IIIT Hyderabad Publications |
|||||||||
|
AUTOMATED FAULT DETECTION AND DIAGNOSIS FOR ENERGY RECOVERY WHEEL UNITS USING STATISTICAL MACHINE LEARNING METHODAuthors: arushi.singhal ,Simaran Singhal,Aviruch Bhatia,Vishal Garg Date: 2018-05-05 Report no: IIIT/TR/2018/83 AbstractBSTRACT: To maintain indoor air quality, there is a need to provide fresh air supply to mechanically conditioned spaces. In tropical climates, supply of fresh air at high temperature increases cooling energy consumption. To reduce the wastage of energy, energy recovery from exhaust air is useful. Energy Recovery Wheel (ERW) can be used to recover both sensible and latent heat from exhaust air at room temperature. If there is a fault in ERW system, it may cause a significant increase in energy consumption compared to the recovered energy. In large commercial buildings with various HVAC equipment installed, faults can remain undetected for hours to months depending on the nature of the fault, results in poor indoor air quality and wastage of energy. In this paper, a method is developed for automating Fault Detection and Diagnosis (FDD) of ERW units. The paper describes the implementation of SVM algorithm on the measured data. Full article: pdf Centre for IT in Building Science |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |