Downhole dynamic ventilation and cooling collaborative control method and system based on digital twinning

Abstract

The application belongs to the technical field of intelligent control in mining industry, and specifically provides a kind of underground dynamic ventilation and cooling collaborative control method and system based on digital twinning, which mainly includes: synchronizing the original data set collected by underground sensor in real time through digital twinning model;Data partition is carried out on the original data set to obtain temperature-equipment group and wind speed-equipment group;According to the temperature-equipment group, the equipment-temperature dynamic relationship atlas is constructed;Extract the key nodes in the equipment-temperature dynamic relationship atlas to generate the key relationship sequence;Generate the ventilation equipment wind speed adjustment amount and the temperature control equipment start-stop instruction.The application dynamically generates the linkage regulation and control instruction of ventilation and temperature control equipment by collaborative analysis of temperature conduction path and equipment correlation, can comprehensively analyze multiple equipment states, temperature path and roadway topology, accurately identify the heat conduction law, realize the collaborative control of ventilation and cooling, improve the system regulation and control efficiency, avoid local control overload, and optimize resource allocation.

Description

Technical Field

[0001] The present invention belongs to the field of mining intelligent control technology, and in particular relates to a method and system for coordinated control of underground dynamic ventilation and cooling based on digital twins. Background Art

[0002] In underground operating environments, the monitoring of underground environmental parameters and equipment control are usually carried out separately. On the one hand, various sensors are used to collect data on environmental parameters such as underground temperature and wind speed. On the other hand, the control of ventilation and temperature control equipment is mostly based on manual experience or preset fixed parameters.

[0003] At present, some ventilation and cooling control methods for underground environments lack comprehensive analysis of the operating status of multiple devices, historical temperature conduction paths and tunnel spatial topology. Since the mine thermal environment is affected by the dynamic coupling of airflow diffusion, equipment layout and heat source distribution, discrete control strategies are difficult to accurately identify the heat conduction patterns across regions and time periods, which greatly reduces the overall control efficiency of the system and easily leads to excessive local control load or unnecessary waste of resources. Summary of the Invention

[0004] This application provides a method and system for coordinated control of underground dynamic ventilation and cooling based on digital twins, which effectively solves the problem that some ventilation and cooling control methods in underground environments in the existing technology lack comprehensive analysis of the operating status of multiple devices, historical temperature conduction paths and tunnel space topology. It can comprehensively analyze the status of multiple devices, temperature paths and tunnel topology, accurately identify the laws of heat conduction, realize coordinated control of ventilation and cooling, improve system regulation efficiency, avoid local control overload, and optimize resource allocation.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present application provides a method for coordinated control of underground dynamic ventilation and cooling based on digital twins, comprising:

[0007] The original data set collected by downhole sensors is synchronized in real time through the digital twin model; wherein the digital twin model is constructed based on the three-dimensional spatial parameters of the downhole tunnel.

[0008] The original data set is divided into temperature-device group and wind speed-device group.

[0009] Construct a device-temperature dynamic relationship map based on temperature-device groups.

[0010] Extract key nodes from the equipment-temperature dynamic relationship graph and generate key relationship sequences.

[0011] According to the wind speed-equipment group and key relationship sequence, collaborative control processing is performed to obtain the wind speed adjustment amount of the ventilation equipment and the start and stop instructions of the temperature control equipment.

[0012] Furthermore, the original data set includes: real-time temperature data, real-time wind speed data and equipment operation status data; wherein, the equipment operation status data includes temperature control equipment and its number and ventilation equipment.

[0013] The original data set is divided into temperature-device groups and wind speed-device groups, including:

[0014] The real-time temperature data is bound to the temperature control device and divided into time windows to form a temperature-device group; the real-time wind speed data is bound to the ventilation equipment and divided into time windows to form a wind speed-device group.

[0015] Furthermore, a device-temperature dynamic relationship map is constructed based on the temperature-device group, including:

[0016] An improved long short-term memory network is used to process the temperature-device group, extract the temperature change trend, associate and map the temperature change trend with the number of the temperature control device, and generate a device-temperature dynamic relationship map.

[0017] Furthermore, the equipment operation status data includes a start / stop flag.

[0018] Extract key nodes from the equipment-temperature dynamic relationship graph and generate key relationship sequences, including:

[0019] The equipment-temperature dynamic relationship map is compressed in multiple stages to obtain a compressed map.

[0020] The shortest path algorithm is used to extract candidate key nodes from the compressed graph.

[0021] According to the start and stop marks in the equipment operation status data, the nodes in the candidate key nodes that are within the equipment operation period are filtered.

[0022] According to the numbering sequence of temperature control equipment, the node temperature values, critical path numbers and start and stop periods are integrated to generate a key relationship sequence.

[0023] Furthermore, the device-temperature dynamic relationship map is subjected to multi-stage compression to obtain a compressed map, including:

[0024] Based on the binding relationship between temperature control devices in the temperature-device group, nodes associated with the same device are merged into a hierarchical device group.

[0025] The temperature data in each hierarchical device group is averaged to generate a compressed hierarchical map.

[0026] Furthermore, the shortest path algorithm is used to extract candidate key nodes from the compressed graph, including:

[0027] In the hierarchical graph, the shortest path algorithm is used to trace back from the current moment node to the historical temperature peak node, and the path back to the historical temperature peak node is marked as the critical path.

[0028] Nodes in the critical path that are directly associated with at least two temperature control devices are extracted as candidate key nodes.

[0029] Furthermore, according to the wind speed-equipment group and key relationship sequence, a coordinated control process is performed to obtain the wind speed adjustment value of the ventilation equipment and the start and stop instructions of the temperature control equipment, including:

[0030] An improved convolutional neural network is used to process wind speed-equipment groups and key relationship sequences. The improved convolutional neural network includes an input layer, a feature matching layer and a control output layer.

[0031] The input layer includes a first branch and a second branch in parallel, the first branch is used to extract wind speed time series features from the wind speed-equipment group, and the second branch is used to extract key relationship features from the key relationship sequence.

[0032] The feature matching layer is used to fuse the wind speed time series features with the key relationship features to generate equipment control priority parameters.

[0033] The control output layer is used to calculate the wind speed adjustment amount of the ventilation equipment and the start and stop instructions of the temperature control equipment according to the equipment control priority parameters.

[0034] Furthermore, the digital twin-based underground dynamic ventilation and cooling coordinated control method also includes: synchronizing the wind speed adjustment amount and the start-stop instruction to the digital twin model.

[0035] Furthermore, the digital twin-based coordinated control method for underground dynamic ventilation and cooling also includes: adjusting the ventilation equipment according to the wind speed adjustment amount, and controlling the temperature control equipment according to the start and stop instructions.

[0036] In a second aspect, the present application provides an underground dynamic ventilation and cooling coordinated control system based on digital twins, which includes:

[0037] Data acquisition module: synchronizes the original data set collected by downhole sensors in real time through the digital twin model; wherein, the digital twin model is constructed based on the three-dimensional spatial parameters of the downhole tunnel.

[0038] Data classification and analysis module: divides the original data set into temperature-device groups and wind speed-device groups.

[0039] Dynamic association module: Constructs a dynamic equipment-temperature relationship map based on temperature-equipment groups.

[0040] Key node extraction module: extracts key nodes from the equipment-temperature dynamic relationship graph and generates a key relationship sequence.

[0041] Collaborative control decision module: performs collaborative control processing based on wind speed-equipment groups and key relationship sequences to obtain wind speed adjustment values ​​for ventilation equipment and start / stop instructions for temperature control equipment.

[0042] In the third aspect, the present application provides an underground dynamic ventilation and cooling collaborative control device based on digital twins, which includes a memory and a processor; the memory is used to store computer programs; the processor is used to implement the steps of the underground dynamic ventilation and cooling collaborative control method based on digital twins as described in the first aspect when executing the computer program.

[0043] In a fourth aspect, the present application provides a storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the steps of the underground dynamic ventilation and cooling coordinated control method based on digital twins as described in the first aspect are executed.

[0044] Beneficial effects of the present invention:

[0045] This application collaboratively analyzes the relationship between temperature conduction paths and equipment, and dynamically generates linkage control instructions for ventilation and temperature control equipment, effectively solving the problem that some ventilation and cooling control methods in existing technologies for underground environments lack comprehensive analysis of the operating status of multiple devices, historical temperature conduction paths, and tunnel space topology. It can comprehensively analyze the status of multiple devices, temperature paths, and tunnel topology, accurately identify heat conduction laws, realize coordinated control of ventilation and cooling, improve system control efficiency, avoid local control overload, and optimize resource allocation.

[0046] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1A schematic diagram of the process of the underground dynamic ventilation and cooling coordinated control method based on digital twin of the present invention is shown;

[0049] Figure 2 A module schematic diagram of the underground dynamic ventilation and cooling coordinated control system based on digital twin of the present invention is shown. DETAILED DESCRIPTION

[0050] In order to solve the problems raised by the background technology, by collaboratively analyzing the relationship between temperature conduction paths and equipment, dynamic generation of linkage control instructions for ventilation and temperature control equipment can be achieved. It can comprehensively analyze the status of multiple devices, temperature paths and tunnel topology, accurately identify the heat conduction rules, realize coordinated control of ventilation and cooling, improve system control efficiency, avoid local control overload, and optimize resource allocation.

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0052] In some embodiments, as Figure 1 As shown, the present application provides a method for coordinated control of underground dynamic ventilation and cooling based on digital twins, including:

[0053] S1. Real-time synchronization of raw data sets collected by downhole sensors through a digital twin model; the digital twin model is constructed based on the three-dimensional spatial parameters of the downhole tunnel.

[0054] The digital twin model is constructed based on the three-dimensional spatial parameters of the underground tunnel, including:

[0055] According to the actual physical structure of the underground tunnel, the tunnel height, width, strike length and equipment installation position parameters are obtained as the basic input for 3D space modeling.

[0056] The parameters are converted into a virtual tunnel model through 3D modeling software, which includes virtual entities of ventilation equipment, temperature control equipment and sensors.

[0057] Compare the spatial coordinates of the virtual tunnel model with the laser scanning point cloud data of the actual tunnel to ensure that the model error is less than the preset threshold and complete the construction of the digital twin model.

[0058] S2. Divide the original data set into temperature-device groups and wind speed-device groups.

[0059] S3. Construct a device-temperature dynamic relationship map based on the temperature-device group.

[0060] S4. Extract key nodes from the equipment-temperature dynamic relationship graph and generate a key relationship sequence.

[0061] S5. Perform collaborative control processing based on the wind speed-equipment group and key relationship sequence to obtain the wind speed adjustment value of the ventilation equipment and the start and stop instructions of the temperature control equipment.

[0062] In some embodiments, the original data set includes: real-time temperature data, real-time wind speed data and equipment operation status data; wherein the equipment operation status data includes temperature control equipment and its number and ventilation equipment.

[0063] Real-time temperature data is the temperature value collected by the downhole temperature sensor at a fixed sampling period (such as once per minute).

[0064] Real-time wind speed data is the wind speed value collected by the built-in wind speed sensor of the ventilation equipment with the same sampling period.

[0065] The equipment operation status data includes the equipment number and start / stop status of the temperature control equipment, and the equipment number of the ventilation equipment.

[0066] In S2, the original data set is divided into temperature-device groups and wind speed-device groups, including:

[0067] Bind real-time temperature data to temperature control devices and divide them into time windows to form temperature-device groups; bind real-time wind speed data to ventilation equipment and divide them into time windows to form wind speed-device groups.

[0068] The real-time temperature data can be grouped according to the device ownership based on the temperature control device number.

[0069] Specifically, a hash table may be established, with the device number of the temperature control device as a key, and the temperature data of the same temperature control device in the same time period may be stored in the same data group.

[0070] The temperature data is divided into consecutive time periods according to a fixed time length. The data in each time period forms a subset of the temperature-device group. For example, the fixed time length can be 5 minutes.

[0071] Similarly, according to the number of ventilation equipment, the real-time wind speed data is bound and divided into time windows to form a wind speed-equipment group.

[0072] For example, the temperature data 002 of the temperature control device T-001 from 13:00:00 to 13:05:00 is [28°C, 29°C, 30°C]. After binding, the subset of the temperature-device group {T-001: [28, 29, 30], timestamp: 13:00-13:05} is generated.

[0073] The wind speed data 003 of the ventilation equipment V-001 from 13:00:00 to 13:05:00 is [1.2m / s, 1.5m / s, 1.8m / s]. After binding, the subset of the wind speed-equipment group {V-001: [1.2, 1.5, 1.8], timestamp: 13:00-13:05} is generated.

[0074] In some embodiments, constructing a device-temperature dynamic relationship map based on the temperature-device group in S3 includes:

[0075] An improved long short-term memory network is used to process the temperature-device group, extract the temperature change trend, associate the temperature change trend with the number of the temperature control device, and generate a device-temperature dynamic relationship map.

[0076] Specifically, the improved long short-term memory network includes: a temporal input layer, a device embedding layer, a feature fusion layer, and a graph generation layer.

[0077] The time series input layer is used to extract the temperature sequence of a temperature-controlled device in the temperature-device group within the time window.

[0078] For example, the temperature sequence of the temperature control device T-001 from timestamps 13:00 to 13:05 is [28°C, 29°C, 30°C].

[0079] The temperature sequence is then processed sequentially by LSTM units according to time steps to extract the temporal features of temperature changes, including temperature change trends, fluctuation amplitudes, and change rates. Temperature change trends include rising / falling trends.

[0080] For example, if the time series characteristic form of temperature change is [0.8, -0.2, 0.5], 0.8 represents the strength of the rising trend, -0.2 represents the instantaneous fluctuation, and 0.5 represents the rate of change.

[0081] The device embedding layer maps the temperature control device into a device embedding vector containing spatial location attributes.

[0082] For example, if the total length of the tunnel is 500 meters, the longitudinal length is 20 meters, and the height is 3 meters, the temperature control device T-001 is mapped to [0.2, 0.5, 0.8] through the table lookup method, which means that the temperature control device T-001 is located at 100 meters horizontally, 10 meters vertically, and 2.4 meters high.

[0083] The feature fusion layer concatenates the temperature change trend and the device embedding vector, generates fusion features through linear transformation in the fully connected layer, and obtains the device-temperature association feature vector.

[0084] The graph generation layer is used to calculate the cosine similarity of the device-temperature association feature vectors between temperature control devices. The adjacency matrix is ​​constructed with the temperature control device numbers as rows and columns and the similarities of the temperature control devices as matrix elements to obtain the device-temperature dynamic relationship graph.

[0085] In some embodiments, S4 extracts key nodes from the device-temperature dynamic relationship graph to generate a key relationship sequence, including:

[0086] S41. Perform multi-stage compression on the equipment-temperature dynamic relationship map to obtain a compressed map.

[0087] S42. Use the shortest path algorithm to extract candidate key nodes from the compressed graph.

[0088] S43. Filter the candidate key nodes that are within the equipment operation period according to the start / stop flags in the equipment operation status data.

[0089] S44. Integrate the node temperature values, critical path numbers, and start / stop periods according to the serial number sequence of the temperature control devices to generate a key relationship sequence.

[0090] In some embodiments, in S41, the device-temperature dynamic relationship map is compressed in multiple stages to obtain a compressed map, including:

[0091] S411. Based on the binding relationship between the temperature control devices in the temperature-device group, nodes associated with the same device are merged into a hierarchical device group.

[0092] Based on the device binding relationship in the temperature-device group, nodes of the same temperature control device in different time windows are identified, and multiple nodes corresponding to the same temperature control device are merged into a hierarchical device group.

[0093] For example, if the temperature control device T-001 has nodes A, B, and C in the time windows 13:00-13:05, 13:05-13:10, and 13:10-13:15, respectively, nodes A, B, and C are merged to generate the hierarchical device group GT-001.

[0094] S412. Take the average of the temperature data in each hierarchical device group to generate a compressed hierarchical map.

[0095] The temperature data within the hierarchical device group is averaged, and the average temperature is used as the attribute of the new node to generate a compressed hierarchical graph.

[0096] For example, if the hierarchical device group GT-001 includes temperature values ​​28°C, 29°C, and 30°C, and the calculated average is 29°C, a new node NT-001 is generated with the attribute 29°C, replacing the original nodes A, B, and C.

[0097] In some embodiments, the shortest path algorithm is used in S42 to extract candidate key nodes from the compressed graph, including:

[0098] S421. In the hierarchical graph, the shortest path algorithm is used to trace back from the current moment node to the historical temperature peak node, and the path traced back to the historical temperature peak node is marked as the critical path.

[0099] The cosine similarity of the temperature change trends between temperature control devices can be calculated and used as the edge weight of the path in the hierarchical graph.

[0100] Locate the node corresponding to the latest time window in the hierarchical graph, start from the current node, and traverse in reverse along the path with the highest edge weight until the historical temperature peak node is found. Mark the traversal path as the key path, and arrange the path nodes in timestamp order.

[0101] For example, if the traversal path is: current node NT-001, node NT-003, node NT-002, and the path edge weights are 0.85 and 0.92 respectively, then the paths NT-001, NT-003, and NT-002 are marked as critical paths.

[0102] S422. Extract nodes in the critical path that are directly associated with at least two temperature control devices as candidate critical nodes.

[0103] Extract the nodes in the critical path that are directly associated with at least two temperature control devices, record the nodes that meet the conditions in path order, and generate a list of candidate critical nodes.

[0104] For example, if the key path nodes are: NT-001, NT-003, NT-002, then NT-003 is extracted as a candidate key node.

[0105] In S43, the timestamps of the candidate key nodes are traversed to filter out the nodes that overlap with the equipment start and stop periods. If the node timestamp is completely included in the equipment operation period, it is retained; otherwise, it is discarded.

[0106] For example, if the timestamp of the candidate key node NT-003 is 13:10-13:15, and the temperature control device T-001 is marked as "running" during this period, the node is retained; if the timestamp of the candidate key node NT-005 is 12:50-12:55, and the temperature control device T-001 is marked as "shutdown" during this period, the node is eliminated.

[0107] Eliminate downtime nodes to prevent issuing instructions to non-operating temperature control devices. Only retain operating time nodes to ensure that ventilation and cooling instructions are accurately applied to active devices, reducing computational redundancy.

[0108] In S44 , the candidate key nodes are arranged in ascending order according to the number of the temperature control device, and the node temperature value, key path sequence number, and start / stop period are extracted for each node in turn to generate a key relationship sequence.

[0109] For example, a key relationship sequence generated at a certain time is: device T-001: node NT-001 (temperature 29°C, path P-001, time period 13:00-14:00); device T-002: node NT-002 (temperature 32°C, path P-001, time period 13:00-14:00).

[0110] In some embodiments, in S5, a coordinated control process is performed based on the wind speed-device group and the key relationship sequence to obtain the wind speed adjustment value of the ventilation device and the start and stop instructions of the temperature control device, including:

[0111] An improved convolutional neural network is used to process wind speed-equipment groups and key relationship sequences. The improved convolutional neural network includes an input layer, a feature matching layer and a control output layer.

[0112] The input layer includes a first branch and a second branch in parallel, the first branch is used to extract wind speed time series features from the wind speed-equipment group, and the second branch is used to extract key relationship features from the key relationship sequence.

[0113] Specifically, the first branch extracts local wind speed fluctuation characteristics through convolution kernel sliding to obtain wind speed time series characteristics. The wind speed time series characteristics include wind speed rising / falling trends, instantaneous fluctuations, and fluctuation frequency.

[0114] For example, if the wind speed time series feature is: [0.7, -0.3, 0.5], 0.7 represents an upward trend in wind speed, -0.3 represents instantaneous fluctuation, and 0.5 represents the frequency of fluctuation.

[0115] Specifically, the second branch encodes the temperature control device number, temperature value, and path sequence number into a dense vector through the embedding layer. After splicing, the key relationship features are extracted through the fully connected layer. The key relationship features include the spatial location attributes of the temperature control device, the temperature state correlation strength, and the path conduction priority.

[0116] The spatial location attributes of the temperature control device are generated by encoding the number of the temperature control device in the embedding layer, reflecting the normalized coordinates of the temperature control device in the digital twin model.

[0117] The temperature state correlation strength is generated by encoding and fusing the node temperature value and the critical path sequence number. The larger the value, the stronger the correlation between the current temperature and the historical peak path.

[0118] Path conduction priority represents the path conduction priority, which is generated by associating the start and stop periods with the equipment operating status. The smaller the value, the less important the conduction role of the node in the path.

[0119] The feature matching layer is used to fuse wind speed time series features with key relationship features to generate equipment control priority parameters.

[0120] The wind speed time series features and key relationship features will be spliced ​​together, and the weights will be automatically and dynamically assigned through the fully connected layer. The equipment control priority parameters will be generated based on the weighted results.

[0121] For example, if the priority parameter of device T-001 is 0.85 and that of device T-002 is 0.62, the wind speed of the ventilation device associated with T-001 is adjusted first.

[0122] The control output layer is used to calculate the wind speed adjustment of the ventilation equipment and the start and stop instructions of the temperature control equipment according to the equipment control priority parameters.

[0123] The priority parameter is linearly mapped to a wind speed adjustment percentage. For example, a priority of 0.85 corresponds to a 15% increase in wind speed, and a priority of 0.62 corresponds to a 5% increase in wind speed.

[0124] If the priority parameter exceeds the preset threshold (such as 0.8), a start / stop instruction for the temperature control device is generated.

[0125] For example, if the priority of temperature control device T-001 is 0.85, the wind speed of ventilation device V-001 is increased by 15%, and T-001 cooling is started at the same time; if the priority of temperature control device T-002 is 0.62, only the wind speed of ventilation device V-002 is increased by 5%, and the temperature control device is not started.

[0126] In some embodiments, the digital twin-based underground dynamic ventilation and cooling coordinated control method also includes: synchronizing the wind speed adjustment amount and the start-stop instructions to the digital twin model.

[0127] In some embodiments, the digital twin-based coordinated control method for underground dynamic ventilation and cooling also includes: adjusting the ventilation equipment according to the wind speed adjustment amount, and controlling the temperature control equipment according to the start and stop instructions.

[0128] According to the wind speed adjustment amount, a control signal is sent to the physical ventilation equipment to adjust its motor speed or blade angle. After the adjustment is completed, the actual wind speed value is sent back through the sensor to verify whether it matches the target value.

[0129] According to the start / stop command (such as starting the temperature control device T-001), the power on / off command is sent to the physical temperature control device; if the command is "start", the refrigeration unit is activated and the target temperature is set (such as 25°C); if the command is "stop", the refrigeration unit is turned off.

[0130] In some embodiments, as Figure 2 As shown, the present application provides an underground dynamic ventilation and cooling coordinated control system based on digital twin, which includes:

[0131] Data acquisition module: The original data set collected by downhole sensors is synchronized in real time through the digital twin model; among them, the digital twin model is built based on the three-dimensional spatial parameters of the downhole tunnel.

[0132] Data classification and analysis module: divides the original data set into temperature-device groups and wind speed-device groups.

[0133] Dynamic association module: Constructs a dynamic equipment-temperature relationship map based on temperature-equipment groups.

[0134] Key node extraction module: extracts key nodes from the equipment-temperature dynamic relationship graph and generates a key relationship sequence.

[0135] Collaborative control decision module: performs collaborative control processing based on wind speed-equipment groups and key relationship sequences to obtain wind speed adjustment values ​​for ventilation equipment and start / stop instructions for temperature control equipment.

[0136] In some embodiments, the present application provides an underground dynamic ventilation and cooling collaborative control device based on digital twins, which includes a memory and a processor; the memory is used to store computer programs; the processor is used to implement the steps of an underground dynamic ventilation and cooling collaborative control method based on digital twins when executing the computer program.

[0137] In some embodiments, the present application provides a storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the steps of a method for coordinated control of underground dynamic ventilation and cooling based on digital twins are executed.

[0138] Any reference to memory, storage, database, or other media used in the embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0139] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or elements that are inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0140] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for coordinated control of underground dynamic ventilation and cooling based on digital twin, characterized in that: include: The digital twin model is used to synchronize the original data set collected by downhole sensors in real time; wherein the digital twin model is constructed based on the three-dimensional spatial parameters of the downhole tunnel; The original data set is divided into temperature-device group and wind speed-device group; Construct a dynamic relationship map between equipment and temperature based on the temperature-equipment group; Extract key nodes from the equipment-temperature dynamic relationship graph and generate key relationship sequences; According to the wind speed-equipment group and key relationship sequence, collaborative control processing is performed to obtain the wind speed adjustment value of the ventilation equipment and the start and stop instructions of the temperature control equipment; The original data set includes: real-time temperature data, real-time wind speed data and equipment operation status data; the equipment operation status data includes temperature control equipment and its number, ventilation equipment, start and stop marks; Extract key nodes from the equipment-temperature dynamic relationship graph and generate key relationship sequences, including: Performing multi-stage compression on the equipment-temperature dynamic relationship map to obtain a compressed map; The shortest path algorithm is used to extract candidate key nodes from the compressed graph; According to the start and stop marks in the equipment operation status data, select the nodes in the equipment operation period among the candidate key nodes; According to the numbering sequence of temperature control equipment, the node temperature values, critical path numbers and start and stop periods are integrated to generate a key relationship sequence.

2. The underground dynamic ventilation and cooling coordinated control method based on digital twin according to claim 1 is characterized in that: The original data set is divided into temperature-device groups and wind speed-device groups, including: The real-time temperature data is bound to the temperature control device and divided into time windows to form a temperature-device group; the real-time wind speed data is bound to the ventilation equipment and divided into time windows to form a wind speed-device group.

3. The underground dynamic ventilation and cooling coordinated control method based on digital twin according to claim 2 is characterized in that: Build a dynamic equipment-temperature relationship map based on temperature-equipment groups, including: An improved long short-term memory network is used to process the temperature-device group, extract the temperature change trend, associate and map the temperature change trend with the number of the temperature control device, and generate a device-temperature dynamic relationship map.

4. The underground dynamic ventilation and cooling coordinated control method based on digital twin according to claim 1 is characterized in that: The device-temperature dynamic relationship map is subjected to multi-stage compression to obtain a compressed map, including: Based on the binding relationship between temperature control devices in the temperature-device group, nodes associated with the same device are merged into a hierarchical device group; The temperature data in each hierarchical device group is averaged to generate a compressed hierarchical map.

5. The underground dynamic ventilation and cooling coordinated control method based on digital twin according to claim 4 is characterized in that: The shortest path algorithm is used to extract candidate key nodes from the compressed graph, including: In the hierarchical graph, the shortest path algorithm is used to trace back from the current moment node to the historical temperature peak node, and the path back to the historical temperature peak node is marked as the critical path; Nodes in the critical path that are directly associated with at least two temperature control devices are extracted as candidate key nodes.

6. The underground dynamic ventilation and cooling coordinated control method based on digital twin according to claim 1 is characterized in that: Based on the wind speed-equipment group and key relationship sequence, collaborative control processing is performed to obtain the wind speed adjustment value of the ventilation equipment and the start and stop instructions of the temperature control equipment, including: An improved convolutional neural network is used to process wind speed-equipment groups and key relationship sequences. The improved convolutional neural network includes an input layer, a feature matching layer, and a control output layer. The input layer includes a first branch and a second branch in parallel, the first branch is used to extract wind speed time series features from the wind speed-equipment group, and the second branch is used to extract key relationship features from the key relationship sequence; The feature matching layer is used to fuse the wind speed time series features with the key relationship features to generate equipment control priority parameters; The control output layer is used to calculate the wind speed adjustment amount of the ventilation equipment and the start and stop instructions of the temperature control equipment according to the equipment control priority parameters.

7. The underground dynamic ventilation and cooling coordinated control method based on digital twin according to claim 1 is characterized in that: Also includes: The wind speed adjustment amount and the start / stop instruction are synchronized to the digital twin model.

8. The underground dynamic ventilation and cooling coordinated control method based on digital twin according to claim 1 is characterized in that: Also includes: The ventilation equipment is adjusted according to the wind speed adjustment amount, and the temperature control equipment is controlled according to the start and stop instructions.

9. A digital twin-based underground dynamic ventilation and cooling coordinated control system, characterized in that: It includes: Data acquisition module: synchronizes the raw data sets collected by downhole sensors in real time through a digital twin model built based on the three-dimensional spatial parameters of the downhole tunnel; Data classification and analysis module: divides the original data set into temperature-device groups and wind speed-device groups; Dynamic association module: builds a dynamic relationship map between equipment and temperature based on temperature-equipment groups; Key node extraction module: extracts key nodes from the equipment-temperature dynamic relationship graph and generates a key relationship sequence; Collaborative control decision module: performs collaborative control processing based on wind speed-equipment groups and key relationship sequences to obtain wind speed adjustment values ​​for ventilation equipment and start / stop instructions for temperature control equipment; The original data set includes: real-time temperature data, real-time wind speed data and equipment operation status data; the equipment operation status data includes temperature control equipment and its number, ventilation equipment, start and stop marks; Extract key nodes from the equipment-temperature dynamic relationship graph and generate key relationship sequences, including: Performing multi-stage compression on the equipment-temperature dynamic relationship map to obtain a compressed map; The shortest path algorithm is used to extract candidate key nodes from the compressed graph; According to the start and stop marks in the equipment operation status data, select the nodes in the equipment operation period among the candidate key nodes; According to the numbering sequence of temperature control equipment, the node temperature values, critical path numbers and start and stop periods are integrated to generate a key relationship sequence.

Images