Condition assessment of underground cable system based on fuzzy logic and machine learning methods

Name: Dineenath Romphoyen

keyword: Underground cable system

LCSH: Machine learning

LCSH: Fuzzy logic

LCSH: Cables

Abstract: In this research, the overall health index of underground cable system is determined using Fuzzy Logic method and machine learning technique known as Random Forest method. The relevant data of 73 feeders has been collected in the prepared evaluation forms, divided into five major component groups: cable, joint, termination, manhole, and duct bank. In each component, various testing methods and diagnostic techniques are applied, and then the numerical score is determined according to the technical criteria for condition assessment. Subsequently, the obtained overall health index is multiplied with the conditional factor to incorporate the differences in installation type and configuration as well as the operating and environmental conditions. Finally, the overall health index based on these two methods is compared to verify the accuracy of the obtained results with the conventional weighting and scoring method to properly plan the preventive and condition-based maintenance and to improve the reliability of the underground cable system.

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Name: Thanapong Suwanasri

Role: thesis advisor

Email : thanapong.s.epe@tggs-bangkok.org

Created: 2023

Modified: 2567-04-04

Issued: 2024-04-04

วิทยานิพนธ์/Thesis

application/pdf

eng

DegreeName: Master of Engineering

Level: Master's Degree

Descipline: Electrical and Software Systems Engineering (International Program)

Grantor: King Mongkut's University of Technology North Bangkok

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	B17640295.pdf	4.12 MB	1	2024-04-17 10:57:44

ใช้เวลา

0.035655 วินาที