Ultrathin coal seam rock burst risk real-time monitoring method based on D-S evidence theory

Abstract

The invention discloses an ultra-thin coal seam rock burst risk real-time monitoring method based on the D-S evidence theory. The method comprises the steps that rock mass mechanical response data information is collected in real time through multi-source mechanical response collaborative sensing equipment; comprehensively evaluating the rock mass impact risk by adopting a comprehensive index analysis method and a bending energy index method; based on the roof separation layer displacement information and the anchor rod stress information, a data driving model is adopted to evaluate the rock mass impact risk; comprehensively evaluating the rock mass impact risk based on a rock mass impact risk evaluation result by adopting a D-S evidence theory; and building an early warning cloud platform for monitoring the rock burst risk of the ultra-thin coal seam in real time by utilizing cloud computing and edge computing modes, wherein the early warning cloud platform is used for querying the impact risk evaluation result in real time. According to the method, impact risk evaluation methods based on an experience-driven model and a data-driven model are mutually fused by adopting a D-S evidence theory, so that the problems of early warning information conflict and the like existing in a single-index threshold model are effectively avoided.

Description

Technical Field

[0001] The present invention relates to the field of coal mine rock burst monitoring and early warning, and in particular to a real-time monitoring method for rock burst risk in an extremely thin coal seam based on DS evidence theory. Background Art

[0002] Rock burst is the main disaster that affects the safe mining of coal mines. The prediction and early warning of rock burst-induced disasters with the help of modern means has become a hot topic at present. Although many mines have introduced rock burst monitoring and early warning platforms, most systems currently only realize cloud visualization of monitoring data, which has the problem of "heavy collection and light analysis". At the same time, the disaster early warning method based on single indicator threshold still occupies the mainstream position, and there are problems such as early warning information conflicts. Summary of the invention

[0003] In view of this, this study, based on the DS evidence theory, integrated the experience-driven model and the data-driven model, and built a rock burst monitoring and early warning cloud platform driven by multi-source data to achieve monitoring and early warning of rock burst risks in fully mechanized mining working faces, thus ensuring the safe development of production work.

[0004] In view of the problems existing in the prior art, the present invention discloses a real-time monitoring method for rock burst risk in an extremely thin coal seam based on DS evidence theory, which specifically comprises the following steps:

[0005] Based on the geological conditions of the mine, multi-source mechanical response collaborative sensing equipment is used to collect rock mass mechanical response data information in real time;

[0006] An empirically driven model based on comprehensive index analysis and bending energy index method is used to comprehensively evaluate rock burst risk.

[0007] The rock impact risk is evaluated using a data-driven model based on the roof delamination displacement information and anchor stress information;

[0008] The DS evidence theory is used to integrate the rock burst risk assessment results of the experience and data-driven model to comprehensively judge the rock burst risk;

[0009] Cloud computing and edge computing are used to build an early warning cloud platform for real-time monitoring of rock burst risks in extremely thin coal seams. The early warning cloud platform is used to query the impact risk assessment results in real time and provide a basis for disaster prevention and control.

[0010] Furthermore, based on the geological conditions of the mine and safety regulations, multi-source mechanical response collaborative sensing equipment is installed. The multi-source mechanical response collaborative sensing equipment includes an anchor stress meter and a roof delamination meter, so as to collect mechanical response information related to stress and displacement of the rock mass.

[0011] Use wired or wireless methods to connect the multi-source mechanical response collaborative sensing equipment to the industrial Internet, configure the MQTT and FTP communication protocols, share the collected rock mechanical response data information, set up a communication protocol matching MQTT and FTP on the early warning cloud platform to receive data, and use the MySQL database to store the data information in the early warning cloud platform.

[0012] Based on the comprehensive index analysis method, the rock burst risk is comprehensively evaluated from two aspects: geological factors and technical factors:

[0013]

[0014] Where W k is the risk index calculated based on the geological factor index (k=1) or the technical factor index (k=2), n k Indicates the number of indicators included in the two factors, w k,i represents the value of the i-th indicator in the two factors, w k,i,max is the maximum score of the ith indicator among the geological factor indicators (k=1) or technical factor indicators (k=2)

[0015] The final evaluation of rock burst risk of the working face is carried out by taking the maximum value

[0016] W c =max(W1,W2)

[0017] Where W c ∈[0,1], is the rock burst risk value of the working face, and the bending energy index U is calculated by the bending energy index method combined with the actual geological conditions of the mine. WQS The probability of rock burst driven by the quantified bending energy index W is calculated by the following empirical formula: b

[0018] W b =0.005U WQS +0.15.

[0019] When evaluating the rock impact risk based on the roof delamination displacement information and anchor stress information: define the failure coefficient index W of the anchor stress gauge used to describe the relationship between the anchor failure state and the impact risk F , the specific expression is modified based on historical cases:

[0020]

[0021] Since the sharp increase in stress of coal rock with impact tendency is the fundamental cause of rock burst disaster, the stress growth rate coefficient is calculated as

[0022]

[0023] where v F is the stress growth coefficient, F2 is the stress value at time t2, F1 is the stress value at time t1, t2-t1 is taken as 1d, and the impact risk value W driven by the stress growth coefficient indicator is analyzed based on historical case data v The empirical expression is:

[0024]

[0025] Correct the data based on actual historical cases of the mine;

[0026] Definition of deformation index W u , using the deformation index W u Quantify the relationship between rock mass deformation and impact risk, where W u The empirical calculation formula is as follows, and the deformation index is corrected by combining the actual historical case data of the mine.

[0027]

[0028] The risk assessment index W obtained by comprehensive index analysis is c , Quantify the probability of rock burst driven by bending energy index W b , failure coefficient index W of anchor stress gauge F , the impact risk value W driven by the stress growth coefficient indicator v And deformation index W u As the basis for data fusion, the mining face is taken as the research object, and the identification framework is determined: Θ = {R1, R2}, where R1 represents the induced rock burst disaster and R2 represents the uninduced rock burst disaster. Based on this identification framework, data fusion processing is carried out to determine the final rock burst risk probability.

[0029] The early warning cloud platform is used to query the multi-source monitoring data of the type and operating status of the mine pressure monitoring equipment, the data evolution trend and the monitoring value of the current specific location measuring point and perform visual display.

[0030] Due to the adoption of the above-mentioned technical scheme, the present invention provides a real-time monitoring method for rock burst risk in extremely thin coal seams based on the DS evidence theory. The method adopts the DS evidence theory to integrate the rock burst risk assessment methods based on the experience-driven model and the data-driven model, thereby effectively avoiding the problems of early warning information conflicts existing in the single indicator threshold model, and realizes the integration of disaster early warning through the early warning cloud platform, reduces the difficulty of data analysis, improves data analysis efficiency, and facilitates users to have a clearer understanding of the stability status of the tunnel, thereby facilitating the improvement of the quality and efficiency of mine safety management and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 Flow chart of the method of the present invention

[0033] Figure 2 The layout diagram of the mine pressure monitoring equipment in the method of the present invention is

[0034] Figure 3 This is the energy index-rock burst probability mapping relationship diagram of the present invention DETAILED DESCRIPTION

[0035] In order to make the technical solutions and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention:

[0036] like Figure 1 A real-time monitoring method for rock burst risk in an extremely thin coal seam based on DS evidence theory is shown, which specifically includes the following steps:

[0037] S1: Combined with the geological conditions of the mine, a multi-source mechanical response collaborative sensing device is installed to collect rock mass mechanical response data in real time. Figure 2 As shown;

[0038] S2: Comprehensively evaluate the impact risk using empirically driven models such as comprehensive index analysis and bending energy index method;

[0039] S3: Combined with monitoring data such as roof delamination displacement and anchor stress, the impact risk is evaluated using a data-driven model;

[0040] S4: Adopt DS evidence theory, integrate the impact risk assessment results driven by the experience-driven model and the data-driven model, and finally achieve a comprehensive assessment of the impact risk;

[0041] S5: Utilize cloud computing, edge computing and other technologies to build a real-time monitoring and early warning cloud platform for rock burst risks in extremely thin coal seams, achieve cloud-based transparency of rock burst risk assessment results, and provide a basis for disaster prevention and control.

[0042] Furthermore, the S1 specifically includes:

[0043] S11: In combination with the geological conditions of the mine and the requirements of safety regulations, install equipment such as anchor (cable) stress gauges and roof separation gauges to collect mechanical responses such as stress and displacement of the rock mass;

[0044] S12: Use network cables, optical fibers or wireless methods to connect sensing devices to the industrial Internet to achieve data transmission, and configure communication protocols such as MQTT and FTP to achieve data sharing;

[0045] S13: Configure the communication protocol matching the above MQTT and FTP on the cloud server to receive the data, and further use the MySQL database to realize the persistent storage of the data in the cloud.

[0046] Further, the S2 includes the following methods:

[0047] Combined with the mining production technology factors and geological factors, the scores of each indicator are determined using Table 1;

[0048] Table 1 Comprehensive index analysis method indicators and evaluation index scores

[0049]

[0050]

[0051] S21: Calculate the impact risk index corresponding to the geological factor index and the mining technical index through formula (1). Where W k is the risk index calculated based on geological factors (k=1) or mining technology factors (k=2), n k Indicates the number of indicators included in the two factors, w k,i represents the value of the i-th indicator in the two factors, w k,i,max It is the maximum score of the i-th indicator in the geological factor (k=1) or mining technology factor (k=2).

[0052]

[0053] S22: Further adopt the maximum value method (Formula 2) to complete the final evaluation of the rock burst risk of the working face. From the structure of Formulas 1 to 2, it can be seen that W c ∈[0,1], and regard it as rock burst risk, such as Figure 3 shown.

[0054] W c =max(W1,W2) (2)

[0055] Furthermore, the S3 specifically includes:

[0056] Based on the calculation method of bending energy index specified in "Measurement, monitoring and prevention of rock burst pressure - Part 1: Classification and technical determination method of rock burst tendency of roof rock", combined with the actual geological conditions of the mine, the bending energy index U WQSThe probability of rock burst driven by bending energy index W is quantified by the empirical formula (Equation 3). b .

[0057] W b =0.005U WQS +0.15 (3)

[0058] Further, the S4: comprises:

[0059] S41: Considering the continuous mining of coal mines, the original stress state of the rock mass is constantly broken, and the tensile stress borne by the anchor rod (cable) is constantly changing, and stress concentration often occurs. When the stress borne by the anchor rod (cable) exceeds the breaking value, it cannot play a supporting role, and there is a great possibility of rock burst disaster. For this reason, the anchor rod failure coefficient W is defined F , which is used to quantify the above physical phenomena. It is worth noting that the formulation of this indicator needs to be combined with the actual engineering geological conditions and the anchor (cable) type and its corresponding breaking value F c , and considering that the impact risk should be between 0 and 1, the present invention calculates the corresponding quantitative W based on historical data F The expression of is shown in formula 4. At the same time, formula 4 can be further modified in combination with historical mining cases.

[0060]

[0061] S42: Considering that the occurrence of rock burst disasters is closely related to the stress environment of the surrounding rock in the mining area, the stress of coal rock with impact tendency usually increases sharply under the disturbance of mining, causing sudden damage, which is the fundamental cause of rock burst disasters. In order to characterize this phenomenon, the stress growth coefficient index is proposed, as shown in formula (5),

[0062]

[0063] In the formula, v F is the stress growth rate (kN / d), F2 is the stress value at time t2, F1 is the stress value at time t1, and t2-t1 is generally 1d. On this basis, the present invention provides the impact risk value W driven by the stress growth rate coefficient indicator through historical case data. v The empirical expression of the calculation is shown in formula (6). Similarly, this indicator can be modified based on the actual historical case data of the mine.

[0064]

[0065] S43: Considering that rock deformation is the most intuitive feature of disasters, almost all factors affecting rock stability will eventually be reflected in the deformation of the rock. Therefore, there must be a close connection between deformation and impact risk. The roof delamination meter is an important means of displacement monitoring. The size of its monitoring value u can truly reflect the deformation state of the roof. Based on its monitoring data, the impact risk can be quantified. In combination with historical case data, the present invention proposes a deformation index W u , quantified the relationship between rock mass deformation and impact risk, W u The empirical calculation formula of is shown in formula (7). Similarly, this indicator can be modified based on the actual historical case data of the mine.

[0066]

[0067] Furthermore, S5 includes: based on the above experience and data-driven impact tendency evaluation results, taking the mining working face as the research object, determining the identification framework: Θ = {R1, R2}, where: R1 represents induced rock burst disaster; R2 represents uninduced rock burst disaster. Based on this identification framework, data fusion processing is carried out.

[0068] The rock burst evaluation indicators extracted from the theoretical model and the data-driven model are selected as evidence sources, and the basic trust distribution is calculated according to the quantitative formula of the evaluation indicators. The Dempster synthesis rule is used for data fusion. During the fusion process, the mass function distribution is shown in Table 2. Taking the stress index as an example, the induced geological disaster W F 1-W without inducing geological disasters F The mass function that constitutes the stress index, the theoretical model and the data-driven model have a total of 5 mass functions, which are used to calculate the impact risk assessment index W through the DS evidence theory f .

[0069] Table 2 Distribution of mass functions of evidence sources

[0070]

[0071] Furthermore, a common architecture is built on cloud platforms such as Vue and Java, and a real-time monitoring and early warning cloud platform for rock burst risk in extremely thin coal seams is developed. Based on the method proposed in steps 2-5, Python is used to develop a data dynamic processing microservice. Data is collected in real time in step 1, and real-time dynamic processing is performed using the methods of steps 2-5. Finally, the processing results are displayed on the cloud platform, where the cloud platform includes the following three aspects: multi-source monitoring data query and visualization display functions that facilitate users to understand the type and operating status of mine pressure monitoring equipment, data evolution trends, and monitoring values ​​of current specific measuring points; report viewing and export functions that facilitate users to understand rock burst risk situations; disaster warning and alarm release functions that facilitate users to learn about rock burst disaster risks at the first time.

[0072] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A real-time monitoring method for rock burst risk in extremely thin coal seams based on DS evidence theory, characterized by: include: Based on the geological conditions of the mine, multi-source mechanical response collaborative sensing equipment is used to collect rock mass mechanical response data information in real time; An empirically driven model based on comprehensive index analysis and bending energy index method is used to comprehensively evaluate rock burst risk. The rock impact risk is evaluated using a data-driven model based on the roof delamination displacement information and anchor stress information; The DS evidence theory is used to integrate the rock burst risk assessment results of the experience and data-driven model to comprehensively judge the rock burst risk; Cloud computing and edge computing are used to build an early warning cloud platform for real-time monitoring of rock burst risks in extremely thin coal seams. The early warning cloud platform is used to query the impact risk assessment results in real time and provide a basis for disaster prevention and control.

2. According to claim 1, a real-time monitoring method for rock burst risk in ultra-thin coal seams based on DS evidence theory is characterized by: Based on the geological conditions of the mine and the requirements of safety regulations, multi-source mechanical response collaborative sensing equipment is installed. The multi-source mechanical response collaborative sensing equipment includes anchor stress gauges and roof delamination gauges, so as to collect mechanical response information related to stress and displacement of the rock mass.

3. The real-time monitoring method for rock burst risk in ultra-thin coal seams based on DS evidence theory according to claim 2 is characterized by: Use wired or wireless methods to connect the multi-source mechanical response collaborative sensing equipment to the industrial Internet, configure the MQTT and FTP communication protocols, share the collected rock mechanical response data information, set up a communication protocol matching MQTT and FTP on the early warning cloud platform to receive data, and use the MySQL database to store the data information in the early warning cloud platform.

4. The real-time monitoring method for rock burst risk in ultra-thin coal seams based on DS evidence theory according to claim 3 is characterized by: Based on the comprehensive index analysis method, the rock burst risk is comprehensively evaluated from two aspects: geological factors and technical factors: Where W k is the risk index calculated based on the geological factor index (k=1) or the technical factor index (k=2), n k Indicates the number of indicators included in the two factors, w k,i represents the value of the i-th indicator in the two factors, w k,i,max The maximum score of the ith indicator in the geological factor index (k = 1) or the technical factor index (k = 2) is used to take the maximum value to make the final evaluation of the rock burst risk of the working face. W c =max(W1,W2) Where W c ∈[0,1], is the rock burst risk value of the working face, and the bending energy index U is calculated by the bending energy index method combined with the actual geological conditions of the mine. WQS The probability of rock burst driven by the quantified bending energy index W is calculated by the following empirical formula: b IN b =0.005U WQS +0.15。 5. The real-time monitoring method for rock burst risk in ultra-thin coal seams based on DS evidence theory according to claim 4 is characterized by: When evaluating the rock impact risk based on the roof delamination displacement information and anchor stress information: define the failure coefficient index W of the anchor stress gauge used to describe the relationship between the anchor failure state and the impact risk F , the specific expression is modified based on historical cases: Since the sharp increase in stress of coal rock with impact tendency is the fundamental cause of rock burst disaster, the stress growth rate coefficient is calculated as where v F is the stress growth coefficient, F2 is the stress value at time t2, F1 is the stress value at time t1, t2-t1 is taken as 1d, and the impact risk value W driven by the stress growth coefficient indicator is analyzed based on historical case data v The empirical expression is: Correct the data based on actual historical cases of the mine; Definition of deformation index W u , using the deformation index W u Quantify the relationship between rock mass deformation and impact risk, where W u The empirical calculation formula is as follows, and the deformation index is corrected by combining the actual historical case data of the mine.

6. The method for real-time monitoring of rock burst risk in ultra-thin coal seams based on DS evidence theory according to claim 5 is characterized by: The risk assessment index W obtained by comprehensive index analysis is c , Quantify the probability of rock burst driven by bending energy index W b , failure coefficient index W of anchor stress gauge F , the impact risk value W driven by the stress growth coefficient indicator v And deformation index W u As the basis for data fusion, the mining face is taken as the research object, and the identification framework is determined: Θ = {R1, R2}, where R1 represents the induced rock burst disaster and R2 represents the uninduced rock burst disaster. Based on this identification framework, data fusion processing is carried out to determine the final rock burst risk probability.

7. A real-time monitoring method for rock burst risk in ultra-thin coal seams based on DS evidence theory according to any one of claims 1 to 6, characterized in that: The early warning cloud platform is used to query the multi-source monitoring data of the type and operating status of the mine pressure monitoring equipment, the data evolution trend and the monitoring value of the current specific location measuring point and perform visual display.

Images