Detection and localization of partial discharge (PD) in power transformer using machine learning methods in acoustic regime

Detection and localization of partial discharge (PD) in power transformer using machine learning methods in acoustic regime


Detection and localization of partial discharge (PD) in power transformer using machine learning methods in acoustic regime

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: Detection and localization of partial discharge (PD) in power transformer using machine learning methods in acoustic regime

ارائه دهنده: Provider: Ashkan Babakhanian

اساتید راهنما: Supervisors: Hamid Reza Karami (Ph.D) Majid Ghaniei (Ph.D)

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: saleh razini (ph.D) mohammad mahdi shahbazi

زمان و تاریخ ارائه: Time and date of presentation: 2023/09/12 10:00AM

مکان ارائه: Place of presentation: SEMINAR 2

چکیده: Abstract: The power transformer is one of the most important and eXpensive equipment of the power network. The failure of the power transformer will have an important and significant impact on the power network. In most cases, power transformer failure is caused bY insulation failure, which PD can identifY well. Detecting and locating PD at the time of occurrence and earlY stages can significantlY reduce power transformer maintenance costs. Therefore, timelY detection and location of PD in power equipment, especiallY power transformer, is of great importance. In this thesis, a non-invasive solution for detecting and locating PD is proposed, which will use an audio sensor to detect the PD signal. This solution uses a combination of audio signal processing methods and machine learning methods. In this thesis, using the information obtained from the sound sensor, different machine learning algorithms are trained in order to locate the partial discharge with appropriate accuracY. FinallY, different machine learning algorithms will be compared from different aspects (mean square error and regression coefficient) and the best machine learning algorithm for PD location will be introduced

فایل: ّFile: