A fault monitoring method and system for a ring network cabinet based on a neighborhood-preserving embedded algorithm

Abstract

The invention relates to the field of distribution safety, and discloses a ring main unit fault monitoring method and a ring main unit fault monitoring system based on a neighborhood preserving embedding algorithm. The method comprises the following steps: acquiring a first data matrix X of historical multivariate data in the running process of a ring main unit; preprocessing and normalizing the data in the first data matrix to generate a second data matrix; determining the number of neighborhoods and the number of dimensions to be reduced according to a neighborhood preserving embedding algorithm NPE model, constructing a multivariate data dimension reduction model under the second data matrix, and setting Hotelling and squared prediction error SPE and corresponding monitoring statistical thresholds; acquiring real-time multivariate data and generating a third data matrix, and preprocessing and normalizing the third data matrix to generate a fourth data matrix; and inputting the fourth data matrix to the NPE model, calculating T<2> and SPE of the real-time data, comparing T<2> and SPE with the corresponding monitoring statistical thresholds, and performing exception handling when T<2> and SPE of the real-time data are greater than the corresponding monitoring statistical thresholds respectively. According to the invention, more details of data can be obtained, and the complexity of fault detection model calculation is reduced.

Description

technical field [0001] The invention relates to the field of power distribution safety, in particular to a method and system for fault monitoring of a ring main unit based on a neighborhood preserving embedded algorithm. Background technique [0002] As the city's power supply mode is changed from overhead lines to underground cables, the requirements for the reliability and quality of power supply of ring network cabinets are getting higher and higher. Underground cables generally have a long operating period and are easily affected by other disasters such as water seepage or insect pests. Therefore, it is particularly important to conduct real-time comprehensive monitoring of the operating status of related equipment in the ring network cabinet along the cable. Traditional online monitoring technologies such as cable fault technology, cable core monitoring technology, fire monitoring and fire extinguishing technology in electrical cabinets, etc. Relying solely on these e...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and system for fault monitoring of a ring network cabinet based on a neighborhood-preserving embedded algorithm, which solves the problem that the monitoring method in the prior art cannot monitor the interrelationship changes among multiple variables, the information is relatively single, and the monitoring accuracy is high. low technical issues

Images