Rotary drilling working condition drilling speed real-time calculation method based on drill bit position dynamic reconstruction
By combining local weighted regression algorithm with expert experience, the drill bit position is dynamically reconstructed, the drilling speed is calculated in real time, and the working conditions are identified. This solves the noise interference and real-time problems of traditional drilling speed calculation and improves the intelligence level of the drilling process.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-03
- Publication Date
- 2026-03-10
AI Technical Summary
Traditional drilling speed calculation methods suffer from severe data noise interference, poor real-time performance, weak working condition identification capabilities, and unclear trend characteristics, resulting in a low level of intelligence in the drilling process.
A local weighted regression algorithm is used to dynamically reconstruct the drill bit position data. Combined with expert experience and preset thresholds, the drilling speed is calculated in real time and the rotary drilling condition is identified, and abnormal data is eliminated.
It achieves real-time and accurate drilling speed calculation, can adapt to various working conditions, and provides a foundation for intelligent analysis of the drilling process.
Smart Images
Figure CN121636897A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of geological drilling intelligence, and particularly relates to a rotary drilling working condition drilling speed real-time calculation method based on dynamic reconstruction of a drill bit position. BACKGROUND
[0002] Drilling speed is a key parameter for measuring drilling efficiency, and its accurate calculation is of great significance for the optimization, safety control and intelligent analysis of the drilling process. Traditional drilling speed calculation methods mostly use sliding average method, difference method or simple filtering technology, which can smooth data fluctuations to some extent, but have the following problems: Severe data noise interference: original drilling data is affected by factors such as equipment vibration and signal transmission interference, resulting in high-frequency noise in the drill bit position data, which directly affects the accuracy of drilling speed calculation.
[0003] Poor real-time performance: traditional methods mostly rely on data smoothing processing within a fixed time window, resulting in lagging drilling speed calculation results that cannot meet the needs of real-time monitoring and dynamic adjustment.
[0004] Poor working condition adaptability: there are various working conditions (such as up and down drilling, hole sweeping, and drilling stopping) in the drilling process, and traditional methods cannot effectively identify and exclude abnormal drilling data, resulting in drilling speed data containing a large number of invalid or abnormal values.
[0005] Trend characteristics are not obvious: the fluctuation of original depth data makes it difficult to extract the drilling speed change trend, affecting subsequent analysis and decision-making.
[0006] Therefore, there is an urgent need for a drilling speed calculation method that can be real-time, accurate and adaptive to various working conditions to improve the intelligent level of the drilling process. SUMMARY
[0007] The purpose of the present application is to provide a rotary drilling working condition drilling speed real-time calculation method based on dynamic reconstruction of a drill bit position to solve the problems of large data noise, poor real-time performance, weak working condition recognition ability and unclear trend characteristics of existing drilling speed calculation methods.
[0008] The above purpose of the present application is achieved by the following technical solutions: S1: real-time acquisition of original parameters in the drilling process, the original parameters including drilling depth, position data, time, pressurizing pressure, power head rotation speed and power head torque; S2: dynamic reconstruction of the position data using a local weighted regression algorithm to obtain the fitted drill bit position; S3: real-time calculation of the drilling speed based on the reconstructed drill bit position and time difference; S4: identification of the rotary drilling working condition based on expert experience and a preset threshold to select effective drilling speed data.
[0009] Optionally, step S2 comprises: constructing a design matrix containing bias terms and historical drill position data; calculating a weight matrix wherein the weight decays as the time distance between the sample point and the target point increases; solving the regression coefficients by weighted least squares method :
[0010] wherein, is the historical drill position data, is a regularization parameter to ensure the matrix invertible; denotes the identity matrix; denotes the transpose of the design matrix ; obtaining a real-time design matrix , fitting the drill position according to the regression coefficients and real-time data , as follows: .
[0011] Optionally, step S2 comprises: constructing a design matrix containing bias terms and historical drill position data; calculating a weight matrix wherein the weight decays as the time distance between the sample point and the target point increases; solving the regression coefficients by weighted least squares method :
[0012] wherein, is the historical drill position data, is a regularization parameter to ensure the matrix invertible; denotes the identity matrix; denotes the transpose of the design matrix ; obtaining a real-time design matrix , fitting the drill position according to the regression coefficients and real-time data , as follows: .
[0013] Optionally, step S3 comprises: the calculation formula of the drilling speed is:
[0014] wherein, and fitted bit position of the first and data points, and are corresponding times.
[0015] Optionally, step S4 comprises: The identification threshold of the rotary drilling condition comprises: The bit position is consistent with the drilling depth; The pressurized pressure is greater than 0 MPa; The rotary speed of the power head is greater than 0 rpm; The torque of the power head is greater than 0 MPa; The drilling speed is greater than 0 m / h.
[0016] Optionally, the method further comprises a drilling speed performance evaluation step based on the static error index and the static error index, comprising: The static error index:
[0017] The dynamic response index:
[0018] wherein, is the actual bit position of the first data points, is the fitted position of the first data points, is the drilling speed of the first data points; and n is the number of samples.
[0019] An electronic device comprises a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory, so that the electronic device executes a rotary drilling condition drilling speed real-time calculation method based on dynamic reconstruction of a bit position.
[0020] A computer-readable storage medium stores instructions, when the instructions are executed, a rotary drilling condition drilling speed real-time calculation method based on dynamic reconstruction of a bit position is executed.
[0021] The technical scheme provided by the application has the beneficial effects that: 1. The application realizes dynamic reconstruction of a bit position through a local weighted regression algorithm, effectively eliminates noise interference of original drilling data, lays a data foundation for drilling speed calculation, and avoids problems such as drilling speed fluctuation and unclear trend caused by original depth data.
[0022] 2. Based on the reconstructed position and real-time time difference, the drilling speed is calculated in real time, which provides basic data support for drilling process optimization and intelligent control.
[0023] 3. Based on expert experience and data analysis, the drilling speed data of rotary drilling working condition is screened, the effective drilling and abnormal working condition are accurately distinguished, the abnormal data interference is avoided, and the data foundation is laid for subsequent intelligent analysis. BRIEF DESCRIPTION OF DRAWINGS
[0024] The present application will be further described below in conjunction with the drawings and examples, wherein: Figure 1 is the overall flow chart of the dynamic reconstruction of the bit position and the drilling speed calculation in the embodiment of the present application; Figure 2 is the comparison chart of the original depth data and the reconstructed depth data in the embodiment of the present application; Figure 3 is the comparison result chart of the drilling speed real-time calculation under the rotary drilling working condition in the embodiment of the present application; Figure 4 is the schematic diagram of the electronic device structure in the embodiment of the present application. DETAILED DESCRIPTION
[0025] In order to have a clearer understanding of the technical features, objects and effects of the present application, the specific embodiments of the present application will be described in detail with reference to the drawings.
[0026] The embodiment of the present application provides a rotary drilling working condition drilling speed real-time calculation method based on dynamic reconstruction of bit position.
[0027] Please refer to Figure 1 , Figure 1 is the step chart of a rotary drilling working condition drilling speed real-time calculation method based on dynamic reconstruction of bit position in the embodiment of the present application, which comprises: S1: Real-time acquisition of original parameters in the drilling process, the original parameters including drilling depth, position data, time, pressurizing pressure, power head rotating speed, power head torque; S2: Dynamic reconstruction of the position data by using local weighted regression algorithm to obtain the fitted bit position; S3: Real-time calculation of the drilling speed based on the reconstructed bit position and the time difference; S4: Identification of the rotary drilling working condition based on expert experience and preset threshold value, and screening of effective drilling speed data.
[0028] Through the above technical scheme, the drilling speed parameter is calculated in real time according to the real-time drilling data bit position and time, which effectively solves the problems of accurate parameter and low parameter calculation precision of traditional method. And the rotary drilling working condition data set is formed by combining expert experience and data analysis, which lays a data foundation for subsequent intelligent analysis of drilling process.
[0029] The application provides an implementation example as follows: real-time acquisition of original drilling parameters, re-fitting of bit position parameters through a local weighted regression algorithm, and realization of dynamic reconstruction of bit position data; secondly, real-time calculation of drilling speed based on the difference between the reconstructed bit position and drilling time, to avoid problems such as drilling speed fluctuation and unclear trend caused by original depth data; finally, screening of rotary drilling condition drilling speed data based on expert experience and data analysis, and elimination of abnormal drilling condition data such as uphole and sweep hole, to ensure the effectiveness of the drilling speed data. Compared with the traditional drilling speed parameter calculation method, the method has real-time and accuracy. The application provides beneficial support and laying for real-time calculation of complex geological drilling process parameters.
[0030] Step S2 comprises: Constructing a design matrix containing a bias term and historical bit position data; Calculating a weight matrix , the weight decays with the increase of the time distance between the sample point and the target point; Solving the regression coefficient through a weighted least square method :
[0031] wherein, is the historical bit position data, is a regularization parameter for ensuring the reversibility of the matrix; represents a unit matrix; represents the transpose of the design matrix ; Obtaining a real-time design matrix , fitting the bit position according to the regression coefficient and real-time data , as follows: .
[0032] Step S2 comprises: The calculation of the weight matrix uses a Gaussian kernel function:
[0033] wherein, is the time of the i th sample point, is the target point time, is a time bandwidth parameter for controlling the decay rate of the weight; represents the weight matrix of the i th sample point; is an exponential function.
[0034] Step S3 comprises: The formula for calculating the penetration rate is:
[0035] wherein, and are the fitted bit positions of the first and data points, respectively. and are the corresponding times.
[0036] As an embodiment, the bit position data fitting indicators include: mean absolute error (MAE), root mean square error (RMSE), and normalized root mean square error (NRMSE).
[0037] Step S4 comprises: The identification threshold of the rotary drilling condition includes: the bit position is consistent with the drilling depth; the pressurizing pressure is > 0 MPa; the power head rotation speed is > 0 rpm; the power head torque is > 0 MPa; the penetration rate is > 0 m / h.
[0038] As an embodiment, the drilling process condition is identified in real time based on expert experience and data analysis, and the abnormal drilling condition data such as up and down drilling and hole sweeping is removed, the rotary drilling condition data is screened in real time, and the penetration rate data is effectively matched with the effective drilling process, thereby laying a foundation for subsequent intelligent analysis.
[0039] The method further comprises a penetration rate calculation performance evaluation step based on the static error indicator and the static error indicator, comprising: The static error indicator:
[0040] The dynamic response indicator:
[0041] wherein, is the actual bit position of the first sample, is the fitted position of the first sample, is the penetration rate of the first sample; and n is the number of samples.
[0042] In an embodiment, the overall process is as shown in Figure 1 , and the specific steps are as follows: Real-time acquisition of original parameters in the drilling process, the original parameters including drilling depth, drill bit position, time, pressurized pressure, power head rotating speed, power head torque and other drilling parameter data; A local weighted regression algorithm is introduced, original drill bit position data collected is refitted based on drill bit position data, and the drill bit position is refitted again in combination with a regression coefficient and real-time data. Figure 2 As shown in the results of comparison of the refitted drill bit position and the original drill bit position, Real-time drilling speed calculation: the time difference between adjacent drilling data and the refitted drill bit position difference are obtained according to real-time calculation data to obtain real-time drilling speed. Drilling condition recognition: drilling condition in the drilling process is recognized in real time based on expert experience and data analysis, non-normal drilling condition data such as up and down drilling and hole sweeping are removed, and rotating drilling condition data is selected in real time to ensure that drilling speed data is effectively matched with an effective drilling process, and to lay a foundation for subsequent intelligent analysis. Figure 3 As shown in the results of comparison of the refitted drill bit position and the original drill bit position, The method of the present application is compared with the traditional method, and the results are shown in Table 2.
[0043] The present application realizes dynamic reconstruction of the drill bit position by local weighted regression, filters noise, accurately identifies the rotating drilling condition in combination with expert experience and data analysis, can output drilling speed data more suitable for the real condition in real time, effectively improves the calculation accuracy and condition adaptability, and provides beneficial support and laying for real-time calculation of complex geological drilling process parameters.
[0044] Table 1: Comparison results of drill bit position fitting performance
[0045] Table 2: Drilling speed calculation performance of rotating drilling condition
[0046] The present application also discloses an electronic device.Figure 4 , Figure 4 is a structural schematic diagram of an electronic device disclosed by an embodiment of the present application. The electronic device 500 can include at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.
[0047] The communication bus 502 is configured to realize connection and communication between the components.
[0048] The user interface 503 can include a display screen, and the optional user interface 503 can further include a standard wired interface and a wireless interface.
[0049] The network interface 504 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
[0050] The present application also discloses a computer readable storage medium, which stores a plurality of instructions adapted to be loaded by a processor to execute the above-mentioned method for real-time calculation of rotary drilling speed in rotary drilling conditions based on dynamic reconstruction of drill bit position.
[0051] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. Any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure.
[0052] The present application is intended to cover any variations, uses, or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field of the present disclosure not recorded in the present disclosure. The specification and examples are only considered as exemplary, and the scope and spirit of the present disclosure are defined by the claims.
Claims
1. A method for real-time calculation of drilling speed in rotary drilling conditions based on dynamic reconstruction of bit position, characterized in that, The method comprises the following steps: S1: collecting original parameters in the drilling process in real time, the original parameters comprising drilling depth, position data, time, pressurizing pressure, power head rotating speed, power head torque; S2: using a local weighted regression algorithm to dynamically reconstruct the position data to obtain fitted drill bit position; S3: based on the reconstructed drill bit position and time difference, calculating drilling speed in real time; S4: identifying rotary drilling conditions based on expert experience and preset threshold to screen effective drilling speed data.
2. The method of claim 1, wherein the method is characterized by, Step S2 comprises: constructing a design matrix including a bias term and historical bit location data; Computing the weight matrix The weights decay as the temporal distance between the sample point and the target point increases. Solving the regression coefficients by weighted least squares : wherein, is historical bit location data, is a regularization parameter to ensure the matrix is invertible; denotes the identity matrix; denotes the transpose of the design matrix denotes the transpose of the design matrix Obtain real-time design matrix from regression coefficients and real-time data fit bit location as follows: .
3. The method of claim 2, wherein the method comprises: Step S2 comprises: The weight matrix The calculation employs a Gaussian kernel function: wherein, is the time of the th sample point, is the target point time, is a time-bandwidth parameter, controlling the decay speed of the weights; denotes the weight matrix of the th sample point; is an exponential function.
4. The method of claim 1, wherein the method is characterized by: Step S3 comprises: The calculation formula of the drilling speed is: wherein, and are the fitted bit positions of the first and data points, respectively, and are the corresponding times.
5. The method of claim 1, wherein the method is characterized by: Step S4 comprises: The identification threshold of the rotary drilling condition comprises: The drill bit position is consistent with the drilling depth; The pressurizing pressure is greater than 0 MPa; The power head rotating speed is greater than 0 rpm; The power head torque is greater than 0 MPa; The drilling speed is greater than 0 m / h.
6. The method of claim 1, wherein the method is characterized by: The method further comprises a drilling speed calculation performance evaluation step based on the static error index and the static error index, comprising: The static error index: The dynamic response index: in, For the first The actual drill bit position of each sample. For the first The fitting position of each sample. For the first The drilling rate of a sample; n is the number of samples.
7. An electronic device, comprising: The electronic device comprises a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to enable the electronic device to execute the rotary drilling condition drilling speed real-time calculation method based on dynamic reconstruction of drill bit position according to any one of claims 1-6.
8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions, when the instructions are executed by a computer, the method for calculating drilling speed in real time based on dynamic reconstruction of drill bit position in rotary drilling conditions according to any one of claims 1-6 is executed.