Evaluation method and device for mountain tunnel construction collapse risk

Abstract

The invention discloses a mountain tunnel construction collapse risk evaluation method and device, and relates to the field of construction safety evaluation. The method comprises the following steps: acquiring historical operation data of a mountain tunnel, and acquiring historical environment data and historical construction data of a target area; constructing a risk factor dynamic network by taking each risk factor as a node, establishing an association relationship between the nodes and an initial weight according to the historical operation data, and determining a coupling relationship between the nodes according to the historical environment data and the historical construction data; determining the current weight of each node according to the current environment data, the current construction data and the initial weight, and determining the coupling strength between the nodes according to the current environment data, the current construction data and the coupling relationship; and calculating an evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environment data and the current construction data. By implementing the technical scheme provided by the invention, accurate evaluation can be performed according to actual conditions.

Description

Technical Field

[0001] This application relates to the technical field of construction safety assessment, and specifically relates to a method and device for evaluating the collapse risk of mountain tunnel construction. Background Art

[0002] With the rapid development of social economy and technological progress, the number of mountain tunnel projects is increasing continuously. Such engineering projects usually have characteristics such as complex geological conditions and long construction periods. While promoting regional economic development, they are also accompanied by high safety risk challenges. Especially when facing unpredictable natural environmental changes, ensuring the safety and stability of the construction process is particularly important.

[0003] Currently, the risk assessment for possible situations during mountain tunnel construction mainly relies on traditional experience judgment or simple data analysis methods for processing. However, these assessment means generally have the problem of insufficient accuracy, and it is difficult to comprehensively capture the complex interaction relationships among various risk factors. Especially in a dynamic environment, they cannot timely reflect the latest change trends, which makes the final obtained risk estimates often inaccurate and unreliable, and easily leads to decision-making mistakes and serious consequences.

[0004] Therefore, there is an urgent need to develop a mountain tunnel construction collapse risk evaluation mechanism that can more accurately reflect the actual situation and has strong adaptability to make up for the loopholes existing in the prior art. Summary of the Invention

[0005] This application provides a method and device for evaluating the collapse risk of mountain tunnel construction. Through dynamic data-driven and non-linear network analysis, the ability to capture complex risk interactions and dynamic changes in the construction environment is significantly improved, providing more accurate and forward-looking risk control support for mountain tunnel construction.

[0006] In the first aspect of this application, a method for evaluating the collapse risk of mountain tunnel construction is provided, which is applied to a risk assessment platform. The method includes: Obtain the historical operation data of the mountain tunnel, and obtain the historical environmental data and historical construction data of the target area. The historical environmental data includes surrounding rock grade, joint density, groundwater seepage volume, and ground settlement. The historical construction data includes surrounding rock deformation, support stress, and tunneling machine parameters; Construct a dynamic network of risk factors with each risk factor as a node, establish the association relationship and initial weight between nodes according to the historical operation data, and determine the coupling relationship between nodes according to the historical environmental data and the historical construction data; obtain the current environmental data and current construction data of the target area, determine the current weight of each node according to the current environmental data, the current construction data, and the initial weight, and determine the coupling strength between nodes according to the current environmental data, the current construction data, and the coupling relationship; Calculate the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data.

[0007] Optionally, the calculating the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data includes: Determine the real-time state of the target risk factor according to the current environmental data and the current construction data, and determine the static risk value of the target risk factor according to the real-time state and the current weight of the target risk factor, where the target risk factor is any one risk factor; Calculate the coupling effect value through a non-linear coupling function according to the real-time state of the risk factor pair, and determine the dynamic risk value of the risk factor pair according to the coupling strength and the coupling effect value of the risk factor pair, where the risk factor pair is a combination of any two risk factors; Calculate the total static risk value according to the static risk value, calculate the total dynamic risk value according to the dynamic risk value, and perform weighted calculation on the total static risk value and the total dynamic risk value to obtain the evaluation value.

[0008] Optionally, the establishing the association relationship and initial weight between nodes according to the historical operation data includes: Obtain the number of events in which the risk factor pair appears from the historical operation data, and calculate the ratio of the number of events to the total number of events to obtain the co-occurrence frequency; Calculate the Pearson correlation coefficient of the risk factor pair in the historical operation data, and perform weighted summation on the co-occurrence frequency and the Pearson correlation coefficient to obtain the initial weight.

[0009] Optionally, the determining the coupling relationship between nodes according to the historical environmental data and the historical construction data includes: Calculate the mutual information value of the risk factor pair under different environmental conditions, where the mutual information value is used to measure the degree of mutual dependence of the two risk factors in the risk factor pair in the environmental data; Calculate the time series correlation of the risk factors during the construction process, where the time series correlation is used to measure the dynamic association degree between two risk factors in the risk factor pair in the construction data; Determine the coupling relationship according to the mutual information value and the time series correlation.

[0010] Optionally, the evaluation value of the construction collapse risk of the target area calculated according to the current weight, the coupling strength, the current environmental data, and the current construction data includes: Calculate the evaluation value of the construction collapse risk of the target area through the following formula: Among them, R(t) represents the evaluation value corresponding to time t, W i (t) represents the weight of node i at time t, S i (t) represents the real-time state of node i at time t, C ij (t) represents the coupling strength between node i and node j at time t, S j (t)) represents the coupling effect value between the real-time state of node i at time t and the real-time state of node j at time t, α represents the static risk contribution coefficient, and β represents the dynamic risk contribution coefficient.

[0011] Optionally, the method further includes: Calculate the weight of node i at time t through the following formula: W i (t) = W i (t - 1) + λ△S i (t) Among them, W i (t) represents the weight of node i at time t, W i (t - 1) represents the weight of node i at time t - 1, λ represents the learning rate, and △S i (t) represents the state change rate of node i.

[0012] Optionally, the method further includes: Train a long short-term memory network model according to the historical operation data, the historical environmental data, and the historical construction data; use the trained long short-term memory network model to predict the real-time state change trend of each node in the future time period, and update the coupling strength between nodes according to the predicted node state change trend; Calculate the evaluation value of the construction collapse risk of the target area within a future preset time period according to the updated coupling strength.

[0013] In the second aspect of the present application, an evaluation system for the risk of collapse in mountain tunnel construction is provided, including a collection module, a construction module, a coupling module, and a calculation module, where: The collection module is configured to obtain the historical operation data of the mountain tunnel, and obtain the historical environmental data and historical construction data of the target area. The historical environmental data includes the surrounding rock grade, joint density, groundwater seepage volume, and ground settlement. The historical construction data includes surrounding rock deformation, support stress, and tunneling machine parameters; The construction module is configured to construct a dynamic network of risk factors with each risk factor as a node, establish the association relationship and initial weight between nodes according to the historical operation data, and determine the coupling relationship between nodes according to the historical environmental data and the historical construction data; The coupling module is configured to obtain the current environmental data and current construction data of the target area, determine the current weight of each node according to the current environmental data, the current construction data, and the initial weight, and determine the coupling strength between nodes according to the current environmental data, the current construction data, and the coupling relationship; The calculation module is configured to calculate the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data.

[0014] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. Both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device executes the method described in any one of the above.

[0015] In the fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions that, when executed, execute the method described in any one of the above.

[0016] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By integrating the historical operation data, historical environmental data, and historical construction data of the mountain tunnel, as well as the current environmental data and current construction data of the target area, a comprehensive and dynamic data foundation is constructed. This enables risk evaluation to be based on the most accurate and up-to-date information, improving the reliability and timeliness of the evaluation; 2. Construct a dynamic network of risk factors with each risk factor as a node. Not only establish the association relationships and initial weights between nodes based on historical data, but also determine the coupling relationships between nodes by combining historical environment and construction data. This method can capture the complex non-linear interactions between risk factors and more realistically reflect the risk dynamics during the construction process; 3. Dynamically adjust the weight of each node according to the current environment and construction data, and determine the coupling strength between nodes. This real-time adjustment mechanism enables the risk assessment to adapt to the changes during the construction process, provides personalized risk evaluation values, and enhances the accuracy and practicality of the assessment; 4. Calculate the evaluation value of the construction collapse risk by combining the current weight, coupling strength, current environment data, and construction data. This method not only considers the influence of single risk factors but also the interactions between risk factors, provides a more comprehensive risk assessment result, and helps to take preventive measures in a timely manner. Description of the Drawings

[0017] Figure 1 is a schematic flowchart of the method for evaluating the construction collapse risk of mountain tunnels disclosed in the embodiments of the present application; Figure 2 is a schematic block diagram of the evaluation system for the construction collapse risk of mountain tunnels disclosed in the embodiments of the present application; Figure 3 is a schematic structural diagram of an electronic device disclosed in the embodiments of the present application.

[0018] Description of the reference numerals: 201, acquisition module; 202, construction module; 203, coupling module; 204, calculation module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Embodiments

[0019] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0020] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0021] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0022] This embodiment discloses an evaluation method for the collapse risk of mountain tunnel construction, which is applied to a risk evaluation platform. Figure 1 It is a schematic flowchart of the evaluation method for the collapse risk of mountain tunnel construction disclosed in the embodiments of the present application. As Figure 1 shown, the method includes the following steps: S101. Obtain the historical operation data of the mountain tunnel, and obtain the historical environmental data and historical construction data of the target area. The historical environmental data includes the surrounding rock grade, joint density, groundwater seepage volume, and ground settlement. The historical construction data includes surrounding rock deformation, support stress, and tunneling machine parameters; S102. Construct a dynamic network of risk factors with each risk factor as a node, establish the association relationship and initial weight between nodes according to the historical operation data, and determine the coupling relationship between nodes according to the historical environmental data and the historical construction data; S103. Obtain the current environmental data and current construction data of the target area, determine the current weight of each node according to the current environmental data, the current construction data, and the initial weight, and determine the coupling strength between nodes according to the current environmental data, the current construction data, and the coupling relationship; S104. Calculate the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data.

[0023] Historical operation data: It includes various data during the construction of completed mountain tunnels, such as construction logs, geological exploration reports, accident records, etc. These data help to understand the routine operations, problems encountered and solutions during construction. Historical environmental data: It includes data such as surrounding rock grade, joint density, groundwater seepage volume, and ground settlement. These data reflect the geological environmental characteristics of the tunnel construction area and are crucial for evaluating the impact of the environment on construction risks. Historical construction data: It covers data such as surrounding rock deformation, support stress, and tunneling machine parameters. These data directly reflect the response of the structure and the operation of construction machinery during construction and are important bases for evaluating construction risks. Identify all factors that may affect the collapse risk of mountain tunnel construction, and define each risk factor as a node in the dynamic network. Based on historical operation data, analyze the correlation between risk factors, establish the correlation relationship between nodes, and determine the initial weight by calculating methods such as co-occurrence frequency and Pearson correlation coefficient to quantify the correlation strength between nodes. Combine historical environmental data and historical construction data to further analyze the coupling relationship between risk factors. Determine the coupling relationship between nodes by calculating the mutual information value of risk factor pairs under different environmental conditions and the time series correlation during construction to more comprehensively reflect the interaction between risk factors. Real-time collect the current environmental data and construction data of the target area, which can reflect the specific construction situation and environmental conditions. According to the current environmental data and construction data, combined with the initial weight, dynamically adjust the weight of each node to reflect the importance and influence of risk factors under the current construction conditions. Based on the current environmental data and construction data, and the determined coupling relationship between nodes, further determine the coupling strength between nodes to quantify the degree of interaction between risk factors under the current construction conditions. Determine the real-time state of each target risk factor according to the current environmental data and construction data, and then combine its current weight to calculate the static risk value of each target risk factor, which reflects the risk degree of a single risk factor in the current state. For any combination of two risk factors, calculate its coupling effect value through a non-linear coupling function, and then determine the dynamic risk value of the risk factor pair according to the coupling strength between nodes to reflect the additional risk brought by the interaction between risk factors. Summarize the static risk values of all target risk factors to obtain the total static risk value, summarize the dynamic risk values of all risk factor pairs to obtain the total dynamic risk value, and finally obtain the final evaluation value of the construction collapse risk of the target area through weighted calculation of the total static risk value and the total dynamic risk value. This evaluation value comprehensively considers the influence of single risk factors and the interaction between risk factors and can more comprehensively and accurately reflect the overall risk level of construction collapse.

[0024] Optionally, calculating the evaluation value of the construction collapse risk of the target area based on the current weight, the coupling strength, the current environmental data, and the current construction data includes: Determining the real-time state of the target risk factor according to the current environmental data and the current construction data, and determining the static risk value of the target risk factor according to the real-time state and the current weight of the target risk factor, where the target risk factor is any one risk factor; Calculating the coupling effect value through a non-linear coupling function according to the real-time state of the risk factor pair, and determining the dynamic risk value of the risk factor pair according to the coupling strength of the risk factor pair and the coupling effect value, where the risk factor pair is a combination of any two risk factors; Calculating the total static risk value according to the static risk value, calculating the total dynamic risk value according to the dynamic risk value, and performing weighted calculation on the total static risk value and the total dynamic risk value to obtain the evaluation value.

[0025] For any risk factor (such as surrounding rock deformation), based on the current environmental data (such as groundwater seepage volume, ground settlement, etc.) and current construction data (such as support stress, tunneling machine parameters, etc.), obtain its specific performance and value at the current moment. For example, the deformation amount of the surrounding rock obtained by real-time monitoring with sensors. Combine the real-time state of the risk factor with its current weight (the weight adjusted according to the initial weight and current environmental and construction data) to calculate its static risk value. The static risk value reflects the degree of contribution of the risk factor to the construction collapse risk independently in the current state. For example, if the real-time state of the surrounding rock deformation is relatively serious and its current weight is large, then its static risk value will be correspondingly high. For any combination of two risk factors (such as groundwater seepage volume and surrounding rock deformation), calculate their coupling effect value in the current real-time state through a non-linear coupling function. The non-linear coupling function can capture the complex interaction relationship between the two risk factors. For example, an increase in the groundwater seepage volume may accelerate the softening and deformation of the surrounding rock, and this interaction can be quantified through the coupling function. Multiply the coupling strength of the risk factor pair (the value determined according to historical data and current environmental and construction data, reflecting the strength of the interaction between the two risk factors) by the coupling effect value to obtain the dynamic risk value of the risk factor pair. The dynamic risk value reflects the additional contribution of the interaction between the two risk factors to the construction collapse risk. For example, if the coupling strength between the groundwater seepage volume and the surrounding rock deformation is large and the coupling effect value is also high, then their dynamic risk value will be significant. Summarize the static risk values of all target risk factors to obtain the total static risk value. This step synthesizes the independent risk contributions of all single risk factors in the current state. Summarize the dynamic risk values of all risk factor pairs to obtain the total dynamic risk value. This step synthesizes the risk contributions of the interactions between all risk factors. Perform a weighted calculation on the total static risk value and the total dynamic risk value to obtain the final evaluation value of the construction collapse risk in the target area. By setting different weight coefficients, the relative importance of static risk and dynamic risk in the final evaluation can be adjusted. For example, if it is considered that the interaction between risk factors has a greater impact on the construction collapse risk, a higher weight can be given to the total dynamic risk value.

[0026] Based on the current environmental data and construction data, the real-time status of each target risk factor can be accurately determined. This method ensures that the risk assessment is based on the latest construction site conditions, thereby improving the timeliness and accuracy of the assessment results. By combining the real-time status and the current weight, the static risk value of each target risk factor is calculated. This not only considers the current status of the risk factor but also its importance and influence under specific construction conditions, providing a basis for subsequent comprehensive risk assessment. By calculating the coupling effect value of the risk factor pair through a non-linear coupling function, the complex non-linear interaction between risk factors can be captured. This method not only considers the impact of a single risk factor but also the interaction between risk factors, making the risk assessment more comprehensive and realistic. Combining the coupling strength and the coupling effect value of the risk factor pair, the dynamic risk value is determined. This reflects the additional risk brought by the interaction between risk factors and helps to identify and warn of potential high-risk situations caused by the synergistic effect between factors. The total static risk value and the total dynamic risk value are calculated separately to quantify and summarize the impacts of single risk factors and the interaction between risk factors. This separate calculation method helps to clearly understand the contributions of different risk sources and provides a scientific basis for formulating risk control measures. By performing a weighted calculation on the total static risk value and the total dynamic risk value, the final construction collapse risk evaluation value is obtained. This method allows for flexible adjustment of the weights of static and dynamic risks according to actual engineering experience and specific requirements, making the risk evaluation more targeted and adaptable.

[0027] Optionally, the establishing of the association relationship and the initial weight between nodes according to the historical operation data includes: Obtaining the number of occurrences of the risk factor pair from the historical operation data and calculating the ratio of the number of occurrences to the total number of events to obtain the co-occurrence frequency; Calculating the Pearson correlation coefficient of the risk factor pair in the historical operation data and performing a weighted summation of the co-occurrence frequency and the Pearson correlation coefficient to obtain the initial weight.

[0028] From the historical operation data, count the number of times each pair of risk factors (a combination of two risk factors) co-occurs. For example, in the historical records of mountain tunnel construction, count the number of times "surrounding rock deformation" and "support stress" occur simultaneously. Divide the number of events of each pair of risk factors by the total number of events to obtain the co-occurrence frequency. The co-occurrence frequency reflects the frequency of co-occurrence of two risk factors in the historical data. The calculation formula is: Co-occurrence frequency = Number of events in which the pair of risk factors occurs / Total number of events. For example, if in 100 events, "surrounding rock deformation" and "support stress" occur simultaneously 20 times, then their co-occurrence frequency is 0.2. Extract the specific values of each pair of risk factors in each event from the historical operation data. For example, extract the values of "surrounding rock deformation" and "support stress" in each event. Calculate the mean value of each risk factor. For example, calculate the average value of all events of "surrounding rock deformation" and the average value of all events of "support stress". Use the Pearson correlation coefficient formula to calculate the degree of linear correlation between pairs of risk factors. The value range of the Pearson correlation coefficient is between [-1, 1]. The closer the value is to 1 or -1, the stronger the correlation. Perform a weighted sum of the co-occurrence frequency and the Pearson correlation coefficient to obtain the initial weight. In order to make the weight value within the range of [0, 1] and the sum of all weights equal to 1, normalization can be performed: By obtaining the number of events in which the pair of risk factors occurs from the historical operation data and calculating the co-occurrence frequency, this method is based on the actual events that have occurred, avoiding subjective speculation, making the establishment of the association relationship between nodes more objective and accurate, and being able to truly reflect the co-occurrence probability of risk factors during the construction process. It not only considers the co-occurrence of pairs of risk factors but also combines the Pearson correlation coefficient to measure the linear correlation between them, thus capturing more comprehensively different types of association relationships between risk factors, including synchronous changes, mutual influences, etc., providing more abundant information for subsequent risk assessment. Performing a weighted sum of the co-occurrence frequency and the Pearson correlation coefficient to obtain the initial weight, this comprehensive calculation method can balance the influence of two different indicators, considering both the frequency of occurrence of pairs of risk factors and the strength of their correlation, making the determination of the initial weight more scientific and reasonable and being able to better reflect the tightness of the association between risk factors. By setting different weight coefficients, the relative importance of the co-occurrence frequency and the Pearson correlation coefficient in the calculation of the initial weight can be flexibly adjusted according to actual engineering experience and data characteristics, making the model have better adaptability and flexibility and being able to be applied to different construction environments and risk assessment requirements. Establishing the association relationship and initial weight between nodes based on historical operation data makes full use of the existing data resources, making the initialization process of the model based on actual data, improving the reliability and credibility of the model, and providing a solid foundation for subsequent dynamic network analysis and risk assessment of risk factors.

[0029] Optionally, determining the coupling relationship between nodes based on the historical environmental data and the historical construction data includes: Calculating the mutual information value of the risk factor pair under different environmental conditions, where the mutual information value is used to measure the degree of mutual dependence between the two risk factors in the environmental data; Calculating the time series correlation of the risk factor pair during the construction process, where the time series correlation is used to measure the degree of dynamic association between the two risk factors in the construction data; Determining the coupling relationship based on the mutual information value and the time series correlation.

[0030] The mutual information value is an index to measure the degree of mutual dependence between two random variables, and it can capture the non-linear relationship between variables. In the analysis of the coupling relationship of risk factor pairs, the mutual information value is used to measure the degree of mutual dependence between two risk factors in the environmental data. Extract the relevant data of two risk factors from the historical environmental data. Calculate the mutual information value between the two risk factors using the mutual information formula. The time series correlation is used to measure the degree of dynamic association between two risk factors during the construction process. Extract the time series data of two risk factors from the historical construction data. Calculate the correlation between the two risk factors using the time series correlation analysis method (such as autocorrelation function, cross-correlation function, etc.). For example, the cross-correlation function can measure the correlation between two time series at different lag times. Based on the mutual information value and the time series correlation, determine the coupling relationship of the risk factor pair. The specific steps are as follows: comprehensively evaluate the mutual information value and the time series correlation to determine the coupling strength of the risk factor pair. The weighted summation method can be used to combine the mutual information value and the time series correlation to obtain the coupling relationship strength value; set a threshold according to the coupling relationship strength value to determine which risk factor pairs have a significant coupling relationship. For example, if the coupling relationship strength value exceeds a preset threshold, it is considered that there is a significant coupling relationship between the two risk factors. Suppose we have two risk factors: surrounding rock deformation (A) and groundwater seepage volume (B). Extract the data of surrounding rock deformation and groundwater seepage volume from the historical environmental data. Calculate the mutual information value I(A, B), and assume that the calculation result is 0.8. Extract the time series data of surrounding rock deformation and groundwater seepage volume from the historical construction data. Calculate the cross-correlation function, and assume that when the lag time is 0, the cross-correlation coefficient is 0.7. Perform weighted summation on the mutual information value 0.8 and the time series correlation 0.7, and assume that the weights are 0.5 and 0.5 respectively, to obtain the coupling relationship strength value: coupling relationship strength value = 0.5×0.8 + 0.5×0.7 = 0.75. Set the threshold to 0.6. Since 0.75 > 0.6, it is determined that there is a significant coupling relationship between surrounding rock deformation and groundwater seepage volume.

[0031] By calculating the mutual information value of risk factors under different environmental conditions, the degree of mutual dependence between two risk factors in environmental data can be effectively measured. The higher the mutual information value, the stronger the correlation between the two risk factors. This dependence may include a change in one risk factor leading to a change in another risk factor, or both being affected by a certain environmental factor, etc. This method can help us identify the potential correlations between risk factors under different environmental conditions, providing a richer information dimension for subsequent risk assessment. Calculating the time series correlation of risk factor pairs during the construction process can capture the dynamic correlation degree of risk factors in construction data. By analyzing the time series correlation, the evolution trend and mutual influence of risk factors during the construction process can be grasped more accurately, helping to detect potential risk changes in a timely manner. Combining the mutual information value and the time series correlation to determine the coupling relationship provides a more comprehensive and accurate measurement method. The mutual information value focuses on measuring the static dependence relationship between risk factors, while the time series correlation emphasizes the dynamic change relationship between risk factors. By synthesizing these two indicators, the coupling relationship between risk factors can be identified and quantified more accurately, avoiding the one-sidedness or omission that may be caused by a single indicator. This method helps to screen out the combination of risk factors that have a significant impact on the construction collapse risk. Among many risk factors, only those risk factor pairs that show a strong correlation in both environmental data and construction data will be determined to have a significant coupling relationship. This enables the risk assessment to focus more on key risk factor combinations, improving the efficiency and pertinence of risk assessment and avoiding excessive attention to irrelevant or weakly related factors.

[0032] Optionally, calculating the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data includes: Calculating the evaluation value of the construction collapse risk of the target area by the following formula: where R(t) represents the evaluation value corresponding to time t, W i (t) represents the weight of node i at time t, S i (t) represents the real-time state of node i at time t, C ij (t) represents the coupling strength between node i and node j at time t, S j (t)) represents the coupling effect value between the real-time state of node i at time t and the real-time state of node j at time t, α represents the static risk contribution coefficient, and β represents the dynamic risk contribution coefficient.

[0033] This formula combines static risk and dynamic risk, not only considering the impact of a single risk factor, but also considering the interaction between risk factors, providing a more comprehensive and accurate assessment of construction collapse risk. By acquiring current environmental data and construction data in real time, dynamically adjusting node weights and coupling strengths, the risk assessment value can timely reflect the actual risk changes during the construction process, and has good dynamic adaptability. Based on this evaluation value, a risk warning threshold can be set to achieve real-time monitoring and early warning of construction risks. At the same time, it provides a scientific basis for construction decisions, helping decision makers choose the optimal construction strategy and effectively reduce construction risks. With the advancement of the construction process and the accumulation of more data, the parameters such as weights, coupling strengths, and coupling functions in the formula can be continuously optimized and updated, so that the risk assessment model can be continuously improved to better cope with the complex and changing construction environment.

[0034] Optionally, the method further includes: The weight of node i at time t is calculated by the following formula: W i (t) = W i (t-1)+λ△S i (t) Among them, W i (t) represents the weight of node i at time t, W i (t-1) represents the weight of node i at time t-1, λ represents the learning rate, △S i (t) represents the state change rate of node i.

[0035] λ represents the learning rate, which is a parameter between 0 and 1 and is used to control the speed of weight update. The larger the learning rate, the faster the weight update; the smaller the learning rate, the slower the weight update. i (t) represents the state change rate of node i at time t, reflecting the change of risk factor i at the current time relative to the previous time. The larger the state change rate, the more drastic the change of risk factor i, and its weight needs to be adjusted accordingly.

[0036] This formula realizes the dynamic adjustment of node weights and can timely reflect the real-time changes of risk factors during the construction process. When the state of a risk factor changes significantly, its weight will be adjusted accordingly, so as to more accurately reflect the current importance of the risk factor in the risk assessment. By controlling the learning rate, the sensitivity and stability to new information can be balanced during the weight update process. A larger learning rate can make the weight quickly adapt to the drastic changes of risk factors, but may lead to large fluctuations in the weight; a smaller learning rate makes the weight change more smoothly, but may respond slowly to the rapid changes of risk factors. Selecting an appropriate learning rate according to actual engineering experience and requirements can effectively adapt to risk changes. The dynamic adjustment of weights can enable the risk assessment model to better reflect the actual risk situation during the construction process. When the state of some risk factors changes, their contributions to the overall risk will also change. By timely adjusting the weights, the evaluation value of the construction collapse risk can be calculated more accurately, providing a more reliable basis for construction decisions. Incorporating this weight update formula into the risk assessment method makes the entire model more flexible and self-adaptive. The model can automatically adjust the weights according to the real-time data during the construction process without manual intervention, improving the automation degree and efficiency of risk assessment.

[0037] Optionally, the method further includes: Training a long short-term memory network model according to the historical operation data, the historical environmental data, and the historical construction data; predicting the real-time state change trend of each node in the future time period by using the trained long short-term memory network model, and updating the coupling strength between nodes according to the predicted node state change trend; Calculating the evaluation value of the construction collapse risk in the future preset time period according to the updated coupling strength.

[0038] Using historical operation data, historical environment data, and historical construction data as the training basis, the LSTM model can learn the patterns and regularities of risk factors changing over time. These data cover various situations during the construction process and the manifestations of risk factors, providing rich learning materials for the model. The LSTM model is good at processing time series data and can capture the dependencies between risk factors at different times. Through training, the model can learn how risk factors evolve over time and how the interactions between different risk factors change over time, thus providing strong support for predicting future risks. The trained LSTM model can predict the real-time state change trends of each node in the future time period. For each risk factor node, the model can output its possible state values at different future time points, providing a forward-looking basis for risk warning and decision-making during the construction process. This prediction ability enables the construction team to understand the dynamic changes of risk factors in advance, timely detect potential risk upward trends or abnormal fluctuations, and thus take preventive measures or adjust the construction plan more targeted. According to the node state change trends predicted by the LSTM model, re-evaluate and update the coupling strength between nodes. If the prediction shows that the correlation between certain pairs of risk factors will increase or decrease in the future time period, the coupling strength will be adjusted accordingly to more accurately reflect the changes in the interactions between risk factors. Using the updated coupling strength, combined with the current weights and the predicted node states, recalculate the evaluation value of the construction collapse risk within a preset future time period. This makes the risk assessment more forward-looking and accurate, can reveal the risk evolution trend during the construction process in advance, and provides stronger support for construction management.

[0039] This embodiment also discloses an evaluation system for the construction collapse risk of mountain tunnels. Figure 2 It is a schematic diagram of the modules of the evaluation system for the construction collapse risk of mountain tunnels disclosed in the embodiments of the present application. As Figure 2 shown, the system includes a collection module 201, a construction module 202, a coupling module 203, and a calculation module 204, where: The collection module 201 is configured to obtain the historical operation data of the mountain tunnel and obtain the historical environment data and historical construction data of the target area. The historical environment data includes the surrounding rock grade, joint density, groundwater seepage volume, and ground settlement. The historical construction data includes surrounding rock deformation, support stress, and tunneling machine parameters. The construction module 202 is configured to construct a dynamic network of risk factors with each risk factor as a node, establish the association relationship and initial weights between nodes according to the historical operation data, and determine the coupling relationship between nodes according to the historical environment data and the historical construction data. The coupling module 203 is configured to obtain the current environmental data and current construction data of the target area, determine the current weight of each node according to the current environmental data, the current construction data, and the initial weight, and determine the coupling strength between nodes according to the current environmental data, the current construction data, and the coupling relationship; The calculation module 204 is configured to calculate an evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data.

[0040] Optionally, the calculation module 204 is configured to: Determine the real-time state of the target risk factor according to the current environmental data and the current construction data, and determine the static risk value of the target risk factor according to the real-time state and the current weight of the target risk factor, where the target risk factor is any one risk factor; Calculate the coupling effect value through a non-linear coupling function according to the real-time state of the risk factor pair, and determine the dynamic risk value of the risk factor pair according to the coupling strength and the coupling effect value of the risk factor pair, where the risk factor pair is a combination of any two risk factors; Calculate the total static risk value according to the static risk value, calculate the total dynamic risk value according to the dynamic risk value, and perform weighted calculation on the total static risk value and the total dynamic risk value to obtain the evaluation value.

[0041] Optionally, the construction module 202 is configured to: Obtain the number of occurrences of the risk factor pair from the historical operation data, and calculate the ratio of the number of occurrences to the total number of events to obtain the co-occurrence frequency; Calculate the Pearson correlation coefficient of the risk factor pair in the historical operation data, and perform weighted summation on the co-occurrence frequency and the Pearson correlation coefficient to obtain the initial weight.

[0042] Optionally, the construction module 202 is configured to: Calculate the mutual information value of the risk factor pair under different environmental conditions, where the mutual information value is used to measure the degree of mutual dependence of the two risk factors in the risk factor pair in the environmental data; Calculate the time series correlation of the risk factor pair during the construction process, where the time series correlation is used to measure the degree of dynamic association of the two risk factors in the risk factor pair in the construction data; Determine the coupling relationship according to the mutual information value and the time series correlation.

[0043] Optionally, the calculation module 204 is configured to: Calculate the evaluation value of the construction collapse risk of the target area by the following formula: where, R(t) represents the evaluation value corresponding to time t, W i (t) represents the weight of node i at time t, S i (t) represents the real-time state of node i at time t, C ij (t) represents the coupling strength between node i and node j at time t, S j (t)) represents the coupling effect value between the real-time state of node i at time t and the real-time state of node j at time t, α represents the static risk contribution coefficient, and β represents the dynamic risk contribution coefficient.

[0044] Optionally, the system further includes a weight module configured to: Calculate the weight of node i at time t by the following formula: W i (t) = W i (t - 1) + λ△S i (t) where, W i (t) represents the weight of node i at time t, W i (t - 1) represents the weight of node i at time t - 1, λ represents the learning rate, and △S i (t) represents the state change rate of node i.

[0045] Optionally, the system further includes a prediction module configured to: Train a long short-term memory network model according to the historical operation data, the historical environment data, and the historical construction data; use the trained long short-term memory network model to predict the real-time state change trend of each node in the future time period, and update the coupling strength between nodes according to the predicted node state change trend; Calculate the evaluation value of the construction collapse risk of the target area within a future preset time period according to the updated coupling strength.

[0046] It should be noted that: when the device provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual application, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be elaborated here.

[0047] This embodiment also discloses an electronic device, referring to Figure 3, the electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, a network interface 304, and at least one memory 305.

[0048] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0049] Among them, the user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0050] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0051] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines, and by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, as well as calling data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 301 and may be implemented separately through a single chip.

[0052] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above method embodiments, etc.; the data storage area may store data involved in the above method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. As Figure 3 shown, in the memory 305 as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program of the evaluation method for the collapse risk of mountain tunnel construction.

[0053] In Figure 3 the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; while the processor 301 can be used to call the application program of the evaluation method for the collapse risk of mountain tunnel construction stored in the memory 305. When executed by one or more processors 301, the electronic device is caused to execute the method of one or more of the above embodiments.

[0054] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0055] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0056] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0057] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0058] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0059] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 305 and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned memory 305 includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0060] The foregoing are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the disclosure of the specification. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An evaluation method for the collapse risk of mountain tunnel construction, characterized in that, Applied to a risk assessment platform, the method includes: Obtain the historical operation data of a mountain tunnel, and obtain the historical environmental data and historical construction data of the target area. The historical environmental data includes surrounding rock grade, joint density, groundwater seepage volume, and ground settlement. The historical construction data includes surrounding rock deformation, support stress, and tunneling machine parameters; Construct a dynamic network of risk factors with each risk factor as a node, establish the association relationship and initial weights between nodes according to the historical operation data, and determine the coupling relationship between nodes according to the historical environmental data and the historical construction data; Obtain the current environmental data and current construction data of the target area, determine the current weight of each node according to the current environmental data, the current construction data, and the initial weights, and determine the coupling strength between nodes according to the current environmental data, the current construction data, and the coupling relationship; Calculate the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data.

2. The evaluation method for the collapse risk of mountain tunnel construction according to claim 1, wherein The calculating the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data includes: Determine the real-time state of the target risk factor according to the current environmental data and the current construction data, and determine the static risk value of the target risk factor according to the real-time state and the current weight of the target risk factor. The target risk factor is any one risk factor; Calculate the coupling effect value through a non-linear coupling function according to the real-time state of the risk factor pair, and determine the dynamic risk value of the risk factor pair according to the coupling strength and the coupling effect value of the risk factor pair. The risk factor pair is a combination of any two risk factors; Calculate the total static risk value according to the static risk value, calculate the total dynamic risk value according to the dynamic risk value, and perform weighted calculation on the total static risk value and the total dynamic risk value to obtain the evaluation value.

3. The evaluation method for the collapse risk of mountain tunnel construction according to claim 2, wherein The establishing the association relationship and initial weights between nodes according to the historical operation data includes: Obtain the number of events in which the risk factor pair appears from the historical operation data, and calculate the ratio of the number of events to the total number of events to obtain the co-occurrence frequency; Calculate the Pearson correlation coefficient of the risk factor pair in the historical operation data, and perform weighted summation on the co-occurrence frequency and the Pearson correlation coefficient to obtain the initial weight.

4. The evaluation method for the collapse risk of mountain tunnel construction according to claim 3, characterized in that, The determining the coupling relationship between nodes according to the historical environmental data and the historical construction data includes: Calculate the mutual information value of the risk factor pair under different environmental conditions. The mutual information value is used to measure the degree of mutual dependence of the two risk factors in the risk factor pair in the environmental data; Calculate the time series correlation of the risk factor pair during the construction process. The time series correlation is used to measure the degree of dynamic association of the two risk factors in the risk factor pair in the construction data; Determine the coupling relationship according to the mutual information value and the time series correlation.

5. The evaluation method for the collapse risk of mountain tunnel construction according to claim 1, wherein Calculating the evaluation value of the construction collapse risk of the target area based on the current weight, the coupling strength, the current environmental data, and the current construction data includes: Calculating the evaluation value of the construction collapse risk of the target area by the following formula: Among them, R(t) represents the evaluation value corresponding to time t, and W i (t) represents the weight of node i at time t, and S i (t) represents the real-time state of node i at time t, and C ij (t) represents the coupling strength between node i and node j at time t, S j (t)) represents the coupling effect value between the real-time state of node i at time t and the real-time state of node j at time t, α represents the static risk contribution coefficient, and β represents the dynamic risk contribution coefficient.

6. The evaluation method for the collapse risk of mountain tunnel construction according to claim 5, wherein The method further includes: Calculating the weight of node i at time t by the following formula: W i W(t) = i W(t - 1)+λ△S i (t) Among them, W i (t) represents the weight of node i at time t, W i (t - 1) represents the weight of node i at time t - 1, λ represents the learning rate, and △S i (t) represents the state change rate of node i.

7. The evaluation method for the collapse risk of mountain tunnel construction according to claim 1, characterized in that, The method further includes: Training a long short-term memory network model according to the historical operation data, the historical environmental data, and the historical construction data; Using the trained long short-term memory network model to predict the real-time state change trend of each node in the future period, and updating the coupling strength between nodes according to the predicted node state change trend; Calculating the evaluation value of the construction collapse risk of the target area within a future preset time period according to the updated coupling strength.

8. An evaluation system for the risk of construction collapse in mountain tunnels, characterized in that, Including an acquisition module, a construction module, a coupling module, and a calculation module, where: The acquisition module is configured to obtain the historical operation data of the mountain tunnel, and obtain the historical environmental data and historical construction data of the target area. The historical environmental data includes the surrounding rock grade, joint density, groundwater seepage volume, and ground settlement. The historical construction data includes surrounding rock deformation, support stress, and tunneling machine parameters; The construction module is configured to construct a dynamic network of risk factors with each risk factor as a node, establish the association relationship and initial weight between nodes according to the historical operation data, and determine the coupling relationship between nodes according to the historical environmental data and the historical construction data; The coupling module is configured to obtain the current environmental data and current construction data of the target area, determine the current weight of each node according to the current environmental data, the current construction data, and the initial weight, and determine the coupling strength between nodes according to the current environmental data, the current construction data, and the coupling relationship; The calculation module is configured to calculate the evaluation value of the construction collapse risk of the target area according to the current weight, the coupling strength, the current environmental data, and the current construction data.

9. An electronic device, characterized in that, Including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. Both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1-7 is executed.

Images