摘要
新型电力系统高比例新能源接入以及“双碳”目标的实施,推动了光伏产业的高速发展,我国光伏装机容量已位居世界前列。针对视频巡检面临的卡顿、故障识别精度不足、数据处理速度无法满足高精度快速故障识别需求的问题,文章提出基于高精度快速故障识别的智能光伏视频巡检技术,通过视频巡检数据传输抗干扰、弹性计算资源分配以及故障识别算法优化,全方位提高故障识别的精度与速度。在此基础上构建了智能光伏视频巡检系统,实现光伏电站全天候、全方位智能监测,与基于并行调度和复杂神经网络的巡检系统相比,传输速率增加了97.20%和85.18%,视频流处理时延降低40.16%和23.78%,识别蜗牛纹故障的精度增加了22.12%和8.77%,全面提高识别精度的同时,实现巡检数据的可靠传输与高效快速处理,提升了巡检的有效性、安全性和可靠性。
The integration of high proportional new energy to a new type power systems and the implementation of the"double carbon"goal have promoted the rapid development of the photovoltaic industry.Currently,China's photovoltaic installation capacity has ranked in the forefront of the world.Facing challenges of transmission jamming,insufficient fault identification precision,and low data processing speed that cannot meet the requirements of high precision and fast fault identification,this paper proposes an intelligent photovoltaic video inspection technology with high precision and fast fault identification.It comprehensively improves fault identification precision and speed with the combined power of anti-interference inspection data transmission,flexible computing resource allocation,and fault identification algorithm optimization.On this basis,an intelligent photovoltaic video inspection system is constructed to realize all-weather and all-round intelligent monitoring of photovoltaic power stations.Compared with the inspection system based on parallel scheduling and complex neural network,the proposed video inspection system increases transmission rate by 97.20%and 85.18%,reduces video stream processing delay by 40.16%and 23.78%,and improves the identification precision of snail stripe fault by 22.12%and 8.77%.The intelligent photovoltaic video inspection system with high precision and fast fault identification can substantially improve identification precision,realize reliable transmission and fast processing of inspection data,and improve inspection efficiency,security,and reliability.
作者
张永伟
李贵
马玉权
汪海波
ZHANG Yongwei;LI Gui;MA Yuquan;WANG Haibo(Guohua Bayannur Wind Power Co.,Ltd.,Bayannur 015321,Inner Mongolia Autonomous Region,China)
出处
《电力信息与通信技术》
2023年第6期73-78,共6页
Electric Power Information and Communication Technology
关键词
光伏电站
智能光伏视频巡检系统
新型电力系统
高精度快速故障识别
photovoltaic power station
intelligent photovoltaic video inspection system
new type power systems
fast-precision and fast fault identification
