Method, system and medium for evaluating the health status of distribution cables based on multi-parameters

Abstract

The invention discloses a method, system and medium for evaluating the health status of distribution cables based on multiple parameters. The method detection predicts the current optimal health state parameters according to the health state parameters respectively, and the obtained N kinds of current optimal health state parameters form an N-dimensional feature vector, and input the pre-trained machine learning model, so as to obtain the tested distribution cable in The health status assessment results in the current state, the machine learning model is pre-trained to establish the mapping relationship between the N-dimensional feature vector and the health status assessment results. The invention can effectively overcome the problem of inaccurate detection of a single parameter, has the advantages of high detection accuracy, strong scalability, and does not depend on specific detection means, and solves the problem of deviations in evaluation results caused by differences in data collection time points and frequencies question.

Description

technical field [0001] The invention relates to a cable detection technology in electric power engineering, in particular to a multi-parameter-based method, system and medium for evaluating the health state of distribution cables. Background technique [0002] The medium and low voltage distribution network equipment has a large number and a wide distribution range, and the types, service life and maintenance status of distribution network equipment are uneven. With the gradual development of the status detection technology of power distribution equipment, although the status detection of power distribution equipment has been promoted to a certain extent, there are still data loss and manual data entry based on a series of detection technologies such as oscillatory wave partial discharge and high-frequency current partial discharge. , data sharing issues, as well as issues such as manual analysis, experience accumulation, periodic review, and complex cable analysis and diagn...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention: Aiming at the above-mentioned problems of the prior art, a method, system and medium for evaluating the health status of distribution cables based on multi-parameters are provided, which can effectively overcome the problem of inaccurate detection of a single parameter and have high detection accuracy. The advantages of high performance, strong scalability, and no dependence on specific detection methods solve the problem of deviations in evaluation results due to differences in data collection time points and frequencies

Images