Intelligent PDC drill bit design system and method based on Unity

Abstract

The invention discloses a PDC drill bit intelligent design system and method based on Un-ity, and the system comprises a data input module which is used for receiving a drill bit design parameter set and a drilling working condition stratum data set; the hydraulic simulation optimization module is used for carrying out simulation analysis on a drill bit bottom hole flow field and chip migration on the basis of the design parameters and the drilling fluid parameters; the core algorithm module is used for carrying out quantitative evaluation on the drill bit design scheme and calculating four core performance indexes including aggressiveness, stability, deflecting capacity and matching performance; and the front end interaction and visualization module is used for generating a parameterized PDC drill bit three-dimensional model. According to the method, drill bit design parameters and stratum working condition data are deeply fused, the problems that traditional design and actual working conditions are disjointed, hydraulic performance evaluation depends on experience estimation, evaluation standards are subjective, iteration efficiency is low and the like are solved, rapid, quantitative and intelligent evaluation and optimization of a design scheme are achieved, and the method is suitable for large-scale popularization and application. And the scientificity, accuracy and efficiency of drill bit design are obviously improved.

Description

Technical Field

[0001] This invention relates to the field of drill bit design, and more specifically to a Unity-based intelligent design system and method for PDC drill bits. Background Technology

[0002] PDC drill bits, as core tools in drilling engineering, hold a crucial position in the field of oil drilling and production equipment technology. Their design performance directly impacts drilling efficiency, drill bit life, and overall operating costs. With the continuous development of the oil industry, the performance requirements for PDC drill bits are also increasing. Efficient and precise drill bit design is of great significance for reducing operating costs and improving extraction efficiency. However, traditional PDC drill bit design technology has gradually revealed many limitations when facing complex and ever-changing practical needs.

[0003] Traditional PDC drill bit design primarily relies on the personal experience of design engineers and semi-empirical formulas. When determining drill bit design parameters, such as the number of blades, crown profile, and cutting tooth layout, engineers typically depend on their accumulated experience and some semi-empirical formulas. When evaluating design options, designers often rely on subjective judgment to weigh multiple interdependent performance indicators such as the drill bit's aggressiveness, stability, and guiding performance. Furthermore, valuable design experience is mostly held by a few senior experts, and new engineers can only gradually accumulate experience through long-term practice and learning.

[0004] Traditional design methods have significant drawbacks. Firstly, they fail to fully and quantitatively integrate actual drilling conditions. The complex nonlinear coupling between drill bit design parameters and the formation characteristics and wellbore trajectory requirements of the target well section is not effectively addressed. Mismatch between the drill bit and the formation leads to low mechanical drilling rates and economic losses. Secondly, the evaluation of design schemes lacks unified, multi-dimensional quantitative standards. In particular, the evaluation of drill bit hydraulic performance often relies on rough estimates of total flow area (TFA) or hydraulic horsepower, failing to accurately predict bottomhole flow field, cleaning efficiency, and scour risk. Designers' subjective judgment makes rapid and accurate comparisons of scheme merits difficult, resulting in long design iteration cycles and low optimization efficiency. Furthermore, design knowledge is difficult to accumulate and pass on, new engineers struggle to quickly grasp design essentials, and the overall design capabilities of enterprises improve slowly. Summary of the Invention

[0005] The purpose of this invention is to overcome the above-mentioned technical deficiencies and propose an intelligent design system and method for PDC drill bits based on Unity.

[0006] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0007] This invention discloses an intelligent design system for PDC drill bits based on Unity, comprising:

[0008] The data input module is used to receive the set of drill bit design parameters and the drilling conditions and formation dataset under the target working conditions input by the user. The formation dataset includes the particle composition distribution, cohesion, friction strength and shear strength of the target formation.

[0009] The hydraulic simulation and optimization module, which is connected to the data input module, is used to perform simulation analysis on the hydraulic performance of the drill bit based on the hydraulic and flow parameters in the drill bit design parameter set and the drilling fluid parameters in the formation dataset.

[0010] The core algorithm module, which is connected to the data input module and the hydraulic simulation optimization module, is used to quantitatively evaluate the drill bit design scheme based on the drill bit design parameter set, the formation dataset, and the results of the hydraulic performance simulation analysis, and to calculate at least the following four core performance indicators: attack index, stability index, directional drilling capability index, and matching index.

[0011] The front-end interaction and visualization module, which is connected to the core algorithm module and the hydraulic simulation optimization module, is used to generate a parameterized PDC drill bit 3D model based on the drill bit design parameter set, and to display the evaluation results of the core performance indicators, the results of the hydraulic performance simulation analysis, and the design optimization suggestions in a visual form.

[0012] In some embodiments, the core algorithm module calculates the aggression index AI using at least one of the following methods:

[0013] a) Calculation method based on mechanical parameters, the formula of which is:

[0014]

[0015] Where T is the torque of the drill bit on the rock, W is the drilling pressure, and R is the drill bit radius;

[0016] b) A weighted calculation method based on geometric parameters, the empirical formula of which is:

[0017]

[0018] Where, n b Let n be the number of blade wings. c β is the total number of cutter teeth, and β is the average rake angle. ref For reference caster angle, w a1 ,w a2 ,w a3 These are the weighting coefficients.

[0019] In some embodiments, the core algorithm module uses at least one of the following methods to calculate the stability index SI:

[0020] a) A calculation method based on the force balance of the drill bit, the formula of which is:

[0021]

[0022] Among them, F x ,F y F is the resultant lateral force component acting on the drill bit from the bottom of the well. z Where K is the axial force, and K is the proportionality coefficient;

[0023] b) A comprehensive calculation method based on multi-factor weighting, the formula of which is:

[0024] SI = w s1 f bal +w s2 f var +w s3 f geo

[0025] Among them, f bal f is the tooth symmetry factor. var f is the torque or axial force fluctuation factor. geo For blade rigidity and vibration damping design factors, w s1 ,w s2 ,w s3 These are the weighting coefficients.

[0026] In some embodiments, the core algorithm module calculates the BRI (Browning Indices of Inclination) using a model that includes multiple weighted influence factors, and the formula is as follows:

[0027] BRI = w b1 f GL +w b2 (1-f GR )+w b3 f prof +w b4 δ side

[0028] Among them, f GL This is a factor set based on the diameter retention length GL, and this factor is inversely proportional to the diameter retention length; f GR The gauge tooth percentage is the ratio of the number of gauge teeth to the total number of teeth; f prof The guiding coefficient value is set according to the shape of the drill bit crown surface; δ side A factor characterizing whether there are lateral cutting structures such as protruding side edges on the blade wing; w b1 ,w b2 ,w b3 ,wb4 These are the weighting coefficients for each item.

[0029] In some embodiments, the core algorithm module calculates the matching index MI through the following steps:

[0030] a) Based on the input drilling conditions and formation dataset, determine an ideal drill bit feature vector D. ideal ;

[0031] b) Process the user-input drill bit design parameter set into the actual design vector D. user ;

[0032] c) Calculate the ideal drill bit eigenvector D using the following weighted Euclidean distance formula. ideal With actual design vector D user Distance L between them:

[0033]

[0034] Where i is the index of each design parameter, d i,ideal Let d be the value of the i-th parameter in the ideal design vector. i,user The value of the i-th parameter in the actual design vector, with weight w. mi The importance of matching is set according to each parameter;

[0035] d) Finally, the matching index is calculated using the following normalization formula:

[0036]

[0037] Among them, L max This represents the maximum possible distance value.

[0038] In some embodiments, the hydraulic simulation optimization module specifically includes:

[0039] a) Computational fluid dynamics simulation engine, which is used to automatically generate fluid domain meshes based on the parameterized PDC drill bit 3D model and simulate the bottom hole flow field distribution, pressure drop and flow velocity around the drill bit and nozzle outlet;

[0040] b) A cuttings transport and scour model, which is used to evaluate the transport trajectory and removal efficiency of drill cuttings at the bottom of the well based on the flow field distribution, using fluid-structure interaction or particle tracking algorithms, and to predict the risk areas of scour and wear of the drill bit body or formation.

[0041] c) A hydraulic parameter evaluation unit, which is used to calculate macroscopic hydraulic performance indicators, including at least drill bit pressure drop, total hydraulic power, unit hydraulic horsepower, or jet impact force.

[0042] In some embodiments, the core algorithm module further includes a rule-based expert model that stores and applies IF-THEN rules in the form of a knowledge base, wherein the IF-THEN rules include at least one of the following types:

[0043] a) Design guidelines and rules: formalize the expert experience in the field of drill bit design, and formulate rules for selecting the number of blades and the size of cutting teeth based on formation hardness, or rules for determining the gauge length based on well type requirements;

[0044] b) Indicator threshold rules: Based on the calculated values ​​of the Aggressiveness Index (AI), Stability Index (SI), Inclination Indicator (BRI), and Matching Index (MI), reasonable ranges and thresholds are set for evaluation and early warning.

[0045] c) Physical Model and Formula: A simplified physical model is embedded in the rule engine to calculate indicators characterizing the physical performance of the drill bit, including mechanical specific energy (MSE) or hydraulic performance parameters; and the expert model also compares the calculation results of the physical performance indicators with one or more of the four core performance indicators to cross-validate the evaluation results of the core performance indicators.

[0046] In some embodiments, the core algorithm module further includes a statistical analysis and machine learning model, which establishes a predictive model from drill bit design parameters to core performance indicators by mining and training historical data samples containing design-performance correspondences. The process includes:

[0047] a) Model training: Based on historical data, select machine learning algorithms such as multiple linear regression, random forest, gradient boosting decision tree or neural network according to the complexity of the relationship, and optimize through cross-validation;

[0048] b) Model embedding and updating: The trained model is embedded into the system as a plug-in to predict various indicator values ​​of user-submitted design schemes; and the system can perform regular incremental training and updating of the model based on new on-site feedback data to enable it to continuously adapt.

[0049] In some embodiments, the core algorithm module further includes a similar case reasoning module, which contains a case library storing historical drill bit designs, formation conditions, and actual drilling results, and provides decision support to users through the following steps:

[0050] a) Retrieval phase: Based on the key features of the design and working conditions currently input by the user, similarity measurement algorithms such as weighted Euclidean distance or cosine similarity are used to search for one or more most similar historical cases from the case library;

[0051] b) Reuse phase: Read the performance results of similar cases retrieved. If a case performs well, recommend its design scheme or key features; if a case exhibits a failure mode, issue a warning to the user.

[0052] c) Revision phase: When reusing cases, consider the differences between the current situation and historical cases, and make appropriate adjustments to the recommended solutions to enhance their relevance;

[0053] d) Evolutionary stage: Allows users to adopt and validate new design solutions and their results as new cases and store them in the case library, so as to continuously enrich and evolve the case library.

[0054] This invention also provides an intelligent design method for PDC drill bits based on Unity, comprising the following steps:

[0055] Receives user input of drill bit design parameter set and drilling condition and formation data set under target working conditions, including formation particle composition, cohesion, and friction strength;

[0056] Based on the drilling fluid parameters in the drill bit design parameter set and formation data set, the hydraulic performance of the drill bit is simulated and analyzed.

[0057] Based on the drill bit design parameter set, formation dataset, and the results of the hydraulic performance simulation analysis, the drill bit design scheme is quantitatively evaluated, and at least the following four core performance indicators are calculated: attack index, stability index, directional drilling capability index, and matching index.

[0058] A parameterized 3D model of the PDC drill bit is generated based on the drill bit design parameter set, and the evaluation results of the core performance indicators, the results of the hydraulic performance simulation analysis, and the design optimization suggestions are displayed in a visual form.

[0059] The steps for generating design optimization suggestions specifically generate at least one of the following types of suggestions:

[0060] a) Parameter adjustment suggestions: The system uses a preset expert rule base for reasoning. When one or more core performance indicators deviate from the preset threshold, the system provides specific design parameter modification directions for that indicator; or, when the hydraulic performance simulation analysis results are unsatisfactory, it provides modification suggestions for nozzle layout or flow channel structure.

[0061] b) Historical Case Reference: Retrieve the most similar cases to the current working conditions and design from the historical case library, and provide reference based on the actual drilling results of the cases; if the similar cases are successful, recommend that users learn from their key design features; if the similar cases are unsuccessful, issue warnings and summarize their design defects for users to avoid.

[0062] This invention provides a Unity-based intelligent design system and method for PDC drill bits, comprising:

[0063] Compared with existing technologies, the beneficial effects of the Unity-based intelligent design system and method for PDC drill bits provided by this invention are as follows: The system collects drill bit design parameters and operating condition data input by the user through a data input module, providing a foundation for subsequent evaluation and design. The hydraulic simulation optimization module and core algorithm module utilize this data for quantitative evaluation and intelligent analysis, calculating four core performance indicators and detailed hydraulic performance parameters, and generating optimization suggestions through various intelligent methods. The front-end interaction and visualization module presents the calculation results and optimization suggestions to the user in a visual manner, enabling the user to intuitively understand the performance of the drill bit design scheme and make adjustments based on the suggestions. This system architecture and workflow effectively solves problems such as the disconnect between design and operating conditions, reliance on rough estimations in hydraulic design, subjective evaluation standards, and low iteration efficiency in traditional drill bit design processes. It achieves integrated intelligent evaluation of design, performance, and hydraulics, improving the scientific nature, accuracy, and efficiency of drill bit design. It also facilitates the accumulation and inheritance of design knowledge, contributing to the improvement of the overall design capabilities of enterprises. Attached Figure Description

[0064] Figure 1 This is a flowchart illustrating an embodiment of the intelligent design method for PDC drill bits based on Unity provided by the present invention. Detailed Implementation

[0065] The technical solutions in the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. The described embodiments are only possible technical implementations of the present invention, but are not limited thereto. Other embodiments obtained by those skilled in the art in conjunction with the embodiments of the present invention without creative effort are also within the protection scope of the present invention.

[0066] This application mainly adopts an intelligent evaluation and optimization scheme that combines drill bit design and working condition data. This achieves the deep integration of drill bit design parameters and formation working condition data, enabling rapid, quantitative, and intelligent evaluation and optimization of the design scheme. The following is a further detailed description of this application.

[0067] Example 1

[0068] The Unity-based intelligent design system for PDC drill bits provided in this application includes a data input module, a hydraulic simulation optimization module, a core algorithm module, and a front-end interaction and visualization module. The data input module receives a set of drill bit design parameters and a dataset of drilling conditions and formation data under the target operating conditions from the user, and transmits this data to the hydraulic simulation optimization module and the core algorithm module. The hydraulic simulation optimization module performs CFD simulation based on the design parameters and drilling fluid parameters. The core algorithm module quantitatively evaluates the drill bit design scheme based on the received dataset and the hydraulic simulation results, and calculates the attack index, stability index, directional drilling capability index, and matching index. It then transmits the evaluation results and optimization suggestions to the front-end interaction and visualization module. The front-end interaction and visualization module generates a parameterized 3D model of the PDC drill bit based on the drill bit design parameter set and displays the evaluation results of the core performance indicators, the hydraulic simulation results, and the design optimization suggestions in a visual format. This allows users to intuitively understand the performance of the drill bit design scheme, facilitating design adjustments and optimizations.

[0069] Specifically, the data input module includes a user input interface and a data storage unit. The user input interface can be a web page, client software interface, etc., providing UI controls such as sliders, drop-down boxes, and input boxes for users to input or adjust drill bit design parameters and operating condition data. The set of drill bit design parameters input by the user covers overall structural parameters, cutting tooth arrangement parameters, hydraulic and flow channel parameters, gauge protection and anti-wear parameters, etc. For example, in the overall structural parameters, there are the number and shape of the cutter wings, the crown profile type (such as shallow cone, double cone, parabolic, etc.), and the inner cone height and outer cone surface radius. The cutting tooth arrangement parameters include the cutting tooth specifications (common ones include...). The parameters include: total number, back rake, side rake, and arrangement on the blade wings (such as number of tooth rows, tooth spacing, helix angle, etc.). Hydraulic and flow parameters include the width and depth of the flushing fluid flow channel (mud-covering trough), the number and diameter of nozzles, and the nozzle orientation angle. Gauge protection and anti-wear parameters include the length of the gauge protection section, the layout of the gauge protection surface and the inlay of hard materials, and the distribution of external cutting teeth.

[0070] The working condition and formation dataset includes formation lithology and strength, wellbore trajectory requirements, drilling parameter ranges, and historical data. Regarding formation lithology and strength, different rock types (such as sandstone, shale, and carbonate rocks) have different uniaxial compressive strengths (UCS) and rock abrasion indices. It further includes detailed rock mechanics parameters such as particle composition distribution (for assessing abrasion), cohesion c, internal friction angle (or overall frictional strength), and shear strength determined by these parameters, all of which affect drill bit design and performance. Wellbore trajectory requirements include well type (vertical, directional, or horizontal), designed build-up rate, and azimuth requirements, such as planned build-up rate targets (° / 30m) and dogleg severity. Drilling parameter ranges include expected weight on bit (WOB) and rotation speed (RPM) ranges, drilling fluid type and density, viscosity, and flow rate. Historical data includes the drill bit models used in similar formations in the past and their performance (such as footage, mechanical drilling rate of OP, failure modes, etc.).

[0071] After the data is input, the system will classify and standardize the data. For example, discrete design parameters such as the number of blades and the number of teeth will be mapped to qualitative design feature vectors, while continuous formation data such as rock hardness, abrasiveness, cohesion, and internal friction angle will be normalized to a standard scale for subsequent model calls.

[0072] The data storage unit stores user-inputted data for easy access by subsequent core algorithm modules. It can utilize database technologies such as relational databases like MySQL or non-relational databases like MongoDB to ensure secure and efficient data storage.

[0073] The hydraulic simulation and optimization module receives drill bit geometry parameters (especially flow channel and nozzle design) and drilling fluid parameters (density, viscosity, and flow rate) from the data input module. Based on a parameterized model generated by Unity, this module automatically meshes the fluid domain and includes a built-in engine for drill bit hydraulic analysis. Its specific functions include: a) A CFD simulation engine: This engine uses the finite volume method (FVM) to perform high-precision numerical simulations of the flow field around the drill bit. It automatically generates the computational domain and mesh based on the input parameterized drill bit model, solves the Navier-Stokes equations (or the RANS model), and obtains a detailed flow field distribution at the bottom of the well, including velocity, pressure distribution, and turbulence intensity at each point. b) A cuttings transport and scour model: Based on the CFD flow field calculation results, this module uses the Lagrange particle tracking method (LPT) or the discrete element method (DEM) coupled with CFD to simulate the transport trajectory of drill cuttings generated by the cutting teeth. By analyzing the residence time and movement path of the particles at the bottom of the well, the cuttings removal efficiency (CCE) is calculated. Simultaneously, based on the bottom-hole flow velocity and particle impact angle and frequency, the erosion wear rate of key components (such as nozzle outlet, cutter blade front surface, and gauge protection surface) is assessed. c) Hydraulic parameter evaluation unit: This unit calculates macroscopic hydraulic performance indicators, including total hydraulic power (THP) and drill bit pressure drop (ΔP), based on simulation results or empirical / semi-empirical formulas. bit The total flow area of ​​the nozzle (TFA), the unit water horsepower (HSI), and the impact force of the jet flow on the bottom of the well (F) j and effective coverage area.

[0074] The core algorithm module comprises a core index calculation model and an intelligent analysis model. The core index calculation model calculates four core indices to quantify the drill bit design's performance under target operating conditions. These four indices are the Attack Index (AI), Stability Index (SI), Bending Rate Index (BRI), and Matching Index (MI). Furthermore, the core algorithm module incorporates key hydraulic indices such as chip removal efficiency (CCE) and erosion wear rate calculated by the hydraulic simulation optimization module into the comprehensive evaluation system of the intelligent analysis model.

[0075] The Aggressiveness Index (AI) is used to characterize the "aggressiveness" of a drill bit in cutting rock, that is, the relative strength of the cutting effect produced by the drill bit per unit drilling pressure. The higher the AI ​​index, the "sharper" the drill bit is, but excessive aggression may sacrifice stability and lifespan.

[0076] When calculating the aggression index AI, at least one of the following methods is used:

[0077] a) Calculation method based on mechanical parameters, the formula of which is:

[0078]

[0079] Where T is the torque of the drill bit on the rock, W is the drilling pressure, and R is the drill bit radius; this ratio essentially measures the normalized torque generated per unit drilling pressure, and can approximately reflect the depth to which the tool cuts into the rock.

[0080] b) A weighted calculation method based on geometric parameters, the empirical formula of which is:

[0081]

[0082] Where, n b Let n be the number of blade wings. c β is the total number of cutter teeth, and β is the average rake angle. ref For reference caster angle, w a1 ,w a2 ,w a3 , where is the weighting coefficient. This formula shows that reducing the number of blade wings, reducing the total number of blade teeth, and reducing the rake angle all improve the AI ​​index.

[0083] The Stability Index (SI) reflects the smoothness of the drill bit during drilling, measuring its vibration resistance and force balance performance. A high SI indicates that the drill bit has a uniform load distribution and is less prone to severe vibration; a low SI, on the other hand, suggests the possibility of instability phenomena such as whirl and jumping.

[0084] When calculating the stability index SI, at least one of the following methods shall be used:

[0085] a) A calculation method based on the force balance of the drill bit, the formula of which is:

[0086]

[0087] Among them, F x ,F y F is the resultant lateral force component acting on the drill bit from the bottom of the well. z For axial force, K is the proportionality coefficient; when the drill bit is subjected to completely symmetrical forces, the lateral force is 0, SI = 1, which is the most stable state.

[0088] b) A comprehensive calculation method based on multi-factor weighting, the formula of which is:

[0089] SI = w s1 f bal +w s2 f var +w s3 f geo

[0090] Among them, f bal The tooth symmetry factor, f, can be used to calculate the force balance coefficient based on the uniformity of the tooth distribution. var The torque or axial force fluctuation factor can be used to calculate the vibration intensity based on the transient variation of drilling pressure-torque. geoConsidering the rigidity and vibration damping design factors of the blade wing, whether the blade wing adopts vibration damping designs such as helix angle and eccentric tooth arrangement; w s1 ,w s2 ,w s3 These are the weighting coefficients.

[0091] The core algorithm module calculates the build-up capability index (BRI) using a model incorporating multiple weighted influence factors. This index quantifies the directional performance of the drill bit in directional wells. A higher BRI indicates that the drill bit can more easily guide the wellbore away from its original trajectory. The calculation formula is as follows:

[0092] BRI = w b1 f GL +w b2 (1-f GR )+w b3 f prof +w b4 δ side

[0093] Among them, f GL This is a factor set based on the diameter retention length GL, and this factor is inversely proportional to the diameter retention length; f GR The gauge tooth percentage is the ratio of the number of gauge teeth to the total number of teeth; f prof The guiding coefficient value is set according to the shape of the drill bit crown surface (such as shallow cone, double cone, or conical); δ side A factor characterizing whether there are lateral cutting structures such as protruding side edges on the blade wing; w b1 ,w b2 ,w b3 ,w b4 These are the weighting coefficients for each item.

[0094] The matching index MI is used to evaluate the suitability of the designed drill bit for the target formation and operating conditions. The core algorithm module calculates the matching index MI through the following steps:

[0095] a) Based on the input drilling conditions and formation dataset, determine an ideal drill bit feature vector D. ideal For example, for hard and brittle formations with high cohesion and high frictional strength, D ideal The recommendation will tend to be more and smaller cutting teeth and a smaller rake angle to enhance durability; while for plastic formations with high cohesion but low frictional strength (such as mudstone), D ideal For directional wells, more aggressive cutting teeth (such as larger back slope angle) and larger flow channels may be recommended to facilitate chip removal; for directional wells, increasing the number of cutter wings and shortening the gauge length are recommended to balance stability and guidance.

[0096] b) Process the user-input drill bit design parameter set into the actual design vector D. user ;

[0097] c) Calculate the ideal drill bit eigenvector D using the following weighted Euclidean distance formula. ideal With actual design vector D user Distance L between them:

[0098]

[0099] Where i is the index of each design parameter, d i,ideal Let d be the value of the i-th parameter in the ideal design vector. i,user The value of the i-th parameter in the actual design vector, with weight w. mi The importance of matching is set according to each parameter;

[0100] d) Finally, the matching index is calculated using the following normalization formula:

[0101]

[0102] Among them, L max This represents the maximum possible distance value.

[0103] The intelligent analysis model includes a rule-based expert model, a statistical analysis and machine learning model, and a similar case reasoning (CBR) module.

[0104] Rule-based expert models store and apply IF-THEN rules in the form of a knowledge base, and the IF-THEN rules include at least one of the following types:

[0105] a) Design guidelines and rules: formalize the expert experience in the field of drill bit design, such as "choose multiple blades and small tooth diameters to improve wear resistance in hard formations", or rules for determining the gauge length according to well type requirements;

[0106] b) Threshold rules for indicators: Based on the calculated values ​​of the Aggressiveness Index (AI), Stability Index (SI), Inclination Capability Index (BRI), and Matching Index (MI), reasonable ranges and thresholds are set for evaluation and early warning. For example, a rule that "if SI is below 0.5, the design force balance is deemed poor"; or, thresholds are set based on the chip removal efficiency (CCE) and scour risk value calculated by the hydraulic simulation optimization module, such as "if CCE is below 70% or the cone scour rate is greater than the threshold, an early warning is issued regarding the risk of mudpacking or scour failure."

[0107] c) Physical Model and Formulas: A simplified physical model is embedded in the rule engine to calculate indices characterizing the physical performance of the drill bit, including mechanical specific energy (MSE) or hydraulic performance parameters; for example, a cutting model based on rock failure mechanics, such as a model based on the Mohr-Coulomb criterion, is introduced. This model uses the cohesion c and internal friction angle φ (or friction intensity) from the input formation parameters to calculate the shear strength τ required for the cutting teeth to break rock.

[0108] τ=c+σ n \tanφ

[0109] Where, σ n This represents the normal stress acting on the shear plane, and its value is related to the drilling pressure (W) and the geometry of the cutting teeth (such as the backslope). The particle composition distribution is used to assess the abrasiveness level of the formation and to correct the model's wear coefficient or influence the calculation of the MSE.

[0110] This physical model can be used to predict the torque (T) generated under a specific drilling pressure (W), thereby more accurately calculating the aggression index AI (AI = T / (W·R)), or to calculate MSE using the Teale formula to verify the rationality of the aggression prediction. Furthermore, the expert model will also compare the calculation results of the physical performance indicators with one or more of the four core performance indicators, or cross-validate them with the results of hydraulic simulations. For example, it can compare the low chip removal efficiency (CCE) obtained from CFD simulation with the high aggression index (AI) to provide early warning of the risk of "mud bagging".

[0111] Statistical analysis and machine learning models are used to establish predictive models from drill bit design parameters to core performance indicators and hydraulic performance indicators by mining and training historical data samples that correspond to design and performance. The process includes:

[0112] a) Model training: Based on historical data such as drill bit tests and field drilling records, select machine learning algorithms, such as multiple linear regression, random forest, gradient boosting decision tree (GBDT) or neural network, according to the complexity of the relationship, and optimize through cross-validation;

[0113] b) Model embedding and updating: The trained model is embedded into the system as a plug-in to predict various indicator values ​​of user-submitted design schemes; and the system can perform regular incremental training and updating of the model based on new on-site feedback data to enable it to continuously adapt.

[0114] The Similar Case Reasoning (CBR) module includes a case library storing historical drill bit designs, formation conditions, and actual drilling results. During the retrieval phase, based on the key features of the design and working conditions input by the user, similarity measurement algorithms such as weighted Euclidean distance or cosine similarity are used to search for the most similar historical cases in the case library, providing users with references. The similarity calculation can comprehensively consider two sub-indicators: formation matching and design similarity, synthesized into a total similarity score with certain weights. During the reuse phase, the performance results of the retrieved similar cases are read. If a case performs well, its design scheme or key features are recommended; if a case exhibits a failure mode, a warning is issued to the user. During the correction phase, considering the differences between the current situation and historical cases, the recommended schemes are appropriately adjusted to enhance their relevance. During the evolution phase, new design schemes adopted and validated by the user, along with their results, can be stored as new cases in the case library, enabling continuous enrichment and evolution of the case library.

[0115] The front-end interaction and visualization module includes a parametric modeling engine and a visualization rendering engine. The parametric modeling engine generates and updates the 3D model of the PDC drill bit in real time using procedural modeling technology, based on the drill bit design parameters input by the user. It can use Unity3D's Mesh modeling API interface, allowing users to write scripts to generate geometry such as cutter wings and cutting teeth in real time based on parameters such as the number of blades and crown contour, and then precisely position and rotate them to construct a complete drill bit model.

[0116] After the 3D model is generated, the system automatically extracts key geometric features for performance calculation and verification. For example, it calculates the blade spacing angle to check symmetry, calculates the cutting tooth distribution density by radius region, measures the length and area of ​​the caliper guard surface, and calculates the volume of the hydraulic channel. This data, directly extracted from the model, makes subsequent performance evaluations and hydraulic simulations more accurate and reliable.

[0117] The visualization rendering engine presents the 3D model, calculation results of core indicators, calculation results from the hydraulic simulation optimization module, and optimization suggestions to users in an intuitive and visual way. It utilizes Unity3D's rendering capabilities to render the 3D model for lighting, materials, and other aspects, making it more realistic. Calculation results of core indicators can be displayed using radar charts, bar charts, etc., allowing users to quickly understand the relative strength of each indicator. The system can also display the relative load of each area on the drill bit model surface using pseudo-color, for example, rendering areas with high loads in red. Optimization suggestions can be presented through text descriptions, color highlighting, or icon highlighting for easy user identification and reference. Simultaneously, the visualization rendering engine is also used to display hydraulic simulation results, such as: displaying the bottom-hole flow field distribution on the 3D model using streamlines, vector arrow diagrams, or slice diagrams; rendering the fluid erosion and wear risk areas or the cleanliness of the bottom of the drill bit surface in pseudo-color cloud map form; or displaying the migration trajectory and removal process of drill cuttings in animation. Optimization suggestions can be presented through text descriptions, color highlighting, or icon highlighting for easy user identification and reference. Finally, users can export a PDF report document containing design parameters, operating conditions, indicator charts, system recommendations, and 3D view snapshots with a single click.

[0118] Furthermore, the Unity 3D engine was chosen as the development platform for this invention because of its comprehensive advantages in parametric real-time modeling, advanced data visualization, and cross-platform compatibility. These advantages are crucial for realizing the core innovation of this invention—namely, the real-time and in-depth integration of PDC drill bit design parameters, performance evaluation, hydraulic simulation, and 3D visualization.

[0119] Specifically, the following specific features of the Unity platform provide indispensable technical support for the implementation of this invention:

[0120] (1) Powerful procedural modeling capabilities: One of the core functions of this invention is to generate a parametric 3D model of the PDC drill bit in real time based on a complex set of design parameters input by the user. Unity provides a powerful C# scripting interface, especially its underlying Mesh API, which allows developers to precisely control the geometric information of the 3D model, such as vertices, triangles, and normals, through code. This enables the system to efficiently achieve "procedural modeling": when the user adjusts parameters such as the number of blades, crown profile, and back rake angle of the cutting teeth, the system does not load or modify the preset CAD model, but instead recalculates and generates a completely new drill bit geometry that precisely conforms to the parameters in real time through scripts. This approach provides a foundation for rapid design iteration and optimization, which is difficult to match by traditional CAD software or general 3D platforms.

[0121] (2) Advanced, customizable rendering pipeline and shaders: This invention not only showcases the drill model, but more importantly, it presents the performance evaluation results in a visual manner. Unity's programmable rendering pipeline (such as URP / HDRP) and powerful shader development capabilities make advanced data visualization possible.

[0122] (3) Custom Shader: The load distribution, wear risk, or hydraulic scour area data calculated by the core algorithm module are directly rendered onto the surface of the drill bit's 3D model in the form of a pseudo-color cloud map. This visualization method, which accurately corresponds abstract performance data with specific model parts, greatly enhances the intuitiveness of the information and helps designers quickly identify the advantages and disadvantages of the design scheme, which is something that simple charts cannot achieve.

[0123] (4) Excellent cross-platform compatibility and integration: As a mature commercial engine, Unity supports one-click deployment of applications to multiple mainstream operating systems such as Windows and macOS. This allows the design system described in this invention to be easily deployed on the workstations of different engineers, demonstrating good versatility. Simultaneously, its flexible architecture facilitates the integration of third-party databases (for case studies), CFD computing cores (such as OpenFOAM), and external machine learning model libraries (such as TensorFlow, PyTorch, etc.), providing convenience for implementing advanced intelligent analysis functions such as statistical analysis and machine learning models.

[0124] (5) Highly Efficient Real-Time Interaction and UI System: This invention emphasizes that users can adjust parameters through the front-end interface and receive immediate feedback on models and performance metrics, forming a rapid design iteration loop. Unity's built-in UI system (UGUI) and event handling mechanism make the development of user interfaces containing complex controls such as sliders, input boxes, and interactive charts (such as radar charts) highly efficient. User operations can be captured in real time and quickly drive the recalculation of back-end algorithms and the refresh of front-end models, ensuring the smoothness of the entire design process and a "what you see is what you get" experience.

[0125] In summary, the Unity platform is not merely a visualization tool for this invention, but rather a comprehensive technological foundation integrating procedural modeling, advanced data visualization, real-time interaction, and cross-platform deployment capabilities. It is precisely this organic combination of specific functions that enables this invention to integrate the previously disconnected stages of "parameter definition," "performance calculation," "hydraulic analysis," and "scheme evaluation" in traditional PDC drill bit design into a seamless, efficient, and intelligent closed-loop design system.

[0126] The implementation principle of this embodiment is as follows: The system collects drill bit design parameters and operating condition data input by the user through the data input module, providing a foundation for subsequent evaluation and design. The hydraulic simulation optimization module and the core algorithm module use this data for quantitative evaluation and intelligent analysis, calculating four core performance indicators and hydraulic performance parameters, and generating optimization suggestions through various intelligent methods. The front-end interaction and visualization module presents the calculation results and optimization suggestions to the user in a visual manner, enabling the user to intuitively understand the performance of the drill bit design scheme and make adjustments based on the suggestions. This system architecture and workflow effectively solves the problems in the traditional drill bit design process, such as the disconnect between design and operating conditions, reliance on rough estimations in hydraulic design, subjective evaluation standards, and low iteration efficiency. It improves the scientificity, accuracy, and efficiency of drill bit design, while also facilitating the accumulation and inheritance of design knowledge, and contributing to the improvement of the overall design capabilities of enterprises.

[0127] Example 2

[0128] Please refer to Figure 1 The intelligent design method for PDC drill bits based on Unity provided in this application includes the following steps:

[0129] S1 receives the user-inputted set of drill bit design parameters and the drilling condition and formation dataset under the target operating conditions. The user initiates the design process through the input panel, inputting or loading a set of drill bit design parameters and operating condition data. The input panel offers various input methods, such as sliders, dropdown menus, and input boxes, facilitating parameter selection and adjustment.

[0130] S2 executes hydraulic performance simulation. Based on the drill bit design parameter set (especially hydraulic and flow channel parameters) and operating data (especially drilling fluid density, viscosity, and displacement) input in S1, the system calls the hydraulic simulation optimization module. This module first automatically generates a fluid domain mesh based on the parametric model, then starts the CFD simulation engine to calculate hydraulic performance indicators such as bottomhole flow field, drill bit pressure drop, cutter carry efficiency (CCE), and erosion wear risk.

[0131] S3, based on the drill bit design parameter set and formation dataset, quantitatively evaluates the drill bit design scheme and calculates at least the following four core performance indicators: attack power index, stability index, directional drilling capability index, and matching index. The core indicator calculation model in the core algorithm module calculates the four core indicators according to the input data, geometric features extracted from the generated 3D model, and hydraulic simulation results obtained in S2, following appropriate calculation methods. During the calculation process, it is necessary to ensure the accuracy of the data and the rationality of the calculation methods to obtain reliable evaluation results.

[0132] S4 generates a parameterized 3D model of the PDC drill bit based on the drill bit design parameter set, and displays the evaluation results of core performance indicators and design optimization suggestions in a visual format. The parameterized modeling engine generates the corresponding 3D drill bit model in real time using procedural modeling technology based on the input drill bit design parameters and displays it in a 3D window. The visualization rendering engine presents the calculation results of the core indicators in S3, the detailed results of the hydraulic simulation in S2 (such as flow field cloud maps and drill cuttings trajectory animations), and optimization suggestions to the user in an intuitive and visual way, such as through charts, text descriptions, and color or icon highlighting.

[0133] Specifically, in the step of generating design optimization suggestions, at least one of the following types of suggestions are generated:

[0134] (1) Parameter adjustment suggestions: The system uses a preset expert rule base for reasoning. When one or more core performance indicators deviate from the preset threshold, the system provides specific design parameter modification directions for that indicator. For example:

[0135] If the aggression is too low, it is recommended to "reduce the number of blades or increase the forward tilt angle to increase the unit rock breaking capacity";

[0136] When the Stability Index (SI) is too low, the system can analyze based on expert rules to determine if the cause is poor tooth symmetry or insufficient blade rigidity, and thus suggest "adding symmetrical blades or arranging balanced teeth".

[0137] If the lateral cutting ability (BRI) is weak, it is recommended to "shorten the diameter retention length or use an eccentric conical crown to enhance the lateral cutting ability";

[0138] If the hydraulic performance of the S2 simulation is poor, such as low chip removal efficiency (CCE), the system recommends "adjusting the nozzle angle to align it with the cutting tooth tip" or "optimizing the flow channel shape to reduce eddies"; if the risk of cone erosion wear is high, it recommends "reducing the corresponding nozzle diameter or adjusting the nozzle orientation to be away from vulnerable parts".

[0139] (2) Historical Case Reference: Retrieve the most similar cases to the current working conditions and design from the historical case library, and provide reference based on the actual drilling results of the cases. If the similar case is a successful case, recommend that users learn from its key design features; if the similar case is a failed case, issue warnings and summarize its design defects for users to avoid.

[0140] Furthermore, users decide whether to make modifications based on the visualized output. If the user accepts the suggestions and modifies the parameters, the process returns to S2 (hydraulic simulation) and S3 (quantitative evaluation), forming a rapid design iteration loop. Users can also select the "one-click optimization" function, allowing the system to automatically adjust parameters based on the suggestions and generate new design schemes for user evaluation. If the user is satisfied with the results, they can export a PDF report containing all information, ending the design process.

[0141] The implementation principle of this embodiment is as follows: This method receives user-input data, performs hydraulic simulation, quantitative evaluation, and index calculation in parallel / serial, generates a 3D model and visualization results, and provides design optimization suggestions, forming a complete drill bit design process. This method closely integrates drill bit design with actual working conditions, emphasizes both hydraulic and mechanical performance, and adopts quantitative evaluation standards, making the design process more scientific and objective. Through design optimization suggestions and rapid iterative closed loops, it can improve design efficiency, reduce design iteration cycles, and also facilitate new engineers to learn and master design essentials, promoting the inheritance of design knowledge and improving the overall design capabilities of the enterprise.

[0142] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A Unity-based intelligent design system for PDC drill bits, characterized in that, include: The data input module is used to receive the set of drill bit design parameters and the drilling conditions and formation dataset under the target working conditions input by the user. The formation dataset includes the particle composition distribution, cohesion, friction strength and shear strength of the target formation. The hydraulic simulation and optimization module, which is connected to the data input module, is used to perform simulation analysis on the hydraulic performance of the drill bit based on the hydraulic and flow parameters in the drill bit design parameter set and the drilling fluid parameters in the formation dataset. The core algorithm module, which is connected to the data input module and the hydraulic simulation optimization module, is used to quantitatively evaluate the drill bit design scheme based on the drill bit design parameter set, the formation dataset, and the results of the hydraulic performance simulation analysis, and to calculate at least the following four core performance indicators: attack index, stability index, directional drilling capability index, and matching index. The front-end interaction and visualization module, which is connected to the core algorithm module and the hydraulic simulation optimization module, is used to generate a parameterized PDC drill bit 3D model based on the drill bit design parameter set, and to display the evaluation results of the core performance indicators, the results of the hydraulic performance simulation analysis, and the design optimization suggestions in a visual form.

2. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, When calculating the aggression index AI, the core algorithm module employs at least one of the following methods: a) Calculation method based on mechanical parameters, the formula of which is: Where T is the torque of the drill bit on the rock, W is the drilling pressure, and R is the drill bit radius; b) A weighted calculation method based on geometric parameters, with the empirical formula as follows: Where, n b Let n be the number of blade wings. c β is the total number of cutter teeth, and β is the average rake angle. ref For reference caster angle, w a1 ,w a2 ,w a3 These are the weighting coefficients.

3. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, When calculating the stability index SI, the core algorithm module employs at least one of the following methods: a) A calculation method based on the force balance of the drill bit, the formula of which is: Among them, F x ,F y F is the resultant lateral force component acting on the drill bit from the bottom of the well. z Where K is the axial force, and K is the proportionality coefficient; b) A comprehensive calculation method based on multi-factor weighting, the formula of which is: SI=w s1 f bal +w s2 f var +w s3 f geo Among them, f bal f is the tooth symmetry factor. var f is the torque or axial force fluctuation factor. geo For blade rigidity and vibration damping design factors, w s1 ,w s2 ,w s3 These are the weighting coefficients.

4. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, The core algorithm module calculates the BRI (Browning Indices of Inclination) using a model that includes multiple weighted influence factors. The formula is as follows: BRI=w b1 f GL +w b2 (1-f GR )+w b3 f prof +w b4 δ side Among them, f GL f is a factor set based on the diameter retention length GL, and this factor is inversely proportional to the diameter retention length; GR The gauge tooth percentage is the ratio of the number of gauge teeth to the total number of teeth; f prof The guiding coefficient value is set according to the shape of the drill bit crown surface; δ side A factor characterizing whether there are lateral cutting structures such as protruding side edges on the blade wing; w b1 ,w b2 ,w b3 ,w b4 These are the weighting coefficients for each item.

5. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, The core algorithm module calculates the matching index MI through the following steps: a) Based on the input drilling conditions and formation dataset, determine an ideal drill bit feature vector D. ideal ; b) Process the user-input drill bit design parameter set into the actual design vector D. user ; c) Calculate the ideal drill bit eigenvector D using the following weighted Euclidean distance formula. ideal With actual design vector D user Distance L between them: Where i is the index of each design parameter, d i,ideal Let d be the value of the i-th parameter in the ideal design vector. i,user The value of the i-th parameter in the actual design vector, with weight w. mi The importance of matching is set according to each parameter; d) Finally, the matching index is calculated using the following normalization formula: Among them, L max This represents the maximum possible distance value.

6. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, The core algorithm module further includes a rule-based expert model, which stores and applies IF-THEN rules in the form of a knowledge base, and the IF-THEN rules include at least one of the following types: a) Design guidelines and rules: formalize the expert experience in the field of drill bit design, and formulate rules for selecting the number of blades and the size of cutting teeth based on formation hardness, or rules for determining the gauge length based on well type requirements; b) Indicator threshold rules: Based on the calculated values ​​of the Aggressiveness Index (AI), Stability Index (SI), Inclination Capability Index (BRI), and Matching Index (MI), reasonable ranges and thresholds are set for evaluation and early warning. c) Physical Model and Formula: A simplified physical model is embedded in the rule engine to calculate indicators characterizing the physical performance of the drill bit, including mechanical specific energy (MSE) or hydraulic performance parameters; and the expert model also compares the calculation results of the physical performance indicators with one or more of the four core performance indicators to cross-validate the evaluation results of the core performance indicators.

7. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, The hydraulic simulation optimization module specifically includes: a) Computational fluid dynamics simulation engine, which is used to automatically generate fluid domain meshes based on the parameterized PDC drill bit 3D model and simulate the bottom hole flow field distribution, pressure drop and flow velocity around the drill bit and nozzle outlet; b) A cuttings transport and scour model, which is used to evaluate the transport trajectory and removal efficiency of drill cuttings at the bottom of the well based on the flow field distribution, using fluid-structure interaction or particle tracking algorithms, and to predict the risk areas of scour and wear of the drill bit body or formation. c) A hydraulic parameter evaluation unit, which is used to calculate macroscopic hydraulic performance indicators, including at least drill bit pressure drop, total hydraulic power, unit hydraulic horsepower, or jet impact force.

8. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, The core algorithm module further includes a statistical analysis and machine learning model. This model establishes a predictive model from drill bit design parameters to core performance indicators by mining and training historical data samples containing design-performance correspondences. The process includes: a) Model training: Based on historical data, select machine learning algorithms such as multiple linear regression, random forest, gradient boosting decision tree or neural network according to the complexity of the relationship, and optimize through cross-validation; b) Model embedding and updating: The trained model is embedded into the system as a plug-in to predict various indicator values ​​of user-submitted design schemes; and the system can perform regular incremental training and updating of the model based on new on-site feedback data to enable it to continuously adapt.

9. The intelligent design system for PDC drill bits based on Unity according to claim 1, characterized in that, The core algorithm module further includes a similar case reasoning module, which contains a case library storing historical drill bit designs, formation conditions, and actual drilling results, and provides decision support to users through the following steps: a) Retrieval phase: Based on the key features of the design and working conditions currently input by the user, similarity measurement algorithms such as weighted Euclidean distance or cosine similarity are used to search for one or more most similar historical cases from the case library; b) Reuse phase: Read the performance results of similar cases retrieved. If a case performs well, recommend its design scheme or key features; if a case exhibits a failure mode, issue a warning to the user. c) Revision phase: When reusing cases, consider the differences between the current situation and historical cases, and make appropriate adjustments to the recommended solutions to enhance their relevance; d) Evolutionary stage: Allows users to adopt and validate new design solutions and their results as new cases and store them in the case library, so as to continuously enrich and evolve the case library.

10. A Unity-based intelligent design method for PDC drill bits, characterized in that, Includes the following steps: Receives user input of drill bit design parameter set and drilling condition and formation data set under target working conditions, including formation particle composition, cohesion, and friction strength; Based on the drilling fluid parameters in the drill bit design parameter set and formation data set, the hydraulic performance of the drill bit is simulated and analyzed. Based on the drill bit design parameter set, formation dataset, and the results of the hydraulic performance simulation analysis, the drill bit design scheme is quantitatively evaluated, and at least the following four core performance indicators are calculated: attack index, stability index, directional drilling capability index, and matching index. A parameterized 3D model of the PDC drill bit is generated based on the drill bit design parameter set, and the evaluation results of the core performance indicators, the results of the hydraulic performance simulation analysis, and the design optimization suggestions are displayed in a visual form. The steps for generating design optimization suggestions specifically generate at least one of the following types of suggestions: a) Parameter adjustment suggestions: The system uses a preset expert rule base for reasoning. When one or more core performance indicators deviate from the preset threshold, the system provides specific design parameter modification directions for that indicator; or, when the hydraulic performance simulation analysis results are unsatisfactory, it provides modification suggestions for nozzle layout or flow channel structure. b) Historical Case Reference: Retrieve the most similar cases to the current working conditions and design from the historical case library, and provide reference based on the actual drilling results of the cases; if the similar cases are successful, recommend that users learn from their key design features; if the similar cases are unsuccessful, issue warnings and summarize their design defects for users to avoid.

Images