Identification of drilling stick-slip vibration conditions based on Empirical Mode Decomposition threshold denoising and Support Vector Machine

The characteristics of the normal and stick-slip vibration signals reflect the drilling conditions, which is significant in recognizing them. In this paper, a new method that combines the Empirical Mode Decomposition (EMD) threshold denoising and Support Vector Machine (SVM) is proposed to classify these characteristics. First, the EMD threshold denoising method is introduced to denoise the raw signals of the drill string vibration. Second, the features of these characteristics are selected by the Intrinsic Mode Function (IMF) energy entropy and marginal spectral energy. Last, the drilling conditions are classified and identified by the Support Vector Machine (SVM). The simulation results show that the identification accuracy of the proposed method is higher than the conventional methods.