A method and system for dynamically evaluating the risk of large-diameter shield tunneling in a volcanic ash stratum

Abstract

The application provides a method and system for dynamically evaluating the risk of large-diameter shield tunneling in a volcanic ash stratum. The method includes: processing the identified key risk factors to obtain real-time risk scores, determining the influence of each risk factor on the overall risk through sensitivity analysis, and normalizing the initial weights; dynamically adjusting the initial weights based on the real-time risk scores and the sensitivity analysis index to form a comprehensive risk index; and combining the obtained comprehensive risk index with a dynamic risk heat map for risk assessment. This method dynamically adjusts the sensitivity analysis and risk heat map to quantify the impact of key risk factors, dynamically updates the risk status using real-time monitoring data, and provides scientific decision support for large-diameter shield tunneling in volcanic ash strata.

Description

Technical Field

[0001] This invention relates to the field of risk assessment, and more specifically, to a method and system for dynamic risk assessment of large-diameter shield tunneling in volcanic ash formations. Background Technology

[0002] Shield tunneling in volcanic ash formations often faces challenges such as poor formation stability, severe cutter wear, and large fluctuations in construction parameters. These risks not only increase the likelihood of construction accidents but also significantly reduce construction efficiency and equipment lifespan. Existing risk assessment methods are mostly static analyses, unable to reflect real-time formation changes and construction risks, and lack sufficient sensitivity identification of risk factors and dynamic adjustment capabilities, leading to significant deviations between assessment results and actual conditions. Furthermore, the reliance on manual experience for parameter adjustments during construction makes it difficult to efficiently handle complex risk scenarios. In summary, the main problems encountered in existing shield tunneling processes include:

[0003] (1) Risk prediction challenges caused by stratigraphic complexity: Volcanic ash strata have complex and rapidly changing geological characteristics, and traditional static assessment methods are difficult to accurately capture stratigraphic changes.

[0004] (2) Problem of insufficient sensitivity of risk factors: Existing assessment methods do not adequately analyze the interaction between risk factors, making it difficult to quantify the contribution of key risk factors.

[0005] (3) Problem of insufficient optimization of construction parameters: The setting of tunneling parameters of shield machine relies heavily on manual experience and lacks data support.

[0006] (4) The problem of balancing construction efficiency and safety: Traditional methods have failed to fully balance construction efficiency and safety.

[0007] In view of this, the present invention is hereby proposed. Summary of the Invention

[0008] In view of this, the present invention proposes a dynamic risk assessment method for large-diameter shield tunneling in volcanic ash formations. This method is based on sensitivity analysis and dynamic adjustment of risk heat maps. The goal is to provide scientific decision support for large-diameter shield tunneling in volcanic ash formations by quantifying the impact of key risk factors and dynamically updating the risk status using real-time monitoring data.

[0009] Specifically, the present invention is achieved through the following technical solutions:

[0010] This invention provides a method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash formations, comprising the following steps:

[0011] The identified key risk factors are processed to obtain real-time risk scores. Sensitivity analysis is used to determine the degree of impact of each risk factor on the overall risk and normalization is used to form initial weights.

[0012] The initial weights are dynamically adjusted using the real-time risk score and the index from the sensitivity analysis to form a comprehensive risk index.

[0013] The obtained comprehensive risk index is combined with the dynamic risk heat map for risk assessment.

[0014] This invention proposes a dynamic risk assessment method based on real-time data acquisition, sensitivity analysis, and dynamic risk heatmaps. This method can perceive changes in construction risks in real time, guide construction teams to make scientific decisions, and thus improve construction efficiency and safety. It provides particularly effective solutions to the following technical problems:

[0015] (1) Risk prediction challenges caused by geological complexity: This method comprehensively reflects the impact of geological changes on risk during tunneling through real-time data acquisition and dynamic heat map updates.

[0016] (2) Problem of insufficient sensitivity of risk factors: This invention dynamically adjusts the weight of risk factors through sensitivity analysis to improve the scientificity and accuracy of risk prediction.

[0017] (3) Problem of insufficient optimization of construction parameters: This method is based on machine learning model to predict short-term risk trends and provides optimization suggestions to achieve scientific adjustment of tunneling parameters.

[0018] (4) The problem of balancing construction efficiency and safety: This invention reduces risks and improves construction efficiency through dynamic risk assessment and optimization adjustment suggestions, ensuring the economy and safety of the tunneling process.

[0019] Preferably, as a further feasible option, the real-time risk score is obtained through two parameters: real-time risk probability and risk impact level. The real-time risk probability is predicted by an autoregressive integral moving average model, and the real-time risk impact level is predicted by a random forest model learning algorithm.

[0020] Preferably, as a further feasible option, the method of prediction using the autoregressive integral moving average model is achieved by describing the dynamic characteristics of time series data through autoregression, difference integral, and moving average, as shown in the following formula:

[0021] ;

[0022] in, c -Constant term, -Autoregressive coefficient, -Random error, - Autoregressive order;

[0023] The prediction algorithm using the random forest model learns from the regression of features on the degree of risk impact. A single decision tree... The predicted value is:

[0024] ;

[0025] in, - The label value of the sample falling into the leaf node; N - The number of samples in this leaf node;

[0026] The mean of all decision tree predictions:

[0027] ;

[0028] in, -No. m The predicted values ​​of each tree for feature X. M - The total number of decision trees.

[0029] Preferably, as a further feasible option, the indices in the sensitivity analysis process are calculated according to the following formula:

[0030] ;

[0031] in, Risk factors i Sensitivity index, Risk scoring Y exist The expected change of conditions This represents the total variance of the risk score.

[0032] Preferably, as a further feasible option, the method for normalizing to form the initial weights includes:

[0033] Sensitivity index Normalization is performed to obtain the initial weights for each risk factor. :

[0034] .

[0035] Preferably, as a further feasible option, the method for dynamically adjusting the initial weights of the sensitivity analysis index includes: based on real-time risk scores. and sensitivity index The process of adjusting weights, including real-time risk scoring The specific formula is as follows:

[0036] ;

[0037] in, For real-time risk scoring, , Here, are parameters, representing the risk probability and the degree of risk impact, respectively;

[0038] Real-time risk scoring and sensitivity index The weights are adjusted according to the following formula:

[0039] .

[0040] Preferably, as a further feasible option, a time smoothing mechanism is introduced during the dynamic adjustment of the initial weights, with the specific formula as follows:

[0041] ;

[0042] in, α - The smoothing coefficient (0~1) determines the proportion of influence between historical weights and current weights.

[0043] Preferably, as a further feasible option, the comprehensive risk index is expressed according to the following formula:

[0044] ;

[0045] in, The weights are dynamically adjusted based on sensitivity analysis. For real-time risk scoring.

[0046] In addition to providing a method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash formations, this invention also provides a system for dynamic risk assessment of large-diameter shield tunneling in volcanic ash formations, comprising:

[0047] Normalization module: Used to process the identified key risk factors to obtain real-time risk scores, determine the impact of each risk factor on the overall risk through sensitivity analysis, and normalize to form initial weights;

[0048] Dynamic adjustment module: used to dynamically adjust the initial weights based on the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index;

[0049] Assessment module: Used to combine the obtained comprehensive risk index with the dynamic risk heat map to conduct risk assessment. Attached Figure Description

[0050] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0051] Figure 1 This is a flowchart of the risk dynamic assessment method of the present invention;

[0052] Figure 2 This is a block diagram of the risk dynamic assessment system of the present invention;

[0053] Figure 3 This is a flowchart illustrating a computer device provided in an embodiment of the present invention. Detailed Implementation

[0054] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure; rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0055] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms. Unless the context clearly indicates otherwise, it should be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0056] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, depending on the context. For example, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0057] Example

[0058] like Figure 1 As shown, this invention provides a method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash formations, comprising the following steps:

[0059] S1. The identified key risk factors are processed to obtain real-time risk scores. Sensitivity analysis is used to determine the degree of influence of each risk factor on the overall risk and normalization is used to form initial weights.

[0060] S2. The initial weights are dynamically adjusted using the real-time risk score and the index from the sensitivity analysis to form a comprehensive risk index.

[0061] S3. Combine the obtained comprehensive risk index with the dynamic risk heat map to conduct a risk assessment.

[0062] Specifically, in step S1, the real-time risk score is obtained through two parameters: the real-time risk probability and the degree of risk impact. The real-time risk probability is predicted by an autoregressive integral moving average model, and the real-time degree of risk impact is predicted by a random forest model learning algorithm.

[0063] Real-time risk scoring is related to two parameters: risk probability and risk impact. Risk probability is the likelihood of a risk occurring. P i - Probability of occurrence (0~1). I i - The degree of risk impact.

[0064] Real-time risk scoring The relationship between risk probability and risk impact can be expressed by the following formula:

[0065] ;

[0066] in, For real-time risk scoring, , Here, are parameters, representing the risk probability and the degree of risk impact, respectively.

[0067] Predicting in real time and It was obtained using an autoregressive integral moving average model and a random forest model learning algorithm.

[0068] The sliding window generation sequence involves generating window data from construction parameters according to a time series. For example, assuming the sliding window is *n*: features—the most recent *n* records of parameters such as cutterhead torque and feed speed; labels—the probability of the risk occurring at the next moment. The method of prediction using the autoregressive integral moving average model describes the dynamic characteristics of the time series data through autoregression, difference integrals, and moving averages, as shown in the following formula:

[0069] ;

[0070] in, c-Constant term, -Autoregressive coefficient, -Random error, - Autoregressive order.

[0071] Random forest models are suitable for processing multidimensional feature data and can perform regression predictions on the degree of impact based on features. The feature selection process chooses key features related to the degree of risk impact, such as cutterhead torque, propulsion speed, formation pressure, and geological information.

[0072] The prediction algorithm using the random forest model learns from the regression of features on the degree of risk impact. A single decision tree... The predicted value is:

[0073] ;

[0074] in, - The label value of the sample falling into the leaf node; N - The number of samples in this leaf node;

[0075] The mean of all decision tree predictions:

[0076] ;

[0077] in, -No. m The predicted values ​​of each tree for feature X. M - The total number of decision trees.

[0078] Preferably, in step S1, the indices in the sensitivity analysis process are calculated according to the following formula:

[0079] ;

[0080] in, Risk factors i Sensitivity index, Risk scoring Y exist The expected change of conditions This represents the total variance of the risk score.

[0081] In the above formula, the sensitivity index The larger the value, the more significant the impact of the risk factor on the total risk.

[0082] Preferably, in step S1, the method for normalizing to form the initial weights includes:

[0083] Sensitivity index Normalization is performed to obtain the initial weights for each risk factor. :

[0084] .

[0085] Preferably, in step S2, the method for dynamically adjusting the initial weights using the sensitivity analysis index includes: real-time risk scoring. and sensitivity index The weights are adjusted according to the following formula:

[0086] .

[0087] To avoid frequent fluctuations in weights, a time smoothing mechanism was also introduced:

[0088] ;

[0089] in, α - The smoothing coefficient (0~1) determines the proportion of influence between historical weights and current weights.

[0090] Specifically, the formula for the comprehensive risk index in step S2 is as follows:

[0091] ;

[0092] in, The weights are dynamically adjusted based on sensitivity analysis. For real-time risk scoring.

[0093] Specifically, step S3 involves combining the comprehensive risk index generated in step S2 with the dynamic risk heatmap to conduct a joint risk assessment, thereby improving the accuracy of the risk assessment. The dynamic risk heatmap includes a horizontal axis and a vertical axis. The horizontal axis represents the probability of risk occurrence (low-high), and the vertical axis represents the degree of risk impact (small-large). The heatmap area is dynamically updated, and the color reflects the risk level (blue-low, yellow-medium, red-high).

[0094] In summary, dynamic risk heatmaps and comprehensive risk indices help construction workers quickly locate high-risk areas. When a risk factor score reaches a high-risk level, the system issues a real-time alert and provides specific suggestions for adjusting construction parameters.

[0095] In addition to providing a dynamic risk assessment method, this invention also provides a dynamic risk assessment system, specifically as follows: Figure 2 As shown, it includes:

[0096] Normalization module 101: It is used to process the identified key risk factors to obtain real-time risk scores, determine the degree of influence of each risk factor on the overall risk through sensitivity analysis, and normalize to form initial weights;

[0097] Dynamic adjustment module 102: used to dynamically adjust the initial weights based on the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index;

[0098] Assessment module 103: used to combine the obtained comprehensive risk index with the dynamic risk heat map to conduct risk assessment.

[0099] In practice, the above modules can be implemented as independent entities or combined in any way to be implemented as the same or several entities. For the specific implementation of each unit, please refer to the previous method implementation examples, which will not be repeated here.

[0100] In summary, the solution of the present invention has the following technical effects:

[0101] (1) Real-time risk monitoring and dynamic assessment: Through sensor networks and real-time data acquisition technology, continuous monitoring of the shield tunneling process is achieved, and through sensitivity analysis and dynamic adjustment of risk heat maps, the risk changes are reflected in real time, thereby improving the timeliness and accuracy of risk assessment.

[0102] (2) Sensitivity analysis-driven dynamic optimization: introduce sensitivity analysis technology to quantify the contribution of key risk factors to the total risk, and dynamically adjust the weight of risk factors based on real-time data to effectively identify and focus on the factors that have the greatest impact on the overall risk and optimize the construction strategy.

[0103] (3) Machine learning-driven risk prediction: Using the autoregressive integral moving average model and random forest algorithm, combined with historical data and real-time data, the short-term trend of risk factors is predicted, the accuracy of risk prediction is improved, and a scientific basis is provided for the adjustment of construction plans.

[0104] (4) Dynamic risk heat map visualization: Construct a dynamic risk heat map to intuitively display the probability and impact distribution of risk factors, making it convenient for the construction team to quickly locate high-risk areas and take countermeasures.

[0105] (5) Alarm and feedback mechanism: When the comprehensive risk index exceeds the preset threshold, the system triggers an alarm and provides adjustment suggestions (such as reducing the tunneling speed, adjusting the cutterhead parameters, etc.) to guide construction personnel to optimize tunneling operations and reduce the probability of construction accidents.

[0106] (6) Improved construction efficiency and safety: Through dynamic evaluation and optimization, the risk of equipment wear and construction delays is reduced, and an effective balance between construction efficiency and safety is achieved.

[0107] Figure 3 This is a schematic diagram of the structure of a computer device disclosed in this invention. (Reference) Figure 3As shown, the computer device 400 includes at least a memory 402 and a processor 401; the memory 402 is connected to the processor via a communication bus 403 and is used to store computer instructions executable by the processor 401. The processor 401 is used to read computer instructions from the memory 402 to implement the steps of the method described in any of the above embodiments.

[0108] For the above-described apparatus embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The apparatus embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0109] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal disks or removable disks), magneto-optical disks, and CD-ROMs and DVD-ROMs. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0110] Finally, it should be noted that although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily used to describe the features of specific embodiments of a particular invention. Certain features described in the various embodiments of this specification may also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0111] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0112] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0113] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash formations, characterized in that, Includes the following steps: The identified key risk factors are processed to obtain real-time risk scores. Sensitivity analysis is used to determine the degree of impact of each risk factor on the overall risk and normalization is used to form initial weights. The initial weights are dynamically adjusted using the real-time risk score and the index from the sensitivity analysis to form a comprehensive risk index. The obtained comprehensive risk index is combined with the dynamic risk heat map for risk assessment. The real-time risk score is obtained through two parameters: real-time risk probability and risk impact. The real-time risk probability is predicted by an autoregressive integral moving average model, and the real-time risk impact is predicted by a random forest model learning algorithm. The method for prediction using the autoregressive integral moving average model describes the dynamic characteristics of time series data through autoregression, difference integral, and moving average. The formula is as follows: in, c -Constant term, -Autoregressive coefficient, -Random error, - Autoregressive order; The prediction algorithm using the random forest model learns from the regression of features on the degree of risk impact. A single decision tree... The predicted value is: in, - The label value of the sample falling into the leaf node; N - The number of samples in this leaf node; The mean of all decision tree predictions: in, -No. m The predicted values ​​of each tree for feature X. M - The total number of decision trees; The indices in the sensitivity analysis process are calculated according to the following formula: in, Risk factors i Sensitivity index, Risk scoring Y exist The expected change of conditions The total variance of the risk score; Methods for normalizing initial weights include: Sensitivity index Normalization is performed to obtain the initial weights for each risk factor. : ； The method for dynamically adjusting the initial weights based on the sensitivity analysis index includes: based on real-time risk scores. and sensitivity index The process of adjusting weights, including real-time risk scoring. The specific formula is as follows: in, For real-time risk scoring, , Here, are parameters, representing the risk probability and the degree of risk impact, respectively; Real-time risk scoring and sensitivity index The weights are adjusted according to the following formula: ； A time smoothing mechanism is also introduced during the dynamic adjustment of the initial weights, as shown in the following formula: in, α - The smoothing coefficient (0~1) determines the proportion of influence between historical weights and current weights; The comprehensive risk index is expressed according to the following formula: in, The weights are dynamically adjusted based on sensitivity analysis. For real-time risk scoring.

2. A risk dynamic assessment system employing the risk dynamic assessment method for large-diameter shield tunneling in volcanic ash strata as described in claim 1, characterized in that, include: Normalization module: Used to process the identified key risk factors to obtain real-time risk scores, determine the impact of each risk factor on the overall risk through sensitivity analysis, and normalize to form initial weights; Dynamic adjustment module: used to dynamically adjust the initial weights based on the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; Assessment module: Used to combine the obtained comprehensive risk index with the dynamic risk heat map to conduct risk assessment.

3. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the risk dynamic assessment method as described in claim 1.

Images