Drilling dynamics measurement of drilling motors and its application in recognition of motor operation states through machine learning

Abstract

Drilling motors are widely used in unconventional oil and gas exploration. Due to the increased non-productive time and drilling costs brought about by accidental damage to drilling motors, predictive maintenance for drilling motors is necessary to optimize asset utilization. However, service companies face significant challenges in achieving predictive maintenance: operational data acquisition, automated statistics analysis, and drilling state recognition. This paper presents a miniature vibration recorder, an automatic statistical analysis method, and a layered recognition algorithm to resolve these challenges and improve tool maintenance efficiency. The designed recorder can be installed in the catch of a conventional mud motor to record drilling dynamics over a drilling motor's entire operation cycle. Time-series data from the recorder can be used to automatically generate operation statistics, mitigating the costs incurred by manual data analysis. The layered recognition algorithm then enables the automatic identification of drilling operation states, i.e., surface, downhole non-drilling, downhole sliding, and downhole rotation. The solutions were validated by deploying the recorder in drilling field runs and analyzing recorded data using the associated design software, yielding a functional data collection, automatic data statistical analysis, and operation state recognition accuracy of 95%. Through achieving improved data collection and analysis, the recorder and software introduced in this work can notify motor owners of the detailed operation history of their tools and enable informed preventive maintenance.