A method for optimizing design of a data monitoring scheme for TBM tunneling engineering

Abstract

This invention relates to the field of tunnel and underground engineering construction monitoring optimization technology, and proposes a method for optimizing the data monitoring scheme design for TBM tunneling projects. This method constructs a monitoring index system for the TBM tunneling process; establishes monitoring cost models and monitoring benefit parameters for each monitoring parameter; comprehensively considers engineering cost factors such as sensor deployment, operation and maintenance, and data processing, as well as the effects of monitoring parameters on tunneling efficiency, construction risk identification, and equipment status assessment, generating an optimal monitoring scheme configuration that meets the constraints of project implementation; during TBM tunneling, changes in tunneling conditions are acquired in real time, and the monitoring scheme is adaptively adjusted when changes exceed preset thresholds, achieving dynamic updates of the monitoring parameter combination; simultaneously, through a full-construction-cycle implementation and feedback mechanism, the monitoring scheme is continuously optimized. This achieves a rational allocation of monitoring resources for TBM tunneling projects while ensuring construction safety and monitoring effectiveness.

Description

Technical Field

[0001] This invention relates to the field of tunnel and underground engineering construction monitoring optimization technology, and in particular to a method for optimizing the design of data monitoring schemes for TBM tunneling projects. Background Technology

[0002] During TBM tunnel construction, TBM excavation equipment and other sensor devices generate a large amount of real-time data, including geological conditions, attitude parameters, tool wear, propulsion pressure, torque, vibration, and other monitoring data. Existing projects generally use multiple types of sensors for data collection, providing effective support for construction decisions. However, with the continuous increase in the number of sensors, monitoring costs, operation and maintenance costs, and data processing and storage costs are all rising. There are problems such as duplication of monitoring items and high redundancy of indicators. Simply reducing the number of sensors may lead to monitoring data that cannot effectively support TBM construction decisions, resulting in increased costs or even decision-making errors.

[0003] Current TBM tunneling monitoring primarily focuses on monitoring accuracy, the number of indicators, and information completeness. However, it lacks quantitative analysis of the relationship between the intrinsic value of monitoring data and the cost of monitoring investment. The selection and combination of monitoring parameters mainly rely on engineering experience, making it difficult to maximize monitoring benefits under cost constraints. Furthermore, different geological regions and different tunneling stages exhibit varying sensitivities and dependencies on monitoring parameters, and existing monitoring schemes typically cannot be dynamically optimized and adjusted in response to changes in working conditions.

[0004] Therefore, it is necessary to provide a method for optimizing the design of data monitoring schemes for TBM tunneling projects, in order to solve the problems existing in the prior art, realize the intelligent optimization and automated output of monitoring parameter combinations, form a monitoring scheme design mechanism that can be dynamically adapted to complex working conditions, thereby reducing monitoring costs, avoiding redundant monitoring, and ensuring that key data can be acquired accurately, economically, and with high value. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies and provide a method for optimizing the design of data monitoring schemes for TBM tunneling projects. This method enables intelligent optimization and automated output of monitoring parameter combinations, forming a monitoring scheme design mechanism that can dynamically adapt to complex working conditions. This reduces monitoring costs, avoids redundant monitoring, and ensures that key data can be acquired accurately, economically, and with high value.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A method for optimizing the design of a data monitoring scheme for TBM tunneling projects includes the following steps: S1. Construct a monitoring index system, collect multi-source monitoring data generated during TBM tunneling, classify monitoring parameters according to sensor type, data type and physical dimension, and set corresponding acquisition frequency, acquisition accuracy and mapping relationship with tunneling working conditions for each monitoring parameter to form a standardized TBM tunneling monitoring index system. S2. Establish a monitoring cost model. For each monitoring parameter in the monitoring indicator system, calculate the monitoring costs generated during sensor deployment, operation, maintenance and data processing, and establish a parameterized monitoring cost model corresponding to each monitoring parameter. S3. Determine the monitoring benefit parameters. Based on historical tunneling data or simulation data samples, evaluate the benefit contribution of each monitoring parameter to tunneling efficiency improvement, construction risk identification and equipment status judgment under different tunneling conditions, and obtain the corresponding monitoring benefit parameters. S4. Generate monitoring scheme configuration. Based on the monitoring cost model and monitoring benefit parameters, and under the premise of meeting the preset cost constraints, combine and select the monitoring parameters to generate the corresponding optimal monitoring scheme configuration. The monitoring scheme configuration shall at least include sensor type, quantity, deployment location, data acquisition frequency and accuracy. S5. Adaptive adjustment of monitoring scheme: Real-time acquisition of tunneling conditions during TBM tunneling. When the conditions change, the monitoring parameter combination is regenerated based on the updated monitoring costs and benefits to obtain a monitoring scheme configuration that matches the current tunneling conditions. S6. Full-cycle implementation and feedback: The monitoring scheme is configured and applied to the entire TBM tunneling construction process. The monitoring scheme is continuously updated based on the feedback of monitoring data to achieve dynamic adjustment of the monitoring scheme.

[0007] Preferably, the monitoring parameters in S1 include at least geological parameters, tunneling attitude parameters, propulsion and torque parameters, tool wear parameters, vibration parameters, and environmental parameters.

[0008] Preferably, step S1 includes: abstracting the collected multi-source monitoring data into multiple monitoring parameters; Set the data type, acquisition frequency, unit of measurement, measurement accuracy, and sensitivity indicators to changes in strata and equipment status for each monitoring parameter; Based on the tunneling conditions, a correlation is established between monitoring parameters and their monitoring importance and decision support value, thereby forming a data monitoring index system for TBM tunneling.

[0009] Preferably, step S2 includes: for each monitoring parameter, obtaining the corresponding sensor purchase cost, on-site installation and deployment cost, operating power supply cost, data transmission cost, data processing and storage cost, and equipment maintenance cost; and summarizing the above cost information to form a set of cost parameters that characterize the monitoring cost of each monitoring parameter.

[0010] Preferably, S3 includes: under different tunneling conditions, for each monitoring parameter in the data monitoring index system, obtaining a monitoring benefit parameter to characterize the degree of influence of the monitoring parameter on the tunneling construction process; The monitoring benefit parameters include at least the efficiency benefit parameters used to characterize changes in tunneling efficiency, the safety benefit parameters used to characterize the early warning capability of surrounding rock risk and machine jamming risk, and the equipment benefit parameters used to characterize the accuracy of judging the wear state of the cutting tools and the operating status of the equipment. Based on the monitoring benefit parameters, the monitoring benefit parameters corresponding to each monitoring parameter under the current tunneling conditions are determined, and the monitoring benefit parameters serve as the basis for generating and adjusting the monitoring scheme configuration.

[0011] Preferably, S4 includes: determining the feasible domain of the monitoring scheme by comprehensively evaluating actual constraints such as budget conditions, available installation space, number of sensors, communication resources, and system power consumption at the engineering site; and conducting a comprehensive comparative analysis of candidate monitoring parameters within the feasible domain based on the cost parameter set of monitoring parameters obtained in S2 and the monitoring benefit parameters obtained in S3, to determine the optimal monitoring scheme configuration that meets the engineering implementation conditions.

[0012] Preferably, S5 includes: during the TBM tunneling construction process, acquiring the tunneling condition status in real time, determining the current tunneling condition status, and triggering a monitoring scheme adjustment process when the degree of change of the tunneling condition status relative to the previous stage exceeds a preset condition sensitivity threshold; after triggering the monitoring scheme adjustment process, based on the monitoring scheme configuration formed in step S4, and combined with the updated tunneling condition status, re-screening and combining the monitoring parameters to generate a monitoring scheme configuration that matches the current tunneling condition status.

[0013] Preferably, in step S6, the monitoring scheme corresponding to the monitoring parameter combination configuration adjusted in step S5 is compared and analyzed with the currently adopted monitoring scheme. When the comprehensive benefits of the new scheme based on the monitoring benefit parameters are better than the current scheme, it is replaced with the new monitoring parameter combination.

[0014] The present invention discloses a method for optimizing the design of a data monitoring scheme for TBM tunneling projects, which has the following beneficial effects.

[0015] This invention constructs a monitoring index system for the TBM tunneling process, classifies and standardizes multi-source monitoring data, and clarifies the acquisition attributes of different monitoring parameters and their correspondence with tunneling conditions. Based on this, monitoring cost models and monitoring benefit parameters are established for each parameter. Taking into account engineering cost factors such as sensor deployment, operation and maintenance, and data processing, as well as the effects of monitoring parameters on tunneling efficiency, construction risk identification, and equipment status assessment, a monitoring scheme configuration that meets the constraints of engineering implementation is generated. During TBM tunneling, changes in tunneling conditions are acquired in real time, and the monitoring scheme is adaptively adjusted when changes exceed preset thresholds, achieving dynamic updates of the monitoring parameter combination. Simultaneously, the monitoring scheme is continuously optimized through a full-cycle implementation and feedback mechanism. Using this method, the rational allocation of monitoring resources for TBM tunneling projects can be achieved while ensuring construction safety and monitoring effectiveness, improving the adaptability of the monitoring scheme to complex and variable construction conditions. Attached Figure Description

[0016] Figure 1 This is a flowchart of a method for optimizing the design of a data monitoring scheme for TBM tunneling projects according to the present invention; Figure 2 This is a schematic diagram of the TBM tunneling monitoring index system provided by the present invention; Figure 3 This is a schematic diagram of the optimized combination of monitoring parameters provided by the present invention; Figure 4 This is a timeline diagram illustrating the dynamic adjustment and benefit evaluation of the TBM full-cycle scheme. Detailed Implementation

[0017] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0018] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0019] Please refer to Figure 1 A method for optimizing the design of a data monitoring scheme for TBM tunneling projects includes the following steps: S1. Construct a monitoring index system, collect multi-source monitoring data generated during TBM tunneling, classify monitoring parameters according to sensor type, data type and physical dimension, and set corresponding acquisition frequency, acquisition accuracy and mapping relationship with tunneling working conditions for each monitoring parameter to form a standardized TBM tunneling monitoring index system. Preferably, in this embodiment, the monitoring parameters in S1 include at least geological parameters, tunneling attitude parameters, propulsion and torque parameters, tool wear parameters, vibration parameters, and environmental parameters.

[0020] Preferably, in this embodiment, S1 includes: abstracting the collected multi-source monitoring data into multiple monitoring parameters; Set the data type, acquisition frequency, unit of measurement, measurement accuracy, and sensitivity indicators to changes in strata and equipment status for each monitoring parameter; Based on the tunneling conditions, a correlation is established between monitoring parameters and their monitoring importance and decision support value, thereby forming a data monitoring index system for TBM tunneling.

[0021] In this specific embodiment, S1 includes: S1.1 The collected multi-source monitoring data is constructed into a monitoring parameter set vector as follows: ; in, Indicates the first One monitoring parameter; And for each monitoring parameter The corresponding set of data retrieval attributes is defined as follows: ; in, The data type of the monitored parameters; To monitor the frequency of parameter acquisition, For the unit of measurement of monitoring parameters, For the accuracy standards of monitoring parameters, To monitor the sensitivity of parameters to different formation conditions, To monitor the sensitivity of parameters to tool wear condition and abnormal risk; S1.2 Establish a state influence function between monitoring parameters and tunneling conditions to characterize the weight of each monitoring parameter and its potential decision support value under different conditions. Its expression is: ; in, Indicates the tunneling working condition; Indicates monitoring parameters Pre-excavation working condition The importance weight of monitoring is as follows; Indicates monitoring parameters Pre-excavation working condition The potential decision support value that can be generated can be quantified. S1.3, Under tunneling conditions Based on the potential decision support value of each monitoring parameter, the monitoring parameter value vector is constructed as follows: ; in, Indicates monitoring parameters Under the current tunneling conditions The corresponding quantification results of potential decision support value; S1.4, Based on the monitoring parameter set vector Data acquisition attribute set corresponding to each monitoring parameter State Influence Function and monitoring parameter value vector A standardized monitoring index system for TBM tunneling is constructed, the expression of which is: ; in, Represents a vector of monitoring parameter sets. Various monitoring parameters attribute set The resulting family of attribute sets; Represents a vector of monitoring parameter sets. State influence function corresponding to each monitoring parameter A set of functions; This represents the set of quantified results of the potential decision support value corresponding to each monitoring parameter under the current tunneling conditions.

[0022] S2. Establish a monitoring cost model. For each monitoring parameter in the monitoring indicator system, calculate the monitoring costs generated during sensor deployment, operation, maintenance and data processing, and establish a parameterized monitoring cost model corresponding to each monitoring parameter. Preferably, in this embodiment, S2 includes: for each monitoring parameter, obtaining the sensor purchase cost, on-site installation and deployment cost, operating power supply cost, data transmission cost, data processing and storage cost, and equipment maintenance cost corresponding to that monitoring parameter; and summarizing the above cost information to form a set of cost parameters used to characterize the monitoring cost of each monitoring parameter.

[0023] In this specific embodiment, step S2 is as follows: S2.1, based on the set of monitoring parameters Based on this, for each monitoring parameter Establish a full-cycle, full-chain cost model for monitoring, targeting each monitoring parameter. Its monitoring cost function is defined as follows: ; in, This indicates the cost of purchasing the sensor; This indicates the cost of installation and deployment; Indicates the cost of power supply; This indicates the cost of data transmission and bandwidth usage; This represents the cost of data processing, storage, and computing resources. This represents the cumulative maintenance and replacement costs over time t. S2.2 Construct a monitoring cost vector from the monitoring costs of all monitoring parameters. This vector is defined as follows: ; To facilitate cost-value comparison among different monitoring parameters, the monitoring cost vector is normalized to obtain a standardized cost representation: ; in, This indicates that the monitoring cost vector is linearly normalized so that each cost component is mapped to the interval [0,1].

[0024] S3. Determine the monitoring benefit parameters. Based on historical tunneling data or simulation data samples, evaluate the benefit contribution of each monitoring parameter to tunneling efficiency improvement, construction risk identification and equipment status judgment under different tunneling conditions, and obtain the corresponding monitoring benefit parameters. Preferably, in this embodiment, S3 includes: under different tunneling conditions, for each monitoring parameter in the data monitoring index system, obtaining a monitoring benefit parameter to characterize the degree of influence of the monitoring parameter on the tunneling construction process; Among them, the monitoring benefit parameters include at least the efficiency benefit parameters used to characterize the changes in tunneling efficiency, the safety benefit parameters used to characterize the early warning capability of surrounding rock risk and jamming risk, and the equipment benefit parameters used to characterize the accuracy of judging the wear state of the cutters or the operating status of the equipment. Based on the monitoring benefit parameters, the monitoring benefit parameters corresponding to each monitoring parameter under the current tunneling conditions are determined, and the monitoring benefit parameters serve as the basis for generating and adjusting the monitoring scheme configuration.

[0025] In this specific embodiment, step S3 is as follows: S3.1, based on the set of monitoring parameters Based on this, for each monitoring parameter Define the monitoring benefit parameter, with the following expression: ; in, For monitoring parameters Under operating conditions The benefit contribution value below; For monitoring parameters Contribution to improving tunneling efficiency; For monitoring parameters Contribution to the accuracy of early warnings regarding surrounding rock risk and machine jamming risk; For monitoring parameters Contribution to the improvement of tool wear prediction capability; The weighting coefficients for the contributions of the three types of benefits can be adjusted according to the actual needs of the project, and must meet the following requirements: ; S3.2. Summarize the monitoring benefit parameters corresponding to each monitoring parameter under the current tunneling conditions to form a monitoring benefit parameter set that characterizes the overall benefit characteristics of the monitoring parameter set. The expression is: ; in, Indicates the operating condition The following is a set of benefit parameters corresponding to each monitoring parameter; S3.3 Map the benefit parameters to the monitoring parameter value indicators defined in step S1, with the following expression: ; in, Indicates monitoring parameters Under operating conditions The corresponding quantitative results of monitoring benefits are as follows.

[0026] S4. Generate monitoring scheme configuration. Based on the monitoring cost model and monitoring benefit parameters, and under the premise of meeting the preset cost constraints, combine and select the monitoring parameters to generate the corresponding monitoring scheme configuration. The monitoring scheme configuration shall at least include sensor type, quantity, deployment location and data acquisition frequency. Preferably, in this embodiment, S4 includes: a set of cost parameters for monitoring parameters obtained in S2 and monitoring benefit parameters obtained in S3, and a comprehensive comparative analysis of the candidate monitoring parameters; based on the comprehensive evaluation results, combined with actual constraints such as budget conditions, available installation space, number of sensors, communication resources and system power consumption at the engineering site, the monitoring parameters are screened and combined to determine the monitoring scheme configuration that meets the engineering implementation conditions.

[0027] In this specific embodiment, step S4 is as follows: S4.1 Standardizing the monitoring cost vector With monitoring benefit parameter set Based on the input, a comprehensive evaluation index for the cost-benefit analysis of data monitoring is constructed, and a comprehensive evaluation function is defined as follows: ; in, This is a comprehensive evaluation value based on the combination of monitoring parameters; For monitoring parameters The selection of variables, when a parameter is selected. When not selected ; This is a cost trade-off coefficient used to adjust for cost sensitivity. S4.2. The feasible region of the monitoring parameters is obtained under constraints such as budget cost, number of sensors, installation space, bandwidth usage, and power consumption. Within the feasible region, the comprehensive evaluation function is used to evaluate the parameters. The optimal combination of monitoring parameters is obtained by maximizing the solution using multi-objective genetic algorithms and other optimization algorithms. The corresponding monitoring scheme configuration is then output, including sensor type, quantity, deployment location, and acquisition frequency, providing basic input conditions for subsequent adaptive adjustment.

[0028] S5. Adaptive adjustment of monitoring scheme: Real-time acquisition of tunneling conditions during TBM tunneling. When the conditions change, the monitoring parameter combination is regenerated based on the updated monitoring costs and benefits to obtain a monitoring scheme configuration that matches the current tunneling conditions. Preferably, in this embodiment, S5 includes: during the TBM tunneling construction, acquiring the tunneling condition status in real time, determining the current tunneling condition status, and triggering a monitoring scheme adjustment process when the degree of change in the tunneling condition status relative to the previous stage exceeds a preset condition sensitivity threshold; after triggering the monitoring scheme adjustment process, based on the monitoring scheme configuration formed in step S4, and combined with the updated tunneling condition status, re-screening and combining the monitoring parameters to generate a monitoring scheme configuration that matches the current tunneling condition status.

[0029] In this specific embodiment, step S5 is as follows: S5.1 During TBM tunneling, the system continuously collects operational parameters reflecting the tunneling status and dynamically updates and determines the current tunneling condition. Operational parameters include at least tunneling attitude parameters, geological type changes, cutter wear, and changes in surrounding rock stress. The change in working condition is calculated based on the differences between previous and subsequent working conditions. Dynamic determination is performed. When the operating condition changes... Exceeding the preset operating condition sensitivity threshold When this occurs, the monitoring parameter combination recalculation process is triggered.

[0030] When the construction status reflected by the above parameters changes, the system generates a change index to characterize the degree of change based on the differences between the previous and subsequent working conditions, and compares this change index with a pre-set working condition sensitivity threshold. When the degree of change in working conditions exceeds the working condition sensitivity threshold, it is determined that the current monitoring scheme is no longer applicable to the existing construction conditions, thereby triggering the adjustment process of the monitoring scheme.

[0031] The triggering condition can be expressed as: ; in, A quantitative indicator of the change in the current operating condition; Sensitive threshold for operating conditions that trigger a reassessment; This indicates that a re-evaluation is triggered. This indicates that the original monitoring plan will be maintained.

[0032] S5.2 After triggering a re-solution, the monitoring cost-benefit comprehensive evaluation index constructed in step S4 is re-initiated. Selecting variables for monitoring parameters The monitoring parameters are updated so that the new set of selected parameters meets the cost-effectiveness conditions under the current geological and tunneling conditions, thereby obtaining a new combination of monitoring parameters and realizing the real-time dynamic adaptability of the monitoring scheme in complex and variable construction environments. Through the above methods, the monitoring scheme can be dynamically adjusted in the complex and ever-changing TBM tunneling construction environment, so that the allocation of monitoring resources always meets the requirements of construction safety, effectiveness and project implementation conditions.

[0033] S6. Full-cycle implementation and feedback: The monitoring scheme is configured and applied to the entire TBM tunneling construction process. The monitoring scheme is continuously updated based on the feedback of monitoring data to achieve dynamic adjustment of the monitoring scheme.

[0034] Preferably, in this embodiment, in S6, the monitoring scheme corresponding to the monitoring parameter combination configuration adjusted in S5 is compared and analyzed with the currently adopted monitoring scheme. When the comprehensive benefits of the new scheme based on the monitoring benefit parameters are better than the current scheme, it is replaced with the new monitoring parameter combination.

[0035] Specifically, in this embodiment, in S6, the latest combination of monitoring parameters, after adaptive adjustment, is configured and deployed throughout the entire TBM tunneling construction cycle. This achieves dynamic closed-loop implementation of the monitoring scheme through real-time data acquisition, real-time feedback, and periodic evaluation. For the monitoring scheme in the execution state, time... The comprehensive benefits at any given moment are defined by the following formula: ; in, This represents the overall benefit value under the current execution strategy. For at any time Monitoring parameters The selected state variable is 1 when selected and 0 when not selected.

[0036] During the tunneling process, as new strata enter, the cutting tool status changes, the propulsion parameters change, and the construction environment fluctuates, new working conditions are continuously acquired in real time. Subsequently, the performance evaluation was updated: ; Will Compared with the previous period's evaluation value In comparison, when the current monitoring scheme is evaluated based on the updated tunneling conditions, if the evaluation results show that the newly generated combination of monitoring parameters is better than the current monitoring scheme in at least one of the following indicators: tunneling efficiency improvement capability, construction risk identification capability, or equipment status monitoring effectiveness, and this advantage remains stable over multiple consecutive evaluation periods, then the new monitoring scheme is determined to have higher overall benefits. After determining that the new monitoring scheme has higher overall benefits, the system replaces the currently executed monitoring parameter combination strategy with the new monitoring parameter combination, and simultaneously updates the corresponding sensor deployment parameters, acquisition frequency and data processing configuration, so that the updated monitoring scheme takes effect in the next execution cycle.

[0037] Through the above-mentioned full-cycle implementation mechanism, the decision-making of monitoring parameter combination is no longer a fixed scheme, but a strategy process that evolves continuously and dynamically throughout the entire TBM tunneling cycle. This ensures that monitoring resources are always kept in the optimal balance between cost and benefit in different geological sections, different tool lifespans, and different tunneling stages, thereby achieving full-cycle TBM tunneling decision optimization driven by data monitoring cost-benefit assessment.

[0038] Application examples This application example selects a long tunnel section in a high-altitude mountainous area of ​​the Sichuan-Tibet Railway, from K35+200 to K38+050, with a total length of approximately 2.85 km and a burial depth of 180-420 m. The terrain is characterized by high ground stress and fractured structure, with lithology mainly consisting of interbedded medium- to fine-grained granodiorite and gneiss, interspersed with three Class III fault fracture zones and one section of highly sensitive rockburst zone. The groundwater is fissure water, with a local risk of high-pressure surges. The TBM adopts a hard rock open-face design, with a cutterhead diameter of 9.86 m, a main drive power of 4 × 630 kW, and a rated torque of 12.5 MN·m. Traditional static monitoring configurations result in both data redundancy and missing key information, and the rockburst risk significantly impacts propulsion safety and cutter life. Therefore, the method of this invention needs to be used for optimized design. The following explanation follows steps S1 to S6.

[0039] Step S1: Construct a monitoring indicator system: In this application example, a vector set of monitoring parameters is formed. (Initial selection in this example) (Item). For each parameter Define a set of attributes ,in For data types, For sampling frequency, For units of measurement For accuracy standards, To assess the sensitivity to different geological conditions, This parameter is sensitive to changes in tool wear, jamming, and abnormal risk.

[0040] To reflect the specificity of rockburst-sensitive scenarios, examples of the attributes of four key parameters are given in the table below: Establish and operate in accordance with the status The state influence function, in, Indicates the tunneling working condition; Indicates monitoring parameters Pre-excavation working condition The importance weight of monitoring is as follows; Indicates monitoring parameters Pre-excavation working condition The potential decision support value that can be generated is quantified. A value vector for the monitoring parameters is defined, with the following formula: ; in, Indicates monitoring parameters Under the current tunneling conditions The corresponding potential decision support value quantification results are calculated in step S3 and backfilled to... In this application example It was obtained by training with samples from similar historical work areas and data from a 200m warm-up tunneling. Figure 2 This is a schematic diagram of the multi-source heterogeneous data index system architecture for TBM tunneling monitoring according to the present invention.

[0041] Step S2: Establish a monitoring cost model: With monitoring parameter set Based on this, for each parameter Construct a full-chain monitoring cost model, whose monitoring cost function is: ,in This indicates the cost of purchasing the sensor; This indicates the cost of installation and deployment; Indicates the cost of power supply; This indicates the cost of data transmission and bandwidth usage; This represents the cost of data processing, storage, and computing resources. Indicates time Accumulated maintenance and replacement costs.

[0042] This example provides annualized cost breakdowns for four key parameters: cutter head torque: , , , , , → RMB / year. Head triaxial vibration (2 sets): → RMB / year. Tool wear depth (3 points): → RMB / year. Construction waste image texture: → RMB / year. Min-max normalization is used. ,in , Range = 18600: Calculation ; ; ; .

[0043] Step S3: Determine monitoring benefit parameters: For each parameter Establish monitoring benefit parameters, the formula is as follows: For monitoring parameters Under operating conditions The benefit contribution value below; For monitoring parameters Contribution to improving tunneling efficiency; For monitoring parameters Contribution to the accuracy of early warning of surrounding rock risk and jamming risk; For monitoring parameters Contribution to the improvement of tool wear prediction capability; The weighting coefficients for the contributions of the three types of benefits, and satisfying the following conditions. This example takes... Based on the fitting results, four examples are shown in the table below: The monitoring benefit parameters corresponding to each monitoring parameter under the current tunneling conditions are summarized to form a monitoring benefit parameter set that characterizes the overall benefit characteristics of the monitoring parameter set. The expression is as follows: The benefit parameters are then mapped to the monitoring parameter value indicators defined in step S1, with the expression being: Backfill to S1 .

[0044] Step S4: Generate monitoring scheme configuration by and Using the input, construct a comprehensive evaluation function, the formula of which is: ,in, This is a comprehensive evaluation value based on the combination of monitoring parameters; For monitoring parameters The selection of variables, when a parameter is selected. When not selected ; This is a cost trade-off coefficient used to adjust for cost sensitivity. =0.43. Constraints set for this work area: Annual budget. RMB; communication bandwidth Mbps; power consumption kW; monitoring points that can be installed Net contribution is calculated using four examples. Calculate torque ;vibration Wear and tear ;image The method combines 0-1 integer programming and heuristic annealing to solve for maximizing... Under the premise of satisfying the above constraints, the optimal 10 items are obtained, and the type, quantity, deployment location and acquisition frequency configuration table are automatically output. Such as torque (10Hz, 2 points), triaxial vibration (200Hz, 2 points), propulsion cylinder pressure (5Hz, 4 points), tool wear depth (1Hz, 3 points), slag image texture (1Hz, 1 point), propulsion speed (5Hz, 1 point), spindle temperature (1Hz, 1 point).

[0045] Figure 3 This is a schematic diagram of the optimized combination of monitoring parameters for TBM tunneling according to the present invention. It shows that under the conditions of rockburst-sensitive hard rock TBM tunneling on the Sichuan-Tibet Railway, the present invention reduces the original 28 monitoring parameters to 10 optimal monitoring parameter combinations through a cost-benefit comprehensive evaluation model, which significantly improves monitoring efficiency and reduces monitoring redundancy.

[0046] Step S5: Adaptively adjust the monitoring scheme: In the rockburst-prone section, a threshold-triggered recalculation mechanism based on "change in operating conditions" is adopted: when Exceeding the preset sensitivity threshold Re-evaluation is triggered at certain times, and the formula is as follows: This example uses history. Distribution 95th quantile and warm-up phase calibration, take During a tunneling operation, when the tunnel entered a Class III fracture zone, the attitude pitch suddenly increased. The standard deviation of torque fluctuation increased by 36%, and the vibration RMS increased by 28%. The calculated comprehensive ΔS = 0.27 ≥ 0.24, trigger = 1, and the system re-calls S4. Seeking a solution, please update. It will automatically generate new monitoring parameter combinations and replace the current scheme.

[0047] Step S6, Full-cycle Implementation and Feedback: Throughout the entire construction cycle, a closed-loop operation of execution-feedback-evaluation-replacement is implemented to continuously monitor the current strategy. Comprehensive benefits ,in This represents the overall benefit value under the current execution strategy. For at any time Monitoring parameters The selected state variable is 1 when selected and 0 when not selected. Comparison between two consecutive evaluation periods (every 48 hours): [The text abruptly ends here, likely due to an incomplete sentence or missing information.] Cycle (before replacement) After triggering, the new strategy is recalculated. cycle ,promote If the threshold is >0.08, the system will automatically switch to a new monitoring scheme and enter the next cycle. Figure 4 This is a time-series diagram illustrating the TBM full-cycle dynamic scheme adjustment and benefit evaluation of the present invention. It shows that during the tunneling process, when the change in working condition ΔS reaches a preset threshold θ, re-optimization is triggered, thereby improving the comprehensive benefit evaluation index. Continuously improve and form a closed loop of dynamic adaptive optimization throughout the entire life cycle.

[0048] Compared with the original static monitoring configuration, statistics during the first 600m implementation period show that: the total annualized monitoring cost decreased by about 42%, the average propulsion efficiency increased by 10.9%, the average early warning of rockburst / abnormal working conditions was 4.1 days in advance, and the average daily data volume decreased from ~520GB / day to ~290GB / day (bandwidth and computing power were significantly controlled).

[0049] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Substitutions may include replacements of some structures, devices, or method steps, or may be complete technical solutions. Equivalent substitutions or modifications made to the technical solutions and inventive concepts of the present invention should all be covered within the scope of protection of the present invention.

Claims

1. A method for optimizing the design of a data monitoring scheme for TBM tunneling projects, characterized in that, Includes the following steps: S1. Construct a monitoring index system, collect multi-source monitoring data generated during TBM tunneling, classify monitoring parameters according to sensor type, data type and physical dimension, and set corresponding acquisition frequency, acquisition accuracy and mapping relationship with tunneling working conditions for each monitoring parameter to form a standardized TBM tunneling monitoring index system. S2. Establish a monitoring cost model. For each monitoring parameter in the monitoring indicator system, calculate the monitoring costs generated during sensor deployment, operation, maintenance and data processing, and establish a parameterized monitoring cost model corresponding to each monitoring parameter. S3. Determine the monitoring benefit parameters. Based on historical tunneling data or simulation data samples, evaluate the benefit contribution of each monitoring parameter to tunneling efficiency improvement, construction risk identification and equipment status judgment under different tunneling conditions, and obtain the corresponding monitoring benefit parameters. S4. Generate monitoring scheme configuration. Based on the monitoring cost model and monitoring benefit parameters, and under the premise of meeting the preset cost constraints, combine and select the monitoring parameters to generate the corresponding optimal monitoring scheme configuration. The monitoring scheme configuration shall at least include sensor type, quantity, deployment location, data acquisition frequency and accuracy. S5. Adaptive adjustment of monitoring scheme: Real-time acquisition of tunneling conditions during TBM tunneling. When the conditions change, the monitoring parameter combination is regenerated based on the updated monitoring costs and benefits to obtain a monitoring scheme configuration that matches the current tunneling conditions. S6. Full-cycle implementation and feedback: The monitoring scheme is configured and applied to the entire process of TBM tunneling construction. The monitoring scheme is continuously updated based on the feedback of monitoring data to achieve dynamic adjustment of the monitoring scheme.

2. The method for optimizing the data monitoring scheme for TBM tunneling projects as described in claim 1, characterized in that, The monitoring parameters in S1 include at least geological parameters, tunneling attitude parameters, propulsion and torque parameters, tool wear parameters, vibration parameters, and environmental parameters.

3. The method for optimizing the data monitoring scheme for TBM tunneling projects as described in claim 1, characterized in that, S1 includes: abstracting the collected multi-source monitoring data into multiple monitoring parameters; Set the data type, acquisition frequency, unit of measurement, measurement accuracy, and sensitivity indicators to changes in strata and equipment status for each monitoring parameter; Based on the tunneling conditions, a correlation is established between monitoring parameters and their monitoring importance and decision support value, thereby forming a data monitoring index system for TBM tunneling.

4. The method for optimizing the data monitoring scheme for TBM tunneling projects as described in claim 1, characterized in that, S2 includes: for each monitoring parameter, obtaining the corresponding sensor purchase cost, on-site installation and deployment cost, operating power supply cost, data transmission cost, data processing and storage cost, and equipment maintenance cost; and summarizing the above cost information to form a cost parameter set used to characterize the monitoring cost of each monitoring parameter.

5. The method for optimizing the data monitoring scheme for TBM tunneling projects as described in claim 1, characterized in that, The S3 includes: under different tunneling conditions, for each monitoring parameter in the data monitoring indicator system, obtaining monitoring benefit parameters to characterize the degree of influence of the monitoring parameter on the tunneling construction process; The monitoring benefit parameters include at least the efficiency benefit parameters used to characterize changes in tunneling efficiency, the safety benefit parameters used to characterize the early warning capability of surrounding rock risk and machine jamming risk, and the equipment benefit parameters used to characterize the accuracy of judging the wear state of the cutting tools and the operating status of the equipment. Based on the monitoring benefit parameters, the monitoring benefit parameters corresponding to each monitoring parameter under the current tunneling conditions are determined, and the monitoring benefit parameters serve as the basis for generating and adjusting the monitoring scheme configuration.

6. The method for optimizing the data monitoring scheme for TBM tunneling projects as described in claim 1, characterized in that, S4 includes: determining the feasible domain of the monitoring scheme by comprehensively evaluating the actual constraints such as the budget conditions, available installation space, number of sensors, communication resources, and system power consumption at the engineering site; and conducting a comprehensive comparative analysis of the candidate monitoring parameters within the feasible domain based on the cost parameter set of monitoring parameters obtained in S2 and the monitoring benefit parameters obtained in S3, to determine the optimal monitoring scheme configuration that meets the engineering implementation conditions.

7. The method for optimizing the data monitoring scheme for TBM tunneling projects as described in claim 1, characterized in that, S5 includes: during the TBM tunneling construction process, acquiring the tunneling condition status in real time, determining the current tunneling condition status, and triggering the monitoring scheme adjustment process when the degree of change of the tunneling condition status relative to the previous stage exceeds a preset condition sensitivity threshold; after triggering the monitoring scheme adjustment process, based on the monitoring scheme configuration formed in step S4, and combined with the updated tunneling condition status, re-screening and combining the monitoring parameters to generate a monitoring scheme configuration that matches the current tunneling condition status.

8. The method for optimizing the data monitoring scheme for TBM tunneling projects as described in claim 1, characterized in that, In step S6, the monitoring scheme corresponding to the monitoring parameter combination configuration adjusted in step S5 is configured and compared with the currently adopted monitoring scheme. When the comprehensive benefits of the new scheme based on the monitoring benefit parameters are better than the current scheme, the new monitoring parameter combination is replaced.

Images