Assessment of Rib Spalling Hazard Degree in Mining Face Based on Background Subtraction Algorithm and Support Vector Machine

Rib spalling is one of the common hazards in a fully mechanized mining face. In order to accurately assess the hazard degree, this study proposes a new method based on background subtraction algorithm and support vector machine (SVM). First, the architecture diagram of rib spalling feature analysis is constructed, and the rib spalling feature indices are determined, including the duration area, height and the centre of ribs spalling height. Then, the specific feature analysis process of rib spalling is performed using the background subtraction algorithm. Furthermore, some virtual 3D rib spalling animations are generated using 3D Studio Max (3Ds Max) software to verify the reasonability of extracted features. Thereafter, the assessment model of rib spalling hazard degree is established based on SVM. Three assessment models based on SVM, back propagation neural network (BPNN) and artificial immune (AI) algorithm have been developed. The assessment accuracy of SVM (reaching 85%) is obviously higher than that of BP-NN (75%) and AI (70%) algorithm. The results indicate the feasibility and superiority of the proposed method in the assessment of rib spalling hazard degree.