Coal mine goaf comprehensive monitoring method based on digital twinning
Through the combination of digital twin model and extreme learning machine model, the problem of poor real-time monitoring of coal mine goaf is solved, and the rapid and accurate monitoring of underground goaf is achieved and the real-time update of waterproof and closed models is improved, which is improved and the accuracy of monitoring is Security.
Patent Information
- Application Number
- CN202411006675.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-12
AI Technical Summary
The existing technology has poor real-time monitoring of coal mine goafs, and it is impossible to quickly and accurately realize comprehensive monitoring of coal mine goafs, especially the lack of digital twin model monitoring methods and real-time update methods for airtight goafs.
Using a comprehensive monitoring method for underground goaf based on digital twins, a digital twin model is constructed by obtaining the structural data and sensing data of the underground goaf wall, and using the extreme learning machine model to perform data preprocessing and early warning logic design, real-time Optimize the model to achieve comprehensive monitoring of underground goaf.
It realizes rapid and accurate comprehensive monitoring of coal mine goaf, improves the real-time update capability of waterproof and sealed models, ensures real-time and accuracy of monitoring, predicts and outputs results in advance, and facilitates safe management.
Smart Images

Figure CN118934050A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent coal mines, and in particular to a method, system, equipment and medium for comprehensive monitoring of underground goaf areas based on digital twins. Background Art
[0002] Coal mine goaf refers to the hollow space or cavity left after underground coal or coal gangue is mined during coal mining operations. During the coal mining process, underground coal resources need to be mined and transported away. Generally, during the excavation process, a tunnel similar to the mountain tunnel on the road is used to gradually open up the tunnel between the underground coal location and the coal mine mouth. Generally, the ore and coal encountered during the mining process are transported to the ground in order to form a reasonable transportation and mining operation surface. With the continuous transportation of coal and other ores, such coal goafs are formed underground.
[0003] At present, the construction and implementation of underground water reservoirs in coal mines provide technical means for utilizing underground water resources in mines. Through the coal pillar dams left over during coal mining and the artificially constructed waterproof and airtight, a closed water storage area is built around the goaf to avoid the waste of resources and environmental pollution caused by direct discharge to the ground; at the same time, it provides a guarantee for industrial and domestic water in the mining area to a large extent. Therefore, the stability of the safe operation of underground water reservoirs in coal mines is crucial to the normal production of coal mines, and the special structure of the waterproof and airtightness of the goaf itself and the underground environment, the changes in the safety and stability of its own structure are the focus of attention of underground reservoirs. The pressure bearing capacity of the waterproof and airtight wall varies according to its layout position, so monitoring the waterproof and airtight wall is crucial to the safety of underground operations. The existing technology for monitoring waterproof and sealed walls obtains monitoring data based on manual inspections, and obtains the bearing capacity of the waterproof and sealed walls through calculation models on the monitoring data. The monitoring data obtained through manual inspections has many iterations and a long update period, and lacks the ability to update the actual data changes in real time. There is no digital twin model monitoring means and real-time update method for the sealing of goaf areas. The real-time performance of comprehensive monitoring of coal mine goafs is poor, and it is impossible to quickly and accurately realize comprehensive monitoring of coal mine goafs. Summary of the invention
[0004] The technical problem to be solved by the present invention is: in order to solve the problem that the existing technology has poor real-time performance in comprehensive monitoring of coal mine goafs and cannot quickly and accurately carry out comprehensive monitoring of coal mine goafs, the present invention provides a comprehensive monitoring method for coal mine goafs based on digital twins, which has good real-time performance and can quickly and accurately carry out comprehensive monitoring of coal mine goafs.
[0005] The technical solution adopted by the present invention to solve the technical problem is: a comprehensive monitoring method for underground goaf areas based on digital twins, the method comprising the following steps:
[0006] S1, obtaining structural data and first sensor data of the wall of the goaf in the mine;
[0007] The structural data includes: the length, width, height, material and shape data of the wall of the underground goaf area; the first sensor data includes: the surface strain, seepage pressure, drilling stress and water level data of the wall of the underground goaf area;
[0008] S2, constructing a first digital twin model based on the structural data;
[0009] S3, preprocessing the first sensor data to form sample data from the processed first sensor data;
[0010] S4, performing early warning logic design on the sample data to obtain multiple monitoring intervals;
[0011] S5, fusing the multiple monitoring intervals with the first digital twin model to obtain a second digital twin model;
[0012] S6, dividing the sample data into independent variable data and dependent variable data, and dividing the independent variable data and the dependent variable data in proportion to obtain a training set and a validation set;
[0013] Among them, seepage pressure, borehole stress and water level data are selected as independent variable data, and surface strain data are selected as dependent variable data;
[0014] S7, inputting the training set into an extreme learning machine model, training the extreme learning machine model, and obtaining a trained extreme learning machine model;
[0015] S8, inputting the verification set into the trained extreme learning machine model to obtain prediction data, wherein the prediction data includes predicted independent variable data and dependent variable data;
[0016] S9, compare the predicted data with each of the monitoring intervals to obtain a comparison result, use the predicted data and the comparison result to update the second digital twin model to obtain a third digital twin model, and realize comprehensive monitoring of the underground goaf area.
[0017] Further, specifically, in step S9, the third digital twin model is dynamically optimized in real time by installing a sensor device on the wall of the goaf underground to collect the first sensor data in real time.
[0018] Further, specifically, the real-time dynamic optimization of the third digital twin model specifically includes the following steps:
[0019] A1, acquiring second sensor data collected in real time, and preprocessing the second sensor data;
[0020] A2, comparing the preprocessed second sensing data with the predicted data to obtain a fitting value;
[0021] A3, comparing the fitting value with a preset threshold;
[0022] If the fitting value is greater than or equal to the preset threshold, the second sensor data preprocessed in step A1 is subjected to steps S4 to S9 to perform real-time dynamic optimization on the third digital twin model;
[0023] If the fitting value is less than the preset threshold, the third digital twin model does not need to be optimized.
[0024] Further, specifically, the step S4 specifically includes:
[0025] Calculate the expected value E(X) and variance σ of each first sensor data in the sample data 2 ∈(0,∞),
[0026] Based on the expected value and variance of each first sensor data, the maximum deviation probability calculation formula of the first sensor data is expressed as:
[0027] Based on the maximum deviation probability calculation formula, calculate The λ values when they are equal to 0.1, 0.15 and 0.2 are: λ1, λ2, λ3;
[0028] Based on the calculated λ1, λ2, and λ3, monitoring intervals are established, namely the first sub-interval (0, λ3+E(X)), the second sub-interval (λ3+E(X), λ2+E(X)), the third sub-interval (λ2+E(X), λ1), and the fourth sub-interval (λ1, +∞).
[0029] Further, specifically, in the step S9, the predicted data is set as Xi, and the predicted data is compared with each of the monitoring intervals step by step, including:
[0030] If the predicted data is in the first sub-interval, i.e., Xi∈(0, λ3+E(X)), the comparison result is that the data is normal, and the monitoring device corresponding to the predicted data under the third digital twin model is displayed in blue. If it is not in the first sub-interval, the comparison continues;
[0031] If the predicted data is in the second sub-interval, i.e., Xi∈(λ3+E(X), λ2+E(X)), the comparison result is data anomaly, and the monitoring device corresponding to the predicted data under the third digital twin model is displayed in yellow. If it is not in the second sub-interval, the comparison continues;
[0032] If the predicted data is in the third sub-interval, i.e., Xi∈(λ2+E(X), λ1), a secondary sound and light alarm is issued, and the comparison result is that the data is abnormal. The monitoring device corresponding to the predicted data under the third digital twin model displays orange. If it is not in the third sub-interval, the comparison continues;
[0033] If the predicted data is in the fourth sub-interval, i.e., Xi∈(λ1, +∞), a first-level sound and light alarm is issued, and the comparison result is that the data is abnormal. Under the third digital twin model, the monitoring equipment corresponding to the predicted data displays red.
[0034] Further, specifically, the preprocessing steps in step S3 or step A1 sequentially include outlier elimination, replacement, denoising and standardization of the first sensor data.
[0035] A digital twin-based underground goaf comprehensive monitoring system, the system comprising:
[0036] An acquisition module is configured to acquire structural data of a wall of a goaf area underground and first sensor data;
[0037] The structural data includes: the length, width, height, material and shape data of the wall of the underground goaf area; the first sensor data includes: the surface strain, seepage pressure, drilling stress and water level data of the wall of the underground goaf area;
[0038] A first construction module is configured to construct a first digital twin model based on the structural data;
[0039] A data processing module, configured to pre-process the first sensor data, and the processed first sensor data forms sample data;
[0040] An early warning logic design module is configured to perform early warning logic design on the sample data to obtain multiple monitoring intervals;
[0041] A fusion module is configured to fuse multiple monitoring intervals with the first digital twin model to obtain a second digital twin model after fusion;
[0042] A data partitioning module is configured to partition the sample data into independent variable data and dependent variable data, and to divide the independent variable data and the dependent variable data in proportion to obtain a training set and a validation set;
[0043] A training module is configured to input the training set into an extreme learning machine model, train the extreme learning machine model, and obtain a trained extreme learning machine model;
[0044] A prediction module is configured to input the verification set into a trained extreme learning machine model to obtain prediction data, wherein the prediction data includes predicted independent variable data and dependent variable data;
[0045] The updating module is configured to compare the predicted data with each of the monitoring intervals to obtain a comparison result, and use the predicted data and the comparison result to update the second digital twin model to obtain a third digital twin model to achieve comprehensive monitoring of underground goaf areas.
[0046] Further, specifically, the update module also includes an optimization unit, which collects the second sensor data in real time by installing a sensor device on the wall of the goaf underground, and performs real-time dynamic optimization on the third digital twin model.
[0047] A computer device comprising:
[0048] processor;
[0049] A memory for storing executable instructions;
[0050] Among them, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the underground goaf comprehensive monitoring method based on digital twin as described above.
[0051] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor implements the digital twin-based comprehensive monitoring method for underground goaf areas as described above.
[0052] The beneficial effects of the present invention are:
[0053] (1) The present invention provides a method for comprehensive monitoring of underground goaf areas based on digital twins. By constructing multi-stage data of structural data and sensor data, the display effect of the digital twin model is optimized step by step, and the early warning logic process is monitored to form a digital twin model that presents a specific change process according to the change of sensor data. The method has good real-time performance and can quickly and accurately monitor the goaf areas of coal mines.
[0054] (2) The present invention constructs a dynamic mapping relationship between the wall of the underground goaf and a large amount of data. By performing relevant progressive processing and fusion on the sensor data of waterproof and airtightness, the processing results are mapped with the wall of the underground goaf in real time, ensuring the accuracy of the waterproof and airtight digital twin model and the accuracy of the predicted output, improving the real-time update capability of the model, predicting the operation status of waterproof and airtightness in advance and outputting the results in a concrete form, which is convenient for safety management personnel to view and manage in real time;
[0055] (3) The extreme learning machine model is used to avoid the complex parameter settings of the input layer, hidden layer, and activation function in traditional neural network training, thereby improving and optimizing the rapid iterative computing capability of the training model and further improving the accuracy of comprehensive monitoring of coal mine goaf areas. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] The present invention is further described below in conjunction with the accompanying drawings and embodiments.
[0057] Figure 1 It is a schematic diagram of the method flow of embodiment 1 of the present invention.
[0058] Figure 2 It is a schematic diagram of the system structure of the second embodiment of the present invention.
[0059] Figure 3 It is a schematic diagram of the computer device structure of the third embodiment of the present invention.
[0060] In the figure, 20, acquisition module; 21, first construction module; 22, data processing module; 23, warning logic design module; 24, fusion module; 25, data partition module; 26, training module; 27, prediction module; 28, update module; 281, optimization unit;
[0061] 10. Computer equipment; 1002. Processor; 1004. Memory; 1006. Transmission device. DETAILED DESCRIPTION
[0062] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.
[0063] Example 1
[0064] The present application embodiment provides a method for comprehensive monitoring of underground goaf areas based on digital twins, such as Figure 1 As shown, the method comprises the following steps:
[0065] S1, obtaining structural data and first sensor data of the wall of the goaf in the mine;
[0066] The structural data include: length, width, height, material and shape data of the wall of the underground goaf. The structural data is obtained through manual measurement, engineering drawings and camera photos, and entered into the database. When executing step S1, the structural data is directly read from the database.
[0067] The first sensing data includes: surface strain, seepage pressure, borehole stress and water level data of the wall of the underground goaf. The first sensing data is obtained by sensors arranged on the wall of the underground goaf, such as obtaining surface strain data through a surface strain gauge, obtaining seepage pressure data through an osmometer, obtaining borehole stress data through a borehole stress gauge, and obtaining water level data through an optical fiber water level meter.
[0068] S2, constructing a first digital twin model based on the structural data. The constructed first digital twin model builds a virtual model of the goaf wall based on the structural data, displaying the shape of the goaf wall and the layered shape of the masonry materials inside the goaf wall building.
[0069] S3, preprocessing the first sensor data to form sample data from the processed first sensor data;
[0070] S4, design early warning logic for sample data to obtain multiple monitoring intervals;
[0071] S5, fusing the multiple monitoring intervals with the first digital twin model to obtain a second digital twin model;
[0072] S6, dividing the sample data into independent variable data and dependent variable data, and dividing the independent variable data and the dependent variable data in proportion to obtain a training set and a validation set;
[0073] Among them, seepage pressure, borehole stress and water level data are selected as independent variable data, and surface strain data are selected as dependent variable data;
[0074] S7, inputting the training set into the extreme learning machine model, training the extreme learning machine model, and obtaining a trained extreme learning machine model;
[0075] S8, inputting the validation set into the trained extreme learning machine model to obtain prediction data, wherein the prediction data includes predicted independent variable data and dependent variable data;
[0076] S9, compare the predicted data with each monitoring interval to obtain a comparison result, use the predicted data and the comparison result to update the second digital twin model to obtain a third digital twin model, and realize comprehensive monitoring of the underground goaf area.
[0077] In this embodiment, in step S9, the third digital twin model is dynamically optimized in real time by installing a sensor device on the wall of the underground goaf to collect the second sensor data in real time, thereby further improving the accuracy of the comprehensive monitoring of the underground goaf.
[0078] In this embodiment, real-time dynamic optimization of the third digital twin model specifically includes the following steps:
[0079] A1, acquiring the second sensor data collected in real time, and preprocessing the second sensor data;
[0080] A2, comparing the preprocessed second sensing data with the predicted data to obtain a fitting value;
[0081] A3, compare the fitted value with the preset threshold;
[0082] If the fitting value is greater than or equal to the preset threshold, the second sensor data preprocessed in step A1 will execute steps S4 to S9 to perform real-time dynamic optimization on the third digital twin model; if the fitting value is less than the preset threshold, the third digital twin model does not need to be optimized.
[0083] In this embodiment, step S4 specifically includes:
[0084] Calculate the expected value E(X) and variance σ of each first sensor data in the sample data 2 ∈(0,∞),
[0085] Based on the expected value and variance of each first sensing data, the maximum deviation probability calculation formula of the first sensing data is expressed as:
[0086] Based on the maximum deviation probability calculation formula, calculate The λ values when they are equal to 0.1, 0.15 and 0.2 are: λ1, λ2, λ3;
[0087] Monitoring intervals are established based on the calculated λ1, λ2, and λ3, and the monitoring intervals are respectively the first sub-interval (0, λ3+E(X)), the second sub-interval (λ3+E(X), λ2+E(X)), the third sub-interval (λ2+E(X), λ1), and the fourth sub-interval (λ1, +∞).
[0088] It should be noted that each type of first sensor data has its corresponding monitoring interval (such as surface strain data has its corresponding monitoring interval), each monitoring interval is set with four sub-intervals, and each sub-interval is divided into levels to facilitate the subsequent determination of the size of each data and the corresponding interval range, and to determine and match the abnormal state warning of the first sensor data.
[0089] In step S6, 80% of the independent variable data and the dependent variable data are used as a training set, and 20% of the data are used as a validation set.
[0090] In step S7, assuming that there are Q first sensing data samples, then the osmotic pressure data is represented by S = {s 11 s 12 s 13 …s 1Q}; Drilling stress data is expressed as: Z = {z 21z 22 z 23 …z 2Q}; water level data is expressed as: E = {e 31 e 32 e 33 …e 3Q}, the strain data (surface strain data) is expressed as: M = {m 11 m 12 m 13 …m 1Q}.
[0091] The independent variable data matrix is represented as:
[0092]
[0093] The dependent variable data representation matrix is:
[0094] Y=[m 11 m 12 m 13 …m 1Q ] 1×Q ;
[0095] The extreme learning machine model (ELM) is optimized, and the connection value ω between the input layer and the hidden layer (the number of neurons in the hidden layer is equal to the number of samples in the training set Q) is set as:
[0096] (Randomly generate any real number);
[0097] The connection value ω is used as a weight for the algorithm to implement the calculation, which avoids the traditional algorithm model mainly based on complex constitutive equations, with a large number of iterations, a long update period, and a lack of real-time update capabilities for actual data changes;
[0098] The execution value b of the hidden layer neuron is:
[0099] (Randomly generate any real number);
[0100] The connection value β between the hidden layer and the output layer is:
[0101]
[0102] Assume that the activation function of the hidden layer neuron is (the activation function can be 0 or 1), then the single variable data output of the network is:
[0103]
[0104] Where l is the total number of independent variable data and dependent variable data;
[0105] The overall output layer of the network can be expressed as:
[0106] Transpose the output layer T to get T', then the overall output layer of the network can be transformed into:
[0107] (where is the hidden layer output matrix), and the least squares method is used to calculate the weights of the hidden layer and the output layer:
[0108] (where is the Moore-Penrose generalized inverse of the hidden layer output matrix). This is the trained extreme learning machine model.
[0109] In step S9, let the predicted data be Xi, and compare the predicted data with each monitoring interval step by step, including:
[0110] If the predicted data is in the first subinterval, i.e., Xi∈(0, λ3+E(X)), the comparison result is that the data is normal, and the monitoring device corresponding to the predicted data under the third digital twin model is displayed in blue. If it is not in the first subinterval, the comparison continues;
[0111] If the predicted data is in the second subinterval, i.e., Xi∈(λ3+E(X), λ2+E(X)), the comparison result is data anomaly, and the monitoring device corresponding to the predicted data under the third digital twin model displays yellow. If it is not in the second subinterval, continue to compare;
[0112] If the predicted data is in the third sub-interval, i.e., Xi∈(λ2+E(X), λ1), a secondary sound and light alarm is issued, and the comparison result is that the data is abnormal. The monitoring device corresponding to the predicted data under the third digital twin model displays orange. If it is not in the third sub-interval, the comparison continues;
[0113] If the predicted data is in the fourth sub-interval, i.e., Xi∈(λ1, +∞), a first-level sound and light alarm is issued, and the comparison result is that the data is abnormal. Under the third digital twin model, the monitoring equipment corresponding to the predicted data displays red.
[0114] By monitoring the predicted data, early warning can be issued for coal mine goaf areas, and the monitoring of predicted data and the safety of waterproofing and sealing can be helped by sound and light alarms and color displays.
[0115] In this embodiment, the preprocessing steps in step S3 or step A1 sequentially include outlier elimination, replacement, denoising and standardization of the first or second sensor data.
[0116] Specifically, abnormal data are detected and eliminated through, but not limited to, mathematical statistics and probability theory methods, and the three-sigma rule, Boxplot, Grubbs hypothesis test and other methods are further used to perform single detection and elimination of outliers.
[0117] The eliminated and missing data are replaced and supplemented by methods such as data smoothing, fitting and interpolation. Preferably, the cubic spline interpolation method is used to calculate and supplement the eliminated and missing data, wherein the cubic spline interpolation constructs a smooth curve passing through a set of scattered data points, which is more accurate and natural when replacing and supplementing data points, and will not appear abrupt outliers, which can improve the accuracy of the data.
[0118] Smoothing technology and wavelet denoising methods can be used to reduce or eliminate noise in the data; differential methods, filtering and other methods can also be used to eliminate constant and periodic noise components in the signal.
[0119] In this embodiment, the fitting degree determination formula is expressed as:
[0120] Among them, ε is 0.05, that is, the preset threshold is equal to 0.05, t j For the prediction data, P j is the second sensor data after preprocessing (P j is one of the surface strain, seepage pressure, borehole stress or water level data corresponding to the prediction data type).
[0121] The data format is unified after outlier elimination, replacement, and denoising, eliminating the differences in characteristic attributes such as properties, dimensions, and magnitudes between different variables, and converting them into a dimensionless standardized value. Outlier elimination, replacement, denoising, and standardization can improve the quality of data and the accuracy of monitoring and analysis.
[0122] In summary, a method for comprehensive monitoring of underground goafs based on digital twins of the present invention optimizes the display effect of digital twin models step by step through multi-stage data construction of structural data and sensor data, and monitors the early warning logic process to form a digital twin model that presents a specific change process for changes in sensor data, with good real-time performance, and can quickly and accurately monitor coal mine goafs. The present invention constructs a dynamic mapping relationship between the wall of the underground goaf and a large amount of data. By performing relevant progressive processing and fusion on each waterproof and airtight sensor data, the processing results are mapped in real time with the wall of the underground goaf, ensuring the accuracy of the waterproof and airtight digital twin model and the accuracy of the predicted output, improving the real-time update capability of the model, and predicting the operation status of the waterproof and airtight in advance and outputting the results in a concrete form, which is convenient for safety management personnel to view and manage in real time. In addition, the extreme learning machine model is used to avoid the premise of complex parameter settings such as input layer, hidden layer and activation function in traditional neural network training, improve and optimize the rapid iterative computing capability of the training model, and further improve the accuracy of comprehensive monitoring of coal mine goafs.
[0123] Example 2
[0124] Based on the same inventive concept as the underground goaf comprehensive monitoring method based on digital twin in the aforementioned embodiment, the embodiment of the present application provides an underground goaf comprehensive monitoring system based on digital twin, the system comprising:
[0125] The acquisition module 20 is configured to acquire the structural data and first sensor data of the underground goaf wall; wherein the structural data includes: the length, width, height, material and shape data of the underground goaf wall, and the first sensor data includes: the surface strain, seepage pressure, drilling stress and water level data of the underground goaf wall.
[0126] The first construction module 21 is configured to construct a first digital twin model based on the structural data.
[0127] The data processing module 22 is configured to pre-process the first sensing data, and the processed first sensing data forms sample data.
[0128] The early warning logic design module 23 is configured to perform early warning logic design on the sample data to obtain multiple monitoring intervals.
[0129] The fusion module 24 is configured to fuse multiple monitoring intervals with the first digital twin model to obtain a second digital twin model after fusion.
[0130] The data partitioning module 25 is configured to partition the sample data into independent variable data and dependent variable data, and then partition the independent variable data and the dependent variable data in proportion to obtain a training set and a validation set.
[0131] The training module 26 is configured to input the training set into the extreme learning machine model, train the extreme learning machine model, and obtain a trained extreme learning machine model.
[0132] The prediction module 27 is configured to input the verification set into the trained extreme learning machine model to obtain prediction data, wherein the prediction data includes predicted independent variable data and dependent variable data.
[0133] The updating module 28 is configured to compare the predicted data with each monitoring interval to obtain a comparison result, and use the predicted data and the comparison result to update the second digital twin model to obtain a third digital twin model to achieve comprehensive monitoring of the underground goaf area.
[0134] In this embodiment, the update module 28 also includes an optimization unit 281, which collects the second sensor data in real time by installing a sensor device on the wall of the underground goaf to perform real-time dynamic optimization on the third digital twin model. The real-time dynamic optimization of the third digital twin model specifically includes the following steps:
[0135] A1, acquiring the second sensor data collected in real time, and preprocessing the second sensor data;
[0136] A2, comparing the preprocessed second sensing data with the predicted data to obtain a fitting value;
[0137] A3, compare the fitted value with the preset threshold;
[0138] If the fitting value is greater than or equal to the preset threshold, the second sensor data preprocessed in step A1 will execute steps S4 to S9 to perform real-time dynamic optimization on the third digital twin model; if the fitting value is less than the preset threshold, the third digital twin model does not need to be optimized.
[0139] The foregoing Figure 1 The various variations and specific examples of a comprehensive monitoring method for underground goaf areas based on digital twins in Example 1 are also applicable to a comprehensive monitoring device for underground goaf areas based on digital twins in this embodiment. Through the above detailed description of a comprehensive monitoring method for underground goaf areas based on digital twins, technical personnel in this field can clearly know the implementation method of a comprehensive monitoring device for underground goaf areas based on digital twins in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.
[0140] Example 3
[0141] An embodiment of the present application provides a computer device, which includes a processor and a memory, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by the processor to implement a comprehensive monitoring method for underground goaf areas based on digital twins as provided in the above method embodiment.
[0142] Figure 3 The hardware structure diagram of a device for implementing a method for comprehensive monitoring of underground goaf areas based on digital twins provided in an embodiment of the present application is shown. The device may participate in or include the apparatus or system provided in an embodiment of the present application. Figure 3 As shown, the computer device 10 may include one or more processors 1002 (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.
[0143] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer device 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).
[0144] The memory 1004 can be used to store software programs and modules of application software, such as a program instruction / data storage device corresponding to a method for comprehensive monitoring of underground goaf areas based on digital twins in an embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, implementing the above-mentioned method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0145] The transmission device 1006 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0146] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer device 10 (or mobile device).
[0147] Example 4 The embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a comprehensive monitoring method for underground goaf areas based on digital twins in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a comprehensive monitoring method for underground goaf areas based on digital twins provided in the above method embodiment.
[0148] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.
[0149] Example 5
[0150] The embodiment of the present invention also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a digital twin-based underground goaf comprehensive monitoring method provided in the above various optional embodiments.
[0151] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0152] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0153] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.
[0154] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.
Claims
1. A comprehensive monitoring method for underground goaf areas based on digital twins, characterized in that: The method comprises the following steps: S1, obtaining structural data and first sensor data of the wall of the goaf in the mine; The structural data includes: the length, width, height, material and shape data of the wall of the underground goaf area; the first sensor data includes: the surface strain, seepage pressure, drilling stress and water level data of the wall of the underground goaf area; S2, constructing a first digital twin model based on the structural data; S3, preprocessing the first sensor data to form sample data from the processed first sensor data; S4, performing early warning logic design on the sample data to obtain multiple monitoring intervals; S5, fusing the multiple monitoring intervals with the first digital twin model to obtain a second digital twin model; S6, dividing the sample data into independent variable data and dependent variable data, and dividing the independent variable data and the dependent variable data in proportion to obtain a training set and a validation set; Among them, seepage pressure, borehole stress and water level data are selected as independent variable data, and surface strain data are selected as dependent variable data; S7, inputting the training set into an extreme learning machine model, training the extreme learning machine model, and obtaining a trained extreme learning machine model; S8, inputting the verification set into the trained extreme learning machine model to obtain prediction data, wherein the prediction data includes predicted independent variable data and dependent variable data; S9, compare the predicted data with each of the monitoring intervals to obtain a comparison result, use the predicted data and the comparison result to update the second digital twin model to obtain a third digital twin model, and realize comprehensive monitoring of the underground goaf area.
2. The method for comprehensive monitoring of underground goaf areas based on digital twins according to claim 1, characterized in that: In step S9, the third digital twin model is dynamically optimized in real time by collecting second sensor data in real time through sensor equipment installed on the wall of the goaf underground.
3. The method for comprehensive monitoring of underground goaf areas based on digital twins according to claim 2, characterized in that: The real-time dynamic optimization of the third digital twin model specifically includes the following steps: A1, collecting second sensor data in real time through a sensor, and preprocessing the second sensor data; A2, comparing the preprocessed second sensing data with the predicted data to obtain a fitting value; A3, comparing the fitting value with a preset threshold; If the fitting value is greater than or equal to the preset threshold, the second sensor data preprocessed in step A1 is subjected to steps S4 to S9 to perform real-time dynamic optimization on the third digital twin model; If the fitting value is less than the preset threshold, the third digital twin model does not need to be optimized.
4. The method for comprehensive monitoring of underground goaf areas based on digital twins according to claim 1, characterized in that: The step S4 specifically includes: Calculate the expected value E(X) and variance σ of each first sensor data in the sample data 2 ∈(0,∞), Based on the expected value and variance of each first sensor data, the maximum deviation probability calculation formula of the first sensor data is expressed as: Based on the maximum deviation probability calculation formula, calculate The λ values when they are equal to 0.1, 0.15 and 0.2 are: λ1, λ2, λ3; Based on the calculated λ1, λ2, and λ3, monitoring intervals are established, namely the first sub-interval (0, λ3+E(X)), the second sub-interval (λ3+E(X), λ2+E(X)), the third sub-interval (λ2+E(X), λ1), and the fourth sub-interval (λ1, +∞).
5. The method for comprehensive monitoring of underground goaf areas based on digital twins according to claim 4, characterized in that: In step S9, the predicted data is set as Xi, and the predicted data is compared with each of the monitoring intervals step by step, including: If the predicted data is in the first sub-interval, i.e., Xi∈(0, λ3+E(X)), the comparison result is that the data is normal, and the monitoring device corresponding to the predicted data under the third digital twin model is displayed in blue. If it is not in the first sub-interval, the comparison continues; If the predicted data is in the second sub-interval, i.e., Xi∈(λ3+E(X), λ2+E(X)), the comparison result is data anomaly, and the monitoring device corresponding to the predicted data under the third digital twin model is displayed in yellow. If it is not in the second sub-interval, the comparison continues; If the predicted data is in the third sub-interval, i.e., Xi∈(λ2+E(X), λ1), a secondary sound and light alarm is issued, and the comparison result is that the data is abnormal. The monitoring device corresponding to the predicted data under the third digital twin model displays orange. If it is not in the third sub-interval, the comparison continues; If the predicted data is in the fourth sub-interval, i.e., Xi∈(λ1, +∞), a first-level sound and light alarm is issued, and the comparison result is that the data is abnormal. Under the third digital twin model, the monitoring equipment corresponding to the predicted data displays red.
6. The method for comprehensive monitoring of underground goaf areas based on digital twins according to claim 3, characterized in that: The preprocessing steps in step S3 or step A1 include, in sequence, performing outlier elimination, replacement, denoising and standardization processing on the first or second sensor data.
7. A comprehensive monitoring system for underground goaf areas based on digital twins, characterized in that: The system comprises: An acquisition module (20) is configured to acquire structural data of a wall of a goaf area underground and first sensor data; The structural data includes: the length, width, height, material and shape data of the wall of the underground goaf area; the first sensor data includes: the surface strain, seepage pressure, drilling stress and water level data of the wall of the underground goaf area; A first construction module (21) is configured to construct a first digital twin model based on the structural data; A data processing module (22) is configured to pre-process the first sensing data, and the processed first sensing data forms sample data; An early warning logic design module (23) is configured to perform early warning logic design on the sample data to obtain a plurality of monitoring intervals; A fusion module (24) is configured to fuse the plurality of monitoring intervals with the first digital twin model to obtain a second digital twin model after fusion; A data partitioning module (25) is configured to partition the sample data into independent variable data and dependent variable data, and to divide the independent variable data and the dependent variable data in proportion to obtain a training set and a validation set; A training module (26) is configured to input the training set into the extreme learning machine model, train the extreme learning machine model, and obtain a trained extreme learning machine model; A prediction module (27) is configured to input the verification set into a trained extreme learning machine model to obtain prediction data, wherein the prediction data includes predicted independent variable data and dependent variable data; The updating module (28) is configured to compare the predicted data with each of the monitoring intervals to obtain a comparison result, and to update the second digital twin model using the predicted data and the comparison result to obtain a third digital twin model, thereby realizing comprehensive monitoring of the underground goaf area.
8. The underground goaf comprehensive monitoring system based on digital twin according to claim 7, characterized in that: The updating module (28) also includes an optimization unit (281) which collects second sensor data in real time by installing a sensor device on the wall of the underground goaf to perform real-time dynamic optimization on the third digital twin model.
9. A computer device, characterized in that: include: processor; A memory for storing executable instructions; Wherein, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the underground goaf comprehensive monitoring method based on digital twins as described in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the underground goaf comprehensive monitoring method based on digital twins as described in any one of claims 1 to 6.
Citation Information
Cited By
Intelligent analysis and early warning method for reservoir seepage pressure data
CN120196983A
A reservoir seepage pressure data intelligent analysis and early warning method
CN120196983B
