Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/70744
Title: | Fault detection and diagnosis for chiller system | Authors: | Aribowo, Andrew Ixara | Keywords: | DRNTU::Engineering::Electrical and electronic engineering | Issue Date: | 2017 | Abstract: | HVAC system is an important part of every structure where it also uses a lot of power consumption. In all HVAC system component, the chiller is one of the most power consuming component, thus, any fault that occurs in a chiller might increase the chiller power consumption and lead to inefficiency of the overall HVAC system. The solution to this problem is fault detection and diagnosis (FDD) which makes it possible to detect the fault and diagnose which kind of fault occurs. This approach reduces the time in finding the fault, thus, reduces the energy consumption during fault and preventing mechanical damages to the chiller. This project focuses on using neural networks as the FDD approach for the chiller system, where the correct detection percentage of faults are calculated using a system with 2 neural networks for regression and classification respectively. | URI: | http://hdl.handle.net/10356/70744 | Schools: | School of Electrical and Electronic Engineering | Rights: | Nanyang Technological University | Fulltext Permission: | restricted | Fulltext Availability: | With Fulltext |
Appears in Collections: | EEE Student Reports (FYP/IA/PA/PI) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ANDREW IXARA ARIBOWO_FYP REPORT-FINAL .pdf Restricted Access | 1.72 MB | Adobe PDF | View/Open |
Page view(s)
319
Updated on Mar 29, 2024
Download(s) 50
18
Updated on Mar 29, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.