Query：
学者姓名：关向雨
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
同步发电机运行过程中可能出现诸如转子偏心、匝间短路和静电荷等缺陷，危及电机的安全运行。在对不同缺陷下轴电压信号和机械振动信号非线性相关分析基础上，提出融合轴电压-振动特征和深度学习的同步发电机缺陷诊断方法。首先，搭建三相同步发电机缺陷物理模拟试验平台，获取不同工况和缺陷下轴电压信号和机械振动信号数据，采用核典型相关分析获取了轴电压信号和振动信号的相关系数；采用梅尔语谱进行轴电压和振动信号图谱预处理，采用并行双分支残差网络分别对轴电压和振动图谱的高维特征进行提取，并采用双线性池化算法对不同模态的高维特征进行融合，在此基础上构建了融合轴电压-振动特征的同步发电机缺陷分类模型。结果表明：轴电压信号和同步电机本体振动信号关联度在故障和正常情况下均超过0.9,所提出的轴电压-振动联合诊断模型在测试集上的准确度、漏报率和误报率等性能方面优于单一轴电压和单一振动诊断算法。本文工作旨在通过监测和分析发电机的运行状态，及时识别潜在故障，提高发电机的运行可靠性。
Keyword ：
信息融合 信息融合 并行双分支残差网络 并行双分支残差网络 故障诊断 故障诊断 机械振动 机械振动 相关分析 相关分析 轴电压 轴电压
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张杭 , 关向雨 , 廖景雯 et al. 融合轴电压-振动特征的同步电机缺陷诊断 [J]. | 电机与控制学报 , 2025 , 29 (07) : 53-62 . |
| MLA | 张杭 et al. "融合轴电压-振动特征的同步电机缺陷诊断" . | 电机与控制学报 29 . 07 (2025) : 53-62 . |
| APA | 张杭 , 关向雨 , 廖景雯 , 徐欣灵 , 陈晓坤 . 融合轴电压-振动特征的同步电机缺陷诊断 . | 电机与控制学报 , 2025 , 29 (07) , 53-62 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为实现不同电工材料表面机械振动的非接触测量,搭建了全光纤 1 550 nm激光多普勒测振(LDV)系统,针对不同电工材料表面粗糙度对反射光的影响以及 IQ 信号不平衡因子对解调波形的影响,提出一种融合材料表面粗糙度光学补偿和正交解调补偿的综合补偿算法.首先基于射线光学分析不同电工材料表面粗糙度对收发一体光学镜头耦合效率的影响,提出采用平凹-凹凹-平凸透镜方案的光学天线前端补偿算法.分析了 IQ信号幅相不平衡对解调结果的影响,通过镜像抑制算法消除该影响,建立不平衡模型验证补偿算法的有效性.搭建了不同电工材料标定平台和气体绝缘开关(GIS)设备振动平台,对所提出的光学和信号补偿算法进行验证.结果表明,该文所提光学补偿方法使不同电工材料表面的激光平均耦合效率提高了 21.92%,信号补偿前的解调信号存在 25.04 dB 的镜像干扰比率(IIR),经过 IQ 信号补偿后,信号的信噪比提高了25.8 dB.验证了所研发的系统能够应用于不同电工设备表面 3～10 m 距离和 10 Hz～2 kHz 频率范围机械振动的无损带电检测.
Keyword ：
光学天线 光学天线 射线光学仿真 射线光学仿真 正交解调补偿 正交解调补偿 激光多普勒测振 激光多普勒测振
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 赖泽楷 , 关向雨 , 涂嘉毅 et al. 基于激光多普勒测振的电力设备表面振动测量及补偿算法 [J]. | 电工技术学报 , 2025 , 40 (6) : 1707-1717 . |
| MLA | 赖泽楷 et al. "基于激光多普勒测振的电力设备表面振动测量及补偿算法" . | 电工技术学报 40 . 6 (2025) : 1707-1717 . |
| APA | 赖泽楷 , 关向雨 , 涂嘉毅 , 林建港 , 徐欣灵 . 基于激光多普勒测振的电力设备表面振动测量及补偿算法 . | 电工技术学报 , 2025 , 40 (6) , 1707-1717 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Compared with a traditional distribution transformer with silicon steel sheet as the core material, the no-load loss of an amorphous alloy transformer is greatly reduced due to its core using iron-based amorphous metal material, which has been applied in many countries. However, due to the brittleness of its amorphous strip, an amorphous alloy transformer is prone to debris in the process of production, transportation and work. The charge and migration characteristics of these debris will reduce the insulation strength of the transformer oil and endanger the safe operation of the transformer. In this paper, a charge measurement platform of amorphous alloy debris is set up, and the charging characteristics of amorphous alloy core debris under different flow velocities, particle radius and plate electric field strength are obtained. The results show that with an increase in pipeline flow velocity, the charge-to-mass ratio of the debris increases first and then decreases. With an increase in electric field strength, the charge-to-mass ratio of the debris increases; with an increase in the number of debris, the charge-to-mass ratio of the debris decreases; with an increase in debris size, the charge-to-mass ratio of the debris increases. The debris with different charge-to-mass ratios and types obtained from the above experiments are added to the simulation model of an amorphous alloy transformer. The lattice Boltzmann method (LBM) coupled with the discrete element method (DEM) is used to simulate the migration process of metal particles in an amorphous alloy transformer under the combined action of gravity, buoyancy, electric field force and oil flow resistance under electrothermal excitation boundary. The results show that the trajectory of the debris is related to the initial position, electric field strength and oil flow velocity. The LBM-DEM calculation model and charge measurement platform proposed in this paper can provide a reference for studying the charge mechanism and migration characteristics of amorphous alloy core debris in insulating oil.
Keyword ：
amorphous alloy core debris amorphous alloy core debris charge characteristics charge characteristics discrete element method discrete element method lattice Boltzmann method lattice Boltzmann method migration characteristic migration characteristic
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yu, Wenxu , Guan, Xiangyu . Study on the Charge Characteristics and Migration Characteristics of Amorphous Alloy Core Debris [J]. | MATERIALS , 2025 , 18 (18) . |
| MLA | Yu, Wenxu et al. "Study on the Charge Characteristics and Migration Characteristics of Amorphous Alloy Core Debris" . | MATERIALS 18 . 18 (2025) . |
| APA | Yu, Wenxu , Guan, Xiangyu . Study on the Charge Characteristics and Migration Characteristics of Amorphous Alloy Core Debris . | MATERIALS , 2025 , 18 (18) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The fault characteristics of photovoltaic (PV) systems are greatly influenced by environmental factors, which causes grand challenges in PV fault detection. Therefore, this paper proposes an anomaly detection algorithm for grid-connected PV system via anomaly-transformer. Firstly, a PV platform was built to carry out fault experiments under different meteorological conditions, and a total of 218 sets of DC voltage/current datasets were constructed. Aiming at the characteristics of multi-dimensional time series data, the multi-branch anomaly-attention mechanism is used to calculate prior-association and series-association, then use transformer to reconstruct the loss values based on the obtained data. The association discrepancy is calculated as the index of anomaly detection, so as to achieve the goal of time-based localization of PV faults. The experimental results show that compared with graph deviation network (GDN), unsupervised anomaly detection (USAD) and other algorithms, the Precision of anomaly-transformer reaches 76.45% and 95.41% respectively in sunny and cloudy test data sets, and the F1-score reaches 86.65% and 97.65% respectively. It can accurately locate the fault time, which provides an effective method for PV fault detection. © Beijing Paike Culture Commu. Co., Ltd. 2024.
Keyword ：
Anomaly detection Anomaly detection Deep learning Deep learning Electric transformer testing Electric transformer testing Fault detection Fault detection Timing circuits Timing circuits
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fu, Xiaoying , Jiang, Wujie , Zhang, Yanfeng et al. Fault Detection for Grid-Connected Photovoltaic System via Anomaly-Transformer Technique [C] . 2024 : 59-67 . |
| MLA | Fu, Xiaoying et al. "Fault Detection for Grid-Connected Photovoltaic System via Anomaly-Transformer Technique" . (2024) : 59-67 . |
| APA | Fu, Xiaoying , Jiang, Wujie , Zhang, Yanfeng , Xiong, Hengping , Guan, Xiangyu . Fault Detection for Grid-Connected Photovoltaic System via Anomaly-Transformer Technique . (2024) : 59-67 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Abnormal conditions of field photovoltaic (PV) array such as open-circuit, short-circuit, and partial shading are embedded in DC side voltage/current curves. Besides, meteorological factors as solar radiation, wind speed, and ambient temperature can also influence fault behaviors. To realize abnormal identify of PV array under environmental interference, this paper presents a graph attention network (GAT) based fault detection algorithm for PV array. Fault simulation experiments are conducted on grid-connected PV array, and the voltage/current curves of the PV DC side under different states (normal, open-circuit, short-circuit, and partial shading) were collected to build dataset. One-dimensional convolution and two parallel graph attention layers are adopted to extract temporal and dimensional features of the voltage/current series. A gated recurrent unit (GRU) is employed to capture the long-term dependencies of the time-series data. Fully connected (FC) layers and variational auto-encoder (VAE) are combined optimized for detecting and locating the PV abnormal events. Model performance are compared with Robust Anomaly Detection (OmniAnomaly), Transformer Networks for Anomaly Detection (TranAD), and Long Short-Term Memory (LSTM), result show that the proposed grid-connected PV array fault detection model achieves an accuracy of 96.8% on the test dataset, providing an effective method for fault diagnosis of grid-connected PV systems under different meteorological conditions. © Beijing Paike Culture Commu. Co., Ltd. 2024.
Keyword ：
Anomaly detection Anomaly detection Fault detection Fault detection Feature extraction Feature extraction Long short-term memory Long short-term memory Statistical tests Statistical tests Time series Time series Wind Wind
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jiang, Wujie , Fu, Xiaoying , Zhang, Yanfeng et al. Anomaly Detection for Grid-Connected Photovoltaic Array via Graph Attention Mechanism [C] . 2024 : 759-769 . |
| MLA | Jiang, Wujie et al. "Anomaly Detection for Grid-Connected Photovoltaic Array via Graph Attention Mechanism" . (2024) : 759-769 . |
| APA | Jiang, Wujie , Fu, Xiaoying , Zhang, Yanfeng , Xiong, Hengping , Wen, Yihan , Guan, Xiangyu . Anomaly Detection for Grid-Connected Photovoltaic Array via Graph Attention Mechanism . (2024) : 759-769 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
High quality 3D reconstruction technique is essential for digital twin (DT) application of power equipment. This work presents a PointNet-MLS combined architecture to realize component segmentation and surface reconstruction of gas insulated switchgear (GIS) with complex background interference. In order to make the GIS ontology point cloud obtained continuous and smooth, greedy projection triangulation is then applied. Lastly, the local features of the GIS point cloud are enhanced, and the three-dimensional geometric properties of the GIS apparatus are better restored using the moving least squares approach. The results show that the mean intersection over union (mIoU) of PointNet++ algorithm for on-site GIS point cloud segmentation can reach 92.1%, which is higher than 32.8% and 13.7% of K-means and PointNet algorithms, respectively. The proposed MLS algorithm can effectively repair the defects of GIS point cloud after greedy projection triangulation, so that the repaired surface part can maintain the three-dimensional shape characteristics of the GIS point cloud. © 2024, Beijing Paike Culture Commu. Co., Ltd.
Keyword ：
Electric switchgear Electric switchgear Image reconstruction Image reconstruction Surface reconstruction Surface reconstruction Triangulation Triangulation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lv, Chaowei , Guan, Xiangyu , Liu, Jiang et al. 3-D Segmentation and Surface Reconstruction of Gas Insulated Switchgear via PointNet-MLS Architecture [C] . 2024 : 187-193 . |
| MLA | Lv, Chaowei et al. "3-D Segmentation and Surface Reconstruction of Gas Insulated Switchgear via PointNet-MLS Architecture" . (2024) : 187-193 . |
| APA | Lv, Chaowei , Guan, Xiangyu , Liu, Jiang , Liao, Jingwen . 3-D Segmentation and Surface Reconstruction of Gas Insulated Switchgear via PointNet-MLS Architecture . (2024) : 187-193 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
振动测量对发现气体绝缘开关设备(gas insulated switchgear，GIS)潜在性缺陷具有重要意义，但GIS本体振动信号易受基础振动、测量噪声以及环境噪声的影响，使得现场GIS振动带电检测和机械缺陷诊断的效果较差。针对此问题，提出一种基于奇异值分解(singular value decomposition, SVD)-改进自适应啁啾模态分解(improve adaptive chirp mode decomposition, IACMD)的现场振动信号降噪算法。该方法首先利用SVD对原始振动信号进行预处理，滤除低频基础振动和测量噪声，其次利用鱼鹰优化算法(osprey optimization algorithm, OOA)对处理后的信号进行自适应模态分解，得到分解后的固有模态(intrinsic mode functions，IMF)分量，再利用互相关系数筛选有效分量重构振动信号。模拟信号与现场信号测试结果表明：与OOA-自适应啁啾模态分解(adaptive chirp mode decomposition，ACMD)和SVD-变分模态分解(variational mode decomposition, VMD)相比，所提出的SVD-IACMD算法可以去除基础振动、测量噪声和环境噪声，保留GIS本体振动的基频和谐波分量，为GIS现场抗干扰振动检测和机械缺陷诊断提供技术支持。
Keyword ：
信号降噪 信号降噪 奇异值分解(SVD) 奇异值分解(SVD) 改进自适应啁啾模态分解(IACMD) 改进自适应啁啾模态分解(IACMD) 机械振动 机械振动 气体绝缘开关设备(GIS) 气体绝缘开关设备(GIS) 鱼鹰优化算法(OOA) 鱼鹰优化算法(OOA)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 涂嘉毅 , 关向雨 , 赵俊义 et al. 基于SVD-IACMD的GIS振动信号去噪算法 [J]. | 电力工程技术 , 2024 , 43 (6) : 163-172 . |
| MLA | 涂嘉毅 et al. "基于SVD-IACMD的GIS振动信号去噪算法" . | 电力工程技术 43 . 6 (2024) : 163-172 . |
| APA | 涂嘉毅 , 关向雨 , 赵俊义 , 林建港 , 赖泽楷 . 基于SVD-IACMD的GIS振动信号去噪算法 . | 电力工程技术 , 2024 , 43 (6) , 163-172 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为获取交变电磁力作用下气体绝缘封闭金属开关设备(GIS)内部导体与外壳之间机械振动的传递和分布特性,该文采用结构声强法构建了 GIS振动能量流动的可视化模型.通过电磁-结构多场耦合方法构建了工频电流激励下的GIS振动功率流模型,并进行了物理模拟试验验证.应用所构建的GIS功率流模型提取了微元的应力张量及速度结果,进而求解了振动能量流的空间分量,并采用空间向量和流线合成的方法实现了 GIS腔体振动能量流动的可视化呈现.对比了触头正常接触和触指缺失缺陷下的GIS腔体振动能量流动特性的差异,结果表明,相比于接触正常状态,在触头接触缺陷状态下,总输入功率流100 Hz与200 Hz分量分别从6.64x10-6W和4.81×10-6 W下降到6.35×10-6 W和4.55×10-6 W,使得外壳振动信号基频幅值比接触正常状态下减小6.25％.分析结果对于开展基于振动检测的GIS机械缺陷诊断提供了技术支持.
Keyword ：
功率流 功率流 振动 振动 气体绝缘设备 气体绝缘设备 结构声强法 结构声强法 触头 触头
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 王扬程 , 关向雨 , 陈志鹏 et al. 基于结构声强法的GIS机械振动传递特性 [J]. | 电工技术学报 , 2024 , 39 (16) : 5162-5171 . |
| MLA | 王扬程 et al. "基于结构声强法的GIS机械振动传递特性" . | 电工技术学报 39 . 16 (2024) : 5162-5171 . |
| APA | 王扬程 , 关向雨 , 陈志鹏 , 林建港 , 赵俊义 . 基于结构声强法的GIS机械振动传递特性 . | 电工技术学报 , 2024 , 39 (16) , 5162-5171 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
传统的激光测振仪多使用氦氖激光器,不满足人眼安全条件,在户外容易受到太阳光干扰.其使用的光学天线大多数仅能工作于氦氖激光器的辐射波段,同时存在结构复杂、成本较高、收集效率低、工作距离较短等不足.为了解决以上问题,基于近红外波段透镜组的扩束和聚焦原理,以Zemax作为设计工具,以点列图和波前图为主要分析手段,设计并制作了一款可工作于1 550 nm的三片式收发一体光学天线,结构简单,成本低.分析结果显示:在0.3～15.0 m的工作距离范围内均可获得直径小于2mm的聚焦光斑;测试结果显示其最大收集效率可达到51.6%.同时,将该光学天线应用于自主设计搭建的激光多普勒测振仪中,实现了不同工作距离下的振动测量,有效扩展了激光测振仪的应用范围和应用场景,在机械、航空、建筑、医学、农学等领域有很大的应用潜力.
Keyword ：
Zemax Zemax 扩束聚焦镜 扩束聚焦镜 激光多普勒测振仪 激光多普勒测振仪
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 郑帅君 , 谢涛 , 马赛 et al. 激光多普勒测振仪中光学天线的优化设计与测试 [J]. | 武汉工程大学学报 , 2024 , 46 (4) : 431-438 . |
| MLA | 郑帅君 et al. "激光多普勒测振仪中光学天线的优化设计与测试" . | 武汉工程大学学报 46 . 4 (2024) : 431-438 . |
| APA | 郑帅君 , 谢涛 , 马赛 , 张余豪 , 张聪 , 关向雨 et al. 激光多普勒测振仪中光学天线的优化设计与测试 . | 武汉工程大学学报 , 2024 , 46 (4) , 431-438 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对气体绝缘组合电器(Gas Insulated Switchgear,GIS)红外巡检中图像对比度低、易受道路等背景辐射干扰,各组件温升差异难以直接提取的不足,提出了基于多光谱语义分割和目标检测的GIS各组件红外特征智能识别算法.采用红外-可见光双光谱成像系统,构建了现场变电站GIS的红外和可见光多光谱数据集;基于MF-net多光谱语义分割框架,采用双分支编码器分别提取GIS外壳红外和可见光特征信息,进而在译码器上实现多光谱特征融合和GIS本体红外图像分割,从而排除了环境背景辐射对GIS组件识别和温升特性提取的影响;将分割后的GIS本体红外图像进行主母线、分支母线、互感器、断路器和隔离开关等组件标记,随后采用YOLOv4算法实现对GIS不同组件的识别.结果表明与未进行语义分割GIS红外组件识别模型相比,所提出模型可以达84.2％平均识别准确率,其中电流互感器精确度达93.68％、断路器精确度达92.68％、召回率达96.20％和F1值得分0.94,GIS组件温升识别能够去除道路等高辐射背景对测温结果干扰,对提高户外GIS设备温升红外热成像的结果可靠性和智能化具有应用价值.
Keyword ：
GIS GIS MFNet MFNet YOLOv4 YOLOv4 可见光图像 可见光图像 红外图像 红外图像 语义分割 语义分割
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 王炜斌 , 林熠 , 刘江 et al. 基于多光谱语义分割的GIS组件红外特征识别方法 [J]. | 电气开关 , 2024 , 62 (2) : 37-42,47 . |
| MLA | 王炜斌 et al. "基于多光谱语义分割的GIS组件红外特征识别方法" . | 电气开关 62 . 2 (2024) : 37-42,47 . |
| APA | 王炜斌 , 林熠 , 刘江 , 关向雨 . 基于多光谱语义分割的GIS组件红外特征识别方法 . | 电气开关 , 2024 , 62 (2) , 37-42,47 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
