In the daily maintenance process of substation, the defect detection of substation equipment is a critical problem. This task is challenging considering of the variety of defects, the rarely sample of various defects ...
详细信息
ISBN:
(纸本)9781665426480
In the daily maintenance process of substation, the defect detection of substation equipment is a critical problem. This task is challenging considering of the variety of defects, the rarely sample of various defects and the complex environment. This paper presents a flow-appearance fusion defect detection method for substation equipment in multiple scenes, which contains a Siamese optical flow module and a defect location module. The Siamese optical flow module is a pretrained optical flow network, which is utilized to obtain forward and backward optical flow between the normal image and the detect image. The optical flow represents the common changing features of different types of defects in multiple scenes. The defect location module utilizes MI-darknet53 to realize the extraction and fusion of appearance and flow features. Then the extracted multiscale features are used to build the feature pyramid network (FPN), which combines semantic defect information in high level and geometric defect information in low level. Finally, FPN is utilized to predict object-level defect areas in three different scales. Experiments show that our proposed method has good reliability and superior performance in the defect detection for the dataset of multi-scene substation equipment.
Light gas protection only operates when gas within the transformer collection chamber reaches threshold volume. Such criterion failed to reflect transformer conditions accurately due to the lack of understanding for d...
详细信息
ISBN:
(纸本)9781665400657
Light gas protection only operates when gas within the transformer collection chamber reaches threshold volume. Such criterion failed to reflect transformer conditions accurately due to the lack of understanding for defect developing process and corresponding gas generation- convergence pattern, which has led to lower protection reliability and has caused several transformer explosions. To address current problem, an experimental tank with structure resembling that of a power transformer is set up, inside which the needle-plate oil-pressboard breakdown model is planted. Experimental results indicate that throughout fault development, voltage drops became more frequent until arcing occurs, so is HFCT signal; meanwhile gas generation rate increases through slight partial discharge, spark discharge and arcing stage, the collected gas volume corresponds with patterns above. The purpose of this study is to clarify the defect developing process and the gas generation-convergence pattern for oil-immersed transformer internal fault in guidance for a more reliable protection method.
Due to the continuous improvement of new energy penetration, grid-forming control has become a hot issue in grid-connected technology. grid-forming control simulates the mechanical and electrical transient characteris...
详细信息
ISBN:
(纸本)9781665414401
Due to the continuous improvement of new energy penetration, grid-forming control has become a hot issue in grid-connected technology. grid-forming control simulates the mechanical and electrical transient characteristics of the synchronous unit. The power or load using the converter has the inertia, damping, frequency and voltage adjustment, and other operating characteristics of the synchronous unit machine technology. This paper introduces the development process and basic concept of grid-forming control. It introduces the application of grid-forming control from three aspects of grid connection, frequency modulation, and virtual inertia. This paper focuses on the current problems of grid-forming control, such as control parameter tuning, power oscillation, and parallel grid-forming control circulation. At the same time, the prospect of research direction is put forward given the above problems.
With the increasing demand for the renewable energy, the stability of the multi-paralleled grid-connected inverters is the important factor for evaluation the capacity of the inverters connected to power grid. In this...
详细信息
ISBN:
(纸本)9781665414401
With the increasing demand for the renewable energy, the stability of the multi-paralleled grid-connected inverters is the important factor for evaluation the capacity of the inverters connected to power grid. In this paper the maximum capacity assessment for multi-paralleled grid-connected inverters using global-admittance based harmonic stability analysis is proposed. The stability analysis method with global admittance has clear physical concept and is convenient for real-time analysis and calculation. The global admittance method is illustrated first. The inverters are sorted by the capacity. The inverters sequence can be divided into two groups based on the stable critical point obtained by the global admittance method. The group with large capacity is taken as a unit. The stability of the combinations formed by this unit and other inverters in the other group is analyzed further. So the maximum capacity of the grid-connected inverters can be assessed. The application example is used to illustrate and verify the proposed method in this paper.
The anomaly detection for substation equipment is of great significance to maintain the safe operation of substations. With the development of deep learning, many anomaly detection methods based on deep convolutional ...
详细信息
ISBN:
(纸本)9781665426480
The anomaly detection for substation equipment is of great significance to maintain the safe operation of substations. With the development of deep learning, many anomaly detection methods based on deep convolutional neural networks (CNN) have been proposed. However, the challenge lies in the diversity of the environment and the variety of anomaly types in the substation. This paper proposes a Flow- Guided Anomaly Detection Method, which contains a data augmentation module and a flow-guided feature fusion module. The data augmentation module utilizes CycleGAN to transfer the style of the images to adapt to changing scenarios, such as different illumination and season conditions. The flow-guided feature fusion module extracts the optical flow between the test image and the template image by a pre-trained FlowNet, which represents the change information between the image pair and is universal for different anomaly types. Then the appearance information and change information of the image are aggregated to obtain the fused feature, which contains more semantic information. Finally, the fused feature is utilized to accurately detect a wider range of abnormal types. Experiments show that our proposed method has superior performance in anomaly detection for substation equipment and is more robust to changing scenarios.
Power semiconductor devices are the essential core components of modern power electronic equipment. Predicting the remaining useful life (RUL) of power semiconductor devices can help formulate reasonable maintenance s...
Power semiconductor devices are the essential core components of modern power electronic equipment. Predicting the remaining useful life (RUL) of power semiconductor devices can help formulate reasonable maintenance strategies for power electronic equipment, thereby improving the availability of energy conversion systems. This article proposes a deep learning method for predicting the RUL of power semiconductor devices, which uses on-state resistance as a critical state parameter. A long short-term memory (LSTM) neural network (NN) model and a convolutional neural network (CNN) model are used to predict the on-state resistance time series data trend. NN models can predict a short section of future data with past data input. The RUL of power semiconductor devices is estimated through curve fitting based on past and predictive data. The proposed method is validated using the power MOSFET accelerated aging dataset from NASA, and the validation results show that the performance of the proposed method is superior to that of existing methods, such as extended Kalman filtering (EKF) and particle filtering (PF).
The high proportion of renewable energy into the power grid, say, the large-scale wind power generation connected to the power grid, is the key approach to achieve the clean and low-carbon energy transition. Under the...
详细信息
ISBN:
(数字)9781728191645
ISBN:
(纸本)9781728191652
The high proportion of renewable energy into the power grid, say, the large-scale wind power generation connected to the power grid, is the key approach to achieve the clean and low-carbon energy transition. Under the premise of ensuring power grid's safe and stable operation, it is necessary to study the influence of wind power capacity expansion on the transient angle stability (TAS). Aiming at several typical dominant modes in Qinghai power system, which holds many new energy resources, the sensitivity of wind power capacity expansion in different locations to the TAS, as well as its key influence factors and feasible explanations, are explored. It may lay the foundation of the location optimization of wind power capacity expansion.
With the development of distributed power generation technologies, parallel operations of virtual synchronous generators (VSGs) and synchronous generators (SGs) become increasingly common in a microgrid. Due to the lo...
详细信息
ISBN:
(纸本)9781665434263
With the development of distributed power generation technologies, parallel operations of virtual synchronous generators (VSGs) and synchronous generators (SGs) become increasingly common in a microgrid. Due to the low overcurrent capacity of VSGs, fault ride-through (FRT) is necessary for microgrids, which makes the transient stability of SG-VSG-based microgrids be different from the traditional power system. In this paper, a new abnormal overcurrent phenomenon caused by FRT is discovered in SG-VSG-based islanded microgrids. Then, characteristics of the output current of the VSG which uses different parameters are compared and analyzed. Furthermore, an optimized FRT method is proposed, which suppresses the abnormal overcurrent. Finally, a simulation is performed to verify the effectiveness of the proposed method on the PSCAD/EMTDC.
This paper proposes a Risk-Averse Just-In-Time (RAJIT) operation scheme for Ammonia-Hydrogen-based Micro-grids (AHMGs) to boost electricity-hydrogen-ammonia coupling under uncertainties. First, an off-grid AHMG model ...
详细信息
This paper analyzes the negative-sequence network diagram of stepped controllable shunt reactor (SCSR) in case of turn-to-turn short-circuit fault and turn-to-ground fault of the SCSR control winding, as well as the l...
详细信息
暂无评论