Multiscale Temporal Convolutional Network-Based End-to-End Recognition of Drill-String Stick-Slip Vibration in Drilling Process

Severe drill-string vibration is a significant source of drilling problems. Most existing methods for vibration recognition rely on downhole data, facing great limitations in practice. In addition, complex and changeable formations result in limited ability of single-scale features to characterize the vibration. To resolve these issues, an end-to-end vibration recognition model using only surface drilling data is proposed based on multiscale features extraction. A multiscale temporal convolutional network is developed to extract multiscale temporal features of multisensor data, enhancing the vibration representation capability to adapt to complex formations. To further improve recognition capability, the bidirectional long short-term memory network is utilized to obtain contextual linkage of multiscale features. Experiments conducted with field data have verified the efficiency of proposed method. It has achieved 97% accuracy, and outperforms existing methods. Furthermore, compared with the recognition result based on single-scale features, it has improved by 6% in accuracy. The proposed method provides automated diagnostics of drill-string vibration.