A digital twin-based intelligent decision-making method and system for dual-mode conversion

By constructing a data processing model using sensors and a CNN convolutional neural network, the dual-mode tunnel boring machine was able to achieve real-time perception and intelligent decision-making under complex geological conditions. This solved the problems of lag and one-sidedness in mode switching decision-making in existing technologies, and improved construction efficiency and safety.

CN123116852APending Publication Date: 2026-11-17KUNMING RAILWAY CONSTR COMPANY OF CHINA RAILWAY NO 8 ENG GRP +4
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611444229.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-17
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

When existing dual-mode tunnel boring machines make mode switching decisions under complex geological conditions, they lack real-time data fusion and intelligent model support, resulting in perception lag and one-sidedness, low construction efficiency, high costs, and a lack of precise guidance for parameter adjustment.

Method used

By using sensors to collect tunneling parameters in real time and combining them with a CNN convolutional neural network to build a data processing model, we can accurately judge the stratigraphic boundary and provide early warning of mode conversion. We can make intelligent decisions by integrating geological, economic benefits and stratigraphic modeling analysis.

Benefits of technology

It enables real-time perception and dynamic assessment of dual-mode tunnel boring machines under complex geological conditions, significantly improving construction efficiency and safety, reducing construction risks, optimizing mode switching strategies, and enhancing the level of intelligent construction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123116852A_ABST
    Figure CN123116852A_ABST
Patent Text Reader

Abstract

This application discloses a dual-mode conversion intelligent decision-making method and system based on digital twins. The method includes: real-time acquisition of tunneling parameter data, including thrust F, torque S, rotational speed W, and tunneling speed V; S2: monitoring and obtaining formation seepage P and joint dip angle; initial data composed of joint dip angle values ​​and monitoring data; preprocessing the initial data to obtain target data; determining the formation boundary; constructing a data processing model to finally obtain output data N; and processing the output data according to different tunneling distances. N Generate a data set with output data N as the ordinate and tunneling distance as the coordinate. D The graph of the function is given by the x-axis, and the slope of the corresponding function is calculated in real time based on the graph. K 1. Refer to the slope K 1. The changes in output data N are used to determine the stratigraphic shape and model for early warning; after the early warning is issued, the final model conversion is carried out with reference to the early warning signal, economic benefit analysis and stratigraphic modeling analysis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application belongs to the field of intelligent construction technology for tunnel engineering, and in particular relates to an intelligent decision-making method and system for dual-mode conversion based on digital twins. Background Technology

[0002] With the rapid development of urban underground space development, transportation network extension, and water conservancy and hydropower engineering construction, tunnel engineering faces the challenge of traversing increasingly complex geological conditions (such as heterogeneous strata, composite strata, and fault fracture zones). To address this complexity, dual-mode tunnel boring machines (TBMs) combining the functions of earth pressure balance TBMs and hard rock tunnel boring machines have emerged. These TBMs can dynamically switch between earth pressure balance mode and hard rock tunneling mode, greatly improving adaptability and construction efficiency in variable strata, and have become key equipment for major projects such as long tunnels and inter-basin water transfer projects.

[0003] The core technological bottlenecks currently faced by dual-mode tunnel boring machines (TBMs) in making mode-switching decisions under complex geological conditions include: Existing technologies primarily rely on offline analysis of preliminary geological survey data and subjective judgment by construction personnel. This results in the failure to effectively integrate and process heterogeneous data from multiple sources, such as geology, equipment status, and the environment, leading to significant lag and bias in the perception of the geological conditions ahead and the adaptability of the current mode. The decision-making process lacks objective, quantitative, and intelligent model support, causing mode switching to be largely a reactive, post-event response rather than proactive early warning and control based on real-time data. Furthermore, the lack of precise guidance for adjusting construction parameters after the switch affects tunneling efficiency and system stability. The system also struggles to continuously iterate and optimize the decision logic and parameters based on actual construction results, ultimately limiting the improvement of intelligent construction levels in tunnel engineering.

[0004] Existing technologies fail to effectively integrate heterogeneous data from multiple sources, including geological information, equipment status information, and environmental information, resulting in significant lag and bias in the perception of the geological conditions ahead and the adaptability of the current model. Core decision-making processes rely excessively on human experience, lacking objective, quantitative, and intelligent decision-making basis and model support. Model switching is largely a reactive response, failing to achieve risk warning and proactive, forward-looking switching. Parameter adjustments after model switching lack precise guidance, impacting construction efficiency and stability. Continuous optimization of decision-making logic and parameters based on actual switching effects and construction data is difficult.

[0005] As a core technology, the current mode conversion decision-making for dual-mode tunnel boring machines (TBMs) mainly relies on the pre-analysis of geological survey data and the experience judgment of construction personnel. However, this approach results in low construction efficiency and high construction costs for current dual-mode TBMs. Therefore, there is an urgent need to develop an innovative intelligent decision-making method and system that utilizes digital twin technology to achieve real-time perception, dynamic evaluation, intelligent decision-making, precise execution, and closed-loop optimization of the EPB / TBM dual-mode conversion process, thereby significantly improving the safety, efficiency, and intelligence level of dual-mode TBM construction. Summary of the Invention

[0006] The purpose of this application is to overcome the problems of existing technologies by disclosing a dual-mode conversion intelligent decision-making method and system based on digital twins, which aims to solve the core technical bottleneck faced by current dual-mode tunnel boring machines when making mode conversion decisions under complex geological conditions.

[0007] The objective of this application is achieved through the following technical solution: A dual-mode conversion intelligent decision-making method based on digital twins, the dual-mode conversion intelligent decision-making method comprising: S1: Sensors are installed at the front end of the tunnel boring machine to collect tunneling parameter data in real time, including thrust F, torque S, rotational speed W, and tunneling speed V; S2: Install a flow meter on the drainage system at the rear of the tunnel boring machine to monitor the ground seepage P. Install a front-facing camera at the front of the tunnel boring machine to detect the ground ahead and transmit images back in real time to determine the joint dip angle. S3: The data transmission unit (DTU) receives and stores the monitoring data from various sensors and flow meters in real time. S4: The initial data consists of joint dip angle values ​​and monitoring data. Based on the preset data requirements of the database, the initial data is preprocessed to obtain the target data. S5: Based on thrust F tunneling speed V cross-sectional area of ​​the cutter head A tunneling distance D To determine the stratigraphic boundaries; S6: Construct a data processing model, which is based on a CNN convolutional neural network and includes an input layer, an output layer, and a hidden layer; The monitored tunneling speed, thrust, torque, rotational speed, and water seepage volume are input into the data processing model. The tunneling speed is not included in the calculation of the output layer but is directly entered into the hidden layer. The final output data is N. S7: Output data based on different tunneling distances N Generate a data set with output data N as the ordinate and tunneling distance as the coordinate. DThe graph of the function is given by the x-axis, and the slope of the corresponding function is calculated in real time based on the graph. K 1. Refer to the slope K 1. Use changes in output data N to predict and establish early warnings of formation shape and pattern; S8: After issuing an early warning, the final model conversion is carried out by referring to the early warning signal, economic benefit analysis and stratigraphic modeling analysis.

[0008] According to a preferred embodiment, in step S4, data preprocessing includes removing outlier data from the initial data.

[0009] According to a preferred embodiment, step S5 includes: Calculate the depth to which the tunnel has been excavated. D Calculate the specific energy of the formation at point 1. SE 1. Specific energy SE 1. Obtained based on the following formula:

[0010] in, F Indicates total thrust. V Indicates the tunneling speed; A represents the cutterhead cross-sectional area. Obtain specific energy SE After 1, the specific energy standard was calculated. K :

[0011] When the excavation reaches the depth of the explored stratigraphic boundary D At time 2, calculate the specific energy of the strata at that location. SE 2, obtained SE 1 and SE 2. Then calculate the rate of change of specific energy. SE ':

[0012] By comparing the relationship between the specific energy change rate SE' and the specific energy standard K, the stratigraphic boundary can be determined: At that time, the boundary situation was stratum one; At that time, the boundary was stratum two; At that time, the boundary was stratum three.

[0013] According to a preferred embodiment, in step S6, the monitored tunneling speed, thrust, torque, rotational speed, and water seepage volume are divided into n groups of input data. The input layer of the data processing model is then used for data computation, including: The first set of data consists of thrust, torque, rotational speed, and water seepage data collected by sensors and flow meters when the tunnel boring machine has advanced to one meter. The second set of data consists of thrust, torque, rotational speed, and water seepage data collected by sensors and flow meters when the tunnel boring machine has advanced to two meters, and so on up to the nth set of data. First-order data t1, t2, ... t are obtained through calculation by the input layer. n The calculation formula is:

[0014]

[0015]

[0016] Where b1, b2, b3, and b4 are weighting coefficients. F 1, S 1, W 1, P 1 represents the thrust, torque, rotational speed, and water seepage corresponding to the first set of data. F 2, S 2, W 2, P 2 represents the thrust, torque, rotational speed, and water seepage corresponding to the second set of data. F n , S n , W n , P n These are the thrust, torque, rotational speed, and water seepage corresponding to the nth set of data; The first-order data obtained from the input layer are input to the hidden layer and processed with the tunneling speed to obtain the actual speeds w1, w2, ... w n Each by f 1 (x), f 2 (x) ... f n (x) express:

[0017]

[0018]

[0019] in, V 1 represents the tunneling speed data collected by the sensor when the tunnel has been excavated to one meter. V 2 represents the tunneling speed data collected by the sensor when the tunnel has reached two meters. V n It is the tunneling speed data collected by the sensor when the tunnel has reached the nth meter, which is determined by the decision data w1, w2, ... wn Together they form the output data N .

[0020] According to a preferred embodiment, step S7 includes: When the rock strata are classified as stratum one, the first method of judgment applies, meaning that when the excavation distance reaches the depth of the exploration strata boundary. D 2. Before that, output the slope of the data function. K 1=0, output data N Remains unchanged; reaches the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K 1=1, at this point, it indicates that the soft and hard rock strata corresponding to stratum one have been reached, and a model conversion warning is issued; When the rock strata are classified as stratum two, the second method of judgment applies, i.e., when the excavation distance reaches the depth of the exploration stratum boundary. D 2. Before that, the output data N has a constant slope. K 1 gradually increases, and 0 ≤ K 1≤0.1, reaching the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K If 1 > 1, it indicates that the soft and hard rock strata corresponding to stratum two have been reached, and a model conversion warning is issued. When the rock strata are classified as strata three, the judgment method is three, that is, when the excavation distance reaches the depth of the exploration strata boundary. D 2. Before that, the output data N has a constant slope. K 1 gradually decreases, and -0.1 ≤ K 1≤0, reaching the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K 1 satisfies 0 < K If 1 < 1, it indicates that the soft and hard rock strata corresponding to stratum three have been reached, and a model conversion warning is issued.

[0021] According to a preferred embodiment, step S8 includes: S81: During the tunneling process, displacement sensors are used to monitor and obtain tunneling distance data. The tooling cost is determined by a weighted average of the costs of each tool, and the number of tool replacements is recorded. T ; S82: During the tunneling process, the economic benefits are calculated according to the following formula:

[0022]

[0023] in, C总 This refers to the total cost of cutting tools from start to finish in hard or soft rock formations. B This refers to the unit price of each tool. i This refers to the number of times the cutting tool is changed. i = T +1, C 每米 This refers to the cost of the cutting tools per meter of tunneling. G 1 refers to the number of days C consumed in completing the excavation of the first stratum; S83: Distance from tunneling to the stratigraphic boundary D At 2 o'clock, the camera detects and senses the geological data ahead in real time. After obtaining the geological data, it combines it with historical data to estimate the energy consumed during tunneling in the corresponding geological strata. C’ 总 ; S84: Calculate conversion cost C 转换 The following equation is satisfied:

[0024] in, C 每天 The cost of daily losses during the first layer of excavation. C 'The daily cost incurred during the excavation of the second stratum.' G 转 This refers to the number of days the project was delayed during the mode conversion. S85: Make a decision, if C 总 ≥ C ' 总 + C 转换 From an economic perspective, model conversion is a better option. The decision on whether to convert the model should be made based on stratigraphic modeling analysis. C 总 < C’ 总 + C 转换 If not, then no mode conversion will be performed.

[0025] According to a preferred embodiment, step S8 further includes: S86: Stratigraphic modeling and analysis. After the conditions for mode conversion are met economically, based on relevant data of the current strata collected by sensors and flow meters, and forward strata data detected by cameras, and based on a preset strata model, a judgment is made. If the stratigraphic data obtained from monitoring differs from the data in the preset stratigraphic model by no more than 10%, then a model conversion will be performed; if the difference exceeds 10%, then no model conversion will be performed. If the tunnel advances one meter and then the relevant geological data is monitored, and the average difference between the current data and the data from the previous meter exceeds 20%, then a mode switch is performed; if it does not exceed 20%, then the tunnel is advanced until the average difference between the relevant geological data and the data from the previous meter exceeds 20%, then a mode switch is performed.

[0026] According to a preferred embodiment, the dual-mode conversion intelligent decision-making method further includes: S9: After the mode conversion is completed, it automatically corrects its own shortcomings based on the situation during and after the conversion.

[0027] This application also discloses: A dual-mode conversion intelligent decision-making system based on digital twins, the dual-mode conversion intelligent decision-making system comprising: at least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the instructions stored in the memory to perform the aforementioned method.

[0028] The aforementioned main solution and its various further alternative solutions can be freely combined to form multiple solutions, all of which are solutions that can be adopted and are claimed in this application. Those skilled in the art, after understanding the solution of this application, will realize that there are many combinations based on the prior art and common general knowledge, all of which are technical solutions to be protected in this application, and will not be exhaustively listed here.

[0029] The beneficial effects of this application are: (1) Sensors are used to monitor the tunneling data of the shield machine, radar is used to detect the geological data of the strata, and the data is transmitted in real time through DTU. Based on the preset database, unreasonable data is automatically removed to ensure the real-time performance and accuracy of the data.

[0030] (2) A data processing model is constructed based on a CNN convolutional neural network to realize intelligent analysis and feature extraction of tunneling parameters. Combined with formation specific energy calculation and rate of change analysis, it enables accurate judgment of formation boundary conditions. Based on the slope change of the output data function and the adaptive switching judgment strategy of formation type according to the data processing model, risk warning and proactive forward-looking mode conversion suggestions are realized, which significantly reduces the dependence on human experience.

[0031] (3) By integrating geological data, economic benefits (tooling costs, conversion costs, and project time losses) with stratigraphic modeling analysis results, a multi-dimensional scientific determination of the timing of mode conversion can be achieved. Economic analysis can automatically quantify and evaluate the cost-benefit ratio before and after conversion, providing an objective basis for decision-making and improving the economic feasibility of engineering projects.

[0032] (4) Through real-time perception, intelligent early warning and precise execution, the uncertainty and risk in the construction process are significantly reduced, the tunneling parameters and mode conversion strategies are optimized, the adaptability of the dual-mode shield machine in complex strata and the overall construction efficiency are improved, and the safety and stability of the construction process are guaranteed. Attached Figure Description

[0033] Picture 1 This is a schematic diagram showing the boundaries of the various strata in this application; Picture 2 This is a schematic diagram of the data processing flow of the data processing model in the dual-mode conversion intelligent decision-making method of this application; Picture 3 This is a graph of the early warning function for each stratum in this application; Picture 4 This is a schematic diagram illustrating the transformation of the application mode; Picture 5 This is a flowchart illustrating the method of this application. Detailed Implementation

[0034] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0035] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0036] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this application is in use. They are only for the convenience of describing this application 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, and therefore should not be construed as a limitation on this application. In addition, the terms "first," "second," and "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0037] Furthermore, terms such as "horizontal," "vertical," and "sag" do not imply that components must be absolutely horizontal or suspended, but rather that they can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal relative to "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0038] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0039] Furthermore, it should be noted that unless otherwise specified in this application, the specific structures, connections, positions, power sources, etc. involved are all things that a person skilled in the art can know without creative effort based on the prior art.

[0040] Example 1 refer to Picture 1 to Picture 5 As shown, this application discloses a dual-mode conversion intelligent decision-making method based on digital twins, which includes the following steps.

[0041] Step S1: Install sensors at the front end of the tunnel boring machine to collect tunneling parameter data in real time, including thrust F, torque S, rotational speed W, and tunneling speed V.

[0042] Step S2: Install a flow meter on the drainage system at the rear of the tunnel boring machine to monitor the ground seepage P. Install a front-facing camera at the front of the tunnel boring machine to detect the ground ahead and transmit images back in real time to determine the joint dip angle.

[0043] Step S3: The data transmission unit (DTU) receives and stores the monitoring data from each sensor and flow meter in real time.

[0044] Step S4: Initial data is composed of joint dip angle values ​​and monitoring data. Based on preset data requirements in the database, the initial data is preprocessed to obtain target data. Data preprocessing includes removing abnormal data from the initial data.

[0045] Step S5: Based on thrust F tunneling speed V cross-sectional area of ​​the cutter head A tunneling distance DTo determine the stratigraphic boundaries.

[0046] Specifically, step S5 includes: calculating the depth to which the tunnel has been excavated. D Calculate the specific energy of the formation at point 1. SE 1. Specific energy SE 1. Obtained based on the following formula:

[0047] in, F Indicates total thrust. V The speed of tunneling is represented by A, and the cross-sectional area of ​​the cutterhead is represented by A.

[0048] Obtain specific energy SE After 1, the specific energy standard was calculated. K :

[0049] When the excavation reaches the depth of the explored stratigraphic boundary D At time 2, calculate the specific energy of the strata at that location. SE 2, obtained SE 1 and SE 2. Then calculate the rate of change of specific energy. SE ':

[0050] By comparing the relationship between the specific energy change rate SE' and the specific energy standard K, the stratigraphic boundary can be determined: At that time, the boundary situation was stratum one; At that time, the boundary was stratum two; At that time, the boundary situation was stratum three, such as Picture 1 As shown.

[0051] Step S6: Construct a data processing model based on a CNN convolutional neural network, comprising an input layer, an output layer, and hidden layers. Input the monitored tunneling speed, thrust, torque, rotational speed, and water seepage into the data processing model. The tunneling speed is not included in the output layer calculation but directly enters the hidden layer, ultimately obtaining output data N. The process is as follows: Picture 2 As shown.

[0052] Specifically, in step S6, the monitored tunneling speed, thrust, torque, rotational speed, and water seepage volume are divided into n groups of input data. The input layer of the data processing model then performs data calculations, including: The first set of data consists of thrust, torque, rotational speed, and water seepage data collected by sensors and flow meters when the tunnel boring machine has advanced one meter. The second set of data consists of thrust, torque, rotational speed, and water seepage data collected by sensors and flow meters when the tunnel boring machine has advanced two meters, and so on up to the nth set of data.

[0053] First-order data t1, t2, ... t are obtained through calculation by the input layer. n The calculation formula is:

[0054]

[0055]

[0056] Where b1, b2, b3, and b4 are weighting coefficients. F 1, S 1, W 1, P 1 represents the thrust, torque, rotational speed, and water seepage corresponding to the first set of data. F 2, S 2, W 2, P 2 represents the thrust, torque, rotational speed, and water seepage corresponding to the second set of data. F n , S n , W n , P n It represents the thrust, torque, rotational speed, and water seepage volume corresponding to the nth set of data.

[0057] The first-order data obtained from the input layer are input to the hidden layer and processed with the tunneling speed to obtain the actual speeds w1, w2, ... w n Each by f 1 (x), f 2 (x) ... f n (x) express:

[0058]

[0059]

[0060] in, V 1 represents the tunneling speed data collected by the sensor when the tunnel has been excavated to one meter. V 2 represents the tunneling speed data collected by the sensor when the tunnel has reached two meters. V n It is the tunneling speed data collected by the sensor when the tunnel has reached the nth meter, which is determined by the decision data w1, w2, ... w n Together they form the output data N .

[0061] Step S7: Based on the output data for different tunneling distancesN Generate a data set with output data N as the ordinate and tunneling distance as the coordinate. D The graph of the function is given by the x-axis, and the slope of the corresponding function is calculated in real time based on the graph. K 1. Refer to the slope K 1. Analyze the changes in output data N to determine stratigraphic shape and pattern for early warning purposes, such as... Picture 3 As shown.

[0062] Specifically, step S7 includes: when the rock strata are classified as stratum one, the judgment method is one, that is, when the excavation distance reaches the exploration stratum boundary depth. D 2. Before that, output the slope of the data function. K 1=0, output data N Remains unchanged; reaches the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K 1=1, at this point, it indicates that the soft and hard rock strata corresponding to stratum one have been reached, and a model conversion warning is issued; When the rock strata are classified as stratum two, the second method of judgment applies, i.e., when the excavation distance reaches the depth of the exploration stratum boundary. D 2. Before that, the output data N has a constant slope. K 1 gradually increases, and 0 ≤ K 1≤0.1, reaching the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K If 1 > 1, it indicates that the soft and hard rock strata corresponding to stratum two have been reached, and a model conversion warning is issued. When the rock strata are classified as strata three, the judgment method is three, that is, when the excavation distance reaches the depth of the exploration strata boundary. D 2. Before that, the output data N has a constant slope. K 1 gradually decreases, and -0.1 ≤ K 1≤0, reaching the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K 1 satisfies 0 < K If 1 < 1, it indicates that the soft and hard rock strata corresponding to stratum three have been reached, and a model conversion warning is issued.

[0063] Step S8: After issuing the warning, refer to the warning signal, economic benefit analysis and stratigraphic modeling analysis to carry out the final model conversion.

[0064] Specifically, step S8 includes: Step S81: During the tunneling process, the tunneling distance data is obtained by monitoring with displacement sensors. The tool cost is determined by weighted summation of the costs of each tool, and the number of tool replacements is recorded.T .

[0065] Step S82: During the tunneling process, the economic benefits calculation satisfies the following formula:

[0066]

[0067] in, C 总 This refers to the total cost of cutting tools from start to finish in hard or soft rock formations. B This refers to the unit price of each tool. i This refers to the number of times the cutting tool is changed. i = T +1, C 每米 This refers to the cost of the cutting tools per meter of tunneling. G 1 refers to the number of days C consumed when the first stratum was excavated.

[0068] Step S83: Distance from tunneling to the stratigraphic boundary D At 2 o'clock, the camera detects and senses the geological data ahead in real time. After obtaining the geological data, it combines it with historical data to estimate the energy consumed during tunneling in the corresponding geological strata. C’ 总 ; Step S84: Calculate the conversion cost C 转换 The following equation is satisfied:

[0069] in, C 每天 The cost of daily losses during the first layer of excavation. C 'The daily cost incurred during the excavation of the second stratum.' G 转 This represents the number of days lost during the mode conversion.

[0070] Step S85: Make a decision, if C 总 ≥ C ' 总 + C 转换 From an economic perspective, model conversion is a better option. The decision on whether to convert the model should be made based on stratigraphic modeling analysis. C 总 < C’ 总 + C 转换 If not, then no mode conversion will be performed.

[0071] Step S86: Stratigraphic modeling and analysis. After the conditions for mode conversion are met economically, based on the relevant data of the current strata collected by sensors and flow meters, the strata data detected by the camera ahead, and the judgment based on the preset strata model, the analysis is performed. If the stratigraphic data obtained from monitoring differs from the data in the preset stratigraphic model by no more than 10%, then a model conversion will be performed; if the difference exceeds 10%, then no model conversion will be performed. If the tunnel advances one meter and then the relevant geological data is monitored, and the average difference between the current data and the data from the previous meter exceeds 20%, then a mode switch is performed; if it does not exceed 20%, then the tunnel is advanced until the average difference between the relevant geological data and the data from the previous meter exceeds 20%, then a mode switch is performed.

[0072] Step S9: After the mode conversion is completed, automatically correct its own deficiencies based on the situation during and after the conversion.

[0073] This application uses sensors to monitor tunnel boring machine excavation data, radar to detect geological data, and transmits data in real time via DTU. Based on a preset database, it automatically removes unreasonable data, ensuring the real-time performance and accuracy of the data.

[0074] This application constructs a data processing model based on a CNN convolutional neural network to achieve intelligent analysis and feature extraction of tunneling parameters. Combined with formation specific energy calculation and rate of change analysis, it enables accurate judgment of formation boundaries. Furthermore, based on the data processing model's output data function slope change and formation type adaptive switching judgment strategy, it provides risk warnings and proactive, forward-looking mode switching suggestions, significantly reducing reliance on human experience.

[0075] This application integrates geological data, economic benefits (tooling costs, conversion costs, and project time losses) and stratigraphic modeling analysis results to achieve a multi-dimensional and scientific determination of the timing of model conversion. The economic analysis can automatically quantify and evaluate the cost-benefit ratio before and after the conversion, providing an objective basis for decision-making and improving the economic feasibility of the project.

[0076] This application significantly reduces uncertainties and risks during construction through real-time perception, intelligent early warning, and precise execution. It optimizes tunneling parameters and mode conversion strategies, improves the adaptability and overall construction efficiency of dual-mode tunnel boring machines in complex strata, and ensures the safety and stability of the construction process.

[0077] Example 2 Based on Embodiment 1, this embodiment also discloses a dual-mode conversion intelligent decision-making system based on digital twins, the dual-mode conversion intelligent decision-making system comprising: at least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor. By executing the instructions stored in the memory, the at least one processor performs the dual-mode conversion intelligent decision-making method corresponding to Embodiment 1.

[0078] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A dual-mode conversion intelligent decision-making method based on digital twins, characterized in that, The dual-mode conversion intelligent decision-making method includes: S1: Sensors are installed at the front end of the tunnel boring machine to collect tunneling parameter data in real time, including thrust F, torque S, rotational speed W, and tunneling speed V; S2: Install a flow meter on the drainage system at the rear of the tunnel boring machine to monitor the ground seepage P. Install a front-facing camera at the front of the tunnel boring machine to detect the ground ahead and transmit images back in real time to determine the joint dip angle. S3: The data transmission unit (DTU) receives and stores the monitoring data from various sensors and flow meters in real time. S4: The initial data consists of joint dip angle values ​​and monitoring data. Based on the preset data requirements of the database, the initial data is preprocessed to obtain the target data. S5: Based on thrust F tunneling speed V cross-sectional area of ​​the cutter head A tunneling distance D To determine the stratigraphic boundaries; S6: Construct a data processing model, which is based on a CNN convolutional neural network and includes an input layer, an output layer, and a hidden layer; The monitored tunneling speed, thrust, torque, rotational speed, and water seepage volume are input into the data processing model. The tunneling speed is not included in the calculation of the output layer but is directly entered into the hidden layer. The final output data is N. S7: Output data based on different tunneling distances N Generate a data set with output data N as the ordinate and tunneling distance as the coordinate. D The graph of the function is the x-axis, and the slope of the corresponding function is calculated in real time based on the graph. K 1. Refer to the slope K 1. Use changes in output data N to predict and establish early warnings of formation shape and pattern; S8: After issuing an early warning, the final model conversion is carried out by referring to the early warning signal, economic benefit analysis and stratigraphic modeling analysis.

2. The intelligent decision-making method for dual-mode conversion based on digital twins as described in claim 1, characterized in that, In step S4, data preprocessing includes removing outlier data from the initial data.

3. The intelligent decision-making method for dual-mode conversion based on digital twins as described in claim 1, characterized in that, Step S5 includes: Calculate the depth to which the tunnel has been excavated. D Calculate the specific energy of the strata at point 1. SE 1. Specific energy SE 1. Obtained based on the following formula: in, F Indicates total thrust. V Indicates the tunneling speed; A represents the cutterhead cross-sectional area. Obtain specific energy SE After 1, the specific energy standard was calculated. K : When the excavation reaches the depth of the explored stratigraphic boundary D At time 2, calculate the specific energy of the strata at that location. SE 2, obtained SE 1 and SE 2. Then calculate the rate of change of specific energy. SE ': By comparing the relationship between the specific energy change rate SE' and the specific energy standard K, the stratigraphic boundary can be determined: At that time, the boundary situation was stratum one; At that time, the boundary was stratum two; At that time, the boundary was stratum three.

4. The intelligent decision-making method for dual-mode conversion based on digital twins as described in claim 3, characterized in that, In step S6, the monitored tunneling speed, thrust, torque, rotational speed, and water seepage volume are divided into n groups of input data. The input layer of the data processing model then performs data calculations, including: The first set of data consists of thrust, torque, rotational speed, and water seepage data collected by sensors and flow meters when the tunnel boring machine has advanced to one meter; the second set of data consists of thrust, torque, rotational speed, and water seepage data collected by sensors and flow meters when the tunnel boring machine has advanced to two meters; and so on up to the nth set of data. First-order data t1, t2, ... t are obtained through calculation by the input layer. n The calculation formula is: Where b1, b2, b3, and b4 are weighting coefficients. F 1, S 1, W 1, P 1 represents the thrust, torque, rotational speed, and water seepage corresponding to the first set of data. F 2, S 2, W 2, P 2 represents the thrust, torque, rotational speed, and water seepage corresponding to the second set of data. F n , S n , W n , P n These are the thrust, torque, rotational speed, and water seepage corresponding to the nth set of data; The first-order data obtained from the input layer are input to the hidden layer and processed with the tunneling speed to obtain the actual speeds w1, w2, ... w n Each by f 1 (x), f 2 (x)……f n (x) express: in, V 1 represents the tunneling speed data collected by the sensor when the tunnel has been excavated to one meter. V 2 represents the tunneling speed data collected by the sensor when the tunnel has reached two meters. V n It is the tunneling speed data collected by the sensor when the tunnel has reached the nth meter, composed of decision data w1, w2, ... w n Together they form the output data N .

5. The intelligent decision-making method for dual-mode conversion based on digital twins as described in claim 4, characterized in that, Step S7 includes: When the rock strata are classified as stratum one, the first method of judgment applies, meaning that when the excavation distance reaches the depth of the exploration strata boundary. D 2. Before that, output the slope of the data function. K 1=0, output data N Remains unchanged; reaches the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K 1=1, at this point, it indicates that the soft and hard rock strata corresponding to stratum one have been reached, and a model conversion warning is issued; When the rock strata are classified as stratum two, the second method of judgment applies, meaning that when the excavation distance reaches the depth of the exploration strata boundary. D 2. Before that, the output data N has a constant slope. K 1 gradually increases, and 0 ≤ K 1≤0.1, reaching the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K If 1 > 1, it indicates that the soft and hard rock strata corresponding to stratum two have been reached, and a model conversion warning is issued. When the rock strata are classified as strata three, the judgment method is three, that is, when the excavation distance reaches the depth of the exploration strata boundary. D 2. Before that, the output data N has a constant slope. K 1 gradually decreases, and -0.1 ≤ K 1≤0, reaching the depth of the exploration stratigraphic boundary D At time 2, output data N Mutation and slope K 1 satisfies 0 < K If 1 < 1, it indicates that the soft and hard rock strata corresponding to stratum three have been reached, and a model conversion warning is issued.

6. The intelligent decision-making method for dual-mode conversion based on digital twins as described in claim 5, characterized in that, Step S8 includes: S81: During the tunneling process, displacement sensors are used to monitor and obtain tunneling distance data. The tooling cost is determined by a weighted average of the costs of each tool, and the number of tool replacements is recorded. T ; S82: During the tunneling process, the economic benefits are calculated according to the following formula: in, C 总 This refers to the total cost of cutting tools from start to finish in hard or soft rock formations. B This refers to the unit price of each tool. i This refers to the number of times the cutting tool is changed. i = T +1, C 每米 This refers to the cost of the cutting tools per meter of tunneling. G 1 refers to the number of days C consumed in completing the excavation of the first stratum; S83: Distance from tunneling to the stratigraphic boundary D At 2 o'clock, the camera detects and senses the geological data ahead in real time. After obtaining the geological data, it combines it with historical data to estimate the energy consumed during tunneling in the corresponding geological strata. C’ 总 ; S84: Calculate conversion cost C 转换 The following equation is satisfied: in, C 每天 The cost of daily losses during the first layer of excavation. C 'The daily cost incurred during the excavation of the second stratum.' G 转 This refers to the number of days the project was delayed during the mode conversion. S85: Make a decision, if C 总 ≥ C ' 总 + C 转换 From an economic perspective, model conversion is a better option. The decision on whether to convert the model should be made based on stratigraphic modeling analysis. C 总 < C’ 总 + C 转换 If not, then no mode conversion will be performed.

7. The intelligent decision-making method for dual-mode conversion based on digital twins as described in claim 6, characterized in that, Step S8 also includes: S86: Stratigraphic modeling and analysis. After the conditions for mode conversion are met economically, based on relevant data of the current strata collected by sensors and flow meters, and forward strata data detected by cameras, and based on a preset strata model, a judgment is made. If the stratigraphic data obtained from monitoring differs from the data in the preset stratigraphic model by no more than 10%, then a model conversion will be performed; if the difference exceeds 10%, then no model conversion will be performed. If the tunnel advances one meter and then the relevant geological data is monitored, and the average difference between the current data and the data from the previous meter exceeds 20%, then a mode switch is performed; if it does not exceed 20%, then the tunnel is advanced until the average difference between the relevant geological data and the data from the previous meter exceeds 20%, then a mode switch is performed.

8. The intelligent decision-making method for dual-mode conversion based on digital twins as described in claim 1, characterized in that, The dual-mode conversion intelligent decision-making method also includes: S9: After the mode conversion is completed, it automatically corrects its own shortcomings based on the situation during and after the conversion.

9. A dual-mode conversion intelligent decision-making system based on digital twins, characterized in that, The dual-mode conversion intelligent decision-making system includes: at least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which executes the instructions stored in the memory to perform the method as described in any one of claims 1 to 8.