Papers by Keyword: Smoke Detection

Abstract: With the purpose of accurately and reliably making a forecast on fire, it is necessary to study the scattering properties of the early smoke particles. Based on the laser scattering principle of smoke particles, a device is designed in combination with aspiration system, semiconductor laser of different wavelength and spectral photoelectric receiving tube as well as the flexible structure and signal processing methods, so as to implement the function of acquiring the laser scattering intensity data of smoke particles from multiple angles. In this paper, through a comparative analysis, the basic data related to the smoke particle detection algorithms is obtained.

Abstract: Because of high fire frequency and huge losses, the research of fire signal detection in the monitoring system is an important task in the fire-preventing field. The fire signal detection method based on vision can overcome the shortcomings that exist in some traditional methods i.e. it can surmount the large impact on environmental interference factors, such as temperature, photographic and smoke of environment. With many researcher’s results, it shows clearly that the error rate of flame recognition is low, and also the real-time ability and the anti-disturbance ability are very good.

Abstract: Smoke detection with multiwalled carbon nanotubes (MWCNTs)/cement composites have been studied. Pellets of MWCNTs reinforced Portland cement have been casted with varying MWCNTs %. The DC transient studies depicted an increase in conductivity when exposed to smoke. Responsivity in the range 26-46% has been obtained under smoky environment based on MWCNTs % in the composites. Ionic conductivity increased with frequency at room temperature under ambient and smoky environments. In this paper, we also report fabrication technique of the pellets and the sensing mechanism is explained on the basis of ionic conductivity of the cementitious material in combination with the conductive carbon fibers present in the porous matrix of the cement.

Abstract: An early smoke detection algorithm based on Codebook model and multiple features is presented in this paper. First, the foreground is obtained by using the Codebook algorithm. Second, the model of color distribution and the model of shape feathers of smoke are applied to detect the suspected smoke area in the foreground. Finally, the false alarm rate is reduced effectively by using dynamic features in the diffusion process of smoke. Experimental results show that our algorithm has good detection performance and achieves real-time requirement which is very important for real application.

Abstract: Focusing on energy-saving issues of boiler, this paper finds out the combustion conditions inside boiler furnace by monitoring and analysis on oxygen content of flue gas, carbon content of fly ash, CO and CO2 contents. The intelligent control of boiler combustion was achieved and combustion efficiency was rosen. Using neural network controlling model, automatic optimization of oxygen delivery volume,coal delivery volume, the total wind pressure of primary air, the secondary air-door opening degree and furnace negative pressure were achieved, and the boiler efficiency increasing by 5 ~ 7%.