面向电力系统现场作业的安全风险管控智能检测算法  

Intelligent Detection Algorithm of Security Risk Management and Control for Power System On-site Operation

作　　者：何敏[1] 秦亮[1] 赵峰 余金沄 刘浩锋 王秋琳 徐兴华[4] 刘开培[1] HE Min;QIN Liang;ZHAO Feng;YU Jinyun;LIU Haofeng;WANG Qiulin;XU Xinghua;LIU Kaipei(School of Electrical and Automation,Wuhan University,Wuhan 430072,China;State Grid Information&Telecommunication Group Co.,Ltd.,Beijing 102211,China;Fujian Yirong Information Technology Co.,Ltd.,Fuzhou 35300,China;National Key Laboratory of Science&Technology on Vessel Integrated Power System,Naval University of Engineering,Wuhan 430034,China)

机构地区：[1]武汉大学电气与自动化学院,武汉430072 [2]国网信息通信产业集团有限公司,北京102211 [3]福建亿榕信息技术有限公司,福州35300 [4]海军工程大学舰船综合电力技术国防科技重点实验室,武汉430034

出　　处：《高电压技术》2023年第6期2442-2457,共16页High Voltage Engineering

基　　金：国家重点研发计划(2020YFB0905900)。

摘　　要：针对电力现场作业下的安全管控存在场景复杂、目标多样且部分遮挡而导致智能安全监测困难的问题,提出一种基于YOLOv7-Tiny的改进算法。首先,搭建了YOLOv7-Tiny检测网络,并在该算法框架中融合通道重组的注意力机制,从而有效提升通道之间的交互能力,增强复杂场景下目标区域的显著度;其次,在特征融合阶段,构建基于残差跳连的多尺度特征融合结构Res-PANet(Residual Path-Aggregation Network)来有效融合多尺度目标,提升场景中的多目标检测能力;同时,在模型的输出检测头中结合Swin-Transformer模块,提升模型的感受野,增强模型对特征图的全局感知,提高模型在部分遮挡情况下的检测能力;接着,在训练时采取改进的Mosaic数据增强方式,提升小目标的分布数量,达到丰富目标场景、提高模型泛化能力的目的;最后,以电力人员安全帽及安全服的穿戴、电力围栏以及电力警示牌为安全作业的监测对象进行改进算法的验证,同时采取基于Score-CAM的热力图分析进一步验证模型改进的有效性。实验结果表明:融合改进模型的平均检测精度达90.1%,图像检测速度为46帧/s,在嵌入式硬件Jetson NX上测试推理延时为75 ms,能有效满足电力安全现场检测精度和检测速度的要求。Aiming at the problem of complex scenes,diverse targets and difficulties in intelligent safety monitoring due to partial occlusion of safety control under power site operations,we propose an improved algorithm based on YOLOv7-Tiny.Firstly,the YOLOv7-Tiny detection network is built,and the attention mechanism of channel reorganization is fused in this algorithm framework to effectively improve the interaction ability between channels and to enhance the saliency of target regions in complex scenes.Secondly,in the feature fusion stage,Res-PANet,a multi-scale feature fusion structure based on residual hopping,is constructed to effectively fuse multi-scale targets and to improve the multi-target detection capability in the scene.At the same time,the Swin-Transformer module is combined in the output detection head of the model to enhance the perceptual field of the model,to achieve enhanced global perception of the feature map by the model,and to improve the detection ability of the model in the case of partial occlusion.Then,an improved Mosaic data enhancement is adopted during training to enhance the number of small target distributions,to achieve the purpose of enriching the target scenes,and to improve the generalization ability of the model.Finally,the wearing of safety helmets and safety clothing of electric personnel,electric fences and electric warning signs are taken as the monitoring objects of safety operations for the verification of the improvement algorithm,and the heat map analysis based on Score-CAM is also adopted to further verify the effectiveness of the model improvement.The experimental results show that the average detection accuracy of the fusion-improved model can reach 90.1%,the image detection speed is 46 frame/s,and the test inference delay is 75 ms on the embedded hardware Jetson NX,which can effectively meet the requirements of power safety field detection accuracy and detection speed.

关 键 词：电力安全 智能监测 YOLOv7-Tiny网络 Shuffle-Attention机制 目标遮挡检测 

分 类 号：TM08[电气工程—电工理论与新技术] TM73