Oil-rich coal mine area geological environment risk prediction system

Abstract

The invention discloses an oil-rich coal mine area geological environment risk prediction system in the technical field of oil-rich coal mining. The system comprises an acquisition module used for acquiring geological data information in a mining area; the data analysis module is used for generating risk information of the geological environment; the prediction module is used for predicting unoccurred risks and formulating countermeasures; and the dynamic early warning module is used for sending an early warning signal to the emergency processing module. And the emergency processing module is used for displaying the early warning signal, the prediction result and the countermeasures in a mining area three-dimensional map in VR in a three-dimensional image form. According to the invention, the corresponding geological environment risk is learned and predicted through various risk prediction models, the system can automatically generate countermeasures according to the prediction result, the intelligence and automation of safety management are realized, and the safety risk caused by human factors is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of rich oil coal mining, and specifically relates to a geological environment risk prediction system for rich oil coal mining areas. Background Art

[0002] The geological environment risk prediction system for rich oil coal mining areas takes the geological environment of coal mining areas as the research object, and comprehensively applies the theories and methods of multiple disciplines such as geology, environmental science, computer science, and information technology to conduct real-time monitoring, data analysis, risk assessment, and prediction and early warning of the geological environment of coal mining areas. This system collects and analyzes geological environment data, identifies potential geological disasters and environmental risks, and provides a scientific basis and technical support for coal mine safety production, environmental protection, and disaster prevention and control.

[0003] Although the geological environment risk prediction system for rich oil coal mining areas plays an important role in coal mine safety production, environmental protection, and disaster prevention and control, there are still some deficiencies in its existing technologies. For example, the decision-making support process may be affected by the subjective judgment and experience of decision-makers, resulting in deviations in decision-making results. Although the system provides emergency plans and emergency response mechanisms, in actual response to emergencies, it still relies on manual decision-making and on-site disposal capabilities.

[0004] In summary, how to solve the problem that in actual response to emergencies, it is necessary to rely on manual decision-making and on-site disposal capabilities to provide emergency treatment measures, resulting in slow emergency response has become a technical problem that needs to be solved urgently by those skilled in the art. Therefore, it is necessary to propose a geological environment risk prediction system for rich oil coal mining areas. Summary of the Invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide a geological environment risk prediction system for rich oil coal mining areas. Through a variety of risk prediction models, the corresponding geological environment risks are learned and predicted. The system can automatically generate countermeasures according to the prediction results, realizing the intelligentization and automation of safety management and reducing the safety risks caused by human factors.

[0006] In order to achieve the above purpose, the technical solution of the present invention is as follows: A geological environment risk prediction system for rich oil coal mining areas, including:

[0007] A collection module: used to collect geological data information in the mining area and send the collected geological data information to the data analysis module;

[0008] A data analysis module: used to analyze geological data information in real time, generate risk information of the geological environment, and the data analysis module sends the risk information to the prediction module;

[0009] Prediction Module: The prediction module communicates with the acquisition module. The prediction module is used to send risk information and geological data information to various prediction models built into the prediction module. Through various prediction models, the risk information of the mining area geological environment is learned and predicted, and corresponding learning and prediction results are obtained. And corresponding countermeasures are generated according to the learning and prediction results, and at the same time, the learning and prediction results and countermeasures are sent to the emergency handling module;

[0010] Dynamic Warning Module: The dynamic warning module, the data analysis module and the acquisition module all communicate with each other. The dynamic warning module is used to use a preset deep learning algorithm to utilize risk information and geological data information to generate a real-time risk level. When the real-time risk level reaches the set threshold, the dynamic warning module sends a warning signal to the emergency handling module;

[0011] Emergency Handling Module: It is used to combine the received warning signal, learning and prediction results and countermeasures with the three-dimensional map of the mining area using VR technology, display the warning signal and learning and prediction results in the three-dimensional map of the mining area in VR in the form of three-dimensional images, and automatically take emergency measures according to the real-time risk level module.

[0012] Furthermore, the acquisition module includes several ground settlement acquisition devices, several groundwater level sensors, several gas monitoring sensors and several barometric pressure sensors. The ground settlement acquisition devices are arranged on the ground around the mining area, the groundwater level sensors are arranged at the groundwater level monitoring points in the mining area, the gas monitoring sensors are arranged inside the mine roadway, and the barometric pressure sensors are arranged inside the mine roadway; the acquisition module generates geological data information from the data collected by the ground settlement acquisition devices, groundwater level sensors, gas monitoring sensors and barometric pressure sensors.

[0013] Furthermore, the geological data information generated by the acquisition module includes ground settlement amount, groundwater level amount, mine oxygen content and mine internal barometric pressure value.

[0014] Furthermore, the ground settlement acquisition device includes a laser emission component for emitting detection laser, a detection component for detecting ground deformation amount and a laser reception component for receiving laser; the laser emission component includes a laser emitter and a first base, and the laser emitter is hinged to the top of the first base; the detection component includes a first plane mirror and a second base, and the reflecting surface of the first plane mirror is fixedly connected to the top of the second base; the laser reception component includes a second plane mirror and a third base, and the non-reflecting surface of the second plane mirror is fixedly connected to the top of the third base; a photosensitive sensor is fixedly connected to one end of the top of the third base close to the second plane mirror.

[0015] Furthermore, the data analysis module includes a historical data recording unit, and the historical data recording unit is used to store the historical geological data information collected by the acquisition module and send the historical geological data information to the prediction module to assist the prediction module in predicting the risk of the mining area geological environment.

[0016] Further, the risk information in the data analysis module includes the ground settlement rate, the rising rate of the groundwater level, the decreasing rate of oxygen in the mine, and the changing rate of pressure in the mine.

[0017] Further, the multiple prediction models in the prediction module include a landslide prediction model, a water level prediction model, an oxygen deficiency prediction model, and an explosion prediction model.

[0018] Further, the learning prediction results in the prediction module include the probability of the risk occurring, the location where the risk occurs, the impact brought by the risk occurrence, and the time period when the risk occurs.

[0019] Further, the warning signals in the dynamic warning module include ground collapse warning, warning of the groundwater level exceeding the warning value, low oxygen content warning, and high pressure warning in the mine; the real-time risk levels include low risk, general risk, medium risk, and high risk;

[0020] The deep learning algorithm includes the following steps:

[0021] Step 1: Set node A as one type of risk information and set node B as one type of geological data information;

[0022] Step 2: The probability of the risk occurring is P(A|B). Set the probability intervals as follows: low risk: 0 - 6%; general risk: 7% - 15%; medium risk: 16% - 40%; high risk: above 41%;

[0023] Step 3: Substitute node A and node B into the following formula:

[0024]

[0025] Obtain the value of P(A|B) and output the real-time risk level by comparing this value with the specified probability interval.

[0026] Further, the emergency measures automatically taken according to the real-time risk level in the emergency handling module include:

[0027] Low risk: Increase the frequency of collecting geological data information by the collection module;

[0028] General risk: Enhance the operating efficiency of the drainage system and ventilation system in the mining area;

[0029] Medium risk: Activate the alarm system in the mine, turn on the emergency backup power supply, and open the escape route;

[0030] High risk: Send an emergency rescue signal to the superior department, and mark the rescue route and escape route as green and display them on the 3D map of the mining area according to the learning prediction results of the prediction module.

[0031] After adopting the above solution, the following beneficial effects are achieved: 1. The system can collect and analyze geological data information in the mining area in real time through the collection module and the analysis module, and can timely discover potential geological environment risks, improving the accuracy and timeliness of prediction. The system is built-in with a variety of prediction models, such as landslide prediction model, water level prediction model, hypoxia prediction model, explosion prediction model, etc., which can conduct targeted predictions for different types of risks, improving the comprehensiveness and accuracy of prediction.

[0032] 2. Through learning and predicting the corresponding geological environment risks by a variety of risk prediction models, the system can update the risk level in real time according to the prediction results, and automatically take emergency measures according to the real-time risk level. By marking the emergency access roads and escape routes on the three-dimensional map for relevant personnel to refer to and execute, the intelligent and automated safety management is realized, reducing the safety risks caused by human factors. At the same time, the system can generate the risk level in real time, and send a warning signal to the emergency handling module when the risk level reaches the set threshold, enabling relevant personnel to respond quickly and take effective measures to reduce the probability and loss of accidents.

[0033] 3. Through the prediction and evaluation of geological environment risks by the prediction module, the system can update the prediction model in real time, improving the accuracy rate of the prediction model. At the same time, it can also provide a scientific basis for the mining plan of the mining area, optimize the mining sequence and intensity, and avoid the occurrence of mining area accidents caused by blind mining. Description of the Drawings

[0034] Figure 1 It is a structural diagram of a geological environment risk prediction system for a rich oil coal mining area according to an embodiment of the present invention.

[0035] Figure 2 It is a front view of a ground settlement collection device according to an embodiment of the present invention.

[0036] The reference numerals in the drawings of the specification include: first base 1, laser emitter 2, first plane mirror 3, second base 4, second plane mirror 5, third base 6, photosensitive sensor 7. Detailed Embodiments

[0037] The following is a further detailed description through specific embodiments:

[0038] Embodiment 1:

[0039] Basically as shown in the attached Figure 1 shown:

[0040] A geological environment risk prediction system for a rich oil coal mining area includes:

[0041] Data collection module: It is used to collect geological data information in the mining area and send the collected geological data information to the data analysis module. The data collection module includes several ground settlement collection devices, several groundwater level sensors, several gas monitoring sensors, and several barometric pressure sensors. The ground settlement collection devices are arranged on the ground around the mining area and automatically record the ground settlement data every 24 hours. The groundwater level sensors are arranged at the groundwater level monitoring points in the mining area, and the data is uploaded every hour. Oxygen concentration monitoring sensors are installed in key areas in the mine roadway, such as the working face and ventilation roadway, etc., and the data is uploaded every 10 minutes. Barometric pressure sensors are installed in the mine roadway and arranged adjacent to the gas monitoring sensors, and the barometric pressure value is recorded every 15 minutes.

[0042] The data collection module generates geological data information from the data collected by the ground settlement collection devices, groundwater level sensors, gas monitoring sensors, and barometric pressure sensors. The geological data information generated by the data collection module includes the ground settlement amount, groundwater level amount, mine oxygen content, and mine internal barometric pressure value.

[0043] Data analysis module: It is used to analyze geological data information in real time and generate risk information of the geological environment. The data analysis module sends the risk information to the prediction module. The data analysis module receives data from the data collection module and immediately calculates the ground settlement rate, groundwater level rise rate, mine internal oxygen reduction rate, and mine internal pressure change rate; the historical data recording unit stores all historical data.

[0044] Prediction module: The prediction module communicates with the data collection module; the prediction module is used to send the risk information and geological data information to various prediction models built in the prediction module, learn and predict the risk information of the mining area geological environment through various prediction models, and obtain corresponding learning and prediction results; and generate countermeasures according to the learning and prediction results, and at the same time send the learning and prediction results and countermeasures to the emergency handling module.

[0045] The learning and prediction results in the prediction module include the probability of risk occurrence, the location of risk occurrence, the impact brought by risk occurrence, and the time period of risk occurrence.

[0046] The prediction module uses historical data to train the collapse prediction model, water level prediction model, hypoxia prediction model, and explosion prediction model. These models are based on the RNN neural network model to predict risks. According to the real-time risk information and geological data, various prediction models make a comprehensive judgment and output the probability of risk occurrence, the location of risk occurrence, the impact brought by risk occurrence, and the time period of risk occurrence. In this embodiment, the prediction results show that the probability of a ground collapse occurring in a certain area within the next 24 hours is 30%, located in the southeast of the mining area, which may affect the surrounding working faces, and it is recommended to take preventive measures immediately.

[0047] Dynamic warning module: The dynamic warning module, the data analysis module, and the acquisition module communicate with each other. The dynamic warning module is used to generate a real-time risk level using a preset deep learning algorithm with risk information and geological data information. When the real-time risk level reaches the set threshold, the dynamic warning module sends a warning signal to the emergency handling module. The warning signals in the dynamic warning module include ground collapse warning, underground water level exceeding the warning value warning, low oxygen content warning, and high pressure warning in the mine.

[0048] The real-time risk levels include low risk, general risk, medium risk, and high risk.

[0049] The deep learning algorithm includes the following steps:

[0050] Step 1: Set node A as one type of risk information and set node B as one type of geological data information;

[0051] Step 2: Node P(A|B) is the probability of the risk occurring. Set the probability intervals as follows: low risk: 0 - 6%; general risk: 7% - 15%; medium risk: 16% - 40%; high risk: above 41%;

[0052] Step 3: Substitute node A and node B into the following formula:

[0053]

[0054] Obtain the value of P(A|B) and output the real-time risk level by comparing this value with the specified probability interval.

[0055] The dynamic warning module evaluates the real-time risk level through the deep learning algorithm, combining risk information and geological data. In this embodiment, the current rising rate of the underground water level exceeds the warning value, and the system determines it as "medium risk".

[0056] Warning signal sending: When the real-time risk level reaches the set threshold, in this embodiment, when the underground water level exceeds the warning value, the dynamic warning module immediately sends the "underground water level exceeding the warning value warning" to the emergency handling module.

[0057] Emergency handling module: It is used to combine the received warning signals, learning prediction results, and countermeasures with the three-dimensional map of the mining area using VR technology, display the warning signals and learning prediction results in the three-dimensional map of the mining area in VR in the form of three-dimensional images, and automatically take emergency measures according to the real-time risk level module.

[0058] The emergency measures automatically taken by the emergency handling module according to the real-time risk level include:

[0059] Low risk: Increase the frequency of the acquisition module to collect geological data information.

[0060] General risks: Enhance the operating efficiency of the drainage system and ventilation system in the mining area.

[0061] Medium risks: Activate the alarm system in the mine, turn on the emergency backup power supply, and open the escape routes.

[0062] High risks: Send emergency rescue signals to the superior department, and mark the rescue routes and escape routes as green according to the learning and prediction results of the prediction module and display them on the 3D map of the mining area.

[0063] After receiving the early warning signal, the emergency handling module combines and displays the 3D map of the mining area with the early warning signal, prediction results, and countermeasures through VR technology. In this embodiment, in VR, the area where the underground water level exceeds the warning value can be seen highlighted, and the specific locations of the emergency drainage measures are marked.

[0064] In this embodiment, since the real-time risk level is medium risk, the system activates the alarm system in the mine, enhances the operating efficiency of the drainage system and ventilation system, and prepares to open the escape routes.

[0065] This system can collect and analyze geological data information in the mining area in real time through the collection module and analysis module, and can timely detect potential geological environment risks, improving the accuracy and timeliness of prediction; the system is built-in with a variety of prediction models, such as landslide prediction models, water level prediction models, hypoxia prediction models, and explosion prediction models, which can conduct targeted predictions for different types of risks, improving the comprehensiveness and accuracy of prediction. Through learning and predicting the corresponding geological environment risks by a variety of risk prediction models, the system can update the risk level in real time according to the prediction results, and automatically take emergency measures according to the real-time risk level. By marking the rescue routes and escape routes on the 3D map for relevant personnel to refer to and execute, it realizes the intelligentization and automation of safety management and reduces the safety risks caused by human factors.

[0066] Embodiment 2:

[0067] Basically as shown in the appendix Figure 2 shown:

[0068] The difference from the above embodiment is that the ground settlement collection device includes a laser emission component for emitting detection laser, a detection component for detecting ground deformation, and a laser receiving component for receiving the laser.

[0069] The laser emission component includes a laser emitter 2 and a first base 1, and the laser emitter 2 is hinged to the top of the first base 1.

[0070] The detection component includes a first plane mirror 3 and a second base 4, and the reflecting surface of the first plane mirror 3 and the top of the second base 4 are fixedly connected by bolts.

[0071] The laser receiving component includes a second plane mirror 5 and a third base 6. The non-reflective surface of the second plane mirror 5 and the top of the third base 6 are fixedly connected by bolts. One end of the top of the third base 6 away from the second plane mirror 5 is fixedly connected with a photosensitive sensor 7 by bolts.

[0072] The specific implementation process is as follows:

[0073] Place the first base 1 outside the ground range in the mining area that needs to be monitored for settlement, place the second base 4 within the ground range that needs to be monitored for settlement, and place the third base 6 outside the ground range that needs to be monitored for settlement. At the same time, make the first base 1, the second base 4, and the third base 6 in a straight line; adjust the emission angle of the laser emitter 2 on the first base 1 so that the laser emitted by the laser emitter 2 can be emitted to the reflective surface of the first plane mirror 3 on the top of the second base 4, and adjust the angle of the first plane mirror 3 so that it can reflect the laser to the reflective surface of the second plane mirror 5 on the third base 6, and then adjust the angle of the second plane mirror 5 so that it can reflect the laser to the photosensitive sensor 7 on the third base 6 again.

[0074] When the ground under the second base 4 settles, the relative position of the second base 4 will drop, and it will drive the relative position of the first plane mirror 3 on the second base 4 to drop. When the first plane mirror 3 drops relatively, at this time, the incident point of the laser on the first plane mirror 3 shifts left and right, and once again causes the incident point of the laser on the reflective surface of the second plane mirror 5 to shift left and right. At this time, the position where the laser is reflected by the reflective surface of the second plane mirror 5 to the photosensitive sensor 7 shifts up and down. The photosensitive sensor 7 identifies the ground settlement amount and settlement rate under the second base 4 by reading the offset amount of the laser on the photosensitive sensor 7.

[0075] At the same time, through the multiple reflections of the laser by the first plane mirror 3 and the second plane mirror 5, it is possible to amplify the tiny deformation of the ground settlement to a measurable range, realizing the function of real-time monitoring of the ground settlement amount and the ground settlement rate.

[0076] The above are only embodiments of the present invention. Specific structures and characteristics and other common knowledge in the art are not described in detail herein. Those of ordinary skill in the art know all the common general technical knowledge in the technical field to which the invention pertains before the filing date or the priority date, can learn all the prior art in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, combine their own abilities to improve and implement this solution. Some typical well-known structures or well-known methods should not become an obstacle for those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can still be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. A geological environment risk prediction system for oil-rich coal mining areas, characterized by: include: Collection module: used to collect geological data information in the mining area and send the collected geological data information to the data analysis module; Data analysis module: used to analyze geological data information in real time and generate risk information of geological environment. The data analysis module sends the risk information to the prediction module; Prediction module: The prediction module communicates with the acquisition module; the prediction module is used to send risk information and geological data information to the multiple prediction models built into the prediction module, and conduct learning and prediction of the risk information of the geological environment of the mining area through the multiple prediction models, and obtain the corresponding learning prediction results; and generate response measures based on the learning prediction results, and send the learning prediction results and response measures to the emergency handling module at the same time; Dynamic warning module: The dynamic warning module, data analysis module and acquisition module all communicate with each other. The dynamic warning module is used to generate real-time risk levels using a preset deep learning algorithm using risk information and geological data information. When the real-time risk level reaches a set threshold, the dynamic warning module sends a warning signal to the emergency processing module; Emergency processing module: It is used to use VR technology to combine the received warning signals, learning prediction results and response measures with the three-dimensional map of the mining area, display the warning signals and learning prediction results in the form of three-dimensional images in the three-dimensional map of the mining area in VR, and automatically take emergency measures according to the real-time risk level module.

2. The geological environment risk prediction system for oil-rich coal mining areas according to claim 1 is characterized by: The acquisition module includes several ground subsidence acquisition devices, several groundwater level sensors, several gas monitoring sensors and several air pressure sensors; The ground subsidence collection device is arranged on the ground around the mining area, the groundwater level sensor is arranged at the groundwater level monitoring point in the mining area, the gas monitoring sensor is arranged inside the mine tunnel, and the air pressure sensor is arranged inside the mine tunnel; the collection module generates geological data information from the data collected by the ground subsidence collection device, groundwater level sensor, gas monitoring sensor and air pressure sensor.

3. The geological environment risk prediction system for oil-rich coal mining areas according to claim 2 is characterized by: The geological data information generated by the acquisition module includes ground subsidence, groundwater level, mine oxygen content and air pressure in the mine.

4. The geological environment risk prediction system for oil-rich coal mining areas according to claim 3 is characterized by: The ground subsidence collection device includes a laser emitting component for emitting detection laser, a detection component for detecting ground deformation, and a laser receiving component for receiving laser; The laser emitting assembly comprises a laser emitter and a first base, wherein the laser emitter is hinged to the top of the first base; The detection assembly includes a first plane mirror and a second base, and the reflection surface of the first plane mirror is fixedly connected to the top of the second base; The laser receiving assembly comprises a second plane mirror and a third base. The non-reflective surface of the second plane mirror is fixedly connected to the top of the third base. A photosensitive sensor is fixedly connected to one end of the top of the third base close to the second plane mirror.

5. The geological environment risk prediction system for oil-rich coal mining areas according to claim 4 is characterized by: The data analysis module includes a historical data recording unit, which is used to store the historical geological data information collected by the collection module and send the historical geological data information to the prediction module to assist the prediction module in predicting the geological environmental risks of the mining area.

6. The geological environment risk prediction system for oil-rich coal mining areas according to claim 5 is characterized by: The risk information in the data analysis module includes the rate of ground subsidence, the rate of groundwater level rise, the rate of oxygen reduction in the mine and the rate of pressure change in the mine.

7. The geological environment risk prediction system for oil-rich coal mining areas according to claim 6 is characterized by: The various prediction models in the prediction module include landslide prediction model, water level prediction model, hypoxia prediction model and explosion prediction model.

8. The geological environment risk prediction system for oil-rich coal mining areas according to claim 7 is characterized by: The learning prediction results in the prediction module include the probability of risk occurrence, the location of risk occurrence, the impact of risk occurrence and the time period of risk occurrence.

9. The geological environment risk prediction system for oil-rich coal mining areas according to claim 8 is characterized by: The warning signals in the dynamic warning module include ground collapse warning, groundwater level exceeding warning value warning, low oxygen content warning and high pressure warning in the mine; Real-time risk levels include low risk, average risk, medium risk and high risk; The deep learning algorithm consists of the following steps: Step 1: Set node A as one of the risk information and node B as one of the geological data information; Step 2: Node P(A|B) is the probability of risk occurrence, and the probability interval is set as low risk: 0-6%; general risk: 7%-15%; medium risk: 16%-40%; high risk: above 41%; Step 3: Substitute nodes A and B into the following formula: The value of P(A|B) is obtained and compared with the specified probability interval to output the real-time risk level.

10. The geological environment risk prediction system for oil-rich coal mining areas according to claim 9 is characterized in that: The emergency response module automatically takes emergency measures based on the real-time risk level, including: Low risk: Increase the frequency of geological data collection by the acquisition module; General risks: Enhance the efficiency of drainage and ventilation systems within the mine area; Medium risk: Activate the mine's alarm system, turn on the emergency backup power supply, and open the escape route; High risk: Send an emergency rescue signal to the superior department, and mark the rescue channel and escape channel as green based on the learning prediction results of the prediction module and display them in the three-dimensional map of the mining area.

Images