Method, system and equipment for predicting wear of drill bit along with well depth and medium
By acquiring multi-source data and using deep learning models to generate continuous drill bit wear curves with well depth, the problem of predicting drill bit wear across the entire well section in existing technologies has been solved. This enables accurate assessment of drill bit wear status and optimization of drilling parameters, thereby improving the level of intelligent decision-making in drilling operations.
Patent Information
- Application Number
- CN202511599178.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-04
- Publication Date
- 2026-02-10
AI Technical Summary
Existing drill bit wear prediction methods cannot predict the continuous wear process throughout the entire well section. Traditional methods have poor universality, laboratory simulations cannot reproduce the real downhole environment, and IADC wear rating can only provide endpoint data, which cannot meet the needs of intelligent drilling decision-making.
By acquiring logging data, drilling engineering data, formation mechanics data, and drilling fluid performance data, and combining them with IADC wear classification data, continuous drill bit wear curves with well depth are generated using well segmentation and deep learning models. Iterative optimization is then performed using bidirectional long short-term memory networks, bidirectional long short-term memory networks with attention mechanisms, or Transformer models.
It enables continuous prediction of drill bit wear curves throughout the entire well section, improving the efficiency and safety of drilling operations, and providing quantitative basis for drill bit remaining life assessment, drilling parameter optimization, and downhole risk early warning.
Smart Images
Figure CN121503218A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of oil and gas drilling engineering technology, and in particular to a method, system, equipment and medium for predicting drill bit wear as well depth increases. Background Technology
[0002] Drill bits are the core rock-breaking tools in drilling operations, and their downhole wear condition directly affects the rate of penetration, drilling safety, and operating costs. Accurate assessment of drill bit wear is a crucial prerequisite for optimizing drilling parameters, predicting remaining drill bit life, and thus reducing costs and increasing efficiency. However, due to the complex downhole environment and the lack of direct detection methods, continuous and accurate prediction of wear conditions remains a pressing technical challenge in this field.
[0003] Existing methods for predicting drill bit wear have significant limitations: empirical models based on a limited number of parameters such as drill pressure and rotational speed have poor universality; laboratory simulations struggle to reproduce the real downhole environment, limiting their guiding value; and the industry-standard IADC (International Association of Drilling Contractors) wear rating system only provides wear data at the entry and exit points, failing to reveal the continuous wear process throughout the wellbore, resulting in significant data sparsity. Given the highly nonlinear interaction between drilling parameters and formation, traditional methods struggle to establish effective models for continuous drill bit wear prediction with depth under the constraint of only endpoint wear data, severely hindering the improvement of intelligent drilling decision-making.
[0004] Therefore, a new method for predicting drill bit wear as well depth is urgently needed. Summary of the Invention
[0005] This invention provides a method, system, equipment, and medium for predicting drill bit wear as well depth, in order to overcome the deficiencies of the prior art.
[0006] This invention provides a method for predicting drill bit wear as well depth, comprising: Acquire logging data for the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; Acquire IADC wear rating data for the target drill bit as it enters and exits the target well section; Based on the logging data of the target well section, the target well section is divided into several sub-well sections; Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, for each sub-well section, the boundary constraints of each sub-well section are set according to the IADC wear rating data of the target drill bit entering and exiting each sub-well section, and the drill bit wear sub-curve with well depth of each sub-well section is obtained. The drill bit wear sub-curve with well depth of each sub-well section is then connected to obtain the initial drill bit wear curve with well depth of the target well section. Based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as well as the target well section's depth, the drill bit wear prediction model iteratively optimizes the initial drill bit wear curve until the model converges, using the drilling engineering data, formation mechanics data, and drilling fluid performance data of the target well section as well as the initial drill bit wear curve ...
[0007] According to the present invention, a method for predicting drill bit wear with well depth is provided. The drilling engineering data includes any one of the following parameters or any combination thereof: drilling pressure, rotational speed, torque, mechanical drilling speed, mechanical specific energy, pump pressure, pump displacement, and drill bit pressure drop; the formation mechanics data includes any one of the following parameters or any combination thereof: compressive strength, elastic modulus, Poisson's ratio, drillability index, and in-situ stress; the drilling fluid performance data includes any one of the following parameters or any combination thereof: density, apparent viscosity, plastic viscosity, dynamic shear force, API filtration loss, friction coefficient, and solid content.
[0008] According to the present invention, a method for predicting drill bit wear with well depth includes acquiring logging data of the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth, comprising: The logging data of the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data varying with well depth, are standardized. The standardization process includes any one or any combination of the following: Based on well depth, all parameter sequences are aligned and resampled to form a unified well depth-feature sequence; Missing data can be filled using linear interpolation, spline interpolation, or statistical methods based on adjacent well data; Statistical methods such as box plots and Z-scores are used to identify and remove outliers, thereby improving data quality.
[0009] According to the present invention, a method for predicting drill bit wear with well depth is provided, wherein acquiring IADC wear classification data of the target drill bit entering and exiting the target well section includes: The IADC wear grading data of the target drill bit entering and exiting the target well section is quantified to obtain a numerical quantity that can represent the overall wear degree of the target drill bit entering and exiting the target well section.
[0010] According to the present invention, a method for predicting drill bit wear with well depth includes quantifying the IADC wear classification data of the target drill bit entering and exiting the target well section to obtain a numerical quantity that can represent the overall wear degree of the target drill bit entering and exiting the target well section, comprising: Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, the wear level of each key part of the target drill bit when entering and exiting the target well section is obtained. Among them, each key part of the target drill bit has a weight coefficient set according to the drill bit type. Based on the wear levels of each key component when the target drill bit enters and exits the target well section and the weighting coefficients of each key component of the target drill bit, the overall wear level of the target drill bit when entering and exiting the target well section is obtained.
[0011] According to the present invention, a method for predicting drill bit wear with well depth is provided, wherein the target well section is divided into several sub-sections based on logging data of the target well section, including: Based on the logging data of the target well section, the target well section is divided into formation segments, and the abrupt changes in lithological interfaces and formation mechanical properties are identified. The target well section is then divided into several sub-sections with relatively consistent geological characteristics.
[0012] According to the present invention, a method for predicting drill bit wear with well depth is provided, wherein, based on the IADC wear grading data of the target drill bit entering and exiting the target well section, boundary constraints are set for each sub-well section according to the IADC wear grading data of the target drill bit entering and exiting each sub-well section, to obtain the drill bit wear sub-curve with well depth for each sub-well section, and the drill bit wear sub-curves with well depth for each sub-well section are connected to obtain the initial drill bit wear curve with well depth for the target well section, including: For each sub-well section, the overall wear degree of the target drill bit entering and exiting each sub-well section is used as the boundary constraint. Through interpolation or function fitting, the drill bit wear sub-curve with well depth for each sub-well section is generated. The drill bit wear sub-curves with well depth for each sub-well section are then connected to obtain the initial drill bit wear curve with well depth for the target well section. The function fitting method can be any of the following: linear interpolation, exponential function, or logarithmic function. The values of the initial drill bit wear curve with well depth in the target well section at the entry and exit points of the target well section are consistent with the overall wear degree values of the target drill bit entering and exiting the target well section obtained from the IADC wear grading data of the target drill bit entering and exiting the target well section.
[0013] According to the present invention, the drill bit wear prediction method with well depth adopts a network architecture of any of the following: Bi-Long Short-Term Memory Network (Bi-LSTM), Bi-Long Short-Term Memory Network with Attention Mechanism (Bi-LSTM-Attention), or Transformer model.
[0014] According to the present invention, a method for predicting drill bit wear as it deepens is provided, wherein the training strategy for the drill bit wear prediction model as it deepens includes any one of the following or any combination thereof: I. Endpoint Constraints: Add boundary constraint terms to the loss function to force the error between the model's predicted values at the well entry and exit points and the measured wear rating results to be less than a preset threshold. II. Multi-objective loss: Combine mean squared error loss (to ensure overall curve fit), boundary constraint loss (to ensure endpoint accuracy), and smoothing regularization term (to avoid excessive curve oscillation). III. Iterative Optimization: After each training cycle is completed, the difference between the predicted drill bit wear curve with well depth output by the current model and the current training target curve (initial drill bit wear curve with well depth) is calculated, and the training target of the next training cycle is updated using the data points of the predicted drill bit wear curve with well depth according to a preset ratio (such as 0.1), thereby realizing the dynamic self-correction of the training signal and making the prediction results gradually approach the actual wear law.
[0015] According to the present invention, a method for predicting drill bit wear with well depth is provided. The resulting drill bit wear curve with well depth can be used to achieve any of the following projects or any combination thereof: dynamic assessment of remaining drill bit life and determination of replacement timing, real-time optimization and adjustment of drilling parameters, early warning of downhole drilling risks, and scientific guidance for drill string assembly design.
[0016] The present invention also provides a drill bit wear prediction system as well as well depth, comprising: The first data acquisition module is used to: acquire logging data of the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; The second data acquisition module is used to acquire IADC wear classification data of the target drill bit entering and exiting the target well section; The well section division module is used to divide the target well section into several sub-well sections based on the logging data of the target well section. The initial drill bit wear curve construction module is used to: based on the IADC wear classification data of the target drill bit entering and exiting the target well section, set the boundary constraints of each sub-well section according to the IADC wear classification data of the target drill bit entering and exiting each sub-well section, obtain the drill bit wear sub-curve of each sub-well section as it travels with the well depth, and connect the drill bit wear sub-curves of each sub-well section as it travels with the well depth to obtain the initial drill bit wear curve as it travels with the well depth of the target well section; The drill bit wear curve prediction module is used to: based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as the target well section changes with well depth, iteratively optimize the initial drill bit wear curve using the drill bit wear prediction model as the target well section changes with well depth until the model converges, and obtain the final drill bit wear curve as the well depth predicted by the model.
[0017] The present invention also provides an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the computer program to implement any of the above-described methods for predicting drill bit wear with well depth.
[0018] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for predicting drill bit wear with well depth.
[0019] The present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute any of the above-described methods for predicting drill bit wear with well depth.
[0020] The present invention provides a method, system, equipment and medium for predicting drill bit wear as it goes deeper, which can bring at least the following benefits: by introducing an initial drill bit wear curve generation method based on well section division, the data provided by the traditional IADC wear classification, which only has two endpoints, is expanded into a continuous drill bit wear curve as it goes deeper throughout the entire well section, thereby achieving a complete characterization of the drill bit wear process under limited data conditions.
[0021] By integrating multi-source information such as logging data, drilling engineering parameters, formation mechanical properties, and drilling fluid performance, and utilizing the nonlinear fitting capability of deep learning models, the comprehensive impact of complex downhole conditions on drill bit wear can be accurately captured, enhancing the model's generalization ability under different geological conditions.
[0022] The generated drill bit wear curves with well depth can intuitively reflect the wear dynamics of the drill bit at different well depths, providing quantitative basis for key decisions such as drill bit remaining life assessment, drilling parameter optimization, and drill string assembly design. This helps to reduce the frequency of unplanned tripping in and out of the well, and improve drilling efficiency and safety. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0024] Figure 1 This is one of the flowcharts for a method to predict drill bit wear as well depth provided by the present invention.
[0025] Figure 2This is the second flowchart of a method for predicting drill bit wear with well depth provided by the present invention, showing the entire process from data acquisition and preprocessing, generation of initial drill bit wear curves with well depth, model training and iterative optimization to wear prediction and application.
[0026] Figure 3 This diagram illustrates the processing of drilling engineering data, formation mechanics data, and drilling fluid performance data, showing the integration and preprocessing flow of these data.
[0027] Figure 4 This diagram illustrates the numerical processing of IADC wear rating data, showing how to calculate the overall wear degree based on the wear level and weighting coefficient of each part of the drill bit.
[0028] Figure 5 This diagram illustrates the generation of the initial drill bit wear curve with well depth, demonstrating the specific method for generating the initial monitoring signal based on formation segmentation and interpolation functions.
[0029] Figure 6 This is a schematic diagram of the structure of a drill bit wear prediction system based on well depth provided by the present invention.
[0030] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, embodiments of this invention, and should not be construed as limiting the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention. In the description of this invention, it should be understood that the terminology used is for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0032] Figure 1 This is a schematic flowchart illustrating a method for predicting drill bit wear as it deepens in well, as provided by the present invention. The executing entity of this method can be any applicable terminal-side device or network-side device, such as a drill bit wear prediction device for well depth.
[0033] See Figure 1 The present invention provides a method for predicting drill bit wear as well depth, which may include: S110. Obtain logging data for the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth.
[0034] In one embodiment, the drilling engineering data includes data on any one of the following parameters or any combination thereof: drilling pressure, rotational speed, torque, mechanical drilling speed, mechanical specific energy, pump pressure, pump displacement, and drill bit pressure drop; the formation mechanics data includes data on any one of the following parameters or any combination thereof: compressive strength, elastic modulus, Poisson's ratio, drillability index, and in-situ stress; the drilling fluid performance data includes data on any one of the following parameters or any combination thereof: density, apparent viscosity, plastic viscosity, dynamic shear force, API filtration loss, friction coefficient, and solids content.
[0035] In one embodiment, after acquiring the logging data of the target well section and the drilling engineering data, formation mechanics data, and drilling fluid performance data varying with well depth, S110 can perform standardization processing on the logging data of the target well section and the drilling engineering data, formation mechanics data, and drilling fluid performance data varying with well depth. The standardization processing includes any one or any combination of the following: Based on well depth, all parameter sequences are aligned and resampled to form a unified well depth-feature sequence; Missing data can be filled using linear interpolation, spline interpolation, or statistical methods based on adjacent well data; Statistical methods such as box plots and Z-scores are used to identify and remove outliers, thereby improving data quality.
[0036] S120. Obtain IADC wear rating data for the target drill bit as it enters and exits the target well section.
[0037] In one embodiment, after acquiring the IADC wear rating data of the target drill bit entering and exiting the target well section, S120 can quantify the IADC wear rating data of the target drill bit entering and exiting the target well section to obtain a numerical quantity that can represent the overall wear degree of the target drill bit entering and exiting the target well section. The specific implementation includes the following steps: Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, the wear level of each key part (such as teeth, bearings, gauge parts) of the target drill bit when entering and exiting the target well section is obtained. Among them, each key part of the target drill bit has a weighting coefficient set according to the drill bit type (such as PDC drill bit, roller cone drill bit). Based on the wear levels of each key component when the target drill bit enters and exits the target well section and the weighting coefficients of each key component of the target drill bit, a weighted sum is obtained to obtain a value representing the overall wear degree of the target drill bit when entering and exiting the target well section.
[0038] S130. Based on the logging data of the target well section, divide the target well section into several sub-well sections.
[0039] In one embodiment, S130 can segment the target well section based on logging data, identify abrupt changes in lithological interfaces and formation mechanical properties (such as compressive strength), and divide the target well section into several sub-sections with relatively consistent geological characteristics. This segmentation is based on the fact that different lithologies (such as mudstone, sandstone, and limestone) exhibit significant differences in the wear mechanism and rate of the drill bit.
[0040] S140. Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, for each sub-well section, set the boundary constraints of each sub-well section according to the IADC wear rating data of the target drill bit entering and exiting each sub-well section, obtain the drill bit wear sub-curve with well depth for each sub-well section, and connect the drill bit wear sub-curves with well depth of each sub-well section to obtain the initial drill bit wear curve with well depth of the target well section.
[0041] To address the issue of sparse measured downhole wear data, this embodiment employs a weakly supervised learning method to generate an initial drill bit wear curve with well depth as a supervision signal for model pre-training, providing the model with a priori wear change trend that conforms to geological laws.
[0042] In one embodiment, S140 may include: For each sub-section (divided according to formation changes or construction stages), the overall wear degree value when the drill bit enters and exits the sub-section (derived from IADC wear classification or wellhead inspection) is used as a boundary constraint. Initial wear sub-curves for each sub-section are generated by interpolation or function fitting. The drill bit wear sub-curves of each sub-section with well depth are then connected to construct a continuous initial drill bit wear curve with well depth for the target well section. The function fitting method can be any of the following: linear interpolation, exponential function, or logarithmic function. For example, linear interpolation can be used in homogeneous soft formation well sections, while exponential function can be used in abrasive formation well sections to simulate possible accelerated wear.
[0043] To ensure physical consistency, the initial drill bit wear curve of the target well section at the entry and exit points of the target well section must be consistent with the overall wear degree value of the target drill bit entering and exiting the target well section, obtained from the IADC wear grading data of the target drill bit entering and exiting the target well section. This process essentially reconstructs a "weakly labeled" wear curve in the absence of continuous field measurements by using formation prior constraints and interpolation / fitting functions.
[0044] S150. Construct a drill bit wear prediction model with well depth and dynamically correct the initial wear curve. Based on the drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve with well depth of the target well section, the drill bit wear prediction model iteratively optimizes the initial drill bit wear curve with well depth using the drilling engineering data, formation mechanics data, and drilling fluid performance data of the target well section with well depth until the model converges, obtaining the final output of the drill bit wear prediction model with well depth: the drill bit wear curve with well depth.
[0045] In one embodiment, the drill bit wear prediction model with well depth employs a depth-time series prediction network, aiming to learn the complex nonlinear relationship between drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve with well depth (between well depth sequence and wear degree) of the target well section as well depth changes. The network architecture adopted by the drill bit wear prediction model with well depth can be any of the following: Bi-LSTM (Bi-LSTM, which can capture the forward and backward dependencies of drilling parameter sequences and is suitable for modeling nonlinear and temporal wear processes), Bi-LSTM-Attention (Bi-LSTM-Attention, which introduces an attention mechanism on the basis of Bi-LSTM to enhance the model's attention to key wear-influencing parameters), or Transformer model (based on self-attention mechanism, suitable for handling long sequence dependencies and feature interactions under large-scale data).
[0046] In one embodiment, the training strategy for the drill bit wear prediction model with well depth includes any one or any combination of the following: I. Endpoint Constraints: A boundary constraint term is added to the loss function to force the error between the model's predicted values at the well entry and exit points and the measured wear classification results to be less than a preset threshold, ensuring that the model is aligned with the actual wear trend at key control points. II. Multi-objective loss: The mean squared error loss (to ensure the overall curve fit), boundary constraint loss (to ensure the accuracy of the endpoints) and smoothing regularization term (to avoid excessive curve oscillation) are used in combination to achieve the overall smoothness and physical consistency of the wear curve; III. Iterative Optimization: After each training cycle, the difference between the predicted drill bit wear curve with well depth output by the current model and the current training target curve (initial drill bit wear curve with well depth) is calculated, and the training target for the next training cycle is updated using the data points of the predicted drill bit wear curve with well depth according to a preset ratio (such as 0.1). This achieves dynamic self-correction of the training signal. This mechanism is equivalent to allowing the model to learn the wear law in a "self-supervised" manner during training, so that the prediction results gradually approach the actual wear law.
[0047] The obtained drill bit wear curves with well depth can be used for the following engineering applications: Drill bit life management: Predict the remaining service life of drill bits based on wear trends to assist in decision-making regarding when to replace drill bits; Drilling parameter optimization: Identify abnormal wear zones and adjust drilling parameters such as drilling pressure and rotation speed to slow down wear. Downhole risk warning: When the predicted wear value or wear rate exceeds the safety threshold, the system can issue a risk warning in advance to prevent downhole failures caused by drill bit failure; Drill string assembly design support: Provides data-driven scientific references for drill bit selection and drill string assembly design in subsequent well sections or adjacent wells.
[0048] This invention provides a method for predicting drill bit wear as it deepens. By fusing multi-source drilling data and wear classification at the tripping and running-out points, an initial drill bit wear curve as it deepens is constructed as a weakly supervised signal. A deep learning model is then used for iterative optimization, ultimately generating a continuous drill bit wear curve as it deepens, conforming to formation and operating condition constraints. This invention achieves at least the following beneficial effects: 1. Effectively overcomes the limitations of data sparsity: By using a weakly supervised learning framework and a method for generating initial drill bit wear curves with well depth, the wear classification information at the only two points of entry and exit from the well is expanded into a continuous wear change curve within the well section, achieving high-precision wear prediction under sparse data conditions.
[0049] 2. Significantly improve prediction accuracy and generalization ability: By deeply integrating multi-source parameters such as drilling engineering and formation mechanics, and utilizing the time-series modeling capability of deep learning models, the model can more accurately reflect the comprehensive impact of complex downhole conditions on drill bit wear, giving it good adaptability and generalizability.
[0050] 3. Enhance data support capabilities for drilling decisions: The generated drill bit wear curves with well depth can intuitively reflect the dynamic changes in drill bit wear with well depth, providing quantitative basis for drill bit remaining life prediction, real-time optimization of drilling parameters, and drill string assembly design, which helps to reduce unplanned tripping operations and improve drilling efficiency and safety.
[0051] This invention's method is applicable not only to common types of drill bits such as PDC and roller cone bits, but also to novel drill bits such as hybrid bits. The method is suitable for various well types, including vertical, directional, and horizontal wells, and exhibits good adaptability to different operating conditions. Furthermore, this method can be integrated with real-time drilling data systems to achieve online prediction of drill bit wear and intelligent decision support.
[0052] The drill bit wear prediction system with well depth provided by the present invention is described below. The drill bit wear prediction system with well depth described below can be referred to in correspondence with the drill bit wear prediction method with well depth described above.
[0053] See Figure 6The present invention provides a drill bit wear prediction system based on well depth, which may include: The first data acquisition module is used to: acquire logging data of the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; The second data acquisition module is used to acquire IADC wear classification data of the target drill bit entering and exiting the target well section; The well section division module is used to divide the target well section into several sub-well sections based on the logging data of the target well section. The initial drill bit wear curve construction module is used to: based on the IADC wear classification data of the target drill bit entering and exiting the target well section, set the boundary constraints of each sub-well section according to the IADC wear classification data of the target drill bit entering and exiting each sub-well section, obtain the drill bit wear sub-curve of each sub-well section as it travels with the well depth, and connect the drill bit wear sub-curves of each sub-well section as it travels with the well depth to obtain the initial drill bit wear curve as it travels with the well depth of the target well section; The drill bit wear curve prediction module is used to: based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as the target well section changes with well depth, iteratively optimize the initial drill bit wear curve using the drill bit wear prediction model as the target well section changes with well depth until the model converges, and obtain the final drill bit wear curve as the well depth predicted by the model.
[0054] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communications interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute the following steps: Acquire logging data for the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; Acquire IADC wear rating data for the target drill bit as it enters and exits the target well section; Based on the logging data of the target well section, the target well section is divided into several sub-well sections; Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, for each sub-well section, the boundary constraints of each sub-well section are set according to the IADC wear rating data of the target drill bit entering and exiting each sub-well section, and the drill bit wear sub-curve with well depth of each sub-well section is obtained. The drill bit wear sub-curve with well depth of each sub-well section is then connected to obtain the initial drill bit wear curve with well depth of the target well section. Based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as well as the target well section's depth, the drill bit wear prediction model iteratively optimizes the initial drill bit wear curve until the model converges, using the drilling engineering data, formation mechanics data, and drilling fluid performance data of the target well section as well as the initial drill bit wear curve ...
[0055] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0056] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being able to be stored on a non-transitory computer-readable storage medium, and the computer program being executed by a processor, enabling the computer to perform the following steps: Acquire logging data for the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; Acquire IADC wear rating data for the target drill bit as it enters and exits the target well section; Based on the logging data of the target well section, the target well section is divided into several sub-well sections; Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, for each sub-well section, the boundary constraints of each sub-well section are set according to the IADC wear rating data of the target drill bit entering and exiting each sub-well section, and the drill bit wear sub-curve with well depth of each sub-well section is obtained. The drill bit wear sub-curve with well depth of each sub-well section is then connected to obtain the initial drill bit wear curve with well depth of the target well section. Based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as well as the target well section's depth, the drill bit wear prediction model iteratively optimizes the initial drill bit wear curve until the model converges, using the drilling engineering data, formation mechanics data, and drilling fluid performance data of the target well section as well as the initial drill bit wear curve ...
[0057] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps: Acquire logging data for the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; Acquire IADC wear rating data for the target drill bit as it enters and exits the target well section; Based on the logging data of the target well section, the target well section is divided into several sub-well sections; Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, for each sub-well section, the boundary constraints of each sub-well section are set according to the IADC wear rating data of the target drill bit entering and exiting each sub-well section, and the drill bit wear sub-curve with well depth of each sub-well section is obtained. The drill bit wear sub-curve with well depth of each sub-well section is then connected to obtain the initial drill bit wear curve with well depth of the target well section. Based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as well as the target well section's depth, the drill bit wear prediction model iteratively optimizes the initial drill bit wear curve until the model converges, using the drilling engineering data, formation mechanics data, and drilling fluid performance data of the target well section as well as the initial drill bit wear curve ...
[0058] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0059] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0060] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for predicting drill bit wear as well depth, characterized in that, include: Acquire logging data for the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; Acquire IADC wear rating data for the target drill bit as it enters and exits the target well section; Based on the logging data of the target well section, the target well section is divided into several sub-well sections; Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, for each sub-well section, the boundary constraints of each sub-well section are set according to the IADC wear rating data of the target drill bit entering and exiting each sub-well section, and the drill bit wear sub-curve with well depth of each sub-well section is obtained. The drill bit wear sub-curve with well depth of each sub-well section is then connected to obtain the initial drill bit wear curve with well depth of the target well section. Based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as well as the target well section's depth, the drill bit wear prediction model iteratively optimizes the initial drill bit wear curve until the model converges, using the drilling engineering data, formation mechanics data, and drilling fluid performance data of the target well section as well as the initial drill bit wear curve ...
2. The method for predicting drill bit wear with well depth according to claim 1, characterized in that, Drilling engineering data includes data on any one of the following parameters or any combination thereof: drilling pressure, rotational speed, torque, mechanical drilling speed, mechanical specific energy, pump pressure, pump displacement, and drill bit pressure drop; Formation mechanics data includes data on any one of the following parameters or any combination thereof: compressive strength, elastic modulus, Poisson's ratio, drillability index, and in-situ stress; Drilling fluid performance data includes data on any one of the following parameters or any combination thereof: density, apparent viscosity, plastic viscosity, dynamic shear force, API filtration loss, friction coefficient, and solids content.
3. The method for predicting drill bit wear with well depth according to claim 2, characterized in that, The acquisition of IADC wear rating data for the target drill bit entering and exiting the target well section includes: Based on the IADC wear rating data of the target drill bit entering and exiting the target well section, the wear level of each key part of the target drill bit when entering and exiting the target well section is obtained. Among them, each key part of the target drill bit has a weight coefficient set according to the drill bit type. Based on the wear levels of each key component when the target drill bit enters and exits the target well section and the weighting coefficients of each key component of the target drill bit, the overall wear level of the target drill bit when entering and exiting the target well section is obtained.
4. The method for predicting drill bit wear with well depth according to claim 3, characterized in that, The process involves dividing the target well section into several sub-sections based on logging data, including: Based on the logging data of the target well section, the target well section is divided into formation segments, and the abrupt changes in lithological interfaces and formation mechanical properties are identified. The target well section is then divided into several sub-sections with relatively consistent geological characteristics.
5. The method for predicting drill bit wear with well depth according to claim 4, characterized in that, The process involves setting boundary constraints for each sub-well section based on the IADC wear grading data of the target drill bit entering and exiting the target well section, obtaining the drill bit wear sub-curve as well depth for each sub-well section, and connecting the drill bit wear sub-curves as well depth for each sub-well section to obtain the initial drill bit wear curve as well depth for the target well section. This includes: For each sub-well section, the overall wear degree of the target drill bit entering and exiting each sub-well section is used as the boundary constraint. Through interpolation or function fitting, the drill bit wear sub-curve with well depth for each sub-well section is generated. The drill bit wear sub-curves with well depth for each sub-well section are then connected to obtain the initial drill bit wear curve with well depth for the target well section. The function fitting method can be any of the following: linear interpolation, exponential function, or logarithmic function. The values of the initial drill bit wear curve with well depth in the target well section at the entry and exit points of the target well section are consistent with the overall wear degree values of the target drill bit entering and exiting the target well section obtained from the IADC wear grading data of the target drill bit entering and exiting the target well section.
6. The method for predicting drill bit wear with well depth according to any one of claims 1-5, characterized in that, The network architecture used in the drill bit wear prediction model with well depth is any one of the following: bidirectional long short-term memory network, bidirectional long short-term memory network with attention mechanism, or Transformer model.
7. The method for predicting drill bit wear with well depth according to claim 6, characterized in that, The training strategy for the drill bit wear prediction model with well depth includes any one of the following or any combination thereof: I. Add a boundary constraint term to the loss function to force the error between the model's predicted values at the well inlet and well outlet points and the measured wear rating results to be less than a preset threshold. II. Comprehensive use of mean squared error loss, boundary constraint loss, and smoothing regularization term; III. After each training cycle is completed, calculate the difference between the predicted drill bit wear curve with well depth output by the current model and the current training target curve, and use the data points of the predicted drill bit wear curve with well depth to update the training target curve of the next training cycle according to a preset ratio, thereby realizing the dynamic self-correction of the training signal.
8. A drill bit wear prediction system based on well depth, characterized in that, include: The first data acquisition module is used to: acquire logging data of the target well section, as well as drilling engineering data, formation mechanics data, and drilling fluid performance data that vary with well depth; The second data acquisition module is used to acquire IADC wear classification data of the target drill bit entering and exiting the target well section; The well section division module is used to divide the target well section into several sub-well sections based on the logging data of the target well section. The initial drill bit wear curve construction module is used to: based on the IADC wear classification data of the target drill bit entering and exiting the target well section, set the boundary constraints of each sub-well section according to the IADC wear classification data of the target drill bit entering and exiting each sub-well section, obtain the drill bit wear sub-curve of each sub-well section as it travels with the well depth, and connect the drill bit wear sub-curves of each sub-well section as it travels with the well depth to obtain the initial drill bit wear curve as it travels with the well depth of the target well section; The drill bit wear curve prediction module is used to: based on drilling engineering data, formation mechanics data, drilling fluid performance data, and the initial drill bit wear curve as the target well section changes with well depth, iteratively optimize the initial drill bit wear curve using the drill bit wear prediction model as the target well section changes with well depth until the model converges, and obtain the final drill bit wear curve as the well depth predicted by the model.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the drill bit wear prediction method as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the drill bit wear prediction method as described in any one of claims 1 to 7.