Search

Wind power scenarios have a significant impact on stochastic optimization problems for power systems in which wind power is a significant component. Generative adversarial networks (GANs) are a powerful class of generative models, and can generate realistic scenarios for renewable power sources without the need for any modeling assumptions. However, the performance of GANs in generating scenarios can further be improved by modifying the way in which a Lipschitz constraint on discriminator network is imposed. Another critical problem of applying deep neural networks is overfitting, a phenomenon especially prone to appear on small training sets. In this paper, we propose an improved GAN for the generation of wind power scenarios. To improve the training speed, we use a gradient penalty term to enforce the Lipschitz constraint based on the output and input of the discriminator network. To improve the scenario quality, we further use a consistency term in the training procedure. Besides, the overfitting problem can be effectively alleviated by the enforced Lipschitz continuity. The proposed method is applied to actual time series data from the NREL wind integration data set. The experimental results demonstrate that our method outperforms the existing methods.

The rotor is a key component of rotating machinery, thus it is of great importance to quantitatively detect its damage. Since the sensitivity matrix in the impedance-based rotor damage identification model with a single piezoelectric transducer has lower rank and the available impedances are not sufficient enough, a highly underdetermined inverse problem arises, which may seriously affect the identification of the damaged location and severity. It follows that a coupled impedance-based composite rotor damages detection method with double piezoelectric transducers is proposed to improve the accuracy of damage identification. In this method, the dynamics characteristics of the electromechanically coupled system can be changed by adding a piezoelectric transducer and a corresponding circuit. Thus the coupled impedance is different from the rotor impedance based on a single piezoelectric transducer. Moreover, owing to the different locations of the two piezoelectric transducers, two sets of sensitivity matrix which are linearly independent with each other are derived, and then more available admittances can be obtained by exciting the two piezoelectric transducers successively. Obviously, the rank of the sensitivity matrix can be increased and the ill-posed inverse problem of damage identification equations can be well improved, which leads to an accurate damage detection. Simulated and experimental results show that the proposed coupled impedance-based composite rotor damages identification method with double piezoelectric transducers can more accurately identify the locations and severities of the compound damages and be more suitable for the detection of composite tiny damages, compared to the impedance-based damage detection method with a single piezoelectric transducer.