Digital Twin-Based Digital Methods, Devices, Equipment, and Media for Drill Rig Hoisting Systems

Abstract

This application discloses a digital twin-based method, apparatus, equipment, and medium for digitizing a drilling rig hoisting system, relating to the field of engineering machinery technology. The method includes: constructing a digital twin model of the target drilling rig hoisting system; performing a virtual-to-real mapping of the digital twin model based on equipment information data; determining simulation data for the digital twin model based on real-time monitoring data, and simulating the digital twin model to quantify its accuracy, thus obtaining an initial digital twin model; performing joint simulation using a pre-set process identification model and the initial digital twin model, and developing corresponding automated update strategies for different processes to enable dynamic updates; and evaluating and verifying the initial digital twin model to obtain the target digital twin model. Therefore, a digital twin model of the drilling rig hoisting system can be created to achieve optimized management of the system based on the digital twin model.

Description

Technical Field

[0001] This invention relates to the field of engineering machinery technology, and in particular to a digital method, device, equipment and medium for a drilling rig hoisting system based on digital twins. Background Technology

[0002] The hoisting system, a critical subsystem of drilling rig equipment, undertakes vital tasks such as hoisting and lowering drill strings and casing, feeding drill strings, and controlling drilling pressure. A malfunction in the hoisting system can lead to a halt in the entire drilling operation, resulting in significant economic losses. Therefore, the stability and safety of the hoisting system determine the overall performance of the drilling rig. Currently, most digital twin methods for drilling rig hoisting systems focus on the system construction level. However, due to the complexity of current drilling rig hoisting systems and their operational characteristics, it is difficult to accurately describe their dynamic characteristics and internal mechanisms using simple mathematical models. This hinders comprehensive analysis, maintenance, and full lifecycle management of the drilling rig hoisting system's performance from multiple dimensions, including structure, components, and functions.

[0003] In summary, how to perform digital twin modeling of the drilling rig hoisting system in order 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 this invention is to provide a digital twin-based method, apparatus, equipment, and medium for digitizing drilling rig hoisting systems, capable of creating digital twin models of the drilling rig hoisting system to achieve optimized management of the system based on the digital twin model. The specific solution is as follows:

[0005] Firstly, this application provides a digital twin-based method for digitizing a drilling rig hoisting system, comprising:

[0006] A digital twin model of the target drilling rig hoisting system is constructed using a pre-defined modeling method; the digital twin model includes a mechanism model, a data model, and a knowledge model.

[0007] According to the preset data acquisition strategy, the equipment information data and real-time monitoring data of the physical equipment in the target drilling rig hoisting system are obtained, and the virtual-real mapping of the digital twin model is performed based on the equipment 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 to quantify the model accuracy of the digital twin model according to the obtained simulation effect, so as to obtain an initial digital twin model whose model accuracy meets the preset accuracy conditions.

[0009] A pre-defined process identification model is used to perform joint simulation with the initial digital twin model. Based on the simulation results obtained under different process processes, an automated update strategy for the initial digital twin model is formulated for the different process processes. The initial digital twin model is dynamically updated according to the automated update strategy. The initial digital twin model is evaluated and verified based on the pre-defined model indicators to obtain a target digital twin model whose comprehensive performance meets the pre-defined performance conditions. The process identification model is a model built on the basis of a pre-defined hybrid automaton.

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

[0011] The structural composition, motion characteristics, and structural features of the target drilling rig hoisting system are analyzed to determine the subsystem set, structural characteristics, and operating parameters of the target drilling rig hoisting system, and to determine the modeling requirements and system data information of the target drilling rig hoisting system.

[0012] Based on the structural characteristics and the set of subsystems, the coupling information between each subsystem in the set of subsystems is determined, and the mechanism model in the digital twin model is constructed based on the set of subsystems, the coupling information, and the operating parameters;

[0013] The pre-collected data related to the operating parameters is preprocessed to obtain processed data, and the data model in the digital twin model is constructed based on the modeling requirement information and the processed data using 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, the step of performing the virtual-real mapping of the digital twin model based on the device information data includes:

[0016] The equipment information data is preprocessed, and theoretical analysis and experimental testing are performed on the target drilling rig hoisting system based on the processed equipment information data to determine the component parameters in the digital twin model.

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

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

[0019] The different processes of the target drilling rig hoisting system are divided into a preset number of continuous state spaces, and a set of system variable parameters is established using the real-time monitoring data and the simulation data.

[0020] The initial state space of the process identification model is set according to the actual situation of the target drilling rig hoisting system, and the transition conditions between each state space are determined; each state space includes the continuous state space and the initial state space.

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

[0022] Optionally, the step of jointly simulating the initial digital twin model using a preset process identification model and the initial digital twin model, and formulating an automated update strategy for the initial digital twin model based on the simulation results under different process processes, so as to dynamically update the initial digital twin model according to the automated update strategy, includes:

[0023] The real-time monitoring data is used to drive a preset process identification model to identify the process of the current target drilling rig hoisting system, obtain relevant information of the current process, and determine the input value of the initial digital twin model based on the relevant information.

[0024] The initial digital twin model is driven by the input value, and the triggering conditions for the automatic update of the current process are set according to the obtained output results and the changing trend of the real-time monitoring data. When the prediction error of the initial digital twin model or the changing trend of the equipment parameters meets the triggering conditions, or when the process changes, the initial digital twin model is updated using a preset update method.

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

[0026] Based on the relevant information, determine the uncertainty parameters and experimental data corresponding to the current process;

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

[0028] Optionally, the evaluation and verification of the initial digital twin model based on preset model indicators includes:

[0029] The real-time performance, dynamic response, and scalability of the initial digital twin model were evaluated and verified.

[0030] The allowable error range is determined based on the current process of the target drilling rig hoisting system.

[0031] The parameters in the initial digital twin model are analyzed to determine the parameter characteristics corresponding to each parameter.

[0032] Each error analysis method is determined based on the parameter characteristics, and the error analysis method is used to perform error analysis on the corresponding parameters in order to evaluate and verify the accuracy of the initial digital twin model based on the allowable error range.

[0033] Secondly, this application provides a digital twin-based digitization device for a drilling rig hoisting system, comprising:

[0034] The model building module is used to construct 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.

[0035] The virtual-real mapping module is used to acquire equipment information data and real-time monitoring data of the physical equipment in the target drilling rig hoisting system according to a preset data acquisition strategy, and to perform virtual-real mapping of the digital twin model based on the equipment information data.

[0036] The model simulation module 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 to 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 conditions.

[0037] The strategy formulation module is used to perform joint simulation using a preset process identification model and the initial digital twin model, and based on the simulation results obtained under different process processes, formulate corresponding automated 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 automated 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 built on a preset hybrid automaton.

[0038] Thirdly, this application provides an electronic device, comprising:

[0039] Memory, used to store computer programs;

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

[0041] Fourthly, this application provides a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned digital twin-based digitization method for drilling rig hoisting systems.

[0042] In this embodiment, a digital twin model of the target drilling rig hoisting system is constructed using a preset modeling method. The digital twin model includes a mechanism model, a data model, and a knowledge model. Equipment information data and real-time monitoring data of the physical equipment in the target drilling rig hoisting system are acquired according to a preset data acquisition strategy. A virtual-to-real mapping is then performed on the digital twin model based on the equipment information data. After the virtual-to-real mapping is completed, simulation data for the digital twin model is determined based on the real-time monitoring data. The digital twin model is then simulated based on the simulation data to quantify its accuracy according to the obtained simulation results. An initial digital twin model whose accuracy meets preset accuracy conditions is obtained. A preset process identification model is used to perform joint simulation with the initial digital twin model. Based on the simulation results obtained under different process conditions, an automated update strategy for the initial digital twin model is formulated for each different process, so that the initial digital twin model can be dynamically updated according to the automated update strategy. 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. As can be seen from the above, this application first constructs a digital twin model of the target drilling rig hoisting system using a preset modeling method, and performs a virtual-to-real mapping of the digital twin model according to a preset data acquisition strategy. After the virtual-to-real mapping is completed, simulation data of the digital twin model is determined based on real-time monitoring data. The digital twin model is then simulated based on the simulation data. An initial digital twin model is obtained by quantifying the model's accuracy. A preset process identification model is then used to perform joint simulation with the initial digital twin model. Based on the obtained simulation results, a corresponding automated update strategy is formulated to dynamically update the initial digital twin model according to the automated update strategy. Finally, the initial digital twin model is evaluated and verified based on preset model indicators to obtain the target digital twin model. In this way, through the above process of this application, the drilling rig hoisting system is digitized based on digital twin technology, and the model is updated according to process conditions, thereby performing 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. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0044] Figure 1 This application discloses a flowchart of a digital twin-based method for digitizing a drilling rig hoisting system.

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

[0046] Figure 3 This application discloses a specific digital twin-based method for digitizing a drilling rig hoisting system.

[0047] Figure 4 This is a comparative diagram of the hook displacement during the tripping process disclosed in this application;

[0048] Figure 5 This is a schematic diagram illustrating the absolute error of the hook displacement during the tripping process disclosed in this application.

[0049] Figure 6 This is a schematic diagram of the structure of a digital device for a drilling rig hoisting system based on digital twin disclosed in this application;

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

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Currently, most digital twin methods for drilling rig hoisting systems focus on the system construction level. However, due to the complexity of current drilling rig hoisting systems and their characteristics during operation, it is difficult to accurately describe the dynamic characteristics and internal mechanisms of drilling rig hoisting systems using simple mathematical models. This makes it impossible to achieve comprehensive analysis, maintenance, and full lifecycle management of drilling rig hoisting system performance from multiple dimensions such as structure, components, and functions.

[0053] To overcome the aforementioned technical problems, this application provides a digital twin-based method for digitizing drilling rig hoisting systems, which performs 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.

[0054] See Figure 1 As shown in the figure, this invention discloses a digital method for drilling rig hoisting systems based on digital twins, including:

[0055] Step S11: Construct 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.

[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 mechanistic model, a data model, and a knowledge model. The data model includes, but is not limited to, equipment physical data, operational data, and virtual data, and supports multiple functions such as equipment status monitoring, fault diagnosis, and performance prediction. The knowledge model supports functions such as decision support, fault diagnosis and prediction, and engineering optimization for the drilling rig hoisting system.

[0057] Specifically, this embodiment first analyzes 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 to determine the modeling requirements and system data information of the target drilling rig hoisting system. The operating parameters include, but are not limited to, major operating parameters such as motor parameters, transmission ratio, braking force, winch torque, and hook running speed, as well as parameters such as motor model, disc brake model, hydraulic system rated flow rate, pump inlet / outlet pressure, and power. 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 braking system formed by the motor, piston pump, hydraulic cylinder, disc brake, and other equipment, and the traveling block-drill string system formed by the overhead crane pulley block, traveling block pulley block, hook, drill string, and other drilling tools. The modeling requirements refer to the modeling objectives and scope, including expected performance indicators, operating environment, and constraints. The system data information includes, but is not limited to, sensor networks, operation logs, maintenance records, and historical operating data. In other words, the structural composition of the target drilling rig hoisting system is analyzed to clarify its equipment characteristics and main components based on the on-site working conditions of the drilling rig. The analysis identifies components and assembly forms that can be simplified for modeling, determining the structural characteristics of the target drilling rig hoisting system to reduce the difficulty of subsequent modeling. The motion characteristics of the target drilling rig hoisting system are analyzed to determine its operating parameters. The structural characteristics of the target drilling rig hoisting system are analyzed to determine the composition of each subsystem in its digital twin model, i.e., the set of subsystems, in order to explore the coupling effect between subsystems and provide ideas for subsequent modeling. Simultaneously, the modeling requirements and system data information of the target drilling rig hoisting system are determined.

[0058] Subsequently, this embodiment determines the coupling information between the subsystems in the subsystem set based on 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. The coupling information includes, but is not limited to, coupling methods and coupling effects. That is, considering the complex mechanical linkages and multidisciplinary collaborative work involved in the internal equipment cooperation of the target drilling rig hoisting system, when constructing the mechanism model, firstly, based on the structural characteristics and the subsystem set, the interaction between multiple physical fields within the system is analyzed to determine the direct or indirect coupling forms between the multiple physical fields, i.e., the coupling information between the subsystems in the subsystem set. Then, based on the subsystem set, the coupling information, and the operating parameters, the mechanism model is constructed from mechanical, temperature, fluid, electrical, and control fields. The physical fields include, but are not limited to, mechanical fields, temperature fields, fluid fields, and electromagnetic fields. Simultaneously, 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 requirements information and the processed data using a preset learning model; it also mines the system data information based on a preset machine learning algorithm to construct the knowledge model in the digital twin model. The preset learning model can be a machine learning model or a deep learning model. That is, the pre-collected data related to the operating parameters from actual applications is preprocessed to obtain processed data, and according to the specific application scenario, the data model is constructed based on the modeling requirements information and the processed data using 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 noted that modeling the aforementioned mechanism model includes, but is not limited to, motor electrical model modeling, hydraulic disc brake electro-hydraulic coupling modeling, drilling rig geometric model modeling, drilling rig hoisting system kinematic modeling, and drilling rig hoisting system dynamic modeling. Specifically, the motor electrical model modeling is used to obtain motor performance data, motor operating status, and motor output information; the hydraulic disc brake electro-hydraulic coupling modeling is used to obtain the hydraulic system status and current brake state; the drilling rig geometric model modeling is used to obtain information such as the size, shape, structure, and assembly of the drilling rig components to obtain a mirror model of the actual physical equipment; the drilling rig hoisting system kinematic modeling is used to obtain the interaction relationships and kinematic equations between the internal equipment of the system; and the drilling rig hoisting system dynamic modeling is used to obtain the magnitude and direction of the forces acting on each piece of equipment in the system, as well as to calculate the system's energy loss, power demand, and efficiency. Therefore, after determining the coupling information, this embodiment can build the mechanistic models of each subsystem in the Simscape environment (a tool for modeling and simulating multi-domain physical systems). Then, based on the interrelationships, coupling methods, and coupling mechanisms between the subsystems, the subsystem models are connected to establish a multi-domain coupled model of the target drilling rig hoisting system, i.e., the mechanistic model. In this way, when modeling the target drilling rig hoisting system, this embodiment first determines the relevant data information required for modeling, reducing the difficulty of subsequent modeling work and providing ideas for subsequent modeling. Simultaneously, the digital twin model is divided into three parts: a mechanistic model, a data model, and a knowledge model, to ensure that the resulting digital twin model is consistent with the target drilling rig hoisting system.

[0060] Step S12: Obtain equipment information data and real-time monitoring data of the physical equipment in the target drilling rig hoisting system according to the preset data acquisition strategy, and perform virtual-real mapping of the digital twin model based on the equipment information data.

[0061] In this embodiment, a preset data acquisition strategy is used to acquire equipment information data and real-time monitoring data of the physical equipment in the target drilling rig hoisting system, and a virtual-real mapping of the digital twin model is performed based on the equipment information data. The equipment information data includes relevant parameter information and status information of each physical entity within the drilling rig hoisting system, and the relevant parameter information includes physical, geometric, and performance parameter information of key equipment in the drilling rig hoisting 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 physical entities.

[0062] It should be noted that before acquiring the device information data and the real-time monitoring data, this embodiment needs to determine the data acquisition strategy. Specifically, the strategy can be selected based on the actual data acquisition requirements and the on-site environment, taking into account factors such as transmission distance, latency, energy consumption, and sampling rate. Furthermore, to achieve the virtual-real mapping of the digital twin model, this embodiment can determine the main data transmission scheme based on communication requirements and the mechanism by which data transmission depends on transmission protocols, access methods, multiple access schemes, channel multiplexing and coding, and multi-user detection technology. This establishes an interaction and integration strategy between data and the digital twin model, achieving data mapping and data fusion, i.e., the interaction and mapping between the digital twin model and the actual data. Specifically, for communication within the digital twin model, interaction can be achieved through standardized interfaces between visualization tools and simulation models; for communication between different digital twin models, it can be achieved through information sharing and data transmission between their respective physical entities; for communication between the digital twin and its corresponding physical entity, it can be achieved through sensor data and status data, remote control, software updates, etc. Here, the different digital twin models refer to the mechanism models corresponding to each subsystem within the digital twin model.

[0063] It should be noted that the process of mapping the virtual and real aspects of the digital twin model based on the equipment information data is as follows: The equipment information data is preprocessed, and theoretical analysis and experimental testing are performed on the target drilling rig hoisting system based on the processed equipment information data to determine the component parameters in the digital twin model; the component parameters and the equipment information data interact through a preset interface to obtain a digital twin model consistent with actual performance. The preprocessing includes, but is not limited to, handling missing data values, removing or correcting erroneous data points, removing duplicate data records, and standardizing and normalizing the data. In other words, considering the abundance of data collected at the drilling rig operation site, and the uncontrollable factors such as the limitations of sensing methods and the harshness of some working environments, data anomalies are inevitable. Therefore, this embodiment requires necessary preprocessing of the collected equipment information data. Subsequently, based on the relevant parameter information in the processed equipment information data, theoretical analysis and experimental testing are performed on the target drilling rig lifting system to determine the component parameters in the model. The interaction between the component parameters and the equipment information data is then conducted through a preset interface to obtain the digital twin model that is consistent with the actual performance. Specifically, in this embodiment, an electrical subsystem consistent with the performance of the motor in the field can be constructed in the Simscape environment of Simulink (a tool for modeling and simulating physical systems in multiple domains) based on parameters such as the motor model, voltage, current, torque, and speed used in the field; a transmission subsystem consistent with the performance of the transmission system in the field can be constructed in the Simscape environment of Simulink based on parameters such as the main transmission method, transmission ratio, and physical properties of the transmission equipment in the field; a hydraulic brake subsystem consistent with the internal parameters and braking effect of the hydraulic brake system in the field can be constructed in the Simscape environment of Simulink based on parameters such as the model, drive system, pump inlet / outlet pressure, and flow rate of the hydraulic disc brake used in the field; and a traveling block-drill string system consistent with the performance of the equipment in the field can be constructed in the Simscape environment of Simulink based on parameters such as the physical properties of the pulley block, hook parameters, and drill string physical properties collected in the field, to form the digital twin model. Figure 2 The diagram shown is a schematic of a digital twin coupling model provided in this application. In this way, this embodiment achieves the virtual-real mapping of the digital twin model through three aspects to obtain a digital twin model consistent with the on-site performance, maximizing the simulation of the target drilling rig hoisting system scenario.

[0064] Step S13: 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 to quantify the model accuracy of the digital twin model according to the obtained simulation effect, so as to obtain an initial digital twin model whose model accuracy meets the preset accuracy conditions.

[0065] In this embodiment, after completing the virtual-real mapping, 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. 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 hoisting system are affected by many factors during actual operation, this embodiment needs to first assign preliminary and reasonable values ​​to the physical parameters that are difficult to determine in the digital twin model based on the real-time monitoring data before proceeding with subsequent updates. This is to supplement the missing physical parameters in the digital twin model. Then, the main simulation data of the digital twin model is determined based on the real-time monitoring data, and a full lifecycle simulation is performed on the constructed digital twin model based on the simulation data. After completing the simulation, key performance indicators for evaluating performance are selected based on the application requirements of the drilling rig hoisting performance. 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. The physical parameters include, but are not limited to, stiffness, inertia, and damping within the mechanical subsystem; and fluid properties and flow characteristics within the hydraulic subsystem. Understandably, 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, then the current digital twin model is the initial digital twin model; if the model accuracy does not meet the preset accuracy condition, then 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, thereby improving the effectiveness of the established digital twin model.

[0067] Step S14: Perform joint simulation using the preset process identification model and the initial digital twin model. Based on the simulation results obtained under different process processes, formulate corresponding automated update strategies for the initial digital twin model for the different process processes. This allows for dynamic updates of the initial digital twin model according to the automated update strategies. The initial digital twin model is then 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.

[0068] In this embodiment, joint simulation is performed based on a preset process identification model and the initial digital twin model to obtain simulation results under different process processes. Based on the simulation results, corresponding automated update strategies for the models are formulated for different process processes, so that the initial digital twin model can be dynamically updated according to the automated update strategies. The initial digital twin model is then evaluated and verified based on preset model indicators to obtain a target digital twin model whose overall performance meets preset performance conditions. The process identification model is a model built on a preset hybrid automaton.

[0069] It is understood that before performing the joint simulation, this embodiment needs to establish the process identification model first. The processing flow is as follows: the different processes of the target drilling rig hoisting system are divided into a preset number of continuous state spaces, and a system variable parameter set is established using the real-time monitoring data and the simulation data; the initial state space of the process identification model is set according to the actual situation of the target drilling rig hoisting system, and the transition conditions between each state space are determined; each state space includes the continuous state space and the initial state space; based on the transition conditions, the system variable parameter set, and 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 aforementioned process includes, but is not limited to, top drive rising (without gripping the drill bit), drill pipe bottom engagement and top drive center tube and drill pipe joint fastening, top drive rotary drilling (gripping the drill bit), and top drive center tube and drill pipe uncoupling; 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 housing vibration, pump inlet / outlet flow rate, inlet / outlet pressure, winch speed, torque, hook displacement, speed, acceleration, top drive speed, hoist Boolean signal, and latch Boolean signal. The parameters include: Kavaboul signal, BOP Boolean signal, mud pump Boolean signal, theoretical drilling rig lifting time, theoretical drilling rig single-joint connection time, theoretical drilling rig running-down time, theoretical drilling rig unhooking time, bottom hole temperature, drilling pressure, drilling depth, number of drill strings, field environmental parameters, drilling geological information, and field communication information. The initial state space mainly includes the state when the top drive is not holding the drill string and is rising when the system is first started. The migration conditions are mainly composed of several relevant parameters that are significantly affected by changes in drilling rig operating conditions, including but not limited to motor speed, top drive speed, vertical distance of top drive rising and falling, bottom hole drilling pressure, and time parameters. In other words, this embodiment divides the different processes of the target drilling rig hoisting system into several continuous state spaces. Then, it establishes a system variable parameter set using the real-time monitoring data and the simulation data. Based on the actual situation of the target drilling rig hoisting system, it sets the initial state space of the process identification model and clarifies the transition conditions between each state space. Finally, during the drilling process, the different state spaces of the drilling rig hoisting system are treated as a discrete dynamic system. Based on the transition conditions, the system variable parameter set, and each state space, the preset hybrid automaton is established, expressed by the following formula:

[0070] ;

[0071] in, Represents a finite set of state variables, including discrete states. and continuous state ; It is a finite set of input variables, including discrete inputs. and continuous input ; It is the initial state set. ; This represents a mapping that describes the continuous evolution of discrete states. ; Denotes an invariant set, and ; Indicates the reset relationship and describes discrete jumps. That is, the continuous dynamic process under discrete events is described in the form of differential equations and difference equations. The switching of discrete events leads to discontinuous jumps in 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 these invariant set conditions, it will also lead to the switching of discrete events. Subsequently, considering the evolution process of the drilling rig hoisting system on the continuous time axis, this embodiment, based on the preset hybrid automaton model, transforms it through a parallel projection structure to effectively layer the structure of the preset hybrid automaton and establish a generalized automaton model to obtain the process identification model. In the model, the continuous dynamic behavior of the system only affects the values ​​of local states, while the discrete dynamic behavior of the system will affect the state values ​​of the entire system. The expression formula of the generalized automaton model is as follows:

[0072] ;

[0073] in, Represents the set of system variables; A finite set representing the state of a continuous space; A finite set representing the initial values ​​of variables and the initial state space; A finite set representing the transitions of discrete events; This represents the set of final spaces. It should be noted that this is the set of system variables. ,in Discrete event variables representing different operational processes mainly include motor output speed, motor output torque, hook displacement, and hook-on / off time parameters; finite sets of continuous spatial states. The established state spaces mainly include top drive rising (drill string not clamped), drill string bottom engagement with top drive center tube and drill string joint, top drive rotary drilling (drill string clamped), and top drive center tube and drill string uncoupled; initial values ​​of variables and a finite set of the initial state space. This represents the initial values ​​of system variable parameters in the initial state space, where the initial state space is assumed to be when the system just starts up, with the top drive rising (drill string not clamped); a finite set of discrete event transitions. Used to describe the transition conditions between state spaces. The parameters involved in the transition conditions mainly include hook displacement, time parameters, bottom hole drilling pressure, equipment Boolean parameters, etc.; the final set of spaces. This includes, but is not limited to, the load capacity of the drilling rig hook and the number of drill rods.

[0074] It should be noted that the joint simulation using the process identification model and the initial digital twin model is to simultaneously identify the real-time process of the system through the process identification model, simulate the initial digital twin model based on the identified process pattern, and formulate a corresponding automated update strategy. Therefore, the process flow for formulating the automated update strategy through joint simulation is as follows: The real-time monitoring data drives the preset process identification model to identify the process of the current target drilling rig hoisting system, obtaining relevant information about the current process, and determining the input value of the initial digital twin model based on this information; the initial digital twin model is driven based on the input value to set the trigger conditions for automated updates of the current process according to the obtained output results 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 equipment parameters meets the trigger conditions, or when the process changes, the initial digital twin model is updated using a preset update method. The relevant information includes the current state space corresponding to the operating condition, the current operating status of the equipment, the current operating parameters of the equipment, the bottom hole status, and the field information; the relevant information is the selected requirement parameters. That is, the real-time monitoring data drives a preset process identification model, promoting state space transformation and updating variables in the field monitoring data portion of the system variable set when the model's migration conditions are met. This identifies the current process of the target drilling rig hoisting system, obtains relevant information about the current process, acquires information changes of the system under different processes based on the relevant information, determines the input value of the initial digital twin model, drives the knowledge model in the initial digital twin model to run, and proposes decision suggestions for relevant data and threshold settings in different state spaces within the working condition identification model based on the output results of the knowledge model and the changing trends of the real-time monitoring data. This allows for threshold setting, alarm setting, and setting current working condition operation suggestion values ​​for relevant data in different state spaces within the process identification model. It is understood that since different process designs have different parameters, this embodiment formulates corresponding automated update strategies based on the identified process. That is, different update strategies are used for different processes to trigger update conditions when the process changes. In addition, when the prediction error is too large, or the trend of the device parameters does not conform, an update condition will be triggered to adjust the parameters of the model.

[0075] It should be further explained that, considering the changes in the state of the internal equipment of the drilling rig's lifting system under different operating conditions and the influence of uncertain parameters used in the modeling, a certain error occurs between the simulation results and the actual operating results. Furthermore, the key parameters involved in updating the digital twin model differ under different operating conditions. To ensure the consistency of response between the twin model and the physical entity, the automated update strategy for different state spaces mainly includes two parts: calculating the model prediction error and evaluating the performance of the digital twin model under the current operating condition; and setting the trigger conditions for model self-update based on the magnitude of the prediction error or the changing trend of key equipment parameters. Specifically, this embodiment can set the trigger conditions for model self-update based on the magnitude of the prediction error or the changing trend of key equipment parameters. The absolute difference, relative difference, or higher-level statistical indicators between the predicted and actual values ​​are calculated, and adaptive model updates are achieved through machine learning and other methods. It is understood that this embodiment can also formulate manual optimization strategies to address the difficulty in monitoring and predicting non-sensitive parameters within the model. These strategies include defining reasonable value ranges for non-sensitive parameters, iterative optimization, and combined optimization.

[0076] It should be noted that the process of dynamically updating the initial digital twin model according to the automated update strategy is as follows: The uncertainty parameters and experimental data corresponding to the current process are determined based on the relevant information; Bayesian inference and variational inference are used to update the uncertainty parameters and experimental data, so as to update the initial digital twin model in conjunction 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 is Then, the expression formula for the Bayesian inference can be as follows:

[0077] ;

[0078] in, Let θ be the posterior distribution of the parameter, also known as the posterior probability density distribution, representing the probability distribution of the parameter given the data. Probability distribution of different values; Let be the likelihood function, representing the likelihood of the parameter taking the value of Data observed under these circumstances The probability of; For parameters The prior distribution is the same as the prior probability density distribution; It is the marginal likelihood function, which represents the observed data under all parameter values. The probability can also be obtained by integrating the likelihood function over all possible parameter values. Therefore, the Bayesian inference can also be expressed as follows:

[0079] ;

[0080] in, Subsequently, the posterior distribution... Approximate to a simpler The goal of variational inference is to find variational parameters. This makes the posterior distribution The closest distribution to the true posterior distribution Therefore, in this embodiment, KL divergence can be used to quantify the mismatch between two distributions in the variational inference. The formula for KL divergence can be expressed as follows:

[0081] ;

[0082] in, Let the expected value of the logarithmic function within the parentheses be represented. Expanding and simplifying the expected value, we get:

[0083] ;

[0084] Where the left side of the equation is a constant, let:

[0085] ;

[0086] in, for The joint distribution of KL divergence is transformed into solving the problem of minimizing KL divergence, thus avoiding the encounter of posterior distribution probability in the process of solving approximate problems.

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

[0088] ;

[0089] in, Let be an m-dimensional vector of error, and let the causes of error include environmental factors, parameter changes, and state degradation. Then, the expression formula for the likelihood function can be:

[0090] ;

[0091] in, These represent the mean and standard deviation of the error, respectively. Prior distributions are selected for the numerous physical parameters within the twin model. Based on experience with the changes in these parameters, most exhibit a continuous process of gradual increase or decrease. Therefore, the beta distribution is chosen to describe this process, and its formula is as follows:

[0092] ;

[0093] in, For parameters to be updated, All parameters are greater than 0. The parameters can be calculated based on prior data regarding parameter changes. The specific value that can be taken, therefore The calculation formula is as follows:

[0094] ;

[0095] in, The mean of the parameters, Let be the standard deviation of the parameter. Combining all the equations, we get:

[0096] ;

[0097] ;

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

[0099] ;

[0100] This embodiment transforms the problem of solving the posterior distribution into solving the ELBO maximum problem. Based on real-time state data and the prior parameter distribution, the posterior parameter distribution can be calculated, thus completing a parameter update. Combining multiple real-time state data, the digital twin model can be updated. In this way, this embodiment first uses real-time monitoring data to drive a preset process identification model, accurately identifying the current operating condition of the drilling rig hoisting system, exploring the changes in equipment state under different operating conditions to guide subsequent work, and establishing a manual optimization and dynamic feedback mechanism. A suitable machine learning algorithm is selected for digital twin updates, achieving real-time virtual mapping of the drilling rig hoisting system.

[0101] As can be seen from the above, the embodiments of this application first construct a digital twin model of the target drilling rig hoisting system using a preset modeling method, and perform 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 real-time monitoring data, and the digital twin model is simulated based on the simulation data. An initial digital twin model is obtained by quantifying the model accuracy. A 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. The initial digital twin model is dynamically updated according to the automatic update strategy, and the initial digital twin model is evaluated and verified based on preset model indicators to obtain the target digital twin model. In this way, through the above process of the embodiments of this application, on the one hand, when modeling the target drilling rig hoisting system, the relevant data information required for modeling is determined first to reduce the difficulty of subsequent modeling work and provide ideas for subsequent modeling; on the other 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 hoisting system; on the other 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, maximizing the simulation of the target drilling rig hoisting system scenario; on the other hand, after completing the virtual-real mapping, through the... The accuracy of the digital twin model is quantified through simulation to ensure that the initial digital twin model meets the preset accuracy conditions and improves 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 hoisting system and explore the changes in equipment status under different working conditions, which facilitates the guidance of subsequent work. On the other hand, the drilling rig hoisting system is digitized based on digital twin technology, and the model is updated according to the process conditions. Then, the drilling rig hoisting system is digitally twin-modeled to achieve optimized management of the drilling rig hoisting system based on the digital twin model.

[0102] As can be seen from the foregoing embodiments, the method of this application can comprehensively evaluate and verify the initial digital twin model from multiple aspects when evaluating and verifying it based on preset model indicators, so as to simulate the scenario of the target drilling rig hoisting system to the greatest extent. Therefore, this embodiment provides a detailed explanation of how to evaluate and verify the initial digital twin model. See [link to documentation]. Figure 3 As shown in the figure, this invention discloses a digital method for drilling rig hoisting systems based on digital twins, including:

[0103] Step S21: Construct 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.

[0104] Step S22: Obtain equipment information data and real-time monitoring data of the physical equipment in the target drilling rig hoisting system according to the preset data acquisition strategy, and perform virtual-real mapping of the digital twin model based on the equipment information data.

[0105] Step S23: 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 to quantify the model accuracy of the digital twin model according to the obtained simulation effect, so as to obtain an initial digital twin model whose model accuracy meets the preset accuracy conditions.

[0106] Step S24: Perform joint simulation using the preset process identification model and the initial digital twin model, 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; the process identification model is a model built on the basis of 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 initial digital twin model, including real-time performance, dynamic response, and scalability, are evaluated and verified. The allowable error range is determined based on the current process of the target drilling rig hoisting system. It is understood that to improve the model's performance indicators, this embodiment can employ efficient data transmission technology, complex data processing algorithms, and high-quality data management strategies. The organic combination of these elements ensures the model's real-time performance. Regarding dynamic response, an ideal digital twin model needs to reflect system state changes in real time and provide dynamic feedback. Furthermore, dynamic response also involves the model's adaptive capability; the model can automatically adjust its parameters and predictions in response to changes in real-time data. In addition, given that the drilling rig hoisting system involves multiple devices, multiple domains, multiple data sets, and multiple operating conditions, the scalability of the digital twin model is reflected in its flexible architecture design. Modular modeling methods allow for additions or replacements as needed, ensuring continuous expansion and improvement of the initial model in constantly changing environments and requirements. In this way, this embodiment verifies and evaluates the model's performance and responsiveness by calculating the model's real-time performance, dynamic response, and scalability. At the same time, it adjusts the allowable error range according to different process procedures to improve the reference value of the model's verification and evaluation.

[0109] Step S26: Analyze the parameters in the initial digital twin model to determine the parameter characteristics corresponding to each parameter, and determine the error analysis method according to the parameter characteristics. Use the error analysis method to perform error analysis on the corresponding parameters, and evaluate and verify the accuracy of the initial digital twin model based on the error allowable range, so as to 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 parameter. Based on these parameter characteristics, a corresponding error analysis method is determined. This error analysis method is then used to perform error analysis on the corresponding parameters. The accuracy of the initial digital twin model is evaluated and verified based on the allowable error range, resulting in a target digital twin model whose overall performance meets preset performance conditions. That is, different error analysis methods are selected for different parameter characteristics. Figure 4 The diagram shown is a comparison of the displacement of the large hook during the tripping process provided in this application. Figure 5 The diagram illustrates the absolute error of the hook displacement during the drilling process provided in this application. For example, this embodiment can utilize the absolute error to perform error analysis on the more intuitive key parameters in the initial digital twin model. For outliers in the model that are difficult to analyze using simple algorithms, mean square error is used for error analysis. Based on the allowable error range, the accuracy of the initial digital twin model is evaluated and verified, resulting in a target digital twin model whose overall performance meets preset performance conditions. The formula for expressing the absolute error is as follows:

[0111] ;

[0112] in, This represents the calculated value from the model. This represents the actual measured value. The formula for expressing the mean square error is as follows:

[0113] ;

[0114] in, These are actual measured values. Here, n represents the number of data points, and the mean squared error and absolute error are compared with the determined allowable error range to determine whether the overall performance of the initial digital twin model meets the preset performance conditions. It is understood that, 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 both theoretical and experimental perspectives. When the overall performance of the initial digital twin model fails to meet the preset performance conditions, this embodiment can optimize the initial digital twin model using the above methods until the overall performance of the initial digital twin model meets the preset performance conditions. In this way, this embodiment verifies and evaluates the digital twin model in terms of real-time performance, accuracy, dynamic response, and scalability to ensure that a target digital twin model with overall performance meeting the preset performance conditions is obtained. Furthermore, when calculating the accuracy of the model, different errors are selected for calculation based on different data types, improving the reliability of the evaluation and verification.

[0115] As can be seen from the above, the embodiments of this application first construct a digital twin model of the target drilling rig hoisting system using a preset modeling method, and perform 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 real-time monitoring data, and the digital twin model is simulated based on the simulation data. An initial digital twin model is obtained by quantifying the model accuracy. A 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. The initial digital twin model is dynamically updated according to the automatic update strategy, and the initial digital twin model is evaluated and verified based on model indicators such as real-time performance, 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 to calculate the accuracy, so as to obtain the target digital twin model. In this way, through the above process of the embodiments of this application, on the one hand, the performance and responsiveness of the model are verified and evaluated by calculating the real-time performance, dynamic response and scalability of the model, and the allowable error range is adjusted according to different process, so as to improve the reference value of the model verification and evaluation; on the other 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; and 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, so as to simulate the scenario of the target drilling rig hoisting system to the greatest extent.

[0116] Accordingly, see Figure 6As shown in the illustration, this application also provides a digital device for a drilling rig hoisting system based on digital twins, comprising:

[0117] The model building module 11 is 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.

[0118] The virtual-real mapping module 12 is used to acquire equipment information data and real-time monitoring data of the physical equipment in the target drilling rig hoisting system according to a preset data acquisition strategy, and to perform virtual-real mapping of the digital twin model based on the equipment information data.

[0119] The 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 to 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 conditions.

[0120] The strategy formulation module 14 is used to perform joint simulation with the initial digital twin model using a preset process identification model, 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 preset performance conditions; the process identification model is a model built on the basis of a preset hybrid automaton.

[0121] As can be seen from the above, the embodiments of this application first construct a digital twin model of the target drilling rig hoisting system using a preset modeling method, and then perform a virtual-real mapping of the digital twin model according to a preset data acquisition strategy. After the virtual-real mapping is completed, simulation data of the digital twin model is determined based on real-time monitoring data, and the digital twin model is simulated based on the simulation data. An initial digital twin model is obtained by quantifying the model's accuracy. A preset process identification model is then used to perform joint simulation with the initial digital twin model, and a corresponding automated update strategy is formulated based on the obtained simulation results. The initial digital twin model is dynamically updated according to the automated update strategy, and the initial digital twin model is evaluated and verified based on preset model indicators to obtain the target digital twin model. In this way, through the above process of the embodiments of this application, the drilling rig hoisting system is digitized based on digital twin technology, and the model is updated according to process conditions, thereby performing 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.

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

[0123] The information determination unit is used to analyze the structural composition, motion characteristics and structural features of the target drilling rig hoisting system in order to determine the subsystem set, structural characteristics and operating parameters of the target drilling rig hoisting system, and to determine the modeling requirements information and system data information of the target drilling rig hoisting system.

[0124] The first model construction unit is used to determine the coupling information between each subsystem in the subsystem set according to the structural characteristics and the subsystem set, and to construct the mechanism model in the digital twin model based on the subsystem set, the coupling information and the operating parameters;

[0125] The second model building unit is used to preprocess the pre-collected data related to the operating parameters to obtain processed data, and to 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 in order to build the knowledge model in the digital twin model.

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

[0128] The experimental testing unit is used to preprocess the equipment information data and perform theoretical analysis and experimental testing on the target drilling rig hoisting system based on the processed equipment information data, so as to determine the component parameters in the digital twin model.

[0129] The 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 embodiments, the digital twin-based drilling rig hoisting system digitization device may further include:

[0131] A set establishment unit is used to divide the different processes of the target drilling rig hoisting system into a preset number of continuous state spaces, and to establish a set of system variable parameters using the real-time monitoring data and the simulation data;

[0132] The condition determination unit is 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 to determine the transition conditions between each state space; each state space includes the continuous state space and the initial state space.

[0133] The structural layering unit is used to establish the preset hybrid automaton based on the migration conditions, the system variable parameter set, and the state spaces, and to layer the structure of the preset hybrid automaton to obtain the process identification model.

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

[0135] The model-driven unit is used to drive a preset process identification model using the real-time monitoring data to identify the process of the current target drilling rig hoisting system, obtain relevant information of the current process, and determine the input value of the initial digital twin model based on the relevant information.

[0136] The model update unit is used to drive the initial digital twin model based on the input value, and to set the trigger conditions for the automatic update of the current process according to the obtained output results 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 trigger conditions, or when the process changes, the initial digital twin model is updated using a preset update method.

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

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

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

[0140] The range determination unit is used to determine the allowable error range based on the current process of the target drilling rig hoisting system.

[0141] The parameter analysis unit is used to analyze the parameters in the initial digital twin model to determine the parameter characteristics corresponding to each parameter.

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

[0143] Furthermore, embodiments of this application also disclose an electronic device, Figure 7 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope 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. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the digital twin-based drilling rig hoisting system digitization method disclosed in any of the foregoing embodiments. Furthermore, 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 operating 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 external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire 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, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

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

[0147] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed digital twin-based digitization method for drilling rig hoisting systems. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0148] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0149] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0150] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0151] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0152] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A digital drilling rig hoist system method based on digital twinning, characterized by, The method comprises the following steps: constructing a digital twin model of a target drilling rig hoisting system by using a preset modeling method; the digital twin model comprises a mechanism model, a data model, and a knowledge model; acquiring equipment information data and real-time monitoring data of entity equipment in the target drilling rig hoisting system according to a preset data acquisition strategy, and performing virtual-real mapping of the digital twin model according to the equipment information data; after the virtual-real mapping is completed, determining simulation data of the digital twin model based on the real-time monitoring data, and simulating the digital twin model based on the simulation data to quantize model precision of the digital twin model according to a simulation effect obtained, so as to obtain an initial digital twin model whose model precision meets a preset precision condition; performing joint simulation of a preset process identification model and the initial digital twin model, and formulating an automatic updating strategy of the initial digital twin model for different processes based on simulation results obtained under different processes, so as to dynamically update the initial digital twin model according to the automatic updating strategy, and evaluate and verify the initial digital twin model based on a preset model index, so as to obtain a target digital twin model whose comprehensive performance meets a preset performance condition; the process identification model is a model established based on a preset hybrid automaton, and is used for identifying a process of the target drilling rig hoisting system; the process comprises top drive ascending in a state of not clamping a drill string, top drive center pipe and drill string joint make-up in a state of clamping a drill string, top drive rotating drilling in a state of clamping a drill string, and top drive center pipe and drill string joint make-up; transition conditions between state spaces of the preset hybrid automaton are constituted by a plurality of related parameters which are obviously affected by drilling rig working condition changes, including hook displacement, motor speed, top drive speed, vertical distance of top drive ascending and lowering, bottom hole drilling pressure, time parameter, and equipment Boolean parameter; wherein, the joint simulation of the preset process identification model and the initial digital twin model, and the formulation of the automatic updating strategy of the initial digital twin model for different processes based on simulation results obtained under different processes, so as to dynamically update the initial digital twin model according to the automatic updating strategy, comprises: driving the preset process identification model by using the real-time monitoring data to identify the process of the target drilling rig hoisting system, obtaining related information of the current process, and determining input values of the initial digital twin model according to the related information; driving the initial digital twin model based on the input values to set a triggering condition of automatic updating of the current process according to obtained output results and a change trend of the real-time monitoring data, so as to update the initial digital twin model by using a preset updating mode when a prediction error of the initial digital twin model or a change trend of equipment parameters meets the triggering condition, or the process changes.

2. The digital twin-based rig hoist system digitization method of claim 1, wherein, The method comprises the following steps: analyzing the structure composition, motion characteristics and structural features of the target drilling hoisting system to determine the subsystem set, structural features and operating parameters of the target drilling hoisting system, and determining the modeling requirement information and system data information of the target drilling hoisting system; determining the coupling information between each subsystem in the subsystem set according to the structural features and the subsystem set, and constructing the mechanism model in the digital twin model based on the subsystem set, the coupling information and the operating parameters; preprocessing the data related to the operating parameters collected in advance 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; mining the system data information based on a preset machine learning algorithm to construct the knowledge model in the digital twin model.

3. The digital twin-based rig hoist system digitization method of claim 1, wherein, The virtual-real mapping of the digital twin model based on the equipment information data comprises the following steps: preprocessing the equipment information data, and performing theoretical analysis and experimental testing on the target drilling hoisting system based on the processed equipment information data to determine the component parameters in the digital twin model; interacting between the component parameters and the equipment information data through a preset interface to obtain the digital twin model consistent with the actual performance.

4. The digital twin-based rig hoist system digitization method of claim 1, wherein, Before the joint simulation of the initial digital twin model and the preset process recognition model, the method further comprises the following steps: dividing the different processes of the target drilling hoisting system into a preset number of continuous state spaces, and establishing a system variable parameter set using the real-time monitoring data and the simulation data; setting the initial state space of the process recognition model according to the actual situation of the target drilling hoisting system, and determining the transition conditions between the state spaces; the state spaces include the continuous state spaces and the initial state space; establishing the preset hybrid automaton based on the transition conditions, the system variable parameter set and the state spaces, and layering the structure of the preset hybrid automaton to obtain the process recognition model.

5. The digital twin-based rig hoist system digitization method of claim 1, wherein, The method for updating the initial digital twin model using a preset updating method comprises the following steps: determining the uncertainty parameters and experimental data corresponding to the current process according to the related information; updating the uncertainty parameters and experimental data using Bayesian inference and variational inference to update the initial digital twin model in combination with the real-time monitoring data.

6. The digital twin-based rig hoist system digitization method according to any one of claims 1 to 5, characterized in that, The method for evaluating and verifying the initial digital twin model based on a preset model index comprises the following steps: evaluating and verifying the real-time performance, dynamic response and scalability of the initial digital twin model; determining the error allowable range according to the current process of the target drilling hoisting system; analyzing the parameters in the initial digital twin model to determine the respective parameter characteristics of the parameters; According to the parameter characteristics, a respective error analysis mode is determined, and error analysis is performed on the corresponding parameters using the error analysis mode to evaluate and verify the accuracy of the initial digital twin model based on the error allowable range.

7. A rig hoist system digitizer based on digital twinning, characterized by, Comprise: The model construction module is used for constructing the digital twin model of the target drilling hoisting system by using a preset modeling method. The digital twin model comprises a mechanism model, a data model, and a knowledge model. The virtual-real mapping module is configured to obtain equipment information data and real-time monitoring data of entity equipment in the target drilling hoisting system according to a preset data acquisition strategy, and perform virtual-real mapping of the digital twin model according to the equipment information data. The model simulation module is configured to determine simulation data of the digital twin model based on the real-time monitoring data after the virtual-real mapping is completed, simulate the digital twin model based on the simulation data, and quantify the model precision of the digital twin model according to the obtained simulation effect to obtain an initial digital twin model that meets a preset precision condition. The strategy formulation module is configured to perform joint simulation of a preset process identification model and the initial digital twin model, formulate an automatic update strategy for the initial digital twin model for different process procedures based on the obtained simulation results under different process procedures, dynamically update the initial digital twin model according to the automatic update strategy, evaluate and verify the initial digital twin model based on a preset model index, and obtain a target digital twin model that meets a preset performance condition. The process identification model is a model established based on a preset hybrid automaton, which is used to identify the process of the target drilling hoisting system. The process comprises top drive ascending in a state of not clamping a drill, top drive center pipe and drill pipe joint make-up in a state of clamping a drill, top drive rotating drilling in a state of clamping a drill, and top drive center pipe and drill pipe make-up. The transition conditions between state spaces of the preset hybrid automaton are constituted by a plurality of related parameters that are obviously affected by drilling conditions, including hook displacement, motor speed, top drive speed, vertical distance of top drive ascending and lowering, bottom hole pressure, time parameter, and equipment Boolean parameter. The strategy formulation module comprises: The model driving unit is configured to drive the preset process identification model using the real-time monitoring data to identify the process of the target drilling hoisting system, obtain related information of the current process, and determine input values of the initial digital twin model according to the related information. A model updating unit is configured to drive the initial digital twin model based on the input value, to set a trigger condition for automatic updating of the current process based on a change trend of the output result and 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 the process changes, the initial digital twin model is updated by using a preset updating mode.

8. An electronic device, comprising: Comprise: a memory for storing a computer program; a processor for executing the computer program to implement the digital twin-based drilling rig hoisting system digitization method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, for storing a computer program; wherein the computer program is executed by a processor to implement the digital twin-based drilling rig hoisting system digitization method of any one of claims 1 to 6.

Images