Deep Learning Based Power Transformer Monitoring Using Partial Discharge Patterns
نویسندگان
چکیده
Measurement and recognition of Partial Discharge (PD) in power apparatus is considered a protuberant tool for condition monitoring assessing the state dielectric system. During operating conditions, PD may occur either form single multiple patterns nature. Currently, pattern recognition, deep learning approaches are used. To evaluate spatial order less features from large-scale patterns, pre-trained network The major drawback traditional that they generate high dimensional data or requires additional steps like dictionary dimensionality reduction. However, real-time applications, interference incorporated measured reduce identification exact causes inaccurate diagnosis equipment. residual pooling layer proposed this work to overcome drawbacks provides fast learning. projected algorithm consists encoding module an aggregation information preserving feature generating. advantages produce low compared other approaches. At last, impact random noise signal on rate investigated addressed.
منابع مشابه
On-line Monitoring System Based on Principle of Electro-acoustic Monitoring for Transformer Partial Discharge
Partial discharge inside a transformer is mainly responsible for the insulation aging and damage of the transformer. However, partial discharge is usually accompanied by external signals like sound, light and electrical signals and detectable physical phenomena such as characteristical gas and dielectric loss. Therefore, it is of great significance to monitor online the external signals and phe...
متن کاملA Transformer Partial Discharge Measurement System Based on Fluorescent Fiber
Based on the physical phenomena of optical effects produced by the partial discharge (PD) and on the characteristics of fluorescent fiber sensing of weak fluorescent signals, a PD measurement system using a fluorescent fiber sensor was designed. The main parameters of the sensing system were calculated, an experimental testing platform for PD simulation in the lab was established, and PD signal...
متن کاملCrop Land Change Monitoring Based on Deep Learning Algorithm Using Multi-temporal Hyperspectral Images
Change detection is done with the purpose of analyzing two or more images of a region that has been obtained at different times which is Generally one of the most important applications of satellite imagery is urban development, environmental inspection, agricultural monitoring, hazard assessment, and natural disaster. The purpose of using deep learning algorithms, in particular, convolutional ...
متن کاملPower Transformer Incipient Faults Monitoring
Power transformers are important and expensive components in the electric power system. The knowledge of the actual status of the transformer insulation behavior, load tap changer performance, temperature, and load condition is necessary in order to evaluate the service performance concerning reliability, availability and safety. Systems abnormalities, loading, switching and ambient condition n...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Intelligent Automation and Soft Computing
سال: 2022
ISSN: ['2326-005X', '1079-8587']
DOI: https://doi.org/10.32604/iasc.2022.024128