A method and system for intelligent drainage through a mine drainage system

Abstract

This invention relates to a method and system for intelligent drainage through a mine drainage system. The mine drainage system includes a digital twin platform, drainage power components installed at each water storage node in a water storage unit, and a pressure transmitter installed on the main pipeline of the water storage unit; the main pipeline is connected to branch pipelines of the water storage nodes; the method includes: S11, acquiring the current back pressure information of the main pipeline and the predicted inflow velocity of each water storage node; S12, for each water storage node, determining the remaining water storage time of the water storage node based on the predicted inflow velocity, maximum volume, and current water storage volume; S13, for each water storage node, acquiring the target control command of the water storage node from a decision matrix based on the remaining water storage time and current back pressure information. This application achieves the technical effect of coordinating the overall pipeline network pressure and dynamically adapting the drainage power source.

Description

Technical Field

[0001] This invention relates to the field of mine drainage technology, and in particular to a method and system for intelligent drainage through a mine drainage system. Background Technology

[0002] During mine production, the underground hydrological environment is complex and changeable. A safe and efficient mine drainage system is a core infrastructure to ensure the safety of mine operations. Traditional mine drainage systems mostly adopt a passive drainage mode of "single centrifugal pump + water level threshold control", that is, the water pump is started when the water level in the water tank reaches the preset high level and the water pump is stopped when the water level drops to the low level.

[0003] However, as mine depths increase and pipeline network complexity grows, this traditional approach reveals serious flaws: First, control is characterized by lag and localization. Traditional systems rely solely on the current water level to react passively, lacking proactive prediction of water inrush trends; and they cannot coordinate various drainage nodes. When a large-scale water inrush occurs suddenly in the mine, multiple nodes will simultaneously activate high-flow-rate pumps to discharge the floodwater.

[0004] Secondly, there is a serious risk of pipe network congestion and pump stalling. Multiple centrifugal pumps simultaneously injecting water into the same main pipe can cause a sharp increase in back pressure. When the back pressure exceeds the pump's maximum head, the actual output of the centrifugal pump will plummet or even drop to zero, resulting in pump stalling. This not only fails to effectively drain water but also easily burns out the motor, paralyzing the entire drainage network system.

[0005] Therefore, there is an urgent need for an intelligent drainage method that can coordinate the overall pipeline pressure and dynamically adapt to the drainage power source, so as to solve the problem of system paralysis caused by back pressure overload of the main pipeline when multiple nodes are draining concurrently, and ensure the safety and efficiency of the mine drainage system. Summary of the Invention

[0006] One of the objectives of this invention is to provide a method and system for intelligent drainage through a mine drainage system.

[0007] According to one aspect of this application, a method for intelligent drainage through a mine drainage system is provided. The mine drainage system includes a digital twin platform, drainage power components installed at various water storage nodes in a water storage unit, and a pressure transmitter installed on the main pipeline of the water storage unit. The pressure transmitter acquires the current back pressure information of the main pipeline. The main pipeline is connected to branch pipelines of the water storage nodes. The drainage power components include centrifugal pumps and positive displacement pumps, which are connected in parallel and switched between the centrifugal pumps and positive displacement pumps via an electromagnetic clutch. The method is applied to the digital twin platform and includes: S11. Obtain the current back pressure information of the main pipeline and the predicted inflow velocity of each water storage node. S12. For each water storage node, determine the remaining water storage time of the water storage node based on the predicted inflow velocity, maximum volume, and current water storage volume. S13. For each water storage node, obtain the target control command of the water storage node from the decision matrix based on the remaining water storage time and the current back pressure information of the water storage node; wherein, the target control command includes turning on the centrifugal pump of the water storage node, turning on the volumetric pump of the water storage node, or controlling the branch pipe of the water storage node to be in the closed state.

[0008] According to another aspect of this application, a mine drainage system is provided. The mine drainage system includes a digital twin platform, drainage power components installed at various water storage nodes in a water storage unit, and a pressure transmitter installed on the main pipeline of the water storage unit. The pressure transmitter acquires the current back pressure information of the main pipeline. The main pipeline is connected to branch pipelines of the water storage nodes. The drainage power components include centrifugal pumps and positive displacement pumps, which are connected in parallel and switched between the centrifugal pumps and positive displacement pumps via an electromagnetic clutch. The digital twin platform includes: The module is used to obtain the current back pressure information of the main pipeline and the predicted inflow velocity of each water storage node. The first and second modules are used to determine the remaining water storage time of each water storage node based on the predicted inflow velocity, maximum volume, and current water storage volume. The first and third modules are used to obtain the target control instructions for each water storage node from the decision matrix based on the remaining water storage time and the current back pressure information. The target control instructions include turning on the centrifugal pump of the water storage node, turning on the volumetric pump of the water storage node, or controlling the branch pipes of the water storage node to be closed.

[0009] According to another aspect of this application, a computer device is provided, including a memory and a processor, wherein a computer program capable of being loaded by the processor and executing the methods described above is stored in the memory.

[0010] According to another aspect of this application, a computer-readable storage medium is provided, storing a computer program that can be loaded by a processor and executed as described above.

[0011] Compared with existing technologies, this application overcomes the hardware limitations of single-pump systems by using a parallel arrangement of centrifugal and positive displacement pumps in the drainage power components, switching between them via an electromagnetic clutch, and acquiring current back pressure information via a pressure transmitter in the main pipeline. This enables global pipeline resistance sensing. By acquiring the predicted inflow velocity of the storage node and combining it with the maximum volume and current water volume, the remaining storage time of the storage node is determined, solving the problem of drainage decision lag. Environmental geological factors and dynamic change rates are transformed into intuitive remaining safety time, providing a buffer for peak-shifting scheduling and early intervention. By obtaining target control commands from the decision matrix based on the remaining storage time and current back pressure information of the storage node, global adaptive peak-shifting scheduling is achieved. This innovatively reduces the dimensionality of the node urgency (representing the local situation) and the main pipeline back pressure (representing the global situation) through matrix processing, avoiding system collapse caused by multiple storage nodes competing for pipeline space. By controlling the activation of the centrifugal or positive displacement pump at the storage node through target control commands, the pipeline impedance is dynamically matched, eliminating the risk of pump failure. Attached Figure Description

[0012] Figure 1 A flowchart of a method for intelligent drainage through a mine drainage system according to an embodiment of this application is shown; Figure 2 A schematic diagram of the structure of a digital twin platform according to an embodiment of this application is shown; Figure 3 Exemplary systems that can be used to implement the various embodiments described in this application are shown. Detailed Implementation

[0013] The present application will now be described in further detail with reference to the accompanying drawings.

[0014] In a typical configuration of this application, the terminal, the device of the service network, and the trusted party all include one or more processors (e.g., a central processing unit (CPU)), input / output interfaces, network interfaces, and memory.

[0015] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory. Memory is an example of computer-readable media.

[0016] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PCM), programmable random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0017] The devices referred to in this application include, but are not limited to, terminals, network devices, or devices formed by integrating terminals and network devices through a network. The terminals include, but are not limited to, any mobile electronic product capable of human-computer interaction (e.g., via a touchpad), such as smartphones and tablets. These mobile electronic products can use any operating system, such as Android or iOS. The network devices include electronic devices capable of automatically performing numerical calculations and information processing according to pre-set or stored instructions. Their hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), and embedded devices. The network devices include, but are not limited to, computers, network hosts, single network servers, multiple network server clusters, or clouds composed of multiple servers. Here, a cloud consists of a large number of computers or network servers based on cloud computing, where cloud computing is a type of distributed computing, consisting of a virtual supercomputer composed of a group of loosely coupled computer clusters. The network includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, VPN network, wireless ad hoc network, etc. Preferably, the device can also be a program running on the terminal, network device, or a device formed by integrating the terminal and network device, network device, touch terminal, or network device and touch terminal through a network.

[0018] Of course, those skilled in the art should understand that the above-described devices are merely examples, and other existing or future devices that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0019] In the description of this application, "multiple" means two or more, unless otherwise expressly and specifically defined.

[0020] refer to Figure 1This invention provides a flowchart of a method for intelligent drainage through a mine drainage system according to an embodiment of this application. The mine drainage system includes a digital twin platform, drainage power components installed at each water storage node in a water storage unit, and a pressure transmitter installed on the main pipeline of the water storage unit. The pressure transmitter acquires the current back pressure information of the main pipeline. The main pipeline is connected to the branch pipelines of the water storage nodes. The drainage power components include a centrifugal pump and a positive displacement pump, which are connected in parallel and switched between the centrifugal pump and the positive displacement pump via an electromagnetic clutch. The method is applied to the digital twin platform and includes steps S11 and S12. Step S13: In step S11, the current back pressure information of the main pipeline and the predicted inflow velocity of each water storage node are obtained. In step S12, for each water storage node, the remaining water storage time of the water storage node is determined based on the predicted inflow velocity, maximum volume, and current water storage volume. In step S13, for each water storage node, the target control command of the water storage node is obtained from the decision matrix based on the remaining water storage time and current back pressure information. The target control command includes activating the centrifugal pump of the water storage node, activating the volumetric pump of the water storage node, or controlling the branch pipeline of the water storage node to be in a closed state. In some embodiments, the mine may include multiple water storage units, each water storage unit including multiple water storage nodes and a main pipeline. The branch pipelines of multiple water storage nodes in the same water storage unit are connected to the main pipeline of the water storage unit, and the water in the water storage nodes is discharged to the surface through the main pipeline. In some embodiments, the water storage nodes include, but are not limited to, water storage tanks, through which mine water is collected. In some embodiments, a centrifugal pump and a positive displacement pump are connected in parallel. One end of the centrifugal pump has a suction pipe that is inserted into a water storage node, and the other end has an outlet pipe that connects to a branch pipe of the water storage node. Similarly, one end of the positive displacement pump has a suction pipe that is inserted into the water storage node, and the other end has an outlet pipe that connects to a branch pipe of the water storage node. Furthermore, a one-way valve is installed on the outlet pipes of both the centrifugal pump and the positive displacement pump to prevent backflow of high-pressure water from one pump to the other pump when it is not in operation. For example, the one-way valve of the positive displacement pump is closed when the centrifugal pump is started, and vice versa. In some embodiments, a motor is installed between the centrifugal pump and the positive displacement pump. One end of the motor is equipped with a first electromagnetic clutch, and the output shaft of that end of the motor is connected to the centrifugal pump; the other end of the motor is equipped with a second electromagnetic clutch, and the output shaft of that end of the motor is connected to the positive displacement pump.When the target control command includes starting the centrifugal pump at the water storage node: the motor starts, and simultaneously, the PLC (for example, in a mine drainage system, the PLC also includes a PLC communicating with a digital twin platform to receive the target control command issued by the digital twin platform; simultaneously, the PLC is electrically connected to the electromagnetic clutch and the motor to control the motor and the corresponding electromagnetic clutch) energizes the coil of the first electromagnetic clutch. The electromagnet inside the first electromagnetic clutch generates a strong magnetic force, tightly engaging the friction disc, so that the motor's power is transmitted to the centrifugal pump; at this time, the second electromagnetic clutch is de-energized and released, and the volumetric pump does not rotate. When the target control command includes starting the volumetric pump at the water storage node: the PLC cuts off the power to the first electromagnetic clutch, and the centrifugal pump slowly stops due to inertia; simultaneously, the second electromagnetic clutch is energized and engaged, so that the motor's power is switched to the volumetric pump, and the volumetric pump begins to pump water forcibly; when the target control command includes the branch pipe of the water storage node being in the closed state, the PLC controls the disengagement of the first and second electromagnetic clutches. In some embodiments, the digital twin platform is electrically connected to the drainage power component, pressure transmitter, and sensor components (e.g., the mine drainage system also includes sensor components) so that the digital twin platform can send target control commands to the corresponding drainage power component, acquire current back pressure information, or sensor data, etc. It should be noted that the "flow velocity" mentioned in this application (e.g., predicted inflow velocity, inflow velocity label information, etc.) refers to volumetric flow rate in fluid mechanics, with units of cubic meters per hour or cubic meters per second, etc.

[0021] Specifically, in step S11, the current back pressure information of the main pipeline and the predicted inflow velocity of each water storage node are obtained. For example, the current back pressure information of the main pipeline is obtained through a pressure transmitter installed on the main pipeline. In some embodiments, the predicted inflow velocity includes, but is not limited to, the estimated volumetric flow rate of groundwater flowing into the water storage node within a certain future time period (e.g., 1 minute, 5 minutes, 10 minutes, etc.). In some embodiments, the predicted inflow velocity is obtained based on the current liquid level change sequence and the current inflow flow sequence of the water storage node. For a detailed explanation of the predicted inflow velocity, please refer to the corresponding embodiments below, which will not be repeated here.

[0022] In step S12, for each water storage node, the remaining water storage time is determined based on the predicted inflow velocity, maximum volume, and current water storage capacity of the node. For example, Here, This indicates the remaining water storage time. This represents the maximum volume. This indicates the current water storage volume. This refers to the predicted inflow velocity. In some embodiments, the remaining water storage time includes, but is not limited to, the time required to fill the current water storage node. In some embodiments, the sensor components include, but are not limited to, level gauges. For example, the current liquid level of the water storage node is obtained through the level gauge, and the current water storage volume of the water storage node is obtained based on the current liquid level and the bottom area of ​​the water storage node. In some embodiments, fixed data such as the bottom area and maximum volume of each water storage node can be pre-stored in the system. Different water storage nodes correspond to different node identifiers, and different node identifiers are associated and bound with the corresponding fixed data such as bottom area and maximum volume for retrieval. Here, those skilled in the art will understand that, in order to avoid the problem of insufficient system response and eventual mine flooding due to blind optimism about the safe time in the event of sudden equipment failure or extreme water disaster conditions, this embodiment directly determines the remaining water storage time of the water storage node based on the maximum volume, current water storage volume, and predicted inflow velocity of the water storage node.

[0023] In step S13, for each water storage node, the target control command for the water storage node is obtained from the decision matrix based on the remaining water storage time and current back pressure information. The target control command includes activating the centrifugal pump, activating the volumetric pump, or controlling the branch pipes of the water storage node to be closed. In some embodiments, the decision matrix includes multiple quadrants, each corresponding to a control command. For example, the target quadrant corresponding to the water storage node is determined based on the remaining water storage time and current back pressure information, and the control command corresponding to the target quadrant is used as the target control command for that water storage node. For a detailed explanation of this part, please refer to the corresponding embodiments below, which will not be repeated here. In this embodiment, the target control command is obtained through the decision matrix, realizing global adaptive peak-shifting drainage scheduling. It creatively matrixes the local node urgency and the global main pipeline back pressure, avoiding system collapse caused by multiple water storage nodes competing for pipeline space.

[0024] In some embodiments, the mine drainage system further includes sensor components disposed at each water storage node in the water storage unit; the predicted inflow velocity is obtained by the following method: for each water storage node, local variable information of the water storage node is obtained through the sensor components; wherein, the local variable information includes the current liquid level and instantaneous inflow flow of the water storage node; a current liquid level change rate sequence and a current inflow flow sequence of the water storage node are generated based on the current liquid level and the instantaneous inflow flow of the water storage node at multiple consecutive times; the predicted inflow velocity of the water storage node is obtained by inputting the current liquid level change rate sequence, the current inflow flow sequence, and the geological structure data of the water storage node into the inflow velocity model. In some embodiments, the instantaneous inflow flow includes the volume content of water flowing from the underground aquifer into the water storage node. In some embodiments, the sensor components include, but are not limited to, level gauges, flow meters, etc. In some embodiments, a level gauge is installed within the water storage node to measure the current liquid level, and a flow meter is installed on the outlet pipes of the centrifugal pump and the positive displacement pump to measure the instantaneous outflow rate. The digital twin platform uses the liquid level rise rate obtained from the level gauge and the instantaneous outflow rate obtained from the flow meter to inversely calculate the instantaneous inflow rate of the water storage node using a mass conservation algorithm. For example, assuming the bottom area of ​​the water storage node is S, the system obtains the liquid level change ΔH within a preset time period Δt using the level gauge and the average outflow rate Qout within that time period using the flow meter on the outlet pipe. According to the law of conservation of mass, the rate of change of water volume within the water storage node (i.e., S × ΔH / Δt) is equal to the difference between the inflow rate (i.e., the instantaneous inflow rate Qin) and the outflow rate (Qout). Therefore, the instantaneous inflow rate Qin = Qout + (S × ΔH / Δt). For example, if the bottom area of ​​the water storage node is 50 m², and the liquid level rises by 1 m in 1 hour, the actual outflow rate of the centrifugal pump measured by the flow meter on the outlet pipe is 100 m³ / h; then the system can accurately calculate that the actual instantaneous inflow rate of the external rock strata is 100 + (50 × 1) = 150 m³ / h. In some embodiments, the current liquid level change rate sequence includes, but is not limited to, the change in the current liquid level of the water storage node over a continuous period of time, and the current inflow rate sequence includes, but is not limited to, the instantaneous inflow rate of the water storage node over a continuous period of time. For example, the system sets the sampling period to 1 minute to acquire data from the past 10 minutes. By recording the level gauge values ​​10 times consecutively and calculating the difference between adjacent time points, a sequence of current level change rates is obtained (e.g., [+0.05 m / min, +0.06 m / min, +0.08 m / min... up to 10 data points]). Similarly, by obtaining 10 consecutive instantaneous inflow rates, a sequence of current inflow rates is obtained (e.g., [5.0 m³ / min, 5.2 m³ / min, 5.5 m³ / min... up to 10 data points]). This reflects the dynamic trend of the inflow status changing over time.In some embodiments, geological structural data includes, but is not limited to, the permeability coefficient of the rock strata at the location of the water storage node, and the straight-line distance from a known aquifer or fault fracture zone. In this embodiment, the predicted inflow velocity of the water storage node is obtained by inputting the current liquid level change rate sequence, the current inflow rate sequence, and the geological structural data of the water storage node into the inflow velocity model. For a detailed explanation of the inflow velocity model, please refer to the corresponding embodiments below, which will not be repeated here.

[0025] In some embodiments, the inflow velocity model employs a Long Short-Term Memory (LSTM) network. The inflow velocity model is obtained by training multiple sets of training data and corresponding inflow velocity label information for each set of training data until the model converges, thus obtaining a trained inflow velocity model. The training data includes historical liquid level change rate sequences, historical inflow flow sequences, and geological structural data of the reservoir node. In some embodiments, the inflow velocity model employs a LSTM network. For example, the inflow velocity model includes an input layer (for inputting multi-dimensional data such as liquid level change rate sequences, inflow flow sequences, and geological structural data), a hidden layer (e.g., using one or two LSTM layers), and an output layer (e.g., a fully connected layer for outputting the predicted inflow velocity). For example, historical liquid level change rate sequences, historical inflow flow sequences, and geological structural data are obtained based on real historical data from the reservoir node. For example, the historical liquid level and historical inflow velocity of water storage node A from 8:00 to 9:00 on April 11, 2023, and the historical inflow velocity of water storage node A at 9:05 on April 11, 2023 are taken. Based on the historical liquid level of this one-hour period, the historical liquid level change rate sequence is obtained, and based on the historical inflow velocity of this one-hour period, the historical inflow velocity sequence is obtained. The historical inflow velocity of water storage node A at 9:05 on April 11, 2023 is used as label information, and the historical inflow velocity sequence and historical liquid level change rate sequence of this one-hour period are used as training data to input into the inflow velocity model for model training. The gradient descent method is used to continuously adjust the parameters inside the inflow velocity model until the difference between the predicted inflow velocity output by the inflow velocity model and the actual inflow velocity model is less than or equal to the target difference, the model is determined to have converged, and the trained inflow velocity model is obtained. Here, those skilled in the art can determine that in gradient descent methods (such as the Adam optimization algorithm), by using the mean square error between the predicted inrush velocity and the actual label value output by the model as the loss function, the gradient descent method can automatically calculate the error and backpropagate it, thereby continuously iteratively updating the neuron weights and bias terms such as the forget gate, input gate, and output gate inside the LSTM network, and achieving model convergence.

[0026] In some embodiments, the decision matrix includes multiple quadrants, each corresponding to a control command. Obtaining the target control command for a water storage node from the decision matrix based on its remaining storage time and current back pressure information includes: determining the matrix coordinate features of the water storage node based on the current back pressure information and its remaining storage time; wherein the matrix coordinate features include the current back pressure urgency and the current node urgency of the water storage node; determining the target quadrant corresponding to the water storage node in the decision matrix based on the current node urgency and the current back pressure urgency, and determining the control command corresponding to the target quadrant as the target control command for the water storage node. For example, the horizontal axis of the decision matrix includes node urgency, and the vertical axis includes back pressure urgency; dividing the node urgency on the horizontal axis into N intervals and the back pressure urgency on the vertical axis into M intervals to obtain multiple quadrants. Determining the current node urgency of the water storage node based on its remaining storage time and the current back pressure urgency based on the current back pressure information of the main pipeline to obtain the matrix coordinate features of the water storage node. Based on the matrix coordinate features of the water storage node, the quadrant in which the matrix coordinate features fall is queried from the decision matrix. This quadrant is taken as the target phenomenon, and the control command corresponding to the target quadrant is taken as the target control command.

[0027] In some embodiments, multiple node urgency levels, time intervals corresponding to each node urgency level, multiple back pressure urgency levels, and back pressure intervals corresponding to each back pressure urgency level are preset. The matrix coordinate features of the water storage node are determined based on the remaining water storage time and current back pressure information, including: determining the target time interval containing the remaining water storage time based on the remaining water storage time of the water storage node, and determining the node urgency corresponding to the target time interval as the current node urgency of the water storage node; determining the target back pressure interval containing the current back pressure information based on the current back pressure information, and determining the back pressure urgency corresponding to the target back pressure interval as the current back pressure urgency of the main pipeline; using the current node urgency and the current back pressure urgency as the matrix coordinate features of the water storage node. For example, node urgency levels include, but are not limited to, safety, alert, and emergency. For example, the time interval corresponding to safety includes ≥3 hours, the time interval corresponding to alert includes (1 hour, 3 hours), and the time interval corresponding to emergency includes ≤1 hour. For example, back pressure urgency levels include, but are not limited to, unobstructed, load, and high pressure. For example, the back pressure range corresponding to unobstructed flow includes <50% of the ultimate head back pressure threshold; the back pressure range corresponding to load includes [50% of the ultimate head back pressure threshold and 80% of the ultimate head back pressure threshold]; and the back pressure range corresponding to high pressure includes (80% of the ultimate head back pressure threshold and the ultimate head back pressure threshold). For instance, the system determines the back pressure range to which the current back pressure information falls based on the current back pressure information of the main pipeline, and uses the back pressure urgency corresponding to that back pressure range as the current back pressure urgency; it also determines the time interval to which the remaining water storage time falls based on the remaining water storage time of the water storage node, and uses the node urgency corresponding to that time interval as the current node urgency.

[0028] In some embodiments, the back pressure intervals corresponding to multiple back pressure urgency levels are independently set for each water storage node; the back pressure intervals corresponding to multiple back pressure urgency levels include a congested back pressure interval, and the lower limit value of the back pressure corresponding to the congested back pressure interval is the ultimate head back pressure threshold; the method further includes step S14 (not shown), in which: after controlling the start of the centrifugal pump of the water storage node, the current liquid level change rate and instantaneous inflow flow of the water storage node are obtained; the actual instantaneous outflow of the centrifugal pump is calculated based on the bottom area of ​​the water storage node, the current liquid level change rate and the instantaneous inflow flow; if the actual instantaneous outflow is lower than the preset quenching pump flow threshold, the current back pressure information of the main pipeline is obtained, and the ultimate head back pressure threshold corresponding to the water storage node is updated to the current back pressure information; when the target control command of the water storage node is subsequently obtained, the target back pressure interval where the current back pressure information of the main pipeline is located is re-determined based on the updated ultimate head back pressure threshold, and the target quadrant and target control command corresponding to the water storage node are determined from the decision matrix based on the back pressure urgency corresponding to the re-determined target back pressure interval. In some embodiments, the actual instantaneous outflow rate includes, but is not limited to, the volumetric flow rate of water actually discharged into the main pipeline by the drainage power component (centrifugal pump or positive displacement pump) after overcoming the current back pressure of the main pipeline. For example, in the above embodiments, the back pressure urgency and the corresponding back pressure range of each water storage node are the same; in other words, each water storage node uses a set of back pressure urgency and the corresponding back pressure range for each back pressure urgency. However, due to the different usage frequency of the drainage power component of each water storage node, the different geographical locations, which affect the physical wear and aging of the centrifugal pump impeller, and the friction fluid resistance loss along the connection of the branch pipes of each water storage node to the main pipeline, the multiple back pressure urgency and the corresponding back pressure range for each back pressure urgency may be different. In some embodiments, the congested back pressure range includes, but is not limited to, the system back pressure caused by the volumetric pressure of the flow in the main pipeline being too high, exceeding the pressure critical range that a specific centrifugal pump can overcome and normally push water outward; if the centrifugal pump is forced to operate under this back pressure range, not only will effective drainage not be achieved, but it will also cause the fluid to generate heat through ineffective friction within the pump chamber. In some embodiments, the flow threshold for the sluggish pump includes, but is not limited to, a set extremely low flow safety warning line (e.g., set to 5% of the centrifugal pump's factory rated outlet flow rate). When the actual instantaneous outlet flow rate of the centrifugal pump is lower than this threshold, it indicates that the water flow is no longer able to effectively remove the heat generated by the pump's high-speed operation, which can easily lead to the motor or impeller burning out due to high-temperature overload. In this embodiment, the need to adjust the limit head back pressure area of ​​the congestion back pressure range (e.g., the maximum back pressure that the centrifugal pump can withstand) is determined by monitoring the actual instantaneous outlet flow rate of the centrifugal pump. For example, if the actual instantaneous outlet flow rate is lower than the preset sluggish pump flow threshold, the current back pressure information of the main pipeline is used as the limit head back pressure threshold of the congestion back pressure range of the water storage node.

[0029] Figure 2 This diagram illustrates the structure of a digital twin platform for a mine drainage system according to an embodiment of this application. The mine drainage system includes a digital twin platform, drainage power components installed at each water storage node in a water storage unit, and a pressure transmitter installed on the main pipeline of the water storage unit. The pressure transmitter acquires the current back pressure information of the main pipeline. The main pipeline is connected to branch pipelines of the water storage nodes. The drainage power components include centrifugal pumps and positive displacement pumps, which are connected in parallel and switched between the centrifugal pumps and positive displacement pumps via an electromagnetic clutch. The digital twin platform includes three modules: Module 1, Module 2, and Module 3. Module 1 is used to obtain the current back pressure information of the main pipeline and the predicted inflow velocity of each water storage node; Module 2 is used to determine the remaining water storage time of each water storage node based on the predicted inflow velocity, maximum volume, and current water storage volume; Module 3 is used to obtain the target control command of each water storage node from the decision matrix based on the remaining water storage time and current back pressure information; wherein, the target control command includes turning on the centrifugal pump of the water storage node, turning on the volumetric pump of the water storage node, or controlling the branch pipeline of the water storage node to be in the closed state.

[0030] Here, the specific implementation methods corresponding to Module 1, Module 2, and Module 3 are the same as or similar to the specific embodiments of steps S11, S12, and S13 above, and therefore will not be repeated here, but are included by reference.

[0031] In addition to the methods and devices described in the above embodiments, this application also provides a computer-readable storage medium storing computer code that, when executed, performs the method described in any of the preceding embodiments.

[0032] This application also provides a computer program product that, when executed by a computer device, performs the method described in any of the preceding claims.

[0033] This application also provides a computer device, the computer device comprising: One or more processors; Memory, used to store one or more computer programs; When the one or more computer programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described in any of the preceding methods.

[0034] Figure 3 Exemplary systems that can be used to implement the various embodiments described in this application are shown; like Figure 3As shown in some embodiments, system 300 can function as any of the devices described in each of the embodiments. In some embodiments, system 300 may include one or more computer-readable media having instructions (e.g., system memory or NVM / storage device 320) and one or more processors (e.g., one or more processors 305) coupled to the one or more computer-readable media and configured to execute the instructions to implement the module and thus perform the actions described in this application.

[0035] In one embodiment, the system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of the processors 305 and / or any suitable device or component communicating with the system control module 310.

[0036] The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. The memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0037] System memory 315 can be used, for example, to load and store data and / or instructions for system 300. In one embodiment, system memory 315 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, system memory 315 may include double data rate type quad synchronous dynamic random access memory (DDR4 SDRAM).

[0038] In one embodiment, the system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to the NVM / storage device 320 and (one or more) communication interfaces 325.

[0039] For example, NVM / storage device 320 may be used to store data and / or instructions. NVM / storage device 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (one or more) non-volatile storage devices (e.g., one or more hard disk drives (HDDs), one or more optical disc drives (CDs), and / or one or more digital universal optical disc (DVD) drives).

[0040] NVM / storage device 320 may include storage resources that are physically part of a device on which system 300 is mounted, or that can be accessed by the device without necessarily being part of it. For example, NVM / storage device 320 may be accessed via a network through one or more communication interfaces 325.

[0041] One or more communication interfaces 325 may provide the system 300 with an interface to communicate over one or more networks and / or with any other suitable device. The system 300 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0042] In one embodiment, at least one of the processors 305 may be logically packaged with one or more controllers of the system control module 310 (e.g., memory controller module 330). In one embodiment, at least one of the processors 305 may be logically packaged with one or more controllers of the system control module 310 to form a system-in-package (SiP). In one embodiment, at least one of the processors 305 may be integrated with the logic of one or more controllers of the system control module 310 on the same die. In one embodiment, at least one of the processors 305 may be integrated with the logic of one or more controllers of the system control module 310 on the same die to form a system-on-a-chip (SoC).

[0043] In various embodiments, system 300 may be, but is not limited to, a server, workstation, desktop computing device, or mobile computing device (e.g., laptop computing device, handheld computing device, tablet computer, netbook, etc.). In various embodiments, system 300 may have more or fewer components and / or different architectures. For example, in some embodiments, system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touchscreen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0044] It should be noted that this application can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In one embodiment, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, a magnetic or optical drive, a floppy disk, or similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0045] Furthermore, a portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0046] Communication media include media through which communication signals containing, for example, computer-readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media can include guided transmission media (such as cables and wires (e.g., optical fibers, coaxial cables, etc.)) and wireless (unguided transmission) media capable of propagating energy waves, such as sound, electromagnetic, RF, microwave, and infrared. Computer-readable instructions, data structures, program modules, or other data can be embodied as modulated data signals in, for example, wireless media (such as carrier waves or similar mechanisms embodied as part of spread spectrum technology). The term "modulated data signal" refers to a signal whose one or more characteristics are altered or set in a manner that encodes information in the signal. Modulation can be analog, digital, or a hybrid modulation technique.

[0047] By way of example and not limitation, computer-readable storage media may include volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memories such as random access memory (RAM, DRAM, SRAM); and non-volatile memories such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or hereafter developed capable of storing computer-readable information / data for use by a computer system.

[0048] Herein, one embodiment of this application includes an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the apparatus is triggered to run a method and / or technical solution based on the foregoing embodiments of this application.

[0049] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. A method for intelligent drainage through a mine drainage system, characterized in that, The mine drainage system includes a digital twin platform, drainage power components installed at each water storage node in the water storage unit, and a pressure transmitter installed on the main pipeline of the water storage unit. The pressure transmitter acquires the current back pressure information of the main pipeline. The main pipeline is connected to the branch pipelines of the water storage nodes. The drainage power components include centrifugal pumps and positive displacement pumps, which are connected in parallel and switched between the centrifugal pumps and positive displacement pumps via an electromagnetic clutch. The method is applied to the digital twin platform, and the method includes: S11. Obtain the current back pressure information of the main pipeline and the predicted inflow velocity of each of the water storage nodes; S12. For each water storage node, determine the remaining water storage time of the water storage node based on the predicted inflow velocity, maximum volume, and current water storage volume of the water storage node. S13. For each water storage node, obtain the target control instruction of the water storage node from the decision matrix based on the remaining water storage time of the water storage node and the current back pressure information; wherein, the target control instruction includes turning on the centrifugal pump of the water storage node, turning on the volumetric pump of the water storage node, or controlling the branch pipe of the water storage node to be in a closed state.

2. The method according to claim 1, characterized in that, The mine drainage system also includes sensor components installed at each of the water storage nodes in the water storage unit; the predicted inflow velocity is obtained through the following method: For each water storage node, local variable information of the water storage node is acquired through the sensor assembly; wherein, the local variable information includes the current liquid level and instantaneous inflow rate of the water storage node; The current liquid level change rate sequence and the current water flow rate sequence of the water storage node are generated based on the current liquid level and the instantaneous water flow rate of the water storage node at multiple consecutive times. The predicted inflow velocity of the water storage node is obtained by inputting the current liquid level change rate sequence, the current inflow flow sequence, and the geological structure data of the water storage node into the inflow velocity model.

3. The method according to claim 2, characterized in that, The inrush flow velocity model employs a long short-term memory network; the inrush flow velocity model is obtained through the following method: The inflow velocity model is trained by using multiple sets of training data and the corresponding inflow velocity label information for each set of training data until the model converges, thus obtaining the trained inflow velocity model; wherein, the training data includes historical liquid level change rate sequence, historical inflow flow sequence, and geological structure data of the water storage node.

4. The method according to claim 1, characterized in that, Determining the remaining water storage time of the water storage node based on its predicted inflow velocity, maximum volume, and current water storage capacity includes: Here, This indicates the remaining water storage time. This represents the maximum volume. This indicates the current water storage volume. This indicates the predicted inrush flow velocity.

5. The method according to claim 1, characterized in that, The decision matrix includes multiple quadrants, each quadrant corresponding to a control command; obtaining the target control command for the water storage node from the decision matrix based on the remaining water storage time and the current back pressure information includes: The matrix coordinate features of the water storage node are determined based on the current back pressure information and the remaining water storage time of the water storage node; wherein, the matrix coordinate features include the current back pressure urgency and the current node urgency of the water storage node; Based on the current node urgency and the current back pressure urgency, the target quadrant corresponding to the water storage node in the decision matrix is ​​determined, and the control command corresponding to the target quadrant is determined as the target control command corresponding to the water storage node.

6. The method according to claim 5, characterized in that, There are multiple node urgency levels, a time interval corresponding to each node urgency level, multiple back pressure urgency levels, and a back pressure interval corresponding to each back pressure urgency level. The step of determining the matrix coordinate features of the water storage node based on the remaining water storage time and the current back pressure information includes: The target time interval in which the remaining water storage time is located is determined based on the remaining water storage time of the water storage node, and the node urgency corresponding to the target time interval is determined as the current node urgency of the water storage node. The target back pressure interval where the current back pressure information is located is determined based on the current back pressure information, and the back pressure urgency corresponding to the target back pressure interval is determined as the current back pressure urgency of the main pipeline. The current node urgency and the current back pressure urgency are used as the matrix coordinate features of the water storage node.

7. The method according to claim 6, characterized in that, The back pressure intervals corresponding to the multiple back pressure urgency levels are independently set for each of the water storage nodes; the multiple back pressure intervals corresponding to the multiple back pressure urgency levels include congested back pressure intervals, and the lower limit value of the back pressure corresponding to the congested back pressure interval is the ultimate head back pressure threshold; the method further includes: After controlling the centrifugal pump of the water storage node to start, the current liquid level change rate and instantaneous inflow rate of the water storage node are obtained; The actual instantaneous outflow rate of the centrifugal pump is calculated based on the bottom area of ​​the water storage node, the current liquid level change rate, and the instantaneous inflow rate. If the actual instantaneous outflow rate is lower than the preset pump flow rate threshold, then the current back pressure information of the main pipeline is obtained, and the ultimate head back pressure threshold corresponding to the water storage node is updated to the current back pressure information. When obtaining the target control command for the water storage node, the target back pressure interval where the current back pressure information of the main pipeline is located is re-determined based on the updated ultimate head back pressure threshold. Based on the back pressure urgency corresponding to the re-determined target back pressure interval, the target quadrant and target control command corresponding to the water storage node are determined from the decision matrix.

8. A mine drainage system, characterized in that, The mine drainage system includes a digital twin platform, drainage power components installed at each water storage node in the water storage unit, and a pressure transmitter installed on the main pipeline of the water storage unit. The pressure transmitter acquires the current back pressure information of the main pipeline. The main pipeline is connected to branch pipelines at the water storage nodes. The drainage power components include centrifugal pumps and positive displacement pumps, which are connected in parallel and switched between each other via an electromagnetic clutch. The digital twin platform includes: The module is used to obtain the current back pressure information of the main pipeline and the predicted inflow velocity of each of the water storage nodes. The first and second modules are used to determine the remaining water storage time of each water storage node based on the predicted inflow velocity, maximum volume, and current water storage volume of the water storage node. The first and third modules are used to obtain the target control instructions for each water storage node from the decision matrix based on the remaining water storage time and the current back pressure information; wherein, the target control instructions include turning on the centrifugal pump of the water storage node, turning on the volumetric pump of the water storage node, or controlling the branch pipes of the water storage node to be in a closed state.

9. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a method for intelligent drainage through a mine drainage system that can be loaded by the processor and executed as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The system stores a method for intelligent drainage via a mine drainage system that can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images