A drilling simulation system and method based on a desert scene

Abstract

This application provides a drilling simulation system and method based on a desert scenario. The system establishes a data-driven relationship between environmental parameters and equipment performance models through a coupling processing module. This allows dynamic environmental data to influence the values ​​of virtual equipment performance parameters through mathematical rules, thereby simulating the continuous impact of the environment on equipment status. Addressing the issue that macroscopic environmental simulation output data cannot be used for real-time operational simulation, the data generated by the environmental simulation module is real-time and can be directly used as calculation input for the coupling processing module and the effect simulation module, achieving compatibility with operational simulation. Furthermore, through equipment performance status, the environmental impact is simultaneously transmitted to the physical interaction level and the operational decision-making level. This transforms environmental factors from isolated external conditions into core variables that drive the simulation process and shape training difficulty. Therefore, it can significantly improve the simulation effect of drilling operations in extreme desert environments.

Description

Technical Field

[0001] This application relates to the field of drilling simulation technology, and in particular to a drilling simulation system and method based on a desert scenario. Background Technology

[0002] Drilling operation simulation replicates actual operation processes in a virtual environment and is configured for process testing and risk assessment. Desert regions are characterized by soft terrain, frequent sandstorms, and significant temperature variations, directly impacting equipment stability and operational safety. Therefore, a simulation solution capable of reflecting the interaction between the desert environment and the drilling system is needed to predict and address complex on-site conditions.

[0003] In the field of drilling simulation, one approach employs high-fidelity process flow simulation. Such systems meticulously reproduce the drilling process logic and internal equipment state control, but the environment in their 3D scenes is merely a visual background. Another approach uses macro-environmental evolution simulation, which couples multiple driving factors such as climate and economy and is configured to predict long-term desertification trends at the regional scale. These two approaches serve different professional objectives.

[0004] High-fidelity process simulations fail to establish a real-time data-driven relationship between environmental parameters and equipment performance models, making it impossible to simulate the continuous impact of the environment on equipment status. Furthermore, the output data from macro-environmental simulations is incompatible with real-time operation simulations in terms of granularity and timeliness. In summary, neither of these approaches achieves the coupling of dynamic environmental factors with the operating logic of drilling equipment, resulting in poor drilling simulation performance in desert environments. Summary of the Invention

[0005] This application provides a drilling simulation system and method based on a desert scenario to solve the problem of poor drilling simulation performance in desert environments.

[0006] In a first aspect, this application provides a drilling simulation system based on a desert scenario, comprising: The environmental simulation module is configured to generate dynamic environmental data for the target desert region; The equipment model library includes at least one drilling equipment model, which has preset environmental sensitivity performance parameters that change according to the dynamic environmental data. The coupling processing module is configured to convert the environmental dynamic data into adjustment amounts for the environmental sensitivity parameters according to predefined mapping rules, so as to output the device performance status. The effect simulation module is configured to simulate the target parameters of the drilling equipment model in the corresponding environment based on the environmental dynamic data and equipment performance status. The target parameters include at least sinking resistance and / or drilling resistance. The operation management module is configured to adjust the operation process or rules associated with the drilling equipment model based on the performance status of the equipment.

[0007] In some feasible embodiments, the environmental sensitivity performance parameter includes at least one health state variable, which is used to characterize the degree of cumulative performance degradation of the drilling equipment model; The coupling processing module is specifically configured to: determine the instantaneous rate of change of the health status variable based on the environmental dynamic data; update the current value of the health status variable based on the instantaneous rate of change, so as to output the cumulative performance degradation degree.

[0008] By determining the instantaneous rate of change of health status variables based on dynamic environmental data and updating the current value, the cumulative performance degradation of equipment can be accurately simulated, thereby enhancing the realism of the simulation.

[0009] In some feasible embodiments, the coupling processing module further includes a parameter estimation model; The device performance status includes performance parameters; The coupling processing module is specifically configured to: adjust at least one parameter in the predefined mapping rules based on the state data generated during the simulation operation, using the parameter estimation model; and use the adjusted parameters to perform the conversion of environmental dynamic data into performance parameters.

[0010] By using a parameter estimation model to adjust the mapping rule parameters based on simulation state data, the dynamic environmental data can be adaptively converted into performance parameters, thereby improving simulation accuracy.

[0011] In some feasible embodiments, the predefined mapping rules include fault trees and probability sampling models; The device performance status includes the triggering status of virtual faults, which is a status identifier used to characterize whether a virtual fault event is determined to have occurred. The coupling processing module is specifically configured to: determine the probability of occurrence of a virtual fault event based on the environmental dynamic data through the fault tree and probability sampling model; perform random sampling based on the probability of occurrence to determine whether the virtual fault event is triggered; and output the corresponding triggering state if the virtual fault event is triggered.

[0012] By using fault tree and probability sampling models to randomly determine the virtual fault triggering state based on dynamic environmental data, the randomness of fault occurrence is simulated, enriching the uncertainty of the simulation scenario.

[0013] In some feasible embodiments, when the equipment model library contains multiple drilling equipment models, the predefined mapping rules include a dynamic resource contention model; The device performance status includes the actual performance status; The coupling processing module is configured as follows: Based on the environmental dynamic data, virtual resource requests are generated for each of the drilling equipment models. The dynamic resource contention model is used to competitively schedule and allocate multiple virtual resource requests to obtain virtual resource results. Based on the virtual resource results, determine the corresponding actual performance status.

[0014] In multi-device scenarios, virtual resource requests are generated based on dynamic environmental data. Resources are allocated and the actual performance status is determined through a dynamic resource contention model, thus reproducing the constraints of resource contention on device performance.

[0015] In some feasible embodiments, the environment simulation module includes an environment parameter constraint network and an environment state machine, wherein the environment state machine is pre-set with state transition conditions; The environmental parameter constraint network is used to acquire environmental parameters and determine the environmental dynamic data based on the physical dependencies between multiple environmental parameters. The environmental state machine is pre-set with state transition conditions, which are used to drive the switching between multiple preset environmental states based on the environmental dynamic data. The environmental states include at least the sandstorm development state, the sandstorm activity state, and the environmental dissipation state.

[0016] The environmental parameter constraint network determines the environmental dynamic data based on physical dependencies, and the environmental state machine switches the environmental state according to the transition conditions to generate high-fidelity environmental dynamic data.

[0017] In some feasible embodiments, the environmental dynamic data includes at least climate parameters, surface parameters, and event parameters; the equipment performance status includes at least performance parameters, the triggering status of virtual faults, the actual performance status, as well as lateral forces and wind-affected structures; the target parameters also include sideslip resistance and wind load sway resistance. The effect simulation module is specifically configured as follows: Based on the surface parameters and performance parameters, the subsidence resistance is calculated using a sand and soil bearing capacity model. Based on the surface parameters and the actual performance state, the drilling resistance is calculated using a shear stress-displacement relationship model. Based on the surface parameters and the lateral forces, the sideslip resistance is calculated using a friction model. Based on the climate parameters, the wind-receiving structure, and the triggering state of the virtual fault, the wind load sway resistance is calculated using a wind vibration response model.

[0018] Based on surface parameters and performance parameters, actual performance status, lateral forces and climate parameters, wind-exposed structure, and virtual fault triggering state, the sinking resistance, drilling resistance, sideslip resistance, and wind load swing resistance are calculated through corresponding mechanical models to comprehensively simulate the forces acting on equipment in desert conditions.

[0019] In some feasible embodiments, the operation management module is configured to: compare the equipment performance status with at least two preset condition thresholds, and adjust the operation process or rules associated with the drilling equipment model according to the comparison results; wherein, when the equipment performance status is lower than a first performance threshold, a virtual warning message is triggered; when the equipment performance status is lower than a second performance threshold, a predefined emergency operation procedure is started and executed; the second performance threshold is different from the first performance threshold.

[0020] The device performance status is compared with preset first and second performance thresholds. If it is lower than the first threshold, a virtual warning message is triggered. If it is lower than the second threshold, an emergency operation procedure is initiated, thus realizing a graded response to device performance degradation.

[0021] Secondly, this application provides a drilling simulation method based on a desert scenario, including: The environmental simulation module generates dynamic environmental data for the target desert area. Environmental sensitivity parameters are obtained through an equipment model library, which includes at least one drilling equipment model. The drilling equipment model has preset environmental sensitivity parameters, which change according to the environmental dynamic data. The coupling processing module converts the environmental dynamic data into adjustment amounts for the environmental sensitivity parameters according to predefined mapping rules, so as to output the device performance status. The effect simulation module simulates the target parameters of the drilling equipment model in the corresponding environment based on the environmental dynamic data and equipment performance status. The target parameters include at least sinking resistance and / or drilling resistance. The operation management module adjusts the operation process or rules associated with the drilling equipment model based on the equipment performance status.

[0022] As can be seen from the above technical solutions, this application provides a drilling simulation system and method based on a desert scenario, comprising: an environment simulation module configured to generate dynamic environmental data of a target desert area; an equipment model library including at least one drilling equipment model, wherein the drilling equipment model has preset environmental sensitivity performance parameters, which change according to the dynamic environmental data; a coupling processing module configured to convert the dynamic environmental data into adjustment amounts for the environmental sensitivity performance parameters according to predefined mapping rules, so as to output the equipment performance status; an effect simulation module configured to simulate the target parameters of the drilling equipment model in the corresponding environment based on the dynamic environmental data and the equipment performance status, wherein the target parameters include at least sinking resistance and / or drilling resistance; and an operation management module configured to adjust the operation process or rules associated with the drilling equipment model according to the equipment performance status.

[0023] Dynamic environmental data is generated by the environmental simulation module, and then converted into adjustment values ​​for the environmental sensitivity parameters of the equipment by the coupling processing module, and the equipment performance status is output. This enables environmental changes to drive the equipment status and operation process in real time, thereby achieving the coupling of dynamic environment and drilling operation logic. Attached Figure Description

[0024] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A schematic diagram of the structure of a drilling simulation system based on a desert scene provided in an embodiment of this application; Figure 2 This is a schematic diagram of the coupling processing module provided in an embodiment of this application; Figure 3 A schematic diagram of the competition strategy provided in the embodiments of this application; Figure 4 A schematic diagram of the target parameters provided in the embodiments of this application; Figure 5 This is a schematic diagram of the execution flow of the job management module provided in an embodiment of this application. Detailed Implementation

[0026] The embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following examples do not represent all embodiments consistent with this application.

[0027] This application provides a drilling simulation system based on a desert scenario in some embodiments, such as... Figure 1 As shown, it includes: an environment simulation module, an equipment model library, a coupling processing module, an effect simulation module, and a job management module.

[0028] The environment simulation module is configured to generate dynamic environmental data for the target desert area. The environment simulation module is a software or hardware functional unit used to reproduce the dynamic natural conditions of the desert area in a virtual environment and generate environmental data that changes over time.

[0029] The environmental simulation module can be implemented based on different technical principles. In one implementation, the module includes a parametric meteorological and geographical model library with built-in mathematical relationships characterizing desert features, such as empirical functions for wind speed and dust storm volume, sine curves for diurnal temperature variation, and water balance models for surface humidity as a function of virtual rainfall and evaporation. By calling these models and inputting geographical location and time parameters, the environmental simulation module calculates continuously changing dynamic environmental data.

[0030] In another implementation, the environmental simulation module uses a physics-based process simulation method and a simplified wind field model based on computational fluid dynamics principles to simulate dust transport and diffusion, generating a three-dimensionally unevenly distributed dust concentration field.

[0031] Regardless of the implementation method used, the environment simulation module breaks away from static backgrounds or preset scripts and generates a sequence of physically meaningful and quantifiable environmental parameters, i.e., dynamic environmental data.

[0032] Environmental dynamic data is used to quantitatively describe the physical environmental state of the target desert area at the time of simulation. Environmental dynamic data includes at least key parameters related to equipment operation and physical interaction. For example, this data may include climate parameters characterizing air conditions, such as instantaneous wind speed, wind direction, dust concentration, and ambient temperature; and parameters characterizing surface conditions, such as surface bearing capacity, surface slope, and soil moisture content at a specific location. Furthermore, when the environmental simulation module simulates a specific climate event, the environmental dynamic data also includes comprehensive indices characterizing the intensity or stage of that event, such as dust storm level or heat wave duration.

[0033] In some embodiments, when the environmental simulation module simulates a specific climate event, the generated environmental dynamic data includes indices characterizing the overall intensity or development stage of the event. These indices are composite indicators, obtained by weighting, combining, or mapping multiple basic environmental parameters according to specific rules, and are used to provide signals for judging the current environmental severity to drive logical responses.

[0034] For example, when simulating a sandstorm event, the environmental simulation module outputs basic data such as wind speed, wind direction, and dust concentration, while simultaneously calculating and outputting a sandstorm level index. The index is defined digitally according to meteorological standards for classifying sandstorm weather levels; for instance, index values ​​are defined as integers from level one to five, with level one corresponding to blowing dust and level five corresponding to an extremely severe sandstorm. The threshold for each level is set based on a combination of wind speed and visibility, with visibility calculated from dust concentration. When the sustained wind speed reaches the first threshold and the minute-average dust concentration exceeds the second threshold, the index is upgraded from level two to level three.

[0035] During operation, the environmental simulation module continuously compares wind speed and dust concentration data with preset thresholds, updates and outputs a dust storm level index. This index, as dynamic environmental data, is read by the operation management module. The operation management module has preset rules: when the index reaches level three, it issues an orange dust storm warning on the virtual operation interface and prompts the initiation of windproof reinforcement procedures; when the index reaches level four, it interrupts the outdoor high-altitude operation process and locks the operation permissions of relevant equipment.

[0036] The comprehensive index enables the environmental simulation module to output physical parameters and environmental state information, which are used for subsequent module decisions and responses to achieve logical judgment in the simulation system.

[0037] After the system starts, the environmental simulation module runs its internal model based on the basic geographic and meteorological parameters of the target desert area. The model includes logic to describe events such as wind speed changes, dust generation and diffusion, diurnal temperature fluctuations, and dust storms or heat waves.

[0038] The environment simulation module does not play a preset weather animation, but rather continuously outputs a series of dynamic environmental data that changes over time based on approximate calculations using physical laws or empirical models.

[0039] For example, when simulating a sunny afternoon, the module may output data on low wind speed, moderate temperature, and extremely low dust concentration. At this time, climate parameters include, but are not limited to, wind speed, wind direction, ambient temperature, and relative humidity; surface parameters include, but are not limited to, surface temperature, surface reflectance, and uniform surface bearing capacity determined based on the default sand type. Due to the sunny weather, the module may not output specific event parameters or may maintain the dust storm level index at level zero, indicating no dust weather.

[0040] When simulating dust storm formation, the module increases the output values ​​of wind speed and dust concentration, and changes the wind direction. In addition to climate parameters and surface parameters, it calculates and outputs event parameters in parallel, such as the dust storm intensity index. All three together serve as dynamic environmental data.

[0041] In some embodiments, the environment simulation module includes an environment parameter constraint network and an environment state machine, wherein the environment state machine is pre-set with state transition conditions; The environmental parameter constraint network is used to acquire environmental parameters and determine the environmental dynamic data based on the physical dependencies between multiple environmental parameters. The environmental state machine is pre-set with state transition conditions, which are used to drive the switching between multiple preset environmental states based on the environmental dynamic data. The environmental states include at least the sandstorm development state, the sandstorm activity state, and the environmental dissipation state.

[0042] Environmental parameter constraint networks are used to handle the physical dependencies between multiple fundamental environmental parameters. These fundamental environmental parameters include initial temperature, humidity, wind speed, and solar radiation intensity. This network is a computational framework embedded with physical rules to constrain the relationships between parameter changes. For example, when the network receives inputs of increased wind speed and humidity, it calculates intermediate environmental data indicating a decrease in temperature based on the principle of evaporative cooling, rather than allowing the parameters to change independently and contradictorily.

[0043] An environmental state machine is used to manage the evolution of desert environmental conditions. The state machine pre-defines multiple preset environmental states, such as dust storm development, dust storm activity, and environmental dissipation. Each state is associated with dynamic environmental behavior patterns and parameter change trends. Internally, the state machine defines state transition conditions, which are determined based on intermediate environmental data output from the environmental parameter constraint network.

[0044] During operation, the environment simulation module first obtains a set of basic environmental parameters from external inputs or built-in models. The environmental parameter constraint network performs deduction and equilibrium calculations based on these parameters and their physical relationships, outputting logically consistent intermediate environmental data. This data is then input into the environment state machine.

[0045] The environmental state machine compares intermediate environmental data with state transition conditions. When specific conditions are met, such as wind speed consistently exceeding a threshold and particulate matter concentration rising at a certain rate in the intermediate environmental data, the state machine switches from the current state to the next state, for example, from a clear state to a sandstorm development state. The environmental simulation module integrates the current state identifier of the environmental state machine with intermediate environmental data to generate dynamic environmental data.

[0046] The combination of environmental parameter constraint networks and environmental state machines enhances the physical realism and logical consistency of environmental simulations. Environmental parameter constraint networks constrain the rationality and consistency of micro-parameter changes, preventing parameter combinations from violating physical laws. Environmental state machines are used to perform macro-level stage division and state management of environmental evolution, enabling environmental changes to exhibit evolutionary stages and patterns. This addresses the problems of isolated environmental parameter settings and a lack of overall evolutionary logic in traditional simulations, providing dynamic environmental data input for coupled processing. This ensures that equipment performance simulations are based on a physically consistent and stage-specific environmental context, thereby enhancing the credibility and training value of the simulation system.

[0047] While simulating the environment, the system loads an equipment model library. This library includes at least one drilling equipment model. These models are digital abstractions of real drilling equipment, including drilling rigs, generators, mud pumps, and transport vehicles.

[0048] The equipment model library contains 3D rendered geometric meshes and texture information, as well as logical attributes that define the equipment's functions and behaviors. Models are the fundamental objects for interactive operations, state calculations, and process simulations in the simulation system. The equipment model library is built using 3D modeling software and then imported into a game engine or simulation platform. The complexity of the models is adjusted according to the simulation fidelity requirements, including simplified solid models or detailed models containing moving parts and subsystems.

[0049] See Figure 2 The drilling rig model has preset environmental sensitivity performance parameters. These parameters change based on dynamic environmental data. They connect environmental conditions with the internal state of the equipment. In some embodiments, the environmental sensitivity performance parameters include at least one health state variable. This health state variable characterizes the cumulative performance degradation of the drilling rig model.

[0050] The coupling processing module is specifically configured to: determine the instantaneous rate of change of the health status variable based on the dynamic environmental data; update the current value of the health status variable based on the instantaneous rate of change, and output the cumulative performance degradation level.

[0051] Among them, health status variables are numerical parameters preset within the drilling equipment model, used to quantify the gradual and irreversible performance losses caused by long-term environmental exposure. For example, the environmentally sensitive performance parameters of the diesel generator model include the intake efficiency coefficient, which is related to the concentration of dust in the air; the environmentally sensitive performance parameters of the hydraulic tongs model include the sealing friction coefficient, which changes with ambient temperature; and the diesel engine model has a filter clogging variable, which increases with the accumulation of dust concentration. During simulation, the coupled processing module adjusts the parameter values ​​based on dynamic environmental data.

[0052] The updated health status variable values ​​characterize the degree of cumulative performance degradation and serve as a component of the equipment's performance status. The degree of cumulative performance degradation is directly expressed by the current value of the health status variable and describes the level of performance baseline decline caused by historical environmental factors. For example, a filter clogging level of 0.5 indicates a cumulative 50% reduction in intake capacity due to fouling.

[0053] The coupling processing module performs calculations for each health state variable. Within each simulation step, the module calculates the instantaneous rate of change of the variable based on the current environmental dynamic data and a predefined damage rate function. For example, based on the dust concentration value, the theoretical growth rate of filter clogging within the current second is calculated proportionally. The module multiplies the instantaneous rate of change by the simulation time step to obtain the damage increment within the current step, and then adds it to the value stored in the health state variable from the previous moment, thus updating the current value of the variable. This process continues, causing the variable value to accumulate integrally with time and environmental effects.

[0054] The updated health status variable values ​​are incorporated into the equipment performance status report output. This data is used by subsequent modules to provide long-term equipment health background. The effect simulation module uses this data to correct component performance parameters, such as internal clearances increased due to wear. The operation management module uses this data to assess equipment reliability and triggers virtual maintenance tasks when cumulative degradation exceeds a threshold. This mechanism simulates equipment performance degradation caused by the environment, enabling the equipment status to have memory and persistence, thereby improving the depth of understanding of equipment lifecycle management and maintenance.

[0055] The coupling processing module is configured to convert environmental dynamic data into adjustment amounts for environmentally sensitive performance parameters according to predefined mapping rules, so as to output the device performance status.

[0056] The coupling processing module executes computational logic, establishing a quantitative relationship between dynamic environmental data and environmentally sensitive performance parameters based on predefined rules, thereby enabling environmental influence on equipment. The mapping rules encapsulated within the coupling processing module are used to transform environmental data into adjustment instructions for equipment performance parameters. These mapping rules, acting as dictionaries or function tables, indicate how environmental data affects equipment parameters.

[0057] The coupling processing module receives data from the environment simulation module, accesses the environmental sensitivity parameters of the equipment in the equipment model library, and outputs a description of the current state of the equipment by executing mapping rules. For each active drilling equipment model, the coupling processing module performs queries and calculations according to the mapping rules. The coupling processing module is implemented as a set of script functions, an independent calculation service, or a logical component within the simulation platform.

[0058] For example, the mapping rule stipulates that the intake efficiency coefficient is negatively correlated with the dust concentration, and the relationship is defined by a formula. The coupling processing module substitutes the current dust concentration value into the formula to calculate the new intake efficiency coefficient.

[0059] See Figure 2During the simulation, the parameter estimation model continuously monitors the state data generated during the simulation and then processes the state data. State data is a collection of intermediate data generated by each module of the system within the simulation cycle, reflecting the current simulation status. State data includes historical sequences of environmental dynamic data, intermediate results calculated by the coupled processing module according to mapping rules, and feedback from the physical interaction results of the effect simulation module.

[0060] See Figure 2 In some embodiments, predefined mapping rules include fault trees and probabilistic sampling models. Fault trees are used to define virtual failure events of the drilling equipment model and their logical causal relationships. Probabilistic models are used to quantify the impact of dynamic environmental data on the probability of failure events occurring.

[0061] The device performance status includes the triggering status of virtual faults, which is a status identifier used to characterize whether a virtual fault event is determined to have occurred. The coupling processing module is specifically configured to: determine the probability of virtual fault events based on environmental dynamic data through fault tree and probability sampling model; perform random sampling based on the probability of occurrence to determine whether the virtual fault event is triggered; and output the corresponding trigger status if the virtual fault event is triggered.

[0062] During operation, the coupling processing module acquires dynamic environmental data and inputs it into a pre-built fault tree. Base events or intermediate events in the fault tree are associated with a probability model. The coupling processing module calls the probability model to calculate the probability of virtual fault events based on the environmental data. Then, a trigger determination is performed for each event to be determined. A random number is generated and compared with the probability of occurrence. If the random number is less than or equal to the probability value, the event is determined to be triggered, and the virtual fault trigger state is set to the identified occurrence state. This state is output as the device performance status.

[0063] For example, when environmental dynamic data indicates an increase in dust concentration, the probability model associated with air filter clogging events outputs a higher probability of occurrence. The coupling processing module determines whether a fault is triggered within the simulation step size by comparing random numbers. The triggered fault state is used to simulate the equipment behavior in the effect simulation module.

[0064] By combining fault trees with probabilistic models, randomized and structured simulations of environmentally induced faults are performed. Fault trees provide a framework for describing fault logic, while probabilistic models establish a dynamic quantitative relationship between environmental data and the probability of faults, simulating the random differences in whether faults occur under the same environment, thereby improving the realism and unpredictability of simulation scenarios.

[0065] See Figure 2 In some embodiments, when the equipment model library contains multiple drilling equipment models, the predefined mapping rules include a dynamic resource contention model. The device performance status includes the actual performance status; The coupling processing module is configured as follows: Based on the environmental dynamic data, virtual resource requests are generated for each of the drilling equipment models. The dynamic resource contention model is used to competitively schedule and allocate multiple virtual resource requests to obtain virtual resource results. Based on the virtual resource results, determine the corresponding actual performance status.

[0066] A dynamic resource contention model is introduced to simulate the virtual resource contention behavior of multiple drilling rigs in a desert environment, based on dynamic environmental data, and its impact on rig performance. The dynamic resource contention model defines the rules for coordinating and allocating virtual resource requests from multiple drilling rigs in a resource-constrained virtual environment. A virtual resource request is a demand declaration for a specific virtual resource generated by the drilling rig model based on dynamic environmental data. Actual performance status reflects the rig's performance after resource contention.

[0067] During operation, when the equipment model library contains multiple active drilling equipment models, the coupling processing module executes resource contention logic. Based on dynamic environmental data obtained from the environmental simulation module, the coupling processing module generates virtual resource requests for each drilling equipment model. For example, when environmental data indicates a sharp rise in temperature, each equipment cooling system model generates a virtual resource request for additional cooling power; when sandstorms increase, the precision instrument model generates a virtual resource request for priority access to its protective shield.

[0068] The dynamic resource contention model is then invoked. This model receives concurrent virtual resource requests as input and performs contention adjudication and resource allocation according to a preset scheduling strategy. The scheduling strategy includes device priority, task criticality, or simulated market bidding rules. After processing, the model outputs the virtual resource allocation result. This result characterizes the virtual resource allocation objects and their allocation quantity or level within the simulation cycle.

[0069] The table below lists common drilling equipment models and the types of virtual resources they compete for:

[0070] When the environmental simulation module outputs dynamic environmental data such as continuously rising dust concentration or ambient temperature exceeding a threshold, the aforementioned equipment model will calculate virtual resource requests through the coupling processing module based on its respective mapping rules (such as power demand functions). These requests are then uniformly submitted to the dynamic resource contention model for centralized scheduling.

[0071] See Figure 3The coupling processing module determines the actual performance state of each drilling equipment model based on the allocation results. Equipment models that successfully obtain sufficient resources maintain normal or slightly degraded performance; equipment models that do not obtain resources or only obtain partial resources have their actual performance downgraded to simulate performance degradation caused by resource constraints. This actual performance state is output as the equipment performance state.

[0072] The dynamic resource competition model transforms environmental data into individual resource demands and simulates the resource allocation process through competitive scheduling. This addresses the problems of isolated simulations of multiple devices and the lack of resource interaction and constraints, enabling the simulation system to reproduce the impact of environmental stress on operational efficiency under resource-limited conditions, thus providing a simulation environment that closely resembles reality.

[0073] In some embodiments, the coupling processing module further includes a parameter estimation model; the device performance status includes performance parameters; the coupling processing module is specifically configured to: adjust at least one parameter in the predefined mapping rules based on the state data generated during simulation operation using the parameter estimation model; and use the adjusted parameters to perform the conversion of environmental dynamic data into performance parameters.

[0074] The parameter estimation model is an algorithmic component of the coupled processing module, used to dynamically fine-tune the coefficients or weights in predefined mapping rules based on the state data generated during simulation. The parameter estimation model does not participate in the standard mapping calculation from environmental data to device state; instead, it is used to optimize the accuracy of the mapping process.

[0075] The parameter estimation model incorporates optimization criteria. These criteria compare the equipment state predicted by the mapping rule with the expected state inferred from state data trends. When the accumulated difference indicates a deviation in the mapping rule's response to specific environmental conditions or equipment models, the parameter estimation model initiates an adjustment process. The model uses an internal estimation algorithm to calculate corrections to one or more internal parameters in the predefined mapping rule. For example, these corrections are used to adjust the proportional coefficient in the formula relating dust concentration to filter efficiency degradation.

[0076] In subsequent mapping calculations, the coupling processing module executes transformation logic based on the adjusted parameter values. This transformation logic involves reading current environmental dynamic data, substituting it into the mapping rules, calculating and outputting updated performance parameter values. These updated performance parameter values ​​are then integrated into the device performance status output.

[0077] Parameter estimation models are used to enable adaptive system coupling, allowing the system to learn and closely approximate the characteristics of the virtual well site environment or the individual differences of specific equipment models during operation, rather than always relying on fixed empirical formulas. By dynamically optimizing mapping parameters, the deviation between simulation behavior and preset training objectives or known scenario experience is reduced, thus providing training on equipment responses that closely reflect actual conditions.

[0078] The calculation process is continuous, ensuring that the equipment's environmental sensitivity parameters closely reflect environmental changes. The coupled processing module integrates the adjusted equipment parameters and status information into an equipment performance status report. This report is dynamic and quantifies the equipment's health and capabilities under environmental conditions. For example, the report might indicate that a generator's current available power is 75% of its rated value.

[0079] The equipment performance status report is sent to both the effect simulation module and the job management module simultaneously.

[0080] The effect simulation module is configured to simulate the target parameters of the drilling equipment model in the corresponding environment based on the environmental dynamic data and equipment performance status. The target parameters include at least sinking resistance and / or drilling resistance.

[0081] The simulation module includes a mechanical model specific to desert geology. When calculating vehicle sinking, the module reads the surface bearing capacity parameters at the vehicle's location from dynamic environmental data, and obtains the vehicle's pressure on the ground from equipment performance data. It then calls the sand bearing capacity model to iteratively calculate the ground yield depth, i.e., the sinking depth. This calculation result is converted into the force that compresses the vehicle's suspension or adjusts the vehicle's chassis position to represent the visual effect of tires sinking into the sand in a 3D scene—that is, the specific manifestation of sinking resistance.

[0082] Similarly, for the drilling process, the effect simulation module reads the shear properties of the sand and the operating parameters such as drilling pressure and rotation speed from the equipment performance status, and calculates the real-time resistance of the drill bit through a shear stress-displacement relationship model. This resistance value is used to correct the drill string's forward speed or characterize the additional torque output by the drive motor.

[0083] In some embodiments, the environmental dynamic data includes at least climate parameters, surface parameters, and event parameters; the equipment performance status includes at least performance parameters, virtual fault triggering status, actual performance status, lateral forces, and wind-receiving structures, wherein the wind-receiving structures include the derrick, the second-level platform, and the drill pipe column.

[0084] See Figure 4 The target parameters also include sideslip resistance and wind load sway resistance. The sideslip resistance is the frictional force threshold for the equipment to resist horizontal slippage, and the wind load sway resistance is the equivalent damping force for the structure to resist wind-induced swaying.

[0085] The effect simulation module is specifically configured as follows: Based on the surface parameters and performance parameters, the subsidence resistance is calculated using a sand and soil bearing capacity model. Based on the surface parameters and the actual performance state, the drilling resistance is calculated using a shear stress-displacement relationship model. Based on the surface parameters and the lateral forces, the sideslip resistance is calculated using a friction model. Based on the climate parameters, the wind-receiving structure, and the triggering state of the virtual fault, the wind load sway resistance is calculated using a wind vibration response model.

[0086] The subsidence resistance is calculated using a sand bearing capacity model. This model takes sand type, moisture content, and density from the surface parameters as inputs to the foundation characteristics, and the equipment's self-weight and ground pressure from the performance parameters as inputs to the loads. It outputs the subsidence amount of the equipment on the sandy surface and converts it into subsidence resistance. The reason for using performance parameters, rather than other state variables, as load inputs is that performance parameters directly reflect the current output capacity of the equipment's power system. When the traction force decreases due to aging or deterioration of the equipment, the subsidence depth will increase under the same sandy conditions. The model outputs subsidence resistance by matching the load with the bearing capacity.

[0087] The sand bearing capacity model was implemented using the particle discrete element method (PFC). Indoor geotechnical tests were conducted on sand samples from the target desert region, including sieve analysis, relative density tests, angle of repose tests, lateral confined compression tests, and direct shear tests, to obtain particle size distribution, ultimate density, angle of repose, compression characteristic curves, and shear stress versus normal displacement curves. Numerical specimens of the same size as those tested in the laboratory were constructed in the PFC simulation software. The micro-parameters of the particle contact constitutive model, including particle stiffness, friction coefficient, bond strength, and damping coefficient, were adjusted to ensure consistency between the simulated angle of repose, compression characteristic curves, and direct shear curves and the laboratory test results, thus completing the micro-parameter calibration. The foundation model dimensions were determined based on Prandtl's foundation bearing capacity theory. The length and depth of the foundation fracture zone were calculated based on the foundation width and the internal friction angle of the sand, serving as the minimum size range for the model. During foundation model construction, based on the calibrated micro-parameters, particle size distribution, and relative density, a particle set with a specified porosity was generated in PFC, and the model boundary was simplified using the semi-infinite space assumption. During the load application phase, vertical directional loads are applied to the foundation model in stages. After each load stage, stability is determined based on the average unbalanced force ratio of particles and the displacement convergence rate. The stable settlement is recorded until the displacement diverges, indicating foundation failure. The model outputs load-settlement curves, which are used to convert the subsidence depth under different ground pressure ratios and then convert it into subsidence resistance.

[0088] Drilling resistance is calculated using a shear stress-displacement relationship model. The model uses the internal friction angle and cohesion from the surface parameters as formation strength inputs, and the drill pressure and rotational speed from the actual performance conditions as cutting power inputs, outputting the drilling resistance required for the drill bit to overcome formation resistance. The actual performance conditions are equipment output values ​​corrected by a resource competition model, used to characterize rock-breaking capacity under constrained working conditions. The model simulates the shear failure process of the cutting teeth on sand units, outputting the drilling resistance.

[0089] The shear stress-displacement relationship model is constructed using the Duncan-Chang hyperbolic model framework. The model describes the shear stress and shear displacement at the interface between the drill bit cutting teeth and the sand as a hyperbolic function. Shear stress-shear displacement curves under different normal stresses are obtained through indoor direct shear tests or single-tooth cutting tests. The initial tangential stiffness and ultimate shear stress are fitted to the hyperbola using the least squares method. The model takes the internal friction angle, cohesion, and normal stress from the surface parameters as inputs, calculates the initial tangential stiffness and ultimate shear stress, and then determines the shear stress value corresponding to any shear displacement. In the simulation implementation, the model is encapsulated as a user-defined material subroutine and embedded in an explicit dynamic finite element solver. Within each simulation step, the program calculates the normal stress based on the contact normal force of the cutting teeth, calculates the cumulative shear displacement based on the relative displacement increment of the cutting teeth, outputs the current shear stress through the hyperbolic model, converts it into a tooth surface resistance component, and obtains the instantaneous drilling resistance by integrating it over time and area along the working surface.

[0090] Sideslip resistance is calculated using a friction model. The model takes the internal friction angle and density of the surface parameters as inputs for interfacial friction characteristics, and the lateral force as the real-time horizontal load input. It outputs the maximum static friction threshold force that the equipment can withstand to resist lateral displacement. The lateral force is the lateral thrust generated by the equipment under conditions of slope, turning, or crosswind, and participates in the static friction balance. The model outputs the maximum static friction threshold force, i.e., the sideslip resistance, using Coulomb's law of friction.

[0091] The friction model is based on Coulomb's law of friction, and the numerical implementation utilizes the enhanced Lagrangian method for contact constraint solving. This is configured and implemented in the contact mechanics module of the finite element software. A contact pair is defined between the drilling equipment's grounding component and the sandy soil surface, with the surface as the target surface and the equipment tracks or support structure as the source surface. In the contact properties, the friction type is enabled, and the Coulomb friction model is selected. The static and dynamic friction coefficients are input. The static friction coefficient is converted based on the internal friction angle of the surface parameters, and the dynamic friction coefficient is taken as 80% to 90% of the static friction coefficient. The viscous state option is enabled to simulate adhesion behavior below the friction threshold, avoiding micro-slip oscillations. The enhanced Lagrangian method is selected for the contact algorithm, and the normal contact stiffness factor and penetration tolerance are set to balance computational efficiency and contact constraint accuracy. Within each simulation increment step, the solver calculates the normal contact pressure on the contact surface, multiplies it by the friction coefficient to obtain the critical friction stress, and determines whether the tangential contact stress exceeds the critical value. If the stress is below the critical friction stress, the contact point remains in a viscous state, and the tangential displacement is constrained. If the stress is above the critical friction stress, the contact point enters a sliding state, the tangential stress is limited to the critical friction stress, and the tangential displacement increment is released. The model outputs the resultant tangential reaction force of the contact surface, which is the maximum static friction threshold of the equipment resisting lateral displacement, i.e., the lateral sliding resistance.

[0092] Wind-borne sway drag is calculated using a wind-induced vibration response model. The model uses wind speed and gust factor from climate parameters as wind field excitation inputs, the geometric dimensions and windward area of ​​the wind-receiving structure as structural characteristic inputs, and a virtual fault-triggered state as an additional damping correction. The virtual fault-triggered state characterizes the situation where sensor gain drift is caused by dust adhesion; in this case, the model reduces the damping coefficient of the control system, thus narrowing the calculated wind-borne sway drag value. The model outputs the equivalent wind-borne sway drag through frequency domain or time domain analysis.

[0093] The wind-induced vibration response model utilizes a global damping model based on the zero-crossing rate method to simplify the simulation of the frequency-varying characteristics of wind-exposed structures under random wind fields. During implementation, the geometric dimensions, windward area, first-order natural frequency, and structural damping ratio of the wind-exposed structure are obtained. The wind speed time history is used as the input excitation and converted into the pulsating wind pressure time history distributed along the height according to building load codes. The core of the model uses the zero-crossing rate method to calculate the equivalent stationary excitation characteristic frequency, which is then substituted into the constitutive equation of the frequency-varying viscoelastic damping material to determine the equivalent stiffness and equivalent damping coefficient of the viscoelastic damping element. A virtual fault trigger state is used as an additional correction factor input. When the sensor fault state is true, the damping coefficient of the control system is reduced by a preset ratio to simulate the damper output deviation caused by sensor gain drift. The model then uses frequency domain spectral analysis or time domain linear acceleration method to solve the wind-induced vibration response of the single-degree-of-freedom or multi-degree-of-freedom system, outputting the peak displacement at the top of the structure and the equivalent static wind load at the base. The ratio of the equivalent static wind load to the lateral stiffness of the structure is converted into wind-induced sway resistance, which is used to characterize the equivalent damping force of the structure against wind-induced swaying.

[0094] During drilling simulation, the effect simulation module calculates target parameters in multiple dimensions based on dynamic environmental data and equipment performance status within the current simulation period. These target parameters correspond to the physical constraints of the drilling equipment model under conditions of soft ground, rock cutting, lateral stability, and wind fields. They are calculated using differentiated physical and mechanical models, depending on specific subsets of dynamic environmental data and equipment performance status.

[0095] In addition to sinking resistance, drilling resistance, sideslip resistance, and wind load oscillation resistance, a complete drilling simulation operation also includes target parameters at the levels of drilling process progress, wellbore condition, drill string attitude, and operational efficiency. These parameters are calculated using physical models or empirical formulas based on specific subsets of dynamic environmental data and equipment performance status.

[0096] The target parameters, including drill bit position and well depth, describe the drilling process. The performance simulation module acquires the actual performance status from the equipment performance status, which includes the actual output values ​​of drill pressure and rotational speed after correction by the dynamic resource competition model. It also acquires surface parameters from the environmental dynamic data, including formation drillability classification. The actual performance status and surface parameters are input into the mechanical drilling rate prediction model. The model outputs the instantaneous drilling rate within the current simulation step, and then updates it by integrating the drill bit position to obtain the current well depth and drill bit spatial coordinates.

[0097] The mechanical drilling rate prediction model utilizes a hybrid model based on mechanistic constraint neural networks and domain adversarial transfer learning. During implementation, a deep neural network regressor is constructed. Input features include the actual values ​​of drill pressure and rotational speed corrected by a dynamic resource competition model, as well as formation drillability classification and mud performance parameters from surface parameters. Dual mechanistic constraints are introduced during the training phase. The data layer incorporates the drill pressure and rotational speed product term from the corrected Young's rate of drilling equation, the unit volume breaking energy term from the mechanical specific energy equation, and the hydraulic parameter terms from the drill bit water power equation as derived features and concatenates them to the input layer. The network layer adds penalty terms to the partial derivatives of drilling rate with respect to drill pressure and rotational speed in the loss function, forcing the model output to be positively correlated with drill pressure and rotational speed. For migrating data from neighboring wells to the target well, a domain adversarial neural network architecture is used. This architecture consists of a feature extractor, a drilling rate regressor, and a domain classifier. Through adversarial training, the feature extractor learns domain-independent feature representations, enabling the transfer of knowledge from neighboring wells to the target well. During real-time operation, the model deploys a dual sliding window incremental update mechanism. The adjacent well sliding window collects engineering data from a 500-meter section above and below the drill bit position as the source domain, while the drilling sliding window collects data from the newly drilled 100 meters in the current well as the target domain. Incremental retraining of the model is triggered with a step size of one column length, enabling the model to adapt to changes in downhole conditions in real time. The model outputs the instantaneous drilling rate within the current simulation step size, and the simulation system integrates the instantaneous drilling rate over the time step to update the drill bit position and current well depth.

[0098] The target parameters include top drive torque, used to evaluate the load state of the rotating system. The effect simulation module acquires performance parameters from the equipment performance status, which characterize the current output capability of the power system after cumulative attenuation, and then acquires event parameters from environmental dynamic data, including the location and extent of cuttings bed accumulation. The performance parameters and event parameters are input into the torque loss model, which integrates drill string-wellbore friction, additional resistance from the cuttings bed, and drill bit rock-breaking reaction torque, and outputs the current real-time top drive torque value.

[0099] The torque loss model utilizes a torque load spectrum generation model based on nonlinear damage accumulation theory. During implementation, a lumped-parameter torsional vibration differential equation is established based on the wellbore structure and drill string assembly. The friction torque between the drill string and the wellbore is calculated based on the contact force and friction coefficient. The contact force is determined by the drill string buckling morphology. When the drill string is compressed beyond the sinusoidal buckling critical load, continuous contact occurs between the drill string and the wellbore; the contact normal pressure is calculated based on the buckling waveform distribution. The additional resistance from the cuttings bed is determined based on the cuttings bed accumulation location and height from the event parameters. The cuttings bed is equivalent to a locally narrowed annulus section, and the additional bulldozing resistance required for the drill string to pass through the cuttings bed is calculated based on particle mechanics theory. The drill bit rock-breaking counter-torque is converted from the drilling resistance output by the shear stress-displacement relationship model to the drill bit radius. The summation of the three torque components yields the total torque requirement at the current moment. The model incorporates the Lemaitre nonlinear damage model for torque load spectrum lifetime loss assessment. This damage model describes the damage caused by each torque cycle as a function of the stress amplitude and the current damage state; when the accumulated damage reaches a threshold, it triggers torque output capacity decay. At the simulation implementation level, the torque loss model is encapsulated as a Matlab / Simulink function module, which receives the upper limit of the current output capability of the power system represented by the performance parameters as the torque limit value, and outputs the real-time torque value of the top drive after the limit processing.

[0100] The target parameters include riser pressure and bottom hole pressure, used to monitor the hydraulic balance of the wellbore. The effect simulation module acquires climate parameters from the environmental dynamic data, including ambient temperature and air pressure, and then acquires the virtual fault trigger status from the equipment performance status, which indicates whether there is an anomaly in the mud pump or sensor. The climate parameters and virtual fault trigger status are input into the hydraulic parameter calculation model. The model outputs riser pressure and bottom hole pressure distribution curves based on mud rheology, circulation flow rate, and well structure.

[0101] The hydraulic parameter calculation model utilizes a hybrid model based on a steady-state flow pressure drop network and intelligent parameter estimation. During implementation, a full-wellbore flow pressure drop network is established based on the wellbore structure, drill string assembly, and mud performance parameters, dividing the drill string, drill bit water holes, and annulus into several control volumes. For each control volume, the friction coefficient is calculated based on geometric dimensions and rheological modes, and the friction pressure drop is calculated using the Darcy-Weisbach formula and the Hertzsbach-Bard rheological model. The model simultaneously solves for the wellbore hydrostatic pressure and backpressure compensation pressure, summing and outputting the riser pressure and bottom hole pressure. For sensor anomalies indicated by virtual fault triggering status, the model uses intelligent parameter estimation for pressure correction. It consists of three artificial neural networks using different training algorithms: the Levenberg-Marquardt algorithm, the gradient descent algorithm, and the elastic backpropagation algorithm. The three neural networks take real-time measurements of ambient temperature, air pressure, mud pit volume, and mud density from the climate parameters as input, and output riser pressure and bottom hole pressure, and are trained independently until convergence. A supervised nonlinear combiner is then used to weight and fuse the outputs of the three networks. The nonlinear combiner is a shallow neural network that uses the outputs of the three networks as inputs and the measured pressure values ​​as supervisory signals to train the fusion weights. When the virtual fault trigger status is true, the system weights and averages the outputs of the neural network committee machine and the mechanistic model. The weights are dynamically adjusted based on historical prediction errors to compensate for measurement deviations caused by sensor failures, and the corrected riser pressure and bottom hole pressure distribution curves are output.

[0102] The target parameters include the mechanical drilling rate, used to measure drilling operation efficiency. The effect simulation module obtains drilling resistance and top drive torque as process inputs, and then obtains the actual values ​​of drill pressure and rotational speed included in the actual performance status of the equipment. The drilling resistance, top drive torque, and actual performance status inputs are used to fit the drilling rate model. Based on the rock breaking energy and energy balance principle, the model outputs the instantaneous mechanical drilling rate and cumulative footage under the current working condition.

[0103] The drilling rate fitting model utilizes a time-series fusion model of support vector regression optimized by an improved dung beetle optimization algorithm. During implementation, drilling resistance, top drive torque, and the actual values ​​of drilling pressure and rotational speed under real-world performance conditions are used as input features, and instantaneous mechanical drilling rate is used as the output label to construct the basic support vector regression model. To address the difficulty in determining the penalty factor, kernel function parameters, and insensitive loss coefficients in support vector regression, an improved dung beetle optimization algorithm is used for parameter optimization. This algorithm introduces four improvement strategies based on the standard dung beetle optimization framework: using weighted fusion to balance global exploration and local exploitation capabilities, introducing an improved echolocation mechanism to enhance population diversity, designing an improved local iterative search to improve convergence accuracy, and adding an optimal solution re-update strategy to avoid getting trapped in local optima. To address the non-stationary nature of drilling rate changes over time, the model further utilizes a time-series adjustment method based on fuzzy C-means clustering and the Mann-Kendall trend test. This method performs fuzzy C-means clustering on historical drilling rate sequences to identify drilling rate modes corresponding to different drilling conditions. For the current input features, they are assigned to each mode according to their membership degree. Within each mode, the Mann-Kendall trend test is used to determine the direction and significance of the drilling rate change trend. Based on the trend test results, the initial drilling rate value output by support vector regression is incrementally adjusted.

[0104] The target parameters include drill string attitude and wellbore trajectory, used for directional drilling operations. The effect simulation module acquires surface parameters from environmental dynamic data, including the formation anisotropy index, and then acquires the lateral forces and wind-induced structural conditions from the equipment performance status. The lateral forces characterize the lateral loads borne by the drill string assembly, and the wind-induced structural conditions characterize the influence of derrick oscillation on the lateral constraint of the drill string. The surface parameters and equipment performance status are input into the lower drill string assembly mechanical model. The model solves for the drill string buckling state and lateral force distribution using the finite element method, outputting the well inclination angle, azimuth angle, and tool face angle.

[0105] The mechanical model of the lower drill string assembly utilizes a nonlinear finite element model based on multi-directional contact friction gap elements and spatial beam elements. In implementation, the lower drill string assembly is discretized into several spatial beam elements, each with six degrees of freedom, used to describe the axial tension, bending, torsion, and shear deformation of the drill string. The wellbore trajectory is described by a spatial curve defined by the inclination angle, azimuth angle, and depth, serving as the geometric constraint boundary for drill string deformation. To address the contact problem between the drill string and the wellbore, the model introduces multi-directional contact friction gap element technology. This gap element is a virtual nonlinear element whose stiffness adjusts according to the gap between the drill string and the wellbore. When the radial displacement of the drill string is less than the wellbore gap, the stiffness of the gap element is fixed to zero; when the radial displacement of the drill string reaches the wellbore gap, the stiffness of the gap element increases sharply, applying a normal contact force constraint to further penetrate, while simultaneously calculating the tangential friction force based on the Coulomb friction model. This gap element is uniformly distributed with multiple contact directions along the circumference of the drill string to simulate the random contact behavior of the drill string at different inclination azimuths and along the wellbore circumference. The model uses the Newton-Raphson iterative method to solve the nonlinear equations, updating the contact state and stiffness matrix in each increment step until the displacement increment and unbalanced force converge. After solving, the lateral force at the drill bit, drill bit inclination angle, and tool face angle are extracted as outputs. Based on the ratio of drill bit lateral force to bit pressure and the drill bit anisotropy index, the theoretical build-up rate of the drill string assembly is calculated using a drill string build-up performance evaluation method. This model is applicable to the analysis of drill string mechanical characteristics under different well inclination angles, different bit pressures, and different stabilizer position combinations, providing a simulation basis for directional drilling trajectory control.

[0106] Taking a simulated desert drilling operation as an example, after system initialization, the environmental simulation module generates dynamic environmental data on the development of a sandstorm. The coupling processing module updates the diesel engine health status variable based on the sandstorm concentration and determines that a virtual fault in the air filter has been triggered. Multiple devices simultaneously request cooling power; after allocation through a dynamic resource contention model, the coupling processing module outputs the actual performance status.

[0107] The simulation module receives the above data and calculates the subsidence resistance using the sand bearing capacity model, the drilling resistance using the shear stress-displacement relationship model, the sideslip resistance using the friction model, and the wind-driven oscillation resistance using the wind vibration response model. In parallel, the simulation module calls the mechanical drilling rate prediction model to update the drill bit position and well depth, the torque loss model to output the real-time top drive torque, the hydraulic parameter calculation model to output the riser pressure and bottom hole pressure, the drilling rate fitting model to output the instantaneous mechanical drilling rate, and the lower drill string assembly mechanics model to output the drill string attitude.

[0108] Meanwhile, the operation management module is configured to adjust the operation flow or rules associated with the drilling equipment model based on the equipment performance status. The operation management module determines the flow direction based on the real-time capabilities of the equipment. The operation flow includes the step of starting all power equipment and loading to 50%. Before executing this step, the operation management module checks the current available power of each power equipment in the equipment performance status report. The report shows that due to the high temperature and dusty environment, the available power of some generators is less than 50% of the rated power. Directly loading to 50% of the rated load may cause a virtual overload trip.

[0109] The operation management module dynamically adjusts the instruction for this step. The instruction is changed to start all power equipment and distribute the load proportionally according to the current available power of each piece of equipment, ensuring the total load does not exceed 80% of the current available power. When the equipment performance status report triggers an engine high-temperature alarm that persists for more than 30 seconds, the operation management module interrupts the standard operating procedure and forcibly inserts and executes the engine overheat emergency response sub-procedure. The sub-procedure requires the operator to perform operations such as virtual shutdown and checking the coolant. The drilling simulation operation process reflects the direct impact of environmental stress on operational decisions.

[0110] See Figure 5 In some embodiments, the operation management module is configured to: compare the equipment performance status with at least two preset condition thresholds, and adjust the operation process or rules associated with the drilling equipment model according to the comparison results; wherein, when the equipment performance status is lower than a first performance threshold, a virtual warning message is triggered; when the equipment performance status is lower than a second performance threshold, a predefined emergency operation procedure is started and executed; the second performance threshold is different from the first performance threshold.

[0111] The first performance threshold is the critical point that triggers the virtual warning message. The second performance threshold is the critical point that triggers the emergency operation procedure. The second performance threshold differs from the first performance threshold and is used to form a progressive protection hierarchy from warning to intervention.

[0112] The job management module continuously receives equipment performance status output from the coupled processing module. Equipment performance status is a quantitative indicator reflecting the current operational capability of the equipment, such as the percentage of power system output or the remaining lifespan of key components. The job management module compares the equipment performance status value with a first performance threshold. When the performance status value is lower than the first performance threshold but higher than a second performance threshold, the system determines that the equipment has deviated from its optimal operating condition. The job management module triggers a virtual warning message. The warning message is presented in text form in the simulation interface status bar, containing the name of the equipment experiencing performance degradation and the current parameter value, without forcibly changing the operating procedure. The job management module continues to monitor the equipment performance status value.

[0113] When the performance status value falls below the second performance threshold, the system determines that the equipment cannot maintain safe operation. The operation management module forcibly starts and executes a predefined emergency operation procedure. The emergency operation procedure is a pre-programmed sequence of instructions that is automatically executed in the logical order of unloading the load, disconnecting the transmission, activating the backup, and recording the event, without the need for manual intervention.

[0114] The first and second performance thresholds are set differently to allow the job management module to output two intervention behaviors during the same performance degradation process. The former is an informational intervention designed to enhance operators' situational awareness, while the latter is a control-oriented intervention designed to prevent damage to virtual devices.

[0115] A multi-level performance threshold comparison mechanism is used to achieve graded management of equipment performance degradation, addressing the problems of traditional simulation systems' black-and-white fault responses and lack of buffering and early warning layers. The first performance threshold provides operators with prompts and adjustment windows. The second performance threshold ensures the system has fallback protection capabilities in case of insufficient human response or sudden changes in conditions.

[0116] The system operates continuously in a loop. The environmental simulation module generates a changing environment. The coupling processing module converts these environmental changes into quantifiable changes in equipment state. The effect simulation module represents these changes in equipment state as physical difficulties. The job management module adjusts the job logic and requirements based on the changes in equipment state. Environmental dynamic data and equipment performance status are coupled as two data streams. Environmental dynamic data is the driving force behind these changes. Equipment performance status serves as the crucial link between them.

[0117] Environmental changes affect equipment performance through the coupled processing module. The resulting changes are reflected in the simulation module as increased operational difficulty in the physical world, and in the job management module as increased operational complexity and decision-making pressure. The desert environment, through computable, transmissible, and representational data links, exerts pressure and challenges on drilling operations, thereby constructing an extreme environment training environment in virtual space.

[0118] For example, in a simulation training session, the environmental simulation module simulates an approaching sandstorm. Wind speed and dust concentration data increase. The coupling processing module receives the data and, according to mapping rules, reduces the intake efficiency coefficient and heat dissipation efficiency coefficient of the diesel generator model. In the output device performance status report, the generator's current available power gradually decreases from 100KW to 65KW.

[0119] The simulation module calculates the increased rolling resistance and enhanced crosswind effects of vehicles based on changes in wind speed and surface sand mobility, making vehicle handling more difficult. The operation management module monitors generator power below the preset safety redundancy threshold of 75kW, automatically suspending the operation of high-power electric heaters and displaying a warning on the interface, instructing the operator that the generator power is insufficient and to prioritize critical loads or activate backup power.

[0120] Based on feedback from the virtual sandstorm environment regarding vehicle descent difficulties and insufficient generator output, operators make judgments and take actions, such as directing vehicles to find shelter, shutting down unnecessary equipment, and starting the backup generator according to procedures. The simulation process forms a coherent, data-driven logical whole, from environmental phenomena to equipment performance to operational requirements.

[0121] Based on the aforementioned drilling simulation system for a desert scenario, some embodiments of this application also provide a drilling simulation method for a desert scenario, including: The environmental simulation module generates dynamic environmental data for the target desert area. Environmental sensitivity parameters are obtained through an equipment model library, which includes at least one drilling equipment model. The drilling equipment model has preset environmental sensitivity parameters, which change according to the environmental dynamic data. The coupling processing module converts the environmental dynamic data into adjustment amounts for the environmental sensitivity parameters according to predefined mapping rules, so as to output the device performance status. The effect simulation module simulates the target parameters of the drilling equipment model in the corresponding environment based on the environmental dynamic data and equipment performance status. The target parameters include at least sinking resistance and / or drilling resistance. The operation management module adjusts the operation process or rules associated with the drilling equipment model based on the equipment performance status.

[0122] Similar parts between the embodiments provided in this application can be referred to mutually. The specific implementation methods provided above are only a few examples under the overall concept of this application and do not constitute a limitation on the scope of protection of this application. For those skilled in the art, any other implementation methods extended from the solution of this application without creative effort shall fall within the scope of protection of this application.

Claims

1. A drilling simulation system based on a desert scenario, characterized in that, include: The environmental simulation module is configured to generate dynamic environmental data for the target desert region; The equipment model library includes at least one drilling equipment model, which has preset environmental sensitivity performance parameters that change according to the dynamic environmental data. The coupling processing module is configured to convert the environmental dynamic data into adjustment amounts for the environmental sensitivity parameters according to predefined mapping rules, so as to output the device performance status. The effect simulation module is configured to simulate the target parameters of the drilling equipment model in the corresponding environment based on the environmental dynamic data and equipment performance status. The target parameters include at least sinking resistance and / or drilling resistance. The operation management module is configured to adjust the operation process or rules associated with the drilling equipment model based on the performance status of the equipment.

2. The drilling simulation system based on a desert scenario according to claim 1, characterized in that, The environmental sensitivity performance parameters include at least one health state variable, which is used to characterize the cumulative performance degradation of the drilling equipment model. The coupling processing module is specifically configured to: determine the instantaneous rate of change of the health status variable based on the environmental dynamic data; update the current value of the health status variable based on the instantaneous rate of change, so as to output the cumulative performance degradation degree.

3. The drilling simulation system based on a desert scenario according to claim 1, characterized in that, The coupling processing module also includes a parameter estimation model; The device performance status includes performance parameters; The coupling processing module is specifically configured to: adjust at least one parameter in the predefined mapping rules based on the state data generated during the simulation operation, using the parameter estimation model; and use the adjusted parameters to perform the conversion of environmental dynamic data into performance parameters.

4. The drilling simulation system based on a desert scenario according to claim 1, characterized in that, The predefined mapping rules include fault trees and probability sampling models; The device performance status includes the triggering status of virtual faults, which is a status identifier used to characterize whether a virtual fault event is determined to have occurred. The coupling processing module is specifically configured to: determine the probability of occurrence of virtual fault events based on the environmental dynamic data and through the fault tree and probability sampling model; Random sampling is performed based on the occurrence probability to determine whether the virtual fault event is triggered; if the virtual fault event is triggered, the corresponding triggering status is output.

5. The drilling simulation system based on a desert scenario according to claim 1 or 4, characterized in that, When the equipment model library contains multiple drilling equipment models, the predefined mapping rules include a dynamic resource competition model; The device performance status includes the actual performance status; The coupling processing module is configured as follows: Based on the environmental dynamic data, virtual resource requests are generated for each of the drilling equipment models. The dynamic resource contention model is used to competitively schedule and allocate multiple virtual resource requests to obtain virtual resource results. Based on the virtual resource results, determine the corresponding actual performance status.

6. The drilling simulation system based on a desert scenario according to claim 1, characterized in that, The environment simulation module includes an environment parameter constraint network and an environment state machine, and the environment state machine is pre-set with state transition conditions. The environmental parameter constraint network is used to acquire environmental parameters and determine the environmental dynamic data based on the physical dependencies between multiple environmental parameters. The environmental state machine is pre-set with state transition conditions, which are used to drive the switching between multiple preset environmental states based on the environmental dynamic data. The environmental states include at least the sandstorm development state, the sandstorm activity state, and the environmental dissipation state.

7. The drilling simulation system based on a desert scenario according to claim 1, characterized in that, The environmental dynamic data includes at least climate parameters, surface parameters, and event parameters; the equipment performance status includes at least performance parameters, virtual fault triggering status, actual performance status, lateral forces, and wind-affected structures; the target parameters also include sideslip resistance and wind load sway resistance. The effect simulation module is specifically configured as follows: Based on the surface parameters and performance parameters, the subsidence resistance is calculated using a sand and soil bearing capacity model. Based on the surface parameters and the actual performance state, the drilling resistance is calculated using a shear stress-displacement relationship model. Based on the surface parameters and the lateral forces, the sideslip resistance is calculated using a friction model. Based on the climate parameters, the wind-receiving structure, and the triggering state of the virtual fault, the wind load sway resistance is calculated using a wind vibration response model.

8. The drilling simulation system based on a desert scenario according to claim 1, characterized in that, The operation management module is configured to: compare the equipment performance status with at least two preset condition thresholds, and adjust the operation process or rules associated with the drilling equipment model according to the comparison results; Specifically, when the device performance status is lower than a first performance threshold, a virtual warning message is triggered; when the device performance status is lower than a second performance threshold, a predefined emergency operation procedure is initiated and executed; the second performance threshold is different from the first performance threshold.

9. A drilling simulation method based on a desert scenario, characterized in that, include: The environmental simulation module generates dynamic environmental data for the target desert area. Environmental sensitivity parameters are obtained through an equipment model library, which includes at least one drilling equipment model. The drilling equipment model has preset environmental sensitivity parameters, which change according to the environmental dynamic data. The coupling processing module converts the environmental dynamic data into adjustment amounts for the environmental sensitivity parameters according to predefined mapping rules, so as to output the device performance status. The effect simulation module simulates the target parameters of the drilling equipment model in the corresponding environment based on the environmental dynamic data and equipment performance status. The target parameters include at least sinking resistance and / or drilling resistance. The operation management module adjusts the operation process or rules associated with the drilling equipment model based on the equipment performance status.

Images