Sensor network-based intelligent monitoring system and method for pillar cracking

Abstract

The present application relates to the technical field of monitoring analysis, and is a pillar cracking intelligent monitoring system and method based on a sensor network, specifically comprising: collecting stress and strain data of a target pillar; constructing a crack propagation prediction model, inputting the stress and strain data of the target pillar into the crack propagation prediction model, and obtaining a three-dimensional risk intensity path of the target pillar; obtaining a stress increment spatial distribution cloud chart; real-time monitoring of hydraulic monitoring data in the crack network, constructing a hydraulic-stress coupling state matrix, fusing the three-dimensional risk intensity path and the stress increment spatial distribution cloud chart, calculating a comprehensive risk index of each pillar to generate a pillar cracking risk map, and executing a pillar cracking risk early warning strategy according to the pillar cracking risk map. The present application solves the problems of low accuracy and lagging early warning of pillar cracking in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring and analysis, and is a sensor network-based intelligent monitoring system and method for pillar cracking. Background Art

[0002] In the field of mine safety monitoring, early warning of pillar cracking is key to preventing rock instability. Traditional methods rely primarily on point sensors (such as strain gauges and displacement gauges) to monitor stress changes in individual pillars or predict crack propagation through static geological models. However, these methods suffer from the following technical bottlenecks: First, there is a lack of implicit tracking of stress redistribution paths. When the bearing capacity of a pillar decreases due to the development of microcracks, the load it bears is dynamically transferred to adjacent pillars or the surrounding rock. This transfer path is influenced by multiple implicit factors, including the stiffness distribution of the surrounding rock, the current stress state of adjacent pillars, and the direction of the geological structural plane. Existing point-based monitoring cannot capture the spatial path and strength gradient of load transfer in real time, leading to misjudgment of the risk of cascading instability. Second, the quantification of the coupling effect of rock micro-vibration and water flow direction is insufficient. The expansion of rock microcracks can alter local seepage pathways and induce groundwater flow deviations. This shift in flow direction (especially when it forms a specific angle with the principal stress direction of the rock mass) significantly accelerates hydraulic fracturing. On the one hand, the water flow, acting perpendicular to the principal stress, abrades the fracture surface by carrying rock debris, reducing the friction coefficient. On the other hand, the high water pressure gradient creates a tensile stress concentration at the crack tip. The synergistic effect of these two factors significantly increases the crack propagation rate in adjacent pillars. Existing technologies only analyze stress or hydrological data in isolation, failing to establish a three-dimensional dynamic coupling model linking flow direction, stress direction, and crack propagation, resulting in delayed early warning. Summary of the Invention

[0003] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0004] The technical problem to be solved by the present invention is that the accuracy of the early warning of pillar cracking is low and the early warning is delayed in the existing technology. An intelligent monitoring system and method for pillar cracking based on a sensor network are proposed.

[0005] In order to achieve the above-mentioned object, the technical solution of the intelligent monitoring method for pillar cracking based on a sensor network of the present invention includes the following steps:

[0006] S1: Collect stress and strain data of the target pillar through distributed optical fiber sensors inside the pillar;

[0007] S2: Construct a crack propagation prediction model, input the stress and strain data of the target pillar into the crack propagation prediction model, and obtain the three-dimensional risk intensity path of the target pillar through discretized node dynamic modeling and risk coefficient quantification;

[0008] S3: Import the three-dimensional risk intensity path into the adjacent pillar stress increment mapping model. Based on the spatial screening mechanism from the pillar boundary to the path node, the final stress increment of all pillars is output to obtain the stress increment spatial distribution cloud map;

[0009] S4: monitoring the hydraulic monitoring data in the fracture network in real time, constructing a hydraulic-stress coupling state matrix, and determining whether to repeat steps S2 and S3 based on the hydraulic-stress coupling state matrix;

[0010] S5: Integrate the three-dimensional risk intensity path and the stress increment spatial distribution cloud map, calculate the comprehensive risk index of each pillar based on the risk coefficient and stress increment of the high-risk nodes in the pillar influence area, generate the pillar cracking risk map and implement the pillar cracking risk warning strategy.

[0011] Furthermore, in S2, the construction of the crack propagation prediction model includes:

[0012] S21: Extract axial stress in rock mass stress monitoring module , shear stress , strain energy density Constructing feature vectors , obtain the stress state characteristic vector set of the target pillar;

[0013] S22: Perform ground stress normalization on the characteristic vector and simultaneously extract the crack precursor feature library from historical pillar cracking events;

[0014] S23: Divide the historical feature vector set into a training set and a test set at a ratio of 7:3, train a crack propagation prediction model, and output the mechanical similarity between the target pillar and the historical cracking event, wherein the crack propagation prediction model adopts a graph convolutional neural network architecture.

[0015] Furthermore, in S2, the construction of the crack propagation prediction model further includes:

[0016] S24: Arrange the mechanical similarity in descending order and intercept the original crack propagation path patterns of the top k historical pillar cracking events with high similarity;

[0017] S25: Obtain the offset of the principal stress direction of the adjacent surrounding rock in historical events Calculate the extreme value of the crack width gradient of the historical pillar cracking event extracted in step S24 before the cracking, and import the extreme value of the crack width gradient into the stress increment calculation model to calculate the stress increment of the adjacent pillars. ;

[0018] wherein, the main stress direction offset is the angle difference between the current main stress direction and the initial ground stress direction;

[0019] S26: extracting the real-time monitored fracture water pressure gradient and the main stress direction angle and importing the hydraulic correction strategy to obtain the hydraulic correction factor ;

[0020] Further, S27 comprises the following specific steps:

[0021] S271: performing spatial path dynamic modeling, comprising: discretizing the fracture propagation path into M nodes, and updating the expansion position parameters of each node, wherein the distance between each node is ;

[0022] S272: calculating the distance from each node to each adjacent pillar and calculating the stress increment at the node, wherein n is the index of the pillar corresponding to the high-similarity historical pillar cracking event, ;

[0023] S273: extracting the hydraulic correction factor in step S26 and the stress increment at the node calculated in step S272, quantifying the node expansion risk intensity to obtain the node risk coefficient;

[0024] S274: extracting the node risk coefficient of each node output in step S273, and comparing the node risk coefficient of each node with the node risk threshold, automatically marking the node greater than or equal to the node risk threshold as a high-risk node, and simultaneously generating a high-risk node set of high-risk nodes ;

[0025] ;

[0026] S275: extracting the high-risk node set and generating a three-dimensional risk intensity path through a cubic B-spline curve fitting.

[0027] Further, S3 comprises the following steps:

[0028] S31: analyzing the spatial coordinates of the three-dimensional risk intensity path, establishing the spatial mapping relationship between the path nodes and the adjacent pillars, calculating the minimum Euclidean distance from each pillar boundary to the path node, and screening the pillars with a minimum Euclidean distance from the pillar boundary to the path node less than three meters as the influence pillars;

[0029] ​S32: Based on the influencing pillars screened out in step S31, a stress increment mapping model for adjacent pillars is established, all influencing pillars are traversed, the final stress increments of all pillars are output, and a stress increment spatial distribution cloud map is obtained.

[0030] Furthermore, S4 includes:

[0031] S41: deploying triaxial flow velocity sensors at high-risk nodes of the three-dimensional risk intensity path output in step S2;

[0032] S42: collecting hydraulic monitoring data at a fixed frequency, wherein the hydraulic monitoring data includes: water pressure gradient and water flow-joint plane angle;

[0033] S43: Based on the hydraulic monitoring data, construct the hydraulic-stress coupling state matrix and calculate the matrix condition number. When , the full-path high-frequency monitoring is triggered, and the hydraulic monitoring data is updated and transmitted to step S2, and steps S2 and S3 are re-executed until the matrix condition number of the hydraulic-stress coupling state matrix is ​​less than 50, then the loop is stopped and step S5 is executed.

[0034] Furthermore, S5 includes:

[0035] S51: Extracting 3D risk intensity path node data and the final stress increments of all the pillars in the stress increment spatial distribution cloud map outputted in step S32;

[0036] S52: Divide the influence area of ​​the pillar and extract the path node set located in the influence area of ​​the pillar;

[0037] S53: Calculate the comprehensive risk index of each pillar based on the path node set;

[0038] S53: Generate a pillar cracking risk map based on the comprehensive risk index of each pillar output in step S52 .

[0039] In addition, the intelligent monitoring system for pillar cracking based on the sensor network of the present invention includes the following modules:

[0040] Rock stress monitoring module, fracture network evolution prediction module, stress redistribution calculation module, hydraulic coupling monitoring module and risk pillar positioning module;

[0041] The rock mass stress monitoring module is used to collect stress and strain data of the target pillar through distributed optical fiber sensors inside the pillar;

[0042] The fracture network evolution prediction module is used to construct a fracture expansion prediction model, input the stress and strain data of the target pillar into the fracture expansion prediction model, and obtain the three-dimensional risk intensity path of the target pillar;

[0043] The stress redistribution calculation module imports the three-dimensional risk intensity path into the adjacent pillar stress increment mapping model, outputs the final stress increment of all pillars, and obtains the stress increment spatial distribution cloud map;

[0044] The hydraulic coupling monitoring module is used to monitor the hydraulic monitoring data in the fracture network in real time and construct a hydraulic-stress coupling state matrix;

[0045] The risk pillar positioning module is used to integrate the three-dimensional risk intensity path and the stress increment spatial distribution cloud map, calculate the comprehensive risk index of each pillar to generate a pillar cracking risk map, and execute the pillar cracking risk early warning strategy according to the pillar cracking risk map.

[0046] A storage medium stores instructions, and when a computer reads the instructions, the computer executes the sensor network-based intelligent monitoring method for pillar cracking.

[0047] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the sensor network-based intelligent monitoring method for pillar cracking is implemented.

[0048] Compared with the prior art, the technical effects of the present invention are as follows:

[0049] This invention significantly improves the accuracy and timeliness of pillar cracking risk warnings. Its most significant benefits are reflected in three aspects: First, it quantifies the dynamic impact of rock micro-motion on water flow direction changes. Using hydraulic correction factors and a coupled state matrix, it systematically captures the key processes by which initial pillar cracking leads to rock structural adjustments, which in turn alter the path and direction of groundwater seepage. Specifically, it quantifies the mechanisms by which changes in the angle between water flow direction and the rock's principal stress accelerate crack propagation (including friction reduction through physical grinding and hydraulic tensile stress concentration), addressing the shortcomings of traditional methods that analyze hydrological and stress data in isolation. Second, the invention accurately predicts the chain failure risk path, constructing a dynamic mapping model of "crack propagation → stress redistribution → load increment in adjacent pillars." By tracking implicit stress transfer through a three-dimensional risk intensity path and combining the current state (stiffness, stress) of adjacent pillars with real-time water flow direction changes, it accurately calculates a comprehensive risk index for each pillar. This allows reliable identification of high-risk pillars most likely to undergo secondary cracking in a chain reaction and their spatial distribution, thus overcoming the previous bottleneck of inaccurate prediction of cascading instability. At the same time, this invention significantly improves the speed and reliability of early warning responses. A real-time sensitivity determination mechanism based on the hydraulic-stress coupling state matrix automatically triggers high-frequency monitoring and iterative model updates when the system enters a critical instability state (where small perturbations lead to drastic output changes). This dynamic closed-loop optimization ensures that the risk map is instantly updated as rock mass micro-movements and water flow conditions change, shortening early warning response time from hours to minutes. It also provides a high-confidence basis for decision-making in tiered control strategies (such as personnel evacuation and enhanced monitoring), effectively preventing large-scale rock mass instability accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0051] Figure 1 Schematic diagram of the process of the intelligent monitoring method for pillar cracking based on the sensor network of the present invention;

[0052] Figure 2 Schematic diagram of the process of step S4 of the present invention;

[0053] Figure 3 The diagram is a structural diagram of the intelligent monitoring system for pillar cracking based on a sensor network of the present invention. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0055] 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 different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0056] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0057] Example 1:

[0058] like Figure 1 As shown, the intelligent monitoring method for pillar cracking based on sensor network of the embodiment of the present invention is as follows: Figure 1 As shown, the specific steps are as follows:

[0059] S1: Collect stress and strain data of the target pillar through distributed optical fiber sensors inside the pillar;

[0060] S2: Construct a crack propagation prediction model, input the stress and strain data of the target pillar into the crack propagation prediction model, and obtain the three-dimensional risk intensity path of the target pillar through discretized node dynamic modeling and risk coefficient quantification;

[0061] In S2, the construction of the crack propagation prediction model includes:

[0062] S21: Extract axial stress in rock mass stress monitoring module , shear stress , strain energy density Constructing feature vectors , obtain the stress state characteristic vector set of the target pillar;

[0063] S22: Perform ground stress normalization on the characteristic vector and simultaneously extract the crack precursor feature library from historical pillar cracking events;

[0064] S23: Divide the historical feature vector set into a training set and a test set at a ratio of 7:3, train a crack propagation prediction model, and output the mechanical similarity between the target pillar and the historical cracking event, wherein the crack propagation prediction model adopts a graph convolutional neural network architecture.

[0065] S24: Arrange the mechanical similarity in descending order and intercept the original crack propagation path patterns of the top k historical pillar cracking events with high similarity;

[0066] S25: Obtain the offset of the principal stress direction of the adjacent surrounding rock in historical events Calculate the extreme value of the crack width gradient of the historical pillar cracking event extracted in step S24 before the cracking, and import the extreme value of the crack width gradient into the stress increment calculation model to calculate the stress increment of the adjacent pillars. ;

[0067] Among them, the principal stress direction offset is the angle difference between the current principal stress direction and the initial ground stress direction;

[0068] For example, in this embodiment, a strategy for obtaining the stress increment of adjacent pillars is provided, specifically:

[0069] ;

[0070] in, is the stress increment of the nth adjacent pillar;

[0071] is the extreme value of the crack width gradient before the historical pillar cracking event, that is, the maximum change rate of the crack width along the path direction;

[0072] The mechanical similarity of the nth adjacent pillar output by the crack propagation prediction model;

[0073] are the crack width conductivity coefficient and the mechanical similarity conductivity coefficient respectively;

[0074] For the stress increment of the adjacent pillars in this embodiment The acquisition strategy aims to solve the problem of crack morphology-stress direction coupling in the existing technology, in which the extreme value of the crack width gradient reflects the energy release intensity, while the offset of the principal stress direction indicates the load transfer direction;

[0075] For example, in this embodiment, a strategy for obtaining the extreme value of the crack width gradient is further provided, specifically: ,in, is the crack width, It is the crack extension path. It should be noted that, in this embodiment, the calculation of the extreme value of the crack width gradient is based on the Irwin crack tip model, which aims to accurately locate the active area of ​​crack expansion. It represents the maximum value of the crack width change rate on the crack extension path. The larger the value, the sudden widening of the crack at a certain point, which means that this place is a stress concentration point, which has a significant impact on the stress transfer of the adjacent pillars.

[0076] S26: Extracting real-time monitoring of fracture water pressure gradients and the angle between the flow and the joint surface , and import it into the hydraulic correction strategy to obtain the hydraulic correction factor ;

[0077] For example, in this embodiment, a hydraulic correction strategy is provided, specifically:

[0078] ;

[0079] in, is the hydraulic correction factor; is the hydraulic coupling correction coefficient; is the baseline water pressure value of the mine water body; is the characteristic length of the crack;

[0080] It should be noted that when the angle between the water flow direction and the maximum principal stress direction of the rock mass (i.e. the normal direction of the joint surface) reaches 90 degrees (i.e. the water flow acts perpendicularly to the principal stress direction), =1, the hydraulic fracturing effect reaches its peak. Driven by high-pressure water flow, fine rock debris carried by the water body invades the fracture surface, significantly reducing the friction coefficient of the fracture surface through physical grinding and lubrication. At the same time, the high water pressure gradient produces a strong tensile stress concentration at the crack tip, causing the effective stress intensity factor at the crack tip to exceed the fracture toughness of the rock mass. These two mechanisms work synergistically: the decrease in the friction coefficient weakens the shear resistance of the fracture surface, while the water pressure tensile stress directly drives the crack expansion, resulting in a rapid increase in the crack expansion rate. The hydraulic correction strategy in this embodiment accurately captures the critical state of hydraulic fracturing by quantifying the coupling effect of the water flow direction angle and the water pressure gradient, which helps to achieve advanced warning of rock instability.

[0081] S27 includes the following specific steps:

[0082] S271: Execute spatial path dynamic modeling, including: discretizing the crack expansion path into M nodes, updating the expansion position parameters of each node, where the distance between each node is ;

[0083] For example, in this embodiment, an extended position parameter of the jth node is provided. The update strategy is as follows:

[0084] ;

[0085] in, and are the extended position parameters of the j-th node and the j-1-th node respectively;

[0086] is the crack extension direction angle, which is the angle between the horizontal crack extension direction and the x-axis obtained by interpolation of the monitoring point data, and represents the main direction of crack extension determined by the stress field; is the elevation-water pressure coupling coefficient, is the fracture water pressure gradient at the jth node;

[0087] For example, in this embodiment, there is also provided a The acquisition strategy is as follows:

[0088] ;

[0089] in, is the angle between the principal stress direction of the monitoring point and the crack surface; is the hydraulic correction factor of monitoring point i; is the distance from node j to the i-th monitoring point,

[0090] It should be noted that the direction angle is obtained by weighted average of the direction angles of neighboring monitoring points, and the weight is inversely proportional to the square of the distance, that is, monitoring points that are close and have active expansion have a greater impact on the direction.

[0091] S272: Count the distances from each node to each adjacent pillar and calculate the stress increment at the node, where n is the index of the pillar number corresponding to the historical pillar cracking event with high similarity. ;

[0092] For example, in this embodiment, a calculation strategy for the stress increment at a node is provided, specifically: ;

[0093] in, is the sum of the stress increments at node j for k historical events; is the stress increment of the nth adjacent pillar on node j;

[0094] In this embodiment, , is the stress increment of the nth adjacent pillar output in step S25; is the distance from the jth node to the nth adjacent pillar; D is the average distance from the jth node to all adjacent pillars;

[0095] It should be noted that stress transfer decays exponentially with distance, which is similar to the attenuation law in elastic mechanics. The calculation strategy of the stress increment at the node in this embodiment is intended to take into account the impact of multiple historical events on the current node. The closer the distance, the greater the impact.

[0096] S273: extracting the hydraulic correction factor in step S26 and the stress increment at the node calculated in step S272, quantifying the node expansion risk intensity, and obtaining a node risk coefficient;

[0097] For example, in this embodiment, a strategy for obtaining a node risk coefficient is further provided, specifically:

[0098] ;

[0099] in, is the node risk coefficient at node j; is the hydraulic correction factor at node j; is the angle between the water flow direction and the principal stress direction at node j;

[0100] It should be noted that the hydraulic driving term reflects the accelerating effect of water pressure on crack expansion; , which reflects the amplification effect of stress increment on risk. The greater the stress, the exponential growth of risk index. is the direction stability term, when =45 degrees, the term is 1 (i.e. maximum), when = 0 degrees or 90 degrees, the term is 0.5 (i.e., minimum). This is because when the water flow direction is 45 degrees to the principal stress, based on the Coulomb criterion, the shear stress is maximum, which is most likely to cause crack sliding and expansion.

[0101] S274: Extract the node risk coefficient of each node output in step S273, and combine the node risk coefficient of each node with the node risk threshold Compare and automatically mark nodes with risk greater than or equal to the node risk threshold as high-risk nodes, and simultaneously generate a high-risk node set for high-risk nodes. ;

[0102] ;

[0103] S275: Extract high-risk node set A three-dimensional risk intensity path is generated by cubic B-spline curve fitting.

[0104] S3: Import the three-dimensional risk intensity path into the adjacent pillar stress increment mapping model. Based on the spatial screening mechanism from the pillar boundary to the path node, the final stress increment of all pillars is output to obtain the stress increment spatial distribution cloud map;

[0105] S31: Analyze the spatial coordinates of the three-dimensional risk intensity path, establish the spatial mapping relationship between the path nodes and the adjacent pillars, calculate the minimum Euclidean distance from each pillar boundary to the path node, and select the pillars whose minimum Euclidean distance from the pillar boundary to the path node is less than three meters as the influencing pillars;

[0106] S32: Based on the influencing pillars screened out in step S31, a stress increment mapping model for adjacent pillars is established, all influencing pillars are traversed, the final stress increments of all pillars are output, and a stress increment spatial distribution cloud map is obtained.

[0107] For example, in this embodiment, a strategy for outputting the final stress increments of all pillars is provided, specifically:

[0108] ;

[0109] in, is the final stress increment of the nth pillar; is the stress increment of the nth adjacent pillar output in step S25;

[0110] is the number of path nodes that affect pillar n; is the distance from the node to the centroid of the pillar; is the distance attenuation coefficient;

[0111] In this embodiment, the distance attenuation coefficient is calibrated through multiple sets of rock mechanics experiments. Specifically, ;

[0112] It should be noted that, in this embodiment, the output strategy of the final stress increment of all pillars is intended to quantify the additional stress borne by adjacent pillars due to crack expansion. The specific output logic is: for each influencing pillar, traverse all its influencing nodes and calculate the final stress increment of all pillars. The stress contribution of each node j to pillar n is (Take node j as an example), the closer the node is to the pillar, the greater its contribution is, divided by the total number of nodes , that is, take the average value as the final stress increment.

[0113] like Figure 2 As shown, S4: real-time monitoring of hydraulic monitoring data in the fracture network, constructing a hydraulic-stress coupling state matrix, and judging whether it is necessary to repeat steps S2 and S3 according to the hydraulic-stress coupling state matrix;

[0114] S41: deploying triaxial flow velocity sensors at high-risk nodes of the three-dimensional risk intensity path output in step S2;

[0115] It should be noted that high-risk nodes are active areas of fracture expansion and hydraulic parameters need to be monitored.

[0116] S42: collecting hydraulic monitoring data at a fixed frequency, wherein the hydraulic monitoring data includes: water pressure gradient and water flow-joint plane angle;

[0117] S43: Based on the hydraulic monitoring data, construct the hydraulic-stress coupling state matrix and calculate the matrix condition number. When , it indicates that the system is in a sensitive state (that is, a small disturbance causes a drastic change in output), triggering full-path high-frequency monitoring, and updating the hydraulic monitoring data before transmitting it to step S2. Steps S2 and S3 are re-executed until the matrix condition number of the hydraulic-stress coupling state matrix is ​​less than 50. The loop is stopped and step S5 is executed.

[0118] It should be noted that by triggering full-path high-frequency monitoring, we can effectively capture signs of instability and provide early warning.

[0119] For example, in this embodiment, a specific construction strategy of the hydraulic-stress coupling state matrix H is provided:

[0120] ;

[0121] Where M is the number of monitoring points; represents the stress increment at the monitoring point M;

[0122] is the water pressure gradient at the monitoring point M; is the water flow-joint surface angle at the monitoring point M.

[0123] It should be noted that the first line is intended to represent that when the water flow direction is perpendicular to the joint surface (i.e. the water flow-joint surface angle is 90 degrees), =1, the hydraulic fracturing effect is the strongest, which quantifies the driving force of hydraulic fracturing; the second row is intended to reflect the local stress situation.

[0124] S5: Integrate the three-dimensional risk intensity path and the stress increment spatial distribution cloud map, calculate the comprehensive risk index of each pillar based on the risk coefficient and stress increment of the high-risk nodes in the pillar influence area, generate the pillar cracking risk map and implement the pillar cracking risk warning strategy.

[0125] S51: Extracting 3D risk intensity path node data and the final stress increments of all the pillars in the stress increment spatial distribution cloud map outputted in step S32;

[0126] S52: Divide the influence area of ​​the pillar and extract the path node set located in the influence area of ​​the pillar;

[0127] For example, in this embodiment, taking pillar n as an example, the affected area of ​​pillar n is , wherein the influence area of ​​the pillar n Including: taking the center of the pillar as the origin, the radius sphere;

[0128] Extract the impact area located at pillar n The path node set within , where the path node set Specifically: ;

[0129] S53: Calculate the comprehensive risk index of each pillar based on the path node set;

[0130] For example, in this embodiment, taking pillar n as an example, a calculation strategy for the comprehensive risk index of pillar n is provided, specifically:

[0131] ;

[0132] in, is the comprehensive risk index of pillar n;

[0133] A set of path nodes The total number of medium and high risk nodes; The node risk coefficient of node j output in step S273;

[0134] The final stress increments of all the pillars in the stress increment spatial distribution cloud map output in step S32; is the compressive strength of pillar n;

[0135] S53: Generate a pillar cracking risk map based on the comprehensive risk index of each pillar output in step S52 .

[0136] For example, in this embodiment, a strategy for generating a pillar cracking risk map is provided, specifically:

[0137] ;

[0138] in, is the spatial influence function of pillar n, N is the total number of pillars;

[0139] In this embodiment, the spatial influence function of pillar n is Specifically:

[0140] ;

[0141] in, is the center coordinate of pillar n;

[0142] It should be noted that the risk index of each pillar is determined by the risk intensity of the path nodes located in its influence area and the stress increment of the pillar itself;

[0143] In this embodiment, the discrete pillar risk index is interpolated into a continuous spatial risk map by using a Gaussian kernel function. The Gaussian kernel function is a commonly used spatial interpolation method in the prior art and complies with the distance attenuation principle.

[0144] For example, in this embodiment, a hierarchical early warning strategy is also implemented according to the risk map, specifically including:

[0145] Extracting pillar cracking risk maps , find the pillar cracking risk map When the maximum risk value is greater than 2, a red alert is activated and personnel are evacuated; when the maximum risk value is greater than or equal to 1.6 but less than 2, an orange alert is activated and the monitoring frequency of the sensor network is increased to 1.5 times the current frequency; when the maximum risk value is less than 1.6, a yellow alert is activated and hydraulic parameter recalibration is started.

[0146] Example 2:

[0147] like Figure 3 As shown, the intelligent monitoring system for pillar cracking based on sensor network in the embodiment of the present invention is as follows: Figure 3 As shown, it includes the following modules:

[0148] Rock stress monitoring module, fracture network evolution prediction module, stress redistribution calculation module, hydraulic coupling monitoring module and risk pillar positioning module;

[0149] The rock mass stress monitoring module is used to collect stress and strain data of the target pillar through distributed optical fiber sensors inside the pillar;

[0150] The fracture network evolution prediction module is used to construct a fracture expansion prediction model, input the stress and strain data of the target pillar into the fracture expansion prediction model, and obtain the three-dimensional risk intensity path of the target pillar;

[0151] The stress redistribution calculation module imports the three-dimensional risk intensity path into the adjacent pillar stress increment mapping model, outputs the final stress increment of all pillars, and obtains the stress increment spatial distribution cloud map;

[0152] The hydraulic coupling monitoring module is used to monitor the hydraulic monitoring data in the fracture network in real time and construct a hydraulic-stress coupling state matrix;

[0153] The risk pillar positioning module is used to integrate the three-dimensional risk intensity path and the stress increment spatial distribution cloud map, calculate the comprehensive risk index of each pillar to generate a pillar cracking risk map, and execute the pillar cracking risk early warning strategy according to the pillar cracking risk map.

[0154] Example 3:

[0155] This embodiment provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0156] The processor executes the above-mentioned intelligent monitoring method for pillar cracking based on the sensor network by calling the computer program stored in the memory.

[0157] This electronic device may vary significantly depending on its configuration or performance. It may include one or more processors (Central Processing Units, CPUs) and one or more memories. The memories may store at least one computer program, which is loaded and executed by the processor to implement the sensor network-based intelligent monitoring method for pillar cracking provided in the above-described method embodiment. The electronic device may also include other components for implementing its functions. For example, the electronic device may include a wired or wireless network interface and input / output interfaces for data input and output. This embodiment will not be described in detail here.

[0158] Example 4:

[0159] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0160] When the computer program is run on a computer device, the computer device is enabled to execute the above-mentioned intelligent monitoring method for pillar cracking based on a sensor network.

[0161] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0162] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0163] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0164] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0165] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0166] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0167] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0169] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0170] In the description of the present specification, the description referring to the terms "one embodiment", "an example", "a specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0171] The basic principles and main features of the present application and the advantages of the present application are shown and described above. It should be understood by those skilled in the art that the present application is not limited by the above embodiments, and the above embodiments and descriptions in the specification are only illustrative of the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. An intelligent monitoring method for pillar cracking based on a sensor network, characterized in that: The method comprises: S1: Collect stress and strain data of the target pillar through distributed optical fiber sensors inside the pillar; S2: Construct a crack propagation prediction model, input the stress and strain data of the target pillar into the crack propagation prediction model, and obtain the three-dimensional risk intensity path of the target pillar through discretized node dynamic modeling and risk coefficient quantification; S3: Import the three-dimensional risk intensity path into the adjacent pillar stress increment mapping model. Based on the spatial screening mechanism from the pillar boundary to the path node, the final stress increment of all pillars is output to obtain the stress increment spatial distribution cloud map; S4: monitoring the hydraulic monitoring data in the fracture network in real time, constructing a hydraulic-stress coupling state matrix, and determining whether to repeat steps S2 and S3 based on the hydraulic-stress coupling state matrix; S5: Integrate the three-dimensional risk intensity path and the stress increment spatial distribution cloud map, calculate the comprehensive risk index of each pillar based on the risk coefficient and stress increment of the high-risk nodes in the pillar influence area, generate the pillar cracking risk map and implement the pillar cracking risk warning strategy.

2. The intelligent monitoring method for pillar cracking based on a sensor network according to claim 1, characterized in that: In S2, the construction of the crack propagation prediction model includes: S21: Extract axial stress in rock mass stress monitoring module , shear stress , strain energy density Constructing feature vectors , obtain the stress state characteristic vector set of the target pillar; S22: Perform ground stress normalization on the characteristic vector and simultaneously extract the crack precursor feature library from historical pillar cracking events; S23: Divide the historical feature vector set into a training set and a test set at a ratio of 7:3, train a crack propagation prediction model, and output the mechanical similarity between the target pillar and the historical cracking event, wherein the crack propagation prediction model adopts a graph convolutional neural network architecture.

3. The intelligent monitoring method for pillar cracking based on sensor network according to claim 2 is characterized in that: In S2, the construction of the crack expansion prediction model further includes: S24: Arrange the mechanical similarity in descending order and intercept the original crack propagation path patterns of the top k historical pillar cracking events with high similarity; S25: Obtain the offset of the principal stress direction of the adjacent surrounding rock in historical events Calculate the extreme value of the crack width gradient of the historical pillar cracking event extracted in step S24 before the cracking, and import the extreme value of the crack width gradient into the stress increment calculation model to calculate the stress increment of the adjacent pillars. ; Among them, the principal stress direction offset is the angle difference between the current principal stress direction and the initial ground stress direction; S26: Extracting real-time monitoring of fracture water pressure gradients Angle with the principal stress direction , and import it into the hydraulic correction strategy to obtain the hydraulic correction factor .

4. The intelligent monitoring method for pillar cracking based on a sensor network according to claim 3 is characterized in that: S27 includes the following specific steps: S271: Execute spatial path dynamic modeling, including: discretizing the crack expansion path into M nodes, updating the expansion position parameters of each node, where the distance between each node is ; S272: Count the distances from each node to each adjacent pillar , and calculate the stress increment at the node, where n is the index of the pillar number corresponding to the historical pillar cracking event with high similarity, ; S273: extracting the hydraulic correction factor in step S26 and the stress increment at the node calculated in step S272, quantifying the node expansion risk intensity, and obtaining a node risk coefficient; S274: Extract the node risk coefficient of each node output in step S273, and compare the node risk coefficient of each node with the node risk threshold, automatically mark the nodes greater than or equal to the node risk threshold as high-risk nodes, and synchronously generate a high-risk node set of high-risk nodes ; ； S275: Extract high-risk node set A three-dimensional risk intensity path is generated by cubic B-spline curve fitting.

5. The intelligent monitoring method for pillar cracking based on sensor network according to claim 4 is characterized in that: S3 includes the following steps: S31: Analyze the spatial coordinates of the three-dimensional risk intensity path, establish the spatial mapping relationship between the path nodes and the adjacent pillars, calculate the minimum Euclidean distance from each pillar boundary to the path node, and select the pillars whose minimum Euclidean distance from the pillar boundary to the path node is less than three meters as the influencing pillars; S32: Based on the influencing pillars screened out in step S31, a stress increment mapping model for adjacent pillars is established, all influencing pillars are traversed, the final stress increments of all pillars are output, and a stress increment spatial distribution cloud map is obtained.

6. The intelligent monitoring method for pillar cracking based on a sensor network according to claim 5, characterized in that S4 include: S41: deploying triaxial flow velocity sensors at high-risk nodes of the three-dimensional risk intensity path output in step S2; S42: collecting hydraulic monitoring data at a fixed frequency, wherein the hydraulic monitoring data includes: water pressure gradient and water flow-joint plane angle; S43: Based on the hydraulic monitoring data, construct the hydraulic-stress coupling state matrix and calculate the matrix condition number. When , the full-path high-frequency monitoring is triggered, and the hydraulic monitoring data is updated and transmitted to step S2, and steps S2 and S3 are re-executed until the matrix condition number of the hydraulic-stress coupling state matrix is ​​less than 50, then the loop is stopped and step S5 is executed.

7. The intelligent monitoring method for pillar cracking based on a sensor network according to claim 6, characterized in that S5 include: S51: Extracting 3D risk intensity path node data and the final stress increments of all the pillars in the stress increment spatial distribution cloud map outputted in step S32; S52: Divide the influence area of ​​the pillar and extract the path node set located in the influence area of ​​the pillar; S53: Calculate the comprehensive risk index of each pillar based on the path node set; S53: Generate a pillar cracking risk map based on the comprehensive risk index of each pillar output in step S52 .

8. A sensor network-based intelligent monitoring system for pillar cracking, used to implement the sensor network-based intelligent monitoring method for pillar cracking according to any one of claims 1 to 7, characterized in that: The system includes the following modules: Rock mass stress monitoring module, fracture network evolution prediction module, stress redistribution calculation module, hydraulic coupling monitoring module and risk pillar positioning module; The rock mass stress monitoring module is used to collect stress and strain data of the target pillar through distributed optical fiber sensors inside the pillar; The fracture network evolution prediction module is used to construct a fracture expansion prediction model, input the stress and strain data of the target pillar into the fracture expansion prediction model, and obtain the three-dimensional risk intensity path of the target pillar; The stress redistribution calculation module imports the three-dimensional risk intensity path into the adjacent pillar stress increment mapping model, outputs the final stress increment of all pillars, and obtains the stress increment spatial distribution cloud map; The hydraulic coupling monitoring module is used to monitor the hydraulic monitoring data in the fracture network in real time and construct a hydraulic-stress coupling state matrix; The risk pillar positioning module is used to integrate the three-dimensional risk intensity path and the stress increment spatial distribution cloud map, calculate the comprehensive risk index of each pillar to generate a pillar cracking risk map, and execute the pillar cracking risk early warning strategy according to the pillar cracking risk map.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the sensor network-based intelligent monitoring method for pillar cracking according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: a memory for storing instructions; The processor is configured to execute the instruction so that the device performs the operation of implementing the intelligent monitoring method for pillar cracking based on a sensor network as described in any one of claims 1 to 7.

Images