Real-time sensing method and system for rock mass state in shield tunneling

Abstract

The invention discloses a rock mass state real-time sensing method and system in shield tunneling. The rock mass state real-time sensing method comprises the following steps: constructing a corresponding relation between rock strength and a penetration index; rock slag characterization parameters are extracted according to the rock slag images, and the corresponding relations between the rock slag characterization parameters and rock mass strength and rock mass integrity coefficients are established respectively; according to the corresponding relation, rock mass state initial information in the shield tunneling process is obtained; according to the corresponding relation between the tunneling parameters and the rock strength, the rock mass strength and the rock mass integrity coefficient, a site construction information database is constructed; and training the deep learning model by adopting the on-site construction information database, and optimizing the rock mass state initial information by adopting the trained deep learning model to obtain a corrected rock mass state. The problems that in the prior art, rock mass state information is not accurately obtained in shield tunneling, and the shield tunneling tunnel rock mass state cannot be effectively reflected in time are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of shield tunnel construction, and in particular to a method and system for instantly sensing rock mass status during shield tunneling. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The shield machine is a heavy-duty tunnel construction tool that integrates machinery, electricity, hydraulics, sensors, and communications. It can realize tunneling, slag removal, support and other processes in one excavation. It has significant advantages such as high mechanization and automation, fast tunneling speed, and small ground disturbance. It has been widely used in tunnel construction operations in the fields of transportation, water conservancy, and mining. Due to the complexity of some engineering geological conditions and the limitations of time, cost, and technical level, it is difficult to carry out comprehensive and detailed geological surveys before shield tunnel construction. During the shield advancement process, unfavorable geological conditions that are not reflected in the geological survey data are often encountered.

[0004] At present, the rock status information such as compressive strength, joint conditions and other parameters in the shield tunneling process is still obtained through manual on-site inspection and indoor testing after sampling. The acquisition means are relatively backward and have poor timeliness. It is impossible to obtain the rock information ahead in real time and accurately. As a result, it is difficult to accurately grasp the rock information when the shield encounters stratum changes or complex geological conditions, resulting in improper replacement of the shield cutter head and even major accidents such as casualties.

[0005] The use of laboratory or field penetration tests to characterize rock mechanics test parameters has been proven feasible by relevant studies and has made some progress. Some scholars and engineers have also used computer vision processing technology to extract digital information from rock slag images and established a connection between rock slag data and key parameters of rock mass information such as rock mass strength and rock mass integrity coefficient; by collecting and processing shield machine propulsion parameters and combining them with formation parameters, and training them through machine learning or deep learning algorithms, they can be used to initially reflect rock mass information. However, existing technologies have the disadvantages of poor timeliness, low accuracy, and incomplete use of comprehensive information in terms of real-time perception of rock mass status during shield tunneling. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a method and system for real-time perception of rock status during shield tunneling, which comprehensively utilizes digital data such as on-site penetration tests, rock slag images, and shield machine tunneling parameters to achieve real-time perception of the rock status ahead during the tunneling process, thereby solving the problem in the prior art that rock status information is not accurately obtained during shield tunneling and cannot timely and effectively reflect the rock status of the shield tunneling tunnel.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for real-time sensing of rock mass status during shield tunneling, comprising:

[0009] The corresponding relationship between rock strength and penetration index is established through rock penetration test;

[0010] Extract rock slag characterization parameters according to the acquired rock slag image, and establish the corresponding relationship between the rock slag characterization parameters and the rock mass strength and rock mass integrity coefficient respectively;

[0011] According to the above correspondence, the initial information of rock mass state during shield tunneling is obtained;

[0012] Obtain the tunneling parameters during shield tunneling, and build a field construction information database based on the corresponding relationship between tunneling parameters and rock strength, rock mass strength and rock mass integrity coefficient;

[0013] The on-site construction information database is used to train the deep learning model, and the trained deep learning model is used to optimize the initial information of the rock mass state to obtain the corrected rock mass state.

[0014] As an optional implementation, the penetration indicators include point indicators, line indicators and surface indicators; specifically: point indicators include the first peak force, sensor average force, rock drillability indicators and penetration force fluctuations; line indicators include tangent modulus, secant modulus, brittleness index and local average force index; surface indicators include penetration work and total average penetration force index.

[0015] As an optional embodiment, the slag characterization parameters include slag length, equivalent diameter, elongation, sphericity and roughness.

[0016] As an optional implementation method, a corresponding relationship between the length of slag, equivalent diameter and elongation and the strength of the rock mass is established, and a quantitative relationship between the sphericity and roughness and the integrity coefficient of the rock mass is established.

[0017] As an optional implementation method, the process of constructing an on-site construction information database includes: preprocessing the acquired cutterhead vibration signal to obtain a noise reduction signal corresponding to the rock mass being excavated, extracting time domain and frequency domain characteristic signals from the noise reduction signal, thereby establishing a mutual feedback relationship between the time domain and frequency domain characteristic signals and the rock strength, rock mass strength and rock mass integrity coefficient, collecting excavation parameters, combining the mutual feedback relationship between the cutterhead vibration signal and the rock strength, rock mass strength and rock mass integrity coefficient, and establishing an on-site construction information database according to the corresponding relationship in the construction process.

[0018] As an optional embodiment, the excavation parameters include thrust, torque, penetration and cutter head rotation speed.

[0019] In a second aspect, the present invention provides a system for real-time sensing of rock mass status during shield tunneling, comprising:

[0020] A first relationship determination module is configured to construct a corresponding relationship between rock strength and penetration index through a rock penetration test;

[0021] A second relationship determination module is configured to extract rock slag characterization parameters according to the acquired rock slag image, and respectively establish corresponding relationships between the rock slag characterization parameters and the rock mass strength and the rock mass integrity coefficient;

[0022] The initial information determination module is configured to obtain the initial information of the rock mass state during the shield tunneling process according to the above correspondence relationship;

[0023] A database construction module is configured to obtain tunneling parameters during shield tunneling and to construct a field construction information database based on the corresponding relationship between the tunneling parameters and rock strength, rock mass strength and rock mass integrity coefficient;

[0024] The perception module is configured to use the on-site construction information database to train the deep learning model, and use the trained deep learning model to optimize the initial information of the rock state to obtain the corrected rock state.

[0025] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in the first aspect is performed.

[0026] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0027] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention proposes a method for real-time perception of rock mass status during shield tunneling, which comprehensively utilizes digital data such as field penetration test, rock slag image conversion digital information, and shield machine tunneling parameters to achieve real-time perception of the rock mass status in front during tunneling. The method solves the problem that the rock mass status information in shield tunneling is not obtained in a timely and accurate manner in the prior art, and cannot effectively reflect the rock mass status of the shield tunneling tunnel in a timely manner, and can adjust the shield machine tunneling parameters in real time.

[0030] The present invention proposes a method for real-time perception of rock state during shield tunneling, establishes a relationship in which the penetration index characterizes the rock strength, extracts rock slag characterization information through rock slag images, establishes a corresponding relationship in which the rock slag information characterizes the rock strength and integrity, uses the cutterhead vibration signal extracted by the sensor to establish a feedback relationship with the rock state information initially acquired, establishes a database based on the matching relationship between shield machine data (including propulsion parameters and cutterhead vibration noise reduction signals) and rock state information (rock strength, rock strength and integrity), realizes the corresponding relationship between rock state parameters and tunneling parameters through regression analysis and optimization algorithm of training set distribution, and finally obtains real-time information on rock state that is jointly decided by integrating field penetration test data, rock slag image data and tunneling parameters, makes up for the shortcomings of untimely and inaccurate acquisition of rock condition parameters in shield tunneling by traditional means, and provides a reference for shield parameter adjustment and even intelligent decision-making.

[0031] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0033] Figure 1 A flowchart of a method for real-time perception of rock mass status during shield tunneling provided in Example 1 of the present invention;

[0034] Figure 2 A schematic diagram of the corresponding relationship between rock strength and penetration index provided in Example 1 of the present invention;

[0035] Figure 3 A schematic diagram of the corresponding relationship between the slag characterization parameters provided in Example 1 of the present invention and the rock mass strength and rock mass integrity coefficient;

[0036] Figure 4 A schematic diagram of establishing the mutual feedback relationship between the cutterhead vibration signal and the rock mass state information provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0037] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0038] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0039] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "comprise" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0040] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0041] Example 1

[0042] like Figure 1 As shown, this embodiment provides a method for real-time perception of rock mass status during shield tunneling, including:

[0043] The corresponding relationship between rock strength and penetration index is established through rock penetration test;

[0044] Extract rock slag characterization parameters according to the acquired rock slag image, and establish the corresponding relationship between the rock slag characterization parameters and the rock mass strength and rock mass integrity coefficient respectively;

[0045] According to the above correspondence, the initial information of rock mass state during shield tunneling is obtained;

[0046] Obtain the tunneling parameters during shield tunneling, and build a field construction information database based on the corresponding relationship between tunneling parameters and rock strength, rock mass strength and rock mass integrity coefficient;

[0047] The database is used to train the deep learning model, and the trained deep learning model is used to optimize the initial information of the rock mass state to obtain the corrected rock mass state.

[0048] In this embodiment, if Figure 2 As shown, through indoor rock penetration test, the corresponding relationship between rock strength and penetration index is established;

[0049] Among them, the penetration index is obtained by the sensor or the force-displacement curve of the penetration process, including point index, line index and surface index;

[0050] Specifically: point indicators include the first peak force, sensor average force, rock drillability index and penetration force fluctuation; line indicators include penetration modulus (including tangent modulus and secant modulus), brittleness index and local average force index; surface indicators include penetration work and total average penetration force index (extracted from the force-displacement curve).

[0051] Therefore, in-situ penetration tests are carried out using shield-mounted or independent penetration equipment to obtain the penetration index of the rock mass ahead during shield excavation, and the initial rock strength is obtained based on the corresponding relationship between rock strength and penetration index.

[0052] In this embodiment, an industrial camera arranged on the upper part of the shield slag conveyor belt is used to capture the slag image, and the slag image is first converted into digital information through image digitization processing.

[0053] Specifically: After the sampling, quantization and encoding process, an m-row n-column digital matrix is ​​obtained to represent the image size, and its specific expression is as follows:

[0054]

[0055] The above digital matrix represents the overall digital information of the slag image, and its essence is a pixel matrix, and each element value f(m,n) represents the pixel value of the corresponding original image position.

[0056] In this embodiment, if Figure 3 As shown, the rock slag characterization parameters are extracted according to the rock slag image, and the corresponding relationships between the rock slag characterization parameters and the rock mass strength and rock mass integrity coefficient are established respectively.

[0057] Specifically:

[0058] The rock slag characterization parameters include rock slag length, equivalent diameter, elongation, sphericity and roughness;

[0059] The quantitative relationship between the length of slag, equivalent diameter and elongation and the strength of rock mass is established; the strength of rock mass is obtained by empirically fitting the length of slag, equivalent diameter, elongation and indoor experimental results;

[0060] The quantitative relationship between sphericity, roughness and rock mass integrity coefficient is established; the rock mass integrity coefficient is obtained by fitting the sphericity and roughness of rock slag with geological survey data.

[0061] Therefore, based on the above correspondence, the initial rock mass strength and the initial rock mass integrity coefficient are obtained according to the rock slag image during the shield excavation process, and then the initial rock state information including the initial rock strength, the initial rock mass strength and the initial rock mass integrity coefficient is obtained.

[0062] In this embodiment, according to the matching relationship between the shield machine data (including tunneling parameters and cutterhead vibration signals) and the rock strength, rock mass strength and rock mass integrity coefficient, a field construction information database is established, and the field construction information database is split into a training set and a verification set. The feedback relationship between the rock state parameters and the tunneling parameters is established through regression analysis of the training set and a machine learning algorithm, which is verified or corrected in the verification set, and finally the real-time information of the rock state that is jointly decided by the integration of the field penetration test data, the slag image data and the tunneling parameters is obtained.

[0063] Specifically:

[0064] (1) Figure 4 As shown in the figure, according to the cutterhead vibration information obtained by the sensor, the noise reduction signal corresponding to the excavated rock mass is obtained through wavelet decomposition, threshold processing and wavelet reconstruction process, and then the time domain and frequency domain characteristic signals are extracted from it. The BP neural network is used to establish the mutual feedback relationship between the time domain and frequency domain characteristic signals and the rock strength, rock mass strength and rock mass integrity coefficient.

[0065] Specifically, the method of using BP neural network to establish the feedback relationship between cutter vibration information and rock strength, rock mass strength and rock mass integrity coefficient is as follows:

[0066] (1-1) The acquired time domain and frequency domain data are denoised and standardized to improve data quality and adapt to the input requirements of the neural network.

[0067] (1-2) Taking the extracted time domain and frequency domain characteristic signals as input, and the rock strength, rock mass strength and rock mass integrity coefficient as output, a BP neural network model is established;

[0068] Among them, the number of input layer nodes is 2, corresponding to the time domain and frequency domain signals of the cutterhead vibration information; the number of output layer nodes is 3, corresponding to the rock strength, rock mass strength and rock mass integrity coefficient on the excavation face; the hyperparameters include activation function, number of hidden layers, and number of hidden layer units.

[0069] (1-3) The BP neural network is trained using the extracted time domain and frequency domain characteristic signals as input and rock strength, rock mass strength and rock mass integrity coefficient as output; wherein, the back propagation algorithm is used during the training process to adjust the weights in the network to minimize the error function.

[0070] (1-4) Hyperparameters are tuned through grid search or Bayesian optimization methods to find the optimal model configuration, and cross-validation techniques are used to evaluate and optimize the model to further improve the model's prediction accuracy and generalization ability.

[0071] (2) The tunneling parameters during shield tunneling were collected, and the feedback relationship between the cutterhead vibration information and the rock mass status information was combined. An on-site construction information database was established according to the corresponding relationship in time or construction process, and randomly divided into two groups: a training set (80%) and a validation set (20%).

[0072] The on-site construction information database includes rock state parameters such as rock strength, rock mass strength, rock mass integrity coefficient, and excavation parameters, and is divided into two groups: a training set and a data set according to the corresponding relationship.

[0073] The excavation parameters include thrust Tr, torque To, penetration rate PRev and cutter head speed RPM.

[0074] (3) Based on the training set, a machine learning algorithm is used for training to establish a rock state information representation method that adapts to the experience of shield parameter adjustment. The preliminary rock state information is verified and further optimized using the validation set to obtain the corrected rock state information. Thus, the rock state information during the excavation process can be instantly perceived by combining the on-site penetration parameters, rock slag digital information, and shield excavation parameters.

[0075] Among them, a rock mass state information representation method that adapts to the experience of shield parameter adjustment is established, and its steps are as follows:

[0076] (3-1) Based on the corresponding relationship during the excavation process, a data set of shield parameters and rock mass status information is established, and the data is cleaned and standardized so that the characteristic data have the same scale.

[0077] (3-2) The thrust Tr, torque To, penetration rate PRev and cutter head speed RPM are taken as input values, and the rock strength, rock mass strength and rock mass integrity coefficient are taken as output values.

[0078] (3-3) Calculate the correlation coefficient between each excavation parameter and rock properties to screen out important features; construct new features, such as parameter ratios.

[0079] (3-4) The training set is input into the selected machine learning algorithm for training to learn the relationship between excavation parameters and rock strength, rock mass strength and rock mass integrity coefficient; the hyperparameters of the model are optimized through cross-validation and grid search to improve the model performance.

[0080] (3-5) Use the validation set to validate the model and evaluate the model’s performance indicators, such as mean square error and R2; based on the validation results, further adjust the model structure and hyperparameters to improve the accuracy and stability of the model.

[0081] (3-6) Based on the trained model, a method for representing the rock mass state is designed. The excavation parameters collected in real time during the excavation process are input into the model, and the estimated values ​​of rock strength, rock mass strength and rock mass integrity coefficient are output; combined with the on-site penetration parameters, rock slag digital information, and shield excavation parameters, the model input is adjusted in real time to improve the accuracy of the rock mass state information.

[0082] Example 2

[0083] This embodiment provides a system for real-time sensing of rock mass status during shield tunneling, including:

[0084] A first relationship determination module is configured to construct a corresponding relationship between rock strength and penetration index through a rock penetration test;

[0085] A second relationship determination module is configured to extract rock slag characterization parameters according to the acquired rock slag image, and respectively establish corresponding relationships between the rock slag characterization parameters and the rock mass strength and the rock mass integrity coefficient;

[0086] The initial information determination module is configured to obtain the initial information of the rock mass state during the shield tunneling process according to the above correspondence relationship;

[0087] A database construction module is configured to obtain tunneling parameters during shield tunneling and to construct a field construction information database based on the corresponding relationship between the tunneling parameters and rock strength, rock mass strength and rock mass integrity coefficient;

[0088] The perception module is configured to use the on-site construction information database to train the deep learning model, and use the trained deep learning model to optimize the initial information of the rock state to obtain the corrected rock state.

[0089] As an optional implementation, the penetration indicators include point indicators, line indicators and surface indicators; specifically: point indicators include the first peak force, sensor average force, rock drillability indicators and penetration force fluctuations; line indicators include tangent modulus, secant modulus, brittleness index and local average force index; surface indicators include penetration work and total average penetration force index.

[0090] As an optional embodiment, the slag characterization parameters include slag length, equivalent diameter, elongation, sphericity and roughness.

[0091] As an optional implementation method, a corresponding relationship between the length of slag, equivalent diameter and elongation and the strength of the rock mass is established, and a quantitative relationship between the sphericity and roughness and the integrity coefficient of the rock mass is established.

[0092] As an optional implementation method, the process of constructing an on-site construction information database includes: preprocessing the acquired cutterhead vibration signal to obtain a noise reduction signal corresponding to the rock mass being excavated, extracting time domain and frequency domain characteristic signals from the noise reduction signal, thereby establishing a mutual feedback relationship between the time domain and frequency domain characteristic signals and the rock strength, rock mass strength and rock mass integrity coefficient, collecting excavation parameters, combining the mutual feedback relationship between the cutterhead vibration signal and the rock strength, rock mass strength and rock mass integrity coefficient, and establishing an on-site construction information database according to the corresponding relationship in the construction process.

[0093] As an optional embodiment, the excavation parameters include thrust, torque, penetration and cutter head rotation speed.

[0094] It should be noted that the above modules correspond to the steps described in Example 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above Example 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer executable instructions.

[0095] In further embodiments, there is also provided:

[0096] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in Embodiment 1 is performed. For the sake of brevity, it will not be described in detail here.

[0097] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0098] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0099] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in Example 1 is completed.

[0100] The method in Example 1 can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it is not described in detail here.

[0101] A computer program product includes a computer program, and when the computer program is executed by a processor, the method described in embodiment 1 is implemented.

[0102] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the process / method as described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of program modules can be combined or divided between program modules as needed. Machine executable instructions for program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0103] The computer program code for implementing the method of the present invention can be written in one or more programming languages. These computer program codes can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the computer or other programmable data processing device, causes the function / operation specified in the flow chart and / or block diagram to be implemented. The program code can be executed completely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer or completely on a remote computer or server.

[0104] In the context of the present invention, computer program codes or related data may be carried by any appropriate carrier to enable a device, apparatus or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, etc. Examples of signals may include electrical, optical, radio, acoustic or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0105] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0106] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for real-time perception of rock mass status during shield tunneling, characterized in that: include: The corresponding relationship between rock strength and penetration index is established through rock penetration test; Extract rock slag characterization parameters according to the acquired rock slag image, and establish the corresponding relationship between the rock slag characterization parameters and the rock mass strength and rock mass integrity coefficient respectively; According to the above correspondence, the initial information of rock mass state during shield tunneling is obtained; Obtain the tunneling parameters during shield tunneling, and build a field construction information database based on the corresponding relationship between tunneling parameters and rock strength, rock mass strength and rock mass integrity coefficient; The on-site construction information database is used to train the deep learning model, and the trained deep learning model is used to optimize the initial information of the rock mass state to obtain the corrected rock mass state.

2. A method for real-time perception of rock mass status during shield tunneling as claimed in claim 1, characterized in that: The penetration indicators include point indicators, line indicators and surface indicators; specifically: point indicators include the first peak force, sensor average force, rock drillability index and penetration force fluctuation; line indicators include tangent modulus, secant modulus, brittleness index and local average force index; surface indicators include penetration work and total average penetration force index.

3. A method for real-time perception of rock mass status during shield tunneling as claimed in claim 1, characterized in that: The slag characterization parameters include slag length, equivalent diameter, elongation, sphericity and roughness.

4. A method for real-time perception of rock mass status during shield tunneling as claimed in claim 3, characterized in that: The corresponding relationship between the length, equivalent diameter and elongation of rock slag and the strength of rock mass is established, and the quantitative relationship between the sphericity and roughness and the integrity coefficient of rock mass is established.

5. A method for real-time sensing of rock mass status during shield tunneling as claimed in claim 1, characterized in that: The process of building a field construction information database includes: preprocessing the acquired cutterhead vibration signal to obtain a noise reduction signal corresponding to the rock mass being excavated, extracting time domain and frequency domain characteristic signals from the noise reduction signal, thereby establishing a mutual feedback relationship between the time domain and frequency domain characteristic signals and the rock strength, rock mass strength and rock mass integrity coefficient, collecting excavation parameters, combining the mutual feedback relationship between the cutterhead vibration signal and the rock strength, rock mass strength and rock mass integrity coefficient, and establishing a field construction information database according to the corresponding relationship in the construction process.

6. A method for real-time sensing of rock mass status during shield tunneling as claimed in claim 1, characterized in that: The excavation parameters include thrust, torque, penetration and cutterhead speed.

7. A real-time rock mass state sensing system during shield tunneling, characterized in that: include: A first relationship determination module is configured to construct a corresponding relationship between rock strength and penetration index through a rock penetration test; A second relationship determination module is configured to extract rock slag characterization parameters according to the acquired rock slag image, and respectively establish corresponding relationships between the rock slag characterization parameters and the rock mass strength and the rock mass integrity coefficient; The initial information determination module is configured to obtain the initial information of the rock mass state during the shield tunneling process according to the above correspondence relationship; A database construction module is configured to obtain tunneling parameters during shield tunneling and to construct a field construction information database based on the corresponding relationship between the tunneling parameters and rock strength, rock mass strength and rock mass integrity coefficient; The perception module is configured to use the on-site construction information database to train the deep learning model, and use the trained deep learning model to optimize the initial information of the rock state to obtain the corrected rock state.

8. An electronic device, characterized in that: The method comprises a memory and a processor and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 6 is completed.

9. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the method described in any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images