To study the flame propagation characteristics of coal dust explosion, principal component analysis and BP neural network are used to predict the farthest distance and the maximum speed of flame propagation. Among the eight influencing factors of flame propagation characteristics, three principal components are extracted and named “the factor of volatility,” “the factor of intermediate diameter,” and “the factor of environmental temperature.” By using BP neural network, it is found that the minimum prediction error of the farthest distance of flame propagation is 2.4%, and the minimum prediction error of the maximum speed of flame propagation is 0.4%, which also proves the necessity of principal component analysis by comparing the prediction errors. The research results provide a theoretical method for predicting the flame propagation characteristics of coal dust explosion.

Nonstick coal is widely distributed in the world and is an important resource for human beings. The explosion characteristics and explosion suppression of nonstick coal dust are increasingly concerning. In this paper, the flame and pressure characteristics of a nonstick coal dust explosion are studied, and the suppression effect of SiO2, KCl, and NH4H2PO4 on the explosion is analyzed. It is concluded that the maximum propagation distance of a nonstick coal dust explosion flame is 0.59 m, the maximum pressure is 0.63 MPa, and the maximum pressure rise rate is 40.79 MPa/s. The explosion suppression effect of SiO2 is worse than that of KCl, but the inhibition effect of NH4H2PO4 is the best among the three kinds of explosion suppressants. When the mass percentage of NH4H2PO4 dust mixed with coal dust is 70%, the coal dust explosion is completely suppressed. It absorbs a certain amount of heat to promote the chemical reaction, which plays a certain role in controlling the explosion process, and its explosion suppression mechanism includes both physical and chemical explosion suppression.