Drilling generated shocks and vibrations (torsional, axial, and lateral) are among the main causes of failures in the drilling industry; because they affect the rate of penetration, directional control, and wellbore quality. Rotary steerable system tools are equipped with measurement devices such as magnetometers, accelerometers, and shocks and vibration sensors from which statistical information is obtained, such as root-mean squared error, maximum peaks, and peak levels. From these statistics, whirl, bit bounce, and stick/slip severity are inferred. Often, the derived statistics are not enough to distinguish between normal drilling versus abnormal drilling for a location in the wellbore or to determine whether the shocks and vibrations are the result of poor drilling practice, formation disturbances, or mechanical failures of the bottomhole assembly, including the bit. Machine learning methods were used for analyzing the high-frequency radial shock burst data, which compresses and classifies the data; i.e., good drilling and abnormal drilling. The method is capable of further clustering the data into whirl or no whirl, bit-bounce or no bit-bounce, formation change or no change, and/or faulty equipment and parts; thus, assist in the robust post-failure analysis of existing data sets and prevent catastrophic failures in real time and improve the trajectory control.

This paper presents a medical approach to classify shock waveforms acquired at 31,250 hertz downhole. The shock signals are treated as drilling electrocardiogram (D-ECG). The D-ECGs are processed using clustering algorithms and merged with drilling incidents to identify an arrhythmic signature pattern that can lead to catastrophic failures. In medicine, the analysis of heartbeat cycles in an electrocardiogram signal is very important for monitoring heart patients. In the drilling industry, downhole shocks are present most of the time. They are present so often that the authors introduce the concept of drilling electrocardiogram (D-ECG) based on shock waveforms acquired at high frequency. The shock module was implemented in hardware using a field programmable gate array (FPGA) and run inside the control unit of an RSS to complement the navigation systems composed. The shock acquisition and processing are performed at 31,250 Hz, providing enough bandwidth to fully reconstruct high-frequency events. A novel methodology combining field incidents with machine learning clustering algorithms is proposed to identify arrhythmic shocks signatures and whirl and bit bounce in real time, preventing failures to the BHA.