Intelligent mine management and control method based on digital twinning

Abstract

The invention relates to the technical field of mine management, and discloses an intelligent mine management and control method based on digital twinning, and the method comprises the steps: 1, collecting various types of data in a mine environment through an Internet of Things technology, a sensor and unmanned aerial vehicle equipment, enabling the data to comprise the operation state of mine equipment, the quality of ore, environment change information and geological data, and carrying out the collection of the data after the data collection, noise removal, abnormal value processing and data integrity verification are carried out; and 2, after data acquisition and processing are completed, constructing a multi-scale digital twinborn model by using the data. Through combination of multi-scale modeling and nonlinear dynamics, the problem of macroscopic and microcosmic dynamic coupling in a mine environment is solved, the digital twin model is updated in real time, the state of a mine system is estimated, the model can respond in real time when the environment changes, and the effects that the precision of the digital twin model is improved and the real-time performance is enhanced are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of mine management, and in particular to a smart mine management and control method based on digital twins. Background Art

[0002] With the advancement of science and technology, mine management faces challenges, including low production efficiency, waste of resources, equipment failure and safety hazards. Traditional mine management and control methods rely on manual decision-making and static models, lack of real-time perception and prediction of the mine environment, resulting in room for improvement in efficiency and safety of mine operations. Especially in the face of changing environments and emergencies, traditional methods cannot respond quickly and effectively, increasing the risk of waste of resources, equipment loss and safety accidents.

[0003] In recent years, digital twin technology, as an emerging management tool, has been widely used in the industrial field. Digital twin technology collects data from physical systems in real time, establishes corresponding virtual models, and realizes comprehensive monitoring and dynamic management of the system. In the mining field, the complexity and variability of the mining environment still have limitations in existing digital twin applications. Specifically, the existing digital twin model cannot handle dynamic changes at both macro and micro scales at the same time; the real-time and accuracy of model updates are poor, and it cannot effectively support real-time decision-making for complex and emergency events; in resource scheduling and production process optimization, traditional control algorithms usually cannot fully consider environmental changes and system constraints, resulting in unsatisfactory optimization results.

[0004] Therefore, how to achieve efficient and accurate digital twin model updates in a mining environment and improve production efficiency and decision response speed through optimized control has become the main problem facing current mine management and control technology. In order to overcome the above-mentioned technical bottlenecks, the present invention proposes a smart mine management and control method based on digital twins to solve the above-mentioned problems. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a smart mine management and control method based on digital twins to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a smart mine management and control method based on digital twins, comprising:

[0007] Step 1: Collect various data in the mining environment through IoT technology, sensors and drone equipment. The data includes the operating status of mining equipment, the quality of ore, environmental change information and geological data. After data collection, perform noise removal, outlier processing and data integrity verification;

[0008] Step 2: After completing data collection and processing, use the data to build a multi-scale digital twin model. The multi-scale digital twin model combines the macro process and micro process in the mine system. The macro process describes the overall mining progress and equipment status of the mine, and the micro process describes the local influencing factors of ore layer changes and equipment wear;

[0009] Step 3: Based on the constructed multi-scale digital twin model, nonlinear dynamic equations are used to model the dynamic changes of the mining system. The nonlinear dynamic equations describe the nonlinear relationship between various links in the mining system, taking into account the complex interaction between the equipment operation status and the mining resources. The inputs in the nonlinear dynamic equations include the current state of the mining system, the equipment operation control quantity, and the interference factors in the environment.

[0010] Step 4: By combining Bayesian filtering and Kalman filtering, the state of the mine system is estimated in real time, wherein the Bayesian filter provides a priori estimation of the state, and the Kalman filter corrects the estimation of the system state based on the real-time data collected by the sensor;

[0011] Step 5: Based on the real-time estimation obtained in step 4, the optimal control algorithm is used to calculate the update strategy for each time step to optimize the control input. The optimal control strategy provides the best decision basis by weighing the model error and the consumption of control input energy.

[0012] Step 6: According to the optimal control strategy in step 5, the state of the digital twin model is updated in real time, and the parameters of the digital twin model are adjusted by applying the optimal control input at each time step;

[0013] Step 7. After the digital twin model is updated, a comprehensive assessment of mine production is conducted based on the updated model. According to the status information provided by the model, the mine operation plan is adjusted to optimize equipment use and resource scheduling. At the same time, the model is used to monitor the mine environment in real time to promptly identify potential safety hazards and environmental issues, and formulate and implement corresponding preventive measures.

[0014] Preferably, in step 2, the construction of the multi-scale digital twin model adopts an asymptotic expansion method, wherein the macroscopic process is represented by the following equation:

[0015]

[0016] Among them, u(x, t) is the state variable of the mine, L0 is the macro-scale dynamic process, L1 is the micro-scale process, ∈ represents the coupling effect of macro- and micro-processes, represents the rate at which the state variable (x, t) of the mining system changes with time, Represents a high-order small quantity.

[0017] Preferably, in step 2, the nonlinear dynamic equation adopts the following form to describe the complex interaction between mining equipment and resources:

[0018]

[0019] in, is the state of the mining system, f(x(t), u(t)) is the nonlinear dynamic function of the mining system, u(t) is the control input, and η(t) is the external disturbance.

[0020] Preferably, in step 4, the combination of Bayesian filtering and Kalman filtering is used to estimate the mine state in real time, wherein the recursive formula of Kalman filtering is:

[0021]

[0022] in, is the state estimate at the current moment, is the state estimate of the previous moment, K k is the Kalman gain, z k is the observation value at the current moment, and H is the observation matrix.

[0023] Preferably, in step 5, the optimal control algorithm adopts a dynamic programming optimization update strategy, and the objective function is:

[0024] Among them, J is the objective function, x(t) is the actual state of the mine, is the state of the digital twin model, Q is the weighted matrix, R is the weight of the control input, u(t) is the control input, and T is the optimized time window.

[0025] Preferably, the control input u(t) is calculated by an optimal control algorithm, which is a dynamic programming or reinforcement learning algorithm, and is used to calculate the optimal update amount at each time step to minimize the error and cost in the objective function J.

[0026] Preferably, in step 6, the real-time update step is based on the optimal control input of each time step, and the state is updated using the following formula:

[0027]

[0028] Where u(t) is the control input, represents the control input u(t) that minimizes the subsequent objective function, x(t) is the actual state of the mine, is the state of the digital twin model, Represents the actual state x(t) and the state of the digital twin model The error between represents the cost of the control input u(t), Q is the weighting matrix, and R is the weight of the control input.

[0029] Preferably, the updating step adjusts the operation plan of mine production, including equipment scheduling, ore transportation and resource allocation, according to the real-time sensor data and the updated digital twin model status.

[0030] Preferably, the safety risk assessment of mining operations is performed based on the updated model, and the assessment is performed according to the following formula:

[0031]

[0032] Among them, S(t) is the safety risk assessment value,

[0033] is a risk prediction function, which represents the combination of the model and real-time data to predict potential safety hazards in mining operations.

[0034] x(t) is the actual state of the mine, is the state of the digital twin model, η(t) is the external disturbance;

[0035] The safety risk assessment result S(t) is used to automatically adjust the mining operation process, optimize the operation plan, and implement corresponding preventive measures according to the assessment result.

[0036] Preferably, the optimization strategy for mine production scheduling is implemented according to the following formula:

[0037] min{f(prod efficiency), g(envir impact), h(risk assess)},

[0038] Among them, f (prod efficiency) represents the production efficiency optimization function, g (envir impact) is the environmental impact minimization function, and h (risk assess) is the safety risk control function.

[0039] The present invention provides a smart mine management and control method based on digital twins, which has the following beneficial effects:

[0040] 1. The present invention solves the problem of macro-micro dynamic coupling in the mining environment by combining multi-scale modeling with nonlinear dynamics, updates the digital twin model in real time, estimates the state of the mining system, ensures that the model can respond in real time when the environment changes, and obtains the effect of improving the accuracy and real-time performance of the digital twin model.

[0041] 2. The present invention uses the optimal control algorithm to comprehensively optimize the system error and the energy consumption of the control input in the objective function, calculate the optimal control strategy, realize the intelligent scheduling of mining operations and efficient allocation of resources, thereby improving the production efficiency of the mine, reducing resource waste, and reducing operating costs.

[0042] 3. The present invention provides decision support through real-time updating of digital twin models and intelligent decision-making algorithms, enabling mine managers to quickly respond to various changes in mine operations, realize intelligent mine management and control, improve management efficiency, speed up decision-making, and promote the intelligent development of mine management. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0044] In order to make the technical personnel in the technical field understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in combination with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a partial embodiment of the present invention, not a complete embodiment. Based on the embodiment of the present invention, other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present invention.

[0045] The present invention is described in detail below in conjunction with the accompanying drawings:

[0046] Example:

[0047] Please see attached Figure 1 , an embodiment of the present invention provides a smart mine management and control method based on digital twins, comprising:

[0048] Step 1: Collect various data in the mining environment through IoT technology, sensors and drone equipment. The data includes the operating status of mining equipment, the quality of ore, environmental change information and geological data. After data collection, perform noise removal, outlier processing and data integrity verification;

[0049] Step 2: After completing data collection and processing, use the data to build a multi-scale digital twin model. The multi-scale digital twin model combines the macro process and micro process in the mine system. The macro process describes the overall mining progress and equipment status of the mine, and the micro process describes the local influencing factors of ore layer changes and equipment wear;

[0050] Step 3: Based on the constructed multi-scale digital twin model, nonlinear dynamic equations are used to model the dynamic changes of the mining system. The nonlinear dynamic equations describe the nonlinear relationship between the various links in the mining system, taking into account the complex interaction between the equipment operation status and the mining resources. The inputs in the nonlinear dynamic equations include the current state of the mining system, the equipment operation control quantity, and the interference factors in the environment.

[0051] Step 4: By combining Bayesian filtering and Kalman filtering, the state of the mine system is estimated in real time. The Bayesian filter provides a priori estimation of the state, and the Kalman filter corrects the estimation of the system state based on the real-time data collected by the sensor.

[0052] Step 5: Based on the real-time estimation obtained in step 4, the optimal control algorithm is used to calculate the update strategy for each time step to optimize the control input. The optimal control strategy provides the best decision basis by weighing the model error and the consumption of control input energy.

[0053] Step 6: According to the optimal control strategy in step 5, the state of the digital twin model is updated in real time, and the parameters of the digital twin model are adjusted by applying the optimal control input at each time step;

[0054] Step 7. After the digital twin model is updated, a comprehensive assessment of mine production is conducted based on the updated model. According to the status information provided by the model, the mine operation plan is adjusted to optimize equipment use and resource scheduling. At the same time, the model is used to monitor the mine environment in real time to promptly identify potential safety hazards and environmental issues, and formulate and implement corresponding preventive measures.

[0055] Benefits of step 1: Ensure that the collected data is authentic and accurate, and avoid model errors and decision-making errors caused by incomplete and inaccurate data. Improve the quality of data and lay a solid foundation for subsequent model construction and analysis. Ensure the automation and efficiency of the data processing process, and reduce manual intervention and errors.

[0056] Benefits of step 2: By combining macro and micro processes, the multi-dimensional dynamic changes of the mine are fully reflected. The model can accurately describe the complex mining environment, cope with changes at different levels and scales in the mine, and improve the adaptability and prediction ability of the model.

[0057] Benefits of step 3: It can capture the complex nonlinear interaction between the equipment operating status and resources in the mining environment, accurately reflect the complexity of the mining environment, provide accurate models, improve the ability to predict the dynamic changes of the system, and avoid the simplification and inadaptability of traditional linear models.

[0058] Benefits of step 4: Providing accurate state estimation can effectively deal with uncertainty and external disturbances in the system and ensure the stability of the model in a dynamic environment. The combination of Kalman filtering and Bayesian filtering can provide accurate state prediction and reduce estimation deviations caused by real-time data changes.

[0059] Benefits of step 5: Providing a mathematical basis for optimizing mining operations, automatically adjusting equipment operation and ore mining operations according to the real-time status of the mine to maximize resource utilization efficiency. By optimizing control strategies, unnecessary energy consumption can be reduced, production costs can be reduced, and operating efficiency can be improved.

[0060] Benefits of step 6: Ensure that the digital twin model is always synchronized with the actual environment of the mine, and the model can reflect the production status of the mine in real time to ensure the timeliness of decision-making. By updating each time step, ensure that the model makes timely adjustments to the mine operation progress, equipment status and resource allocation factors.

[0061] Benefits of Step 7: Provide comprehensive, real-time production monitoring and decision support to improve the accuracy and efficiency of mine management. By timely identifying potential safety hazards and environmental issues, early warnings can be issued and corresponding preventive measures can be taken to reduce safety risks and ensure the sustainability of mine production.

[0062] In step 2, the construction of the multi-scale digital twin model adopts the asymptotic expansion method, in which the macroscopic process is represented by the following equation:

[0063]

[0064] Among them, u(x, t) is the state variable of the mine, L0 is the macro-scale dynamic process, L1 is the micro-scale process, ∈ represents the coupling effect of macro- and micro-processes, represents the rate at which the state variable (x, t) of the mining system changes with time, Represents a high-order small quantity.

[0065] The asymptotic expansion method can effectively couple the macroscopic and microscopic processes of the mining system, and comprehensively describe the dynamic changes of the mining system at different scales. The macroscopic process can reflect the overall operating status of the mine, while the microscopic process can carefully capture the influence of local factors such as equipment wear and ore layer changes, ensuring the multi-dimensional accuracy of the digital twin model.

[0066] Through multi-scale modeling, the digital twin model can focus on local details in the mining system when processing a wide range of mining data, avoiding the situation where micro-level influences are ignored in traditional models, and making the model highly accurate and adaptable when responding to environmental changes and equipment failures.

[0067] It allows the degree of coupling between macro and micro processes to be flexibly adjusted in different application scenarios. If a certain factor in the mining environment becomes important, the influence of the micro process can be enhanced, and vice versa, it can be weakened, providing flexibility and optimization space.

[0068] In step 2, the nonlinear dynamic equations take the following form to describe the complex interaction between mining equipment and resources:

[0069]

[0070] in, is the state of the mining system, f(x(t), u(t)) is the nonlinear dynamic function of the mining system, u(t) is the control input, and η(t) is the external disturbance.

[0071] The equation can accurately capture the complex nonlinear relationship between various links in the mining system. Through the nonlinear dynamic model, it can reflect the nonlinear behavior caused by the interaction of multiple factors in the mining system, ensuring the accuracy of the model in describing the system dynamics.

[0072] The nonlinear dynamic model can handle the impact of external disturbances on the mine production process. By introducing the disturbance term η(t) into the model, the impact of the disturbance on the mine production status can be reflected in a timely manner, thereby enhancing the adaptability and robustness of the digital twin model and ensuring that the system can maintain stable operation in a changing environment.

[0073] By accurately describing the interaction between mining equipment and resources, the nonlinear dynamic equation enables the system to be optimized under different conditions. In practical applications, the operation of equipment scheduling and resource allocation is optimized by adjusting the control input u(t), thereby improving mining operation efficiency and resource utilization. At the same time, the system can adjust the control strategy based on real-time feedback to avoid resource waste.

[0074] In step 4, the combination of Bayesian filtering and Kalman filtering is used to estimate the mine status in real time, where the recursive formula of Kalman filtering is:

[0075]

[0076] in, is the state estimate at the current moment, is the state estimate of the previous moment, K k is the Kalman gain, z k is the observation value at the current moment, and H is the observation matrix.

[0077] By combining Bayesian filtering and Kalman filtering, the prior information of Bayesian filtering and the real-time data correction capability of Kalman filtering can be fully utilized to significantly improve the estimation accuracy of the state of the mine system. Bayesian filtering provides a preliminary estimate of the system state, while Kalman filtering corrects the estimate based on real-time sensor data, making the estimation of the mine state accurate, especially when there is noise and uncertainty in the mine environment.

[0078] In mining production, external disturbances can affect the estimation of system states. Kalman filtering can dynamically adjust state estimates based on new observations, while Bayesian filtering can provide comprehensive prior information to help the system cope with external disturbances.

[0079] By estimating the status of the mine system in real time, managers can make decisions based on accurate status information. Kalman gain K k It provides a real-time feedback mechanism to maximize the impact of the latest observation data on the estimation by adjusting the weight of the state estimation, and provides a basis for decision-making when controlling mining operations, thereby improving the flexibility and adaptability of the mining production process.

[0080] In step 5, the optimal control algorithm adopts a dynamic programming optimization update strategy, and the objective function is:

[0081]

[0082] Among them, J is the objective function, x(t) is the actual state of the mine, is the state of the digital twin model, Q is the weighted matrix, R is the weight of the control input, u(t) is the control input, and T is the optimized time window.

[0083] The control input u(t) is calculated by the optimal control algorithm, which is a dynamic programming or reinforcement learning algorithm, used to calculate the optimal update amount at each time step to minimize the error and cost in the objective function J.

[0084] By optimizing the objective function through the dynamic programming algorithm, the optimal control input u(t) can be accurately calculated at each time step to ensure that the operation decision of the mining system is the best at each moment. The optimization strategy enables the mining operation to run efficiently, reduce resource waste, and improve production efficiency.

[0085] The objective function is obtained by calculating the actual state error The control input energy is weighted to ensure a reasonable balance between the system error and the control input cost. Through the weight matrices Q and R, the system can flexibly adjust the relative importance of the error and control input according to different needs and implement a control strategy that meets actual needs.

[0086] Through the optimal control algorithm, resource scheduling and equipment operation in the mine production process can achieve global optimization rather than local optimization, which means that the system can calculate the optimal update amount at each time step, making the mine's production process coordinated and efficient, and reducing losses caused by delayed and inaccurate decision-making.

[0087] Dynamic programming algorithms are particularly suitable for solving complex nonlinear problems. In mining systems, factors such as equipment wear and ore layer changes can cause the system dynamic behavior to be complex and nonlinear. Dynamic programming algorithms can accurately handle complex nonlinear interactions, ensuring that the optimization process can cover potential influencing factors, improving the accuracy of decision-making and the overall effectiveness of the system.

[0088] In step 6, the real-time update step is based on the optimal control input at each time step, and the state is updated using the following formula:

[0089]

[0090] Where u(t) is the control input, represents the control input u(t) that minimizes the subsequent objective function, x(t) is the actual state of the mine, is the state of the digital twin model, Represents the actual state x(t) and the state of the digital twin model The error between represents the cost of the control input u(t), Q is the weighting matrix, and R is the weight of the control input.

[0091] The update step adjusts the operation plan of mine production, including equipment scheduling, ore transportation, and resource allocation, based on real-time sensor data and the updated digital twin model status.

[0092] The safety risk assessment of mining operations is carried out according to the updated model, and the assessment is carried out according to the following formula:

[0093]

[0094] Among them, S(t) is the safety risk assessment value,

[0095] is a risk prediction function, which represents the combination of the model and real-time data to predict potential safety hazards in mining operations.

[0096] x(t) is the actual state of the mine, is the state of the digital twin model, η(t) is the external disturbance;

[0097] The safety risk assessment result S(t) is used to automatically adjust the mining operation process, optimize the operation plan, and implement corresponding preventive measures based on the assessment results.

[0098] By updating the state based on the optimal control input at each time step, the operation decision of the mining system is ensured to be real-time and optimal. By optimizing the error and the cost of the control input, the digital twin model can be adjusted at each time step to reflect the actual state of the mining operation in real time, reduce the problem of decision lag, and thus improve the accuracy and response speed of the mining operation.

[0099] The update process can automatically adjust the mine production operation plan based on real-time data and the updated digital twin model status. Mine equipment scheduling, ore transportation and resource allocation can all be optimized based on the real-time estimated mine status, achieving efficient use of mine resources and balancing production processes, avoiding resource waste and inefficiency caused by improper planning.

[0100] The present invention can predict potential safety hazards by real-time monitoring of the status of mine operations and simulating the dynamics of mines with a digital twin model. Through the safety risk assessment formula, combined with real-time data and the status of the model, risks can be discovered in a timely manner and preventive measures can be taken to avoid accidents.

[0101] According to the results of safety risk assessment, the mine operation process can be automatically adjusted, the operation plan can be optimized, and production efficiency and safety can be ensured in parallel. By automatically taking preventive measures based on risk assessment, the system can issue early warnings before sudden risks occur and automatically adjust the operation plan, avoiding human errors and decision-making delays, and improving the automation and intelligence level of mine operations.

[0102] The optimization strategy of mine production scheduling is implemented according to the following formula:

[0103] min{f(prod efficiency), g(envir impact), h(risk assess)},

[0104] Among them, f (prod efficiency) represents the production efficiency optimization function, g (envir impact) is the environmental impact minimization function, and h (risk assess) is the safety risk control function.

[0105] The present invention realizes intelligent and efficient mine production scheduling by introducing a comprehensive optimization strategy of production efficiency optimization, environmental impact minimization and safety risk control. The optimization strategy improves mine production efficiency and resource utilization, and focuses on environmental protection and safety risk management. Through real-time monitoring and data-driven decision-making systems, mine operations can be dynamically adjusted in complex environments to ensure that production efficiency and safety go hand in hand, and promote mine operations towards intelligent, green and sustainable development.

[0106] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart mine management and control method based on digital twins, characterized in that: include: Step 1: Collect various data in the mining environment through IoT technology, sensors and drone equipment. The data includes the operating status of mining equipment, the quality of ore, environmental change information and geological data. After data collection, perform noise removal, outlier processing and data integrity verification; Step 2: After completing data collection and processing, use the data to build a multi-scale digital twin model. The multi-scale digital twin model combines the macro process and micro process in the mine system. The macro process describes the overall mining progress and equipment status of the mine, and the micro process describes the local influencing factors of ore layer changes and equipment wear; Step 3: Based on the constructed multi-scale digital twin model, nonlinear dynamic equations are used to model the dynamic changes of the mining system. The nonlinear dynamic equations describe the nonlinear relationship between various links in the mining system, taking into account the complex interaction between the equipment operation status and the mining resources. The inputs in the nonlinear dynamic equations include the current state of the mining system, the equipment operation control quantity, and the interference factors in the environment. Step 4: By combining Bayesian filtering and Kalman filtering, the state of the mine system is estimated in real time, wherein the Bayesian filter provides a priori estimation of the state, and the Kalman filter corrects the estimation of the system state based on the real-time data collected by the sensor; Step 5: Based on the real-time estimation obtained in step 4, the optimal control algorithm is used to calculate the update strategy for each time step to optimize the control input. The optimal control strategy provides the best decision basis by weighing the model error and the consumption of control input energy. Step 6: According to the optimal control strategy in step 5, the state of the digital twin model is updated in real time, and the parameters of the digital twin model are adjusted by applying the optimal control input at each time step; Step 7. After the digital twin model is updated, a comprehensive assessment of mine production is conducted based on the updated model. According to the status information provided by the model, the mine operation plan is adjusted to optimize equipment use and resource scheduling. At the same time, the model is used to monitor the mine environment in real time to promptly identify potential safety hazards and environmental issues, and formulate and implement corresponding preventive measures.

2. According to the digital twin-based smart mine management and control method of claim 1, it is characterized in that: In step 2, the construction of the multi-scale digital twin model adopts the asymptotic expansion method, in which the macroscopic process is represented by the following equation: Among them, u ( x,t ) is the state variable of the mine, L0 is the macro-scale dynamic process, L1 is the micro-scale process, ∈ represents the coupling effect of macro- and micro-processes, Represents the state variable of the mine system ( x,t ) The rate of change of time, Represents a high-order small quantity.

3. The method for intelligent mine management and control based on digital twin according to claim 1, characterized in that: In step 2, the nonlinear dynamic equation takes the following form to describe the complex interaction between mining equipment and resources: in, is the state of the mining system, f(x(t), u(t)) is the nonlinear dynamic function of the mining system, u(t) is the control input, and η(t) is the external disturbance.

4. The method for intelligent mine management and control based on digital twin according to claim 1 is characterized in that: In step 4, the combination of Bayesian filtering and Kalman filtering is used to estimate the mine status in real time, wherein the recursive formula of Kalman filtering is: in, is the state estimate at the current moment, is the state estimate of the previous moment, K k is the Kalman gain, z k is the observation value at the current moment, and H is the observation matrix.

5. The method for intelligent mine management and control based on digital twin according to claim 1, characterized in that: In step 5, the optimal control algorithm adopts a dynamic programming optimization update strategy, and the objective function is: Among them, J is the objective function, x ( t ) For the real status of the mine, is the state of the digital twin model, Q is the weighted matrix, R is the weight of the control input, and u ( t ) is the control input, and T is the optimized time window.

6. The method for intelligent mine management and control based on digital twin according to claim 5 is characterized in that: The control input u ( t ) It is calculated by an optimal control algorithm, which is a dynamic programming or reinforcement learning algorithm, used to calculate the optimal update amount at each time step to minimize the error and cost in the objective function J.

7. The method for intelligent mine management and control based on digital twin according to claim 1 is characterized in that: In step 6, the real-time update step is based on the optimal control input of each time step, and the state is updated using the following formula: Among them, u ( t ) is the control input, Represents the control input u that minimizes the subsequent objective function ( t ) , x ( t ) For the real status of the mine, is the state of the digital twin model, Represents the actual state x ( t ) Status with digital twin models The error between represents the control input u ( t ) The cost of the algorithm is , Q is the weight matrix, and R is the weight of the control input.

8. The method for intelligent mine management and control based on digital twin according to claim 7 is characterized in that: The updating step adjusts the operation plan of mine production, including equipment scheduling, ore transportation and resource allocation, according to the real-time sensor data and the updated digital twin model status.

9. The method for intelligent mine management and control based on digital twin according to claim 8, characterized in that: The safety risk assessment of mining operations is performed based on the updated model, and the assessment is performed according to the following formula: Among them, S ( t ) is the security risk assessment value, is a risk prediction function, which represents the combination of the model and real-time data to predict potential safety hazards in mining operations. x ( t ) For the real status of the mine, is the state of the digital twin model, η ( t ) is an external disturbance; The safety risk assessment result S ( t ) It is used to automatically adjust the mining operation process, optimize the operation plan, and implement corresponding preventive measures based on the evaluation results.

10. The method for intelligent mine management and control based on digital twin according to claim 1, characterized in that: The optimization strategy of mine production scheduling is implemented according to the following formula: min{f(prod efficiency), g(envirimpact), h(risk assess)}, Among them, f (prod efficiency) represents the production efficiency optimization function, g (envir impact) is the environmental impact minimization function, and h (risk assess) is the safety risk control function.

Images