دانلود رایگان مقاله متد نوین تشخیص حوادث در دیگهای بخار و گاز ترکیبی

Abstract

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 (5e10 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.

5. Conclusions

Our investigation has shown that acoustic sensing methods, using a single-point sensor, can be used to detect specific events of interest in domestic C-GFBs. The methods developed allow for the accurate automatic detection of demand type (100 ± 0.0% accuracy) and ignition time (97.1% accuracy). Algorithms to determine demand type were trained on features based on the normalised signal energy for the first 4 s of C-GFB activity. Infrasound pressure pulsations produced during ignition were analysed to identify the time burner ignition occurred. Furthermore our investigation has shown that it is also feasible to determine the motor frequencies of the pre-mix fan and possibly the circulation-pump from the acoustic data gathered.