Drilling rate optimization method based on improved particle swarm optimization algorithm

Abstract

The invention relates to the field of geological exploration, in particular to a drilling speed optimization method based on an improved particle swarm optimization algorithm. According to the method, firstly, a fuzzy C-means clustering method is adopted, well drilling samples are classified, and the range of drilling parameter optimization adjustment is determined according to the classification result; then, a support vector regression method is adopted, and a drilling speed model is constructed; and finally, designing an improved particle swarm optimization algorithm, and determining an optimal operation parameter value. By the adoption of the drilling speed optimization method, the optimal operation range can be effectively given, the optimal model parameter value can be designed, reliable improvement of the drilling efficiency is achieved, and a good foundation is provided for optimal adjustment of drilling.

Description

Technical Field

[0001] The invention relates to the field of geological exploration, and in particular to a drilling speed optimization method based on an improved particle swarm optimization algorithm. Background Art

[0002] Resources and energy are the cornerstone and important guarantee for the stable development of the economy and society. In recent years, my country's demand for resources and energy has continued to remain high. In 2022, my country's energy consumption was initially calculated to be 5.41 billion tons of standard coal, 109.25 million tons of imported natural gas, 290 million tons of coal, and 508.28 million tons of crude oil. With the continuous changes in the international situation, the price of resources and energy has continued to rise, which has become an important constraint on the country's economic and social development. In recent years, with the gradual depletion of shallow resources and energy and the maturity of deep mineralization theory, the development of deep geological exploration technology has become an important way to solve the constraints.

[0003] Geological drilling is the core of geological exploration technology, which can be used to explore the location, content and geological structure of reservoirs for the development of underground resources and energy. In the process of geological drilling, the optimization setting of drilling parameters can effectively maintain the stable operation of the drilling process, and is also a key process to improve drilling safety and efficiency. How to optimize the setting of drilling parameters to effectively drive rock breaking and increase drilling speed is a key issue that needs to be solved.

[0004] In the rock-breaking process of deep geological drilling for thousands of meters, there is a strong solid-liquid-gas interaction at the bottom of the well, which accelerates the wear of the drill bit and drill string, reduces the quality of the wellbore, leads to a decrease in drilling speed, reduces the pure drilling time, and increases drilling costs. These complex geological environments and rock changes lead to complex nonlinear changes in the drilling process, which further bring about high-dimensional changes in the drilling process. The complex nonlinear and high-dimensional changes in the drilling process and the variability of the formation environment make it difficult to meet the complex and changeable drilling process by directly adjusting the drilling process through manual experience, resulting in low efficiency of the drilling process. Summary of the invention

[0005] In order to solve the problems of high-dimensional changes and low efficiency in deep complex geological drilling processes, the present invention provides a drilling speed optimization method based on an improved particle swarm optimization algorithm. For complex geological drilling processes, a suitable and reliable optimization method is designed to give the best drilling parameter values, effectively improve drilling efficiency, and provide good guidance for subsequent drilling process operations. The method mainly includes:

[0006] S1: Based on the data obtained at the drilling site, the fuzzy C-means clustering method is used to classify the drilling data;

[0007] S2: Before modeling, replace the abnormal points in the drilling data; based on the replaced sample data, use the support vector regression method, take the rotation speed, drilling pressure, depth and the current drilling speed as input, and the drilling speed at the next moment as output to build a drilling speed model;

[0008] S3: A particle swarm optimization algorithm with mixed weights, improved speed update mechanism and partial particle swarm update mechanism is designed. Based on the category determined by S1 and the drilling speed model constructed by S1, the drilling parameters are optimized and adjusted to achieve an increase in drilling speed.

[0009] A computer device includes a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm.

[0010] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm.

[0011] A computer program product includes a computer program or an instruction. When the program or the instruction is executed by a processor, the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm are implemented.

[0012] The technical solution provided by the present invention has the following beneficial effects: in the present invention, the optimal cluster number method designed for the fuzzy C-means clustering algorithm can effectively determine the optimal cluster number and provide an adjustment range of decision variables for drilling process operations; a support vector regression method is used to construct a drilling speed model to provide an alternative model for subsequent drilling speed optimization adjustment; an improved particle swarm optimization algorithm is designed for the drilling speed model based on the support vector regression method to determine the optimal operating parameter value, effectively solve the high-dimensional change problem of the drilling speed optimization process, achieve reliable improvement of drilling efficiency, and provide a good foundation for the optimization adjustment of the drilling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0014] Figure 1 is a structural diagram of a drilling speed optimization method based on an improved particle swarm optimization algorithm in an embodiment of the present invention;

[0015] Figure 2 1 is a simulation effect diagram of IEEE CEC2015 test function 1 in an embodiment of the present invention;

[0016] Figure 3 It is a simulation effect diagram of IEEE CEC2015 test function 2 in an embodiment of the present invention;

[0017] Figure 4 3 is a comparison diagram between the drilling speed optimization result and the actual drilling speed in the embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0019] Example 1

[0020] Please refer to Figure 1 , Figure 1 This is a structural diagram of a drilling speed optimization method based on an improved particle swarm optimization algorithm in an embodiment of the present invention. First, the fuzzy C-means clustering method is used to classify the drilling samples, and the range of drilling parameter optimization adjustment is determined according to the classification results. Then, the support vector regression method is used to construct a drilling speed model. Finally, an improved particle swarm optimization algorithm is designed to determine the optimal operating parameter value, and first optimize the drilling process. The specific steps of this method are as follows:

[0021] S1: Based on the data obtained at the drilling site, the fuzzy C-means clustering method is used to classify the drilling data; the specific implementation process of S1 is:

[0022] S1.1: Determine the upper limit θ of the number of clusters based on the number of rock types involved in the drilling data;

[0023] S1.2: Calculate the sum of the distances c from each cluster point to the corresponding cluster center cum :

[0024]

[0025] In the formula, m is the number of clusters in the iterative process, s j is the sample point, core i is the cluster center, S i is the set of points in the i-th cluster;

[0026] S1.3: Calculate the number of clusters m from 2 to θ c cum , the smallest c cum The corresponding number of clusters is the optimal number of clusters.

[0027] In this embodiment, the clustering of drilling data and the determination of the optimization adjustment range are as follows:

[0028] 870 sets of data from the drilling site were collected for optimization and adjustment analysis of the drilling process. The first 830 sets of data were used for fuzzy C-means clustering, and the last 40 sets of data were used for optimization and adjustment analysis. The 830 sets of data were clustered according to the aforementioned fuzzy C-means clustering method and the method for determining the number of clusters. Based on the clustering results, the categories of the last 40 sets of data were determined, and the adjustment range of the optimization process was determined according to the categories.

[0029] S2: Before modeling, replace the abnormal points in the drilling data; based on the replaced sample data, use the support vector regression method, take the rotation speed, drilling pressure, depth and the current drilling speed as input, and the drilling speed at the next moment as output to build a drilling speed model;

[0030] The process of replacing the abnormal points in the drilling data in S2 is to determine the quartile distance Q of the drilling data using the box plot method based on the acquired drilling data, and further calculate the distance q from each sample point to the sample mean i , if q i ≥5Q, the sample point is considered as an abnormal sample point and replaced with the nearest sample. The constructed drilling speed model is:

[0031]

[0032] In this example, based on the constructed drilling speed model, the model output is used as the optimization target, and the drilling pressure and rotation speed in the input are used as decision variables to optimize the drilling speed model.

[0033] S3: A particle swarm optimization algorithm with mixed weights, improved speed update mechanism and partial particle swarm update mechanism is designed. Based on the category determined by S1 and the drilling speed model constructed by S1, the drilling parameters are optimized and adjusted to achieve an increase in drilling speed.

[0034] In S3, the design of mixed weights, improved speed update mechanism and partial particle swarm update mechanism includes the following steps:

[0035] S3.1: During the population iteration process, the individual weights are updated by using a mixed weight consisting of two inertia weights and a random weight. The calculation formula of inertia weight 1 is as follows:

[0036]

[0037] Among them, w a1 is the inertia weight 1, w a-max is the upper limit of the inertia weight 1, γ 1 is a random positive number between 0 and 1, t is the current iteration number, and M is the maximum iteration number;

[0038] The calculation formula of inertia weight 2 is as follows:

[0039]

[0040] Among them, w a2 is the inertia weight 2;

[0041] Random weight w rand The calculation formula is as follows:

[0042]

[0043] Among them, γ 2 is another random positive number between 0 and 1.

[0044] Based on the inertia weight and random weight, calculate the final weight w:

[0045]

[0046] S3.2: Based on the final weight obtained, a new speed update mechanism is designed as follows:

[0047] When the fitness of the local optimal solution of the current individual is less than the fitness of the current individual, the speed is updated as follows:

[0048]

[0049] When the fitness of the individual's local optimal solution is greater than the current individual's fitness, the speed is updated as follows:

[0050]

[0051] Among them, p best,i is the local optimal solution of the current individual, z best is the global optimal solution, γ 3 , γ 4 , γ 5 is a random number, is the speed of the i-th individual in the t-1th iteration, is the position of the i-th individual in the t-th iteration, σ 1 and σ 2 are local and global learning factors, and their update process is as follows:

[0052] σ 1 =σ max -σ max *(tM) / (1-M)

[0053] σ 2 =σ min +σ min *(tM) / (1-M)

[0054] Among them, σ max is the maximum value of the learning factor σ, σ min is the minimum value of the learning factor σ;

[0055] S3.3: Design of partial particle swarm update mechanism

[0056] During the iteration process, when the iteration reaches 85% of the maximum number of iterations, according to the value of the fitness function, the speed and position of 10% of the last 20% of the population are replaced by the 10% of the population with the smallest fitness function value, and the position and speed of the remaining 10% of the population are reinitialized.

[0057] Based on the constructed drilling speed model and the determined adjustment range of the operating parameters, the designed improved particle swarm optimization algorithm is used to achieve drilling speed optimization. Before drilling speed optimization, the performance of the optimization algorithm is first analyzed using test function 1 and test function 2 in the IEEE CEC2015 test function set, such as Figure 2 and Figure 3 Further, the optimization results are compared with the actual results to analyze the effectiveness of the proposed invention, as shown in Figure 4 shown.

[0058] Example 2

[0059] A computer device includes a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm.

[0060] Example 3

[0061] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm.

[0062] Example 4

[0063] A computer program product includes a computer program or an instruction. When the program or the instruction is executed by a processor, the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm are implemented.

[0064] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A drilling speed optimization method based on an improved particle swarm optimization algorithm, characterized in that: include: S1: Based on the data obtained at the drilling site, the fuzzy C-means clustering method is used to classify the drilling data, and a drilling speed model is established based on the classified data; S2: Before modeling, replace the abnormal points in the drilling data; based on the replaced sample data, use the support vector regression method, take the rotation speed, drilling pressure, depth and the current drilling speed as input, and the drilling speed at the next moment as output to build a drilling speed model; S3: A particle swarm optimization algorithm with mixed weights, improved speed update mechanism and partial particle swarm update mechanism is designed. Based on the category determined by S1 and the drilling speed model constructed by S1, the drilling parameters are optimized and adjusted to achieve an increase in drilling speed.

2. A drilling speed optimization method based on improved particle swarm optimization algorithm as claimed in claim 1, characterized in that: The specific implementation process of S1 is: S1.1: Determine the upper limit θ of the number of clusters based on the number of rock types involved in the drilling data; S1.2: Calculate the sum of the distances c from each cluster point to the corresponding cluster center cum : In the formula, m is the number of clusters in the iterative process, s j is the sample point, core i is the cluster center, S i is the set of points in the i-th cluster; S1.3: Calculate the number of clusters m from 2 to θ c cum , the smallest c cum The corresponding number of clusters is the optimal number of clusters.

3. The drilling speed optimization method based on improved particle swarm optimization algorithm according to claim 1, characterized in that: The process of replacing the abnormal points in the drilling data in S2 is to determine the quartile distance Q of the drilling data using the box plot method based on the acquired drilling data, and further calculate the distance q from each sample point to the sample mean i , if q i If ≥5Q, the sample point is considered an abnormal sample point and replaced with the most recent sample.

4. A drilling speed optimization method based on improved particle swarm optimization algorithm as claimed in claim 3, characterized in that: The drilling speed model constructed in S2 is: Among them, ρ is the penalty factor, and is the slack variable, μ is the weight, g i is the output, ψ(·) is the nonlinear mapping, η is the bias, u i is the input, and ε is a small positive number.

5. The drilling speed optimization method based on improved particle swarm optimization algorithm according to claim 1, characterized in that: In S3, the design of mixed weights, improved speed update mechanism and partial particle swarm update mechanism includes the following steps: S3.1: During the population iteration process, the individual weights are updated by using a mixed weight consisting of two inertia weights and a random weight. The calculation formula of inertia weight 1 is as follows: Among them, w a1 is the inertia weight 1, w a-max is the upper limit of the inertia weight 1, γ1 is a random positive number between 0 and 1, t is the current number of iterations, and M is the maximum number of iterations; The calculation formula of inertia weight 2 is as follows: Among them, w a2 is the inertia weight 2; Random weight w rand The calculation formula is as follows: Among them, γ2 is another random positive number between 0 and 1; Based on the inertia weight and random weight, calculate the final weight w: S3.2: Based on the final weight obtained, a new speed update mechanism is designed as follows: When the fitness of the local optimal solution of the current individual is less than the fitness of the current individual, the speed is updated as follows: When the fitness of the individual's local optimal solution is greater than the current individual's fitness, the speed is updated as follows: Among them, p best,i is the local optimal solution of the current individual, z best is the global optimal solution, γ3, γ4, γ5 are random numbers, is the speed of the i-th individual in the t-1th iteration, is the position of the i-th individual in the t-th iteration, σ1 and σ2 are local and global learning factors, and the update process is as follows: σ1=σ max -s max *(tM) / (1-M) σ2=σ min +s min *(tM) / (1-M) Among them, σ max is the maximum value of the learning factor σ, σ min is the minimum value of the learning factor σ; S3.3: Design of partial particle swarm update mechanism During the iteration process, when the iteration reaches 85% of the maximum number of iterations, according to the value of the fitness function, the speed and position of 10% of the last 20% of the population are replaced by the 10% of the population with the smallest fitness function value, and the position and speed of the remaining 10% of the population are reinitialized.

6. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that: A computer program is stored, and when the program is executed by a processor, the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm as described in any one of claims 1 to 5 are implemented.

8. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the steps of the drilling speed optimization method based on the improved particle swarm optimization algorithm as described in any one of claims 1 to 5.

Images