A wellbore trajectory design parameter optimization method based on sparrow search algorithm

Abstract

The application discloses a kind of to be drilled wellbore track intelligent design method based on sparrow search algorithm, first using three-dimensional model method as to be drilled wellbore track design model, the optimization parameter of three-dimensional to be drilled wellbore track is determined as wellbore curvature and stable section length;Then using track potential energy and track length as optimization target to the to be drilled wellbore track obtained is evaluated;Using sparrow search algorithm, establish multi-objective to be drilled wellbore track design parameter optimization model, using different range of design parameters is iterated, until iteration is completed, determine optimal to be drilled wellbore track design parameter.The optimal parameter of to be drilled wellbore track is determined by the method of the application, can fully improve to be drilled wellbore track design efficiency, effectively improve wellbore quality, provide basis for intelligent trajectory control in intelligent drilling system.

Description

Technical Field

[0001] This invention relates to the field of drilling technology, and in particular to an intelligent design method for the trajectory of a wellbore to be drilled based on the sparrow search algorithm. Background Technology

[0002] Intelligent drilling technology can significantly reduce manual labor and lower drilling costs, representing a cutting-edge technology in the global drilling field. Intelligent control and design of the wellbore trajectory during drilling is a crucial component of intelligent drilling technology. Intelligent wellbore trajectory design involves automatically correcting deviations when the actual drilling trajectory deviates from the designed trajectory. When the deviation is significant, the section to be drilled needs to be redesigned, and correction work performed according to the trajectory of that section to bring the actual drilling trajectory back to the designed trajectory or directly reach the target position. This achieves automatic identification and design of the intelligent wellbore trajectory. The main reasons for deviations between the actual drilling trajectory and the designed trajectory are twofold: firstly, inconsistencies between the actual and designed trajectories lead to trajectory deviations; secondly, uncertainties in the geological targets cause changes in the geological targets. In these cases, the wellbore trajectory needs to be redesigned to meet the new target points, i.e., the design of the wellbore trajectory to be drilled.

[0003] Currently, the design of wellbore trajectories mostly involves designing a trajectory based on a given set of data, followed by evaluation to see if it meets the requirements for subsequent operations. If it does not, parameters need to be adjusted, the trajectory redesigned, and evaluated again until a suitable wellbore trajectory is designed. This method of wellbore trajectory design is inefficient, and often the designed trajectory is not optimal. Summary of the Invention

[0004] To address the problem that current wellbore trajectory design is inefficient and often results in non-optimal trajectories, this invention provides a method for optimizing wellbore trajectory design parameters based on a sparrow search algorithm.

[0005] This invention utilizes the Multi-Objective Sparrow Search Algorithm (MOSSA) to comprehensively consider various wellbore trajectory evaluation indicators, establishing an intelligent update and optimization design model and method for the trajectory of a well to be drilled. This model is used to optimize the trajectory design parameters of the well to be drilled, intelligently designing the optimal trajectory that meets various drilling conditions, thus avoiding trajectory design failures caused by unreasonable parameters. Based on the established model, and guided by the principle of relatively small trajectory potential energy and trajectory length, a trajectory parameter optimization design scheme and steps based on the Sparrow Search algorithm are proposed. The research results have important guiding significance for ensuring the quality of wellbore trajectories in horizontal well drilling.

[0006] The method for optimizing the design parameters of a wellbore trajectory based on the sparrow search algorithm provided by this invention comprises the following steps:

[0007] S1. Determine the wellbore trajectory design parameters using a three-dimensional model method. The trajectory design parameters include the wellbore curvature k and the length of the stable inclination section L. 稳 .

[0008] The formula for calculating the wellbore curvature k is as follows:

[0009]

[0010] Where: k - wellbore curvature (° / 30m); γ - dogleg angle; ΔL - well depth variation (m);

[0011] cosγ=cosα1*cosα2+sinα1*sinα2*cosΔφ

[0012] In the formula: α1 and α2 are the inclination angles (°) of the upper and lower measuring points respectively; Δφ is the change in azimuth angle (°) between the upper and lower measuring points.

[0013] S2. Establish an orbit evaluation model with orbital potential energy and orbital length as optimization objectives.

[0014] The orbital potential energy is normalized to the potential energy increment per 100-meter well section, and the formula for calculating the orbital potential energy increment per 100-meter section is as follows:

[0015]

[0016] In the formula: -Increment in orbital potential energy; D n - Current well depth, m; ΔD i - Current wellbore footage increment, in meters; ΔD n -Total advance increment, in meters; - Current wellbore curvature, ° / 30m; - Current wellbore deflection, ° / 30m;

[0017] The formula for calculating the track length L is as follows:

[0018] L = L 稳 +L 圆

[0019] In the formula: L 稳 - Length of the stable inclined section, in meters; L 圆 - Length of the arc segment, in meters (m).

[0020] Length L of the arc segment 圆 The calculation formula is as follows:

[0021]

[0022]

[0023] In the formula: α i It is the well inclination angle. It is the azimuth angle, T is the dogleg severity, and k is the borehole curvature.

[0024] S3. Use the sparrow search algorithm to establish a multi-objective wellbore trajectory design parameter optimization model. The optimization parameter of the model is the length L of the stable inclination section. 稳 Given the wellbore curvature k, the optimization objectives are the orbit length and orbit potential energy.

[0025] Based on the three population groups provided by the model—discoverers, followers, and watchdogs—the iterative equations for their positions and velocities are as follows:

[0026] (1) The position update and iteration formula for the discoverer population is as follows:

[0027]

[0028] In the formula: t - the current iteration number; - The position information of the i-th sparrow in the j-th dimension in the t-th iteration; α - a random number in [0,1]; R2 - warning value, ranging from [0,1]; ST - safety value, ranging from [0.5,1]; Q - a random number following a normal distribution; L - a 1×d matrix with all elements equal to 1;

[0029] (2) The formula for iterating the follower's position is as follows:

[0030]

[0031] In the formula: X p -The current optimal position for the discoverer; - The location information of the worst global condition in the t-th iteration; A- is a 1×d matrix with all elements randomly set to 1 or -1, and A + =A T (AA T ) -1 ;

[0032] (3) The iterative formula for the position of the vigilant is as follows:

[0033]

[0034] In the formula: β- is the step size control parameter, which is a random number that follows a normal distribution with a mean of 0 and a variance of 1; - The location information of the global optimum in the t-th iteration; K- is a random number in [-1, 1]; f i - Current fitness value of the sparrow; f g - The current global best fitness value; f w - The current worst fitness value globally; ε- is the smallest constant to avoid zero in the denominator.

[0035] The optimization model for the multi-objective wellbore trajectory design parameters is constructed as follows:

[0036] S31. The parameters of the wellbore trajectory optimization model are: first stable section length L1, first dogleg degree K1, and intermediate stable section length L... h The five parameters, namely, the second dogleg degree K2, the target front stabilization section length L2, constitute the optimization parameters for multi-target optimization.

[0037] S32. Substitute the parameters determined in step S31 into the three-dimensional model method to calculate other required parameters, and substitute them into the orbital potential energy and orbital length formulas to calculate the orbital potential energy and orbital length.

[0038] S33. In multi-objective optimization, the optimization method is to determine the Pareto optimal dominance situation, store the non-dominated solutions (that is, the points where there is no point that is better than the solution of the individual in all aspects) in a set, divide the individual information in the set by the grid method, and select the individual with the smallest density as the optimal solution by calculating the density.

[0039] S4. Optimize the calculation using parameters within different ranges until the number of iterations reaches the specified number. The optimal parameters are then the global optimal solution after the last iteration.

[0040] The solutions generated in each iteration are sorted using a non-dominated sorting method based on grid partitioning. After each iteration, the individual with the lowest Pareto rank (1) and lowest density in the grid is the optimal solution. Conversely, the individual with the highest Pareto rank and highest density in the grid is the worst solution. After a certain number of iterations, the optimal solution is the position of the individual with the lowest density in the grid after the last iteration (Pareto rank 1).

[0041] The Pareto rank is defined as follows: in a set of solutions, the Pareto rank of the non-dominated solution is defined as 1. Then, after removing the non-dominated solution from the set of solutions, the Pareto rank of the remaining non-dominated solution is defined as 2, and so on for the Pareto rank of all individuals.

[0042] A set of track parameters refers to a range of parameters within a reasonable range for engineering purposes, rather than a fixed value.

[0043] The optimization design of the wellbore trajectory parameters is guided by the relatively small trajectory potential energy and trajectory length.

[0044] Compared with the prior art, the advantages of the present invention are:

[0045] (1) This invention relies on a three-dimensional wellbore trajectory model based on a sloping circular arc, and the selected optimization parameters are more in line with the actual working conditions.

[0046] (2) The present invention takes the wellbore trajectory evaluation index as the optimization target, reduces the evaluation steps of the wellbore trajectory to be drilled, and is conducive to improving the design efficiency of the wellbore trajectory to be drilled.

[0047] (3) The present invention uses the sparrow search algorithm to optimize the design parameters, which improves the efficiency of the design of the wellbore trajectory and overcomes the shortcomings of the existing wellbore trajectory design method which relies too much on human experience to select design parameters and is difficult to obtain the optimal trajectory. It provides a basis for intelligent trajectory control in intelligent drilling systems.

[0048] Other advantages, objectives and features of the present invention will become apparent in part from the following description, and in part from those skilled in the art through study and practice of the invention. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating the method for optimizing the design parameters of the wellbore trajectory based on the sparrow search algorithm of the present invention.

[0050] Figure 2 This is a three-dimensional model method for designing the trajectory of the wellbore to be drilled.

[0051] Figure 3 This is an iterative diagram of the sparrow search algorithm. Detailed Implementation

[0052] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0053] like Figure 1 As shown, the method for optimizing the design parameters of a wellbore trajectory based on the sparrow search algorithm of the present invention includes four steps: S1, determining the design parameters of the wellbore trajectory; S2, establishing a trajectory evaluation model with trajectory potential energy and length as objectives; S3, establishing a multi-objective optimization model for the design parameters of the wellbore trajectory; and S4, iteratively calculating the optimal wellbore trajectory parameters using parameters within different ranges.

[0054] The specific steps of this method are as follows:

[0055] First, the wellbore trajectory is designed using a three-dimensional model method, such as... Figure 2 As shown in the figure, S is the design starting point, s is the tangent vector of the starting point, T is the target point, and t is the tangent vector of the target point. The coordinates and inclination of points S and T are known conditions. L1 is the length of the first stable inclination section, L... hL1 is the length of the intermediate stabilizing section, L2 is the length of the front stabilizing section, s1 and s2 represent the lengths of the arc segments, and L... m L is the distance from point A to M. n It is the distance from point C to N.

[0056] Using vector analysis theory and spatial geometric relationships, the following parameter calculation methods can be derived:

[0057]

[0058]

[0059]

[0060]

[0061] L m =r1tan(θ1 / 2) (5)

[0062] L n =r²tan(θ² / 2) (6)

[0063] In the formula, T s With T t Let be the projection lengths of |AD| onto vectors s and t, respectively; θ be the angle between vectors s and t; and L be the total length of the track.

[0064] From equation (1) to equation (6), we can obtain...

[0065]

[0066] L n =f1(r1,L1,L) h ,L2) (8)

[0067] In the formula,

[0068] a = 4[r2] 2 sin 2 θ-(T s +L h ) 2 ]

[0069]

[0070]

[0071] In addition, one can also obtain

[0072]

[0073] L n =f2(r2,L1,L) hL2) (10)

[0074] in,

[0075] a=(4r1 2 -L 2 +L h 2 (1-cosθ)-2(T) s +L h (T) t +L h )

[0076] b = 4r1 2 (T t -T s )+L h (1-cosθ)

[0077] c = r1 2 [(L 2 -L h (1-cosθ)-2(T) s -L h (T) t +L h )]

[0078] From equations (7), (8), (9), and (10), the constraint equations for the three-dimensional track design can be obtained as follows:

[0079] f1(r2,L1,L h ,L2)=f2(r1,L1,L h ,L2) (11)

[0080] f1(r1,L1,L h ,L2)=f2(r2,L1,L h ,L2) (12)

[0081] Find L m and L n After that, it can be obtained

[0082]

[0083] Where K1 is the first degree of sycophancy, and K2 is the second degree of sycophancy.

[0084] The values ​​of K1 and K2 can uniquely determine the designed trajectory in three-dimensional space, and the discriminant for its solution is:

[0085] Δ=b 2 -4ac≥0 (14)

[0086] Calculations are performed using an iterative method through computer-aided programming.

[0087] Orbital potential energy and orbital length are used as evaluation indicators, and the formula for calculating orbital potential energy is as follows:

[0088]

[0089] Where: k(x) - wellbore curvature (° / 30m); τ(x) - wellbore deflection (° / 30m); E w - Wellbore trajectory potential energy;

[0090] The wellbore curvature was obtained using the three-dimensional model method;

[0091] The formula for calculating wellbore deflection is as follows:

[0092]

[0093] In the formula: κ α - Well inclination change rate -Azimuth rate of change - First derivative of the rate of change of azimuth - First derivative of the rate of change of well inclination, k- Wellbore curvature;

[0094] The orbital potential energy can be further normalized to the potential energy increment over a specific well section, as given by the formula for the orbital potential energy increment:

[0095]

[0096] In the formula: -Increment in orbital potential energy; D n - Current well depth (m); ΔD i - Current well section footage increment (m); ΔD n -Total advance increment (m); - Current wellbore curvature (° / 30m); - Current wellbore deflection (° / 30m);

[0097] The above formula can be used to calculate the orbital potential energy increment of each well segment increment, avoiding the tedious steps of solving the entire well segment.

[0098] Since optimal orbital potential energy and optimal orbital length are often mutually exclusive, a smaller value in one will inevitably lead to a larger value in the other. Therefore, the orbital potential energy is further normalized to the potential energy increment per 100-meter well section for easy comparison. The formula for the orbital potential energy increment per 100 meters is as follows:

[0099]

[0100] In the formula: -Increment in orbital potential energy; D n - Current well depth (m); ΔD i- Current well section footage increment (m); ΔD n -Total advance increment (m); - Current wellbore curvature (° / 30m); - Current wellbore deflection (° / 30m);

[0101] As the second objective in multi-objective optimization, the calculation of the track length increment hinges on the calculation of the circular arc segment length. For the parameters sought, the length of the stable incline segment is relatively easy to calculate, while the length of the circular arc segment L... 圆 The calculation can be performed using the method of minimum curvature. The formula for the method of minimum curvature is as follows:

[0102]

[0103]

[0104]

[0105] In the formula: α i - Well inclination angle, - Azimuth, T- Dogleg severity, k- Borehole curvature.

[0106] The track length is calculated as follows:

[0107] L = L 稳 +L 圆 (twenty two)

[0108] In the formula: L 稳 - Length of the stable inclined section (m); L 圆 - Length of the arc segment (m);

[0109] When using the sparrow search algorithm to optimize the trajectory design parameters of a wellbore to be drilled, the optimization parameters should be clearly defined first, the objective function should be clearly defined second, and the optimization method should be determined finally.

[0110] The following steps are used to construct the multi-objective wellbore trajectory design parameter optimization model:

[0111] Step 1: From the constraint equations of equations (11) and (12), it can be seen that the conditions for designing the track are determined by the length of the first stable incline section L1, the first dogleg angle K1, and the length of the intermediate stable incline section L. h The second dogleg degree K2, the target front stabilizing section length L2, and five other segments are composed of these five segments. According to the design model constraints, the above five sets of data are known. Knowing four of the parameters can solve for the other unknown parameter.

[0112] Step 2: The parameters of the wellbore trajectory optimization model are the five parameters shown in Step 1. Taking a trajectory consisting of a circular arc segment + a stable inclination segment + a circular arc segment as an example, the design requirement is L1 = 0, L h >0, L2=0, L can be given during design.h The range of values ​​for K1 or K2 constitutes the optimization parameters for multi-objective optimization;

[0113] Step 3: The optimization objective is formed by equations (18) and (22). The parameters determined in step 2 are substituted into the three-dimensional model method to calculate other required parameters. The orbital potential energy and orbital length are calculated by substituting back into equations (18) and (22).

[0114] Step 4: In multi-objective optimization, the optimization method differs from the previous method of normalizing multiple objectives into a single function and then performing single-objective optimization. Instead, it determines the Pareto optimal dominance situation and stores non-dominated solutions (that is, points where there is no point that is better than the solution of this individual in all aspects) in a set. The individual information in this set is divided by the grid method, and the individual with the smallest density is selected as the optimal solution by calculating the density.

[0115] like Figure 3 As shown, the intelligent design method for wellbore trajectory based on the sparrow search algorithm has the following specific steps:

[0116] First, initialize the population and non-dominated solution set, assign initial values ​​to the parameters, generate an initial population P1, sort P1 according to the fast domination sort, divide P1 into discoverers and followers proportionally, let the current evolutionary generation be t, and complete the subsequent iterations when t is less than the total evolutionary generation.

[0117] Secondly, evolution produces the next generation of the population. Let the currently evolving individual j complete steps 1) to 4) below when j is smaller than the population size.

[0118] 1) Perform non-dominated sorting and output the Pareto rank of each individual. The Pareto rank is defined as follows: in a set of solutions, the Pareto rank of a non-dominated solution is defined as 1. If a non-dominated solution is removed from the set of solutions, the Pareto rank of the remaining non-dominated solutions is defined as 2, and so on, to obtain the Pareto rank of all individuals.

[0119] 2) Calculate the density information of individuals. Divide the target space into small regions using a grid, and use the number of individuals contained in each region as the density information of the individuals. The more individuals contained in the grid of an individual, the higher its density value, and vice versa.

[0120] 3) Select the optimal and worst solutions. The optimal solution is the individual with a Pareto level of 1 and the lowest density in the grid. Conversely, the worst solution is the individual with the highest Pareto level and the highest density in the grid.

[0121] 4) Based on the sparrow search algorithm, update the position information of the discoverer and follower in the group, and randomly select the guard to update the position. Individuals in the group search for the optimal solution under the guidance of the global optimal solution.

[0122] Finally, the individual information of the global optimal solution is output as the optimal parameters for the optimal wellbore trajectory.

[0123] In summary, the intelligent design method for wellbore trajectory based on the sparrow search algorithm provided by this invention optimizes the design parameters using the sparrow search algorithm, which can significantly improve the efficiency of wellbore trajectory design and effectively improve wellbore quality. It overcomes the shortcomings of existing wellbore trajectory design methods that rely too much on human experience in selecting design parameters and are difficult to obtain the optimal trajectory, thus providing a basis for intelligent trajectory control in intelligent drilling systems.

[0124] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for optimizing the design parameters of a wellbore trajectory based on a sparrow search algorithm, characterized in that, The steps are as follows: S1. Determine the wellbore trajectory design parameters using a three-dimensional model method. The trajectory design parameters include the wellbore curvature k and the length of the stable inclination section L. 稳 ; S2. Establish an orbit evaluation model with orbital potential energy and orbital length as optimization objectives; The orbital potential energy is normalized to the potential energy increment per 100-meter well section, and the formula for calculating the orbital potential energy increment per 100-meter section is as follows: In the formula: -Increment in orbital potential energy; D n - Current well depth, m; ΔD i - Current wellbore footage increment, in meters; ΔD n -Total advance increment, in meters; - Current wellbore curvature, ° / 30m; - Current wellbore deflection, ° / 30m; The formula for calculating the track length L is as follows: L=L 稳 +L 圆 In the formula: L 稳 - Length of the stable inclined section, in meters; L 圆 - Length of the arc segment, in meters; S3. Use the sparrow search algorithm to establish a multi-objective wellbore trajectory design parameter optimization model; the optimization parameter of the optimization model is the length L of the stable inclination section. 稳 Given the wellbore curvature k, the optimization objectives are orbit length and orbit potential energy; S4. Optimize the calculation using parameters within different ranges until the number of iterations reaches the specified number. The optimal parameters are then the global optimal solution after the last iteration.

2. The method for optimizing the design parameters of a wellbore trajectory based on the sparrow search algorithm as described in claim 1, characterized in that, In step S2, the length L of the arc segment 圆 The calculation formula is as follows: In the formula: α i It is the well inclination angle. It is the azimuth angle, T is the dogleg severity, and k is the borehole curvature.

3. The method for optimizing the design parameters of a wellbore trajectory based on the sparrow search algorithm as described in claim 1, characterized in that, In step S3, according to the three population types provided by the model, including discoverers, followers, and vigilants, the iterative equations for their positions and velocities are as follows: (1) The position update and iteration formula for the discoverer population is as follows: In the formula: t - the current iteration number; - The position information of the i-th sparrow in the j-th dimension during the t-th iteration; α is a random number in [0,1]; R2 - warning value, ranging from [0,1]; ST - safety value, ranging from [0.5,1]; Q - a random number following a normal distribution; L - a 1×d matrix with all elements equal to 1; (2) The formula for iterating the follower's position is as follows: In the formula: X p -The current optimal position for the discoverer; - The location information of the worst global condition in the t-th iteration; A- is a 1×d matrix with all elements randomly set to 1 or -1, and A + =A T (AA T ) -1 ; (3) The iterative formula for the position of the vigilant is as follows: In the formula: β- is the step size control parameter, which is a random number that follows a normal distribution with a mean of 0 and a variance of 1; - The location information of the global optimum in the t-th iteration; K is a random number in [-1, 1]; f i - Current fitness value of the sparrow; f g - The current global best fitness value; f w - The current worst fitness value globally; ε - The smallest constant to avoid zero in the denominator.

4. The method for optimizing the design parameters of a wellbore trajectory based on the sparrow search algorithm as described in claim 3, characterized in that, In step S3, the optimization model for the multi-objective wellbore trajectory design parameters is constructed as follows: S31. The parameters of the wellbore trajectory optimization model are: first stable section length L1, first dogleg degree K1, and intermediate stable section length L... h The five parameters, namely, the second dogleg degree K2, the target front stabilization section length L2, constitute the optimization parameters for multi-target optimization. S32. Substitute the parameters determined in step S31 into the three-dimensional model method to calculate other required parameters, and substitute them into the orbital potential energy and orbital length formulas to calculate the orbital potential energy and orbital length. S33. In multi-objective optimization, the optimization method is to determine the Pareto optimal dominance situation, store the non-dominated solutions in a set, divide the individual information in this set by the grid method, and select the individual with the smallest density as the optimal solution by calculating the density.

5. The method for optimizing the trajectory design parameters of a wellbore based on the sparrow search algorithm as described in claim 4, characterized in that, In step S4, the solutions generated in each iteration are sorted using a non-dominated sorting method based on grid partitioning. After each iteration, the individual with the lowest density in the grid and a Pareto level of 1 is the optimal solution; conversely, the individual with the highest Pareto level and the highest density in the grid is the worst solution. After reaching the required number of iterations, the optimal solution is the position of the individual with the lowest density in the grid and a Pareto level of 1 after the last iteration.

6. The method for optimizing the design parameters of a wellbore trajectory based on the sparrow search algorithm as described in claim 4 or 5, characterized in that, The Pareto rank is defined as follows: in a set of solutions, the Pareto rank of the non-dominated solution is defined as 1. Then, after removing the non-dominated solution from the set of solutions, the Pareto rank of the remaining non-dominated solution is defined as 2, and so on for the Pareto rank of all individuals.

Images