TBM tunnel rock burst early warning method and system based on multi-source information fusion

Abstract

The invention discloses a TBM tunnel rockburst early warning method and system based on multi-source information fusion. The method comprises the steps that micro-seismic information, stress field information, rock mass structure information, TBM construction information and multi-cavern group space relation information are obtained; based on the TBM construction information and the multi-cavern group space relation information, denoising the obtained micro-seismic information through a dynamic Bayesian network; and fusing the denoised micro-seismic information, stress field information and rock mass structure information to carry out multi-element and multi-factor tunnel rockburst risk assessment. According to the method, the collected micro-seismic information is denoised by using the TBM construction information and the multi-cavern group spatial relationship information, so that the signal-to-noise ratio of the micro-seismic information is improved; according to the method, the de-noised micro-seismic information, the de-noised stress field information and the de-noised rock mass structure information are fused, comprehensive assessment of the multi-element and multi-factor tunnel rockburst risk is carried out, misjudgment possibly brought by a single data source is avoided, and the rockburst risk can be assessed more comprehensively.

Description

Technical Field

[0001] This application belongs to the technical field of tunnel engineering, and specifically relates to a TBM tunnel rockburst early warning method and system based on multi-source information fusion. Background Art

[0002] During the construction of tunnel boring machine (TBM) tunnels, rockburst is a common rock mass dynamic disaster, usually caused by deep rock mass burial, high in-situ stress, and tunnel excavation disturbance. The occurrence of rockburst not only threatens the safety of construction workers, but also may have a serious impact on equipment and project progress. Therefore, accurate early warning of rockburst is of great significance for ensuring the safety of tunnel construction.

[0003] However, due to the limitations of single indicators, construction noise interference, diverse geological conditions, etc., traditional rockburst early warning methods are difficult to meet the requirements of high precision and real-time performance. Summary of the Invention

[0004] In order to solve the problem that traditional rockburst early warning methods are difficult to meet the requirements of high precision and real-time performance due to the limitations of single indicators, construction noise interference, diverse geological conditions, etc., this application proposes a TBM tunnel rockburst early warning method and system based on multi-source information fusion. This application uses multi-source data (microseismic, stress, rock mass structure, TBM construction) for comprehensive evaluation, avoiding misjudgments that may be caused by single data, and being able to more comprehensively evaluate rockburst risks.

[0005] This application is realized through the following technical solutions:

[0006] A TBM tunnel rockburst early warning method based on multi-source information fusion, comprising:

[0007] Obtain microseismic information, stress field information, rock mass structure information, TBM construction information, and multi-chamber group spatial relationship information respectively;

[0008] Based on the TBM construction information and the multi-chamber group spatial relationship information, denoise the obtained microseismic information through a dynamic Bayesian network;

[0009] Fuse the denoised microseismic information, stress field information, and rock mass structure information for multi-source and multi-factor tunnel rockburst risk assessment.

[0010] In some embodiments, the denoising of the obtained microseismic information through a dynamic Bayesian network based on the TBM construction information and the multi-chamber group spatial relationship information includes:

[0011] In the dynamic Bayesian network, combine the multi-chamber group spatial relationship information to construct a spatial relationship model describing noise propagation:

[0012]

[0013] Adjust the observation model of the dynamic Bayesian network using the C matrix:

[0014]

[0015] Add the spatio-temporal coupling characteristics of the noise between chambers to the state transition model, add state variables for noise interaction, and describe the vibration coupling effect between multiple chambers:

[0016] X t = [S t , N t

[0017] Describe the joint dynamic changes of microseismic signals and noise:

[0018]

[0019] Use the spatial relationship information of the chamber group to perform spatio-temporal filtering on the vibration signal to enhance the significance of the microseismic signal;

[0020] where d ij is the Euclidean distance between chamber i and chamber j; α is the attenuation coefficient; C ij is the spatial interaction term of the noise; S t is the state of the true microseismic signal; N t is the spatio-temporal coupling state of the noise between chambers; F is the state transition matrix, including the time series relationship between the signal and the noise; Q t is the state noise covariance matrix; X t is the state of the true microseismic signal at time t; X t-1 is the state of the true microseismic signal at time t - 1, used to predict the state at time t; O t is the microseismic signal observed at time t; R t is the observation noise covariance matrix; H t is the observation matrix, describing the linear relationship between the observation variable and the state variable, where the observation variable is the actually monitored microseismic signal, vibration and noise signals, and the state variable is the characteristic quantity of microseismic information, TBM construction information and multi-chamber group spatial information; P(O t |X t ) is the observation model, indicating the probability distribution of the observed microseismic signal O t under the condition that the true microseismic signal X t is known; represents the normal distribution.

[0021] ​In some embodiments, based on the TBM construction information and the spatial relationship information of the multi-chamber group, denoising the acquired microseismic information through a dynamic Bayesian network further includes:

[0022] Using the state at the previous moment, predicting the true microseismic signal distribution at the current moment through a state transition model:

[0023]

[0024] Combining the observation data and updating the prediction result using an observation model:

[0025]

[0026] where K t is the Kalman gain matrix, which is used to balance the weights of the predicted value and the observed value; is the prior prediction state at time t, which is the predicted value of the microseismic signal deduced according to the previous moment X t-1 ; is the prior covariance matrix at time t; f(·) is the state transition model; θ is the parameter of the state transition model.

[0027] In some embodiments, it further includes:

[0028] Performing backward smoothing on the entire time series of microseismic signal prediction:

[0029]

[0030] where

[0031]

[0032] where is the estimated state after backward smoothing, and A t is the smoothing gain matrix.

[0033] In some embodiments, respectively acquiring the microseismic information, stress field information, rock mass structure information, TBM construction information, and the spatial relationship information of the multi-chamber group includes:

[0034] Arranging an optical fiber sensor array on the tunnel wall, the rock mass in front of the tunnel heading face, geological faults or fracture zones to acquire the microseismic information;

[0035] And / or, obliquely arranging borehole stress gauges on both sides and the top of the tunnel to acquire the stress field information;

[0036] And / or, acquiring the rock mass structure information through geological radar, core drilling, and underground three-dimensional imaging technology; the rock mass structure information includes fracture distribution, joint direction, and rock strength.

[0037] In some embodiments, the multi - factor tunnel rockburst risk assessment by integrating the denoised microseismic information, stress field information, and rock mass structure information includes:

[0038] Input the denoised microseismic information, stress field information, and rock mass structure information into a pre - established multi - risk assessment model;

[0039] The multi - risk assessment model calculates the probability of rockburst occurrence based on the characteristic quantities of the input position information, stress field information, and rock mass structure information;

[0040] The multi - risk assessment model outputs the rockburst risk level according to the risk threshold.

[0041] In a second aspect, the present application also proposes a TBM tunnel rockburst early warning device based on multi - source information fusion, including:

[0042] An acquisition unit for respectively acquiring microseismic information, stress field information, rock mass structure information, TBM construction information, and multi - chamber group spatial relationship information;

[0043] A value - taking unit for denoising the acquired microseismic information through a dynamic Bayesian network based on the TBM construction information and multi - chamber group spatial relationship information;

[0044] And an evaluation unit for performing multi - factor tunnel rockburst risk assessment by integrating the denoised microseismic information, stress field information, and rock mass structure information.

[0045] In a third aspect, the present application also proposes a TBM tunnel rockburst early warning system based on multi - source information fusion, including: an input device, an output device, a processor, and a memory connected by a bus;

[0046] The processor is used to execute the following steps by calling the operation instructions stored in the memory:

[0047] Respectively acquire microseismic information, stress field information, rock mass structure information, TBM construction information, and multi - chamber group spatial relationship information;

[0048] Based on the TBM construction information and multi - chamber group spatial relationship information, denoise the acquired microseismic information through a dynamic Bayesian network;

[0049] Integrate the denoised microseismic information, stress field information, and rock mass structure information for multi - factor tunnel rockburst risk assessment.

[0050] Fourth aspect, the present application also provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned TBM tunnel rockburst early warning method based on multi-source information fusion are implemented.

[0051] Fifth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned TBM tunnel rockburst early warning method based on multi-source information fusion are implemented.

[0052] For a TBM tunnel rockburst early warning method based on multi-source information fusion provided by the present application, first, the collected microseismic information is denoised by using TBM construction information and multi-chamber group spatial relationship information. Based on the dynamic Bayesian network and combined with the spatial relationship model, time series data is modeled and the noise characteristics are identified, which improves the signal-to-noise ratio of the microseismic information and provides more accurate and reliable microseismic information for the subsequent rockburst risk assessment steps. Then, the denoised microseismic information, stress field information, and rock mass structure information are fused to comprehensively evaluate the multi-source and multi-factor tunnel rockburst risk, avoiding misjudgments that may be caused by a single data source and being able to more comprehensively evaluate the rockburst risk.

[0053] The TBM tunnel rockburst early warning method based on multi-source information fusion provided by the present application can also collect data in real time and dynamically adjust the evaluation strategy, automatically optimize the risk assessment according to different geological conditions and construction states during the construction process, ensuring its real-time performance and applicability.

[0054] Correspondingly, a TBM tunnel rockburst early warning device, system, electronic device, and computer-readable storage medium provided by the present application also have the above technical effects. Description of the Drawings

[0055] The drawings described herein are used to provide a further understanding of the embodiments of the present application, form a part of the present application, and do not limit the embodiments of the present application. In the drawings:

[0056] Figure 1 It is a schematic flow chart of a TBM tunnel rockburst early warning method based on multi-source information fusion proposed by an embodiment of the present application;

[0057] Figure 2 It is a schematic structural block diagram of a TBM tunnel rockburst early warning device proposed by an embodiment of the present application;

[0058] Figure 3 It is a schematic architecture diagram of a TBM tunnel rockburst early warning system proposed by an embodiment of the present application;

[0059] Figure 4 Schematic structural block diagram of the electronic device proposed in the embodiment of the present application;

[0060] Figure 5 Schematic structural block diagram of the computer-readable storage medium proposed in the embodiment of the present application. Detailed implementation manners

[0061] In the following, the term "comprise" or "may comprise" that can be used in various embodiments of the present application indicates the presence of the invented functions, operations or elements, and does not limit the addition of one or more functions, operations or elements. In addition, as used in various embodiments of the present application, the terms "comprise", "have" and their cognates are only intended to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0062] In various embodiments of the present application, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the listed words. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0063] The expressions (such as "first", "second", etc.) used in various embodiments of the present application may modify various constituent elements in various embodiments, but do not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing one element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of various embodiments of the present application, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0064] The terms used in various embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the various embodiments of the present application. As used herein, the singular form is also intended to include the plural form unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the various embodiments of the present application belong. The terms (such as those defined in a commonly used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or being overly formal unless clearly defined in the various embodiments of the present application.

[0065] To make the objectives, technical solutions, and advantages of this application more clear and understandable, the following further elaborates on this application in combination with embodiments and drawings. The illustrative embodiments and descriptions of this application are only used to explain this application and do not limit this application.

[0066] Embodiment:

[0067] Due to the limitations of single indicators, construction noise interference, diverse geological conditions, etc., traditional rockburst warning methods are difficult to meet the requirements of high precision and real-time performance. In response to this, this embodiment proposes a TBM tunnel rockburst warning method based on multi-source information fusion.

[0068] As Figure 1 shown, the rockburst warning method proposed in this embodiment specifically includes the following steps:

[0069] Step 110: Obtain microseismic information, stress field information, rock mass structure information, TBM construction information, and multi-chamber group spatial relationship information respectively.

[0070] Step 120: Based on the TBM construction information and the multi-chamber group spatial relationship information, denoise the obtained microseismic information through a dynamic Bayesian network.

[0071] Step 130: Fuse the denoised microseismic information, stress field information, and rock mass structure information for multi-element and multi-factor tunnel rockburst risk assessment.

[0072] In one embodiment, the specific methods for obtaining each piece of information in Step 110 are as follows:

[0073] It can be understood that microseismic information refers to small-scale vibrations inside the rock mass caused by phenomena such as fractures and slips. These signals are one of the precursors of rockburst occurrence. In this embodiment, a microseismic sensor array can be used to monitor microseismic signals in real time. Usually, the microseismic sensor array is arranged inside the tunnel to monitor the possible small fractures in the rock mass during tunneling. Specifically, piezoelectric sensors, fiber optic sensors, etc. can be deployed in the tunnel. These sensors monitor microseismic signals in real time and capture the frequency, energy, and location of vibration events. For example, a fiber optic sensor array can be deployed in areas prone to microseismic events such as the tunnel wall, the rock mass in front of the tunnel boring face, geological faults, or fracture zones to obtain microseismic signals. TBM construction information is mainly used to identify construction vibration noise and can include mechanical vibration data such as cutterhead vibration and propulsion vibration, etc., all of which can be obtained through body sensors.

[0074] The construction of the tunnel and the surrounding geological conditions can cause changes in the in - situ stress of the rock mass. The areas where these stresses are concentrated are often the occurrence points of rock bursts. In this embodiment, a in - situ stress monitor can be used to monitor the distribution of the stress field around the tunnel, especially the stress changes around the tunneling face. Specifically, equipment such as borehole stress gauges can be obliquely arranged on both sides and the top of the tunnel. During the tunneling process of the tunnel, the stress, strain, and displacement of the surrounding rock mass of the tunnel are measured, and the changing trend of the stress field is analyzed through the data of multiple monitoring points. In this embodiment, oblique arrangement on both sides and the top of the tunnel is considered to avoid stress blind spots caused by a single direction along the tunnel line and improve the reliability of the data.

[0075] The structural characteristics of the rock mass (such as fractures, joints, rock types, etc.) have an important impact on the occurrence of rock bursts. In this embodiment, the stability of the rock mass is understood through the rock mass structure information, and potential weak areas are identified. Specifically, through geological radar, core drilling, or underground three - dimensional imaging technology, the fracture distribution, joint direction, rock strength, and other rock mass structure information of the tunnel and the surrounding rock mass can be obtained.

[0076] The spatial layout of other chambers near the tunnel will affect the stress distribution of the tunnel and the rock mass failure mode. Through the spatial relationship information of the chamber group, the rock burst risk in the multi - chamber area can be predicted in advance. In this embodiment, three - dimensional geological modeling software and numerical simulation methods can be used, combined with on - site measurement data, to establish a spatial relationship model of the tunnel and the surrounding chambers and analyze the mutual influence in the multi - chamber area.

[0077] Vibration noise propagates in the form of waves. When construction is carried out simultaneously in multiple chambers, the waves of different vibration sources may be superimposed at certain positions, generating more complex interference signals. The superimposed vibration signal may cause the noise amplitude to increase non - linearly, increasing the difficulty of the denoising algorithm to distinguish the true microseismic signal. In a multi - chamber group, the structure of the rock mass, fracture distribution, and the spatial relationship between different chambers affect the propagation path of the vibration wave. The vibration wave may reach the same sensor through multiple paths, making the noise signal recorded by the sensor contain the superposition of multiple propagation modes. The construction activities in the multi - chamber group usually have time differences. For example, the blasting construction of a certain chamber may occur simultaneously with the mechanical vibration of another chamber. The temporal overlap may make the temporal characteristics of the noise become complex, thus affecting the accuracy of the dynamic Bayesian network in temporal modeling. The spatial layout of the multi - chamber group will cause reflection, refraction, or scattering of the vibration wave, resulting in the amplification or attenuation of the noise signal at certain positions. Therefore, in one embodiment, step 120 introduces a chamber spatial relationship model into the dynamic Bayesian network to accurately describe the propagation characteristics and intensity distribution of the noise.

[0078] Specifically:

[0079] In a dynamic Bayesian network, a spatial relationship model describing noise propagation is constructed by combining the spatial relationship information of multi-chamber groups:

[0080]

[0081] The observation model of the dynamic Bayesian network is adjusted using the C matrix:

[0082]

[0083] In the state transition model, the spatio-temporal coupling characteristics of noise between chambers are added, and state variables of noise interaction are added to describe the vibration coupling effect between multi-chambers:

[0084] X t =[S t ,N t

[0085] Describe the joint dynamic changes of microseismic signals and noise:

[0086]

[0087] Spatio-temporal filtering is performed on the vibration signal using the spatial relationship information of the chamber group to enhance the significance of the microseismic signal. Among them, d ij is the Euclidean distance between chamber i and chamber j; α is the attenuation coefficient, which is determined according to the rock mass properties; C ij is the spatial interaction term of noise; S t is the state of the true microseismic signal; N t is the spatio-temporal coupling state of noise between chambers; F is the state transition matrix, which contains the time series relationship between signals and noise; Q t is the state noise covariance matrix; X t is the state of the true microseismic signal at time t; X t-1 is the state of the true microseismic signal at time t-1, which is used to predict the state at time t; O t is the microseismic signal observed at time t; R t is the observation noise covariance matrix; H t is the observation matrix, which describes the linear relationship between the observation variable and the state variable. P(O t |X t ) is the observation model, which represents the probability distribution of the observed microseismic signal O t under the condition that the true microseismic signal X t is known. If the measurement error of the sensor is small (low construction noise), then the distribution of P(O t |X t ) will be narrower, indicating that the observed data is more accurate; on the contrary, when the construction noise is large, the uncertainty of the observed data will also increase. ​represents a normal distribution. Then, using the state X at the previous moment t-1 , predict the true distribution of microseismic signals at the current moment through the state transition model:

[0088]

[0089] Combine the observation data O t , and update the prediction result using the observation model:

[0090]

[0091]

[0092] where K t is the Kalman gain matrix, used to balance the weights of the predicted value and the observed value; is the prior predicted state at time t, which is the predicted value of the microseismic signal calculated based on X at the previous moment t-1 ; is the prior covariance matrix at time t; is the updated estimated state at time t, representing the characteristics of the microseismic signal after denoising; ∑ t represents the state estimation error at the current time t, reflecting the estimation accuracy at the current time t; f(·) is the state transition model, which describes how the state of the microseismic signal develops from X at the previous moment t-1 to X at the current moment t ; θ is the parameter of the state transition model, used to define the specific form of f(·), such as TBM construction information, rock mass characteristics, etc.

[0093] It is understandable that a Bayesian Network (BN) is a graphical model used to represent conditional dependencies between variables. A Dynamic Bayesian Network (DBN) is an extended Bayesian Network specifically for processing time series data and is suitable for dealing with complex problems with temporal dependencies. In TBM tunnel construction, due to construction disturbances and environmental noise interference, the microseismic signals collected may contain a large amount of noise. Therefore, in this embodiment, through the DBN model, these noises can be dynamically identified and removed based on historical data and construction information. Specifically, a DBN model can be established to define the temporal characteristics (such as frequency, energy, location, etc.) of the noise sources (such as TBM vibration, construction noise, etc.) and microseismic signals. According to the time series data, the conditional probability distribution between the noise and the true rockburst signal is inferred. Among them, the state variables are the time characteristics (such as frequency, energy) of the microseismic signal, TBM construction disturbance data (such as propulsion speed, torque, etc.), and spatial information (such as tunnel microseismic, fracture information, etc.). The observed variables are the actually monitored microseismic signals, vibration, and noise signals. Through Bayesian inference, the conditional probability between variables is learned based on historical data. The DBN dynamically infers the true source of the microseismic signal according to the spatio-temporal relationship of the sensor data, and eliminates the noise signals unrelated to rockburst from the data, thus providing a more real and reliable data source for the subsequent early warning steps.

[0094] Optionally, after obtaining the predicted time series of the true microseismic signal, it further includes:

[0095] Performing backward smoothing on the entire time series:

[0096]

[0097] Wherein,

[0098]

[0099] Wherein, is the estimated state after backward smoothing, and A t is the smoothing gain matrix. By backward smoothing the predicted time series of the true microseismic signal obtained in the above steps, the signal estimation becomes more stable and accurate, and the influence of construction noise is further reduced.

[0100] It is understandable that the backward smoothing process is an extension of the Kalman filter, which can improve the accuracy of denoising by combining the estimation results of the entire time series to obtain the optimal state estimation.

[0101] In one embodiment, the risk assessment process of step 130 specifically includes:

[0102] The denoised microseismic information, stress field information, and rock mass structure information are input into a comprehensive risk assessment model, and the rockburst risk is judged by fusing this information. Among them, machine learning algorithms (such as support vector machine SVM, random forest RF, or multi-layer perceptron MLP) can be used to construct a multivariate risk assessment model. The model calculates the probability of rockburst occurrence based on various input features (such as denoised microseismic signals, stress values, rock mass structures, etc.). The rockburst risk level output by the model can be adjusted by setting thresholds. For example: low risk (probability 0 - 0.3); medium risk (probability 0.3 - 0.6); high risk (probability 0.6 - 1). This embodiment uses multi-source data (microseismic, stress, rock mass structure, TBM construction) for comprehensive evaluation, avoiding misjudgments that may be caused by a single data source, and being able to more comprehensively and reliably evaluate the rockburst risk. The rockburst early warning method proposed in this embodiment can collect data in real time and dynamically adjust the evaluation strategy, automatically optimizing the risk assessment according to different geological conditions and construction states during the construction process, ensuring the real-time performance and adaptability of the rockburst early warning.

[0103] In another embodiment, this embodiment also proposes a TBM tunnel rockburst early warning device 200 based on multi-source information fusion, as Figure 2 shown. The early warning device 200 includes:

[0104] An acquisition unit 201, configured to acquire microseismic information, stress field information, rock mass structure information, TBM construction information, and multi-chamber group spatial relationship information respectively. The specific information acquisition method is as described in the above step 110, and will not be elaborated here.

[0105] A denoising unit 202, configured to denoise the acquired microseismic information through a dynamic Bayesian network based on the TBM construction information and the multi-chamber group spatial relationship information. The specific denoising process is as described in the above step 120, and will not be elaborated here.

[0106] And an evaluation unit 203, configured to fuse the denoised microseismic information, stress field information, and rock mass structure information for multivariate and multi-factor tunnel rockburst risk assessment. The specific evaluation process is as described in the above step 130, and will not be elaborated here.

[0107] In another embodiment, this embodiment also proposes a TBM tunnel rockburst early warning system 300 based on multi-source information fusion, as Figure 3 shown. The early warning system 300 proposed in this embodiment includes:

[0108] An input device 301, an output device 302, a processor 303, and a memory 304; wherein, the number of the processor 303 and the memory can be one or more, Figure 3Taking a processor 303 and a memory 304 as an example for illustration. The input device 301, the output device 302, the processor 303, and the memory 304 can be connected through a bus or other means. Figure 3 Taking the connection through a bus as an example.

[0109] Among them, by calling the operation instructions stored in the memory 304, the processor 303 is used to perform the following steps:

[0110] Respectively obtain microseismic information, stress field information, rock mass structure information, TBM construction information, and the spatial relationship information of the multi-chamber group;

[0111] Based on the TBM construction information and the spatial relationship information of the multi-chamber group, denoise the obtained microseismic information through a dynamic Bayesian network;

[0112] Fuse the denoised microseismic information, stress field information, and rock mass structure information for multi-factor tunnel rockburst risk assessment.

[0113] Optionally, by calling the operation instructions stored in the memory 304, the processor 303 is further used to execute any implementation manner in the corresponding embodiment of the above warning method.

[0114] In another embodiment, this embodiment also proposes an electronic device 400, as Figure 4 shown. The electronic device 400 includes: a memory 410, a processor 420, and a computer program 411 stored on the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0115] Respectively obtain microseismic information, stress field information, rock mass structure information, TBM construction information, and the spatial relationship information of the multi-chamber group;

[0116] Based on the TBM construction information and the spatial relationship information of the multi-chamber group, denoise the obtained microseismic information through a dynamic Bayesian network;

[0117] Fuse the denoised microseismic information, stress field information, and rock mass structure information for multi-factor tunnel rockburst risk assessment.

[0118] Optionally, when the processor 420 executes the computer program 411, it can implement any implementation manner in the corresponding embodiment of the above warning method.

[0119] It should be noted that the electronic device proposed in this embodiment is the device adopted to implement the above warning method. Therefore, based on the above warning method proposed in this embodiment, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the above warning method will not be introduced in detail here. As long as the electronic device adopted by those skilled in the art to implement the above warning method belongs to the scope protected by this application.

[0120] In another embodiment, this embodiment also proposes a computer-readable storage medium 500, as Figure 5 shown. A computer program 511 is stored on the computer-readable storage medium 500. When the computer program 511 is executed by a processor, the following steps are implemented:

[0121] Obtain microseismic information, stress field information, rock mass structure information, TBM construction information, and multi-chamber group spatial relationship information respectively;

[0122] Based on the TBM construction information and the multi-chamber group spatial relationship information, denoise the obtained microseismic information through a dynamic Bayesian network;

[0123] Fuse the denoised microseismic information, stress field information, and rock mass structure information for multi-factor and multi-element tunnel rockburst risk assessment.

[0124] Optionally, when the computer program 511 is executed by a processor, it can implement any implementation manner in the corresponding embodiment of the above warning method.

[0125] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0127] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0128] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0130] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present application. It should be understood that the above are only specific embodiments of the present application and are not used to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A TBM tunnel rockburst early warning method based on multi-source information fusion, characterized in that, Including: Respectively obtain microseismic information, stress field information, rock mass structure information, TBM construction information, and the spatial relationship information of the multi-chamber group; Based on the TBM construction information and the spatial relationship information of the multi-chamber group, denoise the obtained microseismic information through a dynamic Bayesian network; Fuse the denoised microseismic information, stress field information, and rock mass structure information for multi-factor tunnel rockburst risk assessment.

2. The TBM tunnel rockburst warning method based on multi-source information fusion according to claim 1, wherein The denoising of the obtained microseismic information through a dynamic Bayesian network based on the TBM construction information and the spatial relationship information of the multi-chamber group includes: In the dynamic Bayesian network, combine the spatial relationship information of the multi-chamber group to construct a spatial relationship model describing noise propagation: Use the C matrix to adjust the observation model of the dynamic Bayesian network: Add the spatio-temporal coupling characteristics of the noise between chambers in the state transition model, add state variables of noise interaction, and describe the vibration coupling effect between multi-chambers: X t = [S t , N t ​ Describe the joint dynamic change of microseismic signals and noise: Use the spatial relationship information of the chamber group to perform spatio-temporal filtering on the vibration signal to enhance the significance of the microseismic signal; Among them, d ij is the Euclidean distance between chamber i and chamber j; α is the attenuation coefficient; C ij is the spatial interaction term of the noise; S t is the state of the true microseismic signal; N t is the spatio-temporal coupling state of the noise between chambers; F is the state transition matrix, which contains the time series relationship between the signal and the noise; Q t is the state noise covariance matrix; X t is the state of the true microseismic signal at time t; X t-1 is the state of the true microseismic signal at time t - 1, which is used to predict the state at time t; O t is the microseismic signal observed at time t; R t is the observation noise covariance matrix; H t is the observation matrix, which describes the linear relationship between the observation variable and the state variable, where the observation variable is the actually monitored microseismic signal, vibration and noise signal, and the state variable is the characteristic quantity of the microseismic information, TBM construction information and multi-chamber group space information; P(O t |X t ) is the observation model, which represents the probability distribution of the observed microseismic signal O t under the condition that the true microseismic signal X t is known; represents the normal distribution.

3. The method for predicting rockburst of TBM tunnel based on multi-source information fusion according to claim 2, wherein, The denoising of the obtained microseismic information through a dynamic Bayesian network based on the TBM construction information and the spatial relationship information of the multi-chamber group further includes: Use the state at the previous moment to predict the true microseismic signal distribution at the current moment through the state transition model: Combine the observation data and update the prediction result using the observation model: Among them, K t is the Kalman gain matrix, which is used to balance the weights of the predicted value and the observed value; is the prior predicted state at time t, which is the predicted value of the microseismic signal deduced according to the previous moment X t-1 ; is the prior covariance matrix at time t; f(·) is the state transition model; θ is the parameter of the state transition model.

4. A TBM tunnel rockburst early warning method based on multi-source information fusion according to claim 3, characterized in that Also including: Perform backward smoothing on the entire microseismic signal prediction time series: Wherein, Among them, is the estimated state after backward smoothing, and A t is the smoothing gain matrix.

5. A TBM tunnel rockburst early warning method based on multi-source information fusion according to any one of claims 1-4, characterized in that, The respectively obtaining microseismic information, stress field information, rock mass structure information, TBM construction information, and the spatial relationship information of the multi-chamber group includes: Arrange an optical fiber sensor array on the tunnel wall, the rock mass in front of the tunnel boring face, geological faults or fracture zones to obtain the microseismic information; And / or, obliquely arrange borehole stress gauges on both sides and the top of the tunnel to obtain the stress field information; And / or, obtain the rock mass structure information through geological radar, core drilling, and underground three-dimensional imaging technology; the rock mass structure information includes fracture distribution, joint direction, and rock strength.

6. A TBM tunnel rockburst early warning method based on multi-source information fusion according to any one of claims 1-4, characterized in that, The multi-factor tunnel rockburst risk assessment by fusing the denoised microseismic information, stress field information, and rock mass structure information includes: Input the denoised microseismic information, stress field information, and rock mass structure information into a pre-established multi-factor risk assessment model; The multi-factor risk assessment model calculates the probability of rockburst occurrence according to the characteristic quantities of the input position information, stress field information, and rock mass structure information; The multi-factor risk assessment model outputs the rockburst risk level according to the risk threshold.

7. A TBM tunnel rockburst early warning device based on multi-source information fusion, characterized in that, Including: An acquisition unit for respectively obtaining microseismic information, stress field information, rock mass structure information, TBM construction information, and the spatial relationship information of the multi-chamber group; A value-taking unit for denoising the obtained microseismic information through a dynamic Bayesian network based on the TBM construction information and the spatial relationship information of the multi-chamber group; And an evaluation unit for fusing the denoised microseismic information, stress field information, and rock mass structure information for multi-source and multi-factor tunnel rockburst risk assessment.

8. A TBM tunnel rockburst early warning system based on multi-source information fusion, comprising: An input device, an output device, a processor, and a memory connected through a bus; characterized in that the processor is configured to execute the following steps by calling operation instructions stored in the memory: Obtain microseismic information, stress field information, rock mass structure information, TBM construction information, and multi-chamber group spatial relationship information respectively; Based on the TBM construction information and the multi-chamber group spatial relationship information, denoise the obtained microseismic information through a dynamic Bayesian network; Fuse the denoised microseismic information, stress field information, and rock mass structure information for multi-source and multi-factor tunnel rockburst risk assessment.

9. An electronic device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the TBM tunnel rockburst early warning method based on multi-source information fusion described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the TBM tunnel rockburst early warning method based on multi-source information fusion described in any one of claims 1-6.

Images