Multi-objective optimization method and equipment for increasing drilling speed and reducing state fluctuation of drill string system

The multi-objective optimization method addresses the challenge of increasing drilling speed and reducing drill string vibrations by optimizing drilling pressure and rotation speed, improving efficiency and safety in deep geological drilling.

CN119066974APending Publication Date: 2024-12-03CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411200817.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Deep geological drilling faces challenges in increasing drilling speed while suppressing drill string vibrations, which are coupled with drilling pressure and rotation speed, and the lack of downhole data complicates direct measurement of vibration, leading to safety and efficiency issues.

Method used

A multi-objective optimization method using extreme learning machines and genetic algorithms to establish torque and drilling speed fluctuation indices, optimizing drilling pressure and rotation speed through a multi-objective optimization model, and employing sorting technologies to determine optimal operating parameters.

Benefits of technology

Improves drilling efficiency by reducing drill string vibrations and fluctuations, enhancing safety and stability during the drilling process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066974A_ABST
    Figure CN119066974A_ABST
Patent Text Reader

Abstract

The invention discloses a multi-objective optimization method and equipment for improving the drilling speed and reducing the state fluctuation of a drill string system, and relates to the field of geological drilling engineering.The multi-objective optimization method for improving the drilling speed and reducing the state fluctuation of the drill string system mainly comprises the steps that torque fluctuation and drilling speed fluctuation indexes are established according to mechanism analysis; establishing a drilling speed, torque fluctuation and drilling speed fluctuation calculation model by adopting an extreme learning machine method, setting reasonable constraint conditions by taking the drilling pressure and the rotating speed as decision variables, and jointly forming a multi-objective optimization model; and optimizing the established multi-objective optimization model by adopting a multi-objective genetic algorithm to obtain a feasible solution set, and deciding optimal bit pressure and rotating speed by adopting a sorting technology based on ideal solution similarity. By means of the multi-objective optimization method and device for increasing the drilling speed and reducing the state fluctuation of the drill string system, the drilling efficiency can be improved, and meanwhile the stability of the drilling process is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of geological drilling engineering, and more specifically, to a multi-objective optimization method and device for increasing drilling speed and reducing state fluctuation of a drill string system. Background Art

[0004] Different from shallow drilling, deep drilling needs to traverse more strata, facing strata with different structures such as alternating soft and hard layers, associated faults, and different steepness and gentleness. The rock breaking process of the drill bit is more intense. The drill string required for deep drilling is extremely long, and the drill string is prone to vibration under the intense drill bit-rock interaction, which leads to drill fatigue, reduces wellbore quality, and brings serious safety problems. The complex and changeable geological environment and the harsh construction conditions with frequent drill string vibrations have put forward new requirements for geological drilling equipment and technology, and posed new challenges to the optimization of geological drilling process parameters.

[0005] In the process of deep geological drilling, it is necessary to increase the drilling speed while suppressing the vibration of the drill string to ensure safe and efficient drilling. However, in the actual drilling process, the drilling speed and the vibration of the drill string are mainly coupled together through the two operating quantities of drilling pressure and rotation speed. There is a conflict and contradiction between increasing the drilling speed and reducing the vibration of the drill string. Therefore, it is of great significance to choose the appropriate operating quantity. However, due to the lack of expensive measurement while drilling (MWD) instruments, downhole data cannot be obtained and the vibration degree of the drill string cannot be directly measured. Summary of the invention

[0006] The purpose of the present invention is to provide a multi-objective optimization method and device for improving drilling speed and reducing fluctuations in the state of a drill string system, which can improve drilling efficiency while ensuring the stability of the drilling process.

[0007] The present invention provides a multi-objective optimization method for improving drilling speed and reducing state fluctuation of a drill string system, comprising the following steps: S1: acquiring drilling data, and constructing a torque fluctuation index and a drilling speed fluctuation index according to the drilling data; S2: constructing a multi-objective optimization model by using an extreme learning machine according to the torque fluctuation index, the drilling speed fluctuation index and the drilling speed index; S3: obtaining the optimal drilling pressure and rotation speed according to the multi-objective optimization model by using a multi-objective genetic algorithm and a sorting technology based on the similarity of ideal solutions.

[0008] Furthermore, the drilling data of the multi-objective optimization method for increasing the drilling speed and reducing the fluctuation of the drill string system state include drilling pressure, rotation speed, torque and drilling speed.

[0009] Furthermore, step S1 of the multi-objective optimization method for increasing drilling speed and reducing drilling string system state fluctuation specifically includes: acquiring drilling data, and constructing a torque fluctuation index and a drilling speed fluctuation index according to the drilling data, such as the formula:

[0010]

[0011] Among them, F TRQ and F FROP are the torque fluctuation index and drilling speed fluctuation index, which respectively indicate the degree of torque and drilling speed fluctuation. The larger the value, the more severe the fluctuation. rmax 、T rmin 、T rmean Respectively represent the maximum, minimum and average value of torque; V ROPmax 、V ROPmin 、V ROPmean They represent the maximum, minimum and average drilling speed respectively.

[0012] Furthermore, the multi-objective optimization model of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system includes an objective function and constraints; the objective function includes a drilling speed calculation model, a torque fluctuation calculation model and a drilling speed fluctuation calculation model; the constraints include objective function constraints and operating variable constraints, and the constraints are used to ensure that the optimized value does not exceed the range.

[0013] Furthermore, the input data of the drilling speed calculation model of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system includes drilling pressure, rotation speed, torque, riser pressure, hook load and depth; the output data of the drilling speed calculation model includes the drilling speed; the drilling speed calculation model is as follows:

[0014] V ROP =f ROP (W,R,T r ,S p ,H l ,D),f ROP =ELM(n,ω,b),

[0015] Among them, V ROP Indicates drilling speed, f ROP (.) indicates the drilling speed calculation model, W indicates drilling pressure, R indicates rotation speed, T r Indicates torque, S p Indicates the standpipe pressure, H l represents hook load, D represents depth; ELM(.) represents extreme learning machine, n represents the number of hidden layer nodes, ω represents the weight between the input layer and the output layer, and b represents the bias between the input layer and the output layer.

[0016] Furthermore, the input data of the torque fluctuation calculation model of the multi-objective optimization method for increasing drilling speed and reducing the state fluctuation of the drill string system includes drilling pressure, rotation speed, torque, riser pressure, hook load, depth, and drilling speed; the output data of the torque fluctuation calculation model includes the degree of torque fluctuation; the torque fluctuation calculation model is as follows:

[0017] F TRQ =f TRQ (W,R,T r ,S p ,H l ,D,V ROP ), f TRQ =ELM1(n1,ω1,b1),

[0018] Among them, F TRQ Indicates the degree of torque fluctuation, f TRQ (.) represents the torque fluctuation calculation model, V ROP represents the drilling speed; ELM1(.) represents the extreme learning machine, n1 represents the number of hidden layer nodes, ω1 represents the weight between the input layer and the output layer, and b1 represents the bias between the input layer and the output layer.

[0019] Furthermore, the input data of the drilling speed fluctuation calculation model of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system includes drilling pressure, rotation speed, drilling speed, torque, riser pressure, hook load, and depth; the output data of the drilling speed fluctuation calculation model includes the degree of drilling speed fluctuation; the drilling speed fluctuation calculation model is as follows:

[0020] F FROP =f FROP (W,R,T r ,S p ,H l ,D,V ROP ), f FROP =ELM2(n2,ω2,b2),

[0021] Among them, F FROP Indicates the degree of drilling speed fluctuation; f FROP (.) represents the drilling speed fluctuation calculation model, ELM2(.) represents the extreme learning machine, n2 represents the number of hidden layer nodes, ω2 represents the weight between the input layer and the output layer, and b2 represents the bias between the input layer and the output layer.

[0022] Furthermore, step S3 of the multi-objective optimization method for increasing drilling speed and reducing the state fluctuation of the drill string system specifically includes: S31: optimizing the multi-objective optimization model using a multi-objective genetic algorithm to obtain a feasible solution set of drilling pressure and rotation speed; S32: according to the feasible solution set of drilling pressure and rotation speed, using a sorting technology based on the similarity of ideal solutions to obtain the optimal drilling pressure and rotation speed.

[0023] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system are implemented.

[0024] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system are implemented.

[0025] The multi-objective optimization method and device for increasing drilling speed and reducing fluctuations in the state of the drill string system provided by the present invention have the following beneficial effects:

[0026] The present invention utilizes the law that drill string vibration can be observed through the degree of fluctuation of the drill string system state, and suppresses the drill string vibration by suppressing the fluctuation of the drill string system state, that is, by coordinating and optimizing the two goals of drilling speed and drilling system state fluctuation, the optimal drilling pressure and rotation speed can be obtained to reduce the fluctuation of the drill string system state and thus suppress the drill string vibration; specifically, the present invention establishes torque fluctuation and drilling speed fluctuation indicators based on mechanism analysis; adopts the extreme learning machine method to establish the drilling speed, torque fluctuation and drilling speed fluctuation calculation model, takes the drilling pressure and rotation speed as decision variables, sets reasonable constraints, and together constitutes a multi-objective optimization model; adopts the NSGA-II method to optimize The established multi-objective optimization model is optimized to obtain a feasible solution set, and the TOPSIS method is used to decide the optimal drilling pressure and rotation speed. In short, the present invention can use the well data to decide the optimal drilling pressure and rotation speed variables. By adjusting these two variables, the drilling speed can be improved while reducing the state fluctuations of the drill string system such as drilling speed fluctuations and torque fluctuations, and the drill string vibration can be suppressed. This solves the problem of the prior art that the drilling speed is increased during the drilling process while reducing the state fluctuations of the drill string system and thus suppressing the drill string vibration. The drilling efficiency is improved while the stability of the drilling process is guaranteed, the drilling efficiency is improved and the safety accidents are reduced, and guidance is provided for the research on intelligent control of the drilling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0028] Figure 1 It is a flow chart of a multi-objective optimization method for increasing drilling speed and reducing fluctuations in drill string system state provided by the present invention;

[0029] Figure 2 is a diagram of drilling speed calculation results in a real-time example of the present invention;

[0030] Figure 3 is a diagram of torque fluctuation calculation results in an embodiment of the present invention;

[0031] Figure 4 is a diagram of drilling speed fluctuation calculation results in an embodiment of the present invention;

[0032] Figure 5 is a drilling speed, torque fluctuation and drilling speed fluctuation calculation result error diagram in an embodiment of the present invention;

[0033] Figure 6 is a comparison diagram of drilling speed optimization results in an embodiment of the present invention;

[0034] Figure 7 A comparison diagram of torque fluctuation optimization results in an embodiment of the present invention;

[0035] Figure 8 A comparison diagram of drilling speed fluctuation optimization results in an embodiment of the present invention;

[0036] Fig. 9 It is a structural block diagram of the computer device provided by the present invention. DETAILED DESCRIPTION

[0037] 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.

[0038] Figure 1 A schematic diagram of a multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuations in this embodiment is shown. In this embodiment, the multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuations includes the following steps:

[0039] S1: Acquire drilling data, and construct torque fluctuation index and drilling speed fluctuation index according to the drilling data;

[0040] Specifically, drilling data include drilling pressure, rotation speed, torque, and drilling speed;

[0041] Specifically, the above step S1 includes: acquiring drilling data, and constructing a torque fluctuation index and a drilling speed fluctuation index according to the drilling data, such as the formula:

[0042]

[0043] Among them, F TRQ and F FROP are the torque fluctuation index and drilling speed fluctuation index, which respectively indicate the degree of torque and drilling speed fluctuation. The larger the value, the more severe the fluctuation. rmax , T rmin , T rmean Respectively represent the maximum, minimum and average value of torque; V ROPmax 、V ROPmin 、V ROPmean Respectively represent the maximum, minimum and average values ​​of drilling speed;

[0044] Specifically, torque fluctuation and drilling speed fluctuation indices are established according to the values ​​of torque and drilling speed, respectively; the torque fluctuation and drilling speed fluctuation index formulas used are as follows:

[0045]

[0046]

[0047] Where, T r Indicates torque, V ROP Indicates drilling speed, T rmax , T rmin , T rmean Respectively represent the maximum, minimum and average value of torque; V ROPmax 、V ROPmin 、V ROPmean Respectively represent the maximum, minimum and average value of drilling speed, F TRQ and F FROP Respectively represent the degree of fluctuation of torque and drilling speed. The larger the value, the more severe the fluctuation.

[0048] S2: Based on the torque fluctuation index, drilling speed fluctuation index and drilling speed index, a multi-objective optimization model is constructed using an extreme learning machine;

[0049] Specifically, the multi-objective optimization model includes an objective function and constraints; the objective function includes a drilling speed calculation model, a torque fluctuation calculation model, and a drilling speed fluctuation calculation model; the constraints include objective function constraints and operating variable constraints, and the constraints are used to ensure that the optimized value does not exceed the range;

[0050] Specifically, the input data of the drilling speed calculation model include drilling pressure, rotation speed, torque, riser pressure, hook load and depth; the output data of the drilling speed calculation model include drilling speed; the drilling speed calculation model is as follows:

[0051] V ROP =f ROP (W,R,T r ,S p ,H l ,D),f ROP =ELM(n,ω,b),

[0052] Among them, V ROP Indicates drilling speed, f ROP (.) indicates the drilling speed calculation model, W indicates drilling pressure, R indicates rotation speed, T r Indicates torque, S p Indicates the standpipe pressure, H l represents the hook load, D represents the depth; ELM(.) represents the extreme learning machine, n represents the number of hidden layer nodes, ω represents the weight between the input layer and the output layer, and b represents the bias between the input layer and the output layer;

[0053] Specifically, the input data of the torque fluctuation calculation model include drilling pressure, rotation speed, torque, riser pressure, hook load, depth, and drilling speed; the output data of the torque fluctuation calculation model include the degree of torque fluctuation; the torque fluctuation calculation model is as follows:

[0054] F TRQ =f TRQ (W,R,T r ,S p ,H l ,D,V ROP ), f TRQ =ELM1(n1,ω1,b1),

[0055] Among them, F TRQ Indicates the degree of torque fluctuation, f TRQ (.) represents the torque fluctuation calculation model, V ROP represents the drilling speed; ELM1(.) represents the extreme learning machine, n1 represents the number of nodes in the hidden layer, ω1 represents the weight between the input layer and the output layer, and b1 represents the bias between the input layer and the output layer;

[0056] Specifically, the input data of the drilling speed fluctuation calculation model include drilling pressure, rotation speed, drilling speed, torque, riser pressure, hook load, and depth; the output data of the drilling speed fluctuation calculation model include the degree of drilling speed fluctuation; the drilling speed fluctuation calculation model is as follows:

[0057] F FROP =f FROP (W,R,T r ,S p ,H l ,D,V ROP ), f FROP =ELM2(n2,ω2,b2),

[0058] Among them, F FROP Indicates the degree of drilling speed fluctuation; f FROP (.) represents the drilling speed fluctuation calculation model, ELM2(.) represents the extreme learning machine, n2 represents the number of hidden layer nodes, ω2 represents the weight between the input layer and the output layer, and b2 represents the bias between the input layer and the output layer;

[0059] Specifically, the above step S2 includes: using the ELM method to establish the drilling speed, torque fluctuation and drilling speed fluctuation calculation models respectively, setting reasonable constraints, and jointly forming a multi-objective optimization model;

[0060] Specifically, the optimization model is mainly composed of an objective function and constraints; the objective function is composed of a drilling speed calculation model, a torque fluctuation calculation model, and a drilling speed fluctuation calculation model; the constraints are composed of objective function constraints and operating variable constraints to ensure that the optimized value does not exceed the range;

[0061] Specifically, the objective function is as follows:

[0062]

[0063] in, Indicates the maximum drilling speed, f ROP (.) indicates drilling speed calculation, W indicates drilling pressure, R indicates rotation speed, T r Indicates torque, S p Indicates the standpipe pressure, H l Indicates hook load, D indicates depth, min F TRO Indicates to minimize the torque fluctuation, f TRQ (.) indicates torque fluctuation calculation, V ROP Indicates drilling speed, min F FROP Indicates that the drilling speed fluctuation is minimized, f FROP (.) indicates drilling speed fluctuation calculation;

[0064] Specifically, the constraints are as follows:

[0065]

[0066] Among them, W min Indicates the minimum drilling pressure, W max Indicates the maximum drilling pressure, R min Indicates the minimum speed, R max Indicates the maximum speed, V ROPmax 、V ROPmin Respectively represent the maximum and minimum drilling speed, F TRQ and F FROP They are torque fluctuation index and drilling speed fluctuation index, F TRQmax 、F TRQmin Respectively represent the maximum and minimum values ​​of the torque fluctuation index, F FROPmax 、F FROPmin They represent the maximum and minimum values ​​of the drilling speed fluctuation index respectively;

[0067] Specifically, the inputs of the drilling speed calculation model are: drilling pressure (W), speed (R), torque (T r ), standpipe pressure (S p )、Hook load(H l ), depth (D); output is drilling speed (V ROP ); The drilling speed calculation model is: V ROP =f ROP (W,R,T r ,S p ,H l ,D);

[0068] Using extreme learning machine, the above formula can also be expressed as: ROP =ELM(n,ω,b);

[0069] Specifically, the inputs of the torque fluctuation calculation model are: drilling pressure (W), speed (R), torque (T r ), standpipe pressure (S p )、Hook load(H l ), depth (D), drilling speed (V ROP ); Output is the torque fluctuation degree F TRQ ;

[0070] The torque fluctuation calculation model is: F TRQ =f TRQ (W,R,T r ,S p ,H l ,D,V ROP );

[0071] Using extreme learning machine, the above formula can also be expressed as: TRQ =ELM1(n1,ω1,b1);

[0072] Specifically, the inputs of the drilling speed fluctuation calculation model are: drilling pressure (W), rotation speed (R), drilling speed (V ROP )、Torque(T r ), standpipe pressure (S p )、Hook load(H l )、depth(D)、V POR ; Output is drilling speed fluctuation degree F FROP ; The drilling speed fluctuation calculation model is: F FROP =f FROP (W,R,T r ,S p ,H l ,D,V ROP );

[0073] Using extreme learning machine, the above formula can also be expressed as: FROP =ELM2(n2,ω2,b2);

[0074] Specifically, the algorithm flow of the extreme learning machine ELM is as follows: Suppose there are M groups of drilling samples x j is the n-dimensional input vector, v j is the m-dimensional output vector. The relationship between the input and output of ELM is expressed as follows:

[0075]

[0076] Where L is the number of hidden layer nodes, represents the activation function; ω i is the connection weight between the input neuron and the i-th hidden layer neuron, b iis the bias of the i-th hidden layer neuron; the above formula can be converted into a matrix form and expressed as follows:

[0077] Hβ=V ROP ;

[0078] In the formula, the output matrix H can be calculated as follows:

[0079]

[0080] The connection weights between the hidden layer neurons and the output are β * The calculation is as follows:

[0081] β * =H ^ V ROP ;

[0082] Where H^ is the Moore-Penrose generalized inverse matrix of H;

[0083] S3: According to the multi-objective optimization model, the optimal drilling pressure and rotation speed are obtained by using the multi-objective genetic algorithm and the sorting technology based on the similarity of ideal solutions;

[0084] Specifically, step S3 includes: S31: optimizing the multi-objective optimization model using a multi-objective genetic algorithm to obtain a feasible solution set of drilling pressure and rotation speed; S32: obtaining the optimal drilling pressure and rotation speed according to the feasible solution set of drilling pressure and rotation speed using a sorting technology based on the similarity of ideal solutions;

[0085] Specifically, step S3 can also be implemented in the following manner: a multi-objective genetic algorithm (NSGA-II method) is used to optimize the constructed multi-objective optimization model to obtain a feasible solution set of drilling pressure and rotation speed; then a ranking technique based on the similarity of ideal solutions (TOPSIS method) is used to obtain the optimal drilling pressure and rotation speed from the feasible solution set;

[0086] Specifically, the optimization method includes the following steps:

[0087] Step 1: Initialize the population and randomly generate a group of individuals to form the initial population;

[0088] Step 2: Taking the established optimization model as the fitness function, for each individual in the population, calculate its fitness value on multiple objective functions;

[0089] Step 3: Non-dominated sorting: sort the individuals in the population into different frontier levels;

[0090] Step 4: Calculate the crowding distance for each frontier level to maintain diversity;

[0091] Step 5: Generate a new population and select new individuals to form the next generation population based on non-dominated sorting and crowding distance;

[0092] Step 6: Genetic operation, use crossover and mutation operations to perform genetic operations on the selected individuals to generate new individuals;

[0093] Step 7: Repeat the iterations and execute Step 2-6 repeatedly until the predetermined number of iterations is reached or the stop condition is met;

[0094] Specifically, the Pareto front solution set is obtained through the NSGA-II optimization method, and then the TOPSIS method is used to obtain the optimal drilling pressure and rotation speed.

[0095] In some embodiments, the above-mentioned multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuations may also be implemented in the following manner.

[0096] In this embodiment, 43564 sets of drilling data of a well site are selected as specific objects, which include: drilling pressure, rotation speed, torque, drilling speed and other main operating variables; first, taking 7 minutes as a time scale, the torque fluctuation and drilling speed fluctuation values ​​are calculated; secondly, the drilling speed calculation model, torque fluctuation and drilling speed fluctuation calculation model are established according to historical data; then, the constraint conditions are set and the NSGA-II method is used for optimization; finally, the sliding window length is 100 and the optimization interval is 30 minutes for online optimization;

[0097] In this embodiment, the specific steps of the multi-objective optimization method for increasing the drilling speed and reducing the fluctuation of the drill string system state are as follows:

[0098] (1) Establish torque fluctuation and drilling speed fluctuation indices according to the values ​​of torque and drilling speed, respectively;

[0099] In the process of drilling in complex geology, the site usually shows violent coupling of various vibration modes, such as drilling jump, stick-slip, etc. Excessive vibration will lead to damage to drill tools, premature failure of drill bits and drill tools, etc., which not only reduces the drilling timeliness, but also brings huge safety risks. Therefore, the influence of drill string vibration needs to be considered when optimizing the drilling speed. Considering that downhole data is difficult to obtain, the vibration can be suppressed by suppressing the fluctuation of the drill string system through uphole data. Therefore, this embodiment only uses uphole data to establish a multi-objective optimization method and equipment for improving the drilling speed and reducing the state fluctuation of the drill string system. First, torque and drilling speed fluctuation indicators are established according to mechanism analysis. Then, the extreme learning machine method is used to establish a drilling speed, torque fluctuation and drilling speed fluctuation calculation model, and the drilling pressure and speed are used as decision variables. Reasonable constraints are set to jointly constitute a multi-objective optimization model. Finally, the NSGA-II method is used to optimize the established multi-objective optimization model to obtain a feasible solution set, and the TOPSIS method is used to decide the optimal drilling pressure and speed. The actual data of a well site are used for calibration, and some data are shown in Table 1: (All data in this embodiment are taken to 4 decimal places for display convenience).

[0100] Table 1: Drilling speed fluctuation and torque fluctuation index values

[0101]

[0102]

[0103] (2) Establishing the calculation model of drilling speed, drilling speed fluctuation and torque fluctuation;

[0104] The historical drilling pressure, historical rotation speed, historical torque, historical depth, historical riser pressure and historical hook load are used as input, and the historical drilling speed is used as output to establish a drilling speed calculation model; the historical drilling pressure, historical rotation speed, historical torque, historical depth, historical riser pressure, historical hook load and historical drilling speed are used as input, and the historical drilling speed fluctuation value obtained in step (1) is used as output to establish a drilling speed fluctuation calculation model; the historical drilling pressure, historical rotation speed, historical torque, historical depth, historical riser pressure, historical hook load and historical drilling speed are used as input, and the historical torque fluctuation value obtained in step (1) is used as output to establish a torque fluctuation calculation model; the calculation is performed with a sliding window of 100 and an interval of 30 minutes; the calculation results are as follows: Figure 2 , Figure 3 and Figure 4 As shown in the figure, it is proved that the present invention has a good calculation effect; the model calculation error is as follows Figure 5 As shown, the error is basically between [-0.6, 0.6], which meets the requirements;

[0105] (3) Coordinated optimization of drilling speed, drilling speed fluctuation and torque fluctuation;

[0106] Based on the drilling speed, drilling speed fluctuation and torque fluctuation calculation models obtained in step (2), the NSGA-II method is used to optimize and obtain multiple feasible solutions;

[0107] (4) Using TOPSIS method to obtain the optimal drilling pressure and speed;

[0108] The optimal drilling pressure and speed obtained after optimization are shown in Table 2; Figure 6 , Figure 7 and Figure 8 shown.

[0109] Table 2: Optimal drilling pressure and speed results

[0110]

[0111]

[0112] To measure the optimization effect, the drilling speed, drilling speed fluctuation and torque fluctuation before and after optimization are compared, and the results are shown in Table 3;

[0113] Table 3: Comparison of drilling speed, drilling speed fluctuation and torque fluctuation before and after optimization

[0114]

[0115] As shown in Table 3, after optimization using the NSGA-II method, the overall drilling speed increased by 7.93%, and the drilling speed fluctuation and torque fluctuation were reduced by 20.26% and 6.52%, respectively.

[0116] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system are implemented. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memory.

[0117] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system are implemented.

[0118] like Fig. 9As shown, the computer device may include: at least one processor 121, such as a CPU (Central Processing Unit), at least one communication interface 123, a memory 124, and at least one communication bus 122. Among them, the communication bus 122 is used to realize the connection and communication between these components. Among them, the communication interface 123 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 123 may also include a standard wired interface and a wireless interface. The memory 124 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 124 may also be at least one storage device located away from the aforementioned processor 121. Among them, the memory 124 stores an application program, and the processor 121 calls the program code stored in the memory 124 to perform any of the above method steps. Among them, the communication bus 122 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 122 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9Only one line is used to represent it, but it does not mean that there is only one bus or one type of bus. Among them, the memory 124 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 124 may also include a combination of the above-mentioned types of memory. Among them, the processor 121 may be a central processing unit (English: central processing unit, abbreviated: CPU), a network processor (English: network processor, abbreviated: NP) or a combination of CPU and NP. Among them, the processor 121 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (English: application-specific integrated circuit, abbreviated: ASIC), a programmable logic device (English: programmable logic device, abbreviated: PLD) or a combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. Optionally, the memory 124 is also used to store program instructions. The processor 121 can call program instructions to implement a multi-objective optimization method for increasing drilling speed and reducing fluctuations in the state of the drill string system as in this embodiment.

[0119] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0120] The serial numbers of the embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In a unit claim that lists several means, several of these means may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order and these words may be interpreted as identifiers.

[0121] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0122] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuations, characterized in that: The following steps are involved: S1: Acquire drilling data, and construct a torque fluctuation index and a drilling speed fluctuation index according to the drilling data; S2: constructing a multi-objective optimization model using an extreme learning machine according to the torque fluctuation index, the drilling speed fluctuation index and the drilling speed index; S3: According to the multi-objective optimization model, the optimal drilling pressure and rotation speed are obtained by using a multi-objective genetic algorithm and a sorting technique based on the similarity of ideal solutions.

2. The multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuation according to claim 1, characterized in that: The drilling data includes drilling pressure, rotation speed, torque, and drilling speed.

3. The multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuation according to claim 1, characterized in that: Step S1 specifically includes: acquiring drilling data, and constructing a torque fluctuation index and a drilling speed fluctuation index according to the drilling data, such as the formula: Among them, F TRQ and F FROP are the torque fluctuation index and drilling speed fluctuation index, which respectively indicate the degree of torque and drilling speed fluctuation. The larger the value, the more severe the fluctuation. rmax 、T rmin 、T rmean Respectively represent the maximum, minimum and average value of torque; V ROPmax 、V ROPmin 、V ROPmean They represent the maximum, minimum and average drilling speed respectively.

4. The multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuation according to claim 1, characterized in that: The multi-objective optimization model includes an objective function and constraints; the objective function includes a drilling speed calculation model, a torque fluctuation calculation model and a drilling speed fluctuation calculation model; the constraints include objective function constraints and operating variable constraints, and the constraints are used to ensure that the optimized value does not exceed the range.

5. The multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuation according to claim 4 is characterized in that: The input data of the drilling speed calculation model include drilling pressure, rotation speed, torque, riser pressure, hook load and depth; the output data of the drilling speed calculation model include drilling speed; the drilling speed calculation model is as follows: V ROP =f ROP (W,R,T r ,S p ,H l ,D),f ROP =ELM(n,ω,b), Among them, V ROP Indicates drilling speed, f ROP (.) indicates the drilling speed calculation model, W indicates drilling pressure, R indicates rotation speed, T r Indicates torque, S p Indicates the standpipe pressure, H l represents hook load, D represents depth; ELM(.) represents extreme learning machine, n represents the number of hidden layer nodes, ω represents the weight between the input layer and the output layer, and b represents the bias between the input layer and the output layer.

6. The multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuation according to claim 4, characterized in that: The input data of the torque fluctuation calculation model include drilling pressure, rotation speed, torque, riser pressure, hook load, depth, and drilling speed; the output data of the torque fluctuation calculation model include the degree of torque fluctuation; the torque fluctuation calculation model is as follows: F TRQ =f TRQ (W,R,T r ,S p ,H l ,D,V ROP ),f TRQ =ELM1(n1,ω1,b1), Among them, F TRQ Indicates the degree of torque fluctuation, f TRQ (.) represents the torque fluctuation calculation model, V ROP represents the drilling speed; ELM1(.) represents the extreme learning machine, n1 represents the number of hidden layer nodes, ω1 represents the weight between the input layer and the output layer, and b1 represents the bias between the input layer and the output layer.

7. The multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuation according to claim 4, characterized in that: The input data of the drilling speed fluctuation calculation model include drilling pressure, rotation speed, drilling speed, torque, riser pressure, hook load, and depth; the output data of the drilling speed fluctuation calculation model include the degree of drilling speed fluctuation; the drilling speed fluctuation calculation model is as follows: F FROP =f FROP (W,R,T r ,S p ,H l ,D,V ROP ),f FROP =ELM2(n2,ω2,b2), Among them, F FROP Indicates the degree of drilling speed fluctuation; f FROP (.) represents the drilling speed fluctuation calculation model, ELM2(.) represents the extreme learning machine, n2 represents the number of hidden layer nodes, ω2 represents the weight between the input layer and the output layer, and b2 represents the bias between the input layer and the output layer.

8. The multi-objective optimization method for increasing drilling speed and reducing drill string system state fluctuation according to claim 1, characterized in that: Step S3 specifically includes: S31: Optimizing the multi-objective optimization model using a multi-objective genetic algorithm to obtain a feasible solution set of drilling pressure and rotation speed; S32: According to the feasible solution set of the drilling pressure and the rotation speed, the optimal drilling pressure and the rotation speed are obtained by using a sorting technology based on the similarity of ideal solutions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system as described in any one of claims 1 to 8 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the multi-objective optimization method for increasing the drilling speed and reducing the state fluctuation of the drill string system as described in any one of claims 1 to 8 are implemented.