Search

CN-121993146-A - Rotary guiding dynamic tool face measuring method, device and storage medium based on data fusion

CN121993146ACN 121993146 ACN121993146 ACN 121993146ACN-121993146-A

Abstract

The invention discloses a method, equipment and a storage medium for measuring a rotary guiding dynamic tool face based on data fusion, which comprise the steps of obtaining an optimal gravity tool face estimated value through a unscented Kalman filtering algorithm based on a quaternion theory of rotary coordinate conversion; and fusing the optimal gravity tool face estimated value and the theoretical calculated gravity tool face estimated value to obtain a final predicted value. And the method of combining the unscented Kalman filtering measurement result and the theoretical deduction calculation result is combined to measure the rotation guide dynamic tool face, so that the numerical value is more stable and the precision is higher.

Inventors

  • SONG XIAOJIAN
  • BI LINA
  • HAN XIAOWEN
  • DONG CHENXI
  • FU YU
  • GAO TINGZHENG
  • LI ZONGWEI
  • Tan Anlong
  • LI JIN
  • HU XIUFENG

Assignees

  • 中国石油集团渤海钻探工程有限公司
  • 中国石油天然气集团有限公司

Dates

Publication Date
20260508
Application Date
20241101

Claims (17)

  1. 1. The method for measuring the rotary guiding dynamic tool face based on data fusion is characterized by comprising the following steps of: Based on quaternion theory of rotation coordinate conversion, obtaining an optimal gravity tool face estimated value through an unscented Kalman filtering algorithm ; Based on the rotation guiding tool face calculation principle, a theoretical calculation gravity tool face estimated value is obtained ; Estimating the optimal gravity tool face And said theoretical calculated gravity toolface estimate And (5) fusing to obtain a final predicted value.
  2. 2. The method of claim 1, wherein fusing the optimal gravitational toolface estimate with the theoretical calculated gravitational toolface estimate to obtain a final prediction comprises using a machine learning algorithm to compute an optimal gravitational toolface estimate And theoretical calculation of gravity toolface estimate Fusing and calculating to obtain initial predicted value 。
  3. 3. The method of claim 2, wherein fusing the optimal gravity toolface estimate and the theoretical calculated gravity toolface estimate to obtain a final predicted value further comprises based on the initial predicted value obtained And obtaining a final predicted value in a cyclic iteration mode.
  4. 4. The data fusion-based rotational guided dynamic toolface measurement method of claim 2, wherein the optimal gravity toolface estimate is calculated using a machine learning algorithm And theoretical calculation of gravity toolface estimate The fusion includes: Wherein, the Is that The weight coefficient is used to determine the weight coefficient, Is that Weighting coefficients.
  5. 5. The method for measuring a tool surface of a rotary steerable dynamic tool based on data fusion according to claim 4, wherein an initial predicted value is calculated When, the measurement accuracy is set as: , ; Wherein, the The variance of the gravity toolface estimate is calculated for theory, Is the variance of the optimal gravity toolface estimate.
  6. 6. The method for measuring a rotary steerable dynamic toolface based on data fusion according to claim 3, wherein determining a final predicted value based on the obtained initial predicted value in a loop iteration manner comprises: fusing the initial predicted values As a priori estimate instead of Calculating to obtain new predicted value ; Replacing new predicted value as prior estimated value Continuing to calculate until the obtained new predicted value and The difference between the two is within a predetermined range, and the new predicted value is taken as the final predicted value.
  7. 7. The method for measuring a rotary steerable dynamic toolface based on data fusion according to claim 6, wherein the initial predicted value after fusion As a priori estimate instead of Calculating to obtain new predicted value When adopting the formula Wherein, the Is that The weight coefficient is used to determine the weight coefficient, Is that Weighting coefficients.
  8. 8. The method for measuring a rotary steerable dynamic toolface based on data fusion according to claim 6, wherein the precision epsilon is preset when the final predicted value is obtained by loop iteration based on the obtained initial predicted value, if Then Otherwise, the new predicted value is used as the prior estimated value to replace The calculation is continued.
  9. 9. The data fusion-based rotational-oriented dynamic toolface measurement method of claim 1, wherein the quaternion theory based on rotational coordinate transformation comprises: and establishing an Euler angle conversion matrix according to the definition of the quaternion and the Euler theorem, and converting the Euler angle conversion matrix into the quaternion.
  10. 10. The data fusion-based rotational guided dynamic toolface measurement method of claim 1, wherein the step of passing through a unscented kalman filter algorithm comprises: Discretizing a state equation and a measurement equation based on quaternions; a particle swarm optimization algorithm is adopted to perform optimization on a sigma point scaling factor k in a trace Kalman filtering algorithm; A predetermined number of sigma points are set to approximate the distribution of the entire nonlinear system using the optimal scaling factor.
  11. 11. The data fusion-based rotational guided dynamic toolface measurement method of claim 1, wherein deriving a theoretical calculated gravity toolface estimate based on rotational guided toolface calculation principles comprises: Calculating an angular difference GM of the rotationally guided gravity tool face GTF and the magnetic tool face MTF; and calculating a theoretical gravity tool face estimated value of the rotation guide according to the angle difference GM.
  12. 12. The data fusion-based rotational-oriented dynamic toolface measurement method of claim 1, wherein the quaternion theory based on rotational coordinate transformation comprises: Establishing an Euler angle conversion matrix according to the definition of the quaternion and the Euler theorem, and converting the Euler angle conversion matrix into the quaternion; According to the corresponding relation between the geographic coordinate system O-NED and the drilling tool coordinate system O-XYZ, the gesture matrix T (T) is expressed as follows: , wherein, quaternion q= [ Q0, Q1, Q2, Q3]; 。
  13. 13. The data fusion-based rotational guided dynamic toolface measurement method of claim 1, wherein the step of passing through a unscented kalman filter algorithm comprises: discretizing a state equation and a measurement equation based on quaternion: ; ; Where A is a state transition matrix, u (k) is system state noise, and v (k) is measurement observation noise.
  14. 14. The method for measuring the dynamic tool face of the rotary guide based on the data fusion according to claim 1, wherein the theoretical calculation gravity tool face is obtained based on the calculation principle of the tool face of the rotary guide The estimated values include: Calculating an angular difference GM of the rotationally-oriented gravitational tool face GTF and the magnetic tool face MTF: ; calculating a theoretical gravity tool face estimated value of rotation guidance according to the angle difference GM: 。
  15. 15. A drilling apparatus employing the data fusion-based rotary steerable dynamic toolface measurement method of any one of claims 1-14.
  16. 16. A computer device comprising a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the data fusion-based rotational oriented dynamic toolface measurement method of any one of claims 1-14.
  17. 17. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions, which when executed by a processor, cause the processor to perform the data fusion based rotation oriented dynamic toolface measurement method of any one of claims 1-14.

Description

Rotary guiding dynamic tool face measuring method, device and storage medium based on data fusion Technical Field The invention relates to the technical field of oil and gas drilling, in particular to a method, equipment and a storage medium for measuring a rotary guiding dynamic tool face based on data fusion. Background Rotary steerable drilling is a completely new drilling technique for implementing steering control of the borehole trajectory in the rotary operating state of the drill string. When the rotary guide drilling technology is utilized for drilling operation, three-dimensional borehole track control can be realized without frequently tripping, and the rotary guide drilling technology has the advantages of smoother borehole track and larger extension distance, and has important significance in ensuring the quality of the borehole track, improving the drilling speed and efficiency and meeting the requirements of drilling a well with a complex structure. The rotary steering drilling system mainly comprises information measurement, bidirectional transmission, steering control and other systems, and in the rotary steering drilling process, the real-time control of the well track is realized by controlling the steering mechanism of the rotary steering tool according to the real-time measurement of the well track parameter and the posture parameter of the rotary steering tool. However, in the actual drilling process, the motion acceleration generated by the longitudinal vibration, the transverse vibration and the torque vibration can generate serious interference on the dynamic rotation attitude measurement result, so that the calculated attitude measurement result has larger error. In order to improve the accuracy of the calculated attitude measurement result, some prior art adopts gyroscope rotation speed differential to conduct acceleration error compensation, the compensation method is easy to receive the influence of noise and is poor in compensation effect, some prior art adopts a filtering method based on interference signal power spectrum density analysis, the accuracy of the method is low, the real-time attitude measurement requirement cannot be met due to the fact that the filtering convergence speed is low, and some prior art adopts a well deviation azimuth dynamic rotation calculation method, and the method cannot effectively remove complex noise in the border aiming at hardware filtering of sensor interference noise. Therefore, a method for obtaining a dynamic tool face measurement with more stable value and higher precision is sought, and the technical problem to be solved by those skilled in the art is still needed. Based on this, the prior art still remains to be improved. Disclosure of Invention In order to solve the technical problems, the embodiment of the invention provides a method, equipment and a storage medium for measuring a rotary guiding dynamic tool face based on data fusion, which are used for solving the technical problems of poor measuring stability and low precision of the dynamic tool face in the prior art. In order to solve the above technical problems, some embodiments of the present invention disclose a method for measuring a rotation-oriented dynamic tool surface based on data fusion, which includes: Based on quaternion theory of rotation coordinate conversion, obtaining an optimal gravity tool face estimated value through an unscented Kalman filtering algorithm ; Based on the rotation guiding tool face calculation principle, a theoretical calculation gravity tool face estimated value is obtained; Estimating the optimal gravity tool faceAnd said theoretical calculated gravity toolface estimateAnd (5) fusing to obtain a final predicted value. In some embodiments, fusing the optimal gravity toolface estimate with the theoretical calculated gravity toolface estimate to obtain a final predicted value includes using a machine learning algorithm to compute an optimal gravity toolface estimateAnd theoretical calculation of gravity toolface estimateFusing and calculating to obtain initial predicted value。 In some embodiments, fusing the optimal gravity toolface estimate with the theoretical calculated gravity toolface estimate to obtain a final prediction value further comprises based on the initial prediction value obtainedAnd obtaining a final predicted value in a cyclic iteration mode. In some embodiments, the optimal gravity toolface estimate is calculated using a machine learning algorithmAnd theoretical calculation of gravity toolface estimateThe fusion includes: Wherein, the Is thatThe weight coefficient is used to determine the weight coefficient,Is thatWeighting coefficients. In some embodiments, an initial predictor is calculatedWhen, the measurement accuracy is set as: ,; Wherein, the The variance of the gravity toolface estimate is calculated for theory,Is the variance of the optimal gravity toolface estimate. In some embodiments, deriving the final predicted