Underground engineering water leakage accident monitoring device and early warning method based on 5G communication technology

Abstract

The application provides an underground engineering water inrush accident monitoring device and early warning method based on 5G communication technology, and relates to the technical field of underground engineering water inrush accident monitoring and early warning. The device comprises an alarm, a multi-source information collection box, a water temperature and pressure sensor, a flowmeter, a 5G signal transmitter, a power distribution system, a water quality sensor and a power supply cable. The method realizes effective transmission of on-site water temperature, water pressure, water inflow and ion concentration monitoring signals, and solves the problems of complex wiring and easy damage in traditional wired transmission. The method uses the analytic hierarchy process to construct a water inrush accident risk assessment model, and embeds the risk assessment model into a water inrush accident hidden danger monitoring and intelligent analysis system, so that real-time analysis can be performed on underground engineering water inrush accident hidden danger information, and real-time display of monitoring index abnormality level and real-time alarm of water inrush accident risk level can be realized.

Description

Technical Field

[0001] This invention relates to the field of monitoring and early warning technology for water seepage accidents in underground engineering, and in particular to a monitoring device and early warning method for water seepage accidents in underground engineering based on 5G communication technology. Background Technology

[0002] With the continuous expansion of underground engineering construction (metal mines, coal mines, tunnel projects, etc.) and the increasing mining depth in my country, the frequency of various safety accidents is also rising, among which water inrush accidents are one of the major engineering risk accidents. Water inrush accidents are characterized by their suddenness and uncertainty. Furthermore, the incubation process of water inrush accidents is accompanied by changes in precursory information, often leading to a reactive approach of "construction, observation, and subsequent remediation." Therefore, there is an urgent need to develop real-time monitoring and disaster early warning systems for multi-source precursory information of water inrush accidents to ensure safe construction.

[0003] Existing technologies also include some patents that monitor and warn of water inrush accidents in underground engineering. For example, patent number CN115182784A is a combined sensor for early warning of mine water inrush disasters, which realizes the monitoring of parameters such as crack parameters, temperature, and humidity in the detection hole; patent number CN105179014A is a method and device for early warning of coal mine water inrush disasters, which realizes the monitoring of water temperature, water pressure, and water quality at the mining face and early warning of water inrush.

[0004] Most existing monitoring and early warning devices rely on wired signal transmission. Extensive wiring is susceptible to damage during on-site construction, leading to discontinuity in information monitoring and consequently affecting real-time detection of multi-source precursory information for water inrush accidents and early warning of multi-source disasters. Therefore, leveraging the advantages of 5G communication technology—high data transmission capacity, low latency, and high reliability—a regional Wi-Fi module can be embedded within the sensor to achieve effective transmission of multi-source monitoring signals on-site and synchronous early warning of water disasters between the site and the wellhead terminal. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to address the shortcomings of the prior art by providing an underground engineering water inrush accident monitoring device and early warning method based on 5G communication technology. This device monitors the water pressure, water temperature, water ion concentration and water inflow in rock fissures in real time, and combines 5G communication technology to realize synchronous early warning of water inrush disasters at the site and the well terminal, thereby solving the problem of discontinuous wired signal transmission in existing monitoring devices.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0007] On one hand, this invention provides a monitoring device for underground engineering water seepage accidents based on 5G communication technology, including an alarm, a multi-source information acquisition box, water temperature and pressure sensors, a flow meter, a 5G signal transmitter, a power distribution system, a water quality sensor, and power cables; the multi-source information acquisition box consists of an equipment protection box, an industrial touch screen all-in-one machine, and an acquisition instrument, with the industrial touch screen all-in-one machine and the acquisition instrument housed inside the equipment protection box; the industrial touch screen all-in-one machine integrates a water seepage accident hazard monitoring and intelligent analysis system for monitoring and intelligently analyzing water seepage accident hazards; the alarm is mounted on the equipment protection box and connected to the industrial touch screen all-in-one machine inside the equipment protection box for water seepage disaster alarm;

[0008] The water temperature and pressure sensor is used to collect water temperature and pressure, the flow meter is used to collect water flow rate, and the water quality sensor is used to collect ion concentration.

[0009] The water temperature and pressure sensors, flow meters, and water quality sensors transmit the collected monitoring values ​​to the acquisition device in the multi-source information acquisition box via a wireless network. The acquisition device converts the collected analog signals into current signals and transmits them to the water infiltration accident hazard monitoring and intelligent analysis system integrated in the industrial touch screen all-in-one machine for water infiltration accident hazard monitoring and intelligent analysis. When the monitoring indicators are abnormal, the alarm will sound a water infiltration disaster alarm.

[0010] The power distribution system is connected to the AC power supply via power cables, converting the power supply voltage at the underground engineering site to 12V DC power to power the multi-source information acquisition box.

[0011] The 5G signal generator transmits the monitoring data acquired by the multi-source information acquisition box to the wellhead terminal system in real time, enabling synchronous water inrush disaster early warning between the underground engineering site and the wellhead terminal.

[0012] On the other hand, the present invention also provides a method for early warning of water inrush accidents in underground engineering based on 5G communication technology, comprising the following steps:

[0013] Step S1: Drill holes in the sidewall of the tunnel to install water temperature and pressure sensors;

[0014] Step S2: Drill holes at the water inflow points on the sidewall of the tunnel and install flow meters;

[0015] Step S3: Install a water quality sensor at the downstream end of the flow meter's built-in water guide pipe;

[0016] Step S4: Based on the installation locations of the water temperature and pressure sensors, flow meters, and water quality sensors, install a multi-source information acquisition box, power distribution system, and alarm on the side wall of the tunnel;

[0017] Step S5: The water permeability accident hazard monitoring and intelligent analysis system integrated in the industrial touch screen all-in-one machine conducts risk assessment based on the water permeability accident risk assessment model. The water permeability accident hazard monitoring and intelligent analysis system sets the warning threshold of the risk assessment indicators. If the value of one of the indicators exceeds the warning threshold, the industrial touch screen all-in-one machine triggers the alarm to immediately issue a water permeability disaster warning.

[0018] Step S6: The 5G signal generator transmits the monitoring data obtained by the water inrush accident hazard monitoring and intelligent analysis system to the well terminal system in real time, realizing synchronous water inrush disaster early warning between the site and the well terminal.

[0019] The establishment of the water inrush accident risk assessment model in step S5 includes the following steps:

[0020] Step S51: Establish a risk assessment index system for water inrush accidents: Select water inflow, ion concentration, water pressure, and water temperature as monitoring indicators in the risk assessment index system for water inrush accidents. At the same time, considering the influence of engineering geological conditions on water inrush accidents, select permeability coefficient and water abundance as geological condition indicators in the risk assessment index system. Meanwhile, classify the abnormality levels of the evaluation indicators into: Level IV, Level III, Level II, and Level I, where Level IV is no risk, Level III is low risk, Level II is medium risk, and Level I is high risk.

[0021] Step S52: Establish a water inflow anomaly discrimination model based on a BP neural network to determine the water inflow anomaly criteria; classify water inflow accidents into three levels according to the consequences of the accidents: Level 3, Level 2, and Level 1; establish a water inflow anomaly discrimination model based on a BP neural network; the initial model parameters of the BP neural network model are: input layer nodes are annual average rainfall, water inflow accident level value, water abundance, and burial depth; the number of hidden layer nodes is five, with two hidden layers in total, and the activation function is the Sigmoid function; the output node is the instantaneous growth rate k of the water inflow, and the transfer function of the output layer is the Purelin function; after multiple training sessions, the prediction results obtained from the training are compared with the actual k values ​​in the prediction set to finally determine the optimal water inflow anomaly discrimination model; input the annual average rainfall, water inflow accident level value, water abundance, and burial depth of the underground engineering site into the optimal water inflow anomaly discrimination model, and the model outputs three instantaneous growth rates k of the water inflow. a k b k c k a <k b <k c If the instantaneous growth rate of the water inflow at the current moment is k1 < k a The abnormal water inflow index is Level IV; k a ≤k1<k b The abnormal water inflow index is Level III; k b ≤k1<k cThe abnormal water inflow index is Level II; if k1≥c, the abnormal water inflow index is Level I.

[0022] Step S53: Determine the water temperature anomaly criteria based on the real-time monitored water temperature and the anomaly threshold; select the average water temperature T over a set time period under normal water inflow conditions. s As a threshold for abnormal water temperature, the water temperature T is monitored in real time. n With the abnormal threshold T s By comparison, the water temperature anomaly index value TI is obtained, TI = |T n -T s |;When TI≤0.3, the water temperature anomaly index is Level IV; 0.3<TI≤0.5, the water temperature anomaly index is Level III; 0.5<TI≤1.0, the water temperature anomaly index is Level II; TI>1.0, the water temperature anomaly index is Level I;

[0023] Step S54: Determine the water pressure anomaly criterion based on the current water pressure value and the critical water pressure that the surrounding rock impermeable layer can withstand; set the critical water pressure P that the surrounding rock impermeable layer can withstand. cr =Pl, where P is the critical water pressure that a unit thickness of rock mass can withstand, and l is the thickness of the aquitard; when the current water pressure value P 测 <0.85P cr And the current water pressure value P 测 The difference in water pressure from the previous moment, ΔP < 0, indicates a water pressure anomaly level IV; P 测 <0.85P cr And ΔP≥0, the water pressure anomaly index is Level III; 0.85P cr ≤P 测 <P cr And ΔP < 0, the water pressure anomaly index is Level II; 0.85P cr ≤P 测 <P cr And ΔP≥0, the water pressure anomaly index is Level I;

[0024] Step S55: Determine the anomaly criteria for chloride ion concentration in the water based on the average chloride ion concentration in the mine water and the current chloride ion concentration; let σ be the standard deviation of ion concentration, select the average chloride ion concentration μ of the mine water within a set time period under stable conditions, and let CI be the absolute value of the change in ion concentration, i.e., CI = |C 测 -μ|, where C 测 The current ion concentration is σ. When CI < σ, the ion concentration anomaly index is Level IV; when σ ≤ CI < 2σ, the ion concentration anomaly index is Level III; when 2σ ≤ CI < 3σ, the ion concentration anomaly index is Level II; when CI ≥ 3σ, the ion concentration anomaly index is Level I.

[0025] Step S56: Determine the permeability coefficient anomaly criterion; when permeability coefficient K < 10 -5 The permeability coefficient anomaly index is level IV; 10 -5 ≤K<10 -4 The permeability coefficient anomaly index is Level III; 10 -4 ≤K<10 -2 The permeability coefficient anomaly index is Level II; K≥10 -2 The permeability coefficient anomaly index is Level I.

[0026] Step S57: Determine the criteria for water abundance anomaly; when water abundance q < 0.1, the water abundance index is level IV; 0.1 ≤ q < 1.0, the water abundance index is level III; 1.0 ≤ q < 5.0, the water abundance index is level II; q ≥ 5.0, the water abundance index is level I.

[0027] Step S58: Construct a risk assessment model for water ingress accidents using the analytic hierarchy process (AHP) and conduct a risk assessment of water ingress accidents.

[0028] The risk assessment index system for water inrush accidents is divided into two main categories: monitoring indicators and geological condition indicators. Monitoring indicators include inflow rate, water temperature, water pressure, and ion concentration, while geological condition indicators include permeability coefficient and water-bearing capacity. After comprehensively analyzing the influencing factors of water inrush accidents, based on the sensitivity of each indicator and the magnitude of change during the water inrush disaster process, water pressure and inflow rate are classified as first-level indicators, ion concentration and water temperature as second-level indicators, and permeability coefficient and water-bearing capacity as third-level indicators, with the levels decreasing progressively. Then, the importance of the indicators is compared, a discrimination matrix is ​​established, consistency checks are performed, and the final weights are determined. At the same time, the weights of the lowest-level indicators relative to the highest-level indicators are calculated to establish a risk assessment system weight table for water inrush accident risk assessment.

[0029] The beneficial effects of adopting the above technical solution are as follows: The underground engineering water inrush accident monitoring device and method based on 5G communication technology provided by this invention realizes the effective transmission of monitoring signals for on-site water temperature, water pressure, water inflow, and ion concentration, solving the problems of complex wiring and susceptibility to damage in traditional wired transmission. A water inrush accident risk assessment model is constructed using the Analytic Hierarchy Process (AHP), and this risk assessment model is embedded into a water inrush accident hazard monitoring and intelligent analysis system. This allows for real-time analysis of underground engineering water inrush accident hazard information, real-time display of abnormal levels of monitoring indicators, and real-time alarm of water inrush accident risk levels. Based on the advantages of 5G communication technology, such as large data transmission capacity, low latency, and high reliability, synchronous early warning of water inrush disasters is achieved between the on-site and surface terminals. Attached Figure Description

[0030] Figure 1 A schematic diagram of the installation of an underground engineering water inrush accident monitoring device based on 5G communication technology along the direction of the tunnel, provided in an embodiment of the present invention;

[0031] Figure 2 A schematic diagram of the installation of an underground engineering water inrush accident monitoring device based on 5G communication technology along the cross-sectional direction of the tunnel, provided for an embodiment of the present invention;

[0032] Figure 3 This is a structural block diagram of a water infiltration accident risk assessment model provided in an embodiment of the present invention;

[0033] Figure 4 This is a functional module design block diagram of the water permeability accident hazard monitoring and intelligent analysis system provided in an embodiment of the present invention;

[0034] Figure 5 This is a diagram of the real-time monitoring module interface of the water permeability accident hazard monitoring and intelligent analysis system provided in an embodiment of the present invention;

[0035] Figure 6 This is a diagram of the risk assessment module interface of the water permeability accident hazard monitoring and intelligent analysis system provided in an embodiment of the present invention.

[0036] In the diagram: 1. Alarm; 2. Multi-source information acquisition box; 3. Water temperature and pressure sensor; 4. Flow meter; 5. 5G signal transmitter; 6. Power distribution system; 7. Water pipe; 8. Water quality sensor; 9. Power supply cable; A. Well terminal; B. Water inrush point. Detailed Implementation

[0037] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0038] In this embodiment, a monitoring device for underground engineering water inrush accidents based on 5G communication technology, such as... Figure 1 , 2 As shown, the system includes an alarm 1, a multi-source information acquisition box 2, a water temperature and pressure sensor 3, a flow meter 4, a 5G signal transmitter 5, a power distribution system 6, a water quality sensor 8, and a power supply cable 9. The multi-source information acquisition box 2 consists of an equipment protection box, an industrial touch screen all-in-one machine, and an acquisition instrument. The industrial touch screen all-in-one machine and the acquisition instrument are housed inside the equipment protection box. The industrial touch screen all-in-one machine integrates a water infiltration accident hazard monitoring and intelligent analysis system for monitoring and intelligently analyzing water infiltration accident hazards. The alarm 1 is mounted on the equipment protection box and connected to the industrial touch screen all-in-one machine inside the equipment protection box for water infiltration disaster alarm.

[0039] The water temperature and pressure sensor 3 is used to collect water temperature and pressure, the flow meter 4 is used to collect water flow rate, and the water quality sensor 8 is used to collect ion concentration.

[0040] The water temperature and pressure sensor 3, flow meter 4, and water quality sensor 8 transmit the collected monitoring values ​​to the acquisition instrument in the multi-source information acquisition box 2 via a wireless network. The acquisition instrument converts the collected analog signals into current signals and transmits them to the water infiltration accident hazard monitoring and intelligent analysis system integrated in the industrial touch screen all-in-one machine for water infiltration accident hazard monitoring and intelligent analysis. When the monitoring indicators are abnormal, the alarm 1 will issue a water infiltration disaster alarm.

[0041] The power distribution system 6 is connected to the AC power supply via the power supply cable 9, and converts the power supply voltage at the underground engineering site to 12V DC power to power the multi-source information acquisition box 2.

[0042] The 5G signal generator 5 transmits the monitoring data acquired by the multi-source information acquisition box 2 to the surface terminal system A in real time, realizing synchronous water inrush disaster early warning between the underground engineering site and the surface terminal.

[0043] In this embodiment, a method for early warning of water inrush accidents in underground engineering based on 5G communication technology includes the following steps:

[0044] Step S1: Drill holes in the sidewall of the tunnel to install the water temperature and pressure sensor. First, use an impact drill to drill holes in the sidewall of the tunnel. The diameter of the hole should be larger than the diameter of the pressure guide tube of the water temperature and pressure sensor, preferably about 1 cm larger. The drilling direction should be horizontal, and the hole depth can be determined according to the water flow during the drilling process (generally not exceeding 2m). Then, clean the inside of the hole with water to ensure that the inside of the hole is clean. Next, put the pressure guide tube of the water temperature and pressure sensor into the hole, with the sensor's test connector close to the sandproof mesh at the bottom of the hole. Next, inject waterproof mortar into the gap between the pressure guide tube and the hole. Finally, fix the water temperature and pressure sensor to the sidewall of the tunnel using the mounting plate on the housing of the water temperature and pressure sensor and fixing bolts.

[0045] Step S2: Drill a hole at the water inflow point on the sidewall of the tunnel and install the flow meter 4; First, use an impact drill to drill a hole at the water inflow point B on the sidewall of the tunnel. The diameter of the hole needs to be determined according to the diameter of the water guide pipe 7 that comes with the flow meter 4. The drilling direction is horizontal; then, clean the inside of the hole with water to ensure that the inside of the hole is clean; next, put one end of the water guide pipe 7 into the hole and connect the other end to the flow meter 4; finally, fix the flow meter 4 and the water guide pipe 7 to the rock wall with fixing clips and expansion bolts.

[0046] Step S3: Install water quality sensor 8 at the downstream end of the water guide pipe 7 of the flow meter 4; install water quality sensor 8 at the downstream end of the water guide pipe 7, immerse the probe of water quality sensor 8 into the flowing water, and fix it with a fixing bracket.

[0047] Step S4: Based on the installation locations of the water temperature and pressure sensor 3, flow meter 4, and water quality sensor 8, install the multi-source information acquisition box 2, power distribution system 6, and alarm 1 on the side wall of the tunnel. First, determine the installation locations of the multi-source information acquisition box 2, power distribution system 6, and alarm 1 based on the installation locations of the water temperature and pressure sensor 3, flow meter 4, and water quality sensor 8. Then, fix the multi-source information acquisition box 2, power distribution system 6, and alarm 1 to the side wall of the tunnel using expansion bolts. Finally, the on-site construction personnel connect AC power to the power distribution system 6 through the power supply cable 9.

[0048] Step S5: The water permeability accident hazard monitoring and intelligent analysis system integrated in the industrial touch screen all-in-one machine conducts risk assessment based on the water permeability accident risk assessment model. The water permeability accident hazard monitoring and intelligent analysis system sets the warning threshold of the risk assessment indicators. If the value of one of the indicators exceeds the warning threshold, the industrial touch screen all-in-one machine triggers alarm 1 to immediately issue a water permeability disaster warning.

[0049] Step S6: The 5G signal generator 5 transmits the monitoring data obtained by the water inrush accident hazard monitoring and intelligent analysis system to the well terminal system A in real time, so as to realize synchronous water inrush disaster early warning between the site and the well terminal A.

[0050] In this embodiment, the establishment of the water inrush accident risk assessment model in step S5 includes the following steps:

[0051] Step S51: Establish a risk assessment index system for water inrush accidents: Underground engineering projects are located in areas with complex geological conditions, and different geological conditions have varying impacts on water inrush accidents. If the groundwater is abundant and the surrounding rock stability is poor, the probability of a water inrush accident increases. Water inflow, ion concentration, water pressure, and water temperature are selected as monitoring indicators in the risk assessment index system for water inrush accidents. Considering the impact of engineering geological conditions on water inrush accidents, permeability coefficient and water abundance are selected as geological condition indicators in the risk assessment index system. Furthermore, the anomaly levels of the evaluation indicators are divided into four levels: Level IV, Level III, Level II, and Level I, where Level IV represents no danger, Level III represents low danger, Level II represents moderate danger, and Level I represents high danger.

[0052] Step S52: Determine the criteria for abnormal water inflow: Statistically analyze domestic and international cases of water inrush and classify water inrush accidents into three levels based on their consequences: Level 3, Level 2, and Level 1; Establish a water inflow anomaly discrimination model based on a BP neural network; The initial model parameters of the BP neural network model are: input layer nodes are annual average rainfall, water inrush accident level value, water abundance, and burial depth; the number of hidden layer nodes is five, with two hidden layers, and the activation function is the Sigmoid function; the output node is the instantaneous growth rate k of the water inflow, and the output layer transfer function is the Purelin function; To ensure the accuracy and scientific nature of the neural network model, the case samples are divided into training set, validation set, and test set. Through training, the predicted results are compared with the actual k value to finally determine a reasonable prediction model;

[0053] Step S53: Determine the criteria for abnormal water temperature: Under normal circumstances, the water temperature in a mine's normal inflow is relatively stable, and sudden rises and falls are unlikely. Select the average water temperature T over one month under normal inflow conditions. s As a threshold for abnormal water temperature, the water temperature T is monitored in real time. n With the abnormal threshold T s By comparison, the water temperature anomaly index value TI is obtained, TI = |T n -T s |;When TI≤0.3, the water temperature anomaly index is Level IV; 0.3<TI≤0.5, the water temperature anomaly index is Level III; 0.5<TI≤1.0, the water temperature anomaly index is Level II; TI>1.0, the water temperature anomaly index is Level I;

[0054] Step S54: Determine the water pressure anomaly criterion: During the construction of underground engineering projects, as development progresses, water from the surrounding rock fissures will gush out from the rock wall. Generally, the higher the water pressure, the more significant the deformation and damage of the surrounding rock. With increasing water pressure, the likelihood of a water inrush accident increases. Different strata lithologies have different critical water pressures that the aquitard can withstand. Set the critical water pressure P that the surrounding rock aquitard can withstand. cr =Pl, where P is the critical water pressure that a unit thickness of rock mass can withstand, and l is the thickness of the aquitard; when the current water pressure value P 测 <0.85P cr And the current water pressure value P 测 The difference in water pressure from the previous moment, ΔP < 0, indicates a water pressure anomaly level IV; P 测 <0.85P cr And ΔP≥0, the water pressure anomaly index is Level III; 0.85P cr ≤P 测 <P cr And ΔP < 0, the water pressure anomaly index is Level II; 0.85P cr ≤P 测 <Pcr And ΔP≥0, the water pressure anomaly index is Level I;

[0055] Step S55: Determine the criteria for abnormal chloride ion concentration in water: When a water inrush accident occurs in an underground engineering project, the outflow rate at the outlet will increase, and water from other aquifers will gush outward through the water inrush channel. Different aquifers have different water chemical properties, therefore the ion concentration of the water will also change significantly. Under normal water inrush conditions in the mine, the monitoring curve of chloride ion concentration in the water tends to stabilize, and the distribution pattern of the ion concentration values ​​is similar to a normal distribution curve. In mathematical statistics, if a random variable follows a normal distribution, the probability of occurrence within ±σ is 68.3%, and the probability of occurrence within ±3σ is close to 1. Let σ be the standard deviation of ion concentration, select the average ion concentration μ of the mine under stable conditions for one month, and let CI be the absolute value of the change in ion concentration, i.e., CI = |C 测 -μ|, where C 测 The current ion concentration is σ. When CI < σ, the ion concentration anomaly index is Level IV; when σ ≤ CI < 2σ, the ion concentration anomaly index is Level III; when 2σ ≤ CI < 3σ, the ion concentration anomaly index is Level II; when CI ≥ 3σ, the ion concentration anomaly index is Level I.

[0056] Step S56: Determine the permeability coefficient anomaly criterion: when permeability coefficient K < 10 -5 The permeability coefficient anomaly index is level IV; 10 -5 ≤K<10 -4 The permeability coefficient anomaly index is Level III; 10 -4 ≤K<10 -2 The permeability coefficient anomaly index is Level II; K≥10 -2 The permeability coefficient anomaly index is Level I.

[0057] Step S57: Determine the criteria for water abundance anomalies: when water abundance q < 0.1, the water abundance index is level IV; 0.1 ≤ q < 1.0, the water abundance index is level III; 1.0 ≤ q < 5.0, the water abundance index is level II; q ≥ 5.0, the water abundance index is level I.

[0058] Step S58: Construct a risk assessment model for water inrush accidents, such as... Figure 3As shown, the core concept of the Analytic Hierarchy Process (AHP) is to decompose a complex problem into multiple factors, identify the dominant factor, and then further subdivide these factors at each level to construct a complete hierarchical structure. When assessing the importance of each factor, the relative importance is determined by comparing factors pairwise within the same level, ranking the weights of these factors, and then passing this ranking upwards to ultimately determine the weight of each factor relative to the objective. The main process includes constructing a hierarchical model, comparing the importance of indicators, establishing a discrimination matrix, performing consistency checks, and determining the final weights.

[0059] The risk assessment index system for water inrush accidents is divided into two main categories: monitoring indicators and geological condition indicators. Monitoring indicators include inflow rate, water temperature, water pressure, and ion concentration, while geological condition indicators include permeability coefficient and water-bearing capacity. After comprehensively analyzing the influencing factors of water inrush accidents, based on the sensitivity of each indicator and the magnitude of change during the water inrush disaster process, water pressure and inflow rate are classified as first-level indicators, ion concentration and water temperature as second-level indicators, and permeability coefficient and water-bearing capacity as third-level indicators, with the levels decreasing progressively. Then, the importance of the indicators is compared, a discrimination matrix is ​​established, consistency checks are performed, and the final weights are determined.

[0060] In this embodiment, after weight calculation and passing the random consistency test, it is determined that the established matrix and the determined weights are reasonable. Simultaneously, the weights of the lowest-level indicators relative to the highest-level indicators are calculated, and a weight table for the risk assessment system is established, as shown in Table 1.

[0061] Table 1 Weighting Table of Risk Assessment Indicator System

[0062]

[0063]

[0064] In this embodiment, based on the constructed water infiltration accident risk assessment model, a water infiltration accident hazard monitoring and intelligent analysis system software was developed, such as... Figure 4-6 As shown. The main functional modules include: user login, real-time monitoring, equipment management, historical curve display, historical data query, and risk assessment. This software enables real-time monitoring and risk level alarms for early warning information of water inrush accidents, such as water pressure, water temperature, water quality, and inflow rate.

[0065] (1) Login Module

[0066] After launching the software, it automatically enters the login module. Enter your username and password, then click "Login" to access the main software interface. This module is designed to prevent unauthorized logins, which could lead to system damage and data loss.

[0067] (2) Real-time monitoring module

[0068] As the main interface of the software, this module can display the precursor information and water inrush risk level collected by each sensor in real time. When the value collected by the sensor reaches the alarm threshold, the data panel will display the corresponding abnormality level color. When the user needs to view the real-time monitoring curve, they can click the box in the upper left corner of the data panel, and then the real-time monitoring curve will be displayed on the right side of the interface.

[0069] (3) Historical Curve Module

[0070] Users can filter by channel number, sensor type, alarm level, and start and end time. After selection, click "Search", and the interface will display historical curves that meet the search criteria. Click "Export" to export the historical curves.

[0071] (4) Historical Data Module

[0072] Select the start and end dates of the historical data you wish to query, and click "Query." The interface will display a list of historical data. The data list includes the time, monitoring indicators, geological condition indicators and their corresponding anomaly level colors, water inrush accident risk values ​​and their corresponding risk level colors, etc. When you need to export the historical data, click "Export" to export the historical data file stored in ".CSV" format.

[0073] (5) Equipment Management Module

[0074] The interface displays a list including sensor types, locations, anomaly thresholds, discrimination parameters, and conversion coefficients for all channels. When a user needs to modify sensor information, double-clicking the sensor's "channel number" will bring up a change list on the right side of the interface. Users can modify the sensor type, location, anomaly threshold, discrimination parameters, and conversion coefficients in this list.

[0075] (6) Risk Assessment Module

[0076] The left side of the interface allows you to set the abnormality classification values ​​for geological condition indicators in the water infiltration accident assessment. Enter the corresponding classification values ​​in the three text boxes to the right of the permeability coefficient K and water abundance q. The right side of the interface allows you to set the weights for the water infiltration accident risk assessment indicators. Enter the weight values ​​for different indicators in the text boxes below the weights, and click "Modify Weights" to complete the weight settings for the risk assessment indicators.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope defined by the claims of the present invention.

Claims

1. A method for early warning of water inrush accidents in underground engineering based on 5G communication technology, implemented using an early warning device for water inrush accidents in underground engineering based on 5G communication technology. The device includes an alarm, a multi-source information acquisition box, water temperature and pressure sensors, a flow meter, a 5G signal transmitter, a power distribution system, a water quality sensor, and power cables. The multi-source information acquisition box consists of an equipment protection box, an industrial touch screen all-in-one machine, and an acquisition instrument. The industrial touch screen all-in-one machine and the acquisition instrument are housed within the equipment protection box. The industrial touch screen all-in-one machine integrates a water inrush accident hazard monitoring and intelligent analysis system for monitoring and intelligently analyzing water inrush accident hazards. The alarm is mounted on the equipment protection box and connected to the industrial touch screen all-in-one machine inside the equipment protection box for alarming water inrush disasters. The water temperature and pressure sensor is used to collect water temperature and pressure, the flow meter is used to collect water flow rate, and the water quality sensor is used to collect ion concentration. The water temperature and pressure sensors, flow meters, and water quality sensors transmit the collected monitoring values ​​to the acquisition device in the multi-source information acquisition box via a wireless network. The acquisition device converts the collected analog signals into current signals and transmits them to the water infiltration accident hazard monitoring and intelligent analysis system integrated in the industrial touch screen all-in-one machine for water infiltration accident hazard monitoring and intelligent analysis. When the monitoring indicators are abnormal, the alarm will sound a water infiltration disaster alarm. The power distribution system is connected to the AC power supply via power cables, converting the power supply voltage at the underground engineering site to 12V DC power to power the multi-source information acquisition box. The 5G signal generator transmits the monitoring data acquired by the multi-source information acquisition box to the well terminal system in real time, realizing synchronous water inrush disaster early warning between the underground engineering site and the well terminal; Its features are: The method includes the following steps: Step S1: Drill holes in the sidewall of the tunnel to install water temperature and pressure sensors; Step S2: Drill holes at the water inflow points on the sidewall of the tunnel and install flow meters; Step S3: Install a water quality sensor at the downstream end of the flow meter's built-in water guide pipe; Step S4: Based on the installation locations of the water temperature and pressure sensors, flow meters, and water quality sensors, install a multi-source information acquisition box, power distribution system, and alarm on the side wall of the tunnel; Step S5: The water permeability accident hazard monitoring and intelligent analysis system integrated in the industrial touch screen all-in-one machine conducts risk assessment based on the water permeability accident risk assessment model. The water permeability accident hazard monitoring and intelligent analysis system sets the warning threshold of the risk assessment indicators. If the value of one of the indicators exceeds the warning threshold, the industrial touch screen all-in-one machine triggers the alarm to immediately issue a water permeability disaster warning. The aforementioned risk assessment model for water ingress accidents is established based on the following steps: Step S51: Establish a risk assessment index system for water inrush accidents: Select water inflow, ion concentration, water pressure, and water temperature as monitoring indicators in the risk assessment index system for water inrush accidents. At the same time, considering the influence of engineering geological conditions on water inrush accidents, select permeability coefficient and water abundance as geological condition indicators in the risk assessment index system. Meanwhile, classify the abnormality levels of the evaluation indicators into: Level IV, Level III, Level II, and Level I, where Level IV is no risk, Level III is low risk, Level II is medium risk, and Level I is high risk. Step S52: Establish a water inflow anomaly discrimination model based on BP neural network to determine the water inflow anomaly criteria; Step S53: Determine the water temperature anomaly criteria based on the real-time monitored water temperature and the anomaly threshold; Step S54: Determine the water pressure anomaly criterion based on the current water pressure value and the critical water pressure that the surrounding rock impermeable layer can withstand; Step S55: Determine the criteria for abnormal chloride ion concentration in the water based on the average chloride ion concentration in the mine water and the current chloride ion concentration. Step S56: Determine the permeability coefficient anomaly criteria; Step S57: Determine the criteria for water-rich anomalies; Step S58: Construct a risk assessment model for water ingress accidents using the analytic hierarchy process (AHP) and conduct a risk assessment of water ingress accidents. The risk assessment index system for water inrush accidents is divided into two main categories: monitoring indicators and geological condition indicators. Monitoring indicators include inflow rate, water temperature, water pressure, and ion concentration, while geological condition indicators include permeability coefficient and water-bearing capacity. After comprehensively analyzing the influencing factors of water inrush accidents, based on the sensitivity of each indicator and its variation during the water inrush disaster process, water pressure and inflow rate are classified as the first-level indicators, ion concentration and water temperature as the second-level indicators, and permeability coefficient and water-bearing capacity as the third-level indicators, with the levels decreasing progressively. Then, the importance of the indicators is compared, a discrimination matrix is ​​established, consistency checks are performed, and the final weights are determined. At the same time, the weights of the lowest-level indicators relative to the highest-level indicators are calculated to establish a risk assessment system weight table for water inrush accident risk assessment. Step S6: The 5G signal generator transmits the monitoring data obtained by the water inrush accident hazard monitoring and intelligent analysis system to the well terminal system in real time, realizing synchronous water inrush disaster early warning between the site and the well terminal.

2. The method for early warning of water inrush accidents in underground engineering based on 5G communication technology according to claim 1, characterized in that: The specific method for determining the criteria for water inflow anomaly based on the BP neural network in step S52 is as follows: Based on the consequences of water inrush accidents, water inrush accidents are classified into three levels: Level 3, Level 2, and Level 1; an anomaly discrimination model for inrush volume is established based on a BP neural network; The initial parameters of the BP neural network model are as follows: input layer nodes are annual average rainfall, water inrush accident level, water abundance, and burial depth; there are five hidden layer nodes (two hidden layers in total), and the activation function is the Sigmoid function; the output node is the instantaneous growth rate k of the inflow, and the output layer transfer function is the Purelin function. After multiple training iterations, the predicted results are compared with the actual k values ​​in the prediction set to determine the optimal inflow anomaly discrimination model. The optimal inflow anomaly discrimination model is then input with the annual average rainfall, water inrush accident level, water abundance, and burial depth of the underground engineering site. The model outputs three instantaneous growth rates k of the inflow. a k b k c k a <k b <k c If the instantaneous growth rate of the water inflow at the current moment is k1 < k a The abnormal water inflow index is Level IV; k a ≤k1<k b The abnormal water inflow index is Level III; k b ≤k1<k c If the water inflow anomaly index is Level II, then the water inflow anomaly index is Level I; if k1≥c, then the water inflow anomaly index is Level I.

3. The method for early warning of water inrush accidents in underground engineering based on 5G communication technology according to claim 1, characterized in that: The specific method for determining the water temperature anomaly criterion based on the real-time monitored water temperature and the anomaly threshold in step S53 is as follows: Select the average water temperature T over a set time period under normal water inflow conditions. s As a threshold for abnormal water temperature, the water temperature T is monitored in real time. n With the abnormal threshold T s By comparison, the water temperature anomaly index value TI is obtained, TI=|T n -T s When TI ≤ 0.3, the water temperature anomaly index is Level IV; If 0.3 < TI ≤ 0.5, the water temperature anomaly index is Level III; If 0.5 < TI ≤ 1.0, the water temperature anomaly index is Level II; if TI > 1.0, the water temperature anomaly index is Level I.

4. The method for early warning of water inrush accidents in underground engineering based on 5G communication technology according to claim 1, characterized in that: The specific method for determining the water pressure anomaly criterion in step S54 based on the current water pressure value and the critical water pressure that the surrounding rock impermeable layer can withstand is as follows: Set the critical water pressure P that the surrounding rock impermeable layer can withstand. cr =Pl, where P is the critical water pressure that a unit thickness of rock mass can withstand, and l is the thickness of the aquitard; when the current water pressure value P 测 <0.85P cr And the current water pressure value P 测 The difference in water pressure from the previous moment, ΔP < 0, indicates a water pressure anomaly level IV; P 测 <0.85P cr And ΔP≥0, the water pressure anomaly index is Level III; 0.85P cr ≤P 测 <P cr And ΔP < 0, the water pressure anomaly index is Level II; 0.85P cr ≤P 测 <P cr And ΔP≥0, the water pressure anomaly index is Level I.

5. The method for early warning of water inrush accidents in underground engineering based on 5G communication technology according to claim 1, characterized in that: The specific method for determining the abnormal chloride ion concentration criteria in water based on the average chloride ion concentration in the mine water and the current chloride ion concentration in step S55 is as follows: Let σ be the standard deviation of ion concentration, and select the average chloride ion concentration μ of the mine under stable conditions over a set time period. Let CI be the absolute value of the change in ion concentration, i.e., CI = |C 测 -μ|, where C 测 σ represents the current ion concentration; when CI < σ, the ion concentration anomaly index is Level IV; when σ ≤ CI < 2σ, the ion concentration anomaly index is Level III; when 2σ ≤ CI < 3σ, the ion concentration anomaly index is Level II; when CI ≥ 3σ, the ion concentration anomaly index is Level I.

6. The method for early warning of water inrush accidents in underground engineering based on 5G communication technology according to claim 1, characterized in that: The permeability coefficient anomaly criterion determined in step S56 is as follows: When the permeability coefficient K < 10 -5 The permeability coefficient anomaly index is level IV; 10 -5 ≤K<10 -4 The permeability coefficient anomaly index is Level III; 10 -4 ≤K<10 -2 The permeability coefficient anomaly index is Level II; K≥10 -2 The permeability coefficient anomaly index is Level I.

7. A method for early warning of water inrush accidents in underground engineering based on 5G communication technology according to claim 6, characterized in that: The water-rich anomaly criterion determined in step S57 is as follows: When the water abundance q < 0.1, the water abundance index is level IV; when 0.1 ≤ q < 1.0, the water abundance index is level III; when 1.0 ≤ q < 5.0, the water abundance index is level II; when q ≥ 5.0, the water abundance index is level I.

Images