通过无人机采集光伏组件的图像后,利用小波尺度分解技术来增强图像的对比度和细节,重构无人机视觉巡航成像结果。为消除影响坏点定位准确性的噪声,采用中值滤波法对重构图像进行滤波,同时保留边缘信息和图像清晰度;使用门限二值化将图像中的背景和感兴趣区域进行分割;通过最大类间方差方法计算分割处理得到的背景和感兴趣区域的类间方差,能确定最优门限值,以此将感兴趣区域中的坏点范围单独提取出来;最后,为更加精确定位具体的坏点位置,引入改进的区域生长方法,通过设置生长阈值和梯度振幅门限,能有效定位光伏发电系统中存在的坏点位置。实验证明,所提方法对光伏发电坏点定位误差小,检测精准度高,能有效辅助维护电网安全。
Abstract
After collecting images of photovoltaic modules through drones, wavelet scale decomposition technology is used to enhance the contrast and details of the images, and the visual cruise imaging results of drones are reconstructed. In order to eliminate noise that affects the accuracy of bad point localization, the median filtering method is used to filter the reconstructed image, while preserving edge information and image clarity. Using threshold binarization to segment the background and regions of interest in the image. By using the maximum inter class variance method to calculate the inter class variance of the background and region of interest obtained from segmentation, the optimal threshold value can be determined, thereby extracting the range of bad points in the region of interest separately. Finally, in order to more accurately locate specific bad point locations, an improved region growth method was introduced. By setting growth thresholds and gradient amplitude thresholds, the bad point locations present in photovoltaic power generation systems can be effectively located. The experiment proves that the proposed method has small positioning error for photovoltaic power generation bad points, high detection accuracy, and can effectively assist in maintaining power grid security.
关键词
无人机 /
光伏发电 /
遥感 /
坏点定位 /
灰度均值
Key words
unmanned aerial vehicles /
PV power generation /
remote sensing /
bad point positioning /
mean grayscale
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 朱东垣, 孙一飞, 田有文. 含储能光伏电站并网运行可靠性评价仿真[J]. 计算机仿真, 2022, 39(10): 109-112, 165.
ZU D H, SUN Y F, TIAN Y W.Simulation of grid-connected operation reliability evaluation of photovoltaic power station including energy storage[J]. Computer simulation, 2022, 39(10): 109-112, 165.
[2] REZAEI J, GOLSHAN M E H, ALHELOU H H. Impacts of integration of very large-scale photovoltaic power plants on rotor angle and frequency stability of power system[J]. IET renewable power generation, 2022, 16(11): 2384-2401.
[3] ABRAMOVITZ A, SHMILOVITZ D.Short survey of architectures of photovoltaic arrays for solar power generation systems[J]. Energies, 2021, 14(16): 4917.
[4] HASSAN M A, AL-GHUSSAIN L, KHALIL A, et al.Self-calibrated hybrid weather forecasters for solar thermal and photovoltaic power plants[J]. Renewable energy, 2022, 188: 1120-1140.
[5] 高天龙, 刘卫亮, 张文军. 基于门控循环神经网络的光伏阵列故障识别与定位研究[J]. 热力发电, 2022, 51(3): 21-28.
GAO T L, LIU W L, ZHANG W J.Fault identification and location strategy of photovoltaic power station based on gated recurrent unit[J]. Thermal power generation, 2022, 51(3): 21-28.
[6] 那峙雄, 孙涛, 来广志, 等. 多尺度特征融合的光伏电站故障诊断[J]. 计算机工程与应用, 2022, 58(10): 300-308.
NA Z X, SUN T, LAI G Z, et al.Fault diagnosis for photovoltaic power station by multi-scale features fusion[J]. Computer engineering and applications, 2022, 58(10): 300-308.
[7] 姜萍, 王天亮, 栾艳军. 基于改进SSD的光伏组件故障定位检测[J]. 激光杂志, 2022, 43(5): 43-48.
JIANG P, WANG T L, LUAN Y J.Photovoltaic module fault location detection based on improved SSD[J]. Laser journal, 2022, 43(5): 43-48.
[8] 王涛, 林培杰, 周海芳, 等. 采用ELM和优化电压传感器布局的光伏阵列故障检测与区域定位[J]. 福州大学学报(自然科学版), 2022, 50(4): 475-482.
WANG T, LIN P J, ZHOU H F, et al.Fault detection and location for photovoltaic array using an optimal voltage sensor placement and extreme learning machine[J]. Journal of Fuzhou University (natural science edition), 2022, 50(4): 475-482.
[9] 张治, 马辉, 王林. 采用AFCM-SMOTE-RF的光伏电站故障诊断方法[J]. 电源技术, 2021, 45(11): 1495-1499.
ZHANG Z, MA H, WANG L.Fault diagnosis method of photovoltaic power station using AFCM-SMOTE-RF[J]. Chinese journal of power sources, 2021, 45(11): 1495-1499.
[10] ESCANDE P, WEISS P.Fast wavelet decomposition of linear operators through product-convolution expansions[J]. IMA journal of numerical analysis, 2022, 42(1): 569-596.
[11] 刘志清, 兰奇逊, 徐林, 等. 基于图像处理的光伏局部阴影区域分割方法[J]. 太阳能学报, 2023, 44(2): 391-398.
LIU Z Q, LAN Q X, XU L, et al.Partial shading region segmentation of photovoltaic systems based on image processing[J]. Acta energiae solaris sinica, 2023, 44(2): 391-398.
[12] SINGH A, GABA G S, HEDABOU M.Robust and effective image preprocessing conglomerate method for denoising of both grayscale and color images[J]. Journal of electronic imaging, 2022, 31: 041203.
[13] 陈世群, 杨耿杰, 高伟. 一种基于BOA-SAE-EELM的光伏阵列故障诊断方法[J]. 太阳能学报, 2022, 43(4): 154-161.
CHEN S Q, YANG G J, GAO W.A fault diagnosis method for photovoltaic array via BOA-SAE-EELM[J]. Acta energiae solaris sinica, 2022, 43(4): 154-161.
[14] VARMA G H K, BARRY V R, JAIN R K, et al. An MMTES algorithm for dynamic photovoltaic array reconfiguration to enhance power output under partial shading conditions[J]. IET renewable power generation, 2021, 15(4): 809-820.
[15] 王付胜, 陈韬, 窦盛, 等. 级联H桥光伏逆变器开关管开路故障诊断[J]. 太阳能学报, 2022, 43(5): 187-192.
WANG F S, CHEN T, DOU S, et al.Diagnosis of open-circuit fault of switch tube of cascaded H-bridge photovoltaic inverter[J]. Acta energiae solaris sinica, 2022, 43(5): 187-192.
[16] 张怀捷, 马静雅, 刘浩源, 等. 视觉与惯性融合的多旋翼飞行机器人室内定位技术[J]. 航空学报, 2023, 44(5): 292-304.
ZHANG H J, MA J Y, LIU H Y, et al.Indoor positioning technology of multi-rotor flying robot based on visual-inertial fusion[J]. Acta aeronautica et astronautica sinica, 2023, 44(5): 292-304.
[17] ETARHOUNI M, CHONG B, ZHANG L.A novel square algorithm for maximising the output power from a partially shaded photovoltaic array system[J]. Optik, 2022, 257: 168870.
基金
云南电网有限责任公司电力科学研究院云南电科院三维激光点云数据纠偏维护项目（056200MS62210003）
PDF(1393 KB)
