Deformation monitoring method for soft rock with extremely high ground stress

Abstract

The invention discloses a deformation monitoring method for soft rock with extremely high ground stress, and relates to the related field of tunnel engineering, and the method comprises the following steps: arranging a deformation monitoring sensor; the current surrounding rock tunnel is monitored in real time, and a surrounding rock deformation data set is obtained; carrying out deformation trend analysis based on the deformation trend prediction model, and outputting a predicted deformation speed; inputting the predicted deformation speed into a segmented support decision maker; and if the detected value is larger than the first preset threshold value, the supporting device is connected to perform primary supporting on the current surrounding rock tunnel, and if the detected value is smaller than a second preset threshold value, the supporting device is connected to perform secondary supporting on the surrounding rock tunnel after primary supporting. The technical problems that supporting decision lags, surrounding rock deformation cannot be effectively controlled and potential safety hazards exist in tunnel construction due to the fact that existing extremely-high crustal stress soft rock deformation monitoring is insufficient in monitoring precision are solved, and the purposes of improving monitoring precision, optimizing supporting decision, effectively controlling surrounding rock deformation and improving tunnel construction quality are achieved. And therefore, the safety and stability of tunnel construction are improved.

Description

Technical Field

[0001] The present application relates to the field of tunnel engineering, and in particular to a deformation monitoring method for extremely high ground stress soft rock. Background Art

[0002] In tunnel engineering, especially in tunnel construction under extremely high geostress soft rock environment, surrounding rock deformation control is the key to engineering safety and quality. Due to the characteristics of extremely high geostress soft rock, such as fast deformation, large deformation, and long duration, traditional deformation monitoring and support methods are often difficult to deal with effectively. For example, the data collection and processing efficiency of monitoring surrounding rock deformation through manual measurement or simple sensors is low, and it is difficult to reflect the surrounding rock deformation in real time. The support method based on the experience of construction personnel lacks scientificity and accuracy, and is prone to untimely or excessive support.

[0003] Among the current relevant technologies, the monitoring accuracy of soft rock deformation with extremely high ground stress is insufficient, which leads to delayed support decisions, inability to effectively control surrounding rock deformation, and technical problems such as safety hazards in tunnel construction. Summary of the invention

[0004] The present application provides a deformation monitoring method for extremely high ground stress soft rock, which adopts sensors deployed in an extremely high ground stress soft rock environment, monitors the deformation of the surrounding rock in real time, predicts the deformation trend through a model, makes support decisions in sections according to the predicted speed, performs primary support when the speed exceeds a high threshold, and performs secondary support when the speed is lower than a low threshold, etc., to achieve the technical effect of improving monitoring accuracy, optimizing support decisions, effectively controlling the deformation of the surrounding rock, and thus improving the safety and stability of tunnel construction.

[0005] The present application provides a deformation monitoring method for extremely high ground stress soft rock, comprising: deploying deformation monitoring sensors in an extremely high ground stress soft rock environment; performing real-time monitoring of a current surrounding rock tunnel according to the deformation monitoring sensors to obtain a surrounding rock deformation data set; performing deformation trend analysis on the surrounding rock deformation data set based on a deformation trend prediction model, and outputting a predicted deformation speed; inputting the predicted deformation speed into a segmented support decision maker, the segmented support decision maker is connected to a support device, and the segmented support decision maker includes a first preset threshold and a second preset threshold, and the first preset threshold is greater than the second preset threshold; if the segmented support decision maker detects that the predicted deformation speed is greater than the first preset threshold, connecting the support device to perform primary support on the current surrounding rock tunnel, and if the predicted deformation speed is less than the second preset threshold, connecting the support device to perform secondary support on the surrounding rock tunnel after the primary support.

[0006] In a possible implementation, a deformation trend analysis is performed on the surrounding rock deformation dataset based on a deformation trend prediction model, and the following processing is performed: a historical deformation dataset of the surrounding rock tunnel is collected, including stress changes, displacement vectors, and inclination angles; time series features of the historical deformation dataset are extracted; a long short-term memory network is constructed, and a gradient descent method is used to train the long short-term memory network according to the time series features, with the historical deformation dataset and deformation velocity labels as inputs, to output a deformation trend prediction model.

[0007] In a possible implementation, the following processing is also performed: obtaining model parameters of the deformation trend prediction model; obtaining an updated deformation data set of the surrounding rock tunnel, performing real-time parameter optimization on the model parameters of the deformation trend prediction model according to the updated deformation data set, and outputting an updated deformation trend prediction model.

[0008] In a possible implementation, the following processing is performed: if the segmented support decision maker detects that the predicted deformation speed is greater than the first preset threshold, a first support strength is output, the support device is connected, and the current surrounding rock tunnel is supported once according to the first support strength.

[0009] In a possible implementation, the following processing is performed: if the segmented support decision maker detects that the predicted deformation speed is less than or equal to the first preset threshold, and the predicted deformation speed is greater than or equal to the second preset threshold, a second support strength is output, the support device is connected, and the current surrounding rock tunnel is supported once according to the second support strength; wherein the first support strength is greater than the second support strength.

[0010] In a possible implementation, the following processing is performed: connecting the support device to perform primary support on the current surrounding rock tunnel, wherein the primary support includes top plate installation, anchor rod installation, anchor cable installation and initial concrete spraying; connecting the support device to perform secondary support on the current surrounding rock tunnel, wherein the secondary support includes top plate grouting, anchor rod grouting, anchor cable grouting and re-spraying of concrete.

[0011] In a possible implementation, the following processing is performed: connecting the support device to perform primary support on the current surrounding rock tunnel, and obtaining the concrete spraying particle size of the initial concrete spraying; connecting the support device to perform secondary support on the current surrounding rock tunnel, and obtaining the concrete spraying particle size of the secondary concrete spraying, wherein the concrete spraying particle size of the secondary concrete spraying is smaller than the concrete spraying particle size of the initial concrete spraying.

[0012] In a possible implementation, the current surrounding rock tunnel is monitored in real time according to the deformation monitoring sensor to obtain a surrounding rock deformation data set, and the following processing is performed: the current surrounding rock tunnel is monitored in real time according to the deformation monitoring sensor to obtain multi-source monitoring data; the multi-source monitoring data is time-aligned to obtain multi-source monitoring data after time-alignment processing; the multi-source monitoring data after time-alignment processing is fused to obtain a surrounding rock deformation data set.

[0013] A deformation monitoring method for extremely high ground stress soft rock proposed in this application is to first deploy deformation monitoring sensors in an extremely high ground stress soft rock environment, perform real-time monitoring of the current surrounding rock tunnel according to the deformation monitoring sensors, obtain a surrounding rock deformation data set, then perform deformation trend analysis on the surrounding rock deformation data set based on a deformation trend prediction model, output a predicted deformation speed, and then input the predicted deformation speed into a segmented support decision maker, the segmented support decision maker is connected to a support device, and the segmented support decision maker includes a first preset threshold and a second preset threshold, and the first preset threshold is greater than the second preset threshold, if the segmented support decision maker detects that the predicted deformation speed is greater than the first preset threshold, the support device is connected to perform a primary support on the current surrounding rock tunnel, if the predicted deformation speed is less than the second preset threshold, the support device is connected to perform a secondary support on the surrounding rock tunnel after the primary support, thereby achieving the technical effect of improving monitoring accuracy, optimizing support decisions, and effectively controlling surrounding rock deformation, thereby improving the safety and stability of tunnel construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic flow chart of a deformation monitoring method for extremely high in-situ stress soft rock provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of a process for performing deformation trend analysis in a deformation monitoring method for extremely high geostress soft rock provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a deformation monitoring method for extremely high ground stress soft rock, such as Figure 1 As shown, the method includes: Step S100, deploy deformation monitoring sensors in an extremely high geostress soft rock environment. Specifically, before and during tunnel excavation, deformation monitoring sensors are deployed at key locations (such as tunnel vaults, side walls, etc.) in an extremely high geostress soft rock environment according to the geological conditions, construction methods, and monitoring requirements of the tunnel. Deformation monitoring sensors are devices used to monitor the deformation of rocks or soil, and can provide deformation data in real time or periodically, including stress gauges, displacement gauges, inclinometers, etc. Among them, extremely high geostress soft rock refers to rock formations with high geostress levels and relatively low strength. Such formations are prone to large deformations and instability during tunnel construction.

[0021] Step S200, real-time monitoring of the current surrounding rock tunnel is performed according to the deformation monitoring sensor to obtain a surrounding rock deformation data set. Specifically, the current surrounding rock tunnel is monitored in real time through the deployed deformation monitoring sensor to collect surrounding rock deformation data, including stress changes, displacement vectors, inclination angles, etc., for subsequent analysis and prediction.

[0022] In a possible implementation, the current surrounding rock tunnel is monitored in real time according to the deformation monitoring sensor to obtain a surrounding rock deformation data set, and step S200 further includes step S210, which monitors the current surrounding rock tunnel in real time according to the deformation monitoring sensor to obtain multi-source monitoring data. Specifically, in an extremely high ground stress soft rock environment, various types of deformation monitoring sensors are deployed, such as displacement sensors, strain sensors, pressure sensors, etc. These sensors collect deformation data of the surrounding rock tunnel in real time, including displacement, strain value, pressure distribution, etc. These data from different sensors are used as multi-source monitoring data for subsequent processing and analysis. Step S220, the multi-source monitoring data is subjected to time alignment processing to obtain multi-source monitoring data after time alignment processing. Specifically, since different sensors have different sampling frequencies and data formats, it is necessary to perform time alignment processing on the multi-source monitoring data. The time alignment processing includes determining a unified time base, and then aligning the data of each sensor according to this time base. For missing data points, interpolation methods or other data completion technologies can be used to fill them. Step S230, fuse the multi-source monitoring data after time-series alignment processing to obtain a surrounding rock deformation data set. Specifically, based on the multi-source monitoring data after time-series alignment processing, data fusion technology is used to integrate these data into a unified surrounding rock deformation data set. Data fusion technology includes weighted average, Kalman filtering, neural network and other methods. The fused data set comprehensively reflects the deformation of the surrounding rock tunnel, which is used to provide a basis for subsequent analysis and decision-making. This implementation method fully utilizes the advantages of different sensors through the collection and fusion of multi-source monitoring data, improves the accuracy and reliability of the data, and provides stronger support for subsequent deformation trend analysis and support decision-making.

[0023] Step S300, based on the deformation trend prediction model, the deformation trend of the surrounding rock deformation data set is analyzed, and the predicted deformation speed is output. Specifically, the deformation trend prediction model that has been constructed is used to analyze the collected surrounding rock deformation data set, predict the future deformation trend of the surrounding rock, and output the predicted deformation speed, which is used to evaluate the stability of the surrounding rock and serve as the basis for subsequent support decisions. Among them, the deformation trend prediction model is a model constructed based on historical data and machine learning algorithms, which can predict the deformation trend of the surrounding rock in the future.

[0024] like Figure 2As shown, in a possible implementation, the deformation trend analysis of the surrounding rock deformation data set is performed based on the deformation trend prediction model, and step S300 further includes step S310, collecting the historical deformation data set of the surrounding rock tunnel, including stress changes, displacement vectors and inclination angles. Specifically, historical deformation data on the surrounding rock tunnel are collected from existing monitoring records or databases. These data cover key stages in the construction process such as tunnel excavation and support, and include key indicators such as stress changes (changes in the stress state inside the surrounding rock due to external loads or internal structural adjustments), displacement vectors (changes in the position of a point in the surrounding rock in space, including displacements in both horizontal and vertical directions) and inclination angles (the degree of inclination of the surrounding rock surface or a part relative to the horizontal plane). The data is preprocessed to ensure the accuracy, completeness and consistency of the data.

[0025] Step S320, extracting the time series features of the historical deformation data set. Specifically, based on the statistical and machine learning methods, the collected historical deformation data set is subjected to time series analysis to extract key features that can reflect the deformation trend, including deformation rate (the rate of change of surrounding rock deformation over time, used to describe the speed of deformation), deformation acceleration (the rate of change of deformation rate over time, used to describe the trend of deformation rate), periodic changes in deformation, etc.

[0026] Step S330, construct a long short-term memory network, adopt the gradient descent method according to the time series features, take the historical deformation data set and the deformation speed label as input to train the long short-term memory network, and output a deformation trend prediction model. Specifically, select the long short-term memory network (LSTM) as the prediction model, and LSTM can handle the long-term dependencies in the time series data. Take the extracted time series features as input, and take the deformation speed label in the historical deformation data set (the deformation speed value corresponding to each time series feature in the historical deformation data set) as output to construct the LSTM network. Use the gradient descent method or other optimization algorithms to train the network until the preset convergence condition or number of training rounds is reached. After the training is completed, output the deformation trend prediction model, which can predict the future deformation speed based on the new time series features. This implementation method uses the long short-term memory network to predict the deformation trend, which can capture the long-term dependencies in the data, so that the future deformation speed can be accurately predicted, providing a scientific basis for support decisions in tunnel construction, and improving the safety and stability of construction.

[0027] In a possible implementation, step S300 further includes step S340, obtaining model parameters of the deformation trend prediction model. Specifically, after completing the training of the long short-term memory network (LSTM), extracting model parameters from the trained model, including network weights and biases, etc., which together determine the prediction ability of the model. Step S350, obtaining an updated deformation data set of the surrounding rock tunnel, optimizing the model parameters of the deformation trend prediction model in real time according to the updated deformation data set, and outputting an updated deformation trend prediction model. Specifically, during the tunnel construction process, new deformation monitoring data are continuously collected to form an updated deformation data set, which reflects the latest deformation state of the tunnel surrounding rock. The updated deformation data set is used as input, and the model parameters of the deformation trend prediction model are optimized in real time by using methods such as online learning or incremental learning. Online learning allows the model to update its parameters immediately when receiving new data without retraining the entire model. In the parameter optimization process, the gradient descent method is used to minimize the prediction error and continuously improve the prediction accuracy of the model. After the optimization is completed, the updated deformation trend prediction model is output, which can more accurately reflect the deformation trend of the tunnel surrounding rock. During the tunnel construction process, the deformation state of the surrounding rock is constantly changing. This implementation method can continuously improve the model's prediction ability by collecting and updating deformation data sets and performing online learning or incremental learning on model parameters based on these data, thereby improving the accuracy and reliability of the prediction.

[0028] Step S400, input the predicted deformation speed into the segmented support decision maker, the segmented support decision maker is connected to the support device, and the segmented support decision maker includes a first preset threshold and a second preset threshold, and the first preset threshold is greater than the second preset threshold. Specifically, the obtained predicted deformation speed is input into the segmented support decision maker (a device or system that automatically decides the support method and strength according to the deformation of the surrounding rock), and the decision maker decides whether to start the support device and the strength and method of the support according to the preset thresholds (the first preset threshold and the second preset threshold) and the predicted deformation speed. The support device is a device or structure used to reinforce the surrounding rock and prevent its deformation, such as anchor rods, anchor cables, shotcrete, etc.

[0029] Step S500, if the segmented support decision maker detects that the predicted deformation speed is greater than the first preset threshold, the support device is connected to perform primary support on the current surrounding rock tunnel; if the predicted deformation speed is less than the second preset threshold, the support device is connected to perform secondary support on the surrounding rock tunnel after the primary support. Specifically, according to the decision result of the segmented support decision maker, if the predicted deformation speed is greater than the first preset threshold, it means that the surrounding rock is severely deformed and primary support is required immediately; if the predicted deformation speed is less than the second preset threshold (and primary support has been performed), secondary support is performed to further enhance the stability of the surrounding rock. The specific mode and intensity of support are determined by the segmented support decision maker according to the predicted deformation speed and the preset support scheme. Among them, primary support is a preliminary reinforcement measure for the surrounding rock after tunnel excavation, such as installing anchor rods, spraying concrete, etc. Secondary support is a further reinforcement measure for the surrounding rock on the basis of primary support, such as grouting, re-spraying concrete, etc. The embodiment of the present application adopts technical means such as deploying sensors in an extremely high ground stress soft rock environment, monitoring the deformation of the surrounding rock in real time, predicting the deformation trend through a model, making support decisions in sections according to the predicted speed, performing primary support when the speed exceeds a high threshold, and performing secondary support when the speed is lower than a low threshold, etc., to achieve the technical effect of improving monitoring accuracy, optimizing support decisions, effectively controlling the deformation of the surrounding rock, and thereby improving the safety and stability of tunnel construction.

[0030] In a possible implementation, step S500 further includes step S510, if the segmented support decision maker detects that the predicted deformation speed is greater than the first preset threshold, outputs a first support strength, connects the support device, and performs a support operation on the current surrounding rock tunnel according to the first support strength. Specifically, the segmented support decision maker receives the predicted deformation speed output by the deformation trend prediction model in real time, and compares it with the first preset threshold. If the predicted deformation speed is greater than the first preset threshold, the segmented support decision maker immediately outputs a first support strength instruction, and the first support strength is a higher support strength set for rapidly deforming surrounding rock to cope with the rapid deformation of the surrounding rock and to quickly stabilize the state of the surrounding rock. After receiving the support strength instruction, the support device automatically adjusts to the corresponding support strength state, performs a support operation on the current surrounding rock tunnel according to the first support strength, and ensures the stability of the surrounding rock.

[0031] In a possible implementation, step S500 further includes step S520, if the segmented support decision maker detects that the predicted deformation speed is less than or equal to the first preset threshold, and the predicted deformation speed is greater than or equal to the second preset threshold, outputs a second support strength, connects the support device, and performs a support operation on the current surrounding rock tunnel according to the second support strength; wherein the first support strength is greater than the second support strength. Specifically, the segmented support decision maker continues to receive the predicted deformation speed and compares it with the first preset threshold and the second preset threshold. If the predicted deformation speed is between the first preset threshold and the second preset threshold, the segmented support decision maker outputs a second support strength instruction, and the second support strength is a moderate support strength set for medium-speed deformation surrounding rock, which is used to cope with medium-speed surrounding rock deformation. The support device also receives the support strength instruction and adjusts to the corresponding support strength state. The support device performs a support operation on the current surrounding rock tunnel according to the second support strength, while keeping close monitoring of surrounding rock deformation. The above implementation method fully considers the different speeds and degrees of surrounding rock deformation, and takes corresponding support measures accordingly, realizing accurate monitoring and flexible support of surrounding rock deformation, and effectively improving the safety and stability of tunnel construction.

[0032] In a possible implementation, step S500 further includes step S530, connecting the support device to perform primary support on the current surrounding rock tunnel, wherein the primary support includes the installation of the top plate, the installation of the anchor rod, the installation of the anchor cable and the initial spraying of concrete. Specifically, the primary support includes the installation of the top plate on the top of the tunnel, the top plate is made of a steel frame or reinforced concrete, and is used to support the surrounding rock at the top of the tunnel to prevent it from collapsing due to gravity or ground stress. A hole is drilled in the tunnel surrounding rock, and an anchor rod (for example, a left-handed high-strength resin anchor rod without longitudinal reinforcement with a specification of $20x2200mm, with an anchoring force of more than 120KN) is inserted, one end of the anchor rod is fixed in the surrounding rock, and the other end is connected to the top plate to provide additional support. The installation of the anchor cable is similar to the anchor rod, but the anchor cable is longer and thicker and is made of high-strength material. The anchor cable is inserted deep into the surrounding rock through a drilled hole, and prestress is applied to enhance the stability of the surrounding rock. After the composite beam structure is formed around the tunnel, a thin layer of concrete (primary shotcrete) is sprayed on the surface of the tunnel surrounding rock to seal the cracks and gaps on the surface of the surrounding rock to prevent moisture intrusion and provide a certain degree of support.

[0033] Step S540, connect the support device to perform secondary support on the current surrounding rock tunnel, wherein the secondary support includes top plate grouting, anchor rod grouting, anchor cable grouting and re-spraying concrete. Specifically, the secondary support includes injecting grouting material (such as cement slurry, chemical slurry, etc.) into the gap between the top plate and the surrounding rock to fill the gaps, cracks or holes in the rock and soil and enhance the support force of the top plate. Grouting is performed on the installed anchor rods (grouting anchor rods, for example, grouting anchor rods made of ordinary iron pipes with a wall thickness of 3 to 4 mm, 66 mm grouting holes drilled on the rod body, and a hole spacing of 300 to 400 mm) to enhance the bonding force between the anchor rod and the surrounding rock and improve the support effect. Similarly, grouting is performed on the installed anchor cable to strengthen its connection with the surrounding rock. On the basis of the initial spraying concrete, a thicker layer of concrete is sprayed again (re-spraying concrete) to further improve the support capacity and durability of the tunnel. This implementation method fully considers the complexity and uncertainty of surrounding rock deformation during the construction of large-section tunnels in soft rock with high geostress. The primary support is used to quickly stabilize the surrounding rock to prevent it from collapsing due to excessive deformation. Through measures such as the installation of top plates, anchor rods, anchor cables and initial spraying of concrete, a preliminary support barrier is quickly formed to provide safety for subsequent secondary support and tunnel excavation. Secondary support is a reinforcement and supplement to primary support, which is used to further improve the support capacity and durability of the tunnel. Through measures such as top plate grouting, anchor rod grouting, anchor cable grouting and re-spraying of concrete, the gaps and cracks in the surrounding rock are filled, and the bonding force between the support structure and the surrounding rock is enhanced, thereby improving the overall stability of the tunnel. Through the combination of primary and secondary support, the deformation of the surrounding rock during the construction of large-section tunnels in soft rock with high geostress is effectively controlled, ensuring the safety and stability of tunnel construction.

[0034] In a possible implementation, step S500 further includes step S550, connecting the support device to perform primary support on the current surrounding rock tunnel, obtaining the spraying concrete particle size of the initial spraying concrete, connecting the support device to perform secondary support on the current surrounding rock tunnel, obtaining the spraying concrete particle size of the re-spraying concrete, and the spraying concrete particle size of the re-spraying concrete is smaller than the spraying concrete particle size of the initial spraying concrete. Specifically, when performing the initial spraying concrete operation of the primary support, a particle size measuring device (such as a particle size analyzer) is used to perform a particle size analysis on the sprayed concrete (initial spraying concrete), and the particle size distribution of the initial spraying concrete is recorded and analyzed. Before performing the re-spraying concrete operation of the secondary support, a particle size measuring device is also used to perform a particle size analysis on the concrete to be sprayed (re-spraying concrete). According to the particle size analysis results of the initial spraying concrete and the design requirements of the secondary support, the mix ratio and particle size distribution of the re-spraying concrete are adjusted to ensure that the particle size of the re-spraying concrete is smaller than that of the initial spraying concrete, that is, the re-spraying concrete requires a finer and more uniform particle distribution to provide a better filling effect and surface flatness. According to the adjusted re-sprayed concrete particle size, the secondary support spraying operation is carried out. During the spraying process, the particle size changes of the re-sprayed concrete are continuously monitored to ensure that it always meets the design requirements. This implementation method adjusts the particle size of the re-sprayed concrete to be smaller than the primary sprayed concrete, which can more effectively fill the gaps and cracks in the primary sprayed concrete layer and improve the integrity and density of the support layer, which helps to enhance the support strength of the tunnel and improve the stability and safety of the tunnel.

[0035] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A deformation monitoring method for extremely high ground stress soft rock, characterized in that: The method comprises: In extremely high ground stress soft rock environment, deformation monitoring sensors are deployed; Perform real-time monitoring of the current surrounding rock tunnel according to the deformation monitoring sensor to obtain a surrounding rock deformation data set; Performing deformation trend analysis on the surrounding rock deformation data set based on a deformation trend prediction model, and outputting a predicted deformation velocity; Inputting the predicted deformation speed into a segmented support decision maker, the segmented support decision maker is connected to a support device, and the segmented support decision maker includes a first preset threshold and a second preset threshold, and the first preset threshold is greater than the second preset threshold; If the segmented support decision maker detects that the predicted deformation speed is greater than the first preset threshold, the support device is connected to perform primary support on the current surrounding rock tunnel; if the predicted deformation speed is less than the second preset threshold, the support device is connected to perform secondary support on the surrounding rock tunnel after the primary support.

2. A deformation monitoring method for extremely high ground stress soft rock according to claim 1, characterized in that: The deformation trend analysis of the surrounding rock deformation data set is performed based on the deformation trend prediction model, and the method includes: Collect historical deformation datasets of surrounding rock tunnels, including stress changes, displacement vectors, and tilt angles; Extracting time series features of the historical deformation data set; A long short-term memory network is constructed, and a gradient descent method is used to train the long short-term memory network according to the time series characteristics, with the historical deformation data set and deformation speed label as input, to output a deformation trend prediction model.

3. A deformation monitoring method for extremely high ground stress soft rock according to claim 2, characterized in that: The method further comprises: Obtaining model parameters of the deformation trend prediction model; An updated deformation data set of the surrounding rock tunnel is obtained, model parameters of the deformation trend prediction model are optimized in real time according to the updated deformation data set, and an updated deformation trend prediction model is output.

4. A deformation monitoring method for extremely high ground stress soft rock according to claim 1, characterized in that: If the segmented support decision maker detects that the predicted deformation speed is greater than the first preset threshold, it outputs a first support strength, connects the support device, and performs a support on the current surrounding rock tunnel according to the first support strength.

5. A deformation monitoring method for extremely high ground stress soft rock according to claim 4, characterized in that: If the segmented support decision maker detects that the predicted deformation speed is less than or equal to the first preset threshold, and the predicted deformation speed is greater than or equal to the second preset threshold, a second support strength is output, the support device is connected, and the current surrounding rock tunnel is supported once according to the second support strength; Wherein, the first support strength is greater than the second support strength.

6. A deformation monitoring method for extremely high ground stress soft rock according to claim 5, characterized in that: Connect the support device to perform primary support on the current surrounding rock tunnel, wherein the primary support includes top plate installation, anchor rod installation, anchor cable installation and initial concrete spraying; The supporting device is connected to perform secondary support on the current surrounding rock tunnel, wherein the secondary support includes top plate grouting, anchor rod grouting, anchor cable grouting and re-spraying concrete.

7. A deformation monitoring method for extremely high ground stress soft rock according to claim 6, characterized in that: Connect the support device to support the current surrounding rock tunnel once, and obtain the concrete granularity of the initial concrete spraying; The support device is connected to perform secondary support on the current surrounding rock tunnel to obtain the spraying concrete particle size of the secondary spraying concrete, and the spraying concrete particle size of the secondary spraying concrete is smaller than the spraying concrete particle size of the primary spraying concrete.

8. The deformation monitoring method for extremely high ground stress soft rock according to claim 1, characterized in that: The deformation monitoring sensor is used to monitor the current surrounding rock tunnel in real time to obtain a surrounding rock deformation data set, and the method includes: Perform real-time monitoring of the current surrounding rock tunnel according to the deformation monitoring sensor to obtain multi-source monitoring data; Performing time alignment processing on the multi-source monitoring data to obtain the multi-source monitoring data after the time alignment processing; The multi-source monitoring data after time series alignment are fused to obtain the surrounding rock deformation data set.

Images