Power transmission line galloping grading early warning method based on supervised learning

Abstract

The invention discloses a power transmission line galloping grading early warning method based on supervised learning, and belongs to the field of overhead power transmission line fault prevention and control of a power system. Firstly, temperature and humidity data are corrected through a sliding time window, the wind direction is adjusted to form an included angle with the axial direction of a wire, then influence weights and comprehensive influence factors of different micrometeorological elements on the galloping amplitude are calculated, and sample screening is conducted through a K-means clustering algorithm by means of the comprehensive influence factors. And by taking the micrometeorological elements as input and the amplitude data as output, constructing a galloping prediction model based on a supervised learning algorithm so as to obtain a prediction result. Compared with a classical algorithm, the method provided by the invention proves the superiority of a power transmission line galloping prediction model based on a GA-BP and SVM composite algorithm by judging a prediction error and a prediction effect. According to the method, the degree of matching between the galloping prediction result and the actual state is high, the galloping amplitude can be estimated, the galloping grading early warning function can be realized, and early warning information can be sent out in advance. Operation and maintenance personnel can flexibly formulate inspection strategies and anti-galloping measures, and safe and stable operation of the power transmission line is guaranteed.

Description

technical field [0001] The invention relates to the field of early warning of overhead transmission line faults in power systems, and more particularly, to a galloping classification early warning method for overhead transmission lines based on supervised learning. Background technique [0002] Transmission lines are erected in the natural environment, and their structural safety and stability are easily affected by the natural environment. Galloping is one of the common fault types of overhead transmission lines. Under the action of a certain angle of attack and wind speed, the conductor is prone to large-scale and low-frequency self-excited vibration, which is called galloping. Dancing has a variety of hazards. The lighter ones cause flashover and tripping accidents, and the heavier ones cause damage to hardware and insulators, broken wires, broken wires, and even tower collapse. The frequent occurrence of galloping accidents on transmission lines not only affects the saf...

AI Technical Summary

Problems solved by technology

[0003] The current research on galloping prediction mainly consists of two methods: dynamic analysis of the conductor and then simulating the trajectory of the conductor and building a machine learning galloping prediction model. The coupling mode between them is fluid-solid coupling, and the trajectory model of the wire is too idealized to grasp the aerodynamic characteristics of the wire in real situations, resulting in significant differences between the numerical analysis of galloping and the measured results; the main problem of the latter is to predict The result is relatively broad. It can only judge whether galloping has occurred, cannot predict the amplitude of galloping, and cannot provide graded warnings for the prediction results. Moreover, the data correction and screening of samples were not carried out during the training of the model, resulting in large errors in the model and poor prediction performance. Has a lot of room for improvement

Images