Drilling machine working data analysis method for drilling machine management

Abstract

The invention relates to the technical field of drilling machine management, solves the technical problems that in the prior art, a sensor is prone to environmental interference, the accuracy of an intelligent algorithm is low, and the calculation process is complex, and particularly relates to a drilling machine working data analysis method for drilling machine management. Preprocessing the working data to obtain preprocessed data; s2, the preprocessed data is divided into flutter data, drill rod data, motor data and forward data, and the total flutter force Fzk of the drilling machine is calculated according to the flutter data, the forward speed of the drilling machine can be efficiently analyzed by analyzing and predicting the forward data, the calculation process in the prior art is simplified, the calculation efficiency is improved, and the total flutter force Fzk of the drilling machine is calculated according to the total flutter force Fzk. Moreover, rapid convergence of the prediction result can be carried out globally, the robustness of the algorithm is improved, and the efficiency and accuracy of forward speed prediction are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling rig management, and in particular to a drilling rig work data analysis method for drilling rig management. Background Art

[0002] A drilling rig generally refers to a machine installed at the drilling location where holes are drilled in the strata of a mine. Drilling rig management is an important link to ensure the efficient operation of the drilling rig, extend the life of the equipment, and ensure construction safety. It covers the daily maintenance, safe operation, and troubleshooting of the drilling rig. The drilling rig working data is an important indicator that reflects the operating status, work efficiency, and construction quality of the drilling rig, including but not limited to the drilling depth, drilling rig speed, oil level, vibration force, torque, etc. When analyzing the working data of the drilling rig, the existing technology generally installs multiple sensors at key locations and constructs a prediction model through a neural network algorithm to analyze the drilling rig data. However, this method not only requires the installation of a large number of sensors, but is also easily affected by environmental interference during the drilling process. During the analysis process, the neural network algorithm is difficult to accurately analyze different data, especially the calculation accuracy of nonlinear data is low, the calculation process is complex, and the efficiency is low. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a drilling rig work data analysis method for drilling rig management, which solves the technical problems that the sensors in the prior art are easily affected by environmental interference, the accuracy of the intelligent algorithm is low, and the calculation process is complicated. It achieves the purpose of greatly enhancing the anti-interference performance of the analysis method, improving the accuracy of the analysis, and making the calculation process simple and efficient.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a drilling rig work data analysis method for drilling rig management, the method comprising the following steps:

[0005] S1. Collect the working data of the drilling rig Gz a , and preprocess the working data to obtain preprocessed data;

[0006] S2, dividing the pre-processed data into vibration data, drill rod data, motor data and forward data, and calculating the total vibration force Fz of the drilling rig based on the vibration data k ;

[0007] S3. Take each drill rod on the drilling rig as an inertia body and calculate the single moment of inertia Zg of each inertia body. l , and according to the single moment of inertia Zg l Calculate the overall moment of inertia Z of the drilling rig t ;

[0008] S4. Calculate the motor variable control function Xf based on the motor data u ';

[0009] S5. Obtain the group size N and data dimension W of the forward data, and calculate the forward speed Vq of the drilling rig according to the group size N and data dimension W. s ;

[0010] S6, according to the flutter force Fz k 、Overall moment of inertia Z t , variable control function Xf u ', forward speed Vq s Construct the analytical value Gf of the drilling rig v , according to the analytical value Gf v Get the analysis results of the drilling rig;

[0011] S7. Send the analysis results to the drilling rig control center.

[0012] Preferably, in step S1, the specific implementation steps are as follows:

[0013] S11. Calculate working data Gz a The average The calculation formula is:

[0014]

[0015] Among them, Gz a represents the ath working data, A represents the working data Gz a the number of

[0016] S12. Identify the working data Gz by time series recognition method a The missing values ​​in Gq b , and according to the missing value Gq b Adjacent work data Gq b-1 and Gq b+1 Calculate the fill value Gb c , the calculation formula is as follows:

[0017]

[0018] Among them, Gb c Indicates the cth filling value, Gq b-1 and Gq b+1 Respectively represent the missing value Gq b Adjacent work data;

[0019] S13, based on the average Calculate working data Gz a Fluctuation value The calculation formula is as follows:

[0020]

[0021] in, represents the sth average value, and N represents the average value and work data Gz a The number of groups;

[0022] S14, according to the fluctuation value Calculate the replacement value Gy of the outlier e ', the calculation formula is:

[0023]

[0024] Among them, Gz a+1 and Gz a-1 Respectively represent a+1th and a-1th;

[0025] S15. Create a window with a window size of d and calculate the working data Gz in the window ck The smoothing value Gp f , the calculation formula is:

[0026]

[0027] Among them, Gz ck represents the working data within the window range, and d represents the working data Gz ck the number of

[0028] S16, smoothing value Gp f Generate preprocessed data in chronological order.

[0029] Preferably, in step S2, the specific implementation steps are as follows:

[0030] S21, the vibration data includes amplitude D and frequency Zf g , according to the amplitude D and frequency Zf g , calculate the flutter displacement wy l , the calculation formula is:

[0031] wy l =D×sin(Zf g ·t+θ)

[0032] Wherein, t represents time, and θ represents the phase value of the vibration waveform corresponding to time t;

[0033] S22, according to the vibration displacement wy l Calculate the flutter velocity Vc m , the calculation formula is:

[0034]

[0035] Among them, dwy land dt represent the variation of flutter displacement and time, respectively;

[0036] S23, according to the vibration speed Vc m Calculate the flutter acceleration a j , the calculation formula is:

[0037]

[0038] Among them, dVc m Indicates the flutter speed Vc m The amount of change;

[0039] S24, according to the vibration acceleration a j Calculate the drill's inertia force F g , the calculation formula is:

[0040] F g =m·a j

[0041] Among them, a j represents the vibration acceleration corresponding to the change dt at the jth time, and m represents the mass of the drilling rig;

[0042] S25, according to the inertia force F g Calculate the total flutter force Fz of the drilling rig k , the calculation formula is:

[0043] F k =F g +c·Vc m +K·wy l

[0044] Among them, c represents the damping coefficient of the drilling rig, and K represents the stiffness coefficient of the drilling rig.

[0045] Preferably, in step S3, the specific implementation steps are as follows:

[0046] S31, the drill pipe data includes density gρ i , Square head thickness fh m and the material density of the drill bucket ρf, according to the density gρ i Calculate the single moment of inertia Zg of the inertial body l , the calculation formula is:

[0047]

[0048] Among them, D j and d j Respectively represent the outer diameter and inner diameter of the drill pipe, Zg l represents the single moment of inertia of the lth drill rod;

[0049] S32, according to the square head thickness fh m Calculate the moment of inertia Zf of the square bucket n , the calculation formula is:

[0050]

[0051] Among them, Dd o represents the outer diameter of the drill bucket, ρf represents the material density of the drill bucket square bucket;

[0052] S33, calculate the moment of inertia Zt of the drill tube connected to the drill tube according to the material density ρf of the drill tube p , the calculation formula is:

[0053]

[0054] Among them, D q and d q Respectively represent the outer diameter and inner diameter of the drill tube connected to the drill bucket, Lt k Indicates the height of the drill tube;

[0055] S34, according to the cylinder moment of inertia Zt p Calculate the bucket moment of inertia Zz s , the calculation formula is:

[0056] Zz s =Zf n +Zt p

[0057] Among them, Zz s represents the moment of inertia of the sth bucket;

[0058] S35, according to the barrel rotation inertia Zz s Calculate the overall moment of inertia Z t , the calculation formula is:

[0059]

[0060] Where N represents the single moment of inertia Zg l The number of js a and js b Represent the reduction ratio of the reducer and power box respectively.

[0061] Preferably, in step S4, the specific implementation steps are as follows:

[0062] S41, the motor data includes valve flow coefficient Fk x , volt-ampere gain Fa K and variable piston maximum displacement Xf max , according to the valve flow coefficient Fk x and volt-ampere gain FaK Calculate the chamber pressure Pm of the control chamber in the motor d , the calculation formula is:

[0063]

[0064] Among them, X f Indicates the valve core displacement of the motor's proportional valve, Q l Indicates the proportional valve flow rate of the motor;

[0065] S42, according to the cavity pressure Pm d Calculate the optimal cavity pressure Pm zy , the calculation formula is:

[0066]

[0067] Among them, Sh a represents the cross-sectional area of ​​the control chamber piston, t x Indicates cavity pressure Pm zy The reference time, Xf u Represents the displacement of the motor's variable piston, xl s Indicates the leakage coefficient of the control chamber, β b represents the elastic modulus, V c represents the initial volume of the control chamber;

[0068] S43, according to the optimized cavity pressure Pm zy Calculate the load force balance equation, the expression is:

[0069] Pm zy ·Sh a =m bl ·t x 2 ·Xf u +Bg z ·t x ·Xf u +K e ·Xf u +Fg L

[0070] Among them, m bl Indicates the control cavity quality, Bg z represents the damping coefficient of the control chamber piston, K e Indicates the spring stiffness in the control chamber, Fg L It indicates the initial load force measured in the control cavity;

[0071] S44, according to the maximum displacement of the variable piston Xf max Calculate the instantaneous swing angle γ of the motor b , the calculation formula is:

[0072]

[0073] Among them, γ max represents the maximum swing angle of the motor, γ o Indicates the initial swing angle of the motor;

[0074] S45, according to the instantaneous swing angle γ of the motor b Calculate the variable control function Xf of the motor u '.

[0075] Preferably, the variable control function Xf u The calculation formula of ' is:

[0076]

[0077] Among them, K ec Indicates the motor control chamber pressure-flow coefficient, L b Indicates the conversion ratio, f y represents the hydraulic natural frequency, δ h Indicates the hydraulic damping ratio, Kh r Hydraulic spring rate.

[0078] Preferably, in step S5, the specific implementation steps are as follows:

[0079] S51, determine the initial individual optimal solution Gp by individual tracking method according to the group size N and data dimension W best =(Gp a1 , Gp a2 ...Gp aW ), a=1, 2, ... N;

[0080] S52, determine the initial global optimal solution Qj through the global sharing method according to the group size N and the data dimension W best =(Qj b1 , Qj b2 ……Qj bW ), b = 1, 2, ... N;

[0081] S53, according to the advancing time t of the drilling rig q Computational fitness function vs. g , the calculation formula is:

[0082] vs g =vs o +a d ·t q

[0083] Among them, vs g represents the g-th fitness function, vs o represents the initial velocity of drilling, a d represents the acceleration of the drilling rig;

[0084] S54, according to the fitness function vs g Get the updated value of the kth data vs g (k), and based on the updated value vs g (k) For the individual optimal solution Gp best Make a substitution;

[0085] If vs g (k) <Gp best , then use the updated value vs g (k) Replacement of Gp best ;

[0086] If vs g (k)≥Gp best , then keep Gp best and remove vs g (k);

[0087] S55, according to the updated value vs g (k) For the global optimal solution Qj best Make a substitution;

[0088] If vs g (k) <Qj best , then use the updated value vs g (k) Replace Qj best ;

[0089] If vs g (k)≥Qj best , then keep Qj best and remove vs g (k);

[0090] S56, generate a random weight ω through a random generator, and calculate the optimal solution Gp according to the individual best and the global optimal solution Qj best Calculate the iteration speed Vd k+1 ;

[0091] S57, according to the iteration speed Vd k+1 Calculate the iteration position Xd k+1 , the calculation formula is:

[0092] XD k+1 =Xd k +Vd k+1

[0093] Among them, Xd k+1 Indicates the k+1th iteration position;

[0094] S58. Calculate the number of iterations Ac according to the group size N and the data dimension W. The calculation formula is:

[0095]

[0096] Among them, Ac represents the c-th iteration number;

[0097] S59. Judge whether the iteration terminates according to the iteration number Ac;

[0098] If k + 1 = Ac, the iteration terminates, and the iteration speed Vd k+1 is used as the forward speed Vq s ;

[0099] If k + 1 < Ac, return to step S56 to use the iteration speed Vd k+1 as the previous generation speed Vd k for calculation.

[0100] Preferably, the calculation formula of the iteration speed Vd k+1 is:

[0101] Vd k+1 = ωVd k + C 1 S 1 (Gp best - Xd k ) + C 2 S 2 (Qj best - Xd k )

[0102] Among them, Vd k represents the k-th previous generation speed, C 1 and C 2 represent learning coefficients, S 1 and S 2 represent random numbers between 0 and 1, Xd k represents the k-th previous generation position.

[0103] Preferably, in step S6, the specific implementation steps are as follows:

[0104] S61. Obtain the flutter force Fz k , the overall moment of inertia Z t , the variable control function Xf u ', the forward speed Vq s The data quantities of are P, Q, S, and T respectively, and calculate the weight coefficients α, β, γ, and δ. The calculation formula is:

[0105]

[0106] Among them, α, β, γ, and δ respectively represent the flutter force Fz k , the overall moment of inertia Zt , variable control function Xf u ', forward speed Vq s The corresponding weight coefficient;

[0107] S62, calculate the analysis value Gf according to the weight coefficients α, β, γ and δ v , the calculation formula is:

[0108]

[0109] Among them, Gf v represents the vth analysis value;

[0110] S63, according to the analysis value Gf v Calculate the fluctuation value B d , the calculation formula is:

[0111]

[0112] in, Indicates multiple analysis values ​​Gf v The number of V represents the analytical value Gf v and The number of groups;

[0113] S64, according to the fluctuation value B d Analyze the work of the drilling rig and obtain the analysis results;

[0114] like The drilling rig works normally and generates normal analysis results;

[0115] like The drilling rig is operating abnormally and generates abnormal analysis results.

[0116] By means of the above technical solution, the present invention provides a drilling rig work data analysis method for drilling rig management, which has at least the following beneficial effects:

[0117] 1. The present invention can not only improve the accuracy and processing efficiency of working data, but also reduce the impact of external environment on data and enhance the anti-interference ability of the present invention by efficiently filling missing values ​​in working data, replacing abnormal values ​​of data fluctuations, and smoothing data.

[0118] 2. The present invention takes each drill rod of the drilling rig as a research object, calculates the inertia of a single drill rod, and then comprehensively calculates the rotational inertia of all the drill rods to obtain the overall rotational inertia of the drilling rig. The overall calculation process is simplified, which not only improves the calculation efficiency of the rotational inertia, but also improves the accuracy of the overall rotational inertia.

[0119] 3. The present invention can improve the calculation accuracy of the motor variable control function by calculating the motor control function and the calculation of values ​​such as the comprehensive current and cavity pressure. The state of the motor can reflect the working state of the drilling rig, thereby improving the accuracy of the state analysis of the drilling rig. The motor variable control function can also show the movement of the motor cavity and the internal piston, so it can also perform the working analysis of the motor and timely complete the detection of motor abnormalities.

[0120] 4. The present invention can efficiently analyze the forward speed of the drilling rig by analyzing the forward data and analyzing and predicting the speed and position during the forward movement. It not only simplifies the calculation process of the prior art and improves the calculation efficiency, but also can quickly converge the prediction results globally, and also improves the robustness of the algorithm, greatly improving the efficiency and accuracy of the forward speed prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0121] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0122] Figure 1 The present invention is a flowchart of a drilling rig work data analysis method for drilling rig management. DETAILED DESCRIPTION

[0123] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0124] Due to the technical problems of existing technology sensors being easily affected by environmental interference, low accuracy of intelligent algorithms, and complex calculation processes, please refer to Figure 1 This embodiment provides a drilling rig work data analysis method for drilling rig management, which can greatly enhance the anti-interference performance of the analysis method, improve the accuracy of the analysis, and make the calculation process simple and efficient. The method includes the following steps:

[0125] S1. Collect the working data of the drilling rig Gz a , and preprocess the working data to obtain preprocessed data; the obtained working data Gz a Due to the influence of the mine environment, the working data Gz a Preprocessing is required. In step S1, the specific implementation steps are as follows:

[0126] S11. Calculate working data Gz a The average The calculation formula is:

[0127]

[0128] Among them, Gz a represents the ath working data, A represents the working data Gz a the number of

[0129] S12. Identify the working data Gz by time series recognition method a The missing values ​​in Gq b , and according to the missing value Gq b Adjacent work data Gq b-1 and Gq b+1 Calculate the fill value Gb c , the calculation formula is as follows:

[0130]

[0131] Among them, Gb c Indicates the cth filling value, Gq b-1 and Gq b+1 Respectively represent the missing value Gq b The time series recognition method can quickly find the missing data through the corresponding relationship between data and time. This method is simple and efficient, and is a commonly used missing value search method, which will not be elaborated here.

[0132] S13, based on the average Calculate working data Gz a Fluctuation value The calculation formula is as follows:

[0133]

[0134] in, represents the sth average value, and N represents the average value and work data Gz a The number of groups; the fluctuation value can reflect the working data Gz a The fluctuation range of , helps to identify outliers.

[0135] S14, according to the fluctuation value Calculate the replacement value Gy of the outlier e ', the calculation formula is:

[0136]

[0137] Among them, Gz a+1 and Gz a-1 Respectively represent a+1th and a-1th;

[0138] S15. Create a window with a window size of d and calculate the working data Gz in the window ck The smoothing value Gp f , the calculation formula is:

[0139]

[0140] Among them, Gz ck represents the working data within the window range, and d represents the working data Gz ck The number of working data Gz ck Smoothing can increase the accuracy of data and avoid errors in data processing caused by large fluctuations.

[0141] S16, smoothing value Gp f The preprocessed data is generated by arranging them in chronological order. By efficiently filling missing values ​​in the working data, replacing abnormal values ​​of data fluctuations, and smoothing the data, not only the accuracy and processing efficiency of the working data can be improved, but also the impact of the external environment on the data can be reduced, thereby improving the anti-interference ability of the present invention.

[0142] S2, dividing the pre-processed data into vibration data, drill rod data, motor data and forward data, and calculating the total vibration force Fz of the drilling rig based on the vibration data k ; The preprocessed data contains various data of the drilling rig. In order to facilitate the subsequent classification and processing of different data, the preprocessed data is divided into categories and the total flutter force Fz is calculated. k In step S2, the specific implementation steps are as follows:

[0143] S21, the vibration data includes amplitude D and frequency Zf g , according to the amplitude D and frequency Zf g , calculate the flutter displacement wy l , the calculation formula is:

[0144] wy l =D×sin(Zf g ·t+θ)

[0145] Among them, t represents time, and θ represents the phase value of the vibration waveform corresponding to time t. The phase value can be obtained by obtaining the waveform through an oscilloscope and then calculated through a sine function. The sine function is a common method for calculating waveforms in mathematics, which will not be described in detail here.

[0146] S22, according to the vibration displacement wy l Calculate the flutter velocity Vc m , the calculation formula is:

[0147]

[0148] Among them, dwy l and dt represent the variation of flutter displacement and time, respectively;

[0149] S23, according to the vibration speed Vc m Calculate the flutter acceleration a j , the calculation formula is:

[0150]

[0151] Among them, dVc m Indicates the flutter speed Vc m The amount of change;

[0152] S24, according to the vibration acceleration a j Calculate the drill's inertia force F g , the calculation formula is:

[0153] F g =m·a j

[0154] Among them, a j represents the vibration acceleration corresponding to the j-th time change dt, and m represents the mass of the drilling rig; the mass of the drilling rig can be directly obtained from the nameplate of the drilling rig.

[0155] S25, according to the inertia force F g Calculate the total flutter force Fz of the drilling rig k , the calculation formula is:

[0156] F k =F g +c·Vc m +K·wy l

[0157] Where c represents the damping coefficient of the drilling rig, and K represents the stiffness coefficient of the drilling rig. The damping coefficient and stiffness coefficient of the drilling rig can be directly obtained by the damped vibration attenuation method and the static measurement method. These two methods are common, efficient and concise methods for obtaining the damping coefficient and stiffness coefficient. They will not be described here. k The calculation can provide data support for the subsequent drilling rig work analysis, greatly improving the analysis efficiency.

[0158] S3. Take each drill rod on the drilling rig as an inertia body and calculate the single moment of inertia Zg of each inertia body. l , and according to the single moment of inertia Zg l Calculate the overall moment of inertia Z of the drilling rig tThe prior art general sensor collects multiple physical quantities for complex calculations to obtain the moment of inertia. Not only is the calculation process inefficient, but the data collected by the sensor is prone to errors, and the calculation result has a large error. In order to solve this problem, in step S3, the specific implementation steps are as follows:

[0159] S31, the drill pipe data includes density gρ i , Square head thickness fh m and the material density of the drill bucket ρf, according to the density gρ i Calculate the single moment of inertia Zg of the inertial body l , the calculation formula is:

[0160]

[0161] Among them, D j and d j Respectively represent the outer diameter and inner diameter of the drill pipe, Zg l Represents the single moment of inertia of the lth drill rod; the body of inertia can be understood as an ideal model. Through simple calculation of the body of inertia, the calculation process of the drilling rig's moment of inertia can be simplified, and a large amount of physical quantities are not required for calculation. The overall moment of inertia of the drilling rig is calculated through the coupling of the drill rod rotation, which can not only improve the accuracy but also simplify the calculation process.

[0162] S32, according to the square head thickness fh m Calculate the moment of inertia Zf of the square bucket n , the calculation formula is:

[0163]

[0164] Among them, Dd o represents the outer diameter of the drill bucket, ρf represents the material density of the drill bucket square bucket;

[0165] S33, calculate the moment of inertia Zt of the drill tube connected to the drill tube according to the material density ρf of the drill tube p , the calculation formula is:

[0166]

[0167] Among them, D q and d q Respectively represent the outer diameter and inner diameter of the drill tube connected to the drill bucket, lt k Indicates the height of the drill tube;

[0168] S34, according to the cylinder moment of inertia Zt p Calculate the bucket moment of inertia Zz s , the calculation formula is:

[0169] Zzs =Zf n +Zt p

[0170] Among them, Zz s represents the moment of inertia of the sth bucket;

[0171] S35, according to the barrel rotation inertia Zz s Calculate the overall moment of inertia Z t , the calculation formula is:

[0172]

[0173] Where N represents the single moment of inertia Zg l The number of js a and js b They represent the reduction ratios of the reducer and the power box respectively. Each drill rod of the drilling rig is taken as the research object, the inertia of a single drill rod is calculated, and then the rotational inertia of all the drill rods is comprehensively calculated to obtain the overall rotational inertia of the drilling rig. The overall calculation process is simplified, which not only improves the calculation efficiency of the rotational inertia, but also improves the accuracy of the overall rotational inertia.

[0174] S4. Calculate the motor variable control function Xf based on the motor data u '; The drilling rig motor occupies an important position in the drilling rig analysis. The existing technology can only analyze the motor by collecting data through sensors, and it also needs to cooperate with the neural network algorithm, which is very inefficient. To solve this problem, in step S4, the specific implementation steps are as follows:

[0175] S41, the motor data includes valve flow coefficient Fk x , volt-ampere gain Fa K and variable piston maximum displacement Xf max , according to the valve flow coefficient Fk x and volt-ampere gain Fa K Calculate the chamber pressure Pm of the control chamber in the motor d , the calculation formula is:

[0176]

[0177] Among them, X f Indicates the valve core displacement of the motor's proportional valve, Q l Represents the proportional valve flow of the motor; simplifying the motor's variable mechanism into a valve-controlled cylinder system can simplify the calculation process and improve calculation efficiency.

[0178] S42, according to the cavity pressure Pm d Calculate the optimal cavity pressure Pm zy , the calculation formula is:

[0179]

[0180] Among them, Sh a represents the cross-sectional area of ​​the control chamber piston, t x Indicates cavity pressure Pm zy The reference time, Xf u Represents the displacement of the motor's variable piston, xl s Indicates the leakage coefficient of the control chamber, β b represents the elastic modulus, V c represents the initial volume of the control chamber;

[0181] S43, according to the optimized cavity pressure Pm zy Calculate the load force balance equation, the expression is:

[0182] Pm zy ·Sh a =m bl ·t x 2 ·Xf u +Bg z ·t x ·Xf u +K e ·Xf u +Fg L

[0183] Among them, m bl Indicates the control cavity quality, Bg z represents the damping coefficient of the control chamber piston, K e Indicates the spring stiffness in the control chamber, Fg L It indicates the initial load force measured in the control cavity;

[0184] S44, according to the maximum displacement of the variable piston Xf max Calculate the instantaneous swing angle γ of the motor b , the calculation formula is:

[0185]

[0186] Among them, γ max represents the maximum swing angle of the motor, γ o Indicates the initial swing angle of the motor;

[0187] S45, according to the instantaneous swing angle γ of the motor b Calculate the variable control function Xf of the motor u ', the calculation formula is:

[0188]

[0189] Among them, K ecIndicates the motor control chamber pressure-flow coefficient, L b Indicates the conversion ratio, f y represents the hydraulic natural frequency, δ h Indicates the hydraulic damping ratio, Kh r The hydraulic spring stiffness can improve the calculation accuracy of the motor variable control function by calculating the motor control function and the integrated current, cavity pressure and other numerical calculations. The state of the motor can reflect the working state of the drilling rig, thereby improving the accuracy of the state analysis of the drilling rig. The motor variable control function can also show the movement of the motor cavity and the internal piston, so it can also perform motor working analysis and timely complete the detection of motor abnormalities.

[0190] S5. Obtain the group size N and data dimension W of the forward data, and calculate the forward speed Vq of the drilling rig according to the group size N and data dimension W. s In the prior art, the forward speed of the drilling rig can only be calculated by a complex neural network algorithm, and the accuracy is very low and the convergence speed is slow. In order to solve this problem, in step S5, the specific implementation steps are as follows:

[0191] S51, determine the initial individual optimal solution Gp by individual tracking method according to the group size N and data dimension W best =(Gp a1 , Gp a2 ...Gp aW ), a=1, 2, ... N; the group size N is equivalent to the number of forward data, the data dimension W is equivalent to the number of data types in the forward data, and the individual optimal solution is the optimal position found by each data particle in its individual search history results.

[0192] S52, determine the initial global optimal solution Qj through the global sharing method according to the group size N and the data dimension W best =(Qj b1 , Qj b2 ……Qj bW ), b = 1, 2, ... N; the global optimal solution is the best prediction result found by the entire data particle group during the search process.

[0193] S53, according to the advancing time t of the drilling rig q Computational fitness function vs. g , the calculation formula is:

[0194] vs g =vs o +a d ·t q

[0195] Among them, vs g represents the g-th fitness function, vs orepresents the initial velocity of drilling, a d represents the acceleration of the drilling rig;

[0196] S54, according to the fitness function vs g Get the updated value of the kth data vs g (k), and based on the updated value vs g (k) For the individual optimal solution Gp best Make a substitution; update value vs g (k) is to substitute the kth time into the fitness function vs g The updated value of the kth data obtained in vs g (k).

[0197] If vs g (k) <Gp best , then use the updated value vs g (k) Replacement of Gp best ;

[0198] If vs g (k)≥Gp best , then keep Gp best and remove vs g (k);

[0199] S55, according to the updated value vs g (k) For the global optimal solution Qj best Make a substitution;

[0200] If vs g (k) <Qj best , then use the updated value vs g (k) Replace Qj best ;

[0201] If vs g (k)≥Qj best , then keep Qj best and remove vs g (k);

[0202] S56, generate a random weight ω through a random generator, and calculate the optimal solution Gp according to the individual best and the global optimal solution Qj best Calculate the iteration speed Vd k+1 , the calculation formula is:

[0203] Vd k+1 =ωVd k +C 1 S 1 (Gp best -Xd k )+C 2 S 2(Qj best -Xd k )

[0204] Among them, Vd k represents the k-th previous generation speed, C 1 and C 2 represent learning coefficients, S 1 and S 2 represent random numbers on 0 to 1, Xd k represents the k-th previous generation position; the random generator randomly generates a random weight ω in the range of 1.0 - 2.6, and this random method can improve the convergence speed of the iterative speed Cd k+1 , thereby improving the calculation efficiency of the algorithm. The learning coefficients can be directly obtained according to the historical data of the drilling rig through the experience of the staff.

[0205] S57. Calculate the iterative position Xd k+1 based on the iterative speed Vd k+1 , and the calculation formula is:

[0206] Xd k+1 = Xd k + Vd k+1

[0207] Among them, Xd k+1 represents the (k + 1)-th iterative position;

[0208] S58. Calculate the number of iterations Ac based on the swarm size N and the data dimension W, and the calculation formula is:

[0209]

[0210] Among them, Ac represents the c-th number of iterations;

[0211] S59. Determine whether the iteration terminates according to the number of iterations Ac;

[0212] If k + 1 = Ac, the iteration terminates, and the iterative speed Vd k+1 is used as the forward speed Vq s ;

[0213] If k + 1 < Ac, return to step S56 and use the iterative speed Vd k+1 as the previous generation speed Vd k for calculation. By analyzing the forward data and predicting the speed and position during forward movement, it is possible to efficiently analyze the forward speed of the drilling rig, which not only simplifies the calculation process of the existing technology and improves the calculation efficiency, but also enables the rapid convergence of the prediction results globally and improves the robustness of the algorithm, significantly enhancing the efficiency and accuracy of forward speed prediction.

[0214] S6, according to the flutter force Fz k 、Overall moment of inertia Z t , variable control function Xf u ', forward speed Vq s Construct the analytical value Gf of the drilling rig v , according to the analytical value Gf v Obtain the analysis results of the drilling rig; after obtaining multiple physical quantities, it is necessary to perform a work analysis on the drilling rig. In step S6, the specific implementation steps are as follows:

[0215] S61. Obtaining the flutter force Fz k 、Overall moment of inertia Z t , variable control function Xf u ', forward speed Vq s The number of data are P, Q, S and T respectively, and the weight coefficients α, β, γ and δ are calculated using the following formula:

[0216]

[0217]

[0218] Where α, β, γ and δ represent the flutter force Fz respectively. k 、Overall moment of inertia Z t , variable control function Xf u ', forward speed Vq s The corresponding weight coefficient;

[0219] S62, calculate the analysis value Gf according to the weight coefficients α, β, γ and δ v , the calculation formula is:

[0220]

[0221] Among them, Gf v represents the vth analysis value;

[0222] S63, according to the analysis value Gf v Calculate the fluctuation value B d , the calculation formula is:

[0223]

[0224] in, Indicates multiple analysis values ​​Gf v The number of V represents the analytical value Gf v and The number of groups;

[0225] S64, according to the fluctuation value B d Analyze the work of the drilling rig and obtain the analysis results;

[0226] like The drilling rig works normally and generates normal analysis results;

[0227] like The drilling rig is working abnormally, and an abnormal analysis result is generated. v Further analysis of the working condition of the drilling rig can accurately determine whether the drilling rig is working normally and quickly generate analysis results, thereby improving the work efficiency of the drilling rig work analysis.

[0228] S7. Send the analysis results to the drilling rig control center, which can maintain or repair the drilling rig according to the analysis results.

[0229] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, so the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0230] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A drilling rig work data analysis method for drilling rig management, characterized in that: The method comprises the following steps: S1. Collect the working data of the drilling rig Gz a , and the working data Gz a Perform preprocessing to obtain preprocessed data; S2, dividing the pre-processed data into vibration data, drill rod data, motor data and forward data, and calculating the total vibration force Fz of the drilling rig based on the vibration data k ; S3. Take each drill rod on the drilling rig as an inertia body and calculate the single moment of inertia Zg of each inertia body. l , and according to the single moment of inertia Zg l Calculate the overall moment of inertia Z of the drilling rig t ; S4. Calculate the motor variable control function Xf based on the motor data u '; S5. Obtain the group size N and data dimension W of the forward data, and calculate the forward speed Vq of the drilling rig according to the group size N and data dimension W. s ; S6, according to the total flutter force Fz k 、Overall moment of inertia Z t , variable control function Xf u ', forward speed Vq s Analytical value Gf for building rig v , according to the analytical value Gf v Get the analysis results of the drilling rig; S7. Send the analysis results to the drilling rig control center.

2. The data analysis method according to claim 1, characterized in that: In step S1, the specific implementation steps are as follows: S11. Calculate working data Gz a The average The calculation formula is: Among them, Gz a represents the ath working data, A represents the working data Gz a the number of S12. Identify the working data Gz by time series recognition method a The missing values ​​in Gq b , and according to the missing value Gq b Adjacent work data Gq b-1 and Gq b+1 Calculate the fill value Gb c , the calculation formula is as follows: Among them, Gb c Indicates the cth filling value, Gq b-1 and Gq b+1 Respectively represent the missing value Gq b Adjacent work data; S13, based on the average Calculate working data Gz a Fluctuation value The calculation formula is as follows: in, represents the sth average value, and N represents the average value and work data Gz a The number of groups; S14, according to the fluctuation value Calculate the replacement value Gye' of the outlier, the calculation formula is: Among them, Gz a+1 and Gz a-1 Respectively represent a+1th and a-1th; S15. Create a window with a window size of d and calculate the working data Gz in the window ck The smoothing value Gp f , the calculation formula is: Among them, Gz ck represents the working data within the window range, and d represents the working data Gz ck the number of S16, smoothing value Gp f Generate preprocessed data in chronological order.

3. The data analysis method according to claim 1, characterized in that: In step S2, the specific implementation steps are as follows: S21, the vibration data includes amplitude D and frequency Zf g , according to the amplitude D and frequency Zf g Calculate the flutter displacement wy l , the calculation formula is: wyl=D×sin(Zf g ·t+θ) Wherein, t represents time, and θ represents the phase value of the vibration waveform corresponding to time t; S22, according to the vibration displacement wy l Calculate the flutter velocity Vc m , the calculation formula is: Among them, dwy l and dt represent the variation of flutter displacement and time, respectively; S23, according to the vibration speed Vc m Calculate the flutter acceleration a j , the calculation formula is: Among them, dVc m Indicates the flutter speed Vc m The amount of change; S24, according to the vibration acceleration a j Calculate the drill's inertia force F g , the calculation formula is: F g =m·a j Among them, a j represents the vibration acceleration corresponding to the change dt at the jth time, and m represents the mass of the drilling rig; S25, according to the inertia force F g Calculate the total flutter force Fz of the drilling rig k , the calculation formula is: Fz k =F g +c·Vc m +K·wy l Among them, c represents the damping coefficient of the drilling rig, and K represents the stiffness coefficient of the drilling rig.

4. The data analysis method according to claim 1, characterized in that: In step S3, the specific implementation steps are as follows: S31, the drill pipe data includes density gρ i , Square head thickness fh m and the material density of the drill bucket ρf, according to the density gρ i Calculate the single moment of inertia Zg of the inertial body l , the calculation formula is: Among them, D j and d j Respectively represent the outer diameter and inner diameter of the drill pipe, Zg l represents the single moment of inertia of the lth drill rod; S32, according to the square head thickness fh m Calculate the moment of inertia Zf of the square bucket n , the calculation formula is: Among them, Dd o represents the outer diameter of the drill bucket, ρf represents the material density of the drill bucket square bucket; S33, calculate the moment of inertia Zt of the drill tube connected to the drill tube according to the material density ρf of the drill tube p , the calculation formula is: Among them, D q and d q Respectively represent the outer diameter and inner diameter of the drill tube connected to the drill bucket, Lt k Indicates the height of the drill tube; S34, according to the cylinder moment of inertia Zt p Calculate the bucket moment of inertia Zz s , the calculation formula is: Zz s =Zf n +Zt p Among them, Zz s represents the moment of inertia of the sth bucket; S35, according to the barrel rotation inertia Zz s Calculate the overall moment of inertia Z t , the calculation formula is: Where N represents the single moment of inertia Zg l The number of js a and js b Represent the reduction ratio of the reducer and power box respectively.

5. The data analysis method according to claim 1, characterized in that: In step S4, the specific implementation steps are as follows: S41, the motor data includes valve flow coefficient Fk x , volt-ampere gain Fa K and variable piston maximum displacement Xf max , according to the valve flow coefficient Fk x and volt-ampere gain Fa K Calculate the chamber pressure Pm of the control chamber in the motor d , the calculation formula is: Among them, X f Indicates the valve core displacement of the motor's proportional valve, Q l Indicates the proportional valve flow rate of the motor; S42, according to the cavity pressure Pm d Calculate the optimal cavity pressure Pm zy , the calculation formula is: Among them, Sh a represents the cross-sectional area of ​​the control chamber piston, t x Indicates cavity pressure Pm zy The reference time, Xf u Represents the displacement of the motor's variable piston, xl s Indicates the leakage coefficient of the control chamber, β b represents the elastic modulus, V c represents the initial volume of the control chamber; S43, according to the optimized cavity pressure Pm zy Calculate the load force balance equation, the expression is: Pm zy ·Sh a =m bl ·t x 2 ·Xf u +Bg z ·t x ·Xf u +K e ·Xf u +Fg L Among them, m bl Indicates the control cavity quality, Bg z represents the damping coefficient of the control chamber piston, K e Indicates the spring stiffness in the control chamber, Fg L It indicates the initial load force measured in the control cavity; S44, according to the maximum displacement of the variable piston Xf max Calculate the instantaneous swing angle γ of the motor b , the calculation formula is: Among them, γ max represents the maximum swing angle of the motor, γ o Indicates the initial swing angle of the motor; S45, according to the instantaneous swing angle γ of the motor b Calculate the variable control function Xf of the motor u '.

6. The data analysis method according to claim 5, characterized in that: The variable control function Xf u The calculation formula of ' is: Among them, K ec Indicates the motor control chamber pressure-flow coefficient, L b Indicates the conversion ratio, f y represents the hydraulic natural frequency, δ h Indicates the hydraulic damping ratio, Kh r Hydraulic spring rate.

7. The data analysis method according to claim 1, characterized in that: In step S5, the specific implementation steps are as follows: S51, determine the initial individual optimal solution Gp by individual tracking method according to the group size N and data dimension W best =(Gp a1 , Gp a2 ......Gp aW ), a=1, 2, ... N; S52, determine the initial global optimal solution Qj through the global sharing method according to the group size N and the data dimension W best =(Qj b1 , Qj b2 ......Qj bW ), b=1, 2, ... N; S53, according to the advancing time t of the drilling rig q Computational fitness function vs. g , the calculation formula is: vs g =vs o +a d ·t q Among them, vs g represents the g-th fitness function, vs o represents the initial velocity of drilling, a d represents the acceleration of the drilling rig; S54, according to the fitness function vs g Get the updated value of the kth data vs g (k), and based on the updated value vs g (k) For the individual optimal solution Gp best Make a substitution; If vs g (k) <Gp best , then use the updated value vs g (k) Replacement of Gp best ; If vs g (k)≥Gp best , then keep Gp best and remove vs g (k); S55, according to the updated value vs g (k) For the global optimal solution Qj best Make a substitution; If vs g (k) <Qj best , then use the updated value vs g (k) Replace Qj best ; If vs g (k)≥Qj best , then keep Qj best and remove vs g (k); S56, generate random weight ω through the random generator, and according to the individual optimal solution Gpbes t and the global optimal solution Qj best Calculate the iteration speed Vd k+1 ; S57, according to the iteration speed Vd k+1 Calculate the iteration position Xd k+1 , the calculation formula is: Xd k+1 =Xd k +Vd k+1 Among them, Xd k+1 Indicates the k+1th iteration position; S58. Calculate the number of iterations Ac according to the group size N and the data dimension W. The calculation formula is: Among them, Ac represents the number of c-th iterations; S59, judging whether the iteration is terminated according to the number of iterations Ac; If k+1=Ac, the iteration is terminated and the iteration speed Vd is k+1 As the forward speed Vq s ; If k + 1 < Ac, return to step S56 to calculate the iteration speed Vd k+1 as the previous generation speed Vd k for calculation.

8. The data analysis method according to claim 7, characterized in that: The iteration speed Vd k+1 The calculation formula is: Vd k+1 =ωVd k +C1S1(Gp best -Xd k )+C2S2(Qj best -Xd k ) Among them, Vd k represents the kth previous generation speed, C1 and C2 represent learning coefficients, S1 and S2 represent random numbers between 0 and 1, and Xd k represents the kth predecessor position.

9. The data analysis method according to claim 1, characterized in that: In step S6, the specific implementation steps are as follows: S61. Obtaining the flutter force Fz k 、Overall moment of inertia Z t , variable control function Xf u ', forward speed Vq s The number of data are P, Q, S and T respectively, and the weight coefficients α, β, γ and δ are calculated using the following formula: Where α, β, γ and δ represent the flutter force Fz respectively. k 、Overall moment of inertia Z t , variable control function Xf u ', forward speed Vq s The corresponding weight coefficient; S62, calculate the analysis value Gf according to the weight coefficients α, β, γ and δ v , the calculation formula is: Among them, Gf v represents the vth analysis value; S63, according to the analysis value Gf v Calculate the fluctuation value B d , the calculation formula is: in, Indicates multiple analysis values ​​Gf v The number of V represents the analytical value Gf v and The number of groups; S64, according to the fluctuation value B d Analyze the work of the drilling rig and obtain the analysis results; like The drilling rig works normally and generates normal analysis results; like The drilling rig is operating abnormally and generates abnormal analysis results.

Images