Drilling machine lifting system digitization method, device and equipment based on digital twinning and medium

Abstract

The invention discloses a digital twinning-based drilling machine lifting system digitization method, device and equipment and a medium, and relates to the technical field of engineering machinery, and the digital twinning-based drilling machine lifting system digitization method comprises the steps of constructing a digital twinning model of a target drilling machine lifting system; virtual-real mapping of the digital twin model is carried out according to the equipment information data; determining simulation data of the digital twinborn model based on the real-time monitoring data, and simulating the digital twinborn model to quantify the model precision of the digital twinborn model so as to obtain an initial digital twinborn model; and performing joint simulation by using a preset technological process identification model and the initial digital twinborn model, and making corresponding automatic updating strategies for different technological processes so as to perform dynamic updating according to the automatic updating strategies, and performing evaluation verification on the initial digital twinborn model to obtain a target digital twinborn model. Therefore, digital twinborn modeling can be carried out on the drilling machine lifting system so as to realize optimization management on the drilling machine lifting system based on the digital twinborn model.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering machinery, and in particular to a method, device, equipment and medium for digitizing a drilling rig hoisting system based on digital twins. Background Art

[0002] As a key subsystem of drilling rig equipment, the lifting system is responsible for lifting and lowering drill tools, casing strings, feeding drill tools, and controlling drilling pressure. Once the drilling rig lifting system fails, the overall drilling work may be suspended, resulting in huge economic losses. Therefore, the stability and safety of the drilling rig lifting system determines the working performance of the entire drilling rig. At present, most of the digital twin methods for drilling rig lifting systems are concentrated on the system construction level. However, due to the complexity of the current drilling rig lifting system and its characteristics in the working process, it is difficult to accurately describe the dynamic characteristics and internal mechanisms of the drilling rig lifting system through a simple mathematical model, and it is impossible to achieve comprehensive analysis, maintenance and full life cycle management of the drilling rig lifting system performance from multiple dimensions such as structure, components, and functions.

[0003] In summary, how to conduct digital twin modeling of the drilling rig hoisting system to achieve optimized management of the drilling rig hoisting system based on the digital twin model is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for digitizing a drilling rig hoisting system based on digital twin, which can perform digital twin modeling on the drilling rig hoisting system to achieve optimized management of the drilling rig hoisting system based on the digital twin model. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a method for digitizing a drilling rig hoisting system based on digital twin, comprising:

[0006] Constructing a digital twin model of the target drilling rig lifting system using a preset modeling method; the digital twin model includes a mechanism model, a data model, and a knowledge model;

[0007] Acquire device information data and real-time monitoring data of physical equipment in the target drilling rig lifting system according to a preset data acquisition strategy, and perform virtual-real mapping of the digital twin model according to the device information data;

[0008] After the virtual-real mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, and the digital twin model is simulated based on the simulation data, so as to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain an initial digital twin model whose model accuracy meets the preset accuracy condition;

[0009] A preset process identification model is used to perform joint simulation with the initial digital twin model, and based on the simulation results obtained under different process conditions, corresponding automatic update strategies for the initial digital twin models are formulated for the different process conditions, so that the initial digital twin model can be dynamically updated according to the automatic update strategies, and the initial digital twin model is evaluated and verified based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets preset performance conditions; the process identification model is a model established based on a preset hybrid automaton.

[0010] Optionally, the method of constructing a digital twin model of a target drilling rig hoisting system by using a preset modeling method includes:

[0011] Analyze the structural composition, motion characteristics and structural features of the target drilling rig hoisting system to determine the subsystem set, structural characteristics and operating parameters of the target drilling rig hoisting system, and determine the modeling requirement information and system data information of the target drilling rig hoisting system;

[0012] Determine the coupling information between the subsystems in the subsystem set according to the structural characteristics and the subsystem set, and construct the mechanism model in the digital twin model based on the subsystem set, the coupling information and the operating parameters;

[0013] Preprocessing the pre-collected data related to the operating parameters to obtain processed data, and constructing the data model in the digital twin model based on the modeling requirement information and the processed data through a preset learning model;

[0014] The system data information is mined based on a preset machine learning algorithm to construct the knowledge model in the digital twin model.

[0015] Optionally, performing virtual-reality mapping of the digital twin model according to the device information data includes:

[0016] Preprocessing the equipment information data, and performing theoretical analysis and experimental testing on the target drilling rig lifting system based on the processed equipment information data to determine component parameters in the digital twin model;

[0017] The component parameters and the device information data interact through a preset interface to obtain the digital twin model that is consistent with the actual performance.

[0018] Optionally, before the combined simulation using the preset process identification model and the initial digital twin model, the method further includes:

[0019] Divide the different process steps of the target drilling rig lifting system into a preset number of continuous state spaces, and establish a system variable parameter set using the real-time monitoring data and the simulation data;

[0020] According to the actual situation of the target drilling rig lifting system, the initial state space of the process identification model is set, and the migration conditions between the state spaces are determined; the state spaces include the continuous state space and the initial state space;

[0021] The preset hybrid automaton is established based on the migration condition, the system variable parameter set and the state spaces, and the structure of the preset hybrid automaton is layered to obtain the process identification model.

[0022] Optionally, the method of using a preset process identification model to jointly simulate the initial digital twin model, and formulating corresponding automatic update strategies of the initial digital twin model for the different process based on the obtained simulation results under different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategy, includes:

[0023] Using the real-time monitoring data to drive a preset process identification model to identify the process of the current target drilling rig lifting system, obtain relevant information of the current process, and determine the input value of the initial digital twin model according to the relevant information;

[0024] The initial digital twin model is driven based on the input value to set the trigger condition for automatic update of the current process according to the obtained output result and the change trend of the real-time monitoring data, so that when the prediction error of the initial digital twin model or the change trend of the equipment parameter meets the trigger condition, or when the process changes, the initial digital twin model is updated using a preset update method.

[0025] Optionally, the updating of the initial digital twin model by using a preset updating method includes:

[0026] Determine the uncertainty parameters and experimental data corresponding to the current process according to the relevant information;

[0027] The uncertainty parameters and the experimental data are updated using Bayesian inference and variational inference, so as to update the initial digital twin model in combination with the real-time monitoring data.

[0028] Optionally, the evaluating and verifying the initial digital twin model based on preset model indicators includes:

[0029] Evaluate and verify the real-time performance, dynamic response and scalability of the initial digital twin model;

[0030] Determining an error tolerance range according to the current process of the target drilling rig lifting system;

[0031] Analyzing the parameters in the initial digital twin model to determine parameter characteristics corresponding to each of the parameters;

[0032] Determine respective error analysis methods according to the parameter characteristics, and use the error analysis methods to perform error analysis on the corresponding parameters, so as to evaluate and verify the accuracy of the initial digital twin model based on the allowable error range.

[0033] In a second aspect, the present application provides a digital device for a drilling rig hoisting system based on digital twin, comprising:

[0034] A model building module, used to build a digital twin model of the target drilling rig lifting system using a preset modeling method; the digital twin model includes a mechanism model, a data model and a knowledge model;

[0035] A virtual-to-real mapping module, used to obtain device information data and real-time monitoring data of physical equipment in the target drilling rig lifting system according to a preset data acquisition strategy, and perform virtual-to-real mapping of the digital twin model according to the device information data;

[0036] A model simulation module, used to determine the simulation data of the digital twin model based on the real-time monitoring data after the virtual-real mapping is completed, and simulate the digital twin model based on the simulation data, so as to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain an initial digital twin model whose model accuracy meets the preset accuracy condition;

[0037] A strategy formulation module is used to use a preset process identification model to jointly simulate the initial digital twin model, and based on the simulation results obtained under different process conditions, formulate corresponding automatic update strategies for the initial digital twin model for the different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets preset performance conditions; the process identification model is a model established based on a preset hybrid automaton.

[0038] In a third aspect, the present application provides an electronic device, including:

[0039] Memory, used to store computer programs;

[0040] A processor is used to execute the computer program to implement the aforementioned digital twin-based drilling rig hoisting system digitization method.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned digital twin-based drilling rig hoisting system digitization method is implemented.

[0042] In this embodiment, a digital twin model of the target drilling rig lifting system is constructed using a preset modeling method; the digital twin model includes a mechanism model, a data model, and a knowledge model; the equipment information data and real-time monitoring data of the physical equipment in the target drilling rig lifting system are obtained according to a preset data acquisition strategy, and virtual-to-real mapping of the digital twin model is performed according to the equipment information data; after the virtual-to-real mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, and the digital twin model is simulated based on the simulation data, so as to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain the obtained An initial digital twin model whose model accuracy meets preset accuracy conditions; a preset process identification model is used to jointly simulate the initial digital twin model, and based on the simulation results obtained under different process conditions, corresponding automatic update strategies for the initial digital twin model are formulated for the different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets preset performance conditions; the process identification model is a model established based on a preset hybrid automaton. As can be seen from the above, the present application first uses a preset modeling method to construct a digital twin model of the target drilling rig lifting system, and performs virtual-real mapping of the digital twin model according to a preset data acquisition strategy. After the virtual-real mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, so as to simulate the digital twin model based on the simulation data, and obtain the initial digital twin model by quantifying the model accuracy. The preset process identification model is used to perform joint simulation with the initial digital twin model, and a corresponding automatic update strategy is formulated based on the obtained simulation results, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on the preset model indicators to obtain the target digital twin model. In this way, through the above process of the present application, the digitization of the drilling rig lifting system is realized based on the digital twin technology, and the model is updated according to the process conditions, and then the drilling rig lifting system is digitally modeled to achieve the optimization management of the drilling rig lifting system based on the digital twin model. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0044] Figure 1 A flowchart of a digital method for a drilling rig hoisting system based on digital twin disclosed in this application;

[0045] Figure 2 A schematic diagram of a digital twin coupling model disclosed in this application;

[0046] Figure 3 A flowchart of a specific method for digitizing a drilling rig hoisting system based on digital twins disclosed in this application;

[0047] Figure 4 A schematic diagram of comparison of the displacement of a large hook during a tripping process disclosed in the present application;

[0048] Figure 5 This is a schematic diagram of the absolute error of the displacement of a large hook during a tripping process disclosed in the present application;

[0049] Figure 6 This is a structural schematic diagram of a digital device for a drilling rig lifting system based on digital twinning disclosed in this application;

[0050] Figure 7 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] At present, most digital twin methods for drilling rig hoisting systems are focused on the system construction level. However, due to the complexity of the current drilling rig hoisting system and its characteristics in the working process, it is difficult to accurately describe the dynamic characteristics and internal mechanisms of the drilling rig hoisting system through a simple mathematical model, and it is impossible to achieve comprehensive analysis, maintenance and full life cycle management of the drilling rig hoisting system performance from multiple dimensions such as structure, components and functions.

[0053] In order to overcome the above technical problems, the present application provides a digital twin-based drilling rig hoisting system digitization method to perform digital twin modeling on the drilling rig hoisting system to achieve optimized management of the drilling rig hoisting system based on the digital twin model.

[0054] See also Figure 1 As shown, an embodiment of the present invention discloses a digital method for a drilling rig hoisting system based on digital twin, comprising:

[0055] Step S11, using a preset modeling method to construct a digital twin model of the target drilling rig lifting system; the digital twin model includes a mechanism model, a data model and a knowledge model.

[0056] In this embodiment, a corresponding digital twin model is constructed for the target drilling rig hoisting system according to a preset modeling method. The digital twin model includes a mechanism model, a data model, and a knowledge model; the data model includes but is not limited to equipment physical data, operation data, virtual data, etc., and is a model that supports multiple functions such as equipment status monitoring, fault diagnosis, and performance prediction; the knowledge model is a model that supports decision support, fault diagnosis and prediction, engineering optimization, and other functions of the drilling rig hoisting system.

[0057] Specifically, this embodiment first analyzes the structural composition, motion characteristics and structural features of the target drilling rig lifting system to determine the subsystem set, structural characteristics and operating parameters of the target drilling rig lifting system, and determines the modeling requirement information and system data information of the target drilling rig lifting system. Among them, the operating parameters include but are not limited to the main operating parameters such as motor parameters, transmission ratio, brake braking force, winch torque, hook running speed, as well as motor model, disc brake model, hydraulic system rated flow, pump inlet / outlet pressure, power and other parameters; the subsystem set includes but is not limited to the electrical system formed by the motor, the transmission system formed by the gearbox and winch, the hydraulic brake system formed by the motor, plunger pump, hydraulic cylinder, disc brake and other equipment, the traveling block-drilling block system formed by the crown block pulley block, traveling block pulley block, big hook, drill string and other drilling tools, etc.; the modeling requirement information refers to the target and scope of modeling, including the expected performance indicators, use environment and restrictions; the system data information includes but is not limited to sensor network, operation log, maintenance record and historical operation data, etc. That is, the structural composition of the target drilling rig lifting system is analyzed to clarify the equipment characteristics and main components of the target drilling rig lifting system according to the on-site working conditions of the drilling rig, analyze the parts and assembly forms that can be simplified in modeling, and determine the structural characteristics of the target drilling rig lifting system to reduce the difficulty of subsequent modeling; the motion characteristics of the target drilling rig lifting system are analyzed to determine the operating parameters of the target drilling rig lifting system; the structural characteristics of the target drilling rig lifting system are analyzed to determine the composition of each subsystem in the digital twin model of the target drilling rig lifting system, that is, the subsystem set, so as to explore the coupling effect between the subsystems and provide ideas for subsequent modeling; at the same time, the modeling requirement information and system data information of the target drilling rig lifting system are determined.

[0058] Subsequently, this embodiment determines the coupling information between each subsystem in the subsystem set according to the structural characteristics and the subsystem set, and constructs the mechanism model in the digital twin model based on the subsystem set, the coupling information and the operating parameters. Wherein, the coupling information includes but is not limited to coupling mode, coupling effect, etc. That is, in view of the characteristics of the internal equipment cooperation of the target drilling rig lifting system involving complex mechanical linkage and multidisciplinary collaborative work, when constructing the mechanism model, firstly, according to the structural characteristics and the subsystem set, the interaction between multiple physical fields in the system is analyzed to determine the direct coupling or indirect coupling form between multiple physical fields, that is, the coupling information between each subsystem in the subsystem set, and the mechanism model is constructed from the fields of mechanics, temperature, fluid, electrical, control, etc. based on the subsystem set, the coupling information and the operating parameters. Wherein, the physical fields include but are not limited to mechanical fields, temperature fields, fluid fields, and electromagnetic fields. At the same time, this embodiment preprocesses the pre-collected data related to the operating parameters to obtain processed data, and constructs the data model in the digital twin model based on the modeling requirement information and the processed data through a preset learning model; and mines the system data information based on a preset machine learning algorithm to construct the knowledge model in the digital twin model. Among them, the preset learning model can be a machine learning model or a deep learning model. That is, the data related to the operating parameters collected in advance from actual applications are preprocessed to obtain processed data, and according to the specific application scenario, the data model is constructed based on the modeling requirement information and the processed data through a preset learning model, and the existing system data information is mined using a preset machine learning algorithm to construct the knowledge model.

[0059] It should be pointed out that the modeling of the mechanism model includes but is not limited to the motor electrical model modeling, hydraulic disc brake electro-hydraulic coupling modeling, drilling rig geometric model modeling, drilling rig lifting system kinematic modeling, drilling rig lifting system dynamic modeling, etc. Among them, the motor electrical model modeling is used to obtain motor performance data, motor operating status, motor output information, etc.; the hydraulic disc brake electro-hydraulic coupling modeling is used to obtain the hydraulic system status, the current state of the brake, etc.; the drilling rig geometric model modeling is used to obtain the size, shape, structure, assembly and other information of the drilling rig components to obtain a mirror model of the actual physical equipment; the drilling rig lifting system kinematic modeling is used to obtain the interaction relationship and kinematic equations between the internal devices of the system; the drilling rig lifting system dynamic modeling is used to obtain the force size and direction of each device in the system, and calculate the energy loss, power demand and efficiency of the system. Therefore, after determining the coupling information, the present embodiment can build the mechanism model of each subsystem in the Simscape environment (a tool for modeling and simulating multi-domain physical systems), and then connect the subsystem models according to the mutual relationship, coupling mode and coupling mechanism between the subsystems to establish the multi-domain coupling model of the target drilling rig lifting system, that is, the mechanism model. In this way, when modeling the target drilling rig lifting system, the present embodiment first determines the relevant data information required for modeling to reduce the difficulty of subsequent modeling and provide ideas for subsequent modeling. At the same time, the digital twin model is divided into three parts: the mechanism model, the data model and the knowledge model to ensure that the digital twin model obtained by modeling is consistent with the target drilling rig lifting system.

[0060] Step S12: acquiring equipment information data and real-time monitoring data of physical equipment in the target drilling rig lifting system according to a preset data acquisition strategy, and performing virtual-reality mapping of the digital twin model according to the equipment information data.

[0061] In this embodiment, the preset data acquisition strategy is used to obtain the equipment information data and real-time monitoring data of the physical equipment in the target drilling rig lifting system, and the virtual-real mapping of the digital twin model is performed according to the equipment information data. Among them, the equipment information data includes the relevant parameter information and status information of each physical entity equipment in the drilling rig lifting system, and the relevant parameter information includes the physical, geometric, and performance parameter information of the key equipment in the drilling rig lifting system; the virtual-real mapping includes three aspects: data mapping within the digital twin model, data mapping between different digital twin models, and data mapping between the digital twin model and the physical entity.

[0062] It should be pointed out that before obtaining the device information data and the real-time monitoring data, the present embodiment needs to determine the data acquisition strategy first. Specifically, it can be selected according to the actual data acquisition needs and the field environment, specifically considering factors such as transmission distance, delay, energy consumption, sampling rate, etc. In addition, in order to realize the virtual-real mapping of the digital twin model, the present embodiment can determine the main data transmission scheme according to the communication needs and the mechanism that data transmission depends on the transmission protocol, access method, multi-access scheme, channel multi-channel modulation and coding, and multi-user detection technology, establish the interaction and integration strategy between data and the digital twin model, and realize data mapping and data fusion, that is, the interaction and mapping between the digital twin model and the actual data. Specifically, for the communication between the digital twin models, the interaction can be realized through standardized interfaces between the visualization tools and the simulation models; for the communication between different digital twin models, it can be realized through information sharing and data transmission between the corresponding physical entities; for the communication between the digital twin and the corresponding physical entity, it can be realized through sensor data and status data, remote control, software update, etc. Among them, the different digital twin models refer to the mechanism models corresponding to each subsystem in the digital twin model.

[0063] It should be noted that the processing flow of the virtual-real mapping of the digital twin model based on the device information data is as follows: preprocessing the device information data, and conducting theoretical analysis and experimental testing on the target drilling rig lifting system based on the processed device information data to determine the component parameters in the digital twin model; interacting between the component parameters and the device information data through a preset interface to obtain the digital twin model consistent with the actual performance. Among them, the preprocessing includes but is not limited to processing missing data values, removing or correcting erroneous data points, removing duplicate data records, standardizing and normalizing data, etc. That is, considering that the data collected at the drilling rig operation site is rich in information, and is affected by uncontrollable factors such as the limitations of sensing methods and the harshness of some working environments, data anomalies are inevitable. This embodiment requires necessary preprocessing of the collected equipment information data, and then theoretical analysis and experimental testing of the target drilling rig lifting system are performed based on the relevant parameter information in the processed equipment information data to determine the component parameters in the model, and the component parameters are interacted with the equipment information data through a preset interface to obtain the digital twin model consistent with the actual performance. Specifically, this embodiment can construct an electrical subsystem that is consistent with the performance of the on-site motor in the Simscape environment of Simulink (a tool for modeling and simulating multi-domain physical systems) according to the motor model, voltage, current, torque, speed and other parameters used on-site; construct a transmission subsystem that is consistent with the performance of the on-site transmission system in the Simscape environment of Simulink according to the main transmission mode, transmission ratio, physical properties of the transmission equipment and other parameters of the on-site transmission system; construct a hydraulic brake subsystem that is consistent with the internal parameters and braking effect of the on-site hydraulic brake system in the Simscape environment of Simulink according to the model, drive system, pump inlet / outlet pressure, flow and other parameters of the hydraulic disc brake used on-site; construct a traveling block-drill string system that is consistent with the performance of the on-site equipment in the Simscape environment of Simulink according to the physical properties of the pulley block, the parameters of the big hook, the physical properties of the drill string and other parameters collected on-site, so as to form the digital twin model. Figure 2 The figure shows a schematic diagram of a digital twin coupling model provided by the present application. In this way, the present embodiment realizes the virtual-real mapping of the digital twin model through three aspects to obtain a digital twin model consistent with the on-site performance, simulating the scene of the target drilling rig lifting system to the maximum extent.

[0064] Step S13: After the virtual-reality mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, and the digital twin model is simulated based on the simulation data to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain an initial digital twin model whose model accuracy meets the preset accuracy conditions.

[0065] In this embodiment, after completing the virtual-reality mapping, the simulation data of the digital twin model is determined based on the real-time monitoring data, so as to simulate the digital twin model based on the simulation data, and the model accuracy of the digital twin model is quantified according to the obtained simulation effect, so as to obtain an initial digital twin model whose model accuracy meets the preset accuracy conditions.

[0066] Specifically, considering that the performance parameters of the drilling rig lifting system are affected by many factors during the actual operation, before the subsequent update work is carried out, this embodiment needs to first make a preliminary and reasonable assignment of the physical parameters that are difficult to determine in the digital twin model based on the real-time monitoring data to supplement the physical parameters missing in the digital twin model, and then determine the main simulation data of the digital twin model based on the real-time monitoring data, and perform a full life cycle simulation of the constructed digital twin model based on the simulation data. After completing the simulation, the key performance indicators for evaluating the performance are selected based on the application requirements of the drilling rig lifting performance, and then the accuracy of the model is quantified using methods such as mean square error or root mean square error to verify the effectiveness of the model. Among them, the physical parameters include but are not limited to stiffness, inertia, damping, etc. inside the mechanical subsystem; fluid properties and flow characteristics inside the hydraulic subsystem. It can be understood that after quantifying the model accuracy of the digital twin model, this embodiment can compare the model accuracy with the preset accuracy condition. If the model accuracy meets the preset accuracy condition, the current digital twin model is the initial digital twin model; if the model accuracy does not meet the preset accuracy condition, the current digital twin model needs to be optimized until the model accuracy of the obtained digital twin model meets the preset accuracy condition. In this way, after completing the virtual-real mapping, this embodiment quantifies the model accuracy by simulating the digital twin model to ensure that the obtained initial digital twin model meets the preset accuracy condition and improves the effectiveness of the established digital twin model.

[0067] Step S14: Use the preset process identification model to jointly simulate the initial digital twin model, and based on the simulation results obtained under different process conditions, formulate corresponding automatic update strategies for the initial digital twin model for the different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets preset performance conditions; the process identification model is a model established based on a preset hybrid automaton.

[0068] In this embodiment, a joint simulation is performed based on a preset process identification model and the initial digital twin model to obtain simulation results under different process conditions, and based on the simulation results, corresponding model automation update strategies are formulated for different process conditions, so that the initial digital twin model is dynamically updated according to the automation update strategy, and the initial digital twin model is evaluated and verified based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets the preset performance conditions. Among them, the process identification model is a model established based on a preset hybrid automaton.

[0069] It can be understood that before performing the joint simulation, this embodiment needs to first establish the process identification model, and its processing flow is as follows: the different process of the target drilling rig lifting system is divided into a preset number of continuous state spaces, and the real-time monitoring data and the simulation data are used to establish a system variable parameter set; the initial state space of the process identification model is set according to the actual situation of the target drilling rig lifting system, and the migration conditions between each state space are determined; each state space includes the continuous state space and the initial state space; based on the migration conditions, the system variable parameter set and the each state space, the preset hybrid automaton is established, and the structure of the preset hybrid automaton is layered to obtain the process identification model. The process includes but is not limited to top drive rising (without clamping drill tools), bottom connection of drill pipe and buckling of top drive center pipe and drill pipe joint, top drive rotary drilling (clamping drill tools) and buckling of top drive center pipe and drill pipe; the system variable parameter set includes but is not limited to motor current, voltage, speed, torque, winding temperature, drive end bearing temperature, fan current, lubricating oil pump current, brake oil pump current, gearbox vibration, bearing seat vibration, pump inlet / outlet flow, inlet / outlet pressure, winch speed, torque, hook displacement, speed, acceleration, top drive speed, hanging card Boolean signal, buckle Boolean signal, Kava Boolean signal, BOP Boolean signal, mud pump Boolean signal, theoretical time of drilling rig lifting, theoretical time of drilling rig connecting a single root, theoretical time of drilling rig drilling, theoretical time of drilling rig unbuckling, bottom hole temperature, drilling pressure, drilling depth, number of drill strings, field environmental parameters, drilling geological information, field communication information, etc.; the initial state space mainly includes the state of the top drive rising without clamping the drill bit when the system is just started; the migration condition is mainly composed of multiple related parameters that are significantly affected by changes in the drilling rig working conditions, including but not limited to motor speed, top drive speed, vertical distance of top drive rising and lowering, bottom hole drilling pressure, time parameters, etc. That is, in this embodiment, the different process of the target drilling rig lifting system is divided into several continuous state spaces, and then the real-time monitoring data and the simulation data are used to establish a system variable parameter set, and the initial state space of the process identification model is set according to the actual situation of the target drilling rig lifting system, and the migration conditions between the state spaces are clarified. Finally, during the drilling process, the different state spaces of the drilling rig lifting system are regarded as a discrete dynamic system, and the preset hybrid automaton is established based on the migration conditions, the system variable parameter set and the state spaces. The expression formula is as follows:

[0070] ;

[0071] in, Represents a finite set of state variables, including discrete states and continuous state ; is a finite set of input variables, including discrete input and continuous input ; is the initial state set, ; represents a mapping that describes the continuous evolution in discrete states, ; represents an invariant set, and ; Represents reset relationship, describes discrete transition, . That is, the continuous dynamic process under discrete events is described in the form of differential equations and difference equations, and the switching of discrete events will cause discontinuous jumps of continuous states. Similarly, corresponding to each discrete state, the continuous process of the object satisfies certain invariant set conditions. If the continuous evolution of the object causes the state to exceed this invariant set condition, it will also cause the switching of discrete events. Subsequently, considering the evolution process of the drilling rig lifting system on the continuous time axis, this embodiment, based on the modeling of the preset hybrid automaton, transforms the structure of the preset hybrid automaton through a parallel projection structure, effectively layers the structure of the preset hybrid automaton, and establishes a generalized automaton model to obtain the process identification model. In the model, the continuous dynamic behavior of the system only affects the numerical value of the local state, and the discrete dynamic behavior of the system will affect the state value of the entire system. Among them, the expression formula of the generalized automaton model is as follows:

[0072] ;

[0073] in, Represents a collection of system variables; Represents a finite set of continuous spatial states; A finite set representing the initial values ​​of the variables and the initial state space; Represents a finite set of discrete event transitions; Represents the final space set. It should be noted that the system variable set ,in Represents discrete event variables in different operation processes, mainly motor output speed, motor output torque, hook displacement, make-up and break-out time parameters, etc.; finite set of continuous space states Represents the established state spaces, including top drive rising (without clamping drill bit), bottom of drill pipe combined and top drive center pipe and drill pipe joint buckling, top drive rotary drilling (clamping drill bit) and top drive center pipe and drill pipe buckling; the initial values ​​of variables and the finite set of initial state spaces represents the initial value of the system variable parameter in the initial state space. Here, the initial state space defaults to the system just started, the top drive rises (without clamping the drill bit); the finite set of discrete event transitions It is used to describe the migration conditions between various state spaces. The parameters involved in the migration conditions mainly include hook displacement, time parameters, bottom drilling pressure, equipment Boolean parameters, etc. The final space collection Including but not limited to the load capacity of the drilling rig hook, the number of drill rods, etc.

[0074] It should be noted that the purpose of using the process identification model and the initial digital twin model for joint simulation is to simulate the initial digital twin model according to the identified process mode while performing real-time process identification of the system through the process identification model, and to formulate a corresponding automatic update strategy. Therefore, the processing flow of formulating the automatic update strategy through joint simulation is as follows: using the real-time monitoring data to drive the preset process identification model to identify the process of the current target drilling rig lifting system, obtain relevant information of the current process, and determine the input value of the initial digital twin model according to the relevant information; based on the input value, drive the initial digital twin model to set the trigger condition of the automatic update of the current process according to the output result obtained and the change trend of the real-time monitoring data, so that when the prediction error of the initial digital twin model or the change trend of the equipment parameter meets the trigger condition, or when the process changes, the initial digital twin model is updated using the preset update method. Among them, the relevant information includes the corresponding working condition of the current state space, the current operating state of the equipment, the current operating parameters of the equipment, the bottom hole state and the field information; the relevant information is the selected demand parameter. That is, the preset process identification model is driven by the real-time monitoring data, and the state space conversion is promoted when the migration condition of the model is met, and the variable update of the field monitoring data part in the system variable set is performed to identify the process of the current target drilling rig lifting system, obtain the relevant information of the current process, obtain the information change of the system under different process based on the relevant information, determine the input value of the initial digital twin model, and drive the knowledge model in the initial digital twin model to run, and make decision suggestions for the relevant data and threshold setting in different state spaces within the working condition identification model according to the output result of the knowledge model and the change trend of the real-time monitoring data, so as to set the threshold, alarm and set the current working condition operation recommended value for the relevant data in different state spaces within the process identification model. It can be understood that, since the parameters of different process designs are different, this embodiment formulates its corresponding automatic update strategy according to the identified process, that is, there are different update strategies for different process, so as to trigger the update condition when the process changes. In addition, when the prediction error is too large, or the change trend of the equipment parameters is inconsistent, the update condition will be triggered to adjust the parameters of the model.

[0075] It should be further explained that, considering the influence of the state of the internal equipment of the drilling rig lifting system under different working conditions and the use of uncertain parameters in modeling, the simulation results and the actual operation results have certain errors. At the same time, in different working conditions, the key parameters involved in the update of the digital twin model are also different. In order to ensure the response consistency between the twin model and the physical entity, the automatic update strategy for different state spaces mainly includes calculating the model prediction error, evaluating the performance of the digital twin model under the current working conditions, and setting the trigger conditions for model self-update according to the size of the prediction error or the change trend of the key parameters of the equipment. Specifically, this embodiment can set the trigger conditions for model self-update according to the size of the prediction error or the change trend of the key parameters of the equipment. Calculate the absolute difference, relative difference or more advanced statistical indicators between the predicted value and the actual value, and realize the adaptive update of the model through machine learning and other methods. It can be understood that this embodiment can also formulate a manual optimization strategy for the characteristics that the non-sensitive parameters inside the model are difficult to monitor and estimate, including defining a reasonable value range for non-sensitive parameters, iterative optimization, combined optimization, etc.

[0076] It should be pointed out that the processing flow for dynamically updating the initial digital twin model according to the automatic update strategy is as follows: determine the uncertainty parameters and experimental data corresponding to the current process according to the relevant information; use Bayesian inference and variational inference to update the uncertainty parameters and the experimental data, so as to update the initial digital twin model in combination with the real-time monitoring data. That is, determine the uncertainty parameters and experimental data corresponding to the current process according to the relevant information, and use Bayesian inference and variational inference to update the uncertainty parameters and the experimental data, so as to update the initial digital twin model in combination with the real-time monitoring data. Specifically, in this embodiment, the uncertainty parameters θ to be updated and the experimental data x can be regarded as random variables, and it is assumed that The prior distribution of , then the expression formula of the Bayesian inference can be as follows:

[0077] ;

[0078] in, is the posterior distribution of parameter θ, that is, the posterior probability density distribution, indicating that when the data is known, the parameter Probability distribution of different values; is the likelihood function, which means that when the parameter value is The data was observed under probability; For parameters The prior distribution of is the same as the prior probability density distribution; is the marginal likelihood function, which means that under all parameter values, the observed data The probability can also be obtained by integrating the likelihood function over all possible parameter values, so the expression formula of the Bayesian inference can also be as follows:

[0079] ;

[0080] in, Then, the posterior distribution Approximately the simpler , the goal of variational inference is to find the variational parameters , so that the posterior distribution Closest to the true posterior distribution Therefore, in this embodiment, the KL divergence can be used in the variational inference to quantify the mismatch between the two distributions. The expression formula of the KL divergence can be as follows:

[0081] ;

[0082] in, represents the expectation of the logarithmic function in the brackets. After expanding and simplifying the expectation, we can get:

[0083] ;

[0084] The left side of the equation is a constant. Let:

[0085] ;

[0086] in, for The joint distribution of , after conversion, transforms the problem of solving the minimum KL divergence into the problem of solving the ELBO maximum value, avoiding the encounter of the posterior distribution probability in the process of solving the approximate problem.

[0087] Assume that the real-time status data of the physical entity is , the simulation data of the digital twin model is , then the status data Simulation data with digital twin models The relationship between them is:

[0088] ;

[0089] in, is the m-dimensional vector of error. The causes of error include environmental factors, parameter changes, state degradation, etc. Then the expression formula of the likelihood function can be:

[0090] ;

[0091] in, are the mean and standard deviation of the errors respectively. Prior distributions are selected for many physical parameters in the twin model. According to the experience of changes in various physical parameters, most of them show a continuous change process of gradually increasing or decreasing. Therefore, Beta distribution is selected to describe this change process. The expression formula of Beta distribution is as follows:

[0092] ;

[0093] in, is the parameter to be updated, All of them are parameters greater than 0. According to the prior parameter change data, we can calculate Therefore, The calculation formula is as follows:

[0094] ;

[0095] in, is the parameter mean, is the parameter standard deviation. By combining the various equations, we can get:

[0096] ;

[0097] ;

[0098] Therefore, the objective function can be defined as:

[0099] ;

[0100] This embodiment converts the problem of solving the posterior distribution into the problem of solving the ELBO maximum value. According to the real-time status data and the parameter prior distribution, the parameter posterior distribution can be calculated, thereby completing a parameter update. In combination with multiple real-time status data, the digital twin model can be updated. In this way, this embodiment first uses real-time monitoring data to drive the preset process identification model, accurately identify the current working condition of the drilling rig lifting system, explore the form of equipment status changes under different working conditions, and facilitate the guidance of subsequent work. A manual tuning and dynamic feedback mechanism is established, and a suitable machine learning algorithm is selected for digital twin updates to achieve real-time virtual mapping of the drilling rig lifting system.

[0101] As can be seen from the above, the embodiment of the present application first uses a preset modeling method to construct a digital twin model of the target drilling rig lifting system, and performs virtual-to-real mapping of the digital twin model according to a preset data acquisition strategy. After the virtual-to-real mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, so as to simulate the digital twin model based on the simulation data, and obtain the initial digital twin model by quantifying the model accuracy. The preset process identification model is used to perform joint simulation with the initial digital twin model, and a corresponding automatic update strategy is formulated based on the obtained simulation results, so as to dynamically update the initial digital twin model according to the automatic update strategy, and the initial digital twin model is evaluated and verified based on the preset model indicators to obtain the target digital twin model. In this way, through the above process of the embodiment of the present application, on the one hand, when modeling the target drilling rig lifting system, the relevant data information required for modeling is first determined to reduce the difficulty of subsequent modeling and provide ideas for subsequent modeling; on the one hand, the digital twin model is divided into three parts: mechanism model, data model and knowledge model to ensure that the digital twin model obtained by modeling is consistent with the target drilling rig lifting system; on the one hand, the virtual-real mapping of the digital twin model is realized through three aspects to obtain a digital twin model consistent with the on-site performance, simulating the scenario of the target drilling rig lifting system to the maximum extent; on the one hand, after completing the virtual-real mapping, through The digital twin model is simulated to quantify the model accuracy to ensure that the initial digital twin model meets the preset accuracy conditions and improve the effectiveness of the established digital twin model. On the one hand, real-time monitoring data is used to drive the preset process identification model to accurately identify the current working condition of the drilling rig lifting system and explore the change form of equipment status under different working conditions to guide the subsequent work. On the other hand, the digital twin technology is used to realize the digitization of the drilling rig lifting system, and the model is updated according to the process conditions, and then the digital twin modeling of the drilling rig lifting system is carried out to realize the optimization management of the drilling rig lifting system based on the digital twin model.

[0102] Based on the above embodiments, it can be seen that through the method of the present application, when the initial digital twin model is evaluated and verified based on the preset model indicators, the initial digital twin model can be evaluated and verified comprehensively from multiple aspects to maximize the simulation of the scenario of the target drilling rig lifting system. For this reason, this embodiment describes in detail how to evaluate and verify the initial digital twin model. Figure 3 As shown, an embodiment of the present invention discloses a digital method for a drilling rig hoisting system based on digital twin, comprising:

[0103] Step S21, using a preset modeling method to construct a digital twin model of the target drilling rig lifting system; the digital twin model includes a mechanism model, a data model and a knowledge model.

[0104] Step S22: acquiring equipment information data and real-time monitoring data of physical equipment in the target drilling rig lifting system according to a preset data acquisition strategy, and performing virtual-reality mapping of the digital twin model according to the equipment information data.

[0105] Step S23: After the virtual-reality mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, and the digital twin model is simulated based on the simulation data to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain an initial digital twin model whose model accuracy meets the preset accuracy conditions.

[0106] Step S24, using a preset process identification model and the initial digital twin model to perform joint simulation, and based on the simulation results obtained under different process conditions, formulating corresponding automatic update strategies for the initial digital twin model for the different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategies; the process identification model is a model established based on a preset hybrid automaton.

[0107] Step S25: Evaluate and verify the real-time performance, dynamic response and scalability of the initial digital twin model, and determine the allowable error range based on the current process of the target drilling rig hoisting system.

[0108] In this embodiment, the performance indicators of the real-time, dynamic response and scalability of the initial digital twin model are evaluated and verified, and the error tolerance range is determined according to the current process of the target drilling rig lifting system. It can be understood that in order to improve the above performance indicators of the model, this embodiment can adopt efficient data transmission technology, complex data processing algorithms and high-quality data management strategies, etc., and ensure the real-time performance of the model through the organic combination of various elements; for the dynamic response, it is reflected in an ideal digital twin model that needs to be able to reflect the state changes of the system in real time and provide dynamic feedback. In addition, the dynamic response also involves the adaptive ability of the model. The model can automatically adjust its parameters and predictions according to the changes in real-time data; in addition, due to the characteristics of the drilling rig lifting system involving multiple devices, multiple fields, multiple data and multiple working conditions, the scalability of the digital twin model can be reflected in its flexible architecture design, using modular modeling methods, adding or replacing according to actual needs, ensuring that in the ever-changing environment and needs, it can be continuously expanded and improved on the initial model. In this way, this embodiment verifies and evaluates the performance, responsiveness, and other aspects of the model by calculating the real-time, dynamic response, and scalability indicators of the model, and at the same time adjusts the allowable error range according to different process steps to improve the reference value of the model verification and evaluation.

[0109] Step S26: Analyze the parameters in the initial digital twin model to determine the parameter characteristics corresponding to each of the parameters, and determine the respective error analysis methods according to the parameter characteristics, and use the error analysis method to perform error analysis on the corresponding parameters, so as to evaluate and verify the accuracy of the initial digital twin model based on the allowable error range, and obtain a target digital twin model whose comprehensive performance meets the preset performance conditions.

[0110] In this embodiment, the parameters in the initial digital twin model are first analyzed to determine the parameter characteristics corresponding to each of the parameters, and the corresponding error analysis method is determined according to the parameter characteristics. The error analysis method is used to perform error analysis on the corresponding parameters, so as to evaluate and verify the accuracy of the initial digital twin model based on the error allowable range, and obtain a target digital twin model whose comprehensive performance meets the preset performance conditions. That is, different error analysis methods are selected for different parameter characteristics. Figure 4 The figure shows a schematic diagram of the comparison of the displacement of the big hook during the tripping process provided by the present application. Figure 5 The figure shows a schematic diagram of the absolute error of the displacement of the big hook during the drilling process provided by the present application. For example, in this embodiment, the absolute error can be used to perform error analysis on the more intuitive key parameters in the initial digital twin model, and for some abnormal values ​​in the model that are difficult to analyze errors through simple algorithms, the mean square error is used for error analysis, so as to evaluate and verify the accuracy of the initial digital twin model based on the error allowable range, and obtain a target digital twin model whose comprehensive performance meets the preset performance conditions. Among them, the expression formula of the absolute error is as follows:

[0111] ;

[0112] in, represents the model calculation value, Represents the actual measured value. The expression formula of the mean square error is as follows:

[0113] ;

[0114] in, is the actual measured value, is the model calculation value, and n is the number of data points. By comparing the mean square error and the absolute error with the determined error allowable range, it is determined whether the comprehensive performance of the initial digital twin model meets the preset performance conditions. It can be understood that in order to ensure the accuracy of the model, this embodiment can establish high-quality data, and continuously update and correct the digital twin virtual model from a theoretical and experimental perspective. When the comprehensive performance of the initial digital twin model cannot meet the preset performance conditions, this embodiment can optimize the initial digital twin model using the above method until the comprehensive performance of the initial digital twin model meets the preset performance conditions. In this way, this embodiment verifies and evaluates the digital twin model from the aspects of real-time, accuracy, dynamic response and scalability to ensure that the target digital twin model whose comprehensive performance meets the preset performance conditions is obtained, and when calculating the accuracy of the model, different errors are selected for calculation according to different data types, thereby improving the reliability of evaluation and verification.

[0115] As can be seen from the above, the embodiment of the present application first uses a preset modeling method to construct a digital twin model of the target drilling rig lifting system, and performs virtual-to-real mapping of the digital twin model according to a preset data acquisition strategy. After the virtual-to-real mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, so as to simulate the digital twin model based on the simulation data, and obtain the initial digital twin model by quantifying the model accuracy. The preset process identification model is used to perform joint simulation with the initial digital twin model, and a corresponding automatic update strategy is formulated based on the obtained simulation results to dynamically update the initial digital twin model according to the automatic update strategy, and the initial digital twin model is evaluated and verified based on the model indicators of real-time, dynamic response and scalability, the current error allowable range is determined according to the current process, and different errors are selected according to different data types for accuracy calculation to obtain the target digital twin model. In this way, through the above process of the embodiment of the present application, on the one hand, the performance, responsiveness and other aspects of the model are verified and evaluated by calculating the real-time, dynamic response and scalability indicators of the model, and at the same time, the allowable error range is adjusted according to different process steps to improve the reference of the model verification and evaluation; on the one hand, when calculating the accuracy of the model, different errors are selected for calculation according to different data types, which improves the reliability of the evaluation and verification; on the other hand, when evaluating and verifying the initial digital twin model based on the preset model indicators, the initial digital twin model is comprehensively evaluated and verified from multiple aspects to maximize the simulation of the scenario of the target drilling rig lifting system.

[0116] Accordingly, see Figure 6As shown, the embodiment of the present application also provides a digital device for a drilling rig hoisting system based on digital twin, including:

[0117] A model building module 11 is used to build a digital twin model of the target drilling rig lifting system using a preset modeling method; the digital twin model includes a mechanism model, a data model and a knowledge model;

[0118] A virtual-to-real mapping module 12 is used to obtain device information data and real-time monitoring data of physical equipment in the target drilling rig lifting system according to a preset data acquisition strategy, and perform virtual-to-real mapping of the digital twin model according to the device information data;

[0119] A model simulation module 13 is used to determine the simulation data of the digital twin model based on the real-time monitoring data after the virtual-real mapping is completed, and simulate the digital twin model based on the simulation data, so as to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain an initial digital twin model whose model accuracy meets the preset accuracy condition;

[0120] The strategy formulation module 14 is used to use the preset process identification model and the initial digital twin model to perform joint simulation, and based on the simulation results obtained under different process processes, formulate corresponding automatic update strategies for the initial digital twin model for the different process processes, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets the preset performance conditions; the process identification model is a model established based on a preset hybrid automaton.

[0121] As can be seen from the above, the embodiment of the present application first uses the preset modeling method to construct the digital twin model of the target drilling rig lifting system, and performs virtual-real mapping of the digital twin model according to the preset data acquisition strategy. After the virtual-real mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, so as to simulate the digital twin model based on the simulation data, and obtain the initial digital twin model by quantifying the model accuracy. The preset process identification model is used to perform joint simulation with the initial digital twin model, and a corresponding automatic update strategy is formulated based on the obtained simulation results, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on the preset model indicators to obtain the target digital twin model. In this way, through the above process of the embodiment of the present application, the digitization of the drilling rig lifting system is realized based on the digital twin technology, and the model is updated according to the process conditions, and then the drilling rig lifting system is digitally modeled to achieve the optimization management of the drilling rig lifting system based on the digital twin model.

[0122] In some specific implementations, the model building module 11 may specifically include:

[0123] An information determination unit is used to analyze the structural composition, motion characteristics and structural features of the target drilling rig hoisting system to determine the subsystem set, structural characteristics and operating parameters of the target drilling rig hoisting system, and determine the modeling requirement information and system data information of the target drilling rig hoisting system;

[0124] A first model building unit, configured to determine coupling information between subsystems in the subsystem set according to the structural characteristics and the subsystem set, and to build the mechanism model in the digital twin model based on the subsystem set, the coupling information and the operating parameters;

[0125] A second model building unit is used to preprocess the pre-collected data related to the operating parameters to obtain processed data, and build the data model in the digital twin model based on the modeling requirement information and the processed data through a preset learning model;

[0126] The third model building unit is used to mine the system data information based on a preset machine learning algorithm to build the knowledge model in the digital twin model.

[0127] In some specific implementations, the virtual-to-real mapping module 12 may specifically include:

[0128] An experimental testing unit, used for preprocessing the equipment information data, and performing theoretical analysis and experimental testing on the target drilling rig lifting system based on the processed equipment information data, so as to determine the component parameters in the digital twin model;

[0129] A data interaction unit is used to interact between the component parameters and the device information data through a preset interface to obtain the digital twin model that is consistent with the actual performance.

[0130] In some specific implementations, the digital twin-based drilling rig hoisting system digitization device may further include:

[0131] A set establishment unit, used for dividing the different process of the target drilling rig lifting system into a preset number of continuous state spaces, and establishing a system variable parameter set by using the real-time monitoring data and the simulation data;

[0132] A condition determination unit, used to set the initial state space of the process identification model according to the actual situation of the target drilling rig hoisting system, and determine the migration conditions between the state spaces; the state spaces include the continuous state space and the initial state space;

[0133] A structure stratification unit is used to establish the preset hybrid automaton based on the migration condition, the system variable parameter set and the state spaces, and stratify the structure of the preset hybrid automaton to obtain the process identification model.

[0134] In some specific implementations, the strategy formulation module 14 may specifically include:

[0135] A model driving unit, configured to drive a preset process identification model using the real-time monitoring data to identify the process of the current target drilling rig lifting system, obtain relevant information of the current process, and determine an input value of the initial digital twin model according to the relevant information;

[0136] A model updating unit is used to drive the initial digital twin model based on the input value to set the triggering condition for the automatic update of the current process according to the obtained output result and the changing trend of the real-time monitoring data, so that when the prediction error of the initial digital twin model or the changing trend of the equipment parameters meets the triggering condition, or when the process changes, the initial digital twin model is updated using a preset update method.

[0137] In some specific embodiments, the model updating unit is specifically used to determine the uncertainty parameters and experimental data corresponding to the current process based on the relevant information; use Bayesian inference and variational inference to update the uncertainty parameters and the experimental data, so as to update the initial digital twin model in combination with the real-time monitoring data.

[0138] In some specific implementations, the strategy formulation module 14 may specifically include:

[0139] An evaluation and verification unit, used to evaluate and verify the real-time performance, dynamic response and scalability of the initial digital twin model;

[0140] A range determination unit, configured to determine an error tolerance range according to the current process of the target drilling rig hoisting system;

[0141] A parameter analysis unit, used to analyze the parameters in the initial digital twin model to determine parameter characteristics corresponding to each of the parameters;

[0142] An error analysis unit is used to determine respective error analysis methods according to the parameter characteristics, and use the error analysis method to perform error analysis on the corresponding parameters, so as to evaluate and verify the accuracy of the initial digital twin model based on the allowable error range.

[0143] Furthermore, the present application also discloses an electronic device. Figure 7 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure cannot be regarded as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input-output interface 25 and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the digital twin-based drilling rig lifting system digitization method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0144] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0145] In addition, the memory 22 as a carrier for resource storage may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0146] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the digital twin-based drilling rig hoisting system digitization method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0147] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the digital twin-based drilling rig hoisting system digitization method disclosed above is implemented. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, and no further description will be given here.

[0148] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0149] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0150] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0151] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device 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 device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0152] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, 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 application.

Claims

1. A digital method for drilling rig hoisting system based on digital twin, characterized in that: include: Use the preset modeling method to build a digital twin model of the target drilling rig hoisting system; The digital twin model includes a mechanism model, a data model and a knowledge model; Acquire device information data and real-time monitoring data of physical equipment in the target drilling rig lifting system according to a preset data acquisition strategy, and perform virtual-real mapping of the digital twin model according to the device information data; After the virtual-real mapping is completed, the simulation data of the digital twin model is determined based on the real-time monitoring data, and the digital twin model is simulated based on the simulation data, so as to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain an initial digital twin model whose model accuracy meets the preset accuracy condition; Use a preset process identification model to perform joint simulation with the initial digital twin model, and based on the simulation results obtained under different process conditions, formulate corresponding automatic update strategies for the initial digital twin model for the different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets preset performance conditions; The process identification model is a model established based on a preset hybrid automaton.

2. The method for digitizing a drilling rig hoisting system based on digital twin according to claim 1, characterized in that: The digital twin model of the target drilling rig lifting system is constructed by using a preset modeling method, including: Analyze the structural composition, motion characteristics and structural features of the target drilling rig hoisting system to determine the subsystem set, structural characteristics and operating parameters of the target drilling rig hoisting system, and determine the modeling requirement information and system data information of the target drilling rig hoisting system; Determine the coupling information between the subsystems in the subsystem set according to the structural characteristics and the subsystem set, and construct the mechanism model in the digital twin model based on the subsystem set, the coupling information and the operating parameters; Preprocessing the pre-collected data related to the operating parameters to obtain processed data, and constructing the data model in the digital twin model based on the modeling requirement information and the processed data through a preset learning model; The system data information is mined based on a preset machine learning algorithm to construct the knowledge model in the digital twin model.

3. The method for digitizing a drilling rig hoisting system based on digital twin according to claim 1, characterized in that: The performing virtual-real mapping of the digital twin model according to the device information data includes: Preprocessing the equipment information data, and performing theoretical analysis and experimental testing on the target drilling rig lifting system based on the processed equipment information data to determine component parameters in the digital twin model; The component parameters and the device information data interact through a preset interface to obtain the digital twin model that is consistent with the actual performance.

4. The method for digitizing a drilling rig hoisting system based on digital twin according to claim 1, characterized in that: Before the combined simulation using the preset process identification model and the initial digital twin model, the method further includes: Divide the different process steps of the target drilling rig lifting system into a preset number of continuous state spaces, and establish a system variable parameter set using the real-time monitoring data and the simulation data; According to the actual situation of the target drilling rig lifting system, the initial state space of the process identification model is set, and the migration conditions between the state spaces are determined; the state spaces include the continuous state space and the initial state space; The preset hybrid automaton is established based on the migration condition, the system variable parameter set and the state spaces, and the structure of the preset hybrid automaton is layered to obtain the process identification model.

5. The method for digitizing a drilling rig hoisting system based on digital twin according to claim 1, characterized in that: The method of using a preset process identification model to jointly simulate the initial digital twin model, and formulating corresponding automatic update strategies of the initial digital twin model for the different process based on the obtained simulation results under different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategy, includes: Using the real-time monitoring data to drive a preset process identification model to identify the process of the current target drilling rig lifting system, obtain relevant information of the current process, and determine the input value of the initial digital twin model according to the relevant information; The initial digital twin model is driven based on the input value to set the trigger condition for automatic update of the current process according to the obtained output result and the change trend of the real-time monitoring data, so that when the prediction error of the initial digital twin model or the change trend of the equipment parameter meets the trigger condition, or when the process changes, the initial digital twin model is updated using a preset update method.

6. The method for digitizing a drilling rig hoisting system based on digital twin according to claim 5, characterized in that: The updating of the initial digital twin model by using a preset updating method includes: Determine the uncertainty parameters and experimental data corresponding to the current process according to the relevant information; The uncertainty parameters and the experimental data are updated using Bayesian inference and variational inference, so as to update the initial digital twin model in combination with the real-time monitoring data.

7. The method for digitizing a drilling rig hoisting system based on digital twin according to any one of claims 1 to 6, characterized in that: The evaluating and verifying the initial digital twin model based on the preset model indicators includes: Evaluate and verify the real-time performance, dynamic response and scalability of the initial digital twin model; Determining an error tolerance range according to the current process of the target drilling rig lifting system; Analyzing the parameters in the initial digital twin model to determine parameter characteristics corresponding to each of the parameters; Determine respective error analysis methods according to the parameter characteristics, and use the error analysis methods to perform error analysis on the corresponding parameters, so as to evaluate and verify the accuracy of the initial digital twin model based on the allowable error range.

8. A digital device for drilling rig hoisting system based on digital twin, characterized in that: include: A model building module, used to build a digital twin model of the target drilling rig hoisting system using a preset modeling method; The digital twin model includes a mechanism model, a data model and a knowledge model; A virtual-to-real mapping module, used to obtain device information data and real-time monitoring data of physical equipment in the target drilling rig lifting system according to a preset data acquisition strategy, and perform virtual-to-real mapping of the digital twin model according to the device information data; A model simulation module, used to determine the simulation data of the digital twin model based on the real-time monitoring data after the virtual-real mapping is completed, and simulate the digital twin model based on the simulation data, so as to quantify the model accuracy of the digital twin model according to the obtained simulation effect, and obtain an initial digital twin model whose model accuracy meets the preset accuracy condition; A strategy formulation module, used to use a preset process identification model to perform joint simulation with the initial digital twin model, and based on the simulation results obtained under different process conditions, formulate corresponding automatic update strategies for the initial digital twin model for the different process conditions, so as to dynamically update the initial digital twin model according to the automatic update strategy, and evaluate and verify the initial digital twin model based on preset model indicators to obtain a target digital twin model whose comprehensive performance meets preset performance conditions; The process identification model is a model established based on a preset hybrid automaton.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the digital twin-based drilling rig hoisting system digitization method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, it implements the digital twin-based drilling rig hoisting system digitization method as described in any one of claims 1 to 7.

Images