Tunnel surrounding rock deformation monitoring method and system

Abstract

The invention discloses a tunnel surrounding rock deformation monitoring method and system, and relates to the technical field of surrounding rock deformation monitoring, and the method comprises the steps: interactively obtaining a surrounding rock state association set; monitoring equipment is configured, and a surrounding rock deformation monitoring array is generated; pre-constructing a surrounding rock deformation monitoring cloud; performing traceability analysis according to the surrounding rock deformation early warning to obtain construction technology prediction defects; performing construction deviation positioning to obtain a construction deviation prediction result; and generating a construction early warning instruction, and sending the construction early warning instruction to a construction operation and maintenance center. The technical problems that in the prior art, real-time, comprehensive and automatic monitoring of surrounding rock deformation in tunnel construction is difficult, the early warning precision is low, tunnel construction safety is not effectively guaranteed, and consequently construction efficiency is low are solved, and the purposes of automatic monitoring, accurate early warning and early warning of surrounding rock deformation in tunnel construction are achieved. And the safety of tunnel construction under complex geological conditions and the overall construction efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of surrounding rock deformation monitoring, and in particular to a tunnel surrounding rock deformation monitoring method and system. Background Art

[0002] In the field of tunnel engineering construction, as construction projects continue to expand into complex geological areas, traditional surrounding rock monitoring technology has increasingly exposed many limitations. Due to the weak cementation, uncementation, extremely soft stone and complex water-stable characteristics of the stratum, the surrounding rock often undergoes rapid plastic deformation and rheology during construction, with extremely poor stability, which can easily cause water and sand gushing. However, traditional monitoring technology is difficult to detect subtle changes in the surrounding rock in a timely and accurate manner, and cannot provide effective early warning for construction decisions. In terms of construction technology, there is a lack of systematic seepage field analysis methods, making it difficult to accurately grasp the dynamic impact of groundwater, the accuracy of advanced geological forecasts is insufficient, and the timing and methods of advanced support are also relatively blind, which often leads to frequent safety accidents. Moreover, in the construction safety guarantee link, the operation specifications are unclear, such as the key points of hidden danger investigation and cleaning during support, lining, and tunnel excavation, which greatly affects construction safety. At the same time, due to the lack of in-depth research on the physical and mechanical properties of the stratum, the construction efficiency is also quite low, and the advantages of equipment such as TBM are difficult to give full play.

[0003] The existing technology has the technical problems of difficulty in real-time and comprehensive automated monitoring of surrounding rock deformation during tunnel construction, low early warning accuracy, lack of effective guarantee for tunnel construction safety, and low construction efficiency. Summary of the invention

[0004] The present application provides a tunnel surrounding rock deformation monitoring method and system, which is used to solve the technical problems in the prior art that it is difficult to conduct real-time and comprehensive automated monitoring of surrounding rock deformation during tunnel construction, the early warning accuracy is low, and there is a lack of effective guarantee for tunnel construction safety, resulting in low construction efficiency.

[0005] In view of the above problems, the present application provides a tunnel surrounding rock deformation monitoring method and system.

[0006] In a first aspect of the present application, a method for monitoring deformation of surrounding rock in a tunnel is provided, the method comprising:

[0007] Interactively obtain a surrounding rock state association set, wherein the surrounding rock state association set includes multiple surrounding rock state association indicators; configure monitoring equipment in the tunnel construction area according to the surrounding rock state association set to generate a surrounding rock deformation monitoring array, wherein the surrounding rock deformation monitoring array includes multiple surrounding rock state monitoring devices corresponding to the multiple surrounding rock state association indicators; pre-build a surrounding rock deformation monitoring cloud, and build a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud; when the surrounding rock deformation monitoring cloud receives and analyzes the return data of the surrounding rock deformation monitoring array and the output result is a surrounding rock deformation warning, perform a source tracing analysis based on the surrounding rock deformation warning to obtain construction technology prediction defects; locate construction deviations based on the construction technology prediction defects to obtain construction deviation prediction results; generate construction warning instructions based on the construction deviation prediction results, and send the construction warning instructions to the construction operation and maintenance center.

[0008] A second aspect of the present application provides a tunnel surrounding rock deformation monitoring system, the system comprising:

[0009] A surrounding rock state association set acquisition module is used to interactively obtain a surrounding rock state association set, wherein the surrounding rock state association set includes multiple surrounding rock state association indicators; a surrounding rock deformation monitoring array generation module is used to configure monitoring equipment in the tunnel construction area according to the surrounding rock state association set to generate a surrounding rock deformation monitoring array, wherein the surrounding rock deformation monitoring array includes multiple surrounding rock state monitoring devices corresponding to the multiple surrounding rock state association indicators; a communication link construction module is used to pre-build a surrounding rock deformation monitoring cloud and build a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud; a construction technology prediction defect acquisition module is used to perform source tracing analysis based on the surrounding rock deformation warning to obtain construction technology prediction defects when the surrounding rock deformation monitoring cloud receives and analyzes the return data of the surrounding rock deformation monitoring array and the output result is a surrounding rock deformation warning; a construction deviation prediction result acquisition module is used to locate the construction deviation based on the construction technology prediction defect to obtain the construction deviation prediction result; a construction warning instruction generation module is used to generate a construction warning instruction based on the construction deviation prediction result and send the construction warning instruction to the construction operation and maintenance center.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] Interactively obtain a surrounding rock state association set, wherein the surrounding rock state association set includes multiple surrounding rock state association indicators; configure monitoring equipment in the tunnel construction area according to the surrounding rock state association set to generate a surrounding rock deformation monitoring array, wherein the surrounding rock deformation monitoring array includes multiple surrounding rock state monitoring equipment corresponding to the multiple surrounding rock state association indicators; pre-build a surrounding rock deformation monitoring cloud, and build a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud; when the surrounding rock deformation monitoring cloud receives and analyzes the return data of the surrounding rock deformation monitoring array, and the output result is a surrounding rock deformation warning, perform a source analysis based on the surrounding rock deformation warning to obtain construction technology prediction defects; locate construction deviations based on the construction technology prediction defects to obtain construction deviation prediction results; generate construction warning instructions based on the construction deviation prediction results, and send the construction warning instructions to the construction operation and maintenance center. The technical effect of realizing automated monitoring and accurate warning of surrounding rock deformation in tunnel construction, improving the safety of tunnel construction under complex geological conditions and overall construction efficiency is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a tunnel surrounding rock deformation monitoring method provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a tunnel surrounding rock deformation monitoring system provided in an embodiment of the present application.

[0015] Explanation of the reference numerals: surrounding rock state association set acquisition module 10, surrounding rock deformation monitoring array generation module 20, communication link construction module 30, construction technology prediction defect acquisition module 40, construction deviation prediction result acquisition module 50, construction early warning instruction generation module 60. DETAILED DESCRIPTION

[0016] The present application provides a tunnel surrounding rock deformation monitoring method and system, which is used to solve the technical problems in the prior art that it is difficult to conduct real-time and comprehensive automated monitoring of surrounding rock deformation during tunnel construction, the early warning accuracy is low, and there is a lack of effective protection for tunnel construction safety, resulting in low construction efficiency.

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a tunnel surrounding rock deformation monitoring method, the method comprising:

[0019] Step S100: interactively obtaining a surrounding rock state association set, wherein the surrounding rock state association set includes a plurality of surrounding rock state association indicators.

[0020] Specifically, through multi-channel interaction, a key information set that can comprehensively and accurately reflect the state of the surrounding rock is obtained, namely the surrounding rock state association set. This set covers multiple surrounding rock state association indicators, which reveal the characteristics and state of the surrounding rock from different dimensions. For example, the displacement index of the surrounding rock can accurately measure the movement distance and trend of the surrounding rock in different directions through professional displacement monitoring equipment. Whether it is a tiny millimeter-level displacement or a centimeter-level or even larger movement that may occur under the action of complex geological stress, it can be captured sensitively, thereby intuitively presenting the stability changes of the surrounding rock. The strain index uses strain sensors to carefully monitor the deformation degree of the internal structure of the surrounding rock when it is subjected to external pressure, reflecting the force response of the surrounding rock from a microscopic level, and helping to determine whether the surrounding rock is in the elastic deformation range or has approached the plastic deformation stage. The crack extension index uses equipment such as crack monitors to closely monitor the generation, extension direction, and expansion speed of cracks on the surface and inside of the surrounding rock, which is of key significance for evaluating the structural integrity of the surrounding rock and predicting potential collapse risks. In addition, it may also include the humidity index of the surrounding rock, because in complex and weak strata, humidity changes may affect the mechanical properties of the surrounding rock, and thus affect its stability; and the acoustic wave propagation velocity index of the surrounding rock, through the propagation characteristics of the acoustic wave in the surrounding rock, indirectly infer the density of the surrounding rock, internal structure changes, etc. By interactively integrating these various surrounding rock state related indicators, a complete surrounding rock state related set is formed, which provides indispensable basic data support for subsequent accurate monitoring, scientific analysis and effective decision-making, ensuring that tunnel construction can be steadily advanced in a safe and controllable state.

[0021] Step S200: configuring monitoring equipment in the tunnel construction area according to the surrounding rock state association set to generate a surrounding rock deformation monitoring array, wherein the surrounding rock deformation monitoring array includes a plurality of surrounding rock state monitoring devices corresponding to the plurality of surrounding rock state association indicators.

[0022] Specifically, based on the rock state association set obtained through careful interaction in the early stage, a systematic and professional monitoring equipment configuration will be carried out in the tunnel construction area. For each rock state association indicator in the association set, a highly adapted monitoring device will be accurately deployed, thus building a powerful rock deformation monitoring array. Taking displacement indicators as an example, high-precision laser displacement sensors or total stations and other equipment will be installed at key positions of the tunnel surrounding rock. These devices can capture the displacement changes of the surrounding rock in all directions in real time with their excellent measurement accuracy and stability. For strain indicators, strain gauges or optical fiber strain sensors will be buried inside the surrounding rock to accurately sense the deformation degree of the microstructure of the surrounding rock during the stress process, and convert the stress and strain information inside the surrounding rock into electrical signals or optical signals for transmission. For crack extension indicators, crack meters or high-definition camera monitoring equipment will be placed in areas where cracks may occur. The crack meter can accurately measure the dynamic changes of the crack width, while the camera equipment can record the development trajectory of the crack in the form of images, providing an intuitive basis for analyzing the causes and expansion trends of the cracks. In addition, if the correlation set includes humidity indicators, humidity sensors will be distributed in different locations of the tunnel to monitor the changes in humidity in the surrounding environment of the surrounding rock in real time, providing data support for evaluating the impact of humidity on the stability of the surrounding rock. For the sound wave propagation speed indicator, the sound wave transmitting and receiving devices will be reasonably arranged to indirectly judge the density, integrity and internal structure changes of the surrounding rock by transmitting sound waves and measuring their propagation time and wave speed changes in the surrounding rock. In this way, each surrounding rock status monitoring device performs its duties to ensure that any surrounding rock status changes can be monitored in a timely and accurate manner, effectively ensuring the safety of tunnel construction.

[0023] Step S300: pre-constructing a surrounding rock deformation monitoring cloud, and establishing a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud.

[0024] Specifically, the surrounding rock deformation monitoring cloud is pre-built. It is built based on advanced cloud computing technology and big data processing architecture, and has powerful data storage, analysis and processing capabilities. To build this cloud, it is necessary to conduct in-depth analysis of the surrounding rock state association set, and through the analysis of the indicator linkage effect, explore the hidden internal connections between the associated indicators and decompose them into K groups of state linkage indicators. Then, using the principal component analysis method, K surrounding rock deformation identification models are carefully constructed from these group indicators, which can accurately judge the surrounding rock deformation status based on the input data. Finally, by connecting these models in parallel, the construction of a fully functional and efficient surrounding rock deformation monitoring cloud is completed. At the same time, it is also crucial to build a communication link between the monitoring array and the cloud. According to the mapping relationship between multiple surrounding rock state association indicators and K groups of state linkage indicators, a large number of surrounding rock state monitoring devices are reasonably divided into K groups. Each group of equipment is equipped with a dedicated data transfer edge node, and a stable and reliable wired communication link is built to ensure the high-speed and stable transmission of monitoring data from the device end to the edge node. Next, a wireless communication link is established between the edge node and the K surrounding rock deformation identification models in the cloud, and high-speed wireless network technology is used to achieve rapid data upload and timely issuance of instructions, so that the entire monitoring system can achieve real-time and efficient data interaction and ensure the continuity and accuracy of the monitoring work.

[0025] Step S400: When the surrounding rock deformation monitoring cloud receives and analyzes the feedback data of the surrounding rock deformation monitoring array and outputs a surrounding rock deformation warning, a source analysis is performed based on the surrounding rock deformation warning to obtain construction technology prediction defects.

[0026] Specifically, when the surrounding rock deformation monitoring cloud receives the data sent back by the monitoring array, it first uses the support vector machine (SVM) algorithm to mark the different degrees of surrounding rock deformation in the historical monitoring data into different categories, and then finds the optimal hyperplane to distinguish the data of each category, builds a classification model, and classifies and judges the new data. At the same time, the decision tree algorithm is used to build a tree structure based on the characteristics of displacement rate, strain change, etc., and the deformation category to which the new data belongs is judged along the branch according to the characteristic value. For deep learning technology, the convolutional neural network (CNN) is used to convert the displacement and strain data of the continuous time series into image form, and the spatiotemporal feature patterns are automatically extracted through the convolution layer, pooling layer and fully connected layer to judge the deformation trend of the surrounding rock. In addition, recurrent neural networks (RNNs) and their variants (such as LSTM and GRU) are used to process sequence data and capture temporal dependencies with their memory function and special gating mechanism. The analysis results of these algorithms and techniques are integrated. Once the surrounding rock deformation warning is output, the abnormal values ​​in the warning are input based on the construction deformation causal network. The causal path of construction deformation is found through the nodes and causal edge relationships, and the relevant construction technologies and probabilities are extracted. The risks are evaluated in combination with the historical construction time, and finally the construction technology prediction defects are determined.

[0027] Step S500: locating construction deviations according to the construction technology prediction defects to obtain construction deviation prediction results.

[0028] Specifically, in the quality and safety control process of tunnel construction, the goal is to accurately locate construction deviations and ensure smooth construction. After obtaining the predicted defects of construction technology, the professional technical team will carry out in-depth work on locating construction deviations. For each construction technology involved in the predicted defects, such as precipitation test technology and advance support technology, the construction records are reviewed in detail, including parameter settings, construction sequence, material usage and other information during the construction process. For example, if the advance support technology is judged to have defects, the length, spacing, anchoring force and other parameters of the anchor rods will be carefully checked to see if they meet the design requirements, as well as the installation angle of the support structure, the thickness and strength of the shotcrete, etc. At the same time, a comprehensive analysis is conducted based on the actual conditions of the construction site, such as changes in geological conditions and the impact of the construction environment. By comparing the design plan with the actual construction operation, the differences between the two are found, and these differences are possible construction deviations. Using advanced measuring instruments and testing equipment, the actual state of the tunnel surrounding rock is accurately measured again, and compared and verified with the data collected in the early stage of the monitoring array to further clarify the specific location and degree of the deviation. In addition, we will refer to the construction deviations and solutions in similar engineering cases to conduct a more comprehensive and in-depth analysis of the current construction deviations. After this series of rigorous and meticulous work, we will eventually obtain the construction deviation prediction results, which will provide an accurate basis for the subsequent formulation of targeted rectification measures to ensure the safe and efficient construction of the tunnel.

[0029] Step S600: Generate a construction warning instruction according to the construction deviation prediction result, and send the construction warning instruction to the construction operation and maintenance center.

[0030] Specifically, based on the accurate construction deviation prediction results obtained, the construction early warning instructions are quickly generated. The instructions are rich in content and highly targeted. First, the specific circumstances of the construction deviation will be clearly explained, including the type of deviation, the location of occurrence, the degree of deviation, and the potential risks that may be caused, such as further deterioration of surrounding rock stability and increased risk of water and sand gushing. At the same time, the instructions will clearly give detailed rectification suggestions, such as adjusting construction parameters, optimizing construction processes, replacing construction materials and other specific measures, as well as the implementation priority and expected completion time of each measure. After the instructions are generated, the construction early warning instructions will be sent to the construction operation and maintenance center at the fastest speed with the help of efficient and reliable communication systems, such as dedicated wireless networks, wired communication lines or integrated communication platforms. Construction adjustments will be strictly carried out in accordance with the rectification suggestions to ensure timely correction of deviations, restore normal construction order, effectively ensure tunnel construction safety, improve construction efficiency, and reduce project delays and safety accident risks caused by construction deviations.

[0031] In a possible implementation, step S300 further includes:

[0032] Step S310: performing indicator linkage effect analysis on the surrounding rock state association set to decompose the surrounding rock state association set into K groups of state linkage indicators.

[0033] Step S320: constructing K surrounding rock deformation identification models by performing principal component analysis on the K groups of state linkage indicators.

[0034] Step S330: completing the construction of the surrounding rock deformation monitoring cloud by connecting the K surrounding rock deformation identification models in parallel.

[0035] Specifically, in the initial stage of building the surrounding rock deformation monitoring cloud, through the detailed analysis of the linkage effect of indicators, the internal connection between the indicators is explored and decomposed into K groups of state linkage indicators. Taking the linkage indicators of displacement, stress and crack extension as an example, in the actual tunnel construction scenario, if the displacement of the surrounding rock continues to increase, this may be due to changes in internal stress. When the stress exceeds the safety range and the internal structure of the surrounding rock cannot bear it, it will cause the generation and expansion of cracks. There is a close causal relationship between displacement, stress and crack extension. They influence and interact with each other and reflect the deformation state of the surrounding rock. Once the displacement continues to increase and the stress exceeds the standard accompanied by the continuous expansion of cracks, it often indicates that the deformation and destruction of the surrounding rock have approached an irreversible dangerous stage. Let's look at the linkage indicators of pore water pressure, displacement and ground subsidence. In complex and weak formations, changes in pore water pressure have a significant impact on the stability of the surrounding rock. When the pore water pressure increases, it will generate additional forces on the surrounding rock, causing the stress state of the surrounding rock to change, which in turn leads to increased displacement. The changes in the displacement of the surrounding rock will be transmitted to the surface, causing ground subsidence. Especially when the water flow direction is unreasonable or the precipitation measures are inappropriate, a vicious cycle is formed between pore water pressure and surrounding rock deformation. Water pressure causes surrounding rock deformation, which in turn affects the water flow channel, further changing the water pressure distribution, and ultimately may lead to serious surface subsidence and surrounding rock damage. Through the precise analysis of these complex linkage relationships, the surrounding rock state association set is scientifically decomposed into K groups of state linkage indicators, laying the foundation for the subsequent construction of an accurate monitoring model.

[0036] After completing the index grouping, principal component analysis is performed on K groups of state linkage indicators to construct K surrounding rock deformation identification models. Principal component analysis aims to extract key information from many related variables (i.e., state linkage indicators) and replace the original indicators with a few unrelated comprehensive indicators (principal components), thereby simplifying the data structure while retaining the main characteristics of the original data. For each group of state linkage indicators, principal component analysis assigns different weights according to the importance of each indicator on the surrounding rock deformation, and converts it into a new set of comprehensive indicators, i.e., principal components. These principal components can reflect the information contained in the original indicators to the greatest extent and are independent of each other. For example, when analyzing a group of state linkage indicators including displacement change rate, stress gradient, and crack width change, principal component analysis may find that the displacement change rate plays a leading role in reflecting the current deformation trend of the surrounding rock, the stress gradient has a greater impact on the potential development of deformation, and the crack width change is a key factor in judging the degree of damage to the surrounding rock structure. By combining these indicators with reasonable weights, a principal component that can comprehensively characterize the characteristics of this group of indicators is formed. In this way, K groups of state linkage indicators are processed separately to obtain K principal components, each of which summarizes the relationship between the corresponding group of indicators and surrounding rock deformation from different angles. Based on these principal components, K surrounding rock deformation identification models are constructed, which can accurately judge the deformation state of the surrounding rock according to the input monitoring data, providing strong support for subsequent cloud-based decision-making.

[0037] The construction of the surrounding rock deformation monitoring cloud is completed. Parallel operation means that these models run simultaneously on the cloud platform and jointly process real-time data from the monitoring array. Each model analyzes and judges the data independently, and then summarizes their respective results to the comprehensive decision-making module on the cloud. This parallel structure gives full play to the advantages of each model and improves the reliability and accuracy of the system. When the monitoring data is transmitted to the cloud, K models receive and process it at the same time. For example, one model may have a unique advantage in analyzing displacement-related data, while another model is more sensitive to changes in pore water pressure. They each interpret the data from different dimensions. The comprehensive decision-making module integrates the output results of each model and obtains the final conclusion of surrounding rock deformation judgment through weighted average, majority voting or other fusion algorithms. The surrounding rock deformation monitoring cloud constructed in this way can process massive monitoring data in real time and efficiently, and judge the surrounding rock deformation in a timely and accurate manner. Once an abnormality is found, an early warning signal can be quickly issued to provide strong protection for construction safety and ensure that tunnel construction is carried out safely and orderly under complex geological conditions.

[0038] In a possible implementation, step S320 further includes:

[0039] Step S321: calling surrounding rock deformation data for the K groups of state linkage indicators to obtain K groups of historical state anomaly sequences.

[0040] Step S322: performing statistics on the recurrence frequency of the indicator sequence of the K groups of status linkage indicators in the K groups of historical status abnormality sequences to obtain the K groups of sequence position information.

[0041] Step S323: configuring the linkage hierarchical relationship of the K groups of state linkage indicators according to the K groups of sequence position information to obtain K state abnormality monitoring sequences.

[0042] Step S324: pre-constructing a surrounding rock risk identification model set corresponding to the surrounding rock state association set.

[0043] Step S325: Model calling and hierarchical connection are performed in the surrounding rock risk identification model set according to the K state abnormality monitoring sequences to complete the construction of the K surrounding rock deformation identification models.

[0044] Specifically, in the process of building the surrounding rock deformation identification model, for the K groups of state linkage indicators, it is necessary to deeply explore the historical monitoring data resources and call the surrounding rock deformation data. These historical data cover the monitoring information at different stages and different geological conditions in the past tunnel construction process, and are a valuable basis for analyzing the deformation law of the surrounding rock. By screening and sorting the massive historical data, taking each group of state linkage indicators as a clue, we find the data fragments with abnormal states, and then obtain K groups of historical state abnormal sequences. For example, for the linkage indicators of displacement and stress, when the historical data shows that the displacement increases sharply in a certain period of time and the stress far exceeds the normal range, these continuous data points constitute a set of historical state abnormal sequences. These abnormal sequences reflect the unstable situation that the surrounding rock may face in the past construction, provide key samples for subsequent analysis, and help to identify the surrounding rock problems under what combination of indicators change, so as to accumulate empirical data for building an accurate deformation identification model.

[0045] In order to perform the recurrence frequency statistics of the indicator sequence of K groups of state linkage indicators in K groups of historical state abnormality sequences and obtain the position information of K groups of sequences, the sliding window algorithm combined with the hash table data structure is used to achieve this. First, a sliding window of appropriate size is set for each group of historical state abnormality sequences, and the sliding starts from the starting position of the sequence. For the state linkage indicator value in the window, it is mapped to a unique hash value through a specific hash function, and stored in the hash table, and the position of the window in the sequence is recorded as the sequence position information. After each sliding window, the number of occurrences of the corresponding hash value in the hash table is updated, that is, the statistics of the frequency of occurrence of the indicator sequence are realized. After traversing the entire historical state abnormality sequence, the hash table stores the recurrence frequency of each indicator sequence and its corresponding sequence position information, thereby providing key data support for the subsequent linkage hierarchical relationship configuration, which helps to more accurately build a surrounding rock deformation identification model and ensure the safety of tunnel construction.

[0046] In order to configure the linkage hierarchical relationship of K groups of state linkage indicators according to K groups of sequence position information and obtain K state abnormality monitoring sequences, an algorithm based on time series analysis and causal relationship mining is adopted. First, the time series data corresponding to each group of sequence position information is preprocessed, such as data cleaning, interpolation and other operations, to ensure the integrity and accuracy of the data. Then, the Granger causality test method is used to analyze the causal relationship between the state linkage indicators. If indicator A changes before indicator B in time, and the change of indicator A can significantly affect the change trend of indicator B, it is determined that indicator A has a causal relationship with indicator B, and indicator A is placed at a higher level. According to the results of this causal relationship analysis, a directed acyclic graph is constructed to represent the linkage hierarchical relationship. Finally, based on the constructed directed acyclic graph, starting from the starting node (i.e., the indicator at the highest level), the indicators are combined in sequence according to the hierarchical order to form K state abnormality monitoring sequences, thereby providing strong support for accurately monitoring the deformation state of the surrounding rock and ensuring the safety of tunnel construction.

[0047] When pre-constructing the surrounding rock risk identification model set corresponding to the surrounding rock state association set, the random forest algorithm is used to construct multiple decision tree models by sampling with replacement on a large amount of historical construction data (including surrounding rock state parameters, construction process information, risk events that have occurred, etc.). Each decision tree model evaluates the surrounding rock risk from a different angle. These decision trees together constitute the surrounding rock risk identification model set, which comprehensively considers the impact of multiple factors on surrounding rock stability.

[0048] When calling and hierarchically connecting models in the surrounding rock risk identification model set according to K state anomaly monitoring sequences, the connection relationship between models is constructed based on the Bayesian network algorithm. For each state anomaly monitoring sequence, the conditional probability relationship between the indicators is analyzed, converted into nodes and directed edges in the Bayesian network, and the dependency relationship between the models is determined. Then, according to the structure of the Bayesian network, starting from the model related to the starting indicator of the sequence, the subsequent related models are called and connected in sequence along the directed edges, and the parameters of each model are updated through Bayesian reasoning. Finally, the construction of K surrounding rock deformation identification models is completed, and the accurate prediction of the surrounding rock deformation state is achieved to ensure the safety of tunnel construction.

[0049] In a possible implementation, step S300 further includes:

[0050] Step S340: dividing the plurality of surrounding rock state monitoring devices into K groups of surrounding rock state monitoring devices according to the mapping relationship between the plurality of surrounding rock state associated indicators and the K groups of state linkage indicators.

[0051] Step S350: configuring K data transfer edge nodes for the K groups of surrounding rock status monitoring equipment.

[0052] Step S360: constructing a wired communication link between the K groups of surrounding rock status monitoring equipment and the K data transfer edge nodes.

[0053] Step S370: constructing wireless communication links between the K data transfer edge nodes and the K surrounding rock deformation identification models in the surrounding rock deformation monitoring cloud.

[0054] Specifically, according to the mapping relationship between multiple surrounding rock state-related indicators and K groups of state linkage indicators, a large number of surrounding rock state monitoring devices are scientifically grouped. Each surrounding rock state-related indicator corresponds to a specific monitoring task, and these indicators have an inherent logical connection with the K groups of state linkage indicators. For example, the displacement indicator may be closely related to a group of state linkage indicators including displacement, stress, and crack extension, because displacement changes are often accompanied by stress adjustment and crack development. According to this mapping relationship, the sensors and other equipment responsible for monitoring displacement are divided into the corresponding group of surrounding rock state monitoring equipment. Similarly, the equipment for monitoring pore water pressure will be grouped according to its relationship with the group of state linkage indicators of pore water pressure, displacement, and ground settlement. Through such a detailed division, each group of surrounding rock state monitoring equipment can work closely around a group of state linkage indicators, providing guarantee for the accuracy and effectiveness of subsequent data collection and transmission, ensuring that the monitoring system can comprehensively and accurately capture the surrounding rock state change information from multiple dimensions, and provide reliable data support for tunnel construction safety.

[0055] After completing the grouping of monitoring equipment, we focus on configuring K data transfer edge nodes for K groups of surrounding rock condition monitoring equipment. Each edge node has a certain data processing capability and storage capacity, and can perform preliminary processing on the data from the group of surrounding rock condition monitoring equipment to which it is connected, such as data cleaning, format conversion and other operations, to reduce the burden of cloud data processing and improve data transmission efficiency. For example, for the original displacement data monitored, the edge node can perform simple data verification locally, remove obviously abnormal data points, and then package the processed data for transmission. At the same time, the configuration of edge nodes makes the connection between the monitoring equipment and the cloud more flexible and stable. Even in complex tunnel construction environments, such as electromagnetic interference or signal obstruction, it can ensure that the data has a reliable transfer channel and ensure the continuity of data transmission, laying a solid foundation for the subsequent construction of efficient communication links, effectively avoiding monitoring loopholes caused by data transmission interruptions, and further ensuring tunnel construction safety.

[0056] After configuring the edge nodes, build wired communication links between K groups of surrounding rock state monitoring equipment and K data transfer edge nodes. With its high stability and high reliability, the wired communication link becomes a key link to ensure stable data transmission. For each group of surrounding rock state monitoring equipment and the corresponding edge node, appropriate wired communication technology, such as Ethernet, RS-485 and other standard bus technologies, is used for connection. These technologies have the characteristics of fast transmission speed and strong anti-interference ability, which can ensure that the massive data collected by the monitoring equipment is accurately transmitted to the edge node. For example, in the tunnel construction environment, despite the electromagnetic interference generated by various mechanical equipment and the influence of complex geological conditions, the wired communication link can effectively shield these interferences, ensuring that the surrounding rock state data collected by monitoring equipment such as displacement sensors and strain gauges in real time is stably transmitted to the edge node. At the same time, the wired communication link is easy to maintain and manage. Once a fault occurs, it can be quickly located and repaired, ensuring that the data collection and transmission work of the entire monitoring system is not affected, providing continuous and reliable data support for tunnel construction safety, enabling the construction team to grasp the changes in surrounding rock state in a timely manner and make accurate construction decisions.

[0057] As the last step in building the communication link, a wireless communication link is built between the K data transfer edge nodes and the K surrounding rock deformation identification models in the surrounding rock deformation monitoring cloud. The wireless communication link injects flexibility and efficiency into the entire monitoring system, realizing the rapid upload of data and the timely issuance of instructions. Advanced wireless communication technologies, such as 5G and Wi-Fi6, are used to build a high-speed data channel between the data transfer edge node and the cloud. These technologies can meet the requirements of the monitoring system for large data volume transmission and low latency, ensuring that the data processed by the edge node can be quickly uploaded to the cloud for real-time analysis by the K surrounding rock deformation identification models. At the same time, the instructions generated by the cloud based on the analysis results can also be quickly issued to the edge node through the wireless communication link, and then transmitted to the corresponding monitoring equipment to achieve real-time control and adjustment of the tunnel construction process. For example, when the cloud model analysis finds that the surrounding rock deformation trend is abnormal, an early warning instruction is immediately sent to the edge node through the wireless communication link, and the edge node then notifies the relevant monitoring equipment to start a more intensive data collection mode, so that the construction team can take timely measures, such as strengthening support or adjusting the construction process, to effectively ensure the safety of tunnel construction, avoid safety accidents caused by communication delays, and ensure smooth construction.

[0058] In a possible implementation, step S400 further includes:

[0059] Step S410: the surrounding rock deformation monitoring cloud receives the real-time monitoring data array transmitted back by the surrounding rock deformation monitoring array.

[0060] Step S420: according to the mapping relationship between the plurality of surrounding rock state monitoring devices and the plurality of surrounding rock state associated indicators, and with the K groups of surrounding rock state monitoring devices as constraints, the real-time monitoring data array is divided into K groups of real-time monitoring data.

[0061] Step S430: After the K groups of real-time monitoring data are loaded and sorted according to the K abnormal state monitoring sequences, the K groups of real-time monitoring data are loaded into the K surrounding rock deformation identification models for indirect judgment of surrounding rock deformation, and K surrounding rock deformation judgment results are output.

[0062] Step S440: When any surrounding rock deformation judgment result among the K surrounding rock deformation judgment results is a non-empty set, the surrounding rock deformation warning is generated, wherein the surrounding rock deformation warning includes H surrounding rock state-associated abnormal values.

[0063] Step S450: performing source tracing analysis based on the surrounding rock deformation warning to obtain the predicted defects of the construction technology.

[0064] Specifically, in the key process of tunnel construction safety monitoring, an important stage of data processing and analysis has been opened. The surrounding rock deformation monitoring cloud receives the real-time monitoring data array sent back from the surrounding rock deformation monitoring array. These real-time monitoring data contain rich information on the state of the surrounding rock in the tunnel construction area, which is collected uninterruptedly by multiple surrounding rock state monitoring devices distributed in various key locations. The data is transmitted to the cloud in a high-speed and stable manner through a pre-built communication link. The cloud has a strong data receiving capability and can process data traffic from many monitoring devices at the same time, ensuring the integrity and timeliness of the data, providing sufficient original data for subsequent accurate analysis, and laying the foundation for timely grasp of the dynamic changes of the surrounding rock. It is the first line of defense to ensure the safety of tunnel construction.

[0065] When the cloud successfully receives the real-time monitoring data array, it scientifically divides the massive real-time monitoring data array based on the carefully set mapping relationship between multiple surrounding rock state-related indicators and multiple surrounding rock state monitoring devices, with K groups of surrounding rock state monitoring devices as constraints. For example, the data collected by the monitoring equipment corresponding to the displacement indicator will be divided into the group of real-time monitoring data related to the displacement. Similarly, the data of indicators such as stress and pore water pressure will also be accurately classified according to their corresponding monitoring equipment. This division method enables the data to be organized in an orderly manner according to the surrounding rock state characteristics it reflects, which facilitates subsequent targeted analysis of different groups of data, ensuring that each data point can play the maximum value in the corresponding analysis model, providing a detailed data foundation for accurately judging the deformation state of the surrounding rock, and further improving the level of construction safety assurance.

[0066] After completing the data division, the K groups of real-time monitoring data are carefully loaded and sorted according to the K state abnormal monitoring sequences to ensure that the input order of the data conforms to the pre-set monitoring logic. The sorted K groups of real-time monitoring data are loaded into K surrounding rock deformation identification models in turn. These models use advanced algorithms and deep learning technologies to conduct in-depth mining and analysis of the data. Through the learning of historical data and model training, the model can identify the characteristic patterns in the data, thereby indirectly judging the surrounding rock deformation. For example, the model can comprehensively judge whether the current deformation state of the surrounding rock is within the normal range based on various information such as the changing trend of displacement data, the distribution of stress, and the characteristics of crack expansion, and finally output K surrounding rock deformation judgment results, which provide a key basis for timely discovery of potential surrounding rock deformation risks and ensure that construction safety hazards can be detected and handled as early as possible.

[0067] After obtaining K surrounding rock deformation judgment results, the results are evaluated and warned. Once any of the K judgment results for surrounding rock deformation is a non-empty set, it means that an abnormal signal appears in the monitoring data, indicating that the surrounding rock deformation exceeds the normal range. At this time, a surrounding rock deformation warning is immediately generated, which contains H surrounding rock state-related abnormal values, that is, surrounding rock state-related indicators. These abnormal values ​​are key clues for judging the abnormal state of the surrounding rock. They involve multiple aspects such as sudden increase in displacement, abnormal concentration of stress, and sharp changes in pore water pressure. The warning information will be promptly transmitted to relevant staff so that they can quickly take countermeasures, such as strengthening on-site monitoring, organizing experts to hold consultations, etc., to ensure that the safety of tunnel construction can be timely and effectively guaranteed, and to avoid safety accidents caused by surrounding rock deformation.

[0068] After generating the surrounding rock deformation warning, the root cause of the problem is found through in-depth traceability analysis to obtain the construction technology prediction defects. Based on the construction deformation causal network constructed in the early stage, the H outliers in the surrounding rock deformation warning are input into the network. The construction deformation causal network is formed by converting multiple surrounding rock state-related indicators into state-related causal nodes, abstracting multiple sample construction technologies into construction defect causal nodes, and constructing causal edges based on rich historical construction defect data, and then reasonably allocating conditional probabilities according to the overlapping frequency of causal edges. By searching for paths related to outliers in this complex network, H construction deformation causal paths are accurately found, and then H groups of construction technologies related to them and the corresponding H groups of causal conditional probabilities are extracted. The historical construction time of these construction technologies is further interactively obtained, and the causal conditional probability and historical construction time are comprehensively considered. The risk assessment model is used to conduct a comprehensive risk contribution evaluation. Finally, W construction technologies with risk contributions higher than the preset threshold are accurately locked and determined as construction technology prediction defects, providing a clear direction for subsequent targeted improvement of construction technology and adjustment of construction plans, ensuring that tunnel construction can be carried out safely and efficiently.

[0069] In a possible implementation, step S440 further includes:

[0070] Step S441: constructing a plurality of state-related causal nodes based on the plurality of surrounding rock state-related indicators.

[0071] Step S442: interactively obtain a plurality of sample construction technologies, and construct a plurality of construction defect cause-and-effect nodes based on the plurality of sample construction technologies.

[0072] Step S443: interactively obtain historical construction defect data, and construct causal edges between the multiple state-associated causal nodes and the multiple construction defect causal nodes based on the historical construction defect data.

[0073] Step S444: Conditional probability allocation is configured according to the overlapping frequency of causal edges between causal nodes to complete the construction of the construction deformation causal network.

[0074] Specifically, multiple state-related causal nodes are constructed based on multiple surrounding rock state-related indicators. These surrounding rock state-related indicators are key elements that comprehensively reflect the surrounding rock state, such as displacement, stress, crack extension, pore water pressure, etc. Each indicator is converted into a state-related causal node to capture the change information of the surrounding rock state. Taking displacement as an example, the state-related causal node corresponding to the displacement indicator can reflect the changes in the spatial position of the surrounding rock in real time. Whether it is a small displacement adjustment or a large movement trend, it can be characterized by this node. These nodes are interrelated and independent of each other, and together constitute the basic architecture of the construction deformation causal network, which provides a key information carrier for the subsequent accurate analysis of the causal relationship between surrounding rock deformation and construction technology, and is the cornerstone of building a precise causal network.

[0075] After constructing the state-associated causal nodes, we focus on acquiring multiple sample construction technologies through interaction, and construct multiple construction defect causal nodes based on these sample construction technologies. The sample construction technologies cover various processes, methods and operation procedures involved in the tunnel construction process, such as precipitation test technology, advance support technology, lining construction technology, etc. For each sample construction technology, the defects that may occur during the construction process are analyzed, and these potential defects are abstracted as construction defect causal nodes. For example, in the advance support technology, if the installation angle of the anchor is inaccurate or the anchoring force is insufficient, these possible defects will be defined as the corresponding construction defect causal nodes. These nodes represent the weak links in the construction process. They interact with the state-associated causal nodes and together constitute a complex causal network, which provides important node support for in-depth exploration of the intrinsic connection between construction technology and surrounding rock deformation, and helps to accurately trace the root causes of construction problems.

[0076] After the initial construction of the state-related causal nodes and the construction defect causal nodes is completed, the historical construction defect data is obtained interactively, and the causal edges between multiple state-related causal nodes and multiple construction defect causal nodes are constructed based on these rich data. The historical construction defect data records the various problems that actually occurred in the past tunnel construction, as well as the surrounding rock state and construction technology at that time. Through in-depth analysis of these data, if it is found that a certain construction defect (such as abnormal pore water pressure due to insufficient precipitation test) is always accompanied by a specific surrounding rock state change (such as increased surrounding rock displacement), then a causal edge is established between the corresponding construction defect causal node and the state-related causal node. The direction of the causal edge indicates the direction of the causal relationship, that is, from construction defects to surrounding rock state changes. The existence or absence of the causal edge and the combination of nodes connected by it intuitively reflect the association pattern between construction technology defects and surrounding rock deformation, providing a structural basis for subsequent probability analysis and being able to sort out a clear causal context from complex data.

[0077] As the last key step in constructing the construction deformation causal network, conditional probability allocation is configured according to the overlapping frequency of causal edges between causal nodes, thereby completing the construction of the entire network. The overlapping frequency of causal edges is an important basis for measuring the abnormal state of a specific surrounding rock caused by a construction defect. If a causal edge appears frequently in historical data, it means that there is a strong causal relationship between the construction defect and the corresponding surrounding rock state change. Based on this, a reasonable conditional probability value is assigned to each causal edge, indicating the probability of the corresponding surrounding rock state abnormality under the condition of a specific construction defect. For example, if historical data shows that the probability of surrounding rock crack expansion is high when the anchor bolt anchoring force is insufficient in multiple advance support technologies, then a higher conditional probability value will be assigned to the causal edge connecting the construction defect causal node of insufficient anchor bolt anchoring force in the advance support technology and the causal node associated with the surrounding rock crack expansion state. Through such detailed conditional probability configuration, the construction deformation causal network was completely constructed, which not only enables it to qualitatively describe the causal relationship between construction technology and surrounding rock deformation, but also quantitatively evaluate the risk probability of surrounding rock deformation under various circumstances, providing powerful tool support for subsequent accurate traceability analysis and construction technology defect prediction, effectively ensuring the safety of tunnel construction.

[0078] In a possible implementation, step S450 further includes:

[0079] Step S451: inputting the H surrounding rock state-associated abnormal values ​​in the surrounding rock deformation early warning into the construction deformation causal network, and screening to obtain H construction deformation causal paths.

[0080] Step S452: Extract construction techniques according to the H construction deformation causal paths to obtain H groups of construction techniques and H groups of causal conditional probabilities.

[0081] Step S453: interactively obtain H historical construction times of the H groups of construction techniques.

[0082] Step S454: Evaluate the risk contribution of the H groups of construction technologies according to the H groups of causal conditional probabilities and H historical construction times, and obtain W construction technologies whose risk contributions are higher than a preset threshold as the construction technology prediction defects.

[0083] Specifically, in order to input H surrounding rock state-associated abnormal values ​​into the construction deformation causal network and screen out H construction deformation causal paths, the depth-first search (DFS) algorithm is used. Starting from the state-associated causal node corresponding to each abnormal value, a depth-first traversal is performed along the causal edge. During the traversal process, the nodes and edges passed through are recorded to form a path. When the construction defect causal node is traversed or the path cannot be further expanded, it is determined whether the path meets the conditions related to the abnormal value (such as the combination of nodes and edges on the path can explain the cause of the abnormal value). If so, the path is saved as a construction deformation causal path. Repeat this process until all paths starting from the nodes corresponding to the abnormal values ​​are searched, and finally H construction deformation causal paths are obtained, which provides key clues for the subsequent accurate tracing of the root cause of the construction problem and ensures the safety of tunnel construction.

[0084] For each causal path of construction deformation, the path parsing algorithm is used to extract construction technology and obtain causal conditional probabilities. First, along the path from the starting node to the ending node, the nodes representing the construction technology are identified, and the corresponding construction technology is extracted to form H groups of construction technology. Then, the causal edges connecting the construction technology nodes and the surrounding rock state-related nodes in the path are searched to obtain the pre-set conditional probability values ​​on each causal edge. These values ​​are based on the statistics of historical construction defect data. These conditional probability values ​​are grouped according to the corresponding construction technology to obtain H groups of causal conditional probabilities. In this way, an important data basis is provided for the subsequent comprehensive assessment of construction technology risks, which helps to accurately judge the potential impact of different construction technologies on surrounding rock deformation and ensure the safety of tunnel construction.

[0085] In order to interactively obtain H historical construction times of H groups of construction technologies, database query and association algorithms are used. First, the system is connected to the database storing historical construction data, which covers detailed information of past tunnel construction projects, including construction technology application records, construction time nodes, etc. For each group of construction technologies, its key features such as technology name and process parameters are used as query conditions, and an accurate matching query is performed in the database table. By constructing an association statement, the construction technology table and the time record table are inner-connected according to the associated fields such as project number and construction stage to ensure that the query results accurately correspond to the application period of each group of construction technologies. For example, if a group of construction technologies involves specific anchor support parameters, the query statement accurately locates the construction time period using the parameter, extracts and corresponds to the corresponding group one by one, and finally successfully obtains H historical construction times interactively, providing key time dimension information for subsequent accurate risk assessment and ensuring tunnel construction safety.

[0086] According to the H groups of causal condition probabilities and H historical construction times, the risk contribution of H groups of construction technologies is evaluated, and then the construction technology prediction defects are found. First, the hierarchical analysis method is used to build a judgment matrix with the help of the experts' rich practical experience and a large amount of historical data accumulated in the past. Here, the H groups of causal condition probabilities are regarded as an important evaluation index dimension, and the H historical construction times are regarded as another dimension. For these two dimensions, their relative importance is carefully compared and analyzed, and then they are scored according to certain standards. Through rigorous calculation, the weight of each indicator is determined. Next, the fuzzy comprehensive evaluation method is introduced. For each group of construction technology, the specific value of the causal condition probability corresponding to it and the quantified value of the historical construction time that matches it are input as basic data. Then, according to the weight, these data are operated under specific fuzzy transformation rules, and finally a comprehensive evaluation vector is obtained. Finally, this comprehensive evaluation vector is compared with the pre-set threshold one by one. Those construction technologies with a comprehensive evaluation value higher than the threshold are the key risk points to be found. They are picked out and marked as construction technology prediction defects. In this way, potential technical risks that may affect construction safety can be accurately identified, providing key direction guidance for subsequent adjustments to the construction plan, and ensuring that tunnel construction can proceed safely and smoothly.

[0087] Embodiment 2 is based on the same inventive concept as a tunnel surrounding rock deformation monitoring method in the above embodiment. Figure 2 As shown, the present application provides a tunnel surrounding rock deformation monitoring system, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0088] The surrounding rock state association set acquisition module 10 is used to interactively obtain a surrounding rock state association set, wherein the surrounding rock state association set includes a plurality of surrounding rock state association indicators.

[0089] The surrounding rock deformation monitoring array generation module 20 is used to configure monitoring equipment in the tunnel construction area according to the surrounding rock state association set to generate a surrounding rock deformation monitoring array, wherein the surrounding rock deformation monitoring array includes multiple surrounding rock state monitoring devices corresponding to the multiple surrounding rock state association indicators.

[0090] The communication link building module 30 is used to pre-build the surrounding rock deformation monitoring cloud and build a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud.

[0091] The construction technology prediction defect acquisition module 40 is used to perform source tracing analysis based on the surrounding rock deformation warning to obtain the construction technology prediction defects when the surrounding rock deformation monitoring cloud receives and analyzes the feedback data of the surrounding rock deformation monitoring array and outputs a surrounding rock deformation warning.

[0092] The construction deviation prediction result acquisition module 50 is used to locate the construction deviation according to the construction technology prediction defects and obtain the construction deviation prediction result.

[0093] The construction warning instruction generation module 60 is used to generate a construction warning instruction according to the construction deviation prediction result, and send the construction warning instruction to the construction operation and maintenance center.

[0094] Furthermore, the communication link building module 30 also includes:

[0095] The indicator linkage effect analysis unit is used to decompose the surrounding rock state association set into K groups of state linkage indicators by performing indicator linkage effect analysis on the surrounding rock state association set.

[0096] The surrounding rock deformation identification model construction unit is used to construct K surrounding rock deformation identification models by performing principal component analysis on the K groups of state linkage indicators.

[0097] The surrounding rock deformation monitoring cloud construction unit is used to complete the construction of the surrounding rock deformation monitoring cloud by connecting the K surrounding rock deformation identification models in parallel.

[0098] Furthermore, the surrounding rock deformation identification model building unit also includes:

[0099] The historical state abnormal sequence acquisition unit is used to call the surrounding rock deformation data of the K groups of state linkage indicators to obtain K groups of historical state abnormal sequences.

[0100] The sequence position information acquisition unit is used to perform statistics on the recurrence frequency of the indicator sequence of the K groups of status linkage indicators in the K groups of historical status abnormal sequences to obtain the sequence position information of the K groups.

[0101] The state abnormality monitoring sequence acquisition unit is used to configure the linkage hierarchical relationship of the K groups of state linkage indicators according to the K groups of sequence position information to obtain K state abnormality monitoring sequences.

[0102] The surrounding rock risk identification model set pre-construction unit is used to pre-construct the surrounding rock risk identification model set corresponding to the surrounding rock state association set.

[0103] The hierarchical connection unit is used to perform model calling and hierarchical connection in the surrounding rock risk identification model set according to the K state abnormality monitoring sequences, so as to complete the construction of the K surrounding rock deformation identification models.

[0104] Furthermore, the communication link building module 30 also includes:

[0105] The surrounding rock state monitoring equipment classification unit is used to classify the multiple surrounding rock state monitoring equipment into K groups of surrounding rock state monitoring equipment according to the mapping relationship between the multiple surrounding rock state associated indicators and the K groups of state linkage indicators.

[0106] The data transfer edge node configuration unit is used to configure K data transfer edge nodes for the K groups of surrounding rock status monitoring devices.

[0107] A wired communication link construction unit is used to construct a wired communication link between the K groups of surrounding rock status monitoring equipment and the K data transfer edge nodes.

[0108] The wireless communication link construction unit is used to construct the wireless communication links between the K data transfer edge nodes and the K surrounding rock deformation identification models in the surrounding rock deformation monitoring cloud.

[0109] Furthermore, the construction technology prediction defect acquisition module 40 also includes:

[0110] The real-time monitoring data array receiving unit is used for receiving the real-time monitoring data array transmitted back by the surrounding rock deformation monitoring array on the surrounding rock deformation monitoring cloud.

[0111] The real-time monitoring data division unit is used to divide the real-time monitoring data array into K groups of real-time monitoring data according to the mapping relationship between the multiple surrounding rock state monitoring devices and the multiple surrounding rock state associated indicators and with the K groups of surrounding rock state monitoring devices as constraints.

[0112] The surrounding rock deformation judgment result output unit is used to load and sort the K groups of real-time monitoring data according to the K state abnormality monitoring sequences, load the K groups of real-time monitoring data into the K surrounding rock deformation identification models to perform indirect judgment of surrounding rock deformation, and output K surrounding rock deformation judgment results.

[0113] The surrounding rock deformation warning generation unit is used to generate the surrounding rock deformation warning when any surrounding rock deformation judgment result among the K surrounding rock deformation judgment results is a non-empty set, wherein the surrounding rock deformation warning includes H surrounding rock state associated abnormal values.

[0114] The source tracing analysis unit is used to perform source tracing analysis based on the surrounding rock deformation warning to obtain the predicted defects of the construction technology.

[0115] Furthermore, the surrounding rock deformation early warning generation unit also includes:

[0116] A state-associated causal node construction unit is used to construct a plurality of state-associated causal nodes based on the plurality of surrounding rock state-associated indicators.

[0117] The construction defect causal node construction unit is used to interactively obtain a plurality of sample construction technologies and construct a plurality of construction defect causal nodes based on the plurality of sample construction technologies.

[0118] A causal edge construction unit is used to interactively obtain historical construction defect data, and construct causal edges between the multiple state-associated causal nodes and the multiple construction defect causal nodes according to the historical construction defect data.

[0119] The construction deformation causal network construction unit is used to perform conditional probability allocation configuration according to the overlapping frequency of causal edges between causal nodes, so as to complete the construction of the construction deformation causal network.

[0120] Furthermore, the traceability analysis unit also includes:

[0121] The construction deformation causal path acquisition unit is used to input the H surrounding rock state associated abnormal values ​​in the surrounding rock deformation early warning into the construction deformation causal network, and screen and obtain H construction deformation causal paths.

[0122] The causal condition probability acquisition unit is used to extract construction technology according to the H construction deformation causal paths to obtain H groups of construction technology and H groups of causal condition probabilities.

[0123] The historical construction time acquisition unit is used to interactively obtain H historical construction times of the H groups of construction technologies.

[0124] The construction technology acquisition unit is used to evaluate the risk contribution of the H groups of construction technologies according to the H groups of causal condition probabilities and H historical construction times, and obtain W construction technologies whose risk contributions are higher than a preset threshold as the construction technology prediction defects.

[0125] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0126] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0127] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A tunnel surrounding rock deformation monitoring method, characterized in that: The method comprises: interactively obtaining a surrounding rock state association set, wherein the surrounding rock state association set includes a plurality of surrounding rock state association indicators; Performing monitoring equipment configuration in the tunnel construction area according to the surrounding rock state association set to generate a surrounding rock deformation monitoring array, wherein the surrounding rock deformation monitoring array includes a plurality of surrounding rock state monitoring devices corresponding to the plurality of surrounding rock state association indicators; Pre-constructing a surrounding rock deformation monitoring cloud, and establishing a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud; When the surrounding rock deformation monitoring cloud receives and analyzes the returned data of the surrounding rock deformation monitoring array and outputs a surrounding rock deformation warning, a source analysis is performed based on the surrounding rock deformation warning to obtain construction technology prediction defects; Positioning construction deviations based on construction technology prediction defects to obtain construction deviation prediction results; A construction early warning instruction is generated according to the construction deviation prediction result, and the construction early warning instruction is sent to the construction operation and maintenance center.

2. A tunnel surrounding rock deformation monitoring method according to claim 1, characterized in that: Pre-constructing a surrounding rock deformation monitoring cloud, the method includes: By analyzing the indicator linkage effect of the surrounding rock state association set, the surrounding rock state association set is decomposed into K groups of state linkage indicators; By performing principal component analysis on the K groups of state linkage indicators, K surrounding rock deformation identification models are constructed; By connecting the K surrounding rock deformation identification models in parallel, the construction of the surrounding rock deformation monitoring cloud is completed.

3. A tunnel surrounding rock deformation monitoring method as claimed in claim 2, characterized in that: By performing principal component analysis on the K groups of state linkage indicators, K surrounding rock deformation identification models are constructed, and the method includes: Calling surrounding rock deformation data for the K groups of state linkage indicators to obtain K groups of historical state abnormality sequences; Performing statistics on the recurrence frequency of the indicator sequence of the K groups of status linkage indicators in the K groups of historical status abnormality sequences to obtain the K groups of sequence position information; According to the K groups of sequence position information, a linkage hierarchical relationship of the K groups of state linkage indicators is configured to obtain K state abnormality monitoring sequences; Pre-constructing a surrounding rock risk identification model set corresponding to the surrounding rock state association set; Model calling and hierarchical connection are performed in the surrounding rock risk identification model set according to the K state abnormality monitoring sequences to complete the construction of the K surrounding rock deformation identification models.

4. A tunnel surrounding rock deformation monitoring method as claimed in claim 3, characterized in that: Establishing a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud, the method includes: According to the mapping relationship between the plurality of surrounding rock state associated indicators and the K groups of state linkage indicators, the plurality of surrounding rock state monitoring devices are divided into K groups of surrounding rock state monitoring devices; Configuring K data transfer edge nodes for the K groups of surrounding rock status monitoring equipment; Establishing a wired communication link between the K groups of surrounding rock status monitoring equipment and the K data transfer edge nodes; A wireless communication link is established between the K data transfer edge nodes and the K surrounding rock deformation identification models in the surrounding rock deformation monitoring cloud.

5. A tunnel surrounding rock deformation monitoring method as claimed in claim 4, characterized in that: When the surrounding rock deformation monitoring cloud receives and analyzes the returned data of the surrounding rock deformation monitoring array and outputs a surrounding rock deformation warning, a source analysis is performed based on the surrounding rock deformation warning to obtain construction technology prediction defects. The method includes: The surrounding rock deformation monitoring cloud receives the real-time monitoring data array transmitted back by the surrounding rock deformation monitoring array; According to the mapping relationship between the plurality of surrounding rock state monitoring devices and the plurality of surrounding rock state associated indicators, the real-time monitoring data array is divided into K groups of real-time monitoring data with the K groups of surrounding rock state monitoring devices as constraints; After the K groups of real-time monitoring data are loaded and sorted according to the K abnormal state monitoring sequences, the K groups of real-time monitoring data are loaded into the K surrounding rock deformation identification models to perform indirect judgment of surrounding rock deformation, and K surrounding rock deformation judgment results are output; When any surrounding rock deformation judgment result among the K surrounding rock deformation judgment results is a non-empty set, the surrounding rock deformation warning is generated, wherein the surrounding rock deformation warning includes H surrounding rock state-related abnormal values; A source analysis is performed based on the surrounding rock deformation warning to obtain the predicted defects of the construction technology.

6. A tunnel surrounding rock deformation monitoring method as claimed in claim 5, characterized in that: The method comprises: Constructing a plurality of state-related causal nodes based on the plurality of surrounding rock state-related indicators; Interactively obtain a plurality of sample construction technologies, and construct a plurality of construction defect cause-effect nodes based on the plurality of sample construction technologies; interactively obtaining historical construction defect data, and constructing causal edges between the plurality of state-associated causal nodes and the plurality of construction defect causal nodes according to the historical construction defect data; The conditional probability distribution is configured according to the overlapping frequency of causal edges between causal nodes to complete the construction of the construction deformation causal network.

7. A tunnel surrounding rock deformation monitoring method as claimed in claim 6, characterized in that: According to the surrounding rock deformation early warning, a source analysis is performed to obtain the predicted defects of the construction technology, and the method includes: Inputting the H surrounding rock state-related abnormal values ​​in the surrounding rock deformation early warning into the construction deformation causal network, and screening to obtain H construction deformation causal paths; Extract construction technology according to the H construction deformation causal paths to obtain H groups of construction technology and H groups of causal condition probabilities; Interactively obtain H historical construction times of the H groups of construction technologies; The risk contribution of the H groups of construction technologies is evaluated according to the H groups of causal conditional probabilities and H historical construction times, and W construction technologies whose risk contributions are higher than a preset threshold are obtained as the construction technology prediction defects.

8. A tunnel surrounding rock deformation monitoring system, characterized in that: The system is used to implement a tunnel surrounding rock deformation monitoring method according to any one of claims 1 to 7, and the system comprises: A surrounding rock state association set acquisition module, used for interactively acquiring a surrounding rock state association set, wherein the surrounding rock state association set includes a plurality of surrounding rock state association indicators; A surrounding rock deformation monitoring array generation module, used to configure monitoring equipment in the tunnel construction area according to the surrounding rock state association set to generate a surrounding rock deformation monitoring array, wherein the surrounding rock deformation monitoring array includes a plurality of surrounding rock state monitoring devices corresponding to the plurality of surrounding rock state association indicators; A communication link building module, used to pre-build a surrounding rock deformation monitoring cloud and build a communication link between the surrounding rock deformation monitoring array and the surrounding rock deformation monitoring cloud; A construction technology prediction defect acquisition module is used to perform source analysis based on the surrounding rock deformation warning to obtain construction technology prediction defects when the surrounding rock deformation monitoring cloud receives and analyzes the return data of the surrounding rock deformation monitoring array and outputs a surrounding rock deformation warning as a result; A construction deviation prediction result acquisition module is used to locate the construction deviation according to the construction technology prediction defects and obtain the construction deviation prediction result; The construction warning instruction generation module is used to generate a construction warning instruction according to the construction deviation prediction result, and send the construction warning instruction to the construction operation and maintenance center.

Images