Gold mine ultrahigh confined water burst disaster-caused emergency response system based on intelligent perception and automatic decision

Abstract

The invention relates to the technical field of gold mine safety emergency response, in particular to a gold mine ultrahigh confined water burst disaster-caused emergency response system based on intelligent sensing and automatic decision making. Comprising an intelligent sensing module, an automatic decision-making module and an emergency response module. And the intelligent sensing module adopts a multi-sensor fusion network and a wireless sensor technology to monitor related data of confined water in real time and ensure stable transmission of the data. And the automatic decision-making module establishes a risk assessment model through data fusion and a random forest algorithm, and automatically generates an emergency decision-making scheme. The emergency response module utilizes an early warning program to remotely control emergency equipment, a triangulation positioning algorithm and communication equipment so as to help personnel to evacuate safely and rapidly. According to the method, disasters caused by gushing of the ultrahigh confined water in the gold mine can be effectively prevented and coped with, the emergency response capacity is improved, and personnel safety and smooth production are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of gold mine safety emergency response, and in particular to a gold mine ultra-high pressure water inrush disaster emergency response system based on intelligent perception and automated decision-making. Background Art

[0002] At present, in the process of gold mining, the sudden outburst of ultra-high pressure water is a serious safety hazard. As the depth of gold mining increases, the pressure of the pressurized water also increases. Once a sudden outburst occurs, it may cause serious consequences such as casualties, equipment damage and mine flooding. The existing emergency response system mainly relies on manual monitoring and experience judgment, and there are problems such as untimely warning and inaccurate decision-making, which makes it difficult to effectively deal with the risk of ultra-high pressure water inrush.

[0003] In recent years, with the continuous development of science and technology, intelligent perception and automated decision-making technologies have been gradually applied to various fields. In the field of gold mine safety, the intelligent perception module is used to monitor the relevant parameters of pressurized water in real time, the automated decision-making module is used to conduct risk assessment and decision-making, and finally the emergency response module is used to implement corresponding measures to achieve effective prevention and emergency response to disasters caused by super-high pressurized water inrush in gold mines. Summary of the invention

[0004] In view of the above-mentioned technical problems of untimely warning and inaccurate decision-making, the present invention proposes a method which is simple and easy to operate to achieve effective prevention and emergency response to disasters caused by ultra-high pressure water inrush in gold mines.

[0005] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is that the system includes an intelligent perception module, an automated decision-making module and an emergency response module; the intelligent perception module includes a multi-sensor fusion network, and pressure sensors, water level sensors, water flow velocity sensors, temperature sensors, and high-precision displacement sensors are arranged in the gold mining area and surrounding key positions, and wireless sensor technology is constructed to ensure that the collected sensor data can reach the decision-making system quickly and stably; the automated decision-making module includes processing data using data fusion technology, establishing a risk assessment model using a random forest algorithm, using historical data for training, and automatically generating emergency decision-making plans based on the results of risk assessment and preset emergency response strategies, and continuously simulating and verifying to improve the emergency response capability of the system; the emergency response module includes an early warning program alarm, and the emergency equipment is remotely controlled through the automated decision-making module, and triangulation positioning algorithms and communication equipment are used to help personnel evacuate safely and quickly.

[0006] Preferably, in the intelligent sensing module, pressure sensors, water level sensors, and water flow velocity sensors are used to monitor the pressure, water level changes, and water flow velocity of pressurized water in real time. Temperature sensors are used to monitor changes in ambient temperature. Abnormal changes in water temperature may also indicate the risk of pressurized water inrush. High-precision displacement sensors are used to monitor the displacement of tunnel walls and supporting structures, so as to promptly detect deformations that may be caused by pressurized water pressure.

[0007] Preferably, the intelligent sensing module adopts a low-power design when constructing the wireless sensor technology to extend the service life of the sensor, and improves the reliability and coverage of the network through self-organizing network and routing optimization technology.

[0008] Preferably, the specific operation of the route optimization is:

[0009] Step 1: Evaluate the status of each link in real time

[0010] Step 2: Use the weighted shortest path algorithm to calculate the optimal path based on the link status Where D(i,k) represents the known minimum weight of the shortest path from node i to node k, ω(k,j) is the edge weight from node k to j, and N(i) represents the set of nodes directly adjacent to node i;

[0011] Step 3: Introduce multi-path routing and use the following formula to distribute traffic and improve network redundancy and reliability. Among them, R i is the flow ratio allocated to path i, Q i is the quality factor of path i, represents the sum of the quality factors of all available paths;

[0012] Step 4: Finally, by monitoring the congestion status of each path, the traffic is dispersed to the paths with lighter loads to prevent a single path from being overloaded.

[0013] Preferably, the automated decision module uses data fusion technology to perform weighted averaging on the measurement values ​​of multiple sensors to obtain fused data. Among them, X i (t) is the measurement value of the i-th sensor at time t, ω i (t) represents the dynamic weight of the i-th sensor at time t, is the measurement variance of the i-th sensor at time t. The smaller the measurement variance, the greater the weight.

[0014] Preferably, the automated decision module establishes a risk assessment model using a random forest algorithm, and the operation of automatically generating an emergency decision plan is:

[0015] Step 1: First, divide the data into 70% training set and 30% test set, and use the training set to train the random forest algorithm;

[0016] Step 2: Use the test set data to output the risk score, and take the average of the prediction results of all decision trees as the output risk score Among them, N trees is the number of decision trees, R i is the prediction score of the i-th decision tree, which is a number between 0 and 1;

[0017] Step 3: Then, according to the fuzzy logic system, select the appropriate emergency response strategy and define the fuzzy membership function of the risk score R. The low risk is Medium risk High risk Among them, T0 is the lower limit of low risk, which is 0, T1 is 0.3, T2 is the lower limit of low risk, which is 0.8, and T3 is the upper limit of high risk, which is 1;

[0018] Step 4. Finally, use fuzzy rules to convert the membership into a specific emergency response strategy. If the membership of R is the largest in the low-risk area, the emergency response strategy is to enhance supervision. If the membership of R is the largest in the medium-risk area, the emergency response strategy is to initiate an emergency response. If the membership of R is the largest in the high-risk area, the emergency response strategy is to completely stop work and evaluate.

[0019] Preferably, the steps for implementing the triangulation positioning algorithm in the emergency response module are:

[0020] Step 1: First, multiple Bluetooth beacons are arranged in the gold mine tunnel. Personnel carry devices with Bluetooth function. The devices receive the Bluetooth signal strength from different beacons and calculate the distance between the device and each beacon through the relationship model between signal strength and distance.

[0021] Step 2: Draw a circle with the three reference points as the center and the distance from the target point to each reference point as the radius. The intersection of the three circles is the position of the target point. Suppose the coordinates of the three reference points are A(x1,y1), B(x2,y2), C(x3,y3), the coordinates of the target point T are (x,y), and the distances from the target point to the three reference points are d1, d2, d3. According to the distance formula Combine and solve these three equations to obtain the coordinates of the target point.

[0022] Compared with the prior art, the advantages and positive effects of the present invention are that, through the multi-sensor fusion network and wireless sensor technology of the intelligent perception module, it is possible to monitor the pressurized water-related data in and around the gold mining area in real time and accurately, and to promptly discover potential safety hazards; the automated decision-making module utilizes data fusion technology and random forest algorithm to quickly and accurately conduct risk assessments and automatically generate reasonable emergency decision-making plans, thereby improving the scientific nature and efficiency of decision-making; the emergency response module helps personnel evacuate safely and quickly through early warning program alarms, remote control of emergency equipment, and the use of triangulation positioning algorithms and communication equipment, thereby effectively reducing the losses caused by accidents. DETAILED DESCRIPTION

[0023] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described below in conjunction with embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0024] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments of the following disclosure.

[0025] Embodiment, taking into account that in the current gold mining process, ultra-high pressure water outburst disaster is a serious safety hazard. With the increase of gold mining depth, the pressure of pressurized water also increases. Once an outburst occurs, it may cause serious consequences such as casualties, equipment damage and mine flooding. With the continuous development of science and technology, intelligent perception and automated decision-making technology can change this shortcoming. The present invention proposes an emergency response system for ultra-high pressure water outburst disasters in gold mines based on intelligent perception and automated decision-making. This system is divided into an intelligent perception module, an automated decision-making module and an emergency response module.

[0026] First, a multi-sensor fusion network is used in the intelligent perception module to monitor pressure, water level, water flow, water temperature and other data. Then, considering the transmission quality of sensor information, the present invention constructs a wireless sensor network, and through routing optimization technology, the collected sensor data can reach the decision-making system quickly and stably. First, the status of each link is evaluated in real time. The weighted shortest path algorithm is used to calculate the optimal path according to the link status. Where D(i,k) represents the known minimum weight of the shortest path from node i to node k, ω(k,j) is the edge weight from node k to j, and N(i) represents the set of nodes directly adjacent to node i. Multipath routing is introduced, and traffic is distributed using the formula to improve the redundancy and reliability of the network. Among them, R iis the flow ratio allocated to path i, Q i is the quality factor of path i, It represents the sum of the quality factors of all available paths. Finally, by monitoring the congestion status of each path, the traffic is dispersed to the paths with lighter loads to prevent overload of a single path.

[0027] Considering the data format and quality issues in the automated decision-making module, data fusion technology is first used in this module to perform weighted averaging on the measurement values ​​of multiple sensors to obtain the fused data. Among them, X i (t) is the measurement value of the i-th sensor at time t, ω i (t) represents the dynamic weight of the i-th sensor at time t, is the measurement variance of the i-th sensor at time t. The smaller the measurement variance, the greater the weight.

[0028] Then, in order to realize the emergency decision plan in the automated decision module, the random forest algorithm is used to automatically generate the emergency decision plan. First, the data is divided into 70% training set and 30% test set, and the training set is used to train the random forest algorithm; secondly, the test set data is used to output the risk score, and the average of the prediction results of all decision trees is taken as the output risk score. Among them, N trees is the number of decision trees, R i is the predicted score of the i-th decision tree, which is a number between 0 and 1. Then, according to the fuzzy logic system, the appropriate emergency response strategy is selected and the fuzzy membership function of the risk score R is defined. The low risk is Medium risk High risk Among them, T0 is the lower limit of low risk, which is 0, T1 is 0.3, T2 is the lower limit of low risk, which is 0.8, and T3 is the upper limit of high risk, which is 1; finally, fuzzy rules are used to convert the membership degree into a specific emergency response strategy. If the membership degree of R is the largest in the low-risk area, the emergency response strategy is to enhance supervision; if the membership degree of R is the largest in the medium-risk area, the emergency response strategy is to initiate an emergency response; if the membership degree of R is the largest in the high-risk area, the emergency response strategy is a comprehensive shutdown and evaluation.

[0029] In the emergency response module, in order to help personnel evacuate safely and quickly, it is necessary to use communication equipment such as walkie-talkies to sound an alarm to warn staff, and fully use the triangulation positioning algorithm to accurately locate personnel, clarify the position of staff, and ensure the safe evacuation of staff. First, multiple Bluetooth beacons are arranged in the gold mine tunnels. Personnel carry devices with Bluetooth functions. The devices receive the Bluetooth signal strength from different beacons. The distance between the device and each beacon is calculated through the relationship model between signal strength and distance; a circle is drawn with three reference points as the center and the distance from the target point to each reference point as the radius. The intersection of the three circles is the position of the target point. The coordinates of the three reference points are A(x1,y1), B(x2,y2), and C(x3,y3), and the coordinates of the target point T are (x,y). The distances from the target point to the three reference points are d1, d2, and d3, respectively. According to the distance formula Combine and solve these three equations to obtain the coordinates of the target point.

[0030] Through the application of this system, the ability of gold mines to cope with ultra-high pressure water inrush disasters can be effectively improved, and the risk of casualties and equipment damage can be reduced. At the same time, the various modules of the system work together to achieve comprehensive monitoring and timely response to gold mine safety, with high practicality and reliability.

[0031] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An emergency response system for gold mine ultra-high pressure water inrush disasters based on intelligent perception and automated decision-making, characterized in that: The system includes an intelligent perception module, an automated decision-making module and an emergency response module; the intelligent perception module includes a multi-sensor fusion network, and arranges pressure sensors, water level sensors, water flow velocity sensors, temperature sensors, and high-precision displacement sensors in the gold mining area and surrounding key locations, and builds wireless sensor technology to ensure that the collected sensor data can reach the decision-making system quickly and stably; the automated decision-making module includes using data fusion technology to process data, using random forest algorithm to establish a risk assessment model, using historical data for training, and automatically generating emergency decision-making plans based on the results of risk assessment and preset emergency response strategies, and continuously simulating and verifying to improve the system's emergency response capabilities; The emergency response module includes an early warning program alarm, emergency equipment is remotely controlled through an automated decision-making module, and triangulation positioning algorithms and communication equipment are used to help personnel evacuate safely and quickly.

2. According to claim 1, a gold mine ultra-high pressure water inrush disaster emergency response system based on intelligent perception and automated decision-making is characterized in that: In the intelligent sensing module, pressure sensors, water level sensors, and water flow velocity sensors are used to monitor the pressure, water level changes, and water flow velocity of pressurized water in real time. Temperature sensors are used to monitor changes in ambient temperature. Abnormal changes in water temperature may also indicate the risk of pressurized water inrush. High-precision displacement sensors are used to monitor the displacement of tunnel walls and supporting structures, so as to promptly detect deformations that may be caused by pressurized water pressure.

3. According to claim 1, a gold mine ultra-high pressure water inrush disaster emergency response system based on intelligent perception and automated decision-making is characterized in that: When constructing the wireless sensor technology in the intelligent sensing module, a low-power design is adopted to extend the service life of the sensor, and the reliability and coverage of the network are improved through self-organizing network and routing optimization technology.

4. According to claim 3, a gold mine ultra-high pressure water inrush disaster emergency response system based on intelligent perception and automated decision-making is characterized in that: The specific operations of the route optimization are: Step 1: Evaluate the status of each link in real time Step 2: Use the weighted shortest path algorithm to calculate the optimal path based on the link status Where D(i,k) represents the known minimum weight of the shortest path from node i to node k, ω(k,j) is the edge weight from node k to j, and N(i) represents the set of nodes directly adjacent to node i; Step 3: Introduce multi-path routing and use the following formula to distribute traffic and improve network redundancy and reliability. Among them, R i is the flow ratio allocated to path i, Q i is the quality factor of path i, represents the sum of the quality factors of all available paths; Step 4: Finally, by monitoring the congestion status of each path, the traffic is dispersed to the paths with lighter loads to prevent a single path from being overloaded.

5. According to claim 1, a gold mine ultra-high pressure water inrush disaster emergency response system based on intelligent perception and automated decision-making is characterized in that: The automated decision module uses data fusion technology to perform weighted averaging on the measurement values ​​of multiple sensors to obtain fused data. Among them, X i (t) is the measurement value of the i-th sensor at time t, ω i (t) represents the dynamic weight of the i-th sensor at time t, is the measurement variance of the i-th sensor at time t. The smaller the measurement variance, the greater the weight.

6. The emergency response system for gold mine ultra-high pressure water inrush disaster based on intelligent perception and automated decision-making according to claim 1 is characterized in that: The automated decision-making module establishes a risk assessment model using a random forest algorithm and automatically generates an emergency decision-making plan as follows: Step 1: First, divide the data into 70% training set and 30% test set, and use the training set to train the random forest algorithm; Step 2: Use the test set data to output the risk score, and take the average of the prediction results of all decision trees as the output risk score. Among them, N trees is the number of decision trees, R i is the prediction score of the i-th decision tree, which is a number between 0 and 1; Step 3: Then, according to the fuzzy logic system, select the appropriate emergency response strategy and define the fuzzy membership function of the risk score R. The low risk is Medium risk High risk Among them, T0 is the lower limit of low risk, which is 0, T1 is 0.3, T2 is the lower limit of low risk, which is 0.8, and T3 is the upper limit of high risk, which is 1; Step 4. Finally, use fuzzy rules to convert the membership into a specific emergency response strategy. If the membership of R is the largest in the low-risk area, the emergency response strategy is to enhance supervision. If the membership of R is the largest in the medium-risk area, the emergency response strategy is to initiate an emergency response. If the membership of R is the largest in the high-risk area, the emergency response strategy is to completely stop work and evaluate.

7. The emergency response system for gold mine ultra-high pressure water inrush disaster based on intelligent perception and automated decision-making according to claim 1 is characterized in that: The implementation steps of the triangulation positioning algorithm in the emergency response module are as follows: Step 1: First, multiple Bluetooth beacons are arranged in the gold mine tunnel. Personnel carry devices with Bluetooth function. The devices receive the Bluetooth signal strength from different beacons and calculate the distance between the device and each beacon through the relationship model between signal strength and distance. Step 2: Draw a circle with the three reference points as the center and the distance from the target point to each reference point as the radius. The intersection of the three circles is the position of the target point. Suppose the coordinates of the three reference points are A(x1,y1), B(x2,y2), C(x3,y3), the coordinates of the target point T are (x,y), and the distances from the target point to the three reference points are d1, d2, d3. According to the distance formula (x-x1) 2 +(y-y1) 2 =d1 2 , (x-x2) 2 +(y-y2) 2 =d2 2 , (x-x3) 2 +(y-y3) 2 =d3 2 , combine and solve these three equations to obtain the coordinates of the target point.

Images