To address the issue of inconsistent image quality and data scarcity in bolt defect detection for transmission lines,this paper proposes an improved sparse region-based convolutional neural network(RCNN) based detecti...To address the issue of inconsistent image quality and data scarcity in bolt defect detection for transmission lines,this paper proposes an improved sparse region-based convolutional neural network(RCNN) based detection framework integrating image quality evaluation and text-to-image data augmentation.First,a HyperNetwork-based image quality assessment module is introduced to filter low-quality inspection images in terms of clarity and structural integrity,resulting in a high-quality training dataset.Second,a text-to-image diffusion model is utilized for sample augmentation.By designing text prompts that describe various bolt defect types under diverse lighting and viewing conditions,the model automatically generates realistic synthetic samples.The generated images are further filtered using a combination of quality and perceptual similarity metrics to ensure consistency with the real data distribution.Building upon the sparse RCNN baseline,a dynamic label assignment mechanism and a random decision path detection head are incorporated to enhance bounding box matching and prediction accuracy.Experimental results demonstrate that the proposed method significantly improves detection accuracy(mAP@0.5) over the original sparse RCNN while maintaining low computational cost,enabling more efficient and intelligent inspection of transmission line components.展开更多
该文针对质子交换膜(proton exchange membrane,PEM)电解槽负荷安全快速响应电力系统频率控制难题,提出考虑氧中氢含量的PEM电解槽非线性频率动态响应控制策略。首先,基于质量守恒方程、能量守恒方程、阴阳极压强方程以及小室U-I方程建...该文针对质子交换膜(proton exchange membrane,PEM)电解槽负荷安全快速响应电力系统频率控制难题,提出考虑氧中氢含量的PEM电解槽非线性频率动态响应控制策略。首先,基于质量守恒方程、能量守恒方程、阴阳极压强方程以及小室U-I方程建立PEM电解槽一维机理动态模型,得到电解槽阳极氧中氢含量的数学解析模型;其次,基于全息目标反馈非线性频率响应控制(nonlinear control with objectiveholographicfeedbacks,NCOHF)理论,提出考虑氧中氢含量的PEM电解槽频率响应策略;最后,利用25%风电渗透率的4机2区仿真系统在负荷阶跃及风电功率波动工况进行频率响应分析,验证该文方法相较于传统下垂、加速下垂和频率变化率控制在频率动态响应方面的优越性。展开更多
A distributed energy management in a photovoltaic charging station(PV-CS) is proposed on the basis of different behavioural responses of electric vehicle(EV) drivers. On the basis of the provider or the consumer of th...A distributed energy management in a photovoltaic charging station(PV-CS) is proposed on the basis of different behavioural responses of electric vehicle(EV) drivers. On the basis of the provider or the consumer of the power, charging station and EVs have been modeled as independent players with different preferences. Because of the selfish behaviour of the individuals and their hierarchies, the power distribution problem is modeled as a noncooperative Stackelberg game. Moreover, Karush-Kuhn-Tucker(KKT) conditions and the most socially stable equilibrium are adopted to solve the problem in hand. The consensus network, a learning-based algorithm, is utilized to let the EVs communicate and update their own charging power in a distributed fashion. Simulation analysis is supported to show the static and dynamic responses as well as the effectiveness and workability of the proposed charging power management. For the sake of showing the responses of EV drivers, different behavioural responses of EVs’ drivers to the discount on the charging price offered by the station are introduced. The simulation results show the effectiveness of the proposed energy management.展开更多
基金Supported by the Science and Technology Project from State Grid Corporation of China (No.5700-202490330A-2-1-ZX)。
摘要To address the issue of inconsistent image quality and data scarcity in bolt defect detection for transmission lines,this paper proposes an improved sparse region-based convolutional neural network(RCNN) based detection framework integrating image quality evaluation and text-to-image data augmentation.First,a HyperNetwork-based image quality assessment module is introduced to filter low-quality inspection images in terms of clarity and structural integrity,resulting in a high-quality training dataset.Second,a text-to-image diffusion model is utilized for sample augmentation.By designing text prompts that describe various bolt defect types under diverse lighting and viewing conditions,the model automatically generates realistic synthetic samples.The generated images are further filtered using a combination of quality and perceptual similarity metrics to ensure consistency with the real data distribution.Building upon the sparse RCNN baseline,a dynamic label assignment mechanism and a random decision path detection head are incorporated to enhance bounding box matching and prediction accuracy.Experimental results demonstrate that the proposed method significantly improves detection accuracy(mAP@0.5) over the original sparse RCNN while maintaining low computational cost,enabling more efficient and intelligent inspection of transmission line components.
摘要该文针对质子交换膜(proton exchange membrane,PEM)电解槽负荷安全快速响应电力系统频率控制难题,提出考虑氧中氢含量的PEM电解槽非线性频率动态响应控制策略。首先,基于质量守恒方程、能量守恒方程、阴阳极压强方程以及小室U-I方程建立PEM电解槽一维机理动态模型,得到电解槽阳极氧中氢含量的数学解析模型;其次,基于全息目标反馈非线性频率响应控制(nonlinear control with objectiveholographicfeedbacks,NCOHF)理论,提出考虑氧中氢含量的PEM电解槽频率响应策略;最后,利用25%风电渗透率的4机2区仿真系统在负荷阶跃及风电功率波动工况进行频率响应分析,验证该文方法相较于传统下垂、加速下垂和频率变化率控制在频率动态响应方面的优越性。
基金the Technology Projects of China State Grid Corporation(No.SGJS0000YXJS1800187)
摘要A distributed energy management in a photovoltaic charging station(PV-CS) is proposed on the basis of different behavioural responses of electric vehicle(EV) drivers. On the basis of the provider or the consumer of the power, charging station and EVs have been modeled as independent players with different preferences. Because of the selfish behaviour of the individuals and their hierarchies, the power distribution problem is modeled as a noncooperative Stackelberg game. Moreover, Karush-Kuhn-Tucker(KKT) conditions and the most socially stable equilibrium are adopted to solve the problem in hand. The consensus network, a learning-based algorithm, is utilized to let the EVs communicate and update their own charging power in a distributed fashion. Simulation analysis is supported to show the static and dynamic responses as well as the effectiveness and workability of the proposed charging power management. For the sake of showing the responses of EV drivers, different behavioural responses of EVs’ drivers to the discount on the charging price offered by the station are introduced. The simulation results show the effectiveness of the proposed energy management.