer-Based Control for Structural Load Mitigation and Speed Regulation in Commercial Wind Turbines

Kipchirchir,

Hung Do,

Njiri

et al. 2024

IEEE Access

View full text Add to dashboard Cite

As the size of wind turbines (WTs) increases, an additional increase in the structural load on the WT components is to be expected. This will have an impact on operational safety in terms of damage and service life. Spatial and temporal fluctuations in wind speed are responsible for the fatigue load during power generation. To minimize the effects of varying stresses, advanced control systems that incorporate appropriate models of the disturbances are proposed. These controllers are usually developed based on reduced-order models of nonlinear WTs so that they can minimize uncertainties such as modeling errors. Although robust controllers are able to deal with uncertainties, they are still only developed for design situations. Therefore, their performance can deteriorate significantly under very uncertain operating conditions. Adaptive controllers, on the other hand, are designed to consider multiple operating points in the design. However, most of these methods do not consider the optimization of different objectives in the design for structural load reduction or speed control of WTs. In this paper, a novel adaptive robust observerbased control strategy for structural load reduction and rotor speed regulation of commercial WTs operating at higher wind speed is proposed. To achieve this, a robust disturbance accommodating controller (RDAC) is combined with an adaptive pitch controller (aIPC). This adapts to changing operating points. The proposed control method is tested on a 1.5 MW reference WT (RWT) developed by the National Renewable Energy Laboratory (NREL). The simulation results show that, compared with the state of the art presented on a gain-scheduled proportional integral (GSPI) and RDAC controllers, the proposed control method reduces the structural load on the rotor blades by 10.7 % and 9.2 %, respectively, and on the tower by 36.2 % and 8.4 %, respectively. It therefore makes a key contribution to mitigating the structural dynamic loads on the WT by reducing the load on several WT components. This is achieved without any significant impact on the rotor speed and power control or the generated power under changing operating conditions.INDEX TERMS disturbance accommodating control, load mitigation, robust control, wind turbine.

show abstract

“…The optimal TSR method is used for the practical system where wind speed and turbine speed need to be measured. The loss of induction machines is directly related to the choice of flux level [8]. The higher the flux level is, the larger the iron losses are.…”

Section: Introductionmentioning

confidence: 99%

Optimal Efficiency Control of Wind Mill Induction Generator Using Loss Minimization Technique

Faizal,

Rajam

2023

J. Sci. Res.

View full text Add to dashboard Cite

Improvement of the operating efficiency of generators used in large wind power generation systems becomes important since such a large machine's power loss is not negligible. In the conventional method integral controller is used to reduce the power loss by up to 25 % at low wind speeds. The proposed PID controller method is based on flux level reduction, where the flux level is computed from the machine model for the optimum d-axis current of the generator. For the vector-controlled induction generator, the d-axis current controls the excitation level to minimize generator loss. In contrast, the q-axis current controls the generator torque, by which the speed of the induction generator is controlled according to the variation of the wind speed in order to produce the maximum output power, thereby improve the efficiency of the induction generator.

show abstract

Construction of offline predictive controller for wind farm based on CNN–GRNN

Cited by 5 publications

References 38 publications

Predicting the wear on the non-working side of the rail profile registration method and its validation

Predicting the wear on the non-working side of the rail profile registration method and its validation

Adaptive Robust Observer-Based Control for Structural Load Mitigation and Speed Regulation in Commercial Wind Turbines

Optimal Efficiency Control of Wind Mill Induction Generator Using Loss Minimization Technique

Contact Info

Product

Resources

About