A method and system for drilling control optimization based on bee colony algorithm

Abstract

The application relates to the technical field of drilling control, in particular to a method and system for optimizing drilling control based on a bee colony algorithm, which comprises the following steps: receiving an initial device parameter set uploaded by a target drilling device; receiving a current environment data set uploaded by an environment sensor in the target drilling device; when a device parameter optimization value determined based on the current environment data set is not less than a preset device parameter optimization threshold, optimizing the initial device parameter set to obtain an optimized parameter set corresponding to the initial device parameter set; and when the device parameter optimization value determined based on the current environment data set is less than the preset device parameter optimization threshold, maintaining the execution parameter of the target drilling device as the initial device parameter set. Therefore, the error in drilling parameter optimization caused by large data noise can be avoided, and the accuracy can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of borehole control, in particular to a method and system for optimizing borehole control based on a bee colony algorithm. BACKGROUND

[0002] For any drill bit and drilling method, there is a high-efficiency rock breaking zone and a drilling speed potential tapping region corresponding to any rock. In the drilling process, due to the uncertainty of the stratum drilled, the designed drilling parameters often cannot achieve the expected drilling speed, resulting in low drilling speed, long drilling period, and serious impact on oil and gas field development progress and overall economic benefits. Selecting different drilling parameters will directly affect drilling safety, efficiency and cost. Drilling parameter optimization is to find the optimal drilling parameter combination in real time, quantitatively and accurately under the current drilling state, combined with drilling equipment constraints, to maximize drilling efficiency.

[0003] At present, the prior art obtains real-time drilling data and static drilling data in the drilling process; the real-time drilling data obtained in the real-time drilling data and the static drilling data in the drilling process are subjected to noise reduction processing to obtain standardized drilling data; the constraint conditions of the Bayesian optimization algorithm are determined, including drilling equipment constraints and drilling process constraints; the objective function of the Bayesian optimization algorithm is constructed to obtain the real-time recommended optimal drilling pressure, rotation speed and flow drilling parameters through the Bayesian optimization algorithm; but in the above scheme, the drilling equipment has multi-dimensional data and the data noise is relatively large, and the existing technology cannot guarantee the accuracy. SUMMARY

[0004] In view of the above technical problems, the present application provides a method and system for optimizing borehole control based on a bee colony algorithm, which can avoid the error in drilling parameter optimization caused by large data noise and improve accuracy.

[0005] According to a first aspect of the present application, a method for optimizing borehole control based on a bee colony algorithm is provided, the method comprising the following steps:

[0006] S100, receiving an initial device parameter set A={A1,..., Ai,..., Am} uploaded by a target drilling device, where Ai is the i-th initial device parameter subset, i is in the range of 1 to m, and m is the total number of initial device parameters;

[0007] S200, receiving a current environment data set B={B1,..., Bj,..., Bn} uploaded by an environment sensor in the target drilling device, where Bj is the i-th current environment data subset, j is in the range of 1 to n, and n is the total number of current environment data subsets;

[0008] S300, when F≥F0, A is optimized to obtain a set of optimization parameters C corresponding to A, Ci is an optimization parameter corresponding to Ai, and the execution parameter of the target drilling equipment is controlled to adopt C, wherein F is a device parameter optimization value determined based on B, F0 is a preset device parameter optimization threshold;

[0009] S400, when F<F0, the execution parameter of the target drilling equipment is maintained.

[0010] Further, when m=4, A={A1, A2, A3, A4}, A1 is an initial drill bit speed subset, A2 is an initial feed speed subset, A3 is an initial drilling pressure subset, and A4 is an initial cooling liquid flow subset.

[0011] Further, when n=3, B={B1, B2, B3}, B1 is a current rock hardness data subset, B2 is a current drill bit temperature data subset, and B3 is a current drill bit vibration amplitude data subset.

[0012] Further, the step S300 further includes the following steps:

[0013] S10, any Bj={Bj1, …, Bjr, …, Bjs(j)} is obtained, Bjr is the rth current environment data in Bj, r is in the range of 1 to s(j), and s(j) is the current environment data quantity in Bj;

[0014] S11, based on all Bjr, an optimization degree value Kj corresponding to Bj is obtained;

[0015] S12, according to all Kj, F is obtained, F satisfies the following condition:

[0016] F=∑ m j=1 Wj*Kj, wherein Wj is a weight value corresponding to Kj.

[0017] Further, F satisfies the following condition:

[0018] F=∑ m j=1 Wj*Kj+U0, U0 is an associated optimization degree value corresponding to B.

[0019] According to a second aspect of the present application, a system for drilling control optimization based on a bee colony algorithm is provided, the system comprising:

[0020] The first execution module 100 is configured to receive an initial device parameter set A={A1,..., Ai,..., Am} uploaded to the target drilling device, where Ai represents an ith initial device parameter subset, i ranges from 1 to m, and m represents the total number of initial device parameters.

[0021] The second execution module 200 is configured to receive a current environment data set B={B1,..., Bj,..., Bn} uploaded to the target drilling device by an environment sensor, where Bj represents an ith current environment data subset, j ranges from 1 to n, and n represents the total number of current environment data subsets.

[0022] The third execution module 300 is configured to perform optimization processing on A when F≥F0 to obtain an optimized parameter set C={C1,..., Ci,..., Cm} corresponding to A, where Ci represents an optimized parameter corresponding to Ai, and the execution parameter of the target drilling device is controlled to adopt C, where F represents a device parameter optimization value determined based on B, and F0 represents a preset device parameter optimization threshold.

[0023] The fourth execution module 400 is configured to control the execution parameter of the target drilling device to remain unchanged when F<F0.

[0024] Further, when m=4, A={A1, A2, A3, A4}, A1 represents an initial drill bit speed subset, A2 represents an initial feed speed subset, A3 represents an initial drilling pressure subset, and A4 represents an initial cooling liquid flow subset.

[0025] Further, when n=3, B={B1, B2, B3}, B1 represents a current rock hardness data subset, B2 represents a current drill bit temperature data subset, and B3 represents a current drill bit vibration amplitude data subset.

[0026] Further, the third execution module 300 includes:

[0027] The first acquisition module 10 acquires any Bj={Bj1,..., Bjr,..., Bjs(j)}, where Bjr represents an rth current environment data in Bj, r ranges from 1 to s(j), and s(j) represents the number of current environment data in Bj.

[0028] The second acquisition module 11 obtains an optimization degree value Kj corresponding to Bj based on all Bjr.

[0029] The third acquisition module 12 obtains F according to all Kj, where F satisfies the following condition:

[0030] F=∑ m j=1 Wj*Kj, where Wj represents a weight value corresponding to Kj.

[0031] Further, F meets the following condition:

[0032] F =∑ m j=1 Wj*Kj+U0, U0 refers to the associated optimization degree value corresponding to B.

[0033] The present application has at least the following beneficial effects:

[0034] The present application provides a method for drilling control optimization based on a bee colony algorithm, which comprises the following steps: receiving an initial device parameter set A={A1,..., Ai,..., Am} uploaded by a target drilling device, Ai refers to the i-th initial device parameter subset, i ranges from 1 to m, and m is the total number of initial device parameters; receiving a current environment data set B={B1,..., Bj,..., Bn} uploaded by an environment sensor in the target drilling device, Bj refers to the i-th current environment data subset, j ranges from 1 to n, and n is the total number of current environment data subsets; when F≥F0, A is optimized to obtain an optimized parameter set C={C1,..., Ci,..., Cm} corresponding to A, Ci refers to the optimized parameter corresponding to Ai, so as to control the execution parameter of the target drilling device to adopt C, wherein F refers to the device parameter optimization value determined based on B, and F0 refers to a preset device parameter optimization threshold; when F<F0, the execution parameter of the target drilling device is maintained; it can be known that the error in drilling parameter optimization caused by large data noise can be avoided, and the accuracy can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0036] Figure 1 The flowchart of the method for drilling control optimization based on a bee colony algorithm provided by the embodiments of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0038] As Figure 1As shown, the embodiment of the present application provides a method for drilling control optimization based on the bee colony algorithm, which comprises the following steps:

[0039] S100, receiving an initial device parameter set A={A1,..., Ai,..., Am} uploaded by a target drilling device, wherein Ai represents an ith initial device parameter subset, i ranges from 1 to m, m represents the total number of initial device parameters, and it can be understood that:

[0040] The initial device parameter refers to a parameter used by the drilling device for drilling, for example, a drill bit rotation speed, a feed speed, a drilling pressure, a cooling liquid flow, etc.

[0041] Preferably, when m=4, A={A1, A2, A3, A4}, A1 represents an initial drill bit rotation speed subset, A2 represents an initial feed speed subset, A3 represents an initial drilling pressure subset, and A4 represents an initial cooling liquid flow subset.

[0042] Further, the step S100 further comprises the following steps:

[0043] S101, obtaining a maximum value Ai(max) corresponding to any Ai and a minimum value Ai(min) corresponding to Ai, wherein Ai(max) represents the maximum value of the ith initial device parameter, and Ai(min) represents the minimum value of the ith initial device parameter;

[0044] S102, determining p initial device parameter regions corresponding to Ai according to the maximum value Ai(max) corresponding to Ai and the minimum value Ai(min) corresponding to Ai, wherein the xth initial device parameter region is [Vix1, Vix2), and x ranges from 1 to p; it can be understood that the starting value of the first initial device parameter region is Ai(min), and the end value of the pth initial device parameter region is Ai(max);

[0045] Wherein, Vix1 meets the following condition:

[0046] Vix1=Ai(min)+(x-1)*(Ai(max)-Ai(min)) / p;

[0047] Wherein, Vix2 meets the following condition:

[0048] Vix2=Ai(min)+x*(Ai(max)-Ai(min)) / p.

[0049] Further, the method further comprises the following step of obtaining p:

[0050] Step 1, obtain the initial device parameter span value L={L1, …, Li, …, Lm}, Li=Ai(max)-Ai(min), step 2, determine p according to L; that is, L is sorted in size order L0={L01, …, L0y, …, L0q},

[0051] q=m, g1=GCD(L02, L01)=GCD(L02, L02%L01), where L02>L01, then determine g2 according to g1, g2=GCD(g1, L03); and so on until all numbers are calculated, finally GCD(L01, …, L0y, …, L0q) is obtained, and GCD(L01, …, L0y, …, L0q)*m is taken as p; wherein, the GCD() function is the greatest common divisor function of two numbers.

[0052] S103, according to all initial device parameter regions corresponding to Ai, obtain any Ai={Ai1, …, Aix, …, Aip}, Aix refers to the xth initial device parameter randomly selected from Ai, that is, Aix is randomly selected from the xth initial device parameter region.

[0053] Based on the maximum and minimum values of different initial device parameters, the device parameter region suitable for division is determined, and the device parameter value is randomly selected from the device parameter region to avoid incomplete device parameter coverage, which leads to the inability to optimize the device parameters, thereby avoiding the error of drilling parameter optimization caused by large data noise, and improving the accuracy.

[0054] S200, receiving the current environment data set B={B1, …, Bj, …, Bn} uploaded by the environment sensor in the target drilling device, Bj refers to the ith current environment data subset, and j takes a value in the range of 1 to n, n is the total number of current environment data subsets. It can be understood that: the current environment data refers to the current surrounding environment data of the drilling device and the device environment data, for example, rock hardness, drill bit temperature, drill bit vibration amplitude, etc.

[0055] Preferably, when n=3, B={B1, B2, B3}, B1 is the current rock hardness data subset, B2 is the current drill bit temperature data subset, and B3 is the current drill bit vibration amplitude data subset.

[0056] S300, when F≥F0, A is optimized to obtain the corresponding optimization parameter set C={C1,..., Ci,..., Cm} of A, Ci refers to the optimization parameter corresponding to Ai, to control the execution parameter of the target drilling equipment to adopt C, wherein F refers to the equipment parameter optimization value determined based on B, F0 refers to the preset equipment parameter optimization threshold; wherein the equipment parameter optimization value is used to reflect the index of whether the target equipment starts to optimize the equipment parameter, and the person skilled in the art can set the preset equipment parameter optimization threshold according to the actual demand, which will not be repeated here.

[0057] Further, the step S300 further includes the following steps:

[0058] S10, any Bj={Bj1,..., Bjr,..., Bjs(j)} is obtained, Bjr refers to the rth current environment data in Bj, r takes the value range of 1 to s(j), and s(j) refers to the current environment data amount in Bj;

[0059] S11, based on all Bjr, the optimization degree value Kj corresponding to Bj is obtained; further, Kj meets the following conditions:

[0060] Kj= ((∑ s（j） r=1 Bjr / s(j))-Bjmin) / (Bjmax-Bjmin)+ (Bjmax-(∑ s（j） r=1 Bjr / s(j))) / (Bjmax-Bjmin)+√((∑ s（j） r=1 (Bjr-(∑ s（j） r=1 Bjr / s(j))) 2 )

[0061] S12, according to all Kj, F is obtained, F meets the following conditions:

[0062] F=∑ m j=1 Wj*Kj, wherein Wj refers to the weight value corresponding to Kj, and the person skilled in the art sets the weight value according to the actual demand, and the preselected Wj=1 / m.

[0063] Further, F meets the following conditions:

[0064] F=∑ m j=1 Wj*Kj+U0, U0 refers to the correlation optimization degree value corresponding to B; it can be understood that: the correlation optimization degree value is the optimization degree generated by considering the correlation degree between Bj based on ∑ m j=1 Wj*Kj.

[0065] The correlation optimization degree generated based on the correlation degree of mutual influence between different environment data avoids the situation of determining only with environment data when starting to optimize the device parameters, which leads to inaccurate judgment time and further leads to error in drilling parameter optimization, thereby improving the accuracy.

[0066] Specifically, the S300 step further includes the following steps:

[0067] S301, obtaining Ai={Ai1, …, Aix, …, Aip};

[0068] S302, determining the intermediate device parameter Dix corresponding to Aix based on Aix, wherein Dix meets the following condition:

[0069] Dix=Aix+φix*(Aix-Giy), wherein φix is a random parameter optimization influence factor corresponding to Aix, φix∈[-1, 1], and Giy is the yth initial device parameter in Ai except Aix, and y has a value range of 1 to q, q=p-1;

[0070] S303, when e -Dix > e -Aix , determining that Ci is Dix.

[0071] The above-mentioned optimization method can avoid the error in drilling parameter optimization caused by large data noise and improve the accuracy.

[0072] S400, when F<F0, maintaining the execution parameter of the target drilling device; that is, when F<F0, the execution parameter is Aix.

[0073] The above-mentioned method for optimizing drilling control based on the bee colony algorithm includes: receiving an initial device parameter set uploaded by a target drilling device; receiving a current environment data set uploaded by an environment sensor in the target drilling device; when a device parameter optimization value determined based on the current environment data set is not less than a preset device parameter optimization threshold, optimizing the initial device parameter set to obtain an optimized parameter set corresponding to the initial device parameter set; and when the device parameter optimization value determined based on the current environment data set is less than the preset device parameter optimization threshold, maintaining the execution parameter of the target drilling device as the initial device parameter set. It can be known that the method can avoid the error in drilling parameter optimization caused by large data noise and improve the accuracy.

[0074] Another embodiment provides a system for optimizing drilling control based on the bee colony algorithm, which includes:

[0075] The first execution module 100 is configured to receive an initial device parameter set A={A1,..., Ai,..., Am} uploaded to the target drilling device, where Ai represents an ith initial device parameter subset, i ranges from 1 to m, and m represents the total number of initial device parameters. It can be understood that:

[0076] The initial device parameter refers to a parameter used by the drilling device for drilling, for example, a drill bit rotation speed, a feed speed, a drilling pressure, a cooling liquid flow, and the like.

[0077] Preferably, when m=4, A={A1, A2, A3, A4}, A1 represents an initial drill bit rotation speed subset, A2 represents an initial feed speed subset, A3 represents an initial drilling pressure subset, and A4 represents an initial cooling liquid flow subset.

[0078] Further, the first execution module 100 further performs the following steps:

[0079] S101, obtaining a maximum value Ai(max) corresponding to any Ai and a minimum value Ai(min) corresponding to Ai, where Ai(max) represents the maximum value of the ith initial device parameter, and Ai(min) represents the minimum value of the ith initial device parameter;

[0080] S102, determining p initial device parameter regions corresponding to Ai according to the maximum value Ai(max) and the minimum value Ai(min) corresponding to Ai, where the xth initial device parameter region is [Vix1, Vix2), and x ranges from 1 to p. It can be understood that the starting value of the first initial device parameter region is Ai(min), and the end value of the pth initial device parameter region is Ai(max).

[0081] Wherein, Vix1 meets the following condition:

[0082] Vix1=Ai(min)+(x-1)*(Ai(max)-Ai(min)) / p;

[0083] Wherein, Vix2 meets the following condition:

[0084] Vix2=Ai(min)+x*(Ai(max)-Ai(min)) / p.

[0085] Further, the above steps further include the following step of obtaining p:

[0086] Step 1, obtaining an initial device parameter span value L={L1,..., Li,..., Lm}, Li=Ai(max)-Ai(min), and step 2, determining p according to L; that is, after L is sorted in size order, L0={L01,..., L0y,..., L0q},

[0087] q = m, g1 = GCD (L02, L01) = GCD (L02, L02%L01), wherein L02> L01, and then g2 is determined according to g1, g2 = GCD (g1, L03); and so on, until all numbers are calculated, and finally GCD (L01,..., L0y,..., L0q) is obtained, and GCD (L01,..., L0y,..., L0q) * m is taken as p; wherein the GCD () function is a greatest common divisor function of two numbers.

[0088] S103, according to all initial device parameter regions corresponding to Ai, any Ai={Ai1,..., Aix,..., Aip} is obtained, and Aix refers to the xth initial device parameter randomly selected from Ai, that is, Aix is randomly selected from the xth initial device parameter region.

[0089] Based on the maximum and minimum values of different initial device parameters, the device parameter region suitable for division is determined, and the device parameter value is randomly selected in the device parameter region to avoid incomplete coverage of the device parameters, so that the optimization of the device parameters cannot be realized, and the error caused by large data noise in the optimization of the drilling parameters is avoided, and the accuracy is improved.

[0090] The second execution module 200 is configured to receive a current environment data set B={B1,..., Bj,..., Bn} uploaded by an environment sensor in a target drilling device, and Bj refers to the ith current environment data subset, and j has a value range of 1 to n, and n is the total number of current environment data subsets. It can be understood that: the current environment data refers to the current surrounding environment data of the drilling device and the device environment data thereof, for example, rock hardness, drill bit temperature, drill bit vibration amplitude, etc.

[0091] Preferably, when n = 3, B = {B1, B2, B3}, B1 is a current rock hardness data subset, B2 is a current drill bit temperature data subset, and B3 is a current drill bit vibration amplitude data subset.

[0092] The third execution module 300 is configured to optimize A when F≥F0, to obtain an optimized parameter set C={C1,..., Ci,..., Cm} corresponding to A, Ci refers to an optimized parameter corresponding to Ai, and the execution parameter of the target drilling device is controlled to adopt C, wherein F refers to a device parameter optimization value determined based on B, and F0 refers to a preset device parameter optimization threshold; wherein the device parameter optimization value is used to reflect an index of whether the target device starts to optimize the device parameter, and a person skilled in the art can set the preset device parameter optimization threshold according to actual needs, which will not be described here.

[0093] Further, the third execution module 300 further comprises:

[0094] The first obtaining module 10 is configured to obtain any Bj={Bj1,..., Bjr,..., Bjs(j)}, where Bjr represents the rth current environment data in Bj, r ranges from 1 to s(j), and s(j) represents the amount of current environment data in Bj;

[0095] The second obtaining module 11 is configured to obtain an optimization degree value Kj corresponding to Bj based on all Bjr; further, Kj satisfies the following condition:

[0096] Kj= ((∑ s（j） r=1 Bjr / s(j)) - Bjmin) / (Bjmax - Bjmin) + (Bjmax - (∑ s（j） r=1 Bjr / s(j))) / (Bjmax - Bjmin) + √ (∑ s（j） r=1 (Bjr - (∑ s（j） r=1 Bjr / s(j)) 2 )

[0097] The third obtaining module 12 is configured to obtain F according to all Kj, and F satisfies the following condition:

[0098] F=∑ m j=1 Wj*Kj, where Wj represents a weight value corresponding to Kj, the weight value is set by a person skilled in the art according to actual requirements, and pre-selection is Wj=1 / m.

[0099] Further, F satisfies the following condition:

[0100] F=∑ m j=1 Wj*Kj+U0, where U0 represents an associated optimization degree value corresponding to B; it can be understood that the associated optimization degree value is an optimization degree generated by considering the correlation degree between Bj based on ∑ m j=1 Wj*Kj.

[0101] The above-mentioned associated optimization degree is generated based on the correlation degree between different environment data, which avoids the case of using only environment data to determine the device parameters to be started for optimization, thereby avoiding inaccurate judgment timing and the resulting error in drilling parameter optimization, and improving the accuracy.

[0102] Specifically, the third execution module 300 further performs the following steps:

[0103] S301, obtaining Ai={Ai1,..., Aix,..., Aip};

[0104] S302, based on Aix, determine the intermediate device parameter Dix corresponding to Aix, wherein Dix meets the following conditions:

[0105] Dix = Aix + φix * (Aix - Giy), where φix refers to the random parameter optimization influence factor corresponding to Aix, φix ∈ [-1, 1], and Giy refers to the y-th initial device parameter in Ai other than Aix, where the value of y ranges from 1 to q, and q = p - 1;

[0106] S303, when e -Dix >e -Aix At that time, Ci is determined to be Dix.

[0107] The above-mentioned optimization method can avoid errors in drilling parameter optimization caused by large data noise and improve accuracy.

[0108] The fourth execution module 400 is used to maintain the execution parameters of the target drilling equipment when F < F0; that is, when F < F0, the execution parameter is Aix.

[0109] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. It should also be understood that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for optimizing drilling control based on a bee colony algorithm, characterized in that, The method comprises the following steps: S100, receiving an initial device parameter set A={A1,..., Ai,..., Am} uploaded by a target drilling device, Ai represents an i-th initial device parameter value range, i represents a value range of 1 to m, m represents a total number of initial device parameters, and the S100 step further comprises the following steps: S101, acquiring a maximum value Ai(max) corresponding to any Ai and a minimum value Ai(min) corresponding to the Ai; S102, determining p initial device parameter regions corresponding to the Ai according to the maximum value Ai(max) corresponding to the Ai and the minimum value Ai(min) corresponding to the Ai, wherein an x-th initial device parameter region is [Vix1, Vix2), and x represents a value range of 1 to p; Vix1=Ai(min)+(x-1)*(Ai(max)-Ai(min)) / p; Vix2=Ai(min)+x*(Ai(max)-Ai(min)) / p; The method further comprises the following steps of acquiring p: Step 1, acquiring an initial device parameter span value L={L1,..., Li,..., Lm}, Li=Ai(max)-Ai(min), step 2, determining p according to L; that is, L is sorted in size order, L0={L01,..., L0y,..., L0q}, q=m, g1=GCD(L02, L01)=GCD(L02, L02%L01), wherein L02>L01, g2 is determined according to g1, g2=GCD(g1, L03), and in this way, until all numbers are calculated, GCD(L01,..., L0y,..., L0q) is finally obtained, and GCD(L01,..., L0y,..., L0q)*m is taken as p; S103, acquiring any Ai={Ai1,..., Aix,..., Aip} according to all initial device parameter regions corresponding to the Ai, Aix represents an x-th initial device parameter randomly selected from the Ai; S200, receiving a current environment data set B={B1,..., Bj,..., Bn} uploaded by an environment sensor in a target drilling device, Bj represents an i-th current environment data subset, j represents a value range of 1 to n, and n represents a total number of current environment data subsets; S300, when F≥F0, optimizing A to obtain an optimized parameter set C={C1,..., Ci,..., Cm} corresponding to A, Ci represents an optimized parameter corresponding to Ai, and C is used to control an execution parameter of the target drilling device, wherein F represents a device parameter optimization value determined based on B, F0 represents a preset device parameter optimization threshold; the S300 step further comprises the following steps: S10, acquiring any Bj={Bj1,..., Bjr,..., Bjs(j)}, Bjr represents an r-th current environment data in Bj, r represents a value range of 1 to s(j), and s(j) represents a current environment data quantity in Bj; ​ ​ S11, based on all Bjr, get the optimization degree value Kj corresponding to Bj; wherein, Kj conforms to the following conditions: Kj= ((∑ s（j） r=1 Bjr / s(j))-Bjmin) / (Bjmax-Bjmin)+ (Bjmax-(∑ s（j） r=1 Bjr / s(j))) / (Bjmax-Bjmin)+√(∑ s（j） r=1 (Bjr-(∑ s（j） r=1 Bjr / s(j)) 2 ) S12, obtaining F according to all Kj, F meets the following condition: F =∑ m j=1 Wj*Kj, where Wj refers to the weight value corresponding to Kj; S400, when F 2. The method for optimization of borehole control based on swarm algorithm according to claim 1, characterized in that, When m=4, A={A1, A2, A3, A4}, A1 is an initial drill bit speed range value, A2 is an initial feed speed range value, A3 is an initial drilling pressure range value, and A4 is an initial cooling liquid flow range value.

3. The method for optimization of borehole control based on swarm algorithm according to claim 1, characterized in that, When n=3, B={B1, B2, B3}, B1 is a current rock hardness data subset, B2 is a current drill bit temperature data subset, and B3 is a current drill bit vibration amplitude data subset.

4. The method for optimization of borehole control based on swarm algorithm according to claim 1, characterized in that, F meets the following condition: F =∑ m j=1 Wj*Kj+U0, U0 refers to the corresponding associated optimization degree value of B.

5. A system for optimization of borehole control based on swarm algorithm, characterized by, The system comprises: A first execution module 100 is configured to receive an initial device parameter set A={A1,..., Ai,..., Am} uploaded by a target drilling device, where Ai represents an i-th initial device parameter value range, i represents a value range of 1 to m, m represents a total number of initial device parameters, and the initial device parameter set A is used to control an execution parameter of the target drilling device. A second execution module 200 is configured to receive a current environment data set B={B1,..., Bj,..., Bn} uploaded by an environment sensor in the target drilling device, where Bj represents an i-th current environment data subset, j represents a value range of 1 to n, n represents a total number of current environment data subsets, and the current environment data set B is used to determine an optimized value of a device parameter. A third execution module 300 is configured to, when F≥F0, optimize A to obtain an optimized parameter set C={C1,..., Ci,..., Cm} corresponding to A, where Ci represents an optimized parameter corresponding to Ai, and the execution parameter of the target drilling device is controlled to adopt C, F represents a device parameter optimized value determined based on B, F0 represents a preset device parameter optimization threshold, and the third execution module 300 comprises: A first acquisition module 10 is configured to acquire any Bj={Bj1,..., Bjr,..., Bjs(j)}, where Bjr represents an r-th current environment data in Bj, r represents a value range of 1 to s(j), and s(j) represents a current environment data quantity in Bj. The second obtaining module 11 obtains an optimization degree value Kj corresponding to Bj based on all Bjr; wherein Kj meets the following condition: Kj= ((∑ s（j） r=1 Bjr / s(j))-Bjmin) / (Bjmax-Bjmin)+ (Bjmax-(∑ s（j） r=1 Bjr / s(j))) / (Bjmax-Bjmin)+√((∑ s（j） r=1 Bjr-(∑ s（j） r=1 Bjr / s(j)) 2 ). A third acquisition module 12 is configured to obtain F according to all Kj, and F meets the following condition: F =∑ m j=1 Wj*Kj, where Wj refers to the weight value corresponding to Kj; A fourth execution module 400 is configured to, when F 6. The system for optimization of borehole control based on swarm algorithm according to claim 5, characterized in that, When m=4, A={A1, A2, A3, A4}, A1 is an initial drill bit speed range value, A2 is an initial feed speed range value, A3 is an initial drilling pressure range value, and A4 is an initial cooling liquid flow range value.

7. The system for optimization of borehole control based on swarm algorithm according to claim 5, wherein, When n=3, B={B1, B2, B3}, B1 is a current rock hardness data subset, B2 is a current drill bit temperature data subset, and B3 is a current drill bit vibration amplitude data subset.

8. The system for optimization of borehole control based on swarm algorithm according to claim 5, wherein, F meets the following condition: U0 is the corresponding correlation optimization degree value of B.

Images