Coal mine intelligent ventilation optimization regulation and control method and system based on digital twinning

Abstract

The application discloses a coal mine intelligent ventilation optimization regulation and control method and system based on digital twinning, and belongs to the technical field of coal mine safety ventilation. The method comprises the following steps: determining the three-dimensional space topological relationship of the coal mine ventilation system based on mine structure data, and mapping real-time ventilation state data to corresponding roadway nodes and branch paths to obtain a twinned ventilation state; performing simulation calculation based on the three-dimensional space topological relationship to obtain a theoretical ventilation distribution state, comparing the twinned ventilation state with the theoretical ventilation distribution state, determining a wind volume deviation area and a gas concentration abnormal area, obtaining a ventilation deviation feature to perform virtual pre-performance, determining an adjustment scheme meeting ventilation demand constraints and energy consumption constraints, and generating an optimized regulation and control instruction; controlling the entity ventilation facilities to perform adjustment actions, and updating the three-dimensional space topological relationship by using feedback data. The application realizes accurate regulation and control and dynamic optimization of the ventilation system, and improves the safety and energy-saving effect of the coal mine ventilation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal mine safety ventilation, and particularly relates to a coal mine intelligent ventilation optimization regulation method and system based on digital twinning. BACKGROUND

[0002] In the safety production of coal mines, the ventilation system is the core system for protecting the lives of underground workers and maintaining normal production order. Its operation efficiency and regulation accuracy are directly related to the safety level of the mine. Traditional coal mine ventilation management mainly relies on manual experience for air volume distribution and adjustment. Ventilation parameters are obtained through regular inspection and manual measurement, and then artificial analysis and decision-making are performed according to the ventilation network calculation theory. With the increasing depth of coal mining and the increasing complexity of roadway layout, the dynamic characteristics and nonlinear features of the ventilation system become more and more prominent, and the traditional ventilation management method has been difficult to meet the safety production needs of modern mines.

[0003] In recent years, with the development of Internet of Things technology, sensor technology and computer simulation technology, coal mine ventilation systems have gradually transformed towards intelligence and automation. Some mines have deployed ventilation parameter monitoring systems that can collect real-time wind speed, wind pressure, gas concentration and other key parameters, and perform ventilation network calculation through computer software to provide data support for ventilation management. At the same time, digital twinning technology, as a new technology that deeply integrates physical entities and virtual models, has been widely applied in industrial manufacturing, urban management and other fields, providing a new technical path for the intelligent management of coal mine ventilation systems. The existing coal mine ventilation management technology still has many shortcomings. First, there is a lack of effective spatial mapping mechanism between the ventilation data collected by the existing monitoring system and the ventilation network model. Real-time monitoring data often exists in discrete point form, making it difficult to accurately reflect the spatial distribution state of the entire ventilation system, resulting in a disconnection between monitoring data and theoretical calculation model, and failing to truly depict the actual operation status of the ventilation system, affecting the accuracy and timeliness of ventilation anomaly identification. The existing ventilation regulation method is mainly based on static ventilation network calculation. When adjusting the ventilation facilities, there is a lack of pre-verification mechanism for the adjustment effect, and the adjustment scheme often relies on the experience judgment of engineering and technical personnel, making it difficult to accurately predict the ventilation effect after adjustment, and prone to problems such as insufficient air volume in local areas or energy waste due to improper adjustment. The blindness and randomness of adjustment are large, and it is difficult to achieve precise regulation. The monitoring, analysis, decision-making and execution in the existing ventilation management system are relatively independent, and there is a lack of closed-loop feedback mechanism. The effect data after adjustment implementation cannot be fed back to the simulation model for model correction, resulting in a gradual accumulation of the deviation between the theoretical model and the actual ventilation system, a continuous decline in the accuracy of simulation calculation, and a failure to achieve dynamic optimization and continuous improvement of the ventilation system, limiting the intelligent level of ventilation management. SUMMARY

[0004] The embodiment of the present application provides a coal mine intelligent ventilation optimization regulation method and system based on digital twinning, and at least can solve some problems existing in the prior art.

[0005] In a first aspect, the embodiment of the present application provides a coal mine intelligent ventilation optimization regulation method based on digital twinning, comprising:

[0006] obtaining real-time ventilation state data and mine structure data under a coal mine;

[0007] determining a three-dimensional spatial topological relationship of a coal mine ventilation system based on the mine structure data, and mapping the real-time ventilation state data to corresponding roadway nodes and branch paths according to spatial coordinates to obtain a twinned ventilation state;

[0008] performing simulation calculation based on the three-dimensional spatial topological relationship to obtain a theoretical ventilation distribution state, comparing the twinned ventilation state with the theoretical ventilation distribution state to determine a wind volume deviation area and a gas concentration abnormal area, and obtaining a ventilation deviation feature;

[0009] virtually pre-acting on an adjustment state of a ventilation facility in the three-dimensional spatial topological relationship according to the ventilation deviation feature, determining an adjustment scheme meeting ventilation demand constraints and energy consumption constraints, and generating an optimization regulation instruction based on the adjustment scheme;

[0010] controlling corresponding entity ventilation facilities to perform adjustment actions based on the optimization regulation instruction, collecting real-time ventilation state data after adjustment as feedback data, and updating the three-dimensional spatial topological relationship by using the feedback data to keep consistency between simulation calculation and actual ventilation conditions.

[0011] determining a three-dimensional spatial topological relationship of a coal mine ventilation system based on the mine structure data, and mapping the real-time ventilation state data to corresponding roadway nodes and branch paths according to spatial coordinates to obtain a twinned ventilation state, comprising:

[0012] determining a roadway connectivity relationship based on roadway topological data in the mine structure data, and determining node positions and branch connection relationships of air flow paths based on ventilation facility position data in the mine structure data to obtain the three-dimensional spatial topological relationship;

[0013] extracting spatial coordinate information of each measurement point data in the real-time ventilation state data, and calculating spatial distances between the measurement point data and each roadway node in the three-dimensional spatial topological relationship for the spatial coordinate information of each measurement point data;

[0014] selecting a roadway node matched with each measurement point data based on the spatial distances, and taking a roadway node identifier of the matched roadway node as a roadway node identifier to which the corresponding measurement point data belongs.

[0015] Based on the roadway node identification, the air volume distribution data, the air pressure distribution data and the gas concentration distribution data of the corresponding measuring point are associated with the branch path between the roadway node and the adjacent node;

[0016] According to the wind flow continuity constraint, the real-time ventilation state data on the branch path between the adjacent nodes is interpolated to obtain the twin ventilation state corresponding to all nodes and branch paths of the three-dimensional space topology.

[0017] Based on the three-dimensional space topology, a simulation calculation is performed to obtain a theoretical ventilation distribution state. The twin ventilation state is compared with the theoretical ventilation distribution state to determine an air volume deviation area and a gas concentration abnormal area, and obtain a ventilation deviation feature, including:

[0018] The roadway nodes in the three-dimensional space topology are taken as network nodes, and the branch paths are taken as network branches. A ventilation network solving equation is used to solve the ventilation network to obtain the theoretical air pressure value of each network node and the theoretical air volume value of each network branch, which are taken as the theoretical ventilation distribution state.

[0019] Based on the measured air volume value of each roadway node in the twin ventilation state and the theoretical air volume value of the corresponding network node in the theoretical ventilation distribution state, the air volume deviation area is determined.

[0020] The measured gas concentration value of each roadway node in the twin ventilation state is compared with the ventilation safety concentration limit value node by node to determine the roadway node whose measured gas concentration value exceeds the ventilation safety concentration limit value. Based on the over-limit roadway node and the nodes in its coverage range in the spatial continuous distribution, a gas concentration abnormal area is determined.

[0021] Based on the air volume deviation area, the gas concentration abnormal area and the regional spatial range, the ventilation deviation feature is obtained.

[0022] Based on the measured air volume value of each roadway node in the twin ventilation state and the theoretical air volume value of the corresponding network node in the theoretical ventilation distribution state, the air volume deviation area is determined, including:

[0023] According to the mapping relationship between the roadway node identification in the twin ventilation state and the network node number in the theoretical ventilation distribution state, the measured air volume value of the roadway node with the same spatial position and the theoretical air volume value of the corresponding network node are determined.

[0024] The difference between the measured air volume value of the roadway node and the theoretical air volume value of the corresponding network node at each same spatial position is calculated to obtain the air volume deviation value of each roadway node.

[0025] The air volume deviation value is processed to obtain a relative deviation rate, the relative deviation rate is compared with a preset air volume deviation judgment criterion, and a roadway node with a relative deviation rate exceeding the air volume deviation judgment criterion is determined as a deviation node;

[0026] Based on the spatial connection relationship between the deviation nodes in the three-dimensional space topology relationship, the deviation nodes connected by a direct branch path are clustered into a same deviation area group;

[0027] The node identifier, air volume deviation value, relative deviation rate, and branch path identifier connecting the deviation nodes of all the deviation nodes in each deviation area group are extracted to obtain the air volume deviation area.

[0028] According to the ventilation deviation feature, a virtual pre-visualization of the adjustment state of the ventilation facility in the three-dimensional space topology relationship is performed, an adjustment scheme meeting the ventilation demand constraint and the energy consumption constraint is determined, and an optimized regulation and control instruction is generated based on the adjustment scheme, including:

[0029] According to the ventilation deviation feature, a target area to be adjusted is determined in the three-dimensional space topology relationship, and a candidate adjustment object is determined as a ventilation facility affecting the ventilation state of the target area according to the connection path of the target area in the three-dimensional space topology relationship;

[0030] A plurality of groups of virtual adjustment parameters are determined for each candidate adjustment object, the virtual adjustment parameters are applied to the boundary conditions of the corresponding ventilation facility in the three-dimensional space topology relationship, virtual pre-visualization calculation is performed by using a ventilation network solving equation, and a pre-visualization ventilation distribution state corresponding to each group of virtual adjustment parameters is obtained;

[0031] The pre-visualization air volume value and the pre-visualization gas concentration value of the target area are extracted from each pre-visualization ventilation distribution state, and a candidate adjustment parameter group meeting the ventilation demand constraint and the ventilation safety concentration constraint is selected based on the pre-visualization air volume value and the pre-visualization gas concentration value;

[0032] The total energy consumption value of the ventilation system corresponding to each candidate adjustment parameter group is calculated, one candidate adjustment parameter group is selected as an optimal adjustment parameter group based on the total energy consumption value of the ventilation system, and the adjustment scheme is obtained;

[0033] The optimal adjustment parameter group of each candidate adjustment object in the adjustment scheme is converted into an action instruction of the corresponding ventilation facility, and the optimized regulation and control instruction is generated.

[0034] A plurality of groups of virtual adjustment parameters are determined for each candidate adjustment object, the virtual adjustment parameters are applied to the boundary conditions of the corresponding ventilation facility in the three-dimensional space topology relationship, virtual pre-visualization calculation is performed by using a ventilation network solving equation, and a pre-visualization ventilation distribution state corresponding to each group of virtual adjustment parameters is obtained, including:

[0035] determine a physical dimension and a value boundary of the adjustment parameter according to the facility type and the current adjustment state parameter of each candidate adjustment object;

[0036] generate a plurality of virtual adjustment parameter values within the value boundary based on the value boundary and the current adjustment state parameter, and arrange the virtual adjustment parameter values in sequence to obtain a virtual adjustment parameter sequence;

[0037] combine each virtual adjustment parameter value in the virtual adjustment parameter sequence with the identifier of the candidate adjustment object to obtain a plurality of groups of virtual adjustment parameters;

[0038] determine the location of the corresponding ventilation facility of each candidate adjustment object in the three-dimensional space topological relationship, and update the boundary condition value of the location of the corresponding ventilation facility in the three-dimensional space topological relationship based on each group of virtual adjustment parameters;

[0039] for the three-dimensional space topological relationship updated for each group of virtual adjustment parameters, solve the theoretical wind pressure value of each network node and the theoretical wind volume value of each network branch using a ventilation network solving equation to obtain the corresponding each group of virtual adjustment parameters;

[0040] combine the network node theoretical wind pressure value and the network branch theoretical wind volume value corresponding to each group of virtual adjustment parameters to determine the pre-play ventilation distribution state corresponding to each group of virtual adjustment parameters.

[0041] based on the optimization control instruction, control the corresponding entity ventilation facility to perform an adjustment action, and collect real-time ventilation state data after adjustment as feedback data, and update the three-dimensional space topological relationship using the feedback data to maintain consistency between simulation calculation and actual ventilation conditions, including:

[0042] based on the identifier of each candidate adjustment object in the optimization control instruction, determine the communication interface of the corresponding entity ventilation facility;

[0043] issue a control instruction to the corresponding entity ventilation facility through the communication interface to drive the entity ventilation facility to perform an adjustment action, and receive an adjustment completion state signal feedback by the entity ventilation facility, and record the actual adjustment parameter value of each entity ventilation facility;

[0044] after the entity ventilation facility completes the adjustment action, collect real-time ventilation state data of each monitoring point after adjustment through a real-time monitoring sensor network as the feedback data;

[0045] based on the feedback data and the actual adjustment parameter value, calculate the actual adjustment response characteristics;

[0046] According to the actual adjustment response characteristic and the actual adjustment parameter value, a wind resistance characteristic parameter of a network node or a network branch where a corresponding ventilation facility in the three-dimensional space topological relationship is located is corrected, and a gas concentration measurement value in the feedback data is updated to a gas concentration attribute value of a corresponding roadway node in the three-dimensional space topological relationship, so as to keep consistency between simulation calculation and actual ventilation condition.

[0047] In a second aspect, the embodiment of the present application provides a coal mine intelligent ventilation optimization and regulation system based on digital twinning, which comprises:

[0048] A first unit is configured to acquire real-time ventilation state data and mine structure data of a coal mine underground;

[0049] A second unit is configured to determine a three-dimensional space topological relationship of a coal mine ventilation system based on the mine structure data, and map the real-time ventilation state data to corresponding roadway nodes and branch paths according to spatial coordinates to obtain a twinned ventilation state;

[0050] A third unit is configured to perform simulation calculation based on the three-dimensional space topological relationship to obtain a theoretical ventilation distribution state, compare the twinned ventilation state with the theoretical ventilation distribution state, determine a wind volume deviation area and a gas concentration abnormal area, and obtain a ventilation deviation feature;

[0051] A fourth unit is configured to virtually pre-act on an adjustment state of a ventilation facility in the three-dimensional space topological relationship according to the ventilation deviation feature, determine an adjustment scheme that meets ventilation demand constraints and energy consumption constraints, and generate an optimization and regulation instruction based on the adjustment scheme;

[0052] A fifth unit is configured to control a corresponding physical ventilation facility to perform an adjustment action based on the optimization and regulation instruction, acquire real-time ventilation state data after the adjustment as feedback data, and update the three-dimensional space topological relationship by using the feedback data, so as to keep consistency between simulation calculation and actual ventilation condition.

[0053] In a third aspect, the embodiment of the present application provides an electronic device, which comprises:

[0054] A processor;

[0055] A memory for storing processor-executable instructions;

[0056] The processor is configured to invoke the instructions stored in the memory to execute the method described above.

[0057] In a fourth aspect, the embodiment of the present application provides a computer readable storage medium, which stores computer program instructions, and the computer program instructions are executed by a processor to implement the method described above.

[0058] The present application realizes accurate mapping of real-time ventilation state data and three-dimensional space topology by constructing a digital twin model of a coal mine ventilation system, can intuitively reflect the actual operation status of the underground ventilation system, provides a visual digital basis for ventilation management, and solves the problems of information dispersion and non-intuitive state perception in traditional ventilation management.

[0059] By comparing the twin ventilation state with the theoretical ventilation distribution state, the present application can timely identify the air volume deviation area and the gas concentration abnormal area, and perform virtual pre-rehearsal of ventilation facility adjustment based on the three-dimensional space topology relationship, so as to evaluate the adjustment effect before actual regulation and control, ensure that the adjustment scheme meets the ventilation demand constraint and the energy consumption constraint, effectively avoid safety risks and energy waste caused by blind adjustment, and improve the scientificity and accuracy of ventilation regulation and control.

[0060] The present application establishes a closed-loop regulation and control mechanism from data acquisition, deviation identification, scheme optimization to execution feedback, continuously updates the three-dimensional space topology relationship by taking the adjusted real-time ventilation state data as feedback, maintains the dynamic consistency of the digital twin model and the actual ventilation system, realizes adaptive optimization adjustment of the ventilation system, and improves the intelligent management level and operation efficiency of the coal mine ventilation system. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 A flowchart of the coal mine intelligent ventilation optimization regulation and control method based on digital twinning of the present application embodiment.

[0062] Figure 2 A flowchart of determining the air volume deviation area of the present application embodiment. DETAILED DESCRIPTION

[0063] To make the purpose, technical scheme and advantages of the present application embodiment clearer, the technical scheme of the present application embodiment will be described clearly and completely below in combination with the drawings of the present application embodiment. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0064] The technical scheme of the present application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments.

[0065] Figure 1 A flowchart of the coal mine intelligent ventilation optimization regulation and control method based on digital twinning of the present application embodiment. As shown in Figure 1 the method comprises:

[0066] obtain real-time ventilation state data and mine structure data of a coal mine underground;

[0067] determine a three-dimensional spatial topological relationship of a coal mine ventilation system based on the mine structure data, and map the real-time ventilation state data to corresponding roadway nodes and branch paths according to spatial coordinates to obtain a twin ventilation state;

[0068] perform simulation calculation based on the three-dimensional spatial topological relationship to obtain a theoretical ventilation distribution state, compare the twin ventilation state with the theoretical ventilation distribution state, determine a wind volume deviation area and a gas concentration abnormal area, and obtain a ventilation deviation feature;

[0069] based on the ventilation deviation feature, virtually simulate adjustment of ventilation facilities in the three-dimensional spatial topological relationship, determine an adjustment scheme that meets ventilation demand constraints and energy consumption constraints, and generate an optimized regulation and control instruction based on the adjustment scheme;

[0070] based on the optimized regulation and control instruction, control corresponding physical ventilation facilities to perform adjustment actions, collect real-time ventilation state data after adjustment as feedback data, and update the three-dimensional spatial topological relationship using the feedback data to maintain consistency between simulation calculation and actual ventilation conditions.

[0071] In an alternative embodiment, based on the mine structure data, a three-dimensional spatial topological relationship of a coal mine ventilation system is determined, and the real-time ventilation state data is mapped to corresponding roadway nodes and branch paths according to spatial coordinates to obtain a twin ventilation state, including:

[0072] determine a roadway connectivity relationship based on roadway topological data in the mine structure data, and determine node positions and branch connection relationships of air flow paths based on ventilation facility position data in the mine structure data to obtain the three-dimensional spatial topological relationship;

[0073] extract spatial coordinate information of each measurement point data in the real-time ventilation state data, and for the spatial coordinate information of each measurement point data, calculate spatial distances between the measurement point data and each roadway node in the three-dimensional spatial topological relationship;

[0074] based on the spatial distances, select roadway nodes that match each measurement point data, and take roadway node identifiers of the matched roadway nodes as roadway node identifiers to which the corresponding measurement point data belongs;

[0075] based on the roadway node identifiers, associate wind volume distribution data, wind pressure distribution data, and gas concentration distribution data of the corresponding measurement points with branch paths between the roadway nodes and adjacent nodes to which the measurement points belong, respectively;

[0076] According to the wind flow continuity constraint, the real-time ventilation state data on the branch path between adjacent nodes is interpolated to obtain the twin ventilation state corresponding to all nodes and branch paths of the three-dimensional space topology.

[0077] In the process of establishing the three-dimensional space topology of the coal mine ventilation system, first, the roadway topology data in the mine structure data is read, which is stored in the form of a data table, and each record contains roadway number, starting coordinates, ending coordinates, roadway cross-sectional area, roadway length, and other attribute information. The roadway number uses a hierarchical coding method, for example, the main haulage roadway number is H001, and its branch roadways are numbered as H001-01, H001-02. The connection relationship between adjacent roadways is extracted by analyzing the data table and determining the roadway connectivity by identifying the coincidence of the starting coordinates and ending coordinates of the roadways. When the ending coordinates of roadway H001 are X coordinate 800 meters, Y coordinate 200 meters, and Z coordinate -450 meters, and the starting coordinates of roadway H002 are exactly the same, it is determined that the two roadways are connected at this spatial location, and a connection record is established in the data structure.

[0078] The ventilation facility position data is continuously read, which records the specific installation positions of air doors, air windows, adjustable air windows, air bridges, and other ventilation facilities. Each ventilation facility record contains facility number, facility type, installation coordinates, roadway number to which it belongs, facility status, and other information. For example, the air door facility number FM-023 is installed at the coordinates X coordinate 450 meters, Y coordinate 180 meters, and Z coordinate -420 meters, and the roadway number to which it belongs is H003, and the current state is closed. The original roadway nodes are subdivided according to the positions of these ventilation facilities, and a new topology node is created at each ventilation facility installation position. The roadway H003 originally connected directly from point A to point B is divided into three parts after the installation of the air door FM-023, namely the node from point A to the air door position, the air door node, and the node from the air door position to point B. This subdivision ensures that the air flow path accurately reflects the regulation of the air flow by the ventilation facilities.

[0079] The established three-dimensional space topology is stored in a graph structure, where the node data structure contains node identification, three-dimensional space coordinates, node type, connection relationship list, and other fields, and the node type is divided into roadway intersection nodes, ventilation facility nodes, and working face nodes. The branch path data structure contains path identification, starting node identification, ending node identification, path length, roadway cross-sectional area, and wind resistance coefficient. A specific topology node record is node identification N-156, spatial coordinates X coordinate 620 meters, Y coordinate 240 meters, and Z coordinate -380 meters, node type roadway intersection node, and connection relationship list containing four adjacent nodes N-155, N-157, N-201, and N-202.

[0080] The real-time ventilation state data is collected from sensors distributed throughout the mine. Each sensor measurement point generates a data record containing the measurement point number, collection timestamp, spatial coordinates, wind speed, wind pressure, oxygen concentration, carbon monoxide concentration, gas concentration, and other information. For example, the sensor with measurement point number S-089 is located at X coordinate 615 meters, Y coordinate 238 meters, and Z coordinate -382 meters. At a certain time, the wind speed collected is 2.8 meters per second, the wind pressure is 1080 pascals, the oxygen concentration is 19.5 percent, the carbon monoxide concentration is 0.0008 percent, and the gas concentration is 0.35 percent.

[0081] For the spatial coordinates of measurement point S-089, all nodes in the three-dimensional spatial topological relationship are traversed, and the spatial distance from the measurement point to each node is calculated. The calculation method is to respectively calculate the coordinate difference in the X direction, Y direction, and Z direction between the measurement point coordinates and the node coordinates, square the three difference values, add the three square values, and take the square root to obtain the spatial straight-line distance. The distance from measurement point S-089 to node N-156 is calculated as a difference of 5 meters in the X direction, a difference of 2 meters in the Y direction, and a difference of 2 meters in the Z direction, with a square sum of 29, and the distance after taking the square root is approximately 5.39 meters. After calculating the distance from the measurement point to all nodes, the node with the smallest distance is selected as the matching node. The distance between measurement point S-089 and node N-156 is 5.39 meters, which is the smallest among all calculated distances, so node identifier N-156 is selected as the roadway node identifier to which the measurement point belongs.

[0082] After associating the measurement point data with the node identifier, the ventilation parameter data of the measurement point is distributed to the corresponding topological structure. The wind speed data of measurement point S-089, 2.8 meters per second, is multiplied by the roadway cross-sectional area data. Assuming that the roadway cross-sectional area at this location is 12 square meters, the calculated air volume at this location is 33.6 cubic meters per second. This air volume data is associated with node N-156 and also distributed to each branch path adjacent to the node. Node N-156 connects four branch paths, and the data of the measurement point is determined to be applicable to which branch paths according to the wind flow direction. By analyzing the wind pressure gradient direction, it is determined that the air flow flows from node N-155 to node N-156, and then from node N-156 to nodes N-157 and N-201. Therefore, the data of measurement point S-089 is associated with paths N-155 to N-156, N-156 to N-157, and N-156 to N-201.

[0083] For the branch path without direct sensor measurement, the interpolation method is used to supplement the ventilation data. The path P-078 connects the node N-156 and the node N-157, with a length of 85 meters. At the starting node N-156, there is a flow rate data of 33.6 cubic meters per second from the sensor S-089. At the ending node N-157, there is a flow rate data of 32.8 cubic meters per second from the sensor S-105. Along the path, multiple virtual interpolation points are established, with an interpolation point every 10 meters. There are a total of 8 interpolation points on the path. At the interpolation point 10 meters away from the starting point, the flow rate value is calculated based on the distance weighting from both ends of the node. The distance weight from the starting point is 75 meters, and the distance weight from the ending point is 10 meters. The flow rate value is calculated as the flow rate difference of 0.8 cubic meters per second multiplied by the distance ratio of 10 divided by 85, and then subtracting the product from the starting flow rate. The interpolation flow rate is 33.51 cubic meters per second.

[0084] In the interpolation calculation process, the continuity constraint of air flow is required, i.e. the total inflow at any node should be equal to the total outflow. The node N-156 has an inflow branch path with a flow rate of 33.6 cubic meters per second, and two outflow branch paths. The flow rates of the two outflow paths are checked to see if they are equal to the inflow. When it is detected that the outflow path flow rate sum of the node N-156 is 32.1 cubic meters per second, which is 1.5 cubic meters per second different from the inflow of 33.6 cubic meters per second, the difference is distributed and adjusted according to the initial flow rate ratio of each outflow path. The initial flow rate of the outflow path P-078 is 20.3 cubic meters per second, and the initial flow rate of the outflow path P-079 is 11.8 cubic meters per second, with a flow rate ratio of about 1.72 to 1. The flow rate difference of 1.5 cubic meters per second is distributed according to the ratio, with the path P-078 increasing by 0.95 cubic meters per second and the path P-079 increasing by 0.55 cubic meters per second. The flow rate sum of the two outflow paths after adjustment reaches 33.6 cubic meters per second, satisfying the continuity constraint.

[0085] The interpolation calculation of gas concentration distribution data takes into account the gas diffusion and mixing characteristics. The gas concentration at the starting point of the path P-078 is 0.35 percent, and the gas concentration at the ending point is 0.42 percent. The gas concentration at the intermediate interpolation points is not only affected by the concentrations at both ends, but also needs to consider whether there is a gas emission source in the section of the roadway. Reading the mine geological data, it is identified that there is a gas emission in the adjacent working face of the path, with an emission amount of 0.8 cubic meters per minute. In calculating the gas concentration at the interpolation point 40 meters away from the starting point, in addition to the distance weighted calculation of the base concentration, the contribution of the accumulated emission gas to the concentration in this section is also added. The emission gas amount is divided by the ventilation flow rate of the section, resulting in a concentration increment of 0.04 percent. The final gas concentration value at this point is obtained by superimposing the base interpolation concentration.

[0086] The interpolation of the wind pressure distribution data needs to consider the resistance loss along the path. The wind pressure at the starting point of the path P-078 is 1080 Pa, and the wind pressure at the end point is 1065 Pa, with a pressure difference of 15 Pa caused by the friction resistance of the section. According to the length of the roadway, the length of the roadway, the average wind speed, and the friction resistance coefficient, the theoretical pressure drop value is calculated. The length of the roadway is 14 meters, the length of the roadway is 85 meters, the average wind speed is 2.75 meters per second, and the friction resistance coefficient is 0.018 kg per cubic meter. These parameters are substituted into the resistance calculation method to obtain a theoretical pressure drop of 14.8 Pa, which is basically consistent with the measured pressure difference of 15 Pa. The wind pressure value of the interpolation point is gradually deducted from the starting wind pressure, and the cumulative resistance loss at the interpolation point 40 meters from the starting point is 15 Pa, which is multiplied by the distance ratio 40 divided by 85, resulting in 7 Pa. The wind pressure at this point is 1080 Pa minus 7 Pa, and the calculation result is 1073 Pa.

[0087] After completing the data mapping and interpolation calculation of all nodes and branch paths, a complete twin ventilation state data set is generated, which is indexed by time stamp and records the air volume, wind pressure, and gas concentration values of each node in the three-dimensional spatial topological relationship at a certain time, as well as the detailed wind flow parameter distribution on each branch path. The twin ventilation state data realizes real-time mapping of the physical ventilation system in the digital space, providing a data basis for analysis, early warning, and optimization control of the ventilation system.

[0088] In an alternative embodiment, based on the three-dimensional spatial topological relationship, a theoretical ventilation distribution state is obtained by simulation calculation, and the twin ventilation state is compared with the theoretical ventilation distribution state to determine the air volume deviation area and the gas concentration abnormal area, and obtain the ventilation deviation characteristics, including:

[0089] The roadway nodes in the three-dimensional spatial topological relationship are taken as network nodes, and the branch paths are taken as network branches. The ventilation network solving equation is used to solve the ventilation network to obtain the theoretical wind pressure value of each network node and the theoretical air volume value of each network branch, which is taken as the theoretical ventilation distribution state.

[0090] Based on the measured air volume value of each roadway node in the twin ventilation state and the theoretical air volume value of the corresponding network node in the theoretical ventilation distribution state, the air volume deviation area is determined.

[0091] The measured gas concentration value of each roadway node in the twin ventilation state is compared with the ventilation safety concentration limit value node by node to determine the roadway node whose measured gas concentration value exceeds the ventilation safety concentration limit value. Based on the spatially continuous distribution of the over-limit roadway nodes and the nodes within their coverage, the gas concentration abnormal area is determined.

[0092] The ventilation deviation feature is obtained by associating and combining the air volume deviation region, the gas concentration abnormal region, and the region space range.

[0093] In the simulation calculation, the three-dimensional space topological relationship of the mine ventilation system is converted into a calculable network model. The specific processing mode is to map each roadway node into a network node and map the branch path connecting two roadway nodes into a network branch. For example, in a certain mine ventilation system, the main air inlet shaft is set as the network node N001, which is connected to the air inlet roadway of the mining area through the main transportation roadway, and the roadway is taken as the network branch B001. The inlet position of the air inlet roadway of the mining area is set as the network node N002. In this way, all the roadway nodes and branch paths of the entire ventilation system are mapped and converted one by one.

[0094] After the network model is constructed, the ventilation network solving equation is used for solving calculation. The solving process is based on the wind flow continuity law and the energy conservation law in the ventilation system. At each network node, the sum of the wind volume of all branches flowing into the node is equal to the sum of the wind volume of all branches flowing out of the node. In any closed loop, the algebraic sum of the wind pressure along the loop is zero. Meanwhile, the wind pressure drop of each network branch is equal to the product of the wind resistance and the square of the wind volume. By establishing the equation set containing all the network nodes and network branches, the convergent solution is obtained by using the iterative solving method. The convergence criterion is set as that the wind volume change rate of the adjacent two times of iteration calculation is less than one thousandth.

[0095] After the iterative calculation, the theoretical wind pressure value of each network node and the theoretical wind volume value of each network branch are obtained. For example, the theoretical wind pressure value of the network node N002 is 1580 Pa, the theoretical wind volume value of the network branch B001 is 280 cubic meters per second, the theoretical wind pressure value of the network node N015 is 1320 Pa, and the theoretical wind volume value of the network branch B014 is 65 cubic meters per second. These calculation results constitute a complete theoretical ventilation distribution state, which reflects the ventilation state that should be reached under the existing ventilation system topological structure and equipment configuration conditions.

[0096] The real-time collected twin ventilation state data is compared and analyzed with the theoretical ventilation distribution state. For each roadway node, the measured wind volume value in the twin ventilation state is extracted, and the theoretical wind volume value of the corresponding network node in the theoretical ventilation distribution state is obtained. The deviation amount between the two is calculated, which is equal to the measured wind volume value minus the theoretical wind volume value. Meanwhile, the deviation rate is calculated, which is equal to the deviation amount divided by the theoretical wind volume value multiplied by 100%. For example, the measured wind volume value of the roadway node D025 is 58 cubic meters per second, and the theoretical wind volume value of the corresponding network node is 65 cubic meters per second. Therefore, the deviation amount is -7 cubic meters per second, and the deviation rate is -10.8%.

[0097] The air volume deviation determination threshold is pre-set, for example, 15%. When the absolute value of the air volume deviation rate of a roadway node exceeds the threshold, the node is marked as an air volume deviation node. After the deviation determination is completed by traversing all roadway nodes, all air volume deviation nodes are identified. Based on the connection relationship in the three-dimensional spatial topological relationship, the air volume deviation nodes that are adjacent or connected in space are found, and these nodes and the roadway section where they are located are combined to form an air volume deviation area. For example, the air volume deviation rates of roadway nodes D025, D026, and D027 are -10.8%, -16.3%, and -14.2% respectively, and these three nodes are continuously distributed in the same return airway of the mining area in space. Therefore, the three nodes and the return airway section of the mining area where they are located are delineated as an air volume deviation area R01.

[0098] For the identification of gas concentration anomalies, the measured gas concentration values of each roadway node are extracted from the twin ventilation state. The main monitored gas types include methane, carbon monoxide, carbon dioxide, etc. The concentration limits of various gases are set according to the ventilation safety standards, for example, the methane concentration limit in the return airway of the mining area is 1%, the methane concentration limit in the mining and excavation working face is 1%, and the carbon monoxide concentration limit is 24 / 10000. The measured gas concentration value of each roadway node is compared with the concentration limit of the corresponding position type.

[0099] When the measured gas concentration value of a roadway node exceeds the ventilation safety concentration limit, the node is marked as a gas concentration overrun node. For example, the measured methane concentration value of roadway node D032 is 1.3%, which exceeds the concentration limit of 1% at this location. Therefore, node D032 is marked as a gas concentration overrun node. After the concentration comparison is completed by traversing all roadway nodes, the distribution of all gas concentration overrun nodes is obtained.

[0100] The gas concentration overrun nodes that are continuously distributed in the three-dimensional space are found. The basis for determining continuity is that there is a direct roadway connection relationship between the nodes and the distance is within a set range. The continuous determination distance is set to 50 meters. When the roadway distance between two gas concentration overrun nodes is less than 50 meters, the two nodes are considered to be spatially continuous. Multiple overrun nodes that are spatially continuous are identified as an aggregation area, and the influence coverage range of the aggregation area is determined based on the flow direction of the air flow. The coverage range includes all nodes within a certain distance downwind of the overrun nodes. The coverage distance is set to 100 meters. For example, the methane concentrations of nodes D032, D033, and D034 are all overrun and spatially continuously distributed. These three nodes and the nodes D035 and D036 within a range of 100 meters downwind of the three nodes jointly constitute a gas concentration anomaly area A01.

[0101] After obtaining the air volume deviation region and the gas concentration abnormal region, correlation combination analysis is performed to determine whether the two types of regions exist in spatial overlap or adjacent relationship. When the air volume deviation region and the gas concentration abnormal region exist in spatial intersection, or the boundary distance of the two regions is less than 30 meters, it is considered that the two regions exist in correlation. The spatial range coordinates of the correlation region, the involved roadway node number, the numerical characteristics of the air volume deviation, the type and degree of the gas concentration overrun are recorded. For example, the air volume deviation region R01 and the gas concentration abnormal region A01 exist in partial spatial overlap, the overlap region contains nodes D025 to D034, the air volume deviation rate of the region is-15% to-10.8%, and the methane concentration overrun amplitude is 0.2% to 0.3%. The comprehensive information is integrated to form the ventilation deviation feature, which completely describes the problem region location, problem nature, severity and spatial distribution range in the ventilation system, and provides accurate data support for subsequent ventilation system regulation and safety warning.

[0102] In an optional embodiment, based on the measured air volume value of each roadway node in the twin ventilation state and the theoretical air volume value of the corresponding network node in the theoretical ventilation distribution state, the air volume deviation region is determined, including:

[0103] According to the mapping relationship between the roadway node identifier in the twin ventilation state and the network node number in the theoretical ventilation distribution state, the measured air volume value of the roadway node with the same spatial position and the theoretical air volume value of the corresponding network node are determined;

[0104] The difference value of the measured air volume value of each roadway node at the same spatial position and the theoretical air volume value of the corresponding network node is calculated to obtain the air volume deviation value of each roadway node;

[0105] The air volume deviation value is processed to obtain the relative deviation rate, the relative deviation rate is compared with the preset air volume deviation judgment criterion, and the roadway node with the relative deviation rate exceeding the air volume deviation judgment criterion is determined as a deviation node;

[0106] Based on the spatial connection relationship between each deviation node in the three-dimensional space topology relationship, the deviation nodes connected by the direct branch path are clustered into the same deviation region group;

[0107] The node identifier, air volume deviation value, relative deviation rate and branch path identifier connecting the deviation nodes of all the deviation nodes in each deviation region group are extracted to obtain the air volume deviation region.

[0108] Figure 2 The flowchart for determining the air volume deviation region of the embodiment of the present application is shown in FIG. 1. Figure 2As shown, in the process of determining the wind volume deviation area, it is necessary to systematically compare and analyze the measured wind volume value of each roadway node in the twin ventilation state with the theoretical wind volume value of the corresponding network node in the theoretical ventilation distribution state. This process relies on the pre-established mapping relationship table between the roadway node identification and the network node number, which records the unique identification code of each roadway node and its corresponding network node number, ensuring that nodes with the same spatial position can be accurately matched. Taking a mine ventilation system as an example, the identification of roadway node A-101 corresponds to the node number N-056 in the theoretical ventilation network, both of which are located at the intersection of the third horizontal transport roadway and the return airway in the east wing of the mine, with spatial coordinates of X coordinate 2350 meters, Y coordinate 1820 meters, and Z coordinate -580 meters.

[0109] After establishing the mapping relationship, the measured wind volume data of each roadway node and the theoretical wind volume data of the corresponding network node are extracted one by one. For roadway node A-101, the real-time data collected by the wind speed sensor and the air pressure sensor installed at this location, combined with the roadway cross-sectional area calculation, obtains a measured wind volume value of 42.3 cubic meters per second. In the theoretical ventilation distribution state, the theoretical wind volume value of network node N-056 determined according to the ventilation resistance calculation and wind volume allocation principle is 38.5 cubic meters per second. Similarly, for roadway node A-102 corresponding to network node N-057, the measured wind volume value is 55.8 cubic meters per second, and the theoretical wind volume value is 60.2 cubic meters per second; for roadway node A-103 corresponding to network node N-058, the measured wind volume value is 28.6 cubic meters per second, and the theoretical wind volume value is 30.1 cubic meters per second.

[0110] After obtaining the wind volume data of all paired nodes, the difference between the measured wind volume value of each roadway node at the same spatial position and the theoretical wind volume value of the corresponding network node is calculated. For node A-101, subtract the theoretical wind volume value of 38.5 cubic meters per second from the measured wind volume value of 42.3 cubic meters per second to obtain a wind volume deviation value of 3.8 cubic meters per second, indicating that the actual ventilation volume of this node is higher than the theoretical design value. For node A-102, subtract the theoretical wind volume value of 60.2 cubic meters per second from the measured wind volume value of 55.8 cubic meters per second to obtain a wind volume deviation value of -4.4 cubic meters per second, indicating that the actual ventilation volume of this node is lower than the theoretical design value. The wind volume deviation value of node A-103 is -1.5 cubic meters per second. By traversing all the mapped nodes, a complete wind volume deviation value dataset is formed.

[0111] To eliminate the comparability problem of deviation values caused by different theoretical air volume reference values of different roadway nodes, it is necessary to convert the absolute deviation value into a relative deviation rate. The calculation method of the relative deviation rate is to divide the air volume deviation value by the corresponding theoretical air volume value, and then multiply by 100%. For node A-101, the air volume deviation value 3.8 cubic meters per second is divided by the theoretical air volume value 38.5 cubic meters per second, resulting in a quotient value of 0.0987, and multiplying by 100% gives a relative deviation rate of 9.87%. The relative deviation rate of node A-102 is calculated as -4.4 divided by 60.2 and multiplied by 100%, resulting in -7.31%. The relative deviation rate of node A-103 is -1.5 divided by 30.1 and multiplied by 100%, resulting in -4.98%. This normalization processing makes the deviation degree of nodes with different air volume levels comparable.

[0112] After determining the relative deviation rate, the relative deviation rate of each node is compared with the preset air volume deviation criterion one by one. The criterion is set according to the mine safety regulations and ventilation management requirements, and is usually set as ±8% as the acceptable deviation range threshold. When the absolute value of the relative deviation rate of a node exceeds 8%, the node is marked as a deviation node. In the above case, the relative deviation rate of node A-101 is 9.87%, which exceeds the threshold of 8% and is marked as a deviation node. The relative deviation rate of node A-102 is -7.31%, and the absolute value is 7.31%, which does not exceed the threshold and is not a deviation node. Further inspection found that the relative deviation rate of node A-105 is 12.3%, the relative deviation rate of node A-108 is -10.6%, and the relative deviation rate of node A-112 is 15.8%. These nodes are all identified as deviation nodes.

[0113] After identifying all the deviation nodes, it is necessary to analyze the spatial connectivity between these deviation nodes based on the three-dimensional spatial topological relationship. The three-dimensional spatial topological relationship records the connection of each node in the roadway network through branch paths, including whether there is a direct connection between nodes and the path identification of the branch. For deviation nodes A-101 and A-105, it is found that there is a direct connection between them through branch path P-231, which is a 120-meter long transportation roadway section. It is also found that there is a connection between deviation nodes A-105 and A-108 through branch path P-245, with a path length of 85 meters. Deviation node A-112 does not have a direct branch path connection with other identified deviation nodes, and its nearest neighbor node is a non-deviation node.

[0114] According to the spatial connectivity relationship, a clustering method is used to merge the deviation nodes connected by the direct branch path into the same deviation area group. Deviation nodes A-101, A-105 and A-108 are clustered into a deviation area group G-01 because they form a continuous ventilation path through branch paths P-231 and P-245. This area group covers a section of the main ventilation path on the third level of the east wing, including three deviation nodes and two connecting branches. Deviation node A-112 is isolated in space and forms a deviation area group G-02. If subsequent analysis finds that there is a branch path P-287 connecting deviation nodes A-115 and A-112, A-115 will be included in the deviation area group G-02.

[0115] After clustering the deviation area groups, detailed feature information of each deviation area group is extracted. For the deviation area group G-01, all deviation node identifiers contained therein are extracted as A-101, A-105 and A-108. The air volume deviation values of each node are 3.8 cubic meters per second, 4.7 cubic meters per second and -6.4 cubic meters per second, respectively. The relative deviation rates are 9.87%, 12.3% and -10.6%, respectively. The branch path identifiers connecting these deviation nodes are P-231 and P-245, which correspond to specific roadway sections. For the deviation area group G-02, the identifier of the deviation node A-112 is extracted. The air volume deviation value is 9.5 cubic meters per second, and the relative deviation rate is 15.8%. This area group has no connecting branch path information. By integrating the above node identifiers, air volume deviation values, relative deviation rates and branch path identifiers, a structured air volume deviation area data is formed, providing accurate spatial positioning and quantitative basis for subsequent ventilation system optimization and adjustment.

[0116] In an optional implementation, according to the ventilation deviation characteristics, a virtual preview of the adjustment state of the ventilation facilities in the three-dimensional spatial topological relationship is performed, an adjustment scheme that meets the ventilation demand constraint and the energy consumption constraint is determined, and an optimized control instruction is generated based on the adjustment scheme, including:

[0117] According to the ventilation deviation characteristics, a target area to be adjusted is determined in the three-dimensional spatial topological relationship, and a candidate adjustment object is determined as a ventilation facility that affects the ventilation state of the target area according to the connected path of the target area in the three-dimensional spatial topological relationship.

[0118] For each candidate adjustment object, a plurality of groups of virtual adjustment parameters are determined, the virtual adjustment parameters are applied to the boundary conditions of the corresponding ventilation facilities in the three-dimensional spatial topological relationship, virtual preview calculation is performed by using a ventilation network solving equation, and a preview ventilation distribution state corresponding to each group of virtual adjustment parameters is obtained.

[0119] extracting a pre-performance air volume value and a pre-performance gas concentration value of the target area from each pre-performance ventilation distribution state, and screening a candidate adjustment parameter group meeting the ventilation demand constraint and the ventilation safety concentration constraint based on the pre-performance air volume value and the pre-performance gas concentration value;

[0120] calculating a total energy consumption value of the ventilation system corresponding to each candidate adjustment parameter group, selecting a candidate adjustment parameter group as an optimal adjustment parameter group based on the total energy consumption value of the ventilation system, and obtaining the adjustment scheme;

[0121] converting the optimal adjustment parameter group of each candidate adjustment object in the adjustment scheme into an action instruction of a corresponding ventilation facility, and generating the optimization control instruction.

[0122] In the automatic optimization control process of the mine ventilation system, when a ventilation deviation feature of insufficient air volume in a certain area is detected, the abnormal area is immediately located in the established three-dimensional spatial topological relationship model. Assuming that the actual air volume of a coal mining face at a -450-meter level of a mine is 18 cubic meters per second, and the safe operation of the area requires an air volume of 25 cubic meters per second, the coal mining face is identified as a target area to be adjusted. The control system traces the upstream ventilation path of the target area in the three-dimensional spatial topological relationship, and identifies all ventilation nodes between the main ventilation room and the working face, including the main air duct branch, the adjustment air window, the local ventilation fan, and the air door. Through topological relationship analysis, it is determined that the candidate adjustment objects affecting the ventilation state of the target area include the third adjustment air window 300 meters away from the target area, the local ventilation fan dedicated to the area, and the auxiliary air door 150 meters upstream.

[0123] For the third adjustment air window as a candidate adjustment object, five groups of virtual adjustment parameters are generated, and the air window opening degrees are set to 30%, 45%, 60%, 75%, and 90%, respectively. The air window ventilation resistance coefficients corresponding to each group of virtual adjustment parameters are set to 8.5, 6.2, 4.1, 2.8, and 1.9 Pa·s2 / m3, respectively. These virtual adjustment parameters are sequentially applied to the boundary condition setting of the corresponding ventilation facility node in the three-dimensional spatial topological relationship model. When the air window opening degree is set to 60%, the ventilation resistance coefficient of the node is modified to 4.1, while the boundary conditions of other ventilation facilities remain unchanged. The ventilation network solver engine is called, which iteratively calculates based on the node air volume balance principle and the loop air pressure balance principle. During the calculation process, the entire ventilation network is divided into 127 nodes and 156 branches, and a wind volume conservation equation is established for each node, requiring the total wind volume flowing into the node to be equal to the total wind volume flowing out of the node. A wind pressure balance equation is established for each independent loop, requiring the product of the ventilation resistance and the square of the wind volume in each branch in the loop to be zero.

[0124] After the virtual rehearsal calculation is completed, the target area's rehearsal wind volume value is 22 cubic meters per second when the window opening is 60%, and the rehearsal gas concentration is 0.65% methane and 15 ppm carbon monoxide. Continue to calculate the rehearsal results of other opening combinations. When the opening is 75%, the target area's rehearsal wind volume reaches 26 cubic meters per second, the methane concentration drops to 0.48%, and the carbon monoxide concentration drops to 11 ppm. Extract the rehearsal ventilation distribution state corresponding to all five groups of virtual adjustment parameters, and perform data extraction and safety evaluation for the target area. According to the mine's ventilation demand constraints, the minimum air volume requirement for the coal mining face is 25 cubic meters per second, the methane concentration must be less than 0.8%, and the carbon monoxide concentration must be less than 20 ppm. By comparing the rehearsal data of each group, it is found that the rehearsal wind volume is only 19 cubic meters per second when the opening is 30%, and 21 cubic meters per second when the opening is 45%, both of which do not meet the minimum air volume requirement. These two groups of parameters are excluded. The rehearsal wind volumes corresponding to the three groups of parameters with openings of 60%, 75%, and 90% are 22 cubic meters per second, 26 cubic meters per second, and 28 cubic meters per second, respectively. The rehearsal wind volume of the 60% opening still does not meet the standard, and only the two groups of parameters with openings of 75% and 90% meet the ventilation demand constraints and gas concentration safety constraints, and are determined as candidate adjustment parameter groups.

[0125] For the local ventilation fan as the candidate adjustment object, four groups of virtual adjustment parameters are set, with fan speeds of 800 revolutions per minute, 950 revolutions per minute, 1100 revolutions per minute, and 1250 revolutions per minute. In the virtual rehearsal calculation, different speeds correspond to different fan characteristic curves, and the boundary conditions of the facility node are updated according to the corresponding relationship between fan wind pressure and wind volume. When the speed is 1100 revolutions per minute, the virtual rehearsal shows that the target area's wind volume reaches 27 cubic meters per second, and the methane concentration is 0.52%, meeting the safety constraint requirements. Record this parameter group and continue to evaluate other speed combinations.

[0126] After obtaining the candidate adjustment parameter sets of all candidate adjustment objects, the total energy consumption of the ventilation system corresponding to each parameter combination scheme is calculated. For the combination scheme of the third adjustment air window opening degree of 75% and the local ventilation fan speed of 1100 revolutions per minute, the running power of the main ventilation fan of the whole mine is 420 kilowatts, the total power of all local ventilation fans is 185 kilowatts, and the energy consumption of the compressed air power door is 12 kilowatts. The total energy consumption value of the ventilation system of this scheme is 617 kilowatts. When the air window opening degree is adjusted to 90% and the local ventilation fan speed is reduced to 950 revolutions per minute, the main ventilation fan power is reduced to 405 kilowatts, the total power of the local ventilation fan is reduced to 158 kilowatts, and the energy consumption of the compressed air power equipment is 12 kilowatts. The total energy consumption value of this scheme is 575 kilowatts. By comparing the energy consumption values of all candidate adjustment parameter sets that meet the safety constraints, the parameter combination with the lowest energy consumption value is selected as the optimal adjustment parameter set, and the adjustment scheme is determined as the third adjustment air window opening degree of 90% and the local ventilation fan speed of 950 revolutions per minute, and the auxiliary air door remains in the current open state.

[0127] The optimal adjustment parameter set in the adjustment scheme is converted into specific device action instructions. For the third adjustment air window, the generated action instruction includes device address encoding 03A7, instruction type opening degree adjustment, target opening degree value 90%, and execution time set to 180 seconds. The instruction is sent to the air window controller through the field bus. For the local ventilation fan, the generated action instruction includes device address encoding 05B2, instruction type frequency conversion speed regulation, target speed value 950 revolutions per minute, and acceleration time set to 30 seconds. The instruction is sent to the frequency conversion control cabinet through the industrial Ethernet. The optimization control instruction set integrates the action instructions of all candidate adjustment objects and sets the execution priority and time sequence relationship to ensure that each ventilation facility completes the adjustment action in the predetermined order and realizes the accurate optimization control of the target area ventilation state.

[0128] In an alternative embodiment, a plurality of sets of virtual adjustment parameters are determined for each candidate adjustment object, the virtual adjustment parameters are applied to the boundary conditions of the corresponding ventilation facility in the three-dimensional space topological relationship, and the ventilation network solving equation is used for virtual pre-play calculation to obtain the pre-play ventilation distribution state corresponding to each set of virtual adjustment parameters, including:

[0129] According to the facility type and the current adjustment state parameter of each candidate adjustment object, the physical dimension and the value boundary of the adjustment parameter are determined;

[0130] Based on the value boundary and the current adjustment state parameter, a plurality of virtual adjustment parameter values are generated within the value boundary, and the virtual adjustment parameter values are arranged in sequence to obtain a virtual adjustment parameter sequence;

[0131] combining each virtual adjustment parameter value in the virtual adjustment parameter sequence with the identification of the candidate adjustment object, to obtain multiple groups of virtual adjustment parameters;

[0132] determining the positions of the corresponding ventilation facilities of each candidate adjustment object in the three-dimensional space topological relationship, and updating the boundary condition values of the positions of the corresponding ventilation facilities in the three-dimensional space topological relationship based on each group of virtual adjustment parameters;

[0133] for each group of virtual adjustment parameters, solving the theoretical wind pressure values of each network node and the theoretical air volume values of each network branch corresponding to the group of virtual adjustment parameters by using the ventilation network solving equation based on the updated three-dimensional space topological relationship;

[0134] combining the theoretical wind pressure values of each network node and the theoretical air volume values of each network branch corresponding to each group of virtual adjustment parameters, to determine the pre-play ventilation distribution state corresponding to each group of virtual adjustment parameters.

[0135] When determining multiple groups of virtual adjustment parameters for each candidate adjustment object, the facility type attribute of the candidate adjustment object needs to be read, and the facility types include air door, adjustment air window, local ventilation fan, main ventilation fan and other ventilation equipment. For the adjustment object of the air door type, the physical dimension of the adjustment parameter is the opening percentage, and the value range is between 0 and 100, wherein 0 represents the completely closed state, and 100 represents the completely opened state. When the current adjustment state parameter of a certain air door is 60% opening, the value is taken as the reference value, and the mechanical structure restriction condition of the air door is combined to determine that the minimum opening of the air door is 10% and the maximum opening is 100%, so that the value boundary of the adjustment parameter of the air door is 10% to 100%. For the adjustment object of the local ventilation fan type, the physical dimension of the adjustment parameter is the rotating speed, which is in units of revolutions per minute. When the rated rotating speed of a certain local ventilation fan is 1450 revolutions per minute and the current operating rotating speed is 1200 revolutions per minute, the rotating speed value boundary of the local ventilation fan is determined to be 800 revolutions per minute to 1450 revolutions per minute according to the frequency converter speed range of the equipment.

[0136] When generating the virtual adjustment parameter values based on the value boundary and the current adjustment state parameter, an equal interval sampling method is used to generate a plurality of discrete parameter values within the value boundary. For a damper with an opening of 60% and a value boundary of 10% to 100%, 15 virtual adjustment parameter values are generated. The span of the value boundary is 90%, and the sampling interval is about 6.43% obtained by dividing the span by 14. Starting from the minimum boundary value of 10%, the sampling interval is increased successively, and the generated virtual adjustment parameter values are 10%, 16.43%, 22.86%, 29.29%, 35.71%, 42.14%, 48.57%, 55%, 61.43%, 67.86%, 74.29%, 80.71%, 87.14%, 93.57%, and 100% in turn. The 15 parameter values are arranged in ascending order to form a virtual adjustment parameter sequence. For a local fan with a speed of 1200 revolutions per minute and a value boundary of 800 to 1450 revolutions per minute, 15 virtual adjustment parameter values are also generated. The span of the value boundary is 650 revolutions per minute, and the sampling interval is about 46.43 revolutions per minute. The generated virtual adjustment parameter sequence is 800, 846.43, 892.86, 939.29, 985.71, 1032.14, 1078.57, 1125, 1171.43, 1217.86, 1264.29, 1310.71, 1357.14, 1403.57, and 1450 revolutions per minute.

[0137] When each virtual adjustment parameter value in the virtual adjustment parameter sequence is combined with the identifier of the candidate adjustment object, the unique identifier of the candidate adjustment object is read. Assuming that the identifier of a certain damper is FD-A-205, the identifier FD-A-205 is paired with the parameter values 10%, 16.43%, 22.86%, and the like, respectively, to generate 15 groups of virtual adjustment parameters, represented as FD-A-205 paired with 10%, FD-A-205 paired with 16.43%, FD-A-205 paired with 22.86%, and the like. For the local fan with the identifier FJ-B-108, the identifier is paired with the 15 speed parameter values to generate FJ-B-108 paired with 800 revolutions per minute, FJ-B-108 paired with 846.43 revolutions per minute, and the like.

[0138] In the three-dimensional space topology relationship, the position of each candidate adjustment object corresponding to the ventilation facility is determined by traversing the node set and branch set of the three-dimensional space topology relationship. For the air door with identifier FD-A-205, the branch record containing the identifier is searched in the branch set, and the branch B267 between the air door connection node N158 and the node N159 is located. The current boundary condition value of the branch B267 is read, and the boundary condition includes the wind resistance value and the ventilation area. When the air door opening degree is 60%, the corresponding effective ventilation area is 2.4 square meters, and the wind resistance value is 0.15 kilograms per cubic meter. When the virtual adjustment parameter value 10% is applied, according to the corresponding relationship between the air door opening degree and the effective ventilation area, the effective ventilation area is calculated to be 0.4 square meters, and according to the inverse proportional relationship between the ventilation area and the wind resistance, the wind resistance value is calculated to be 5.4 kilograms per cubic meter. The boundary condition value of the branch B267 is updated to the ventilation area 0.4 square meters and the wind resistance value 5.4 kilograms per cubic meter. When the virtual adjustment parameter value 100% is applied, the effective ventilation area is updated to 4 square meters, and the wind resistance value is updated to 0.09 kilograms per cubic meter.

[0139] For each set of virtual adjustment parameter updated three-dimensional space topology relationship, the ventilation network solving equation is used for iterative calculation. Taking the three-dimensional space topology relationship after applying the virtual adjustment parameter FD-A-205 with 10% as an example, read all the updated branch boundary conditions and node boundary conditions. Assuming that the ventilation network contains 200 nodes and 280 branches, the node wind pressure balance equation set and the branch air volume continuity equation set are established. The node wind pressure balance equation describes the algebraic sum of the wind pressure drop of each branch at each node equal to zero, and the branch air volume continuity equation describes the total air volume flowing into the node equal to the total air volume flowing out of the node. Set the initial iteration parameters, set the initial wind pressure value of all nodes to the standard atmospheric pressure 101325 pascals, and set the initial air volume value of all branches to the estimated average air volume. Perform the first iteration calculation, calculate the wind pressure drop of each branch according to the wind resistance value and the assumed air volume, and then adjust the wind pressure value of each node according to the node wind pressure balance equation. After the calculation is completed, check whether the residual value of all node wind pressure balance equations is less than the set threshold value 0.1 pascal. When the residual value of some nodes after the first iteration exceeds the threshold value, the updated node wind pressure value is used to recalculate the air volume value of each branch, and the second iteration is entered. After multiple iterations, when the residual value of all node wind pressure balance equations is less than 0.1 pascal, and the residual value of all branch air volume continuity equations is less than 0.01 cubic meters per second, it is determined that the iteration converges, and the theoretical wind pressure value of each network node and the theoretical air volume value of each network branch corresponding to the set of virtual adjustment parameters are output. For the node N158, the theoretical wind pressure value is 101280 pascals, and for the branch B267, the theoretical air volume value is 8.5 cubic meters per second.

[0140] When the network node theoretical wind pressure values and the network branch theoretical wind volume values corresponding to each group of virtual adjustment parameters are combined, the ventilation network is solved for the 15 groups of virtual adjustment parameters, and 15 groups of calculation results are obtained. Each group of calculation results contains wind pressure value data of 200 nodes and wind volume value data of 280 branches. The entire node wind pressure values and the entire branch wind volume values corresponding to the virtual adjustment parameter FD-A-205 with 10% are combined as the first group of pre-play ventilation distribution states, which describes the wind pressure and wind volume distribution of the entire ventilation network when the damper FD-A-205 is adjusted to 10% opening. The calculation results corresponding to the virtual adjustment parameter FD-A-205 with 16.43% are combined as the second group of pre-play ventilation distribution states. In this way, 15 groups of pre-play ventilation distribution states are generated, each state corresponding to a specific virtual adjustment parameter value, providing complete pre-play data support for subsequent adjustment scheme evaluation.

[0141] In an optional implementation, based on the optimization control instruction, an adjustment action is controlled to be performed on the corresponding entity ventilation facility, and real-time ventilation state data after adjustment is collected as feedback data, and the three-dimensional space topological relationship is updated based on the feedback data, so as to keep consistency between simulation calculation and actual ventilation condition, including:

[0142] Based on the identification of each candidate adjustment object of the optimization control instruction, a communication interface of the corresponding entity ventilation facility is determined;

[0143] A control instruction is issued to the corresponding entity ventilation facility through the communication interface, the entity ventilation facility is driven to perform an adjustment action, and an adjustment completion state signal fed back by the entity ventilation facility is received, and actual adjustment parameter values of each entity ventilation facility are recorded;

[0144] After the entity ventilation facility completes the adjustment action, real-time ventilation state data of each monitoring point after adjustment is collected by a real-time monitoring sensor network as the feedback data;

[0145] Based on comparison calculation of the feedback data and the actual adjustment parameter values, actual adjustment response characteristics are obtained;

[0146] According to the actual adjustment response characteristics and the actual adjustment parameter values, the wind resistance characteristic parameters of the network nodes or network branches where the ventilation facilities are located in the three-dimensional space topological relationship are corrected, and the gas concentration measurement values in the feedback data are updated to the gas concentration attribute values of the corresponding roadway nodes in the three-dimensional space topological relationship, so as to keep consistency between simulation calculation and actual ventilation condition.

[0147] When the optimization control instruction is generated, a query operation needs to be performed in the device management database according to the identification information of each candidate adjustment object in the instruction, and the database stores information such as device number, device type, communication protocol type and communication interface address of all downhole entity ventilation facilities. Taking No. 3 air door in a mine as an example, its device identification is FM-003, and through the identification, it is retrieved in the database that the air door uses ModbusTCP communication protocol, the communication interface address is 192.168.10.35, and the port number is 502. For fan equipment, for example, No. FJ-012 local fan, its communication interface uses PROFINET protocol, the interface address is 192.168.10.68, and the port number is 34962. A communication connection table is established to map and associate the identification of each device to be controlled with the corresponding communication interface parameters.

[0148] After establishing the communication connection, specific control instructions are issued to each entity ventilation facility through the obtained communication interface. For air door equipment, the control instruction contains an opening angle parameter, for example, the opening angle of No. FM-003 air door is set to 45 degrees, and the parameter is packaged into a data frame conforming to the ModbusTCP protocol specification, which contains device address, function code, register address and hexadecimal representation of angle value. For local fan FJ-012, the control instruction contains a speed regulation parameter, which adjusts the speed from the current 1200 revolutions per minute to 1450 revolutions per minute, encodes the parameter according to the PROFINET protocol format and sends it through the network. After receiving the control instruction, the entity ventilation facility starts the actuator to adjust, the electric actuator of the air door drives the air door blade to rotate to the target angle, and the frequency converter of the fan adjusts the motor power frequency to change the speed. When the device completes the adjustment action, its controller generates an adjustment completion status signal and returns it to the monitoring system through the communication interface. The status signal contains device identification, adjustment completion timestamp and actual achieved parameter value. After receiving the feedback signal of FM-003 air door, the actual opening angle is recorded as 44.7 degrees, and the completion time is 14:32:18 on a certain day. Similarly, the actual speed of FJ-012 fan is recorded as 1448 revolutions per minute, and the completion time is 14:32:22 on a certain day. These actual adjustment parameter values are stored in the adjustment history data table.

[0149] After the adjustment of the entity ventilation facility, the real-time monitoring sensor network deployed in each roadway in the underground mine begins to collect new ventilation state data. The sensor network is composed of wind speed sensors, wind pressure sensors, and gas concentration sensors. Each sensor collects data according to the set sampling period. Taking a main transportation roadway as an example, the wind speed sensor numbered CS-205 deployed in the roadway starts collecting data 3 minutes after the adjustment is completed, and measures the wind speed at this point to be 3.2 meters per second. The wind pressure sensor numbered CP-205 measures the wind pressure at this point to be 680 pascals. The methane concentration sensor numbered CG-205 measures the methane concentration to be 0.35 percent. In the air return roadway, the wind speed sensor numbered CS-312 measures the wind speed to be 2.8 meters per second, and the carbon monoxide concentration sensor numbered CG-312 measures the carbon monoxide concentration to be 18 ppm. Each sensor transmits the collected data to the data collection server of the ground monitoring center through the underground industrial Ethernet ring network. The server performs time stamp verification and data validity verification on the received data, and stores the valid data as a feedback data set after eliminating abnormal data beyond the physical range.

[0150] The ventilation state parameters in the feedback data set are compared and calculated with the baseline state data before the adjustment. Taking the roadway where the FM-003 air door is located as an example, the wind speed at this location before the adjustment is 2.5 meters per second, and the wind pressure is 520 pascals. After the adjustment, the wind speed changes to 3.2 meters per second, and the wind pressure changes to 680 pascals. The wind speed change is 0.7 meters per second, and the wind pressure change is 160 pascals. Combined with the actual adjustment parameter value, the opening angle of the FM-003 air door is adjusted from 30 degrees to 44.7 degrees, and the angle change is 14.7 degrees. By analyzing the relationship between the angle change and the wind speed change and the wind pressure change, the actual adjustment response characteristic of the air door is obtained. The response characteristic shows that for every 1 degree increase in the opening angle of the air door, the wind speed at this location increases by about 0.048 meters per second, and the wind pressure increases by about 10.9 pascals. For the FJ-012 fan, the speed is increased from 1200 revolutions per minute to 1448 revolutions per minute, with a speed change of 248 revolutions per minute. The corresponding downstream roadway wind speed is increased from 2.1 meters per second to 2.8 meters per second, with a wind speed change of 0.7 meters per second. It is concluded that for every 100 revolutions per minute increase in the speed of the fan, the downstream wind speed increases by about 0.28 meters per second.

[0151] According to the calculated actual adjustment response characteristics, the wind resistance characteristic parameters of the corresponding nodes or branches in the three-dimensional space topological relationship model are corrected. In the topological relationship model, the network branch corresponding to the FM-003 air door is Branch-128, and the original wind resistance coefficient parameter of this branch is 0.085 kg / m3. According to the actual adjustment response characteristics, when the opening angle of the air door is 44.7 degrees, the equivalent wind resistance coefficient of this branch should be corrected to 0.062 kg / m3. The parameter record of Branch-128 branch is located in the model database, and the wind resistance coefficient field value is updated to 0.062. For the network node corresponding to the FJ-012 fan, the node number is Node-076, and the coefficients of the wind pressure and air volume relationship curve in the original fan characteristic parameters need to be adjusted according to the actual operation characteristics. The fan characteristic curve parameters of the node are updated, so that the fan performance used in simulation calculation is consistent with the actual operation performance.

[0152] Meanwhile, the gas concentration measurement value in the feedback data is updated to the attribute data of the corresponding roadway node in the three-dimensional space topological relationship. The methane concentration sensor numbered CG-205 corresponds to the Node-205 node in the topological model, and the methane concentration attribute value of this node is updated from the original 0.42 percent to the newly collected 0.35 percent. The carbon monoxide concentration sensor numbered CG-312 corresponds to the Node-312 node, and the carbon monoxide concentration attribute value of this node is updated to 18 ppm. Through this parameter correction and data update operation, the network structure parameters, equipment characteristic parameters and environmental state parameters in the three-dimensional space topological relationship model are synchronized with the actual ventilation condition in the mine, ensuring that the model used in subsequent simulation calculation can truly reflect the running state of the current ventilation system and providing an accurate calculation basis for the next round of ventilation optimization and control.

[0153] The coal mine intelligent ventilation optimization and control system based on digital twinning of the embodiment of the application comprises:

[0154] A first unit is configured to acquire real-time ventilation state data and mine structure data in a coal mine;

[0155] A second unit is configured to determine a three-dimensional space topological relationship of a coal mine ventilation system based on the mine structure data, and map the real-time ventilation state data to corresponding roadway nodes and branch paths according to spatial coordinates to obtain a twinned ventilation state;

[0156] A third unit is configured to perform simulation calculation based on the three-dimensional space topological relationship to obtain a theoretical ventilation distribution state, compare the twinned ventilation state with the theoretical ventilation distribution state, determine a wind volume deviation area and a gas concentration abnormal area, and obtain ventilation deviation characteristics;

[0157] The fourth unit is configured to virtually simulate the adjustment state of the ventilation facility in the three-dimensional space topology relationship according to the ventilation deviation feature, determine an adjustment scheme meeting the ventilation demand constraint and the energy consumption constraint, and generate an optimized regulation and control instruction based on the adjustment scheme.

[0158] The fifth unit is configured to control the corresponding physical ventilation facility to perform an adjustment action based on the optimized regulation and control instruction, collect real-time ventilation state data after the adjustment as feedback data, and update the three-dimensional space topology relationship by using the feedback data, so as to keep consistency between the simulation calculation and the actual ventilation condition.

[0159] In a third aspect, an electronic device is provided, including:

[0160] a processor;

[0161] a memory for storing processor-executable instructions;

[0162] The processor is configured to invoke the instructions stored in the memory to execute the method described above.

[0163] In a fourth aspect, a computer-readable storage medium is provided, which stores computer program instructions, and the computer program instructions are executed by a processor to implement the method described above.

[0164] The present application can be a method, device, system and / or computer program product. The computer program product can include a computer-readable storage medium having stored thereon computer-readable program instructions that, when executed by a computer, cause the computer to carry out various aspects of the present application.

[0165] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligent ventilation optimization and control in coal mines based on digital twins, characterized in that, include: Acquire real-time ventilation status data and mine structure data in underground coal mines; Based on the mine structure data, the three-dimensional spatial topology of the coal mine ventilation system is determined, and the real-time ventilation status data is mapped to the corresponding roadway nodes and branch paths according to spatial coordinates to obtain twin ventilation status. Simulation calculations are performed based on the aforementioned three-dimensional spatial topological relationships to obtain the theoretical ventilation distribution state. The twin ventilation state is then compared with the theoretical ventilation distribution state to identify areas of airflow deviation and abnormal gas concentration, thus obtaining ventilation deviation characteristics, including: The roadway nodes in the three-dimensional spatial topology are taken as network nodes, and the branch paths are taken as network branches. The ventilation network is solved using the ventilation network solution equation to obtain the theoretical wind pressure value of each network node and the theoretical air volume value of each network branch, which are taken as the theoretical ventilation distribution state. Based on the measured air volume values ​​of each roadway node in the twin ventilation state and the theoretical air volume values ​​of the corresponding network nodes in the theoretical ventilation distribution state, the air volume deviation area is determined. The ventilation deviation characteristics are obtained by associating and combining the airflow deviation area, the gas concentration abnormal area, and the spatial range of the area. Based on the measured air volume values ​​of each roadway node in the twin ventilation state and the theoretical air volume values ​​of the corresponding network nodes in the theoretical ventilation distribution state, the air volume deviation area is determined, including: Based on the mapping relationship between the roadway node identifier in the twin ventilation state and the network node number in the theoretical ventilation distribution state, the measured air volume value of the roadway node with the same spatial location and the theoretical air volume value of the corresponding network node are determined. The difference between the measured air volume value of each roadway node at the same spatial location and the theoretical air volume value of the corresponding network node is calculated to obtain the air volume deviation value of each roadway node; The airflow deviation value is processed to obtain a relative deviation rate. The relative deviation rate is compared with a preset airflow deviation judgment criterion, and roadway nodes whose relative deviation rate exceeds the airflow deviation judgment criterion are identified as deviation nodes. Based on the spatial connectivity between the deviation nodes in the three-dimensional spatial topology, deviation nodes with direct branch path connections are clustered into the same deviation region group; Extract the node identifier, airflow deviation value, relative deviation rate, and branch path identifier connecting the deviation nodes from all deviation nodes in each deviation region group to obtain the airflow deviation region. Based on the ventilation deviation characteristics, the adjustment state of the ventilation facilities is virtually simulated in the three-dimensional spatial topology to determine the adjustment scheme that meets the ventilation demand constraints and energy consumption constraints, and an optimized control command is generated based on the adjustment scheme. Based on the optimized control command, the corresponding physical ventilation facility is controlled to perform adjustment actions, and real-time ventilation status data after adjustment is collected as feedback data. The feedback data is used to update the three-dimensional spatial topology to maintain the consistency between simulation calculation and actual ventilation conditions.

2. The method according to claim 1, characterized in that, Based on the mine structure data, the three-dimensional spatial topology of the coal mine ventilation system is determined, and the real-time ventilation status data is mapped to the corresponding roadway nodes and branch paths according to spatial coordinates to obtain twin ventilation status, including: Based on the roadway topology data in the mine structure data, the roadway connectivity is determined, and based on the ventilation facility location data in the mine structure data, the node locations and branch connections of the airflow path are determined, thus obtaining the three-dimensional spatial topology. Extract the spatial coordinate information of each measuring point in the real-time ventilation status data, and calculate the spatial distance between the measuring point data and each roadway node in the three-dimensional spatial topology for the spatial coordinate information of each measuring point data. Based on the spatial distance, a roadway node matching each measurement point data is selected, and the roadway node identifier of the matching roadway node is used as the roadway node identifier to which the corresponding measurement point data belongs; Based on the roadway node identifier, the air volume distribution data, air pressure distribution data and gas concentration distribution data of the corresponding measuring point are associated with the branch paths between the roadway node and the adjacent nodes, respectively. Based on the airflow continuity constraint, the real-time ventilation status data on the branch paths between adjacent nodes are interpolated to obtain the twin ventilation status corresponding to all nodes and branch paths in the three-dimensional spatial topology.

3. The method according to claim 1, characterized in that, Identify areas of abnormal gas concentration, including: The measured gas concentration values ​​of each roadway node in the twin ventilation state are compared with the ventilation safety concentration limit node by node to determine the roadway nodes whose measured gas concentration values ​​exceed the ventilation safety concentration limit. Based on the spatially continuous distribution of the roadway nodes exceeding the limit and the nodes within their coverage area, the abnormal gas concentration area is determined.

4. The method according to claim 1, characterized in that, Based on the ventilation deviation characteristics, a virtual simulation of the ventilation facility's adjustment state is performed within the three-dimensional spatial topology to determine an adjustment scheme that satisfies ventilation demand constraints and energy consumption constraints. Based on this adjustment scheme, optimized control commands are generated, including: Based on the ventilation deviation characteristics, the target area to be adjusted is determined in the three-dimensional spatial topology. Based on the connectivity path of the target area in the three-dimensional spatial topology, the candidate adjustment objects are determined as ventilation facilities that affect the ventilation state of the target area. For each candidate adjustment object, multiple sets of virtual adjustment parameters are determined. These virtual adjustment parameters are applied to the boundary conditions of the corresponding ventilation facilities in the three-dimensional spatial topology. Virtual pre-simulation calculations are performed using the ventilation network solution equation to obtain the pre-simulation ventilation distribution state corresponding to each set of virtual adjustment parameters. Extract the pre-simulated air volume and pre-simulated gas concentration values ​​of the target area from each pre-simulated ventilation distribution state, and screen out candidate adjustment parameter groups that meet ventilation demand constraints and ventilation safety concentration constraints based on the pre-simulated air volume and pre-simulated gas concentration values; Calculate the total energy consumption of the ventilation system corresponding to each candidate set of adjustment parameters, and select a candidate set of adjustment parameters as the optimal set of adjustment parameters based on the total energy consumption of the ventilation system to obtain the adjustment scheme; The optimal adjustment parameter set of each candidate adjustment object in the adjustment scheme is converted into the corresponding action command of the ventilation facility, and the optimized control command is generated.

5. The method according to claim 4, characterized in that, For each candidate adjustment object, multiple sets of virtual adjustment parameters are determined. These virtual adjustment parameters are applied to the boundary conditions of the corresponding ventilation facilities in the three-dimensional spatial topology. Virtual pre-simulation calculations are performed using the ventilation network solution equation to obtain the pre-simulated ventilation distribution state corresponding to each set of virtual adjustment parameters, including: Based on the facility type and current regulation status parameters of each candidate regulation object, determine the physical dimensions and value boundaries of the regulation parameters; Based on the value boundary and the current adjustment state parameter, multiple virtual adjustment parameter values ​​are generated within the value boundary, and the virtual adjustment parameter values ​​are arranged in order to obtain a virtual adjustment parameter sequence. Each virtual adjustment parameter value in the virtual adjustment parameter sequence is combined with the identifier of the candidate adjustment object to obtain multiple sets of virtual adjustment parameters; In the three-dimensional spatial topology, the location of the ventilation facility corresponding to each candidate adjustment object is determined, and the boundary condition values ​​of the corresponding ventilation facility locations in the three-dimensional spatial topology are updated based on each set of virtual adjustment parameters. For each set of virtual control parameters updated in three-dimensional space topology, the theoretical wind pressure values ​​of each network node and the theoretical air volume values ​​of each network branch corresponding to that set of virtual control parameters are obtained by solving the ventilation network equations. The theoretical wind pressure values ​​of network nodes and the theoretical air volume values ​​of network branches corresponding to each set of virtual adjustment parameters are combined to determine the pre-simulated ventilation distribution state corresponding to each set of virtual adjustment parameters.

6. The method according to claim 1, characterized in that, Based on the optimized control command, the corresponding physical ventilation facility is controlled to perform adjustment actions, and real-time ventilation status data after adjustment is collected as feedback data. The feedback data is used to update the three-dimensional spatial topology to maintain consistency between simulation calculations and actual ventilation conditions, including: Based on the identifiers of each candidate control object in the optimized control command, the communication interface for querying the corresponding physical ventilation facility is determined; The system sends control commands to the corresponding physical ventilation facilities through the communication interface, drives the physical ventilation facilities to perform adjustment actions, receives adjustment completion status signals from the physical ventilation facilities, and records the actual adjustment parameter values ​​of each physical ventilation facility. After the physical ventilation system completes its adjustment, real-time ventilation status data at each monitoring point is collected via a real-time monitoring sensor network as the feedback data. The actual adjustment response characteristics are obtained by comparing the feedback data with the actual adjustment parameter values. Based on the actual adjustment response characteristics and the actual adjustment parameter values, the wind resistance characteristic parameters of the network nodes or branches where the ventilation facilities are located in the three-dimensional spatial topology are corrected, and the gas concentration measurement values ​​in the feedback data are updated to the gas concentration attribute values ​​of the corresponding roadway nodes in the three-dimensional spatial topology to maintain the consistency between the simulation calculation and the actual ventilation conditions.

7. A digital twin-based intelligent ventilation optimization and control system for coal mines, used to implement the method as described in any one of claims 1-6, characterized in that, include: The first unit is used to acquire real-time ventilation status data and mine structure data in underground coal mines; The second unit is used to determine the three-dimensional spatial topology of the coal mine ventilation system based on the mine structure data, and to map the real-time ventilation status data to the corresponding roadway nodes and branch paths according to spatial coordinates to obtain twin ventilation status; The third unit is used to perform simulation calculations based on the three-dimensional spatial topological relationship to obtain the theoretical ventilation distribution state. The twin ventilation state is compared with the theoretical ventilation distribution state to determine the air volume deviation area and the gas concentration abnormal area, thereby obtaining the ventilation deviation characteristics. The fourth unit is used to virtually simulate the adjustment state of the ventilation facilities in the three-dimensional spatial topology based on the ventilation deviation characteristics, determine the adjustment scheme that meets the ventilation demand constraints and energy consumption constraints, and generate optimized control instructions based on the adjustment scheme; The fifth unit is used to control the corresponding physical ventilation facilities to perform adjustment actions based on the optimized control instructions, and to collect real-time ventilation status data after adjustment as feedback data. The feedback data is used to update the three-dimensional spatial topology to maintain the consistency between simulation calculations and actual ventilation conditions.

8. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 6.

Images