Mining intelligent ventilation scheduling decision-making system based on wind network calculation

Abstract

The invention discloses a mining intelligent ventilation scheduling decision-making system based on wind network calculation, and relates to the technical field of mining equipment, and the system comprises a data collection module which is used for collecting ventilation data of a whole mine; the wind network resolving module is used for reading the whole mine ventilation data in real time, carrying out wind network resolving and simulating the mine ventilation condition in real time to obtain a mine wind demand result; the data analysis module is used for analyzing the whole mine ventilation data and the mine wind demand result data; performing wind network diagnosis according to the underground roadway topological structure, and obtaining an optimization strategy according to a wind network diagnosis result; and the linkage control module is used for controlling automatic regulation and control of related equipment according to the optimization strategy. According to the invention, underground ventilation parameters are collected in a unified manner, wind network resolving data are analyzed in a unified manner, and ventilation facilities and equipment are subjected to linkage control, so that the purposes of supplying wind according to needs and controlling wind in catastrophe are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of mining equipment, and more particularly to a mining intelligent ventilation scheduling decision system based on wind network solution. Background Art

[0002] The ventilation system consists of ventilation power and its devices, ventilation shaft and tunnel networks, and airflow monitoring and control facilities. Currently, mine ventilation mostly uses fixed air volume ventilation for ventilation work. However, the complex and changeable working and production environment underground will cause the air volume required for working faces and tunnels to change under different working conditions. Ventilation work must meet the normal work needs of underground workers. If the air supply volume cannot be adjusted in time according to actual needs, serious accidents may occur. In addition, in actual production work, although multiple ventilation environment parameter monitoring points can be arranged underground, the goal of linked control of monitoring parameters, wind network solution data and ventilation facilities and equipment cannot be achieved.

[0003] Therefore, how to provide an intelligent mine ventilation scheduling decision system based on wind network solution, uniformly collect underground ventilation parameters, uniformly analyze wind network solution data, and perform linkage control of ventilation facilities and equipment to achieve on-demand air supply and disaster control is a problem that technical personnel in this field urgently need to solve. Summary of the Invention

[0004] In view of this, the present invention provides a mine intelligent ventilation scheduling decision system based on wind network solution, which uniformly collects underground ventilation parameters and uniformly analyzes wind network solution data. According to the wind network diagnosis expert database, the ventilation facilities and equipment are linked controlled with the results of ventilation auxiliary decision-making to achieve the purpose of on-demand air supply and disaster control, which is very necessary for coal mine ventilation safety.

[0005] In order to achieve the above objectives, the present invention adopts the following technical solution: a mine intelligent ventilation scheduling decision system based on wind network solution, comprising: Data acquisition module, used to collect ventilation data of the entire mine; A wind network solution module is used to read the ventilation data of the entire mine in real time, perform wind network solution, simulate the mine ventilation conditions in real time, and obtain the mine air requirement result; A data analysis module is used to analyze the ventilation data of the entire mine and the mine air demand result data; perform air network diagnosis based on the topological structure of the underground tunnel, and obtain an optimization strategy based on the air network diagnosis results; The linkage control module is used to control the automatic regulation of related equipment according to the optimization strategy.

[0006] Preferably, the wind network solution is based on the Gauss-Seidel iterative method to successively solve the loop air volume correction value until the correction value meets the preset accuracy.

[0007] Preferably, the wind network solution step includes: Input mine ventilation network parameter information; Perform wind resistance sorting, solve the minimum wind resistance tree, and determine the composition of independent circuits; Determine the characteristic curve of the fan; First, assign initial values ​​to the remaining tree edges, and then calculate the initial wind volume of each branch; Iterative calculation, calculate the air volume correction value of each circuit respectively, and perform air volume correction on all branches of the circuit; After each iteration, determine whether the accuracy requirement is met. If so, terminate the calculation; otherwise, return to continue the iteration. Output the calculated results of the ventilation network air volume.

[0008] Preferably, during the air network solution process, the calculation formula for the loop air volume correction value is as follows: ; Where: are the wind pressure expressed by the fan characteristic curve equation and the slope of the fan characteristic curve, respectively, and n represents the number of branches; is the air volume value of branch j; is the basic loop matrix; Indicates wind resistance; Indicates natural wind pressure.

[0009] Preferably, the calculation formula for air volume correction of all branches of the loop is as follows: ; Where: are the air volume values ​​of branch j before and after correction, represents the correction value of loop k at the i-th iteration.

[0010] Preferably, after each iteration, whether the accuracy requirement is met is determined, including: Determine whether the absolute value of the maximum value among all correction values ​​in a certain cycle is less than or equal to the set accuracy value, that is, it satisfies the following formula: ; Where EPS stands for precision, Indicates the maximum value among all correction values.

[0011] Preferably, a wind network diagnosis expert database is established, wherein the wind network anomalies in the wind network diagnosis expert database are divided into three major groups: wind path, equipment sensor, and wind network structure, and each group has different anomaly types; Based on the topological structure of the underground tunnel, the wind network diagnosis is carried out, and an optimization strategy is given based on the wind network diagnosis expert database. According to the optimization strategy, the air flow in the mine ventilation area is optimized.

[0012] Preferably, the related equipment includes: a main ventilator, a local ventilator, a damper and a window.

[0013] It can be seen from the above technical solution that compared with the existing technology, the present invention discloses a mine intelligent ventilation scheduling decision system based on wind network solution, which uniformly collects underground ventilation parameters and uniformly analyzes wind network solution data. According to the wind network diagnosis expert database, the ventilation facilities and equipment are linked and controlled based on the results of ventilation auxiliary decision-making to achieve the purpose of on-demand air supply and disaster wind control. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0015] Figure 1 This is a schematic diagram of the operating steps of the intelligent ventilation scheduling decision system provided by an embodiment of the present invention.

[0016] Figure 2 Schematic diagram of abnormal classification of the wind network diagnosis expert library provided by an embodiment of the present invention.

[0017] Figure 3 This is a schematic diagram of the database table design of the wind network diagnosis expert library provided by an embodiment of the present invention.

[0018] Figure 4 A schematic structural diagram of an intelligent ventilation system for mining provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 are within the scope of protection of the present invention.

[0020] The embodiment of the present invention discloses a mine intelligent ventilation scheduling decision system based on wind network solution, such as Figure 1 Shown, including: Data acquisition module, used to collect ventilation data of the entire mine; A wind network solution module is used to read the ventilation data of the entire mine in real time, perform wind network solution, simulate the mine ventilation conditions in real time, and obtain the mine air requirement result; A data analysis module is used to analyze the ventilation data of the entire mine and the mine air demand result data; perform air network diagnosis based on the topological structure of the underground tunnel, and obtain an optimization strategy based on the air network diagnosis results; The linkage control module is used to control the automatic regulation of related equipment according to the optimization strategy.

[0021] In a specific embodiment of the present invention, the data acquisition module collects relevant parameters such as wind speed, air volume, gas, etc. at key points of ventilation in the entire mine, as well as operating parameters of ventilation facilities and equipment, and uploads them to the mine ventilation monitoring center; the system classifies and stores the target data according to storage requirements, specifically including: (1) Coal mine basic data: Basic data includes mine ventilation system diagrams, ventilation network diagrams, fan models and parameters, damper locations and dimensions, roadway dimensions and locations, and a wind network diagnostic expert database. Basic data is mostly static and rarely changes once established, but it is crucial to the design and operation of intelligent ventilation systems. Therefore, the relational database MySQL is used for storage to facilitate structured data management and query.

[0022] (2) Real-time data: This type of data is continuously generated, changes frequently, and requires low-latency processing. It requires a time series database such as Redis to store and efficiently query data points that change over time. At the same time, a reasonable sampling rate and data retention policy should be set to balance storage costs and query requirements.

[0023] (3) Historical data: Data accumulated over a period of time is called historical data. This historical data can be used for ventilation system performance evaluation and historical troubleshooting. Therefore, in terms of storage design, it is necessary to use a time series database to store historical monitoring data. At the same time, the data can be transferred to a lower-cost storage medium such as HDFS for long-term storage. For data that requires in-depth analysis, it can be imported into a data warehouse such as InfluxDB for complex queries and report generation.

[0024] In a specific embodiment of the present invention, the system uses a wind network solution module to read underground sensor data in real time, perform wind network solution, simulate mine ventilation conditions in real time, calculate the mine air demand, and save it to the server; the wind network solution adopts the Scott-Hinsley method. This method is based on graph theory and follows the three laws of air flow: the nodal air volume balance law, the loop air pressure balance law, and the ventilation resistance law. The basic principle of its air volume solution is to successively solve the loop air volume correction value based on the Gauss-Seidel iterative method until the correction value meets the preset accuracy, and finally obtain the asymptotic air volume value that approximates the true solution of the system of equations.

[0025] Specifically, the basic steps of the Scott-Hinsley wind network solution are as follows: Step 1: Input the mine ventilation network parameter information, such as network structure status, branch attribute parameters, solution accuracy, etc. Step 2: Sort the wind resistance, solve the minimum wind resistance tree, and determine the composition of the independent loop; Specifically, solving the minimum drag tree determines the composition of the independent loop, including: 1. Wind Network Empowerment Modeling The ventilation network is abstracted into a graph theory model, where nodes represent tunnel intersections, branches represent ventilation tunnels, and branch weights are wind resistance values ​​Ri (units are );‌ If there are fixed air volume branches or special local wind networks (such as parallel branches), they need to be simplified according to the preset conditions: the local wind networks with significantly lower wind resistance than other branches are merged into a single branch, and the wind resistance of the simplified branch is taken as the maximum value in the local wind network.

[0026] 2. Apply Kruskal's algorithm ‌Sort branches‌: Sort all branches by wind resistance value from small to large;‌ ‌Stepwise edge selection‌: Starting from the branch with minimum wind resistance, select edges one by one to add to the spanning tree, ensuring that no loops are formed, until all nodes are connected;‌ Output: The minimum wind resistance tree generated finally contains There are branches (N is the number of nodes), and the remaining branches are cotyledons (the number of independent loops is equal to the number of cotyledons). 3. Correspondence between remaining branches and loops Each residual branch corresponds to an independent loop. When the residual branch is added to the minimum wind resistance tree, it will form a unique closed loop with the path in the tree, that is, an independent loop. 4. Trial backtracking to circle the loop Path tracing: Starting from one end of the remaining branch, trace back along the tree of least wind resistance to the other end, recording all branches passed; ‌Loop Generation‌: Merge the residual branches with the backtracking path to form a complete independent loop, with the loop direction defined by the residual branch wind direction; Avoid duplication: Mark processed subpaths with a hash table to avoid resolving repeated subproblems and improve efficiency. 5. Special treatment One-way airflow restriction: If the circuit where the remaining branches are located has one-way branches (such as fans or dampers), the circuit closure rules need to be adjusted according to the airflow direction.

[0027] Step 3: Due to the instability of fan operation, it is necessary to find the fan characteristic curve. The wind pressure characteristic curve can be regarded as a quadratic or cubic power function. The part of the curve within the normal operating range of the fan can be approximated as a quadratic parabola. Specifically, the process of solving the fan characteristic curve includes: 1. Establish Mathematical model: Based on the geometric parameters of the fan impeller and the principles of fluid mechanics, Mathematical model: H=a0+a1Q+a2Q²; 2. Pipeline network equation: Pipeline network resistance is proportional to the square of the air volume, that is, H=RQ², where R is the comprehensive air resistance of the pipeline network; 3. Solving a system of equations: Simultaneous fan Equation and pipe network equation, solve equation H 风机 =RQ 2 , get the actual operating air volume Q and air pressure H, and thus get the fan characteristic curve curve Step 4: Draft the initial wind volume. Usually, the initial values ​​are assigned to the remaining tree edges first, and then the initial wind volume of each branch is calculated. For computer calculation, any set of integers can be given as the initial value. Specifically, the calculation of the initial wind volume of each branch includes: taking the wind volume of the remaining tree as a known quantity, and using the node wind volume balance equation ∑Q 入 =∑Q 出 , by traversing the tree structure layer by layer to solve the branch wind volume‌.

[0028] ‌Start from the root node of the minimum wind resistance tree (usually the wind turbine inlet node) and proceed in the order of branch topology; According to the wind volume of the remaining tree edges and the known node flow constraints, the wind volume of each branch is recursively deduced.

[0029] Step 5: Iterate and calculate the air volume correction value of each circuit respectively, and perform air volume correction on all branches of the circuit; Step 6: Accuracy judgment: After each iteration, determine whether the accuracy requirement is met. If so, terminate the calculation; otherwise, jump to Step 5 to continue the iteration. Step 7: Output the calculated results of the ventilation network air volume.

[0030] Specifically, in the ventilation network graph G=(V,E), the number of nodes is m=|V|, the number of branches is n=|E|, and the number of independent loops is l =n-m+1; During the Scott-Hinsley method wind network solution, the calculation formula for the circuit air volume correction value is as follows: ; Where: are the wind pressure expressed by the fan characteristic curve equation and the slope of the fan characteristic curve, respectively, and n represents the number of branches; is the air volume value of branch j; is the basic loop matrix; Indicates wind resistance; Indicates natural wind pressure.

[0031] Specifically, the calculation formula for air volume correction for all branches of the circuit is as follows: ; Where: are the air volume values ​​of branch j before and after correction, Represents the correction value of loop k at the i-th iteration .

[0032] Specifically, after each iteration, whether the accuracy requirements are met is determined, including: Determine whether the absolute value of the maximum value among all correction values ​​in a certain cycle is less than or equal to the set accuracy value, that is, it satisfies the following formula: ; Where EPS represents the precision, which is generally 0.001~0.01; Indicates the maximum value among all correction values.

[0033] Specifically, a wind network diagnosis expert database is established. The wind network anomalies in the wind network diagnosis expert database are divided into three major groups: wind path, equipment sensor, and wind network structure. Each group has different anomaly types. Based on the topological structure of the underground tunnel, the wind network diagnosis is carried out, and an optimization strategy is given based on the wind network diagnosis expert database. According to the optimization strategy, the air flow in the mine ventilation area is optimized.

[0034] In a specific embodiment of the present invention, the whole mine ventilation data and the mine air demand result data are analyzed; the air network diagnosis is performed according to the underground tunnel topology structure; and the specific implementation process of the optimization strategy based on the air network diagnosis results includes: Step 1: Data analysis: Analyze sensor data, facility and equipment operating parameters, and wind network solution data, and issue audible and visual alarms for sensors that exceed the limit based on upper and lower thresholds.

[0035] Step 2: Establish a wind network diagnosis expert database (such as Figure 2 and Figure 3As shown in Table 1): Wind network anomalies are divided into three major groups: wind paths, equipment sensors, and wind network structures. Each group has different anomaly types. For example, the wind path group includes anomaly types such as wind speed exceeding the limit, wind speed being too low, wind flow reversal, drastic wind flow changes, and supply and demand imbalance. Taking the wind speed anomaly in the wind path group as an example, based on the regulations on diversion speed in the wells and tunnels (as shown in Table 1), the expert library parameter expression is set to batch set the wind speed thresholds for the inlet and return air lanes of all mining areas to [0.25, 6] m / s. Wind speeds outside this range are diagnosed as wind speed anomalies, wind speed being too low, or wind speed exceeding the limit.

[0036] Table 1 Permissible airflow speed in shafts and tunnels

[0037] Step 3: Air network diagnosis and scheduling decision: Utilizing sensor data and air network solution data, air network diagnosis is performed based on the underground tunnel topology. Optimization strategies are developed based on the experience of the expert database to optimize the airflow in the mine ventilation area.

[0038] Among them, when diagnosing the wind network, the wind network solver calculates a theoretical value, and the sensor measures an actual value. If there is a deviation between the actual value and the theoretical value, the wind network is abnormal.

[0039] The expert database will record abnormal conditions, abnormal causes, and optimization strategies; based on the abnormal conditions diagnosed by the wind network, the expert database will be searched and matched, and optimization strategies will be given.

[0040] Specifically, the related equipment includes: a main ventilator, a local ventilator, a damper and a window.

[0041] Specifically, based on the optimization strategy derived from the ventilation network diagnostic analysis results, the mine's main ventilation fans, local ventilation fans, dampers, windows, and other related equipment and facilities are controlled, automatically regulating the mine ventilation system to achieve on-demand air supply and avoid airflow disturbances, insufficient air volume, and over-ventilation in the mine. Real-I / O is physical and interacts directly with hardware devices, offering higher performance and lower latency, meeting the high-performance, low-latency requirements of coordinated ventilation system control. Based on the optimized air adjustment recommendations, the upper computer triggers the PLC control of the lower computer of the underground facilities and equipment through Real-I / O, thereby achieving the purpose of coordinated control.

[0042] In a specific embodiment of the present invention, in order to make up for the shortcomings of the existing technology of the three related technologies of ventilation parameter monitoring, ventilation facility equipment control, and wind network solution of mine ventilation systems, the embodiment of the present invention provides a system to realize ventilation parameter perception, real-time and timely diagnosis of wind network, ventilation auxiliary decision-making, and air volume allocation and control unified monitoring, unified allocation, unified control, and unified scheduling.

[0043] An intelligent ventilation system for mines, such as Figure 4 As shown, including the server layer: (1) Database server: It is equipped with database software (such as MongoDB, MySQL), has an external interface, and is responsible for storing and managing system-related data.

[0044] (2) Ventilation server: Install intelligent ventilation software, support OPC, MODBUS, FTP, API interface protocols and have external interfaces, mainly used for intelligent control and management of ventilation systems.

[0045] Network transmission layer: An industrial control fiber ring network connects the ring network switch (located in the dispatching room) and field switches to achieve reliable data transmission. Ethernet interfaces are used to connect different devices and ensure stable network communications.

[0046] Field control layer: Field subsystem control PLC: controls field equipment and is the core equipment of field automation control.

[0047] Subsystem host control machine: equipped with OPC, MODBUS, FTP, API interface protocols, as well as configuration software or dedicated control software, used to monitor and manage the on-site subsystem.

[0048] Various sensors: distributed on site, responsible for collecting environmental and ventilation parameter information such as wind speed, wind pressure, and gas concentration, and transmitting the data to the server for processing and analysis.

[0049] The ground dispatch center is equipped with a ventilation software industrial computer, a data server database, and wind network sensors. The industrial computer is installed with the intelligent ventilation master control software platform, which exchanges data with the data server. The wind network solution service's results, analyzed and calculated by the master control software, control ventilation facilities such as the main fan, local ventilators, dampers, and windows to perform micro-adjustments, optimizing the ventilation system. This also enables other functions, such as wind network fault warning and analysis, on-demand autonomous air supply, disaster wind control, and thermal dust simulation.

[0050] Based on the mine ventilation system diagram, the ventilation facilities at various locations and positions are depicted to reflect the operating status of the ventilation facilities, such as: the operation status of the main fan; the start and stop of the local fan, and the level; the damper switch status; the air window opening, etc.; the underground tunnel topology network structure is constructed, and the real-time wind flow demonstration is carried out according to the wind network solution results. The main ventilation parameters of each wind measuring point are monitored and displayed in real time: such as wind speed, etc.

[0051] Wind network diagnosis and analysis: Establish a wind network diagnosis expert database, obtain data from each ventilation monitoring point in real time, combine the wind network solution data, analyze and diagnose the wind network based on the expert database, and according to the diagnosis results, promptly deal with abnormal wind paths to ensure the normal and safe operation of the wind network.

[0052] The specific functions of the system in the embodiment of the present invention are as follows: (1) Ventilation facility equipment information management In view of the large number and dispersion of ventilation facilities and equipment, the system has the function of facility query. By inputting the relevant type of equipment or facilities at a certain location, the system can display the equipment information, operating status, monitoring parameter data at that location, and view the monitoring video images near the facility and equipment.

[0053] (2) Wind network solution Sensors collect data such as gas, carbon monoxide, oxygen, and wind speed at key wind measurement nodes, dampers, and windows underground. The data is uploaded to the intelligent ventilation network database for storage. The wind network solution module reads and compares the data, and pushes the air adjustment decision strategy to the linkage control module based on the wind network diagnosis expert database.

[0054] (3) Wind network diagnosis and early warning The wind network diagnosis expert database system diagnoses and issues early warnings for wind paths, equipment sensors, and wind network structures. When the system detects an abnormality, an alarm screen automatically pops up, giving both an audible and visual alarm and a disposal strategy.

[0055] (4) Intelligent linkage control Main fan: Regulate the main fan to operate in the optimal state according to the wind network monitoring data and solution results; realize main fan fault warning and maintenance push according to the fan status monitoring and solution results.

[0056] Local ventilation fan: Adaptive frequency conversion to adjust air volume according to wind network monitoring data and solution results.

[0057] Air damper: Adjust the opening and closing status of the air damper according to the wind network solution results to keep the ventilation system in the optimal state, and combine video monitoring to observe the status of the air damper facility in real time.

[0058] Wind window: Adjust the wind window opening in real time according to the monitored wind volume data and wind network solution results to meet the requirements of the plan.

[0059] Emergency mode: In the event of emergency modes such as equipment failure, fire, flood, gas exceeding the limit, etc., equipment linkage can be remotely implemented according to the plan to achieve automatic control.

[0060] (5) Intelligent ventilation decision-making The system mines and analyzes sensor data and wind network data to accurately identify abnormal ventilation status, causes and locations, and provides real-time warnings and assesses the timeliness, impact scope and severity of abnormal disasters.

[0061] (6) Data report analysis The system has the function of real-time curve and historical curve analysis, and can conduct horizontal and vertical comparative analysis of important parameters of sensors and ventilation facilities and equipment; the system also supports querying historical data, and querying and exporting ventilation-related reports (daily reports, monthly reports, and annual reports).

[0062] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0063] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A mine intelligent ventilation scheduling decision system based on wind network solution, characterized in that: include: Data acquisition module, used to collect ventilation data of the entire mine; A wind network solution module is used to read the ventilation data of the entire mine in real time, perform wind network solution, simulate the mine ventilation conditions in real time, and obtain the mine air requirement result; A data analysis module is used to analyze the ventilation data of the entire mine and the mine air demand result data; perform air network diagnosis based on the topological structure of the underground tunnel, and obtain an optimization strategy based on the air network diagnosis results; The linkage control module is used to control the automatic regulation of related equipment according to the optimization strategy.

2. The mine intelligent ventilation scheduling decision system based on wind network solution according to claim 1 is characterized in that: The wind network solution is based on the Gauss-Seidel iterative method to solve the loop air volume correction value one by one until the correction value meets the preset accuracy.

3. The mine intelligent ventilation scheduling decision system based on wind network solution according to claim 2 is characterized in that: The steps of wind network solution include: Enter the mine ventilation network parameter information; Perform wind resistance sorting, solve the minimum wind resistance tree, and determine the composition of independent circuits; Determine the characteristic curve of the fan; First, assign initial values ​​to the remaining tree edges, and then calculate the initial wind volume of each branch; Iterative calculation, calculate the air volume correction value of each circuit respectively, and perform air volume correction on all branches of the circuit; After each iteration, determine whether the accuracy requirement is met. If so, terminate the calculation; otherwise, return to continue the iteration. Output the calculated results of the ventilation network air volume.

4. The mine intelligent ventilation scheduling decision system based on wind network solution according to claim 3 is characterized in that: During the air network solution process, the calculation formula for the loop air volume correction value is as follows: ； Where: are the wind pressure expressed by the fan characteristic curve equation and the slope of the fan characteristic curve, respectively, and n represents the number of branches; is the air volume value of branch j; is the basic loop matrix; Indicates wind resistance; Indicates natural wind pressure.

5. The mine intelligent ventilation scheduling decision system based on wind network solution according to claim 3 is characterized in that: The calculation formula for air volume correction for all branches of the circuit is as follows: ； Where: are the air volume values ​​of branch j before and after correction, represents the correction value of loop k at the i-th iteration.

6. The mine intelligent ventilation scheduling decision system based on wind network solution according to claim 3 is characterized in that: After each iteration, determine whether the accuracy requirements are met, including: Determine whether the absolute value of the maximum value among all correction values ​​in a certain cycle is less than or equal to the set accuracy value, that is, it satisfies the following formula: ； Where EPS stands for precision, Indicates the maximum value among all correction values.

7. The mine intelligent ventilation scheduling decision system based on wind network solution according to claim 1 is characterized in that: Establish a wind network diagnosis expert database. The wind network anomalies in the database are divided into three categories: wind path, equipment sensor, and wind network structure. Each group has different anomaly types. Based on the topological structure of the underground tunnel, the wind network diagnosis is carried out, and an optimization strategy is given based on the wind network diagnosis expert database. According to the optimization strategy, the air flow in the mine ventilation area is optimized.

8. The mine intelligent ventilation scheduling decision system based on wind network solution according to claim 1 is characterized in that: The related equipment includes: main ventilator, local ventilator, damper and window.

Images