Electric reactor vibration monitoring system based on LOF-FCM fuzzy clustering algorithm

Abstract

The invention relates to an electric reactor vibration monitoring system based on an LOF-FCM fuzzy clustering algorithm, and belongs to the field of electronic devices. The electric reactor vibration monitoring system based on the LOF-FCM fuzzy clustering algorithm comprises a sensor terminal part, a signal processing circuit part, a data acquisition part and a PC end which are in signal connection in sequence. According to the invention, real-time on-line monitoring of vibration displacement, speed and acceleration of the reactor can be realized, vibration data information of the reactor can be fed back in time, and multi-dimensional data of reactor vibration evaluation can be provided; a LOF outlier factor detection algorithm and a FCM fuzzy clustering algorithm are organically fused, a part of outlier data can be removed before clustering, and the accuracy of the FCM clustering algorithm is greatly improved; the placement position error of the sensor can be eliminated through the improved LOF-FCM fuzzy clustering algorithm, real-time online accurate detection is realized, and the accuracy of a vibration monitoring system is improved.

Description

technical field [0001] The invention belongs to the field of electronic devices and relates to a reactor vibration monitoring system based on LOF-FCM fuzzy clustering algorithm. Background technique [0002] Reactors will generate electromagnetic vibrations during on-site operation of substations. Electromagnetic attraction is one of the key factors leading to the electromagnetic vibration of the reactor. Electromagnetic attraction is Maxwell force, which is due to the fact that when the main magnetic flux passes through the iron core with high magnetic permeability and the air gap with low magnetic permeability, it will produce a certain The force of the reduced magnetic field energy forces the reactor core to deform periodically. The magnetostrictive effect is another main factor that causes the electromagnetic vibration of the reactor, because the magnetization state of the iron core changes under the action of the external magnetic field, resulting in a change in its ow...

AI Technical Summary

Problems solved by technology

[0004] At present, most of the existing reactor vibration monitoring systems are only aimed at the vibration data monitored by a certain placement position of a certain sensor, which has a large randomness. At the same time, the sensor placement error and the substation site Due to the interference factors of the electromagnetic environment, the monitored vibration data has a large uncertainty error, and at the same time, the data placed by multiple sensors is not integrated to evaluate the vibration state of the overall reactor, so as to achieve the uncertainty of the reactor from the calculation level gender error

[0005] At the same time, there are researches on the LOF outlier detection algorithm and the FCM fuzzy clustering algorithm at home and abroad, but there is no process of combining the two algorithms to form a new clustering algorithm, and the existing domestic and foreign The vibration monitoring system does not apply the fuzzy clustering algorithm to the vibration data processing, and there is a lack of relevant research

Images