Large-diameter shield tunnel segment performance early warning method and system based on artificial intelligence

Abstract

The invention relates to a large-diameter shield tunnel segment performance early warning method and system based on artificial intelligence, and the method comprises the steps: S1, arranging a pressure sensing device at a groove in the edge of a segment, splicing the pressure sensing device, and completing the shaping of the segment, so that the inner circumference of a tunnel forms a preset shape; s2, the pressure value of the pressure sensing device of the shaped segment is put into an early warning window; determining whether the early warning window needs to be updated or not based on the pressure value of the pressure sensing device in the current early warning window t; if yes, updating an early warning window; s3, inputting the pressure value sequence in the early warning window into an artificial intelligence model to obtain a target segment, and performing performance early warning on the target segment; the tunnel segment performance is monitored and early warned in real time, the monitoring result is adjusted in time, secondary grouting and peripheral reinforcement are conducted on the segment needing early warning relieving in parallel, and the construction efficiency of a large-diameter shield tunnel is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of tunnel deformation monitoring, and particularly relates to a method and system for warning the performance of segment linings of large-diameter shield tunnels based on artificial intelligence.

Background Art

[0002] A tunnel is an engineering structure buried in the ground and is a form of human utilization of underground space. The shield method is the main construction method for tunnel engineering. With the acceleration of the urbanization process, the construction of urban rail transit has developed rapidly, the number of transfer stations has increased, and there are overlapping intersections between different lines. The overlapping shield construction conditions of the access line of the parking lot and the main line are increasing. In the construction of urban tunnels, more complex geological environment conditions will be encountered, such as karst, underground rivers, karst collapse columns in carbonate distribution areas, rock bursts in high in-situ stress areas, coal and gas outbursts in coal-bearing strata, complex geological structures, and geological disasters such as groundwater gushing, collapse, and large deformation. In addition, during the tunneling process of the shield construction curve section of subway construction, due to the small turning radius of the tunnel, the turning amplitude of the shield tunneling during construction is relatively large, the internal space of the tunnel is small, the thrust of the jacking cylinder is tangent to the tunnel curve, and the shield tail and the segment linings will be squeezed, which will cause the tunnel to shift outward.

[0003] The construction of shield tunnels in China is increasing continuously, and the construction technology is becoming increasingly mature. The large-diameter shields currently promoted and used have high working efficiency. However, the construction of large-scale shield tunnels is a complex and technically demanding project. With the continuous increase in the development of urban underground space, the application of shield tunnels is becoming increasingly widespread. However, the increase in the tunnel diameter poses many technical challenges during the construction process, especially in terms of construction safety, structural stability, and the impact on the surrounding environment. Therefore, how to timely warn and respond to possible construction risks has become the key to ensuring the safe and efficient construction of large-diameter shield tunnels.

[0004] During the construction of large-diameter shield tunnels, the following risks and challenges are mainly faced: First: The increase in tunnel burial depth and the change in overburden load. As the tunnel burial depth increases, the load on the overlying soil layer of the tunnel will also increase significantly, resulting in changes in the physical properties and mechanical behavior of the soil layer. These changes are usually difficult to monitor in real time and accurately predict, and are likely to have an adverse impact on the stability of the tunnel. Traditional soil mechanics models cannot fully consider complex geological environments and construction conditions. Second: The structural deformation problem caused by the decrease in the ratio of segment thickness to diameter. As the diameter of the shield tunnel increases, the ratio of segment thickness to diameter decreases, which leads to a reduction in the stiffness of the tunnel structure and an increase in deformation. Traditional structural analysis methods are difficult to comprehensively evaluate and monitor the deformation of shield tunnels in real time. Third: The influence of the increase in the number of lining structure segments on the internal force response. As the number of segments of the large-diameter shield tunnel lining structure increases, the distribution and transfer of internal forces become more complex, which may lead to stress concentration or local overload in some areas. This structural risk is difficult to accurately simulate and warn in traditional designs. Fourth: The increase in the internal force response caused by the self-weight of the segments. As the cross-section of the segments increases, the self-weight of the segments also increases, resulting in a greater internal force borne by the tunnel lining structure. In traditional structural designs and construction processes, it is difficult to monitor in real time the internal force changes caused by the self-weight of the segments. In view of the above problems, the performance warning method for large-diameter shield tunnels based on artificial intelligence can provide targeted warnings and decision-making support through real-time data collection, intelligent analysis, and prediction. This method can not only improve the safety and stability during tunnel construction but also effectively optimize the construction plan, reduce resource waste, and improve construction efficiency.

[0005] With the rapid development of artificial intelligence, wireless communication technology, and big data technology, it provides a basis for the safe and rapid construction of tunnel engineering; multiple construction units and infrastructure providers have started to research and develop software and hardware facilities for segment performance warning during the whole stage and are committed to promoting and developing intelligent, digital, and information-based tunnel engineering construction. How to use modern means to assist and support the high-tech development of tunnel engineering construction and promote tunnel engineering construction intelligently is a technical problem to be solved. Through real-time data analysis and warning, the present invention can effectively improve the prediction accuracy of soil layer load changes and reduce potential safety hazards during construction; by monitoring and warning the performance of tunnel segments in real time and making timely adjustments to the monitoring results, for the segments that need to lift the warning, secondary grouting and peripheral reinforcement are carried out in parallel to ensure the construction efficiency of large-diameter shield tunnels.

Summary of the Invention

[0006] In order to solve the above problems in the prior art, the present invention proposes a method and system for segment performance warning of large-diameter shield tunnels based on artificial intelligence. The method includes:

[0007] Step S1: Set a pressure sensing device at the groove on the edge of the segment, assemble and complete the shaping of the segment so that the inner circumference of the tunnel forms a preset shape;

[0008] Step S2: Put the pressure value of the pressure sensing device of the shaped segment into the warning window; the warning window includes the pressure values of the pressure sensing devices arranged continuously in chronological order; after each preset time interval, when the monitoring time point arrives, obtain the pressure value of each pressure sensing device at the monitoring time point t; determine whether the warning window needs to be updated based on the pressure values of the pressure sensing devices within the current warning window t; if so, update the warning window; where: t is the monitoring time point and its corresponding warning window number;

[0009] Step S3: Input the pressure value sequence in the warning window into the artificial intelligence model to obtain the target segment and perform performance warning on the target segment;

[0010] Step S4: Disturb and / or perform secondary shaping on the target segment, and return to Step S2 after completing the disturbance and / or secondary shaping.

[0011] Further, the pressure sensing device is set at the gap between the segments.

[0012] Further, there is a groove at the segment joint, and a pressure sensing device is set in the groove.

[0013] Further, the pressure sensing device is communicatively connected to the warning server by wired or wireless means and sends the monitored pressure value to the warning server.

[0014] Further, the pressure sensing device sets a unique identifier according to the shaping order of its corresponding segment.

[0015] Further, Step S2 specifically includes the following steps:

[0016] Step S21: Put the pressure value of the pressure sensing device of the shaped segment into the warning window; the warning window includes the pressure values of the pressure sensing devices arranged continuously in order; the pressure values in the warning window form a pressure value sequence Pr t =(pr t,l ); where: t is the monitoring time point, pr t,l is the element value of the l-th element in the warning window at the monitoring time point t; l ∈ 1~L; L is the warning window length;

[0017] Step S22: Calculate the k-order difference sequence using the following formulas (1)-(3);

[0018]

[0019] Step S23: Calculate the symmetric stability of the difference sequence based on the k-th order difference sequence; specifically: calculate the symmetric stability STD using the following formula (4);

[0020]

[0021] Step S24: If the difference between the symmetric stability STD and the smaller value is less than the deviation threshold, delete the pressure value with the earliest time in the warning window from the warning window; thereby sliding out the segment corresponding to the pressure value with the earliest time from the warning window.

[0022] An artificial intelligence-based segment performance warning system for large-diameter shield tunnels, which is used to implement the above-mentioned artificial intelligence-based segment performance warning method for large-diameter shield tunnels.

[0023] An artificial intelligence-based segment performance warning control platform for large-diameter shield tunnels, which is used to implement the above-mentioned artificial intelligence-based segment performance warning method for large-diameter shield tunnels.

[0024] An artificial intelligence-based segment performance warning control server for large-diameter shield tunnels, which is used to implement the above-mentioned segment performance warning method for large-diameter shield tunnels.

[0025] An artificial intelligence-based segment performance warning control device for large-diameter shield tunnels, which is used to implement the above-mentioned artificial intelligence-based segment performance warning method for large-diameter shield tunnels.

[0026] The beneficial effects of the present invention include:

[0027] (1) Relying on artificial intelligence technology, through real-time data analysis and warning, it can effectively improve the prediction accuracy of soil layer load changes. Through big data analysis and prediction, key parameters such as stress and deformation during shield construction are collected in real time, and the deformation trend is warned, and corresponding measures are taken in time to prevent structural damage or environmental impact, reduce potential safety hazards that may occur during construction, discover the abnormal change trend of the internal force of the lining structure, ensure the overall stability of the tunnel lining, consider and accurately evaluate the influence of the self-weight of the segment on the internal force of the structure, and warn of potential risks in advance;

[0028] (2) By monitoring and warning the performance of tunnel segments in real time and making timely adjustments to the monitoring results, the warning window range is determined based on the symmetric stability and asymmetric stability analysis of the warning window, and the concurrent construction speed is supported by scientific calculations; for the segments that need to be de-warned, secondary grouting and peripheral reinforcement are carried out in parallel, ensuring the construction efficiency of large-diameter shield tunnels.

[0029] (3) Considering two different artificial intelligence models based on the pressure value sequence and the pressure difference sequence simultaneously, the applicable range of the artificial intelligence model is extended. By merging the warning results of the artificial intelligence model considering the degree of difference, the target segment and the auxiliary target segment are scientifically located, providing a data support basis for secondary shaping and manual disturbance.

BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, but do not constitute an improper limitation of the present invention. In the drawings:

[0031] Figure 1 It is a schematic diagram of a segment performance warning system for large-diameter shield tunnels based on artificial intelligence of the present invention.

DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The present invention will be described in detail below with reference to the drawings and specific embodiments. The illustrative embodiments and descriptions are only used to explain the present invention, but do not limit the present invention.

[0033] As shown in the attached Figure 1 figure, the present invention provides a method for warning the performance of segments in large-diameter shield tunnels based on artificial intelligence. The method includes the following steps:

[0034] Step S1: Set a pressure sensing device at the edge groove of the segment, assemble and complete the shaping of the segment, so that the inner circumference of the tunnel forms a preset shape;

[0035] Preferably: The pressure sensing device is arranged at the gap between the segments; there is a groove at the segment gap, and a pressure sensing device is arranged in the groove;

[0036] Preferably: The pressure sensing device communicates with the warning server in a wired or wireless manner and sends the monitored pressure value to the warning server; the pressure value of each pressure sensing device is obtained at the monitoring time point t, and a preset time interval is separated between two consecutive monitoring time points; that is to say, shaping and monitoring are carried out in parallel;

[0037] Step S2: Put the pressure values of the pressure sensing devices of the shaped segments into the warning window; the warning window includes the pressure values of the pressure sensing devices arranged in chronological order continuously; every time the monitoring time point arrives after a preset time interval, the pressure value of each pressure sensing device is obtained at the monitoring time point t; it is determined whether the warning window needs to be updated based on the pressure values of the pressure sensing devices in the current warning window t; if so, the warning window is updated; where: t is the monitoring time point and its corresponding warning window number;

[0038] Preferably: The pressure sensing device is set with a unique identifier according to the shaping order of its corresponding segment;

[0039] Preferably: determining whether to update the warning window specifically includes: after finishing shaping a segment, determining to update the warning window; at this time, updating the warning window means deleting the pressure value with the earliest time in the warning window from the warning window;

[0040] The specific steps of step S2 are as follows:

[0041] Step S21: Put the pressure value of the pressure sensing device of the segment that has completed shaping into the warning window; the warning window includes consecutive pressure values of the pressure sensing devices arranged in order; the pressure values in the warning window form a pressure value sequence Pr t =(pr t,l ); where: t is the monitoring time point, pr t,l is the element value of the l-th element in the warning window at the monitoring time point t; l ∈ 1 to L; L is the warning window length;

[0042] Preferably: The window length is a preset value; for example: the window length is 100;

[0043] Step S22: Calculate the k-th order difference sequence using the following formulas (1) to (3);

[0044]

[0045] Step S23: Calculate the symmetric stability of the difference sequence based on the k-th order difference sequence; specifically: calculate the symmetric stability STD using the following formula (4);

[0046]

[0047] Alternatively: The specific step S23 is: calculate the asymmetric stability of the difference sequence based on the k-th order difference sequence; specifically: calculate the asymmetric stability UnSTD using the following formula (4); where: k1 is the degree of asymmetry;

[0048]

[0049] Preferably: k1 = k / 2;

[0050] Step S24: If the symmetric stability STD is close to a smaller value, delete the pressure value with the earliest time in the warning window from the warning window; thereby sliding out the segment corresponding to the pressure value with the earliest time from the warning window; of course, the larger the k value, the higher the requirement for stability, but it may reduce the construction parallelism;

[0051] Preferably: Perform secondary grouting on the segments that have slid out of the warning window, reinforce the outer periphery of the segments through secondary grouting, and maintain the shape of the inner periphery of the tunnel;

[0052] Preferably, the smaller value is 0; the way to determine whether the symmetry stability STD is close to the smaller value is to compare the difference between the symmetry stability STD and the smaller value with the deviation threshold to determine whether it is close to the smaller value;

[0053] Alternatively, if the asymmetry stability UnSTD is less than the stability threshold, the pressure value with the earliest time in the warning window is deleted from the warning window;

[0054] Preferably, the stability threshold is a preset value;

[0055] Step S3: Input the pressure value sequence in the warning window into the artificial intelligence model to obtain the target segment, and perform performance warning on the target segment;

[0056] The specific steps of step S3 are as follows:

[0057] Step S31: Input the pressure value sequence Pr t =(pr t,l ) into the first warning model to obtain the first warning result AT1; where: the input of the first warning model is L pressure values in the pressure value sequence; the output is L first warning values at1 of all corresponding segments l ; the first warning value is a probability value between 0 and 1; the higher the probability value, the higher the probability value that the corresponding segment is the target segment;

[0058] Step S32: Calculate the pressure difference sequence Input the pressure value sequence into the second warning model to obtain the second warning result; where: the input of the second warning model is L-1 pressure differences in the pressure difference sequence; the output is the second adjacent warning value ajAT1=(ajat1 l ), l∈2~L; the warning value is a probability value between 0 and 1; the higher the probability value, the higher the probability value that every two adjacent segments are the target segments; Split the second adjacent warning value to obtain L second warning values AT2=(at2 l ) corresponding to each segment, l∈1~L;

[0059] The splitting of the second adjacent warning value ajAT1=(ajat2 l ) to obtain the second warning value AT2=(at2 l ) corresponding to each segment is specifically: split using the following formulas (6)~(7);

[0060] at2 1 =ajat2 1+1 (6);

[0061] at2 l=(ajat2 1 +ajat2 1+1 ) / 2(7);

[0062] Preferably, both the first warning model and the second warning model are deep neural networks; further, the deep neural network is a neural network model with multiple hidden layers, and the neural network model includes an input layer, a hidden layer, and an output layer;

[0063] Preferably, the inputs of the first warning model and the second warning model further include the on-site environment and the segment orientation information; the on-site environment describes information such as the construction site geology and temperature; the segment orientation information describes the position of the segment in a complete ring; by adding the attributes of this dimension, the warning accuracy can be increased;

[0064] Step S33: If the segments corresponding to the maximum values of the first warning value and the second warning value are the same segment, then the segment corresponding to the maximum value is set as the target segment; otherwise, proceed to the next step;

[0065] Step S34: Calculate the first difference degree d1 of the first warning value and the second difference degree d2 of the second warning value based on formulas (8) - (9), where the first difference degree and the second difference degree are respectively used to indicate the differential warning capabilities of the first warning value and the second warning value for the target segment; when the differential warning capability is greater, the differential presentation capability of the warning value for the target segment is stronger, and vice versa; specifically: calculate the first difference degree d1 and the second difference degree d2 using the following formula; where: at1 1 is the mean value of the first warning index; at2 l is the mean value of the second warning index;

[0066]

[0067] Step S35: Determine the combined warning value based on the first warning value, the second warning value, the first difference degree, and the second difference degree; determine the target segment based on the combined warning value; specifically: calculate the combined warning value AT=(at 1 ), l ∈ 2 - L; take the segment corresponding to the maximum value of the combined warning value at 1 as the core target segment;

[0068]

[0069] Alternatively: Calculate the combined warning value AT=(at 1 ) based on the following formula, l ∈ 2 - L;

[0070]

[0071] Where: β1 and β 2 are the first adjustment coefficient and the second adjustment coefficient respectively;

[0072] Preferred: β 1 =β 2 =1;

[0073] Alternatively: determining the first adjustment coefficient and the second adjustment coefficient by an artificial intelligence model;

[0074] Step S36: cluster the L first warning values ​​to obtain L1 first clustering results; determine the segment corresponding to the element value in the first cluster with the largest element value and put it into the first target segment set to be selected; perform the same operation on the L second warning values ​​to obtain the second target segment set to be selected; determine the segment corresponding to the element of the intersection and / or union of the first target segment set to be selected and the second target segment set to be selected as the auxiliary target segment;

[0075] Step S37: determining the core target segment and the auxiliary target segment as the target segment; of course, only the core target segment can be selected as the target segment; assisting other detection means to determine the segment that needs synchronous interference;

[0076] The present invention simultaneously considers two different artificial intelligence models based on pressure value sequence and pressure difference sequence, expands the application scope of artificial intelligence models, and scientifically locates target segments and auxiliary target segments by combining the early warning results of artificial intelligence models through difference degree, providing data support basis for secondary shaping and artificial disturbance;

[0077] Step S4: disturbing and / or reshaping the target segment, and returning to step S2 after the disturbance and / or reshaping is completed; specifically: taking the core target segment as the operation center point and the auxiliary target segment as the operation range limit, disturbing the target segment to correct the deviation of the target segment, and adjusting the soil disturbance range through real-time monitoring data during the actual operation;

[0078] Preferably: using a high-pressure water gun to disturb the target segment, for example: digging and draining the back of the target segment;

[0079] The present invention monitors and warns tunnel segment performance in real time, makes timely adjustments to monitoring results, and performs secondary grouting and peripheral reinforcement on segments that need to be cleared of warnings, thereby ensuring the construction efficiency of large-diameter shield tunnels.

[0080] Based on the same inventive concept, the present invention proposes an artificial intelligence-based early warning system for the performance of large-diameter shield tunnel segments, the system comprising: a monitoring device, an early warning server; the sending device and the early warning server are connected via wireless communication;

[0081] Preferably, the monitoring device is arranged at the segment joint; the monitoring device is a pressure sensing device; the monitoring device is configured to monitor the segments at preset time intervals and at the monitoring time points, and transmit the collected monitoring data to the early warning server; the early warning server analyzes the monitoring data within the early warning window and issues corresponding early warnings.

[0082] Preferably, the early warning server can also be used to store, analyze and present historical monitoring data; continuously issue early warnings during the initial, middle and late stages of segment erection, for example, judge problems such as the convergence displacement, misalignment, position change, water leakage, and damage of the segments, which can obviously provide early warnings for the settlement early warning of the interval soil layer.

[0083] Based on the same inventive concept, the present invention also provides a processing unit, which can be connected to the receiving device and receive the data sent by the sending device in parallel.

[0084] Based on the same inventive concept, the present invention also provides an artificial intelligence-based segment performance early warning system for large-diameter shield tunnels. The system includes a sending device and multiple receiving devices. Each of the multiple receiving devices can implement data transmission and data verification by using the above error detection method.

[0085] In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0086] The terms "data processing apparatus", "data processing system", "user equipment", or "computing device" encompass all kinds of apparatus, devices, and machines for processing data, including, by way of example, programmable processors, computers, system-on-chips, or multiple of the foregoing or combinations thereof. The apparatus can include dedicated logic circuitry, such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits). In addition to hardware, the apparatus may also include code that creates an execution environment for the computer programs, for example, code that constitutes processor firmware, protocol stacks, database management systems, operating systems, cross-platform runtime environments, virtual machines, or combinations of one or more of the foregoing. The apparatus and the execution environment can implement various different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.

[0087] A computer program (which may also be referred to as a program, software, software application, script, or code) can be written in any form of programming language, including assembly or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may or may not correspond to a file in a file system. The program can be stored in a part of a file that holds other programs or data (such as one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple cooperating files (such as files that store one or more modules, subroutines, or portions of code). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0088] Those skilled in the art will appreciate that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0089] The present invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart illustrations and / or block diagrams, and combinations of flows and / or blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing device create means for implementing the functions specified in the flowFigure 1 means for the functions specified in one or more processes and / or boxes Figure 1 or in one or more boxes.

[0090] The embodiments in the present specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference may be made to each other.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that modifications or equivalent replacements can still be made to the specific implementation manners of the present invention. Any modification or equivalent replacement without departing from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A large-diameter shield tunnel segment performance early warning method based on artificial intelligence, characterized in that: include: Step S1: a pressure sensing device is arranged at the groove of the edge of the segment, and the segment is assembled and shaped so that the inner periphery of the tunnel is formed into a preset shape; Step S2: placing the pressure value of the pressure sensing device of the segment that has completed shaping into the early warning window; The warning window includes pressure values ​​of pressure sensing devices arranged in time sequence continuously; a monitoring time point arrives after a preset time interval, and the pressure value of each pressure sensing device is obtained at the monitoring time point t; based on the pressure value of the pressure sensing device in the current warning window t, it is determined whether the warning window needs to be updated; if so, the warning window is updated; wherein: t is the monitoring time point and its corresponding warning window number; Step S3: inputting the pressure value sequence in the warning window into the artificial intelligence model to obtain the target segment, and performing performance warning on the target segment; Step S4: Perform disturbance and / or secondary shaping on the target segment, and return to step S2 after completing the disturbance and / or secondary shaping.

2. The artificial intelligence-based large-diameter shield tunnel segment performance early warning method according to claim 1 is characterized in that: The pressure sensing device is arranged in the gap between the pipe sheets.

3. The artificial intelligence-based early warning method for large-diameter shield tunnel segment performance according to claim 2 is characterized in that: A groove is arranged at the gap between the pipe segments, and a pressure sensor is arranged in the groove.

4. The artificial intelligence-based large-diameter shield tunnel segment performance early warning method according to claim 3 is characterized in that: The pressure sensing device is connected to the early warning server in a wired or wireless manner and sends the monitored pressure value to the early warning server.

5. The artificial intelligence-based large-diameter shield tunnel segment performance early warning method according to claim 4 is characterized in that: The pressure sensing device is set with a unique identification according to the shaping order of its corresponding pipe segment.

6. The artificial intelligence-based large-diameter shield tunnel segment performance early warning method according to claim 4 is characterized in that: The step S2 specifically includes the following steps: Step S21: putting the pressure value of the pressure sensor device of the segment that has been shaped into an early warning window; the early warning window includes the pressure values ​​of the pressure sensor devices arranged in sequence; the pressure values ​​in the early warning window constitute a pressure value sequence Pr t =(pr t,l );where: t is the monitoring time point, pr t,l is the element value of the lth element in the warning window at the monitoring time point t; l∈1~L; L is the length of the warning window; Step S22: Calculate the k-order difference sequence using the following formulas (1) to (3); Step S23: Calculate the symmetric stability of the difference sequence based on the k-order difference sequence; specifically: calculate the symmetric stability STD using the following formula (4); Step S24: If the difference between the symmetric stability STD and the smaller value is less than the deviation threshold, the earliest pressure value in the warning window is deleted from the warning window; thereby the segment corresponding to the earliest pressure value slides out of the warning window.

7. An artificial intelligence-based early warning system for large-diameter shield tunnel segments, characterized in that: The system is used to implement the artificial intelligence-based large-diameter shield tunnel segment performance early warning method described in any one of claims 1 to 6.

8. An artificial intelligence-based early warning control platform for large-diameter shield tunnel segment performance, characterized in that: The platform is used to implement the artificial intelligence-based large-diameter shield tunnel segment performance early warning method described in any one of claims 1 to 6.

9. An artificial intelligence-based large-diameter shield tunnel segment performance early warning control server, characterized in that: The server is used to implement the artificial intelligence-based large-diameter shield tunnel segment performance early warning method described in any one of claims 1 to 6.

10. An artificial intelligence-based early warning control device for large-diameter shield tunnel segment performance, characterized in that: The device is used to implement the artificial intelligence-based large-diameter shield tunnel segment performance early warning method described in any one of claims 1 to 6.

Images