Intelligent visual tunnel excavation model test device, system and method

Abstract

The invention discloses an intelligent visual tunnel excavation model test device, which comprises a model test box and a tunnel supporting structure, and is characterized in that the model test box is composed of a plurality of model box walls and a detachable model box wall; an acting force applying structure is fixed on the outer side of the model test box body through an acting force adjusting threaded rod and an acting force adjusting bolt, and an acting force display is arranged at one end of the acting force adjusting threaded rod; the tunnel supporting structure is formed by splicing a plurality of assemblies capable of being spliced, and splicing connectors are arranged on the connecting side walls of the assemblies capable of being spliced. An intelligent sensing device is arranged in the tunnel supporting structure. The invention further discloses an intelligent visual tunnel excavation model test system and method. According to the invention, a test scheme is conveniently formed, the action effect of the supporting structure in the tunnel excavation process is visually displayed, and the time cost and economic cost of the test are reduced.

Description

Technical Field

[0001] The present invention relates to an intelligent visual tunnel excavation model test device, system and method. Background Art

[0002] Tunnel model tests are an important means to study the stress and strain conditions of support structures and rock and soil masses during tunnel excavation, and are of guiding significance for the later adjustment and optimization of support control technologies. Traditional model test devices have certain limitations in actual operation. Their operation processes are complex and often require technicians to perform cumbersome settings and adjustments, resulting in low test efficiency. At the same time, traditional data monitoring means have problems of insufficient accuracy and large fluctuations. The monitored data collected lacks stability and is difficult to provide reliable data support for engineering decisions. This instability may stem from various factors such as insufficient equipment sensitivity and environmental interference. In addition, traditional means usually can only perform subsequent processing and analysis after exporting the monitored data. The analysis process not only takes time, but may also be difficult to reflect the actual dynamic changes during tunnel excavation in a timely manner due to data lag. On this basis, the traditional method also lacks a tunnel excavation dynamic visualization system and cannot intuitively present the real-time changes of key parameters such as stress and deformation during the construction process, restricting the engineering personnel's comprehensive control and risk warning capabilities of the construction state.

[0003] In view of the above problems, an intelligent visual tunnel excavation model test device, system and method are provided. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent visual tunnel excavation model test device, system and method to overcome the existing defects, which is convenient for forming a test plan, intuitively displays the action effect of the support structure during tunnel excavation, and reduces the time cost and economic cost of the test.

[0005] The technical solution to achieve the above purpose is: An intelligent visual tunnel excavation model test device of the present invention includes: a model test box and a tunnel support structure. The model test box is composed of multiple model box walls and a detachable model box wall. An acting force application structure is fixed to the outside of the model test box body through an acting force adjusting threaded rod and an acting force adjusting bolt, and an acting force display is provided at one end of the acting force adjusting threaded rod. The tunnel support structure is spliced by multiple splicing components. Among them, splicing interfaces are provided on the connecting side walls of the splicing components. An intelligent sensing device is built in the tunnel support structure.

[0006] Preferably, the model test box is made of Q235 steel plate material.

[0007] Preferably, the detachable model box wall is one of a horseshoe-shaped detachable box wall, a circular detachable box wall, and a straight-wall-shaped detachable box wall.

[0008] An intelligent visual tunnel excavation model test system according to the second aspect of the present invention includes: A test plan database for storing long-term test conditions and corresponding test plans; A test plan intelligent formulation module for calling a test plan according to the MTL multi-task learning deep learning algorithm and automatically formulating a test plan according to the current test conditions; A monitoring data processing module for processing and analyzing the monitored force data and sensor data according to the automatically formulated test plan to generate a dynamic monitoring diagram of the stress and strain of the tunnel support structure, a stress and strain curve diagram of a specified node, and a stress and strain cloud diagram of the rock and soil mass; A visual display module for visually displaying the dynamic monitoring diagram of the stress and strain of the tunnel support structure, the stress and strain curve diagram of a specified node, and the stress and strain cloud diagram of the rock and soil mass.

[0009] Preferably, in the test plan intelligent formulation module, a self-attention mechanism and a graph neural network are combined on the basis of MTL multi-task learning to capture the global dependencies between input features and model the relationships of input parameters; And a dynamic weighting strategy based on task uncertainty is introduced, including: The loss function is designed for each task , an uncertainty parameter is introduced, and the weight is dynamically adjusted: ; In the formula, is the weight of task .

[0010] An intelligent visual tunnel excavation model test method according to the third aspect of the present invention includes: Step S1, inputting the relevant parameters of the designed conditions into the test plan intelligent formulation module to form a test plan; Step S2, configuring the corresponding test rock and soil body according to the formed test plan, preparing the excavation method and the tunnel support structure; Step S3, connecting the intelligent visual tunnel excavation model test device to the intelligent visual tunnel excavation model test system and setting the tunneling parameters; Step S4, performing tunnel excavation simulation, and real-time monitoring the stress and strain of the support structure, and dynamically adjusting the tunneling parameters when necessary; Step S5, after the excavation is completed, perform test data analysis and summary.

[0011] Preferably, in the step S1, the relevant parameters include but are not limited to the mechanical properties of the rock and soil mass, the tunnel size, and the tunnel support structure parameters.

[0012] The beneficial effects of the present invention are as follows: By simplifying the operation process, improving the stability and accuracy of data monitoring, and introducing a real-time dynamic visualization system, the present invention not only significantly improves the test efficiency but also realizes the precise monitoring and risk warning capabilities for the entire process of tunnel excavation, making it more convenient to form a test plan, intuitively demonstrating the effect of the support structure during tunnel excavation, and reducing the time cost and economic cost of the test. Description of the Drawings

[0013] Figure 1 is a structural diagram of an intelligent visualization tunnel excavation model test device of the present invention; Figure 2 is a schematic diagram of the model box wall and the detachable model box wall of the present invention; Figure 3 is a schematic diagram of the acting force adjusting threaded rod, the acting force adjusting bolt, the acting force applying structure, and the acting force display of the present invention; Figure 4 is a schematic diagram of the horseshoe-shaped detachable box wall of the present invention; Figure 5 is a schematic diagram of the circular detachable box wall of the present invention; Figure 6 is a schematic diagram of the straight-wall-shaped detachable box wall of the present invention; Figure 7 is a schematic diagram of the tunnel support structure and the intelligent sensing device of the present invention; Figure 8 is a schematic diagram of the spliceable component and the assembly interface of the present invention; Figure 9 is a module diagram of an intelligent visualization tunnel excavation model test system of the present invention; Figure 10 is a flowchart of an intelligent visualization tunnel excavation model test method of the present invention.

[0014] In the figure: 1, model test box; 2, model box wall; 3, detachable model box wall; 4, acting force adjusting threaded rod; 5, acting force adjusting bolt; 6, acting force applying structure; 7, acting force display; 8, tunnel support structure; 9, spliceable component; 10, assembly interface; 11, intelligent sensing device; 31, horseshoe-shaped detachable box wall; 32, circular detachable box wall; 33, straight-wall-shaped detachable box wall; 100, test plan database; 200, intelligent test plan formulation module; 300, monitoring data processing module; 400, visualization display module. Detailed Embodiments

[0015] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] As Figure 1-8 shown, an intelligent visual tunnel excavation model test device includes: a model test box 1 and a tunnel support structure 8. The model test box 1 is composed of multiple model box walls 2 and a detachable model box wall 3. The outer side of the model test box body 1 is fixed with a force application structure 6 through a force adjustment screw rod 4 and a force adjustment bolt 5. One end of the force adjustment screw rod 4 is provided with a force display 7. The tunnel support structure 8 is spliced by multiple splicing components 9. Among them, the splicing interfaces 10 are arranged on the connecting side walls of the splicing components 9. The tunnel support structure 8 is internally provided with an intelligent sensing device 11.

[0018] In the embodiment, the model test box 1 is made of Q235 steel plate material.

[0019] In the embodiment, the detachable model box wall 3 is one of a horseshoe-shaped detachable box wall 31, a circular detachable box wall 32, and a straight-wall-shaped detachable box wall 33.

[0020] As Figure 9 shown, an intelligent visual tunnel excavation model test system includes: a test plan database 100, a test plan intelligent formulation module 200, a monitoring data processing module 300, and a visual display module 400.

[0021] The test plan database 100 is used to store long-term test conditions and corresponding test plans.

[0022] The test plan intelligent formulation module 200 is used to call the test plan according to the MTL multi-task learning deep learning algorithm and automatically formulate the test plan according to the current test conditions.

[0023] In the embodiment, the self-attention mechanism and the graph neural network are combined based on MTL multi-task learning to capture the global dependencies between input features and model the relationships of input parameters; And a dynamic weighting strategy based on task uncertainty is introduced, including: The loss function is designed to introduce an uncertainty parameter for each task to dynamically adjust the weight: ; In the formula, is the weight of task .

[0024] The monitoring data processing module 300 is used to process and analyze the monitored force data and sensor data according to the automatically formulated test plan, and generate the stress-strain dynamic monitoring diagram of the tunnel support structure 8, the stress-strain curve diagram of the specified node, and the stress-strain cloud diagram of the rock and soil mass.

[0025] The visualization display module 400 is used to visually display the stress-strain dynamic monitoring diagram of the tunnel support structure 8, the stress-strain curve diagram of the specified node, and the stress-strain cloud diagram of the rock and soil mass.

[0026] As Figure 10 shown, an intelligent visualization tunnel excavation model test method includes: Step S1, input the relevant parameters of the designed working condition into the test plan intelligent formulation module to form a test plan.

[0027] In the embodiment, the relevant parameters include but are not limited to the mechanical properties of the rock and soil mass, the tunnel size, and the parameters of the tunnel support structure 8 Step S2, configure the corresponding test rock and soil mass according to the formed test plan, and prepare the excavation method and the tunnel support structure 8.

[0028] Step S3, connect the intelligent visualization tunnel excavation model test device to the intelligent visualization tunnel excavation model test system, and set the tunneling parameters.

[0029] Step S4, conduct tunnel excavation simulation, and monitor the stress and strain of the support structure in real time, and dynamically adjust the tunneling parameters when necessary.

[0030] Step S5, after the excavation is completed, conduct test data analysis and summary.

[0031] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent visual tunnel excavation model test device, characterized in that, Comprising: A model test box (1) and a tunnel support structure (8), The model test box (1) is composed of multiple model box walls (2) and a detachable model box wall (3). The outer side of the model test box body (1) fixes a force application structure (6) through a force adjustment screw rod (4) and a force adjustment bolt (5), and a force display (7) is arranged at one end of the force adjustment screw rod (4); The tunnel support structure (8) is spliced by multiple splicing components (9). Among them, assembly interfaces (10) are arranged on the connecting side walls of the splicing components (9); An intelligent sensing device (11) is built in the tunnel support structure (8).

2. The intelligent visual tunnel excavation model test device according to claim 1, characterized in that, The model test box (1) is made of Q235 steel plate material.

3. The intelligent visual tunnel excavation model test device according to claim 1, characterized in that The detachable model box wall (3) adopts one of a horseshoe-shaped detachable box wall (31), a circular detachable box wall (32), and a straight-wall detachable box wall (33).

4. An intelligent visual tunnel excavation model test system, characterized in that, Comprising: A test plan database for storing long-term test conditions and corresponding test plans; A test plan intelligent formulation module for calling a test plan according to the MTL multi-task learning deep learning algorithm and automatically formulating a test plan according to the current test conditions; A monitoring data processing module for processing and analyzing the monitored force data and sensor data according to the automatically formulated test plan, and generating a stress-strain dynamic monitoring diagram of the tunnel support structure (8), a stress-strain curve diagram of a specified node, and a stress-strain cloud diagram of the rock and soil mass; A visualization display module for visually displaying the stress-strain dynamic monitoring diagram of the tunnel support structure (8), the stress-strain curve diagram of a specified node, and the stress-strain cloud diagram of the rock and soil mass.

5. An intelligent visual tunnel excavation model test system according to claim 4, characterized in that, In the test plan intelligent formulation module, a self-attention mechanism and a graph neural network are combined based on MTL multi-task learning to capture the global dependencies between input features and model the relationships of input parameters; And a dynamic weighting strategy based on task uncertainty is introduced, including: The loss function is designed for each task by introducing an uncertainty parameter to dynamically adjust the weights: ； In the formula, is the task weight.

6. An intelligent visual tunnel excavation model test method, characterized in that, Comprising: Step S1: Input the relevant parameters of the design conditions into the test plan intelligent formulation module to form a test plan; Step S2: Configure the corresponding test rock and soil body according to the formed test plan, and prepare the excavation method and the tunnel support structure (8); Step S3: Connect the intelligent visualization tunnel excavation model test device to the intelligent visualization tunnel excavation model test system and set the tunneling parameters; Step S4: Conduct tunnel excavation simulation, and monitor the stress and strain of the support structure in real time, and dynamically adjust the tunneling parameters when necessary; Step S5: After the excavation is completed, conduct test data analysis and summary.

7. The intelligent visual tunnel excavation model test method according to claim 6, characterized in that In the step S1, the relevant parameters include but are not limited to the mechanical properties of the rock and soil mass, the tunnel size, and the parameters of the tunnel support structure (8).

Images