Abstract
Vibration signal measurement is one of the important methods to study the movement mode of the drill string. Through the interpretation of the vibration signal, the vibration pattern of the drill string can be accurately identified. MWD is a measurement method which can more directly reflect the vibration information of the drill string. In this paper, firstly, the drill string vibration signal is obtained by the sensors with a three-axis accelerometer and a gyroscope, and the sensor’s response has been solved and analyzed, which proves the effectiveness of this method for expressing drill string vibration information and the correlation between the measured signals. Then, the correlation coefficient, as the characteristic information basing on signal combination, is proposed; since the correlation coefficients of different patterns have different distribution characteristics, supervised machine learning is used to establish a classification model of vibration patterns. Finally, through the application of classification model in the actual drill data, the specific vibration types of various modes are clarified, which proves that the classification model can effectively distinguish different vibration modes and its accuracy can reach up to 95%.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
