Real-Time Prediction of Mud Motor Failure Using Surface Sensor Data Features and Trends

Abstract

Mud motor failure is a significant contributor to non-productive time in lower-cost land drilling operations, e.g. in North America. Typically, motor failure prevention methodologies range from re-designing or performing sophisticated analytical modeling of the motor power section, to modeling motor performance using high-frequency downhole measurements. In this paper, we present data analytics methods to detect and predict motor failures ahead of time using primarily surface drilling measurements.We studied critical drilling and non-drilling events as applicable to motor failure. The impacts of mud motor stalls and drill-off times were investigated during on-bottom drilling. For the off-bottom analysis, the impact of variations in connection practices (pick up practices, time spent backreaming, and time spent exposing the tools to damaging vibrations) was investigated. The relative importance of the various features found to be relevant was calculated and incorporated into a real-time mud motor damage index.A historical drilling dataset, consisting of surface data collected from 45 motor runs in lateral hole sections of unconventional shale wells drilled in early to mid-2019, was used in this study. These motor runs contained a mix of failure and non-failure cases. The model was found to accurately predict motor failure due to motor wear and tear. Generally, the higher the magnitude of the impact stalls experienced by the mud motor, the greater the probability of eventual failure. Variations in connection practices were found not to be a major wear-and-tear factor. However, it was found that connection practices varied significantly and were often driller-dependent.The overall result shows that simple surface drilling parameters can be used to predict mud motor failure. Hence, the value derived from surface sensor information for mud motor management can be maximized without the need to run more costly downhole sensors. In addition to this cost optimization, drillers can now monitor motor degradation in real-time using the new mud motor index described here.