Coal-Rock Interface Identification Method Based on Dimensionless Parameters and Support Vector Machine

摘要

In order to identify the Coal-Rock interface of mechanized caving mining, a new method based on dimensionless parameters and support vector machine is proposed. Detect the acoustic pressure signal of the tail beam of the hydraulic support, extract the dimensionless parameters of acoustic pressure signal peak factor C, pulse factor I, margin factor, skewness factor P, kurtosis factor K and form factor S to construct the feature vectors, as support vector machine training samples to establish classifier for identifying the Coal-Rock interface. The experimental result shows that feature vectors constructed by the dimensionless parameters input support vector machine can automatically identify the Coal-Rock interface. It provides a new thinking and method for the study of Coal-Rock interface identification.