Search

With the development of wind resources under flat terrain, wind farms in extreme wind conditions are developed, and the size of the WT's rigid-flexible coupling components increases. Therefore, accurately understanding the load characteristics and transmission mechanism of each component plays an important scientific role in improving the reliability of WT (WT) design and operation. Through the collation and analysis of the literature, this review summarizes the research results of large-scale WT load under source–grid coupling. According to the classification of sources, the variation characteristics of different loads are analyzed, and different research methods for different loads are summarized. In addition, the relative merits of the existing improvement schemes are analyzed, and the existing problems are pointed out. Finally, a new research idea of 'comprehensively considering the coupling effects of source and network factors, revealing WT load characteristics and transmission mechanism' is summarized. This paper provides important implications for the safety design and reliable operation research of large WTs with complex terrain. [ABSTRACT FROM AUTHOR]

Aiming at the problem where the current engineering wake model does not describe the wind speed distribution of the wake in the complex terrain wind farm completely, based on the three-dimensional full wake model (3DJGF wake model), this paper proposed a wake model that can predict the three-dimensional wind speed distribution of the entire wake region in the complex wind farm, taking into account the Coanda effect, wind shear effect, and wake subsidence under the Gaussian terrain. Two types of Doppler lidar were used to conduct wind field experiments, and the inflow wind profile and three-dimensional expansion of the wake downstream of the wind turbine on the Gaussian terrain were measured. The experimental results showed that the wake centerline and terrain curve showed similar variation characteristics, and the near wake profile was similar to a super-Gaussian shape (asymmetric super-Gaussian shape) under low-wind-speed conditions, while the near wake profile presented a bimodal shape (asymmetric bimodal shape) under high-wind-speed conditions. The predicted profiles of the Gaussian terrain wake model were compared with the experimental data and the three typical wake models. The comparison results showed that the newly proposed Gaussian terrain wake model fit well with the experimental data in both near wake and far wake regions, and it had better performance in predicting the wake speed of the Gaussian terrain wind farm than the other three wake models. It can effectively predict the three-dimensional velocity distribution in the whole wake region of complex terrain. [ABSTRACT FROM AUTHOR]

Under the background of the "strong direct current and weak alternating current" large power grid, the synchronous condenser with dynamic reactive power support capability becomes more important. Due to factors such as manufacturing, installation, and changes in operating conditions, there are many faults associated with the synchronous condenser. This paper studies a fault diagnosis method based on multi-scale zooming learning framework. First, through the energy fully connected (energy FC) layer, the synchronous condenser feature components of the fault signal of the camera are learned, and the transient features of the signal are enhanced. At the same time, the data is adaptively compressed and the effective features are mapped in a distributed manner. The faults are effectively diagnosed and isolated in advance. Secondly, a multi-scale learning framework is constructed to learn the multi-frequency features in the vibration signal. Finally, experiments show that the proposed method has certain advantages over the existing excellent models. The accuracy rate of diagnosis is higher than 99%. [ABSTRACT FROM AUTHOR]

CNN extracts the signal characteristics layer by layer through the local perception of convolution kernel, but the rotation speed and sampling frequency of the vibration signal of rotating equipment are not the same. Extracting different signal features with a fixed convolution kernel will affect the local feature perception and ultimately affect the learning effect and recognition accuracy. In order to solve this problem, the matching between the size of convolution kernel and the signal (rotation speed, sampling frequency) was optimized with the matching relation obtained. Through the study of this paper, the ability of extracting vibration features of CNN was improved, and the accuracy of vibration state recognition was finally improved to 98%. [ABSTRACT FROM AUTHOR]