摘要
针对架空输电线路垂度的监测与估计,现有方法对传感器数量要求较高且估计精度较低,基于此,文章提出一种基于最优智能传感配置与机器学习的输电线路垂度监测与估计方法。首先,基于线性整数规划的最优智能传感配置方法,将传统点测量系统的传感器数量减少50%,且不影响系统监测数据的准确性;然后,构建最小二乘(Least Squares,LS)估计模型,且将LS的估计值输入支持向量机进行输电线路垂度估计,进一步提高所提方法的估计准确率;最后,在PLS-CADD软件中对垂度和张力进行仿真,验证所提方法性能。实验结果表明,在水平跨度张力不等的实际运行中,所提方法能够保持较高的监测与估计准确度。
In view of the monitoring and estimation of overhead transmission line sag,the existing methods have higher requirements on the number of sensors and lower estimation accuracy.Therefore,a monitoring and estimation method of transmission line sag based on optimal intelligent sensor configuration and machine learning is proposed.Firstly,an optimal intelligent sensor configuration method based on linear integer programming is proposed,which can reduce the number of sensors in traditional point measurement system by half and does not affect the accuracy of the system monitoring data.Then,the least square(LS)estimation model is constructed,and the LS estimation value is input to support vector machine for transmission line sag estimation,which further improves the accuracy of the proposed method.Finally,the sag and tension data are simulated on PLS-CADD to verify the performance of the proposed method.The experimental results show that the proposed method can maintain high monitoring and estimation accuracy in the actual operation with unequal horizontal span tension,and the performance of the proposed method is the best compared with other methods.
作者
宰红斌
张毅
朱旭东
单荣荣
ZAI Hongbin;ZHANG Yi;ZHU Xudong;SHAN Rongrong(State Grid Jincheng Power Supply Company,Jincheng 048000,China;NARI Technology Development Co.,Ltd.,Nanjing 211106,China)
出处
《电力信息与通信技术》
2021年第6期1-8,共8页
Electric Power Information and Communication Technology
基金
国家重点研发计划项目(2018YFB0905000)。
关键词
最优智能传感配置
机器学习
垂度监测
垂度估计
点测量系统
optimal intelligent sensor configuration
machine learning
sag monitoring
sag estimation
point measurement system
