Font Size: a A A

Research On Fault Diagnosis Technology Of Light Measurement System In High Voltage Converter Station

Posted on:2021-01-25Degree:MasterType:Thesis
Country:ChinaCandidate:S HuangFull Text:PDF
GTID:2392330614966080Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
Energy-transmitting optical fibers and remote modules are the two key components of the optical measurement system of high-voltage converter stations.Due to the influence of various external environmental factors,the failure rate of the two is high,which causes abnormalities and risks in the overall system.However,the current research on the working status and diagnosis of energytransmitting optical fibers and remote modules is relatively lacking in this field.Therefore,the research on the working status of the energy-transmitting optical fibers and the remote modules is separately carried out to achieve the status detection and fault diagnosis,so as to analyze the operation reliability of the energy-transmitting optical fibers and the remote modules,which has extremely important practical significance for strengthening the safe and reliable operation of the optical measurement system of high-voltage converter stations.This paper mainly studies the fault diagnosis of energy-transmittings optical fiber and remote modules in the optical measurement system of the high-voltage converter station.The main research work includes: Firstly,using unsupervised LOF(Local Outlier Factor)outlier detection algorithm to study outlier determination and fault diagnosis of the energy transmission fiber.The LOF algorithm is used to detect the singular value of the energy transmission fiber loss data collected at the highvoltage converter station,so that the faulty energy-transmitting optical fibers in the fiber link were effectively and accurately detected.Second,the density peak clustering algorithm is used to study the life prediction and fault diagnosis of remote modules.The density peak clustering algorithm is used to perform clustering processing and outlier determination on the data of the remote module operation status collected in the field test to accurately and intuitively distinguish the remote modules located in the cluster center and the remote modules that deviate from their respective cluster centers from a large number of remote modules,which realizes the life prediction and fault diagnosis of the remote modules.Third,develop a high-voltage converter station optical measurement system application software to realize the basic information and test results of energy-transmitting optical fibers and remote modules to the management personnel in the form of human-computer interaction.The results after data processing are displayed through a visual interface,so that managers can more effectively monitor and manage the working status of the energy-transmitting optical fibers and remote modules.
Keywords/Search Tags:high-voltage converter stations, energy-transmitting optical fiber, remote module, outlier detection, density peak clustering
PDF Full Text Request
Related items