基于极限学习机的输电线路风险监测方法研究

Research on transmission line risk monitoring method based on extreme learning machine

输电线路安全运行关系到国民经济的发展,本文基于极限学习机对输电线路风险监测方法进行研究。搜集影响输电线路安全运行的各种数据,对非量化数据进行量化处理,并将各种数据转化为风险监测、设备质量、服务水平、外部环境以及天气环境五种类型。对数据进行归一化处理,采用训练集数据对极限学习机模型进行训练,得到极限学习机模型。以100条不同输电线路为例,选择80条为训练集数据,20条为测试集数据进行风险监测计算。结果表明,基于极限学习机的输电线路风险监测模型计算精度高,同时在运行时间等多个指标上明显优于BP神经网络风险监测模型,对输电线路风险监测有参考价值。

The safe operation of transmission line is related to the development of national economy.This paper studies the risk monitoring method of transmission line based on extreme learning machine.Collect all kinds of data that affect the safe operation of transmission lines,quantify the non quantitative data,and transform all kinds of data into five types:risk monitoring,equipment quality,service level,external environment and weather environment.The data are normalized,and the extreme learning machine model is trained with the training set data to get the extreme learning machine model.Taking 100 different transmission lines as examples,80 are selected as the training set data and 20 as the test set data for risk monitoring calculation.The results show that the calculation accuracy of transmission line risk monitoring model based on extreme learning machine is high,and it is better than BP neural network risk monitoring model in many indexes such as running time,which has a certain reference value for transmission line risk monitoring.