Dust Explosion Characteristic Mechanisms Analysis Based on Information Identification

We present a novel and practical image characteristic information architecture recognition for explosive dust detection. The Fourier transform domain of the fractional derivative is used to define the image filtering framework. The Rudin-Osher-Fatemi (ROF) model, in a bounded variation imagery function space, is selected to obtain prior noise knowledge, including the noise variance. The texture and non-texture regions of the imagery are divided based on statistical information about the local image variance. We compare our proposed modelling with other widely adopted algorithms. This comparison reveals the feature recognition accuracy involved in achieving good segmentation performance. We thus demonstrated that the noise suppression and staircase effect were better for the dust imagery, and that the overlapping particles were effectively separated. The research results indicated the correctness and feasibility of the proposed model, which provides a theoretical and experimental basis for the design of dust explosion concentration intervals.