แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Watit Benjapolakul. Fault cause classification on PEA 33 kV distribution system using supervised machine learning compared to artificial neural network. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2021.
Fault cause classification on PEA 33 kV distribution system using supervised machine learning compared to artificial neural network
Name: Witsanu Promrat
Organization :
Chulalongkorn University. Department of Electrical Engineering
Email :
6170406421@student.chula.ac.th
Name: Wuttiphong Pupatanan
Organization :
Chulalongkorn University. Department of Electrical Engineering
Email :
6170407021@student.chula.ac.th
Name: Watit Benjapolakul
Organization :
Chulalongkorn University. Department of Electrical Engineering
Email :
Watit.B@chula.ac.th
LCSH:
Electric power systems
LCSH:
Machine learning
Abstract:
A fault occurring in a distribution system has low reliability. Therefore, when a fault occurs, the system restoration should have the fastest. The purpose of this article is to develop an algorithm to classify the cause of faults in Provincial Electricity Authority (PEA.) distribution systems in southern area 2 of Thailand with waveform characterization and compares the performance of the supervised machine learning (SML) and the artificial neural network (ANN) technique to reduce the outage duration. The characteristic signature of voltage and current waveform i.e., voltage dip, rate of change of current and voltage, neutral current and voltage, temporary or permanent fault, fault type, and evolving fault were extracted, provided to SML and ANN to classify the cause of faults focusing on animals, tree contact, and equipment failure. Accuracy testing of the algorithm by real testing was performed with the distribution system of PEA in the central-southern area of Thailand. The result shows that when the group of fault events is correctly classified, the proposed method can provide the high accuracy of identifying fault cause with the lowest ML accuracy of 81.21% and the lowest ANN accuracy of 62.50%. Consequently, In the condition of this paper, the SML can classify more accurately than the ANN.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2021
Modified:
2025-12-16
Issued:
2025-12-16
บทความ/Article
application/pdf
BibliograpyCitation :
In Electrical Engineering Academic Association (Thailand), IEEE Thailand Section, and College of Engineering. Rangsit University. The 2021 9th International Electrical Engineering Congress (iEECON 2021) (P00698). Pathum Thani : Rangsit University, 2021
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.027518 วินาที
Witsanu Promrat
| Title | Contributor | Type |
|---|---|---|
| Fault cause classification on PEA 33 kV distribution system using supervised machine learning compared to artificial neural network
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Witsanu Promrat;Wuttiphong Pupatanan;Watit Benjapolakul | บทความ/Article | |
| Development of a current measuring instrument for PEA distribution transformer using IoT-based technology
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Channarong Phongraktham;Witsanu Promrat;Wuttiphong Pupatanan;Nateetorn Poonniam | บทความ/Article |
Wuttiphong Pupatanan
| Title | Contributor | Type |
|---|---|---|
| Fault cause classification on PEA 33 kV distribution system using supervised machine learning compared to artificial neural network
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Witsanu Promrat;Wuttiphong Pupatanan;Watit Benjapolakul | บทความ/Article | |
| Development of a current measuring instrument for PEA distribution transformer using IoT-based technology
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Channarong Phongraktham;Witsanu Promrat;Wuttiphong Pupatanan;Nateetorn Poonniam | บทความ/Article |
Watit Benjapolakul
| Title | Contributor | Type |
|---|---|---|
| Automated railway crossing system using zigbee/IEEE 802.15.4 standard
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Muhammad Mansattha;Watit Benjapolakul | บทความ/Article | |
| Prediction of solar cell energy production using machine learning
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Phoomiphat Hongthanakornhirun;Watit Benjapolakul ;Lunchakorn Wuttisittikulkij | บทความ/Article | |
| Fault cause classification on PEA 33 kV distribution system using supervised machine learning compared to artificial neural network
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Witsanu Promrat;Wuttiphong Pupatanan;Watit Benjapolakul | บทความ/Article |