In this section
@article{Neeld:2016:10.1016/j.buildenv.2016.01.029,
author = {Neeld, T and Eaton, J and Naylor, PA and Shipworth, D},
doi = {10.1016/j.buildenv.2016.01.029},
journal = {Building and Environment},
pages = {1--9},
title = {A novel method of determining events in combination gas boilers: Assessing the feasibility of a passive acoustic sensor},
url = {http://dx.doi.org/10.1016/j.buildenv.2016.01.029},
volume = {100},
year = {2016}
}
TY - JOUR
AB - To assess the impact of interventions designed to reduce residential space heating demand, investigators must be armed with field-trial applicable techniques that accurately measure space heating energy use. This study assesses the feasibility of using a passive acoustic sensor to detect gas consumption events in domestic combination gas-fired boilers (C-GFBs). The investigation has shown, for the C-GFB investigated, the following events are discernible using a passive acoustic sensor: demand type (hot water or central heating); boiler ignition time; and pre-mix fan motor speed. A detection algorithm was developed to automatically identify demand type and burner ignition time with accuracies of 100% and 97% respectfully. Demand type was determined by training a naive Bayes classifier on 20 features of the acoustic profile at the start of a demand event. Burner ignition was determined by detecting low frequency (5–10 Hz) pressure pulsations produced during ignition. The acoustic signatures of the pre-mix fan and circulation-pump were identified manually. Additional work is required to detect burner duration, deal with detection in the presence of increased noise and expand the range of boilers investigated. There are considerable implications resulting from the widespread use of such techniques on improving understanding of space heating demand.
AU - Neeld,T
AU - Eaton,J
AU - Naylor,PA
AU - Shipworth,D
DO - 10.1016/j.buildenv.2016.01.029
EP - 9
PY - 2016///
SN - 0360-1323
SP - 1
TI - A novel method of determining events in combination gas boilers: Assessing the feasibility of a passive acoustic sensor
T2 - Building and Environment
UR - http://dx.doi.org/10.1016/j.buildenv.2016.01.029
UR - http://hdl.handle.net/10044/1/29498
VL - 100
ER -
Speech and Audio Processing Lab
CSP Group, EEE Department
Imperial College London
Exhibition Road, London, SW7 2AZ, United Kingdom