Method and system for dynamically evaluating large-diameter shield tunneling risk in volcanic ash stratum

Abstract

The invention provides a volcanic ash stratum large-diameter shield tunneling risk dynamic assessment method and system, and the method comprises the steps: carrying out the data processing of recognized key risk factors, obtaining a real-time risk score, determining the influence degree of each risk factor on the overall risk through sensitivity analysis, and carrying out the normalization of the influence degree to form an initial weight; dynamically adjusting the initial weight through the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; and combining the obtained comprehensive risk index with a dynamic risk heat map to carry out risk assessment. The method is based on sensitivity analysis and risk heat map dynamic adjustment, and aims to provide scientific decision support for volcanic ash stratum large-diameter shield tunneling workers by quantifying the influence of key risk factors and utilizing real-time monitoring data to dynamically update the risk state.

Description

Technical Field

[0001] The present invention relates to the field of risk assessment, and in particular to a method and system for dynamically assessing the risk of large-diameter shield tunneling in volcanic ash strata. Background Art

[0002] Shield construction under volcanic ash strata often faces problems such as poor stratum stability, severe tool wear, and large fluctuations in construction parameters. These risks not only increase the possibility of construction accidents, but also significantly reduce construction efficiency and equipment life. Existing risk assessment methods are mostly static analysis, which cannot reflect stratum changes and construction risks in real time, and lack the sensitivity to risk factors and the ability to adjust dynamically, resulting in a large deviation between the assessment results and the actual situation. In addition, the construction process mostly relies on manual experience to adjust parameters, which makes it difficult to efficiently deal with complex risk scenarios. In general, the main problems encountered in the existing shield construction process are: (1) Difficulties in risk prediction due to formation complexity: The geological characteristics of volcanic ash formations are complex and change rapidly, and traditional static assessment methods are difficult to accurately capture formation changes.

[0003] (2) The problem of insufficient sensitivity of risk factors: Existing assessment methods do not adequately analyze the mutual impact between risk factors, making it difficult to quantify the contribution of key risk factors.

[0004] (3) Insufficient optimization of construction parameters: The setting of shield machine excavation parameters mostly relies on manual experience and lacks data support.

[0005] (4) The difficulty in balancing construction efficiency and safety: Traditional methods fail to fully take into account both construction efficiency and safety.

[0006] In view of this, the present invention is proposed. Summary of the invention

[0007] In view of this, the present invention proposes a dynamic assessment method for the risk of large-diameter shield tunneling in volcanic ash strata. The method is based on sensitivity analysis and dynamic adjustment of risk heat maps. The goal is to quantify the impact of key risk factors and dynamically update the risk status using real-time monitoring data, so as to provide scientific decision-making support for large-diameter shield tunneling workers in volcanic ash strata.

[0008] Specifically, the present invention is achieved through the following technical solutions: The present invention provides a method for dynamically assessing the risk of large-diameter shield tunneling in volcanic ash strata, comprising the following steps: The key risk factors identified are processed to obtain real-time risk scores. The impact of each risk factor on the overall risk is determined through sensitivity analysis and normalized to form initial weights. Dynamically adjusting the initial weights through the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; The obtained comprehensive risk index is combined with the dynamic risk heat map to perform risk assessment.

[0009] The present invention proposes a dynamic risk assessment method based on real-time data collection, sensitivity analysis and dynamic risk heat map, which can perceive the changes in construction risks in real time and guide the construction team to make scientific decisions, thereby improving construction efficiency and safety. In particular, it can provide good solutions to the following technical problems: (1) Difficulties in risk prediction caused by geological complexity: This method comprehensively reflects the impact of geological changes on risks during excavation through real-time data collection and dynamic heat map updates.

[0010] (2) Problem of insufficient sensitivity of risk factors: The present invention dynamically adjusts the weights of risk factors through sensitivity analysis to improve the scientificity and accuracy of risk prediction.

[0011] (3) Insufficient optimization of construction parameters: This method predicts short-term risk trends based on machine learning models and provides optimization suggestions to achieve scientific adjustment of excavation parameters.

[0012] (4) The problem of difficulty in balancing construction efficiency and safety: The present invention reduces risks while improving construction efficiency through dynamic risk assessment and optimization adjustment suggestions, thereby ensuring the economy and safety of the excavation process.

[0013] Preferably, as a further implementable scheme, the real-time risk score is obtained by two parameters: real-time risk probability and risk impact degree. The real-time risk probability is predicted by an autoregressive integrated moving average model, and the real-time risk impact degree is predicted by a random forest model learning algorithm.

[0014] Preferably, as a further implementable solution, the method of predicting by the autoregressive integrated moving average model is achieved by describing the dynamic characteristics of time series data through autoregression, differential integration and moving average, and the formula is as follows: ; in, c - constant term, - autoregression coefficients, - Random errors, -autoregressive order; The prediction by learning the algorithm of random forest model is to make regression prediction based on the impact of features on risk. The predicted value of is: ; in, -The sample label value 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 value of feature X by the tree, M -Total number of decision trees.

[0015] Preferably, as a further implementable solution, the index in the sensitivity analysis process is calculated according to the following formula: ; in, Risk factors i The sensitivity index, Score Risk Y exist The conditional expected change of is the total variance of the risk score.

[0016] Preferably, as a further implementable solution, the method of normalizing to form the initial weights includes: The sensitivity index Normalization is performed to obtain the initial weight of each risk factor. : .

[0017] Preferably, as a further implementable solution, the method for dynamically adjusting the initial weights by the sensitivity analysis index includes: and sensitivity index The process of adjusting weights, where risk scores are scored in real time The specific formula is: ; in, For real-time risk scoring, , are parameters, which are risk probability and risk impact degree respectively; Real-time risk scoring and sensitivity index Adjust the weights according to the following formula: .

[0018] Preferably, as a further implementable solution, a time smoothing mechanism is introduced in the process of dynamic adjustment of the initial weights. The specific formula is as follows: ; in, α -Smoothing coefficient (0~1), which determines the influence ratio of historical weight and current weight.

[0019] Preferably, as a further implementable solution, the comprehensive risk index is expressed according to the following formula: ; in, The weights are dynamically adjusted based on sensitivity analysis. Score risk in real time.

[0020] In addition to providing a method for dynamically assessing the risk of large-diameter shield tunneling in volcanic ash strata, the present invention also provides a system for dynamically assessing the risk of large-diameter shield tunneling in volcanic ash strata, comprising: Normalization module: used to process the data of 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 them to form initial weights; Dynamic adjustment module: used for dynamically adjusting the initial weights through the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; Evaluation module: used to combine the obtained comprehensive risk index with the dynamic risk heat map to perform risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Various other advantages and benefits will become apparent to those skilled in the art by reading the following detailed description of the preferred embodiments. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. The same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 is a flow chart of the risk dynamic assessment method of the present invention; Figure 2 is a block diagram of the risk dynamic assessment system of the present invention; Figure 3 A flowchart of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] Exemplary embodiments will be described in detail herein, examples of which are shown 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 the present disclosure. Instead, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims. The terms used in the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items. It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" used herein may be interpreted as "at the time" or "when" or "in response to determining", Example like Figure 1 As shown, the present invention provides a method for dynamically assessing the risk of large-diameter shield tunneling in volcanic ash strata, comprising the following steps: S1. 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 them to form initial weights; S2. Dynamically adjusting the initial weights through the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; S3. Combining the obtained comprehensive risk index with the dynamic risk heat map to conduct risk assessment.

[0023] Specifically, in step S1, the real-time risk score is obtained through two parameters: real-time risk probability and risk impact degree. The real-time risk probability is predicted by the autoregressive integrated moving average model, and the real-time risk impact degree is predicted by the random forest model learning algorithm.

[0024] Real-time risk scoring is related to two parameters: risk probability and risk impact. Risk probability is the probability of risk occurrence. P i -Probability of occurrence (0~1), I i - Risk impact.

[0025] Real-time risk scoring The relationship between the risk probability and the risk impact degree is expressed by the following specific formula: ; in, For real-time risk scoring, , are parameters, which are risk probability and risk impact degree respectively.

[0026] Predict real-time and It is obtained by using the autoregressive integrated moving average model and random forest model learning algorithm.

[0027] The sliding window generation sequence is to generate window data from the construction parameters in time series. For example, assuming the sliding window is 𝑛: Features - the latest 𝑛 records of parameters such as cutter head torque and propulsion speed; Label - the probability of risk occurrence at the next moment. The method of predicting by the autoregressive integral moving average model is achieved by describing the dynamic characteristics of time series data through autoregression, differential integration and moving average. The formula is as follows: ; in, c - constant term, - autoregression coefficients, - Random errors, -Autoregressive order.

[0028] The random forest model is suitable for processing multi-dimensional feature data, and can perform regression prediction on the impact degree based on the features. In the feature selection part, key features of the risk impact degree are selected, such as cutter head torque, propulsion speed, formation pressure, geological information, etc.

[0029] The prediction by learning the algorithm of random forest model is to make regression prediction based on the impact of features on risk. The predicted value of is: ; in, -The sample label value 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 value of feature X by the tree, M -Total number of decision trees.

[0030] Preferably, in step S1, the index in the sensitivity analysis process is calculated according to the following formula: ; in, Risk factors i The sensitivity index, Score Risk Y exist The conditional expected change of is the total variance of the risk score.

[0031] In the above formula, the sensitivity index The larger the value is, the more significant the impact of the risk factor on the total risk is.

[0032] Preferably, in step S1, the method of normalizing to form initial weights includes: The sensitivity index Normalization is performed to obtain the initial weight of each risk factor. : .

[0033] Preferably, in step S2, the method for dynamically adjusting the initial weights by the sensitivity analysis index includes: real-time risk scoring and sensitivity index Adjust the weights according to the following formula: .

[0034] In order to avoid frequent fluctuations in weights, a time smoothing mechanism is introduced: ; in, α -Smoothing coefficient (0~1), which determines the influence ratio of historical weight and current weight.

[0035] Specifically, the formula for forming the comprehensive risk index in step S2 is as follows: ; in, The weights are dynamically adjusted based on sensitivity analysis. Score risk in real time.

[0036] Specifically, step S3 combines the comprehensive risk index formed in step S2 with the dynamic risk heat map to conduct risk assessment to improve the accuracy of risk assessment. The dynamic risk heat map includes a horizontal axis and a vertical axis. The horizontal axis is the probability of risk occurrence (low-high), and the vertical axis is the degree of risk impact (small-large). The heat map area is dynamically updated, and the color reflects the risk level (blue-low, yellow-medium, red-high).

[0037] In short, dynamic risk heat maps and comprehensive risk indexes can help construction workers quickly locate high-risk areas. When a risk factor score reaches a high risk level, the system will issue a warning in real time and output specific construction parameter adjustment suggestions.

[0038] In addition, the present invention provides a dynamic risk assessment method and a dynamic risk assessment system. Figure 2 As shown, including: Normalization module 101: 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 them to form initial weights; Dynamic adjustment module 102: used to dynamically adjust the initial weights according to the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; Evaluation module 103: used to combine the obtained comprehensive risk index with the dynamic risk heat map to perform risk evaluation.

[0039] In specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0040] In summary, the solution of the present invention has the following technical effects: (1) Real-time risk monitoring and dynamic assessment: Through sensor networks and real-time data acquisition technology, the shield tunneling process can be continuously monitored. Through sensitivity analysis and dynamic adjustment of risk heat maps, risk changes can be reflected in real time, thereby improving the timeliness and accuracy of risk assessment.

[0041] (2) Dynamic optimization driven by sensitivity analysis: Introduce sensitivity analysis technology to quantify the contribution of key risk factors to the total risk, and dynamically adjust the weights of risk factors based on real-time data, effectively identify and focus on factors that have the greatest impact on the overall risk, and optimize construction strategies.

[0042] (3) Risk prediction driven by machine learning: The autoregressive integrated moving average model and random forest algorithm are used to combine historical data with real-time data to predict the short-term change trend of risk factors, improve the accuracy of risk prediction, and provide a scientific basis for the adjustment of construction plans.

[0043] (4) Dynamic risk heat map visualization: Construct a dynamic risk heat map to intuitively display the probability and impact distribution of risk factors, so that the construction team can quickly locate high-risk areas and take countermeasures.

[0044] (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 excavation speed, adjusting the cutter parameters, etc.), promptly guiding construction personnel to optimize excavation operations and reduce the probability of construction accidents.

[0045] (6) Improved construction efficiency and safety: Through dynamic evaluation and optimization adjustment, the risks of equipment wear and construction delays are reduced, achieving an effective balance between construction efficiency and safety.

[0046] Figure 3 This is a schematic diagram of the structure of a computer device disclosed in the present invention. Figure 3 As 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, and 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.

[0047] For the above-mentioned device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0048] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including, for example, 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 ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuits.

[0049] Finally, it should be noted that although this specification contains many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of specific embodiments of specific inventions. Certain features described in multiple embodiments within this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.

[0050] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood 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.

[0051] 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 can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0052] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the scope of protection of the present disclosure.

Claims

1. A method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata, characterized in that: The steps include: The key risk factors identified are processed to obtain real-time risk scores. The impact of each risk factor on the overall risk is determined through sensitivity analysis and normalized to form initial weights. Dynamically adjusting the initial weights through the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; The obtained comprehensive risk index is combined with the dynamic risk heat map to perform risk assessment.

2. The method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata according to claim 1 is characterized in that: The real-time risk score is obtained by two parameters: real-time risk probability and risk impact degree. The real-time risk probability is predicted by an autoregressive integrated moving average model, and the real-time risk impact degree is predicted by a random forest model learning algorithm.

3. The method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata according to claim 2 is characterized in that: The method predicted by the autoregressive integrated moving average model is achieved by describing the dynamic characteristics of time series data through autoregression, differential integration and moving average. The formula is as follows: in, c - constant term, - autoregression coefficients, - Random errors, -autoregressive order; The prediction by learning the algorithm of random forest model is to make regression prediction based on the impact of features on risk. The predicted value of is: in, -The sample label value 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 value of feature X by the tree, M -Total number of decision trees.

4. The method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata according to claim 3 is characterized in that: The index in the sensitivity analysis process is calculated according to the following formula: in, Risk factors i The sensitivity index, Score Risk Y exist The conditional expected change of is the total variance of the risk score.

5. The method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata according to claim 4 is characterized in that: The methods for normalizing the initial weights include: The sensitivity index Normalization is performed to obtain the initial weight of each risk factor. : 。 6. The method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata according to claim 5 is characterized in that: The method for dynamically adjusting the initial weights by the sensitivity analysis index includes: and sensitivity index The process of adjusting weights, where risk scores are scored in real time The specific formula is: in, For real-time risk scoring, , are parameters, which are risk probability and risk impact degree respectively; Real-time risk scoring and sensitivity index Adjust the weights according to the following formula: 。 7. The method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata according to claim 6 is characterized in that: A time smoothing mechanism is also introduced in the process of dynamic adjustment of initial weights. The specific formula is as follows: in, α -Smoothing coefficient (0~1), which determines the influence ratio of historical weight and current weight.

8. The method for dynamic risk assessment of large-diameter shield tunneling in volcanic ash strata according to claim 7 is characterized in that: The comprehensive risk index is expressed according to the following formula: in, The weights are dynamically adjusted based on sensitivity analysis. Score risk in real time.

9. A risk dynamic assessment system using the risk dynamic assessment method for large-diameter shield tunneling in volcanic ash strata according to any one of claims 1 to 8, characterized in that: include: Normalization module: used to process the data of 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 them to form initial weights; Dynamic adjustment module: used for dynamically adjusting the initial weights through the real-time risk score and the index of the sensitivity analysis to form a comprehensive risk index; Evaluation module: used to combine the obtained comprehensive risk index with the dynamic risk heat map to perform risk assessment.

10. 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, the steps of the risk dynamic assessment method according to any one of claims 1 to 8 are implemented.

Images