Intelligent mine management system and method based on digital twinning

Abstract

The invention relates to the field of mine intelligent management, in particular to a mine intelligent management system and method based on digital twinning. Comprising the following steps: collecting data of different dimensions, and carrying out standardization processing on the data of different dimensions to obtain standardized data of different dimensions; inputting the standardized data of different dimensions into a digital twinborn model, performing dynamic mapping by adopting a digital twinborn state mapping algorithm, and calculating a global state variable of the mine; generating an optimal operation decision of the equipment by using a multi-constraint optimization decision algorithm; and generating an operation instruction of the equipment by using an equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization, and converting the operation instruction of the equipment in the digital twin model into an equipment control signal. The technical problem that unnecessary equipment failure and shutdown may be caused under the condition of resource shortage or unstable equipment state due to the lack of a coordinated and unified control mechanism for operation of multiple pieces of equipment in a mine is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent mine management, and in particular to an intelligent mine management system and method based on digital twins. Background Art

[0002] With the continuous development of mining, resource utilization and safety management, the mining industry is facing complex technical and management challenges. The traditional mine management model relies on manual monitoring, manual recording and basic data analysis, which is inefficient, slow to respond and has a high risk of errors. Therefore, the introduction of intelligent, digital and intelligent management systems for mines has become a key direction for the transformation and upgrading of the mining industry. Against this background, digital twin technology has been gradually applied to the field of mine management, and intelligent mine management systems and methods based on digital twins have emerged. Digital twin technology has brought unprecedented changes to mine management, not only solving many problems in the traditional mine management model, but also providing solid technical support for the intelligent and digital transformation of mines. By collecting data from various aspects of mining equipment, environment, production, etc., a virtual model that is completely consistent with the actual situation of the mine is created, which can realize real-time monitoring, prediction, optimization and intelligent decision-making of mines, improve the production efficiency, safety and sustainability of mines, and promote the mining industry to a more efficient and smarter future.

[0003] However, the existing intelligent mine management methods have the following technical problems: the data provided by sensors are prone to offset and scale differences, which affect the accuracy and consistency of the data; the real-time status monitoring and fault diagnosis of traditional mining equipment rely on static or local perception data, which cannot fully reflect the overall health and operating status of the equipment. When faced with sudden failures or complex working environments, the response speed is slow and it is impossible to warn and adjust the equipment status in time; it is implemented through empirical judgment or simple rules, lacks global optimization and consideration of multiple constraints, and it is difficult for equipment resource consumption and operating efficiency to reach the optimal state. In actual operation, the resource consumption and overall operating efficiency of the equipment may be ignored, resulting in resource waste or equipment damage; the operation of multiple devices in a mine lacks a coordinated and unified control mechanism, which may lead to conflicts, redundant operations or inefficiency between devices. In the case of tight resources or unstable equipment status, it may cause unnecessary equipment failures and downtime; the execution of operating instructions for traditional mining equipment relies on manual intervention or manual adjustment, and lacks an efficient automated instruction generation mechanism. Summary of the invention

[0004] The present invention provides a mine intelligent management system and method based on digital twins to solve the problem that the data provided by sensors are prone to offset and scale differences, affecting the accuracy and consistency of the data; the real-time status monitoring and fault diagnosis of traditional mining equipment rely on static or local perception data, which cannot fully reflect the overall health and operating status of the equipment. When facing sudden failures or complex working environments, the response speed is slow, and it is impossible to warn and adjust the equipment status in time; it is implemented through empirical judgment or simple rules, lacks global optimization and consideration of multiple constraints, and it is difficult for equipment resource consumption and operating efficiency to reach the optimal state. In actual operation, the resource consumption and overall operating efficiency of the equipment may be ignored, resulting in resource waste or equipment damage; the operation of multiple devices in a mine lacks a coordinated and unified control mechanism, which may lead to conflicts, redundant operations or inefficiency between devices, and may cause unnecessary equipment failures and shutdowns when resources are tight or the equipment status is unstable; the execution of operating instructions for traditional mining equipment relies on manual intervention or manual adjustment, and lacks an efficient automated instruction generation mechanism.

[0005] The digital twin-based mine intelligent management system and method of the present invention specifically include the following technical solutions:

[0006] The intelligent mine management method based on digital twins includes the following steps:

[0007] S1: Collect data of different dimensions and perform standardization on the data of different dimensions to obtain standardized data of different dimensions;

[0008] S2: Input the standardized data of different dimensions into the digital twin model, use the digital twin state mapping algorithm for dynamic mapping, and calculate the global state variables of the mine;

[0009] S3: Based on the global state variables of the mine, a multi-constrained optimization decision algorithm is used to generate the optimal operation decision of the equipment;

[0010] S4: Based on the optimal operation decision of the equipment, the equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization is used to generate the equipment operation instructions, the equipment operation instructions are input into the digital twin model, and the equipment operation instructions in the digital twin model are converted into equipment control signals, and sent to the equipment in the mine through the communication network.

[0011] Preferably, the S1 specifically includes:

[0012] The standardization formula is:

[0013]

[0014] Among them, S i(t) represents the data after the standardization of the i-th dimension at time t; x i (t) represents the i-th dimension data collected at time t; μ i represents the historical mean of the i-th dimension data; σ i Represents the historical standard deviation of the i-th dimension data.

[0015] Preferably, the S2 specifically includes:

[0016] The digital twin state mapping algorithm extracts time series features based on standardized data of different dimensions to obtain characteristic values ​​of different dimensions; introduces data real-time weights, and uses an exponential decay function to adjust the data real-time weights.

[0017] Preferably, the S2 specifically includes:

[0018] In the implementation process of the digital twin state mapping algorithm, the instantaneous rate of change is introduced, and the eigenvalues ​​of each input and the weights between the eigenvalues ​​and the global state variables of the mine are weighted summed, and the hyperbolic tangent function is applied to perform nonlinear mapping.

[0019] Preferably, the S2 specifically includes:

[0020] The calculation formula of the global state variable of the mine is:

[0021]

[0022] Among them, M j (t) represents the global state variable of the jth mine at time t; tanh represents the hyperbolic tangent function; Indicates the sum of the n-dimensional standardized data; n represents the total number of dimensions of the data; w ij (t) represents the weight between the eigenvalue of the i-th dimension and the global state variable of the j-th mine at time t; βj represents the bias parameter of the global state variable of the j-th mine; M j (t-Δt) represents the global state variable of the jth mine at time t-Δt, i.e., the historical global state variable; F i (t) represents the eigenvalue of the i-th dimension at time t.

[0023] Preferably, the S3 specifically includes:

[0024] The multi-constraint optimization decision algorithm generates the best operation decision by maximizing the objective function; and establishes global resource constraints, manages the resource consumption of all devices, calculates the sum of the resource consumption of all devices, and compares it with the total resource limit.

[0025] Preferably, the S3 specifically includes:

[0026] The calculation formula for the optimal operation decision is:

[0027]

[0028] in, represents the optimal operation decision set of the kth device at time t; Represents the set of operational decisions that can maximize the objective function; represents the sum of each device in the mine; K represents the number of devices in the mine; represents the sum of each global state variable of the mine, m is the number of global state variables of the mine; c kj (t) represents the influence weight of the global state variable of the jth mine on the operation decision of the kth equipment at time t; M j (t) represents the global state variable of the jth mine at time t; λ represents the penalty factor; R k (A k (t)) represents the resources consumed by the kth device at time t according to the operation decision.

[0029] Preferably, the S3 specifically includes:

[0030] The global resource constraint formula is:

[0031]

[0032] Among them, R k (A k (t)) represents the resources consumed by the kth device according to the operation decision at time t; represents the sum of each device in the mine; R o (t) represents the total resource constraint at time t.

[0033] Preferably, the S4 specifically includes:

[0034] The device closed-loop control and operation instruction generation algorithm based on collaborative optimization uses the collaborative relationship matrix and collaborative relationship weights between devices, adjusts the operation instructions of each device through calculation, and uses the activation function for smooth control. The specific formula is:

[0035]

[0036] Among them, O k (t) represents the operation instruction of the kth device at time t; Sigmoid represents the activation function; α represents the synergistic relationship weight; Represents the operation instruction adjustment item of the kth device; ∑ l≠k Indicates the sum of all devices except the kth device itself; Ckl represents the collaborative relationship matrix between the kth device and the lth device; represents the optimal operation decision of the lth device at time t; represents the optimal operation decision of the kth device at time t.

[0037] The mine intelligent management system based on digital twin includes the following parts:

[0038] Data acquisition module, data preprocessing module, digital twin state mapping module, multi-constraint optimization decision module, and operation instruction generation module;

[0039] Data acquisition module: collects data of different dimensions in real time and outputs the data of different dimensions to the data preprocessing module;

[0040] Data preprocessing module: standardizes the data of different dimensions from the data acquisition module to obtain standardized data of different dimensions, and outputs the standardized data of different dimensions to the digital twin state mapping module;

[0041] Digital twin state mapping module: inputs the standardized data of different dimensions from the data preprocessing module into the digital twin model, uses the digital twin state mapping algorithm for dynamic mapping, calculates the global state variables of the mine, and outputs the global state variables of the mine to the multi-constraint optimization decision module;

[0042] Multi-constraint optimization decision module: Based on the global state variables of the mine in the digital twin state mapping module, the multi-constraint optimization decision algorithm is used to generate the optimal operation decision of the equipment, and the optimal operation decision of the equipment is output to the operation instruction generation module;

[0043] Operation instruction generation module: Based on the optimal operation decision of the equipment based on the multi-constraint optimization decision module, the operation instructions of the equipment are generated using the equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization. The operation instructions of the equipment are input into the digital twin model, and the operation instructions of the equipment in the digital twin model are converted into equipment control signals, which are sent to the equipment in the mine through the communication network.

[0044] The beneficial effects of the technical solution of the present invention are:

[0045] 1. By deploying distributed sensors in mining equipment and mining areas, collecting multi-dimensional data in real time, and standardizing data of different dimensions, the offset and scale differences between data of different dimensions can be eliminated, ensuring the consistency and accuracy of the data, so that subsequent analysis and decision-making are based on unified and reliable data, thereby improving the accuracy and efficiency of condition monitoring of mining equipment.

[0046] 2. Inputting standardized data of different dimensions into the digital twin model and calculating the global state variables of the mine through the digital twin state mapping algorithm can realize real-time monitoring and prediction of the overall operating status of the mine. By extracting and smoothing time series features, the impact of abnormal fluctuations is effectively reduced, ensuring the stability and accuracy of the mine status. At the same time, the introduction of data real-time weights and instantaneous change rates can flexibly respond to external changes or equipment failures, thereby improving the mine's responsiveness and operation and maintenance efficiency.

[0047] 3. By taking weighted sum of the standardized data and historical state variables of different dimensions and using nonlinear mapping of the hyperbolic tangent function, the global state variables of the mine (such as equipment health index, resource mining efficiency, etc.) can be accurately calculated. The calculation of the global state variables of the mine takes into account the instantaneous changes and long-term trends of the standardized data of different dimensions, which helps to make a comprehensive and accurate assessment of the mine operation, thereby improving the accuracy and reliability of operational decisions.

[0048] 4. Use a multi-constraint optimization decision algorithm to generate the optimal operation decision for the equipment based on the global state variables of the mine. It comprehensively considers the resource consumption of the equipment, the relationship between the global state variables and the equipment, and the global resource constraints of the mine, ensuring the optimization of equipment operation. At the same time, it effectively reduces resource consumption, avoids resource overload and equipment failure, ensures the sustainable use of mine resources and the safe and stable operation of equipment, and can maximize the overall operating efficiency of the mine.

[0049] 5. Based on the optimal operation decision of the equipment, accurate operation instructions are generated through the collaborative optimization control algorithm between equipment, which can ensure the efficient collaboration of multiple equipment, avoid redundant operation and interference between equipment, and improve the overall operation efficiency of the mine. Through the smooth control of the activation function, the fluctuation of equipment operation instructions is reduced, and the unstable operation of equipment is avoided.

[0050] 6. Based on digital twin technology, it can monitor the operating status of the mine in real time, automatically generate and adjust the operating instructions of the equipment, reduce human intervention, improve the automation level of mine operations, optimize mine resource allocation, improve production efficiency, and reduce operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a structural diagram of the mine intelligent management system based on digital twins described in the present invention;

[0052] Figure 2 This is a flow chart of the intelligent mine management method based on digital twins described in the present invention. DETAILED DESCRIPTION

[0053] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0055] The specific scheme of the digital twin-based mine intelligent management system and method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0056] Refer to the attached Figure 1 , which shows a structure diagram of a mine intelligent management system based on digital twins provided by an embodiment of the present invention, the system includes the following parts:

[0057] Data acquisition module, data preprocessing module, digital twin state mapping module, multi-constraint optimization decision module, and operation instruction generation module;

[0058] Data acquisition module: deploy sensors to collect data of different dimensions in real time through a distributed sensor network, and output the data of different dimensions to the data preprocessing module;

[0059] Data preprocessing module: standardizes the data of different dimensions from the data acquisition module to obtain standardized data of different dimensions, and outputs the standardized data of different dimensions to the digital twin state mapping module;

[0060] Digital twin state mapping module: inputs the standardized data of different dimensions from the data preprocessing module into the digital twin model, uses the digital twin state mapping algorithm for dynamic mapping, calculates the global state variables of the mine, and outputs the global state variables of the mine to the multi-constraint optimization decision module;

[0061] Multi-constraint optimization decision module: Based on the global state variables of the mine in the digital twin state mapping module, the multi-constraint optimization decision algorithm is used to generate the optimal operation decision of the equipment, and the optimal operation decision of the equipment is output to the operation instruction generation module;

[0062] Operation instruction generation module: Based on the optimal operation decision of the equipment based on the multi-constraint optimization decision module, the equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization is used to generate the equipment's operation instructions, and the equipment's operation instructions are input into the digital twin model. The equipment's operation instructions in the digital twin model are converted into specific equipment control signals, and sent to the mine's equipment through the communication network.

[0063] Refer to the attached Figure 2 , which shows a flow chart of a mine intelligent management method based on digital twins provided by an embodiment of the present invention, the method comprising the following steps:

[0064] S1. Collect data of different dimensions and perform standardization on the data of different dimensions to obtain standardized data of different dimensions;

[0065] Sensors are deployed on mining equipment (such as crushers, conveyor belts, pumps, and drills) and mining areas (such as pits, mines, and mining equipment operation points). The types of sensors include but are not limited to accelerometers, pressure sensors, temperature sensors, humidity sensors, and vibration sensors. Data of different dimensions are collected in real time through a distributed sensor network. 1 (t), x 2 (t), ..., x i (t), ..., x n (t)}, where x i (t) represents the i-th dimension data collected at time t, such as vibration data and temperature data, and n represents the total number of dimensions of the data; and the data of different dimensions are standardized to obtain standardized data of different dimensions; the standardization eliminates the offset influence of the data of different dimensions by subtracting the historical mean, and eliminates the scale difference of the data of different dimensions by dividing by the historical standard deviation, so that the data of different dimensions have a unified distribution range, ensuring that the data of different dimensions maintain accuracy and consistency;

[0066] The standardization formula is:

[0067]

[0068] Among them, S i (t) represents the data after the standardization of the i-th dimension at time t; x i (t) represents the i-th dimension data collected at time t, such as vibration data and temperature data; μi represents the historical mean of the i-th dimension data, which is used to reflect the central trend of the i-th dimension data; σ i Represents the historical standard deviation of the i-th dimension data, which is used to measure the degree of dispersion of the i-th dimension data;

[0069] S2. Input the standardized data of different dimensions into the digital twin model, use the digital twin state mapping algorithm for dynamic mapping, and calculate the global state variables of the mine;

[0070] The standardized data of different dimensions are input into the digital twin model, and the digital twin state mapping algorithm is used for dynamic mapping to calculate the global state variables of the mine. The parameters of the digital twin model are continuously adjusted through the optimization process to improve the accuracy of the global state variables of the mine.

[0071] The digital twin state mapping algorithm extracts time series features based on data standardized in different dimensions. In the feature extraction process, the current moment standardized data in different dimensions is used to reflect the immediate state. The data standardized in different dimensions over a period of time in the past are integrated and averaged to reflect the data trend over a period of time in the past. This plays a role in smoothing data fluctuations, helps smooth sudden abnormal data, and provides a smooth trend analysis. The current moment standardized data in different dimensions are combined with the standardized data in different dimensions over a period of time in the past, so that the digital twin state mapping algorithm can simultaneously take into account the instantaneous changes and long-term trends of the standardized data in different dimensions.

[0072] At the same time, data real-time weights are introduced to balance the impact of standardized data of different dimensions at the current moment and standardized data of different dimensions in the past period of time. The exponential decay function can be used to automatically adjust the data real-time weights according to the fluctuation of standardized data of different dimensions. When the standardized data of different dimensions changes dramatically, the real-time standardized data is crucial, and people tend to rely on the real-time standardized data; when the standardized data changes steadily, the historical standardized data can provide a stable reference, and people tend to rely on the historical standardized data;

[0073] By introducing the instantaneous rate of change, the digital twin state mapping algorithm can respond to external changes or equipment failures in a timely manner;

[0074] The global state variables of the mine are used to reflect the operation status of the entire mine. In order to calculate the global state variables of the mine, the eigenvalues ​​of each input and the weights between the eigenvalues ​​and the global state variables of the mine are weighted and summed. At the same time, the influence of historical global state variables is considered to avoid misleading short-term fluctuations, and the hyperbolic tangent function is applied to provide nonlinear mapping;

[0075] The calculation formula of the global state variable of the mine is:

[0076]

[0077] Among them, M j(t) represents the global state variable of the jth mine at time t, reflecting the overall operation status of the mine, such as the mine equipment health index and resource mining efficiency; tanh represents the hyperbolic tangent function, providing nonlinear mapping; Indicates the sum of the n-dimensional standardized data; w ij (t) represents the weight between the eigenvalue of the i-th dimension and the global state variable of the j-th mine at time t; β j represents the bias parameter of the global state variable of the jth mine; M j (t-Δt) represents the global state variable of the jth mine at time t-Δt, i.e., the historical global state variable; F i (t) represents the eigenvalue of the i-th dimension at time t, and the calculation formula is:

[0078]

[0079] Among them, S i (t) represents the data after the i-th dimension is standardized at time t; γ represents the real-time weight of the data, which is used to balance the influence of the data after the i-th dimension is standardized at time t and the data after different dimensions are standardized in the past period of time. The calculation formula is: The exponential decay function can be used to automatically adjust the real-time weight of data according to the degree of fluctuation of standardized data of different dimensions. When the standardized data changes dramatically, the real-time standardized data is crucial, and people tend to rely on the real-time standardized data; when the standardized data changes steadily, the historical standardized data can provide a stable reference, and people tend to rely on the historical standardized data. κ represents the sensitivity parameter of the real-time weight adjustment of data, which is used to control the influence of the fluctuation amplitude on the real-time weight of data. It can be set according to the specific implementation scenario and is not limited here. It represents the standard deviation of the data after the i-th dimension is standardized at time t, reflecting the volatility of the data after standardization in different dimensions; It represents the average value of the standardized data of the i-th dimension in the past Δt period. Specifically, it integrates the standardized data of the i-th dimension at time τ in the time interval [t-Δt, t], and averages the integration results to reflect the data trend in the past period of time and play a role in smoothing data fluctuations. i (τ) represents the data after normalization of the i-th dimension at time τ; Δt represents the length of the time window, which can be set according to the specific implementation scenario and is not limited here; T represents the integral variable; represents the instantaneous change rate of the data after standardization of the i-th dimension at time t; ξ represents the weight of the instantaneous change rate, which determines the importance of the instantaneous change rate of the data after standardization of different dimensions in the feature. The calculation formula is: ΔS i(t) represents the change in the data after the i-th dimension is standardized at time t, which is obtained by calculating the difference between the current value and the previous value of the data after the i-th dimension is standardized; ∈ represents a constant to avoid division by zero, which is a very small positive number used to ensure that the denominator will not be zero; max(|ΔS i (t)|,∈) means taking the maximum value to ensure that there will be no extremely small changes in the data after normalization of different dimensions in the calculation;

[0080] S3, based on the global state variables of the mine, use the multi-constrained optimization decision algorithm to generate the optimal operation decision of the equipment;

[0081] Based on the global state variables of the mine, a multi-constrained optimization decision algorithm is used to generate the optimal operation decision of the equipment;

[0082] The multi-constrained optimization decision algorithm generates the optimal operation decision by maximizing the objective function. The objective function comprehensively considers the relationship between the global state variables of the mine and the equipment, the resource consumption of the equipment, and the penalty factor. By maximizing the objective function, the optimal operation decision of the equipment can be found to ensure the minimization of mine resource consumption and the optimization of equipment operation, and to ensure the stability of the overall operation of the mine under the global resource constraint conditions;

[0083] To ensure that the overall resources do not exceed the limit, the multi-constrained optimization decision algorithm needs to uniformly manage the resource consumption of all equipment, calculate the sum of the resource consumption of all equipment, and ensure that it does not exceed the total resources available in the mine, avoiding equipment failure or reduced production efficiency due to resource overload;

[0084] To ensure safe and efficient operation of the equipment, the operation decision of each equipment must be within a reasonable working range, which is set by the equipment design parameters;

[0085] The calculation formula for the optimal operation decision is:

[0086]

[0087] in, represents the optimal operation decision set of the kth device at time t. The optimal operation decision set includes the personalized operation decisions of all K devices in the mine; Represents the set of operational decisions that can maximize the objective function; It means to sum each device in the mine, and there are K devices in total; represents the sum of each global state variable of the mine, m is the number of global state variables of the mine; c kj (t) represents the influence weight of the global state variable of the jth mine on the operation decision of the kth equipment at time t; M j(t) represents the global state variable of the jth mine at time t, reflecting the overall operation status of the mine, such as the mine equipment health index and resource mining efficiency; λ represents the penalty factor, which is used to adjust the weight of resource consumption and can be set according to the specific implementation scenario, and is not limited here; R k (A k (t)) represents the resources consumed by the kth device at time t according to the operation decision, such as fuel consumption and operating time;

[0088] Global resource constraint formula:

[0089]

[0090] Among them, R k (A k (t)) represents the resources consumed by the kth device at time t according to the operation decision, such as fuel consumption and operating time; It means to sum up each device in the mine, there are K devices in total; R o (t) represents the total resource limit at time t, which can be set according to the specific implementation scenario and is not limited here;

[0091] Global resource constraints can ensure that the total resources consumed by the equipment according to the operation decision cannot exceed the total resource limit of the mine, preventing the mine's resource carrying capacity from being exceeded, thereby ensuring the sustainable operation of the mine;

[0092] Equipment operation status constraint formula:

[0093] A k (t)∈Y k

[0094] Among them, A k (t) represents the operation decision of the kth device at time t; ∈ represents belonging to; Y k represents the feasible operating range of the kth device, which is set by the device design parameters;

[0095] Equipment operating state constraints can ensure that the equipment's operating decisions are within the feasible operating range, preventing the equipment from exceeding design limits, thereby avoiding equipment damage or unsafe operation;

[0096] S4. Based on the optimal operation decision of the equipment, use the equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization to generate the equipment operation instructions, input the equipment operation instructions into the digital twin model, and convert the equipment operation instructions in the digital twin model into equipment control signals, and send them to the equipment in the mine through the communication network;

[0097] Based on the optimal operation decision of the equipment, the equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization is used to generate the equipment operation instructions;

[0098] The device closed-loop control and operation instruction generation algorithm based on collaborative optimization utilizes the collaborative relationship matrix and collaborative relationship weights between devices, adjusts the operation instructions of each device through calculation, and performs smooth control through activation functions to avoid excessive fluctuations in the operation instructions, resulting in unstable operation of the device;

[0099] The formula for generating the device's operating instructions is:

[0100]

[0101] Among them, O k (t) represents the operation instruction of the kth device at time t; Sigmoid represents the activation function, which is used for smooth control to avoid excessive fluctuations in the operation instructions, resulting in unstable operation of the device; α represents the synergy relationship weight, which is used to adjust the degree of influence of the synergy effect between devices, which can be set according to the specific implementation scenario and is not limited here; represents the operation instruction adjustment item of the kth device, which is determined by the synergy relationship between the kth device and the lth device and the difference in the optimal operation decision; ∑l ≠k Indicates the sum of all devices except the kth device itself; C kl It represents the coordination relationship matrix between the kth device and the lth device, which is set according to the actual operation status of the devices and the task coordination situation; represents the optimal operation decision of the lth device at time t; represents the optimal operation decision of the kth device at time t;

[0102] Through collaborative optimization, it can ensure that multiple devices can work together efficiently during operation, avoid unnecessary interference and redundancy between devices, and improve the overall operation efficiency of the mine;

[0103] The operating instructions of the equipment are input into the digital twin model, and the operating instructions of the equipment in the digital twin model are converted into specific equipment control signals and sent to the equipment in the mine through the communication network.

[0104] In summary, the digital twin-based mine intelligent management system and method have been completed.

[0105] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0106] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. The intelligent mine management method based on digital twin is characterized by: The following steps are involved: S1: Collect data of different dimensions and perform standardization on the data of different dimensions to obtain standardized data of different dimensions; S2: Input the standardized data of different dimensions into the digital twin model, use the digital twin state mapping algorithm for dynamic mapping, and calculate the global state variables of the mine; S3: Based on the global state variables of the mine, a multi-constrained optimization decision algorithm is used to generate the optimal operation decision of the equipment; S4: Based on the optimal operation decision of the equipment, the equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization is used to generate the equipment operation instructions, the equipment operation instructions are input into the digital twin model, and the equipment operation instructions in the digital twin model are converted into equipment control signals, and sent to the equipment in the mine through the communication network.

2. The method for intelligent mine management based on digital twin according to claim 1, characterized in that: The S1 specifically includes: The standardization formula is: Among them, S i (t) represents the data after the standardization of the i-th dimension at time t; x i (t) represents the i-th dimension data collected at time t; μ i represents the historical mean of the i-th dimension data; σ i Represents the historical standard deviation of the i-th dimension data.

3. The method for intelligent mine management based on digital twin according to claim 1, characterized in that: The S2 specifically includes: The digital twin state mapping algorithm extracts time series features based on standardized data of different dimensions to obtain characteristic values ​​of different dimensions; introduces data real-time weights, and uses an exponential decay function to adjust the data real-time weights.

4. The method for intelligent mine management based on digital twin according to claim 3 is characterized in that: The S2 specifically includes: In the implementation process of the digital twin state mapping algorithm, the instantaneous rate of change is introduced, and the eigenvalues ​​of each input and the weights between the eigenvalues ​​and the global state variables of the mine are weighted summed, and the hyperbolic tangent function is applied to perform nonlinear mapping.

5. The method for intelligent mine management based on digital twin according to claim 4 is characterized in that: The S2 specifically includes: The calculation formula of the global state variable of the mine is: Among them, M j (t) represents the global state variable of the jth mine at time t; tanh represents the hyperbolic tangent function; Indicates the sum of the n-dimensional standardized data; n represents the total number of dimensions of the data; w ij (t) represents the weight between the eigenvalue of the i-th dimension and the global state variable of the j-th mine at time t; βj represents the bias parameter of the global state variable of the j-th mine; M j (t-Δt) represents the global state variable of the jth mine at time t-Δt, i.e., the historical global state variable; F i (t) represents the eigenvalue of the i-th dimension at time t.

6. The method for intelligent mine management based on digital twin according to claim 1, characterized in that: The S3 specifically includes: The multi-constraint optimization decision algorithm generates the best operation decision by maximizing the objective function; and establishes global resource constraints, manages the resource consumption of all devices, calculates the sum of the resource consumption of all devices, and compares it with the total resource limit.

7. The method for intelligent mine management based on digital twin according to claim 6, characterized in that: The S3 specifically includes: The calculation formula for the optimal operation decision is: in, represents the optimal operation decision set of the kth device at time t; Represents the set of operational decisions that can maximize the objective function; represents the sum of each device in the mine; K represents the number of devices in the mine; represents the sum of each global state variable of the mine, m is the number of global state variables of the mine; c kj (t) represents the influence weight of the global state variable of the jth mine on the operation decision of the kth equipment at time t; M j (t) represents the global state variable of the jth mine at time t; λ represents the penalty factor; R k (A k (t)) represents the resources consumed by the kth device at time t according to the operation decision.

8. The method for intelligent mine management based on digital twin according to claim 7, characterized in that: The S3 specifically includes: The global resource constraint formula is: Among them, R k (A k (t)) represents the resources consumed by the kth device according to the operation decision at time t; represents the sum of each device in the mine; R o (t) represents the total resource constraint at time t.

9. The method for intelligent mine management based on digital twin according to claim 1, characterized in that: The S4 specifically includes: The device closed-loop control and operation instruction generation algorithm based on collaborative optimization uses the collaborative relationship matrix and collaborative relationship weights between devices, adjusts the operation instructions of each device through calculation, and uses the activation function for smooth control. The specific formula is: Among them, O k (t) represents the operation instruction of the kth device at time t; Sigmoid represents the activation function; α represents the synergistic relationship weight; Represents the operation instruction adjustment item of the kth device; ∑ l≠k Indicates the sum of all devices except the kth device itself; C kl represents the collaborative relationship matrix between the kth device and the lth device; represents the optimal operation decision of the lth device at time t; represents the optimal operation decision of the kth device at time t.

10. A mine intelligent management system based on digital twins, applied to the mine intelligent management method based on digital twins as claimed in claim 1, characterized in that: Includes the following parts: Data acquisition module, data preprocessing module, digital twin state mapping module, multi-constraint optimization decision module, and operation instruction generation module; Data acquisition module: collects data of different dimensions in real time and outputs the data of different dimensions to the data preprocessing module; Data preprocessing module: standardizes the data of different dimensions from the data acquisition module to obtain standardized data of different dimensions, and outputs the standardized data of different dimensions to the digital twin state mapping module; Digital twin state mapping module: inputs the standardized data of different dimensions from the data preprocessing module into the digital twin model, uses the digital twin state mapping algorithm for dynamic mapping, calculates the global state variables of the mine, and outputs the global state variables of the mine to the multi-constraint optimization decision module; Multi-constraint optimization decision module: Based on the global state variables of the mine in the digital twin state mapping module, the multi-constraint optimization decision algorithm is used to generate the optimal operation decision of the equipment, and the optimal operation decision of the equipment is output to the operation instruction generation module; Operation instruction generation module: Based on the optimal operation decision of the equipment based on the multi-constraint optimization decision module, the operation instructions of the equipment are generated using the equipment closed-loop control and operation instruction generation algorithm based on collaborative optimization. The operation instructions of the equipment are input into the digital twin model, and the operation instructions of the equipment in the digital twin model are converted into equipment control signals, which are sent to the equipment in the mine through the communication network.

Images