A SVM-based method for identifying fracture modes of rock using WVD spectrogram features of AE signals

In order to achieve the highly efficient and accurate identification of fracture modes including tension or shear fractures during rock failure, an intelligent method based on Wigner-Ville distribution (WVD) spectrogram features acoustic emission (AE) signals was proposed. This mainly constructed by following steps: Firstly, AE hits corre-sponding were obtained through conducting Brazilian disc test (tension fracture) direct (shear limestone. Secondly, WVD spectro-grams these tensile-type shear-type respectively extracted then trans-formed into image relatively low-dimension as sample set gray-level cooccurrence matrix (GLCM) histogram oriented gradient (HOG). Finally, basis processed classified features, identifica-tion model established a support vector machine (SVM) learning algorithm. To verify this method, limestone subjected biaxial compres-sion identified method. The results showed that not only can greatly re-veal change from tension-dominated shear-dominated fractures, but also has advantages over RA-AF value such applicability, accuracy practicality.