On investigation of burning and gasification of coal fuel crushed at mills with high-energy impact

• Published in: Journal of physics. Conference series Vol. 1128; no. 1; pp. 12061 - 12065
• Main Authors: Abdurakipov, S S, Burdukov, A P, Butakov, E B, Kuznetsov, A V
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.11.2018
• Subjects: Artificial neural networks; Coal; Coal gasification; Combustion; Cylindrical chambers; Fuel oils; Mills; Neural networks; New technology; Nuclear fuels; Pulverized coal
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1128/1/012061

The development of new promising technologies based on coal fuel is certainly topical. This article is devoted to application of new technology of gas and fuel oil replacement by mechanically activated micronized coal in power engineering: ignition and stabilization of pulverized coal flame combustion. Enhancement of coal reactivity at its grinding with mechanical activation is associated with an increase in the reaction rate of carbon material. The process of combustion was studied on the 1-MW setup with tangential scroll supply of pulverized coal-air mixture and cylindrical reaction chamber. Experiments were carried out by using brown coals. Coal, ground by the standard boiler mill, was fed to the input of high-energy mills and then was directed to the scroll inlet of the burner-reactor with the transport air. The suspension was ignited by a gas igniting device with the power of 50 kW. Experimental studies on air gasification of micronized coal were conducted in the reaction chamber at the temperature of 1000-1200 °C and air excess ratio α = 0.5. Intensive mechanical activation of coals led to increase the chemical activeness. This effect can be used for development of new highly boosted processing methods for coals with various levels of metamorphism. The obtained results of visualization were used to train the state-of-art deep convolutional neural network. It was shown that the developed neural network was able to automatically determine the combustion regimes from flame images.