Railway tunnel full-life-cycle model test system and test method considering train vibration

Abstract

The invention discloses a railway tunnel full-life-cycle model test system and test method considering train vibration, and relates to the technical field of railway tunnel engineering. The model test system adopts modular design and comprises a box frame module, a constant-pressure loading module, an excitation system module, a seepage system module and a monitoring system module. The test method comprises the steps of physical similar model laying, constant-pressure loading control, tunnel excavation and supporting, vibration loading and data monitoring analysis. By accurately simulating an initial stress field and train vibration loads in the construction and operation stages of the tunnel, dynamic monitoring of stress strain, deformation and damage processes of the tunnel surrounding rock and the lining structure in the whole life cycle is achieved. The device has the advantages of compact structure, modular design, high loading precision and stability, real simulation and the like, and a scientific basis can be provided for the fields of performance evaluation, structure optimization, reinforcement design and the like in the whole life cycle of the railway tunnel.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel model testing, and in particular to a railway tunnel full life cycle model testing system and a testing method taking train vibration into consideration. Background Art

[0002] By the end of 2023, China has put into operation a total of more than 45,000 km of high-speed railways, and has built 4,561 high-speed railway tunnels with a total length of 7,735 km, including 115 extra-long tunnels with a length of more than 10 km, about 1,471 km. According to the operation status of my country's high-speed railways, the permissible speed is usually between 250 and 350 km / h, and the structure is mainly ballastless track. Therefore, high-speed railway tunnels have extremely strict requirements for the deformation control of tunnel structures, especially the control of the flatness of the railway has reached the millimeter level.

[0003] According to the existing operational tunnel disease data in my country, tunnels built in soft surrounding rocks, especially under conditions of high ground stress and developed groundwater, often experience large deformation damage phenomena such as cracking of shotcrete layers, distortion of steel arch frames or grids, support encroachment, and bottom heaving during the construction phase. During the operation phase, under the repeated effects of high ground stress and train loads, tunnel bottom deformation diseases frequently occur, such as mud oozing out of the seam at the joint between the invert filling layer and the ballast slab, fractures in the side ditch walls, obvious arching of the track, and cracks in the ballast slab.

[0004] In response to the diseases caused by different reasons, measures such as adding pressure relief holes, anchoring rail slab cables (rods), and grouting to reinforce tunnel joints have been taken. These measures were taken passively after the disease occurred. The deformation of the bottom of some tunnels has been controlled, while the deformation of some tunnels is still continuing. The occurrence of these diseases has a great impact on the construction and operation of high-speed railway tunnels. High-speed railway trains are often limited in speed or even stopped because of this. These diseases not only seriously affect the normal operation of trains, but also pose a potential threat to the safety of passengers.

[0005] Model tests, with their intuitiveness, economy and high controllability, have shown great advantages in solving complex tunnel engineering problems. Not only can they truly, comprehensively, intuitively and accurately display the deformation and destruction process of the model, reducing the cost and risk of field tests, but they can also be repeated under strictly controlled conditions to improve research reliability. In addition, model tests are flexible and applicable, and can simulate and analyze various tunnel engineering problems, provide data support for theoretical research, and assist in engineering design verification.

[0006] However, the existing tunnel model test equipment and test methods mainly focus on improving the loading method of the model device boundary, and can often only simulate one aspect of the working conditions such as tunnel excavation, support or train load. It is impossible to comprehensively consider the impact of multiple factors (such as high ground stress, groundwater, train vibration, etc.) on tunnel stability. There is a lack of dynamic simulation of the whole process and complex working conditions. At the same time, the data collection is single, which leads to deviations in the results of the model test. Summary of the invention

[0007] Based on this, it is necessary to provide a railway tunnel full life cycle model test system and test method that takes train vibration into consideration, targeting the existing tunnel model test equipment and test methods, which lack dynamic simulation of the whole process and complex working conditions, and have single data collection, which leads to deviations in the results of model tests.

[0008] A railway tunnel full life cycle model test system considering train vibration, comprising:

[0009] A box frame module, comprising a box frame and a surrounding rock physics similarity model arranged in the box frame, wherein a tunnel physics similarity model is arranged in the surrounding rock physics similarity model;

[0010] A constant pressure loading module, used for applying pressure to the surrounding rock physical similarity model;

[0011] An excitation system module, used for outputting an excitation load to the tunnel physical similarity model;

[0012] A seepage system module, used to apply water pressure to the surrounding rock physical similarity model; and

[0013] A monitoring system module is used to monitor static data during the tunnel construction phase and dynamic data caused by train vibration during the tunnel operation phase. The monitoring system module includes multiple sensor units, and the multiple sensor units include a first sensor unit arranged in the surrounding rock physical similarity model, a second sensor unit arranged in the tunnel physical similarity model, and a third sensor unit arranged outside the surrounding rock physical similarity model.

[0014] In one embodiment, the constant pressure loading module includes a top constant pressure loading module and a side constant pressure loading module, the top constant pressure loading module is installed on the top of the box frame, and the side constant pressure loading module is installed on the side wall of the box frame.

[0015] In one embodiment, the top constant pressure loading module and the side constant pressure loading module both include a reaction frame, a servo electric cylinder and a loading plate, the reaction frame is installed on the box frame, the servo electric cylinder is installed on the reaction frame, the loading plate is connected to the servo electric cylinder, and the loading plate is abutted against the physical similarity model of the surrounding rock.

[0016] In one of the embodiments, the connection line of the servo electric cylinder is provided with an anti-electromagnetic interference structure.

[0017] In one embodiment, the surrounding rock physical similarity model includes primary support, secondary lining, model anchor rods, rail model and load distribution beam, the primary support is installed on the inner wall of the excavated tunnel, the secondary lining is installed on the inner side of the primary support, the model anchor rods are buried in the surrounding rock physical similarity model, and after the model anchor rods pass through the primary support and the secondary lining, they are fixed to the inner surface of the secondary lining, the rail model is installed at the bottom of the secondary lining, and the load distribution beam is fixedly connected to the rail model.

[0018] In one of the embodiments, the vibration excitation system module includes a vibration exciter and a fixed bracket, the fixed bracket is connected to the box frame, the vibration exciter is installed on the fixed bracket, and the vibration exciter acts on the tunnel physical similarity model.

[0019] In one embodiment, the monitoring system module also includes a computer, a dynamic signal analyzer and a static signal analyzer, the dynamic signal analyzer and the static signal analyzer are electrically connected to the computer, the dynamic signal analyzer is used to receive the dynamic data collected by the sensor unit, and the static signal analyzer is used to receive the static data collected by the sensor unit.

[0020] In one of the embodiments, the first sensor unit is used to monitor the surrounding rock pressure, the permeability pressure of the surrounding rock, the strain, deformation and acceleration of the surrounding rock, the second sensor unit is used to monitor the axial force, acceleration, displacement and strain of the tunnel, and the third sensor unit is used to monitor the strain and displacement of the surrounding rock surface and the temperature of the surrounding rock and lining.

[0021] In one embodiment, the first sensor unit includes an earth pressure box, a piezometer, an accelerometer, a strain brick and a distributed optical fiber. The earth pressure box, the piezometer and the strain brick are distributed in an array around the tunnel physical similarity model in the surrounding rock physical similarity model. The accelerometer is arranged in the surrounding rock physical similarity model at the bottom of the tunnel physical similarity model. The distributed optical fiber is arranged around the tunnel physical similarity model and bends and extends in the surrounding rock physical similarity model.

[0022] The second sensor unit includes an axial force meter, an accelerometer, a displacement meter and an FBG sensor, wherein the axial force meter is installed in the side wall of the tunnel physical similarity model, the accelerometer and the displacement meter are installed on the inner surface of the tunnel physical similarity model, and the FBG sensor is arranged on the inner surface of the tunnel physical similarity model;

[0023] The third sensor unit includes a DIC system and an infrared thermal imaging camera arranged on the front side of the surrounding rock physical similarity model. The DIC system is used to monitor the strain changes and displacements of the surrounding rock surface, and the infrared thermal imaging camera monitors the temperature changes of the surrounding rock and lining during construction and operation.

[0024] A railway tunnel full life cycle model test method considering train vibration includes the following steps:

[0025] Laying the surrounding rock physical similarity model layer by layer in the box frame, and burying the first sensor unit at a predetermined position during the laying process of the surrounding rock physical similarity model;

[0026] After the surrounding rock physical similarity model solidifies and hardens, a constant pressure loading module is installed on the box frame, a third sensor unit is designed on the front side of the surrounding rock physical similarity model, and a seepage system module maintains water pressure on the surrounding rock physical similarity model;

[0027] The constant pressure loading module is used to apply pressure to the surrounding rock physical similarity model, a tunnel is excavated in the surrounding rock physical similarity model, a tunnel physical similarity model is installed in the tunnel after the tunnel excavation is completed, and a second sensor unit is installed in the tunnel physical similarity model;

[0028] The excitation system module is installed on the box frame. The excitation system module outputs excitation loads to the tunnel physical similarity model cyclically according to the input customized train vibration waveform, so as to simulate the actual vibration conditions during tunnel operation.

[0029] The above-mentioned railway tunnel full life cycle model test system and test method considering train vibration, the monitoring system module is used to monitor the static data of the tunnel construction stage and the dynamic data caused by the train vibration during the tunnel operation stage, realizing the dynamic simulation of the whole process of railway tunnel from construction to operation. The sensor units of the monitoring system module are distributed in the surrounding rock, in the tunnel and outside the surrounding rock, and a variety of sensors and monitoring systems are used to comprehensively monitor the stress, strain, deformation, temperature and other parameters during the model test. The model test system and test method can ensure the accuracy of the simulation test results by dynamically simulating the whole process of tunnel construction to operation and comprehensively monitoring the multi-parameters of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the specific implementation of the present invention, the following will briefly introduce the drawings required for use in the specific implementation. In all the drawings, each element or part is not necessarily drawn according to the actual scale.

[0031] Figure 1It is an overall schematic diagram of the model test system of the present invention;

[0032] Figure 2 It is a schematic diagram of the front side of the box frame part of the present invention;

[0033] Figure 3 It is a schematic diagram of the rear side of the box frame part of the present invention;

[0034] Figure 4 It is a schematic diagram of the top constant pressure loading module of the present invention;

[0035] Figure 5 It is a side view of the top constant pressure loading module of the present invention;

[0036] Figure 6 is a schematic diagram of a servo loading control system of the present invention;

[0037] Figure 7 It is a front view of a physical similarity model of a tunnel of the present invention;

[0038] Figure 8 is a schematic diagram of the excitation system module of the present invention;

[0039] Fig. 9 A schematic diagram of the installation position of the vibration system module of the present invention;

[0040] Fig.10 is a schematic diagram of a seepage system module of the present invention;

[0041] Fig.11 It is a schematic diagram of the laying process of the similar material model of the present invention;

[0042] Fig.12 This is a schematic diagram of the layout of the monitoring sensors of the present invention;

[0043] Fig.13 It is a schematic diagram of the layout of the distributed optical fiber and FBG sensor of the present invention;

[0044] Fig.14 This is a schematic diagram of the layout of the control system of the digital image correlation method (DIC) of the present invention;

[0045] Fig.15 is a schematic diagram of a monitoring system module of the present invention;

[0046] Fig.16 is a flow chart of the model test method of the present invention;

[0047] Fig.17 The figure is a flow chart of the digital-physical fusion experimental method of the present invention.

[0048] Reference numerals:

[0049] 10-box frame module, 11-bench, 12-front plate frame, 121-observation plate, 122-door, 123-hinge, 124-elastic latch, 125-handle, 126-reinforcement beam, 13-rear plate frame, 131-detachable steel frame, 14-side plate frame, 20-constant pressure loading module, 202-top constant pressure loading module, 204-lateral constant pressure loading module, 21-reaction frame, 22-servo electric cylinder, 221-box, 222-cylinder, 223-reducer, 224-servo motor, 225-piston rod, 22 6-waterproof pressure sensor, 23-loading plate, 24-front flange, 25-guide device, 251-linear bearing, 252-guide shaft, 253-guide shaft support, 26-relay box, 30-excitation system module, 31-exciter, 32-fixed bracket, 321-column, 322-beam, 323-fixed plate, 324-mounting plate, 325-mounting bracket, 33-pressure sensor, 40-seepage system module, 41-water storage tank, 42-water tank bracket, 43-water inlet pipe, 44-drain pipe, 50-monitoring system module, 5 1-first sensor unit, 511-earth pressure box, 512-osmometer, 513-accelerometer, 514-strain brick, 515-distributed optical fiber, 52-second sensor unit, 521-axial force meter, 522-displacement meter, 523-FBG sensor, 53-third sensor unit, 531-speckle pattern production area, 532-strong light, 533-CCD industrial camera, 534-infrared thermal imaging camera, 54-computer, 55-static signal analyzer, 56-dynamic signal analyzer, 57-optical fiber sensing system, 58-FBG sensor monitoring system, 60-physical similarity model of surrounding rock, 70-physical similarity model of tunnel, 71-primary support, 72-secondary lining, 721-arch filling, 722-base plate, 723-track plate, 73-model anchor, 731-wire rope, 732-screw, 733-tray, 734-nut, 74-rail model, 75-load distribution beam, 80-servo loading control system, 90-vibration control system module, 91-vibration control computer, 92-digital signal generation system, 93-power amplifier. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the invention is not limited by the specific implementation disclosed below.

[0051] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0053] See also Figure 1 The railway tunnel full life cycle model test system considering train vibration in one embodiment includes a box frame module 10, a constant pressure loading module 20, an excitation system module 30, a seepage system module 40 and a monitoring system module 50. The box frame module 10 includes a box frame and a surrounding rock physical similarity model 60 arranged in the box frame, and a tunnel physical similarity model 70 is arranged in the surrounding rock physical similarity model 60.

[0054] Please also read Figure 2 In one embodiment, the box frame includes a stand 11, a front plate frame 12, a rear plate frame 13 and a side plate frame 14. The front plate frame 12 and the rear plate frame 13 are fixed on the stand 11 at intervals. The side plate frame 14 connects the front plate frame 12 and the rear plate frame 13 to form a space for accommodating the surrounding rock physical similarity model 60, and the stand 11 closes the bottom end of the space.

[0055] In one embodiment, a transparent observation panel 121 is provided on the front panel frame 12 to facilitate observation of the surrounding rock and tunnel in the box frame. An openable and closable door 122 is also provided on the front panel frame 12 to facilitate tunnel excavation and sensor deployment.

[0056] Specifically, the observation plate 121 can be made of an acrylic plate. Of course, the observation plate 121 can also be made of plates of other transparent materials. The door 122 is rotatably mounted on the observation plate 121 through a hinge 123. The door 122 is provided with an elastic latch 124 and a handle 125. The handle 125 can facilitate the opening and closing of the door 122, and the elastic latch 124 can close the door 122. Furthermore, during the laying and loading of similar materials, the door 122 is fixed by a reinforcing beam 126 to prevent excessive lateral deformation.

[0057] Please also read Figure 3In one embodiment, the rear plate frame 13 includes a plurality of detachable steel frames 131 distributed in a matrix, and the plurality of detachable steel frames 131 are detachably connected by bolts. The rear plate frame 13 is formed by assembling a plurality of detachable steel frames 131, which can facilitate the layer-by-layer laying and compaction of the surrounding rock physical similarity model 60 and the arrangement of sensors. The side plate frame 14 is a temporary baffle, which serves as a lateral template. After the surrounding rock physical similarity model 60 solidifies, the side plate frame 14 needs to be removed to facilitate the constant pressure loading module 20 to apply lateral pressure to the surrounding rock physical similarity model 60.

[0058] The constant pressure loading module 20 is installed on the box frame, and the constant pressure loading module 20 is used to apply pressure to the surrounding rock physical similarity model 60. In one embodiment, the constant pressure loading module 20 includes a top constant pressure loading module 202 and a lateral constant pressure loading module 204. The top constant pressure loading module 202 is installed on the top of the box frame, and is used to apply downward pressure to the surrounding rock physical similarity model 60, and the lateral constant pressure loading module 204 is installed on the side of the box frame, and is used to apply lateral pressure to the surrounding rock physical similarity model 60.

[0059] Please also read Figures 4 to 5 In one embodiment, the top constant pressure loading module 202 and the side constant pressure loading module 204 have the same structure, and both include a reaction frame 21, a servo electric cylinder 22, and a loading plate 23. The reaction frame 21 is mounted on the box frame, the servo electric cylinder 22 is mounted on the reaction frame 21, the loading plate 23 is connected to the servo electric cylinder 22, the loading plate 23 abuts against the surrounding rock physical similarity model 60, and the thrust generated by the servo electric cylinder 22 is transmitted through the loading plate 23 to generate pressure on the surrounding rock physical similarity model 60.

[0060] Specifically, the reaction frame 21 is connected to the front plate frame 12 and the rear plate frame 13 by bolts, and the servo electric cylinder 22 is fixed to the reaction frame 21 by the front flange 24. A guide device 25 for guiding the travel direction of the servo electric cylinder 22 is provided on the reaction frame 21. In one embodiment, the guide device 25 includes a linear bearing 251, a guide shaft 252 and a guide shaft support 253, the linear bearing 251 is installed on the reaction frame 21, the guide shaft support 253 is installed on the loading plate 23, the guide shaft 252 is slidably penetrated in the linear bearing 251, and the guide shaft 252 is connected to the guide shaft support 253, so as to guide the movement of the servo electric cylinder 22.

[0061] In one embodiment, the servo electric cylinder 22 includes a housing 221, a cylinder 222, a reducer 223 and a servo motor 224. The housing 221 is mounted on the top of the cylinder 222, the reducer 223 and the servo motor 224 are mounted on the side wall of the cylinder 222, and the output end of the servo motor 224 is connected to the reducer 223, and the reducer 223 is connected to the housing 221. The rotation of the servo motor 224 is transmitted to the housing 221 after being decelerated by the reducer 223. After the housing 221 realizes the steering of the transmission, it drives the screw nut in the cylinder 222 to rotate, realizes the up and down movement of the piston rod 225, and drives the loading plate 23 to move.

[0062] Compared with the traditional hydraulic loading reaction device, the reaction device of the present invention has a compact structure, reasonable force, and makes full use of the box frame to provide reaction force, without the need to set a large reaction frame 21 outside the force-applying mechanism. The servo electric cylinder 22 converts the rotational motion of the motor into the linear motion of the piston rod 225 through the screw and the screw nut. Compared with the hydraulic cylinder and the air cylinder, the servo electric cylinder 22 utilizes the closed-loop control characteristics of the servo motor 224, which can easily realize the precise control of thrust, speed and position, and achieve high-intensity, high-speed, high-precision and stable long-term operation.

[0063] Please also read Figure 6 In one embodiment, a relay box 26 is installed on the reaction frame 21, and the relay box 26 is electrically connected to the servo loading control system 80. The relay box 26 is used to control the synchronization and coordination of multiple electric cylinders during movement, and is used to control parameters such as the speed and force of the electric cylinders. In the top constant pressure loading module 202 and the lateral constant pressure loading module 204, the servo electric cylinder 22 can be loaded and unloaded independently, and can flexibly realize complex loading and unloading conditions, including the overall loading and local loading of the surrounding rock physical similarity model 60.

[0064] In one embodiment, a waterproof pressure sensor 226 is installed at the front end of the piston rod 225 of the servo electric cylinder 22. During the loading process, the servo loading control system 80 can accurately control the movement speed and position of the servo electric cylinder 22 through the pressure signal fed back by the waterproof pressure sensor 226, thereby improving the control accuracy and stability of the equipment.

[0065] In one embodiment, the servo electric cylinder 22 significantly improves the performance and efficiency of the device with its advantages of small size, high power, fast response speed and high precision. However, the problem of electromagnetic interference cannot be ignored, which may seriously affect the accuracy and normal operation of the device. The main cause of electromagnetic interference is the interaction of magnetic fields generated during the power supply of wires. Therefore, in this embodiment, the connecting line of the servo electric cylinder 22 is provided with an anti-electromagnetic interference structure.

[0066] Specifically, anti-interference magnetic rings are installed between the power lines of each servo electric cylinder 22, especially between strong wires, to reduce the magnetic field interference generated by the power lines. Anti-interference magnetic rings are installed on the servo signal lines of each servo electric cylinder 22 to reduce the electromagnetic interference on the signal lines. Wires and electrical components with anti-interference capabilities are selected, such as shielded cables, anti-interference filters, etc., to reduce the spread of electromagnetic interference.

[0067] Use shielded anti-interference plugs on the power cord and signal cord of each servo electric cylinder 22 to ensure good shielding between the plug and the socket. Install a grounded anti-interference terminal block in the control cabinet and connect all wires that need to be grounded to the terminal block to ensure that the equipment is well grounded. Ensure that the strong and weak current parts of all servo electric cylinders 22 are completely separated and arranged in independent lines to avoid electromagnetic interference.

[0068] Please also read Figure 7 In one embodiment, the tunnel physical similarity model 70 includes an initial support 71, a secondary lining 72, a model anchor 73, a rail model 74, and a load distribution beam 75. The initial support 71 uses a special smearing tool to evenly smear the similar material on the inner wall of the tunnel after tunnel excavation to form the initial support 71. The secondary lining 72 is installed on the inner side of the initial support 71. The secondary lining 72 is also provided with an invert filling 721, a base plate 722, and a track plate 723. The base plate 722 is installed on the invert filling 721, and the track plate 723 is provided on the base plate 722. The invert filling 721, the base plate 722, and the track plate 723 can be manufactured by 3D printing or cast-in-place prefabrication.

[0069] The model anchor rod 73 is buried in the surrounding rock physical similarity model 60, and the model anchor rod 73 passes through the initial support 71 and the secondary lining 72 and is fixed to the inner surface of the secondary lining 72. The rail model 74 is installed at the bottom of the secondary lining 72. Specifically, the rail model 74 is installed on the track plate 723, and the rail model 74 can be made by 3D printing. The load distribution beam 75 is fixedly connected to the rail model 74.

[0070] In one embodiment, the model anchor 73 includes a wire rope 731, a screw 732, a tray 733 and a nut 734. The screw 732 is inserted into the hole of the secondary lining 72. One end of the wire rope 731 is arranged in the surrounding rock, and the other end of the wire rope 731 passes through the screw 732 and is located in the secondary lining 72. After the end of the screw 732 located in the secondary lining 72 is sleeved with the tray 733, it is locked and fixed with the nut 734.

[0071] The model anchor rod 73 is made by printing. During the model laying process, the model anchor rod 73 is buried at a predetermined position in the surrounding rock physical similarity model 60, and a hole is drilled at a corresponding position of the secondary lining 72. During the test, the model anchor rod 73 is allowed to pass through the secondary lining 72 and be fixed on the inner surface of the secondary lining 72, and the nut 734 at the end of the model anchor rod 73 is quickly tightened to apply prestress.

[0072] Please also read Figure 8 The excitation system module 30 is installed on the box frame, the excitation system module 30 is connected to the tunnel physical similarity model 70, and the excitation system module 30 is used to output an excitation load to the tunnel physical similarity model 70. In one embodiment, the excitation system module 30 includes an exciter 31 and a fixed bracket 32, the fixed bracket 32 ​​is connected to the box frame, the exciter 31 is installed on the fixed bracket 32, and the exciter 31 acts on the tunnel physical similarity model 70.

[0073] Please also read Fig. 9 In one embodiment, the fixed bracket 32 ​​includes a column 321, a beam 322, a fixing plate 323, a mounting plate 324 and a mounting frame 325. The column 321 is mounted on the box frame. Specifically, the column 321 is mounted on the rear plate frame 13. The beam 322 is connected to the column 321 through the fixing plate 323, and the beam 322 extends into the tunnel physical similarity model 70. The mounting frame 325 is mounted on the beam 322 through the mounting plate 324, and the exciter 31 is mounted on the mounting frame 325. A pressure sensor 33 is connected to the vibration rod of the exciter 31, and the pressure sensor 33 is abutted against the load distribution beam 75, and the vibration load is transmitted to the rail model 74 and the sub-rail structure by the load distribution beam 75.

[0074] In one embodiment, the model test system further includes a vibration control system module 90, which is used to transmit a customized train vibration waveform to the exciter 31, and drive the exciter 31 to output the excitation load repeatedly. The exciter 31 can output different vibration load amplitudes and frequencies, and can truly simulate the actual vibration conditions of the train during tunnel operation.

[0075] Specifically, the vibration control system module 90 includes a vibration control computer 91, a digital signal generating system 92 and a power amplifier 93. The vibration control computer 91 is electrically connected to the digital signal generating system 92, and the digital signal generating system 92 is electrically connected to the power amplifier 93. The equivalent train load loading during the test is mainly achieved by the cooperation of the digital signal generating system 92, the power amplifier 93 and the exciter 31. The customized train vibration waveform is input into the vibration control computer 91, the digital signal generating system 92 generates an electrical signal and outputs it to the power amplifier 93, the power amplifier 93 amplifies the electrical signal and transmits it to the exciter 31, driving the exciter 31 to output the excitation load cyclically.

[0076] Please also read Fig.10 The seepage system module 40 is used to load water pressure on the surrounding rock physical similarity model 60. In one embodiment, the seepage system module 40 includes a water tank 41, a water tank bracket 42, a water inlet pipe 43 and a drain pipe 44. The water tank 41 is installed on the water tank bracket 42, the water inlet pipe 43 is fixed on the rear plate frame 13, the water inlet pipe 43 is located at the top of the surrounding rock physical similarity model 60, the water inlet pipe 43 is connected to the water tank 41 through a water supply pipe, and the drain pipe 44 is installed on the stand 11. The water pressure loading is achieved by controlling the water head height in the water tank 41. By placing the water tank 41 on the water tank bracket 42 at a certain height, the constant loading of the hydraulic pressure can be maintained.

[0077] Please also read Figures 11 to 14 The monitoring system module 50 is used to monitor static data in the tunnel construction stage and dynamic data caused by train vibration in the tunnel operation stage. The monitoring system module 50 includes a plurality of sensor units, including a first sensor unit 51 disposed in the surrounding rock physical similarity model 60, a second sensor unit 52 disposed in the tunnel physical similarity model 70, and a third sensor unit 53 disposed outside the surrounding rock physical similarity model 60.

[0078] Among them, the first sensor unit 51 is used to monitor the surrounding rock pressure, the permeability pressure of the surrounding rock, the surrounding rock strain, deformation and surrounding rock acceleration; the second sensor unit 52 is used to monitor the axial force, acceleration, displacement and strain of the tunnel; the third sensor unit 53 is used to monitor the strain and displacement of the surrounding rock surface and the temperature of the surrounding rock and lining.

[0079] In one embodiment, the first sensor unit 51 includes an earth pressure box 511, a piezometer 512, an accelerometer 513, a strain brick 514, and a distributed optical fiber 515. The earth pressure box 511, the piezometer 512, and the strain brick 514 are arrayed in the surrounding rock physical similarity model 60 along the circumferential direction of the tunnel. The accelerometer 513 is arranged in the surrounding rock physical similarity model 60 at the bottom of the tunnel physical similarity model 70, and the distributed optical fiber 515 is arranged around the tunnel physical similarity model 70 and bends and extends in the surrounding rock physical similarity model 60.

[0080] Among them, the soil pressure box 511 is used to monitor the change of surrounding rock pressure, obtain the interaction between the lining and the surrounding rock, and the dynamic response of the tunnel foundation soil and the attenuation law of the vibration wave. The piezometer 512 is used to monitor the osmotic pressure of the surrounding rock under the action of groundwater. The accelerometer 513 in the surrounding rock is used to monitor the acceleration response characteristics of the base surrounding rock structure under vibration load. The strain brick 514 is used to monitor the strain of the surrounding rock around the tunnel. The radial strain and tangential strain can be calculated by the measured strain, and then the radial stress and tangential stress of the surrounding rock can be calculated to study the change and distribution of the radial stress and tangential stress of the surrounding rock. The distributed optical fiber 515 is an OFDR distributed optical fiber. The distributed optical fiber 515 is arranged in an S shape and is used to monitor the deformation of the surrounding rock at different depths. At the same time, the distributed optical fiber 515 arranged in the outer ring of the tunnel is used to monitor the strain of the outer wall of the second lining of the tunnel.

[0081] In one embodiment, the second sensor unit 52 includes an axial force meter 521, an accelerometer 513, a displacement meter 522, and a FBG sensor 523. The axial force meter 521 is installed in the side wall of the tunnel physical similarity model 70, the accelerometer 513 and the displacement meter 522 are installed on the inner surface of the tunnel physical similarity model 70, and the FBG sensor 523 is arranged on the inner surface of the tunnel physical similarity model 70.

[0082] Specifically, the axial force meter 521 is installed on the tray 733 of the model anchor 73 to monitor the changes in the axial force of the anchor. The accelerometer 513 in the tunnel is arranged on the rails, the track plate 723 and the invert arch to monitor the transmission and attenuation of the vibration load from the top of the track downward. The displacement meter 522 is arranged on the arch crown, arch waist, side wall, invert arch and track plate 723 to monitor the settlement displacement of the tunnel arch crown, arch waist, side wall, and the uplift displacement value of the track plate 723 and the invert arch. The FBG sensor 523 is installed on the inner surface of the tunnel to monitor the strain changes of the inner wall of the tunnel.

[0083] In one embodiment, the third sensor unit 53 includes a DIC system and an infrared thermal imaging camera 534, which are arranged in front of the surrounding rock physical similarity model 60. The DIC system includes a speckle pattern production area 531, a strong light 532 and a CCD industrial camera 533, wherein the speckle pattern production area 531 is arranged on the surface of the surrounding rock physical similarity model 60, the strong light 532 is used to provide lighting for the speckle pattern production area 531, and the CCD industrial camera 533 is used to take pictures of the speckle pattern production area 531. Among them, the DIC system is used to monitor the strain change and displacement of the surrounding rock surface, and the infrared thermal imaging camera 534 is used to monitor the temperature change of the surrounding rock and lining during construction and operation.

[0084] Please also read Fig.15 In one embodiment, the monitoring system module 50 further includes a computer 54, a static signal analyzer 55, and a dynamic signal analyzer 56. The distributed optical fiber 515 is electrically connected to the optical fiber sensing system 57, and the FBG sensor 523 is electrically connected to the FBG sensing monitoring system 58. The dynamic signal analyzer 56, the static signal analyzer 55, the optical fiber sensing system 57, and the FBG sensing monitoring system 58 are electrically connected to the computer 54.

[0085] The dynamic signal analyzer 56 is used to receive the dynamic data collected by the sensor unit, and the static signal analyzer 55 is used to receive the static data collected by the sensor unit. Specifically, the soil pressure box 511, the osmometer 512, the axial force meter 521, the displacement meter 522 and the strain brick 514 are electrically connected to the static signal analyzer 55, and the soil pressure box 511, the osmometer 512, the axial force meter 521, the accelerometer 513, the displacement meter 522 and the strain brick 514 are electrically connected to the dynamic signal analyzer 56.

[0086] Therefore, the static data monitored during the tunnel construction phase include: surrounding rock pressure P r,s , osmotic pressure P w,s , Anchor bolt axial force F b,s , monitor the settlement displacement u of the tunnel vault, arch waist and side wall s , the strain of the surrounding rock around the tunnel ε r,s , deformation of surrounding rock at different depths δ r,s (z), strain ε of the outer wall of the tunnel secondary lining i,s , the strain of the tunnel outer wall ε o,s , the temperature of surrounding rock and lining during construction ΔT s change.

[0087] The dynamic data caused by train vibration during the tunnel operation phase include: the acceleration of the tunnel and the surrounding rock structure a str,d , dynamic pressure of surrounding rock P r,d , dynamic osmotic pressure Pw,d , dynamic anchor axial force F b,d , monitor the settlement and dynamic displacement of the tunnel vault, arch waist and side wall d 、Dynamic strain of surrounding rock around the tunnel ε r,d , deformation of surrounding rock at different depths δ r,d (z), dynamic strain ε of the outer wall of the tunnel secondary lining i,d 、Dynamic strain of the tunnel outer wall ε o,d , the temperature of surrounding rock and lining during construction ΔT d change.

[0088] See also Fig.16 The present invention also provides a railway tunnel full life cycle model test method taking train vibration into consideration. To implement the test method, the above-mentioned model test system is used. Specifically, the test method includes the following steps:

[0089] Step S110: laying the surrounding rock physical similarity model 60 layer by layer in the box frame, and burying the first sensor unit 51 at a predetermined position during the laying process of the surrounding rock physical similarity model 60.

[0090] Please also read Fig.11 Specifically, according to the physical similarity simulation test plan, the surrounding rock physical similarity model 60 is laid in the box frame, and the side plate frame 14 is used as a temporary baffle, which is bolted to the front plate frame 12 and the rear plate frame 13. The surrounding rock physical similarity model 60 is laid layer by layer, and the detachable steel frame 131 of the rear plate frame 13 is installed in blocks and fixed with bolts until the model is laid to the designed height.

[0091] At the same time, the door 122 in the front plate frame 12 is closed, and the reinforcement beam 126 is installed for reinforcement. During the model laying process, according to the test plan, the steel wire rope 731 of the model anchor 73 and the PVC pipe with holes are buried at the predetermined position in the surrounding rock physical similarity model 60. According to the test requirements, the earth pressure box 511, the piezometer 512, the accelerometer 513 and the strain brick 514 are buried in the surrounding rock physical similarity model 60, and the distributed optical fiber 515 is arranged in an "S" shape at different depths of the surrounding rock physical similarity model 60 to measure the strain and deformation of the surrounding rock physical similarity model 60 at different depths.

[0092] Step S120: After the surrounding rock physical similarity model 60 solidifies and hardens, a constant pressure loading module 20 is installed on the box frame, a third sensor unit 53 is designed on the front side of the surrounding rock physical similarity model 60, and the seepage system module 40 maintains water pressure on the surrounding rock physical similarity model 60.

[0093] Specifically, after the surrounding rock physics similarity model 60 solidifies and hardens in step S110, the side plate frame 14 is removed, and the top constant pressure loading module 202 and the side constant pressure loading module 204 are bolted to the front plate frame 12 and the rear plate frame 13. The reinforcement beam 126 is removed, the door 122 in the front plate frame 12 is opened, and a professional speckle making tool is used to make speckles on the speckle pattern making area 531 on the front side of the surrounding rock physics similarity model 60.

[0094] A strong light 532, a CCD industrial camera 533 and an infrared thermal imaging camera 534 are placed on the front side of the box frame module 10, and the earth pressure box 511, the piezometer 512 and the strain brick 514 buried in the surrounding rock physical similarity model 60 are electrically connected to the static signal analyzer 55. The distributed optical fiber 515 is electrically connected to the optical fiber sensing system 57 and connected to the computer 54. The water storage tank 41 is connected to the water inlet pipe 43 through the water supply pipe, and the water inlet pipe 43 is connected to the pre-buried PVC pipe with holes in the surrounding rock physical similarity model 60. The water storage tank 41 is placed on a water tank bracket 42 at a certain height, and the water head height in the water storage tank 41 is controlled to maintain a constant load of hydraulic pressure.

[0095] Step S130: using the constant pressure loading module 20 to apply pressure to the surrounding rock physical similarity model 60, excavating a tunnel in the surrounding rock physical similarity model 60, installing a tunnel physical similarity model 70 in the tunnel after the tunnel excavation is completed, and installing a second sensor unit 52 in the tunnel physical similarity model 70.

[0096] Specifically, according to the test plan, vertical loading pressure and horizontal loading pressure are set in the servo loading control system 80 to simulate the initial stress field. Through the precise control of the top constant pressure loading module 202 and the lateral constant pressure loading module 204, the boundary of the surrounding rock physical similarity model 60 is loaded in stages and a constant pressure is maintained.

[0097] After the model boundary loading is completed, the load is kept unchanged, and the system checks whether the model device is in a balanced state through the monitoring of the earth pressure box 511, the strain brick 514 and the distributed optical fiber 515. The door 122 in the front plate frame 12 is opened, and the tunnel is excavated in sections using the step method. The DIC system is used to monitor the displacement of the surrounding rock, and the infrared thermal imaging camera 534 is used to monitor the temperature change. The stress and strain changes of the tunnel surrounding rock are monitored in time during the excavation process.

[0098] After the tunnel excavation is completed, support is carried out in time, and a special 122 smearing tool is used to evenly apply similar materials on the inner wall of the tunnel to form an initial support 71. Then the prefabricated secondary lining 72 is installed. During the installation process, the bonding between the inner wall of the tunnel and the secondary lining 72 is ensured to ensure the integrity and compactness of the fit between the surrounding rock and the secondary lining 72. Before the installation of the secondary lining 72, holes are pre-drilled on the secondary lining 72 so that the model anchor rod 73 embedded in the surrounding rock physical similarity model 60 can pass through the secondary lining 72 and be fixed on the inner surface of the secondary lining 72. An axial force meter 521 is installed on the tray 733 of the model anchor rod 73 and electrically connected to the static signal analyzer 55. The axial force meter 521 can not only serve as the anchor end of the model anchor rod 73, but also monitor the tension value of the model anchor rod 73 during the entire experiment. In addition, prestress can be applied by tightening the nut 734 at the end of the model anchor rod 73, and the accuracy of the prestress can be determined by the stress monitoring shown by the axial force meter 521.

[0099] Before the installation of the secondary lining 72, a distributed optical fiber 515 is laid on the outer surface of the tunnel and electrically connected to the optical fiber sensing system 57. An FBG sensor 523 is laid on the inner surface of the tunnel and electrically connected to the FBG sensing monitoring system 58 to measure the strain of the inner and outer surfaces of the secondary lining 72 during the test. After the installation of the secondary lining 72, displacement meters 522 are laid on the tunnel vault, side walls and vault bottom to monitor the convergence deformation of the secondary lining 72 during the test. During the tunnel support process, the changes in the stress and strain of the surrounding rock, the stress and strain and convergence deformation of the secondary lining 72, the interaction between the surrounding rock and the lining, the axial force of the anchor cable, etc. are monitored in a timely manner.

[0100] Step S140: The excitation system module 30 is installed on the box frame. The excitation system module 30 outputs excitation loads to the tunnel physical similarity model 70 cyclically according to the input customized train vibration waveform, so as to simulate the actual vibration conditions during tunnel operation.

[0101] Specifically, after the monitoring data in step S130 reaches stability, the detachable steel frame 131 in the middle of the rear plate frame 13 is removed according to the relative position of the tunnel and the rear plate frame 13. The exciter 31 is installed on the rear plate frame 13 through the fixing bracket 32, and the exciter 31 extends into the tunnel along with the crossbeam 322.

[0102] The rail model 74 produced by 3D printing is installed on the track plate 723 of the secondary lining 72, and the load distribution beam 75 is fixedly installed on the rail model 74. The pressure sensor 33 at the front end of the vibration rod of the exciter 31 is abutted against the load distribution beam 75, and the pressure sensor 33 is electrically connected to the dynamic signal analyzer 56.

[0103] According to the test plan, accelerometers 513 and displacement meters 522 are arranged above the invert filling 721 of the secondary lining 72, above the track plate 723 and above the rail model 74, and the earth pressure box 511, piezometer 512, axial force meter 521, accelerometer 513, displacement meter 522 and strain brick 514 arranged in the above steps are electrically connected to the dynamic signal analyzer 56.

[0104] The vibration control computer 91, digital signal generation system 92, power amplifier 93 and exciter 31 of the vibration control system module 90 are electrically connected. Start the excitation system module 30, input the customized train vibration waveform into the vibration control computer 91, the digital signal generation system 92 generates an electrical signal and outputs it to the power amplifier 93, the power amplifier 93 amplifies the electrical signal and transmits it to the exciter 31, driving the exciter 31 to output the excitation load repeatedly. The exciter 31 can output different vibration load amplitudes, frequencies, and intervals, and can truly simulate the actual vibration conditions of different axle loads, different operating speeds, and different tracking intervals during tunnel operation.

[0105] By analyzing the dynamic monitoring data (acceleration, dynamic strain, dynamic earth pressure, dynamic seepage pressure, etc.) during vibration loading, we can obtain the dynamic response law of the load amplitude (i.e. train axle weight), loading frequency (i.e. train speed) and loading times on the stress and deformation of the surrounding rock and lining structure of the railway tunnel under long-term loading conditions, as well as the destruction process and influencing factors of the tunnel bottom drum deformation under the combined action of the initial stress field and train vibration.

[0106] The railway tunnel full life cycle model test system and test method considering train vibration have at least the following advantages:

[0107] 1. The monitoring system module 50 is used to monitor the static data of the tunnel construction stage and the dynamic data caused by the train vibration during the tunnel operation stage, realizing the dynamic simulation of the whole process of the railway tunnel from construction to operation. The sensor units of the monitoring system module 50 are distributed in the surrounding rock, in the tunnel and outside the surrounding rock, and a variety of sensors and monitoring systems are used to comprehensively monitor the stress, strain, deformation, temperature and other parameters during the model test. The model test system and test method can ensure the accuracy of the simulation test results by dynamically simulating the whole process of the tunnel from construction to operation and comprehensively monitoring the multi-parameters of the whole system.

[0108] 2. The modular design makes the model test system compact, lightweight, and space-saving. Through detachable connection methods such as bolts, the box frame module 10, constant pressure loading module 20, excitation system module 30, monitoring system module 50, and seepage system module 40 are flexibly assembled and disassembled, which is convenient for laying, loading, monitoring, and disassembly and cleaning of the model. At the same time, the modular design also improves the operating efficiency and stability of the equipment, and can fully simulate various complex working conditions of railway tunnels throughout their life cycle.

[0109] 3. The servo electric cylinder 22 is used as the loading device, and the closed-loop control characteristics of the servo motor 224 are used to achieve precise control of thrust, speed and position. Compared with the traditional hydraulic loading method, the present invention has the advantages of high strength, high speed, high precision and stable long-term operation, and can more accurately simulate the initial stress field of the tunnel and the stress and deformation changes of the tunnel surrounding rock-lining structure under long-term loading conditions.

[0110] 4. Through the vibration control system module 90, customized input and precise control of the train vibration waveform are realized. The exciter 31 can output different vibration load amplitudes, frequencies, and intervals, and can truly simulate the actual vibration conditions of different axle loads, different operating speeds, and different tracking intervals during tunnel operation. At the same time, combined with the analysis of dynamic monitoring data by the monitoring system module 50, the dynamic response laws of the load amplitude, loading frequency, and loading times under long-term loading conditions to the stress and deformation of the surrounding rock and lining structure of the railway tunnel can be obtained.

[0111] 5. The present invention not only considers the influence of train vibration on railway tunnels, but also realizes the simulation of groundwater in the full life cycle model test through the seepage system module 40. This enables the present invention to more comprehensively reflect the various complex working conditions of railway tunnels in the full life cycle, especially the effect of groundwater on the stress and deformation of tunnel surrounding rocks and lining structures and the influence on tunnel stability.

[0112] 6. A variety of sensors and monitoring systems are used to comprehensively monitor stress, strain, deformation, temperature and other parameters during the model test. Through the use of DIC system, infrared thermal imaging camera 534, static signal analyzer 55, dynamic signal analyzer 56, optical fiber sensing system 57 and FBG sensing monitoring system 58 and other equipment, real-time and high-precision monitoring of multiple parameters of tunnel surrounding rock and lining structure is achieved. The integrated application of these technologies not only improves the accuracy and reliability of monitoring, but also provides rich data support for in-depth analysis of the stress, deformation and failure process of the tunnel.

[0113] Furthermore, the model test method is relatively accurate and objective, but the physical test information that can be obtained is relatively small. The numerical simulation method can fully consider its internal interactions and obtain complete and comprehensive physical field information. Therefore, the digital-physical fusion test method can achieve accurate prediction of tunnel status, comprehensive evaluation of dynamic response, early warning and prevention of safety risks, and optimization of tunnel design and construction.

[0114] When using the digital-physical fusion test method, in the physical space, the fundamental purpose of the model test is to conduct targeted and in-depth exploration of key monitoring points with unknown complex performances to obtain their true response under the target state. From a theoretical point of view, if the key physical fields of the model test and the corresponding parts of the complete structural numerical model completely coincide, it can be considered that this result is consistent with the response of the overall structure in the actual scenario. However, the test measurement conditions are limited and it is difficult to meet the full-field comparison requirements. In addition, considering the errors in the model laying, loading and other links, it is difficult to achieve an ideal coincidence state between the digital-physical space. Therefore, representative and easy-to-measure key points can be selected as evaluation points. In the fusion test process, the difference between the key points of the digital-physical space is minimized based on interactive adjustment methods to achieve synchronous approximation to the real overall response of the tunnel.

[0115] Please also read Fig.17 The above-mentioned measured data can provide high-dimensional and complete data for the artificial intelligence model. The static data of tunnel construction phase monitoring + dynamic data of tunnel operation phase monitoring are selected to form the physical space, which is used as the data source to carry out the optimization and simulation of numerical simulation and artificial intelligence algorithm. The static data of construction phase monitoring drives the simulation construction of numerical space and builds the underlying data architecture of numerical simulation. The construction phase data and operation phase data are imported into the artificial intelligence algorithm as driving data for model training, and the physical and mechanical parameters are dynamically predicted. At the same time, the missing data of the physical space is supplemented in real time to ensure that the data dimension in each time state reaches the embedded value of the numerical space. The optimized, corrected and supplemented physical and mechanical parameters are obtained by calculating the error of the loss function, and the result is used to dynamically drive the numerical simulation. The mapping expression of the tunnel state and dynamic response is obtained through the fusion calculation of the numerical simulation.

[0116] In one implementation, the construction phase data and the operation phase data are imported as driving data into the artificial intelligence algorithm for model training, and the dynamic prediction of the physical and mechanical parameters can be specifically:

[0117] There are two types of outputs: one is the parameter prediction of the future time series and the complementary data of the current time series or the future time series. The output of the model is a comprehensive result, which covers various physical field information and dynamic responses of the tunnel in different time states (construction phase and operation phase). Specifically, it includes the stress distribution, deformation, vibration response (including dynamic data caused by train vibration), temperature field distribution, etc. of the tunnel. These outputs together constitute a comprehensive description of the overall state and dynamic behavior of the tunnel.

[0118] The physical and mechanical parameters include material parameters in the rock constitutive model (such as elastic modulus, Poisson's ratio, internal friction angle, permeability, compressive strength, tensile strength, shear strength, damage evolution equation and strength attenuation parameters, etc.), physical and mechanical parameters of the lining (such as elastic modulus, Poisson's ratio, compressive strength, tensile strength, shear strength, damage index of the lining material), boundary condition parameters (such as ground stress field, groundwater conditions), etc. These parameters describe the environmental conditions and boundary constraints of the tunnel, dynamic parameters (such as vibration frequency, amplitude, acceleration of train loads, etc., which describe the dynamic effects of trains on the tunnel during the operation stage.

[0119] In one embodiment, the steps for real-time filling of missing data in physical space are as follows: interpolation methods or model-based algorithms can be used to fill in missing data in a single time series, and forward filling, backward filling, or filling based on statistical methods or machine learning can be used to fill in missing data in multiple time series.

[0120] In one embodiment, the result is used to dynamically drive numerical simulation, and the process of obtaining the mapping expression of the tunnel state and dynamic response through the fusion calculation of the numerical simulation is specifically as follows:

[0121] Data integration and preprocessing: Update the corresponding parameters in the numerical simulation model according to the optimized, corrected and completed physical and mechanical parameters obtained through interactive adjustment in the digital-physical fusion experiment. These parameters may include the elastic modulus, Poisson's ratio, compressive / tensile / shear strength, damage factor, etc. of the material. Ensure that these parameters are numerically continuous and complete, and match the input format required for numerical simulation. Perform necessary unit conversion and scale adjustment on these parameters to meet the calculation requirements of the numerical simulation software.

[0122] Numerical simulation model construction: According to the actual situation of the tunnel project and the selection of numerical simulation methods (such as finite element method, finite difference method, discrete element method, etc.), a numerical simulation model of the tunnel and its surrounding environment is constructed. In the model, the geometry, size, material properties and boundary conditions of the tunnel are accurately set to ensure that the model can truly reflect the actual situation of the tunnel.

[0123] Parameter import and dynamic drive: Import the preprocessed physical and mechanical parameters into the numerical simulation model as input data for model calculation. These parameters may include the elastic modulus, Poisson's ratio, compressive strength, etc. of the surrounding rock, the thickness and material properties of the lining, and the train load during the tunnel operation stage.

[0124] In one embodiment, numerical simulation can adopt grid-based simulation methods (such as finite element method, finite difference method), particle / point-based simulation methods (such as discrete element method (DEM), smooth particle flow method (SPH) and material point method (MPM)) and block-based simulation methods. Artificial intelligence algorithms can adopt RNN-LSTM, ARIMA, multi-dimensional convolutional neural network models. The loss function can adopt MSE, MAE, Huber loss as a single-temporal loss function.

[0125] Specifically, the single-temporal loss function Huber Loss can be:

[0126]

[0127] Among them, y is the true value, f(x) is the predicted value, δ is the parameter of Huber loss, when the prediction deviation is less than δ, it uses the mean square error (MSE), when the prediction deviation is greater than δ, it uses the linear error. ,y) represents the average loss function over the entire time series, measuring the predicted value The difference between the true value y and It means that the average of T time steps is taken, and T represents the total length of the time series, that is, the total number of time steps. Represents the loss value at the t-th time step, comparing the t-th prediction value and the true value y (t) , represents the predicted value at the tth time step, y (t) Represents the true value at the t-th time step.

[0128] In one embodiment, a cross entropy loss function is used as a multi-temporal dynamic loss function, and training and learning can be performed based on the PINN framework to integrate multi-source data fusion models such as images, perception data, and digital graphics to carry out work.

[0129] 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A railway tunnel full life cycle model test system considering train vibration, characterized in that: include: A box frame module, comprising a box frame and a surrounding rock physics similarity model arranged in the box frame, wherein a tunnel physics similarity model is arranged in the surrounding rock physics similarity model; A constant pressure loading module, used for applying pressure to the surrounding rock physical similarity model; An excitation system module, used for outputting an excitation load to the tunnel physical similarity model; A seepage system module, used for applying water pressure to the surrounding rock physical similarity model; and A monitoring system module is used to monitor static data during the tunnel construction phase and dynamic data caused by train vibration during the tunnel operation phase. The monitoring system module includes multiple sensor units, and the multiple sensor units include a first sensor unit arranged in the surrounding rock physical similarity model, a second sensor unit arranged in the tunnel physical similarity model, and a third sensor unit arranged outside the surrounding rock physical similarity model.

2. The railway tunnel full life cycle model test system considering train vibration according to claim 1 is characterized in that: The constant pressure loading module includes a top constant pressure loading module and a side constant pressure loading module. The top constant pressure loading device module is installed on the top of the box frame, and the side constant pressure loading module is installed on the side wall of the box frame.

3. The railway tunnel full life cycle model test system considering train vibration according to claim 2 is characterized in that: The top constant pressure loading module and the side constant pressure loading module both include a reaction frame, a servo electric cylinder and a loading plate. The reaction frame is installed on the box frame, the servo electric cylinder is installed on the reaction frame, the loading plate is connected to the servo electric cylinder, and the loading plate abuts against the surrounding rock physical similarity model.

4. The railway tunnel full life cycle model test system considering train vibration according to claim 3 is characterized in that: The connecting line of the servo electric cylinder is provided with an anti-electromagnetic interference structure.

5. The railway tunnel full life cycle model test system considering train vibration according to claim 1 is characterized in that: The surrounding rock physical similarity model includes initial support, secondary lining, model anchor rods, rail model and load distribution beam. The initial support is installed on the inner wall of the excavated tunnel, the secondary lining is installed on the inner side of the initial support, the model anchor rods are buried in the surrounding rock physical similarity model, and after the model anchor rods pass through the initial support and the secondary lining, they are fixed on the inner surface of the secondary lining, the rail model is installed at the bottom of the secondary lining, and the load distribution beam is fixedly connected to the rail model.

6. The railway tunnel full life cycle model test system considering train vibration according to claim 1 is characterized in that: The vibration excitation system module includes a vibration exciter and a fixed bracket, wherein the fixed bracket is connected to the box frame, the vibration exciter is installed on the fixed bracket, and the vibration exciter acts on the tunnel physical similarity model.

7. The railway tunnel full life cycle model test system considering train vibration according to claim 1 is characterized in that: The monitoring system module also includes a computer, a dynamic signal analyzer and a static signal analyzer. The dynamic signal analyzer and the static signal analyzer are electrically connected to the computer. The dynamic signal analyzer is used to receive the dynamic data collected by the sensor unit, and the static signal analyzer is used to receive the static data collected by the sensor unit.

8. The railway tunnel full life cycle model test system considering train vibration according to claim 1 is characterized in that: The first sensor unit is used to monitor the surrounding rock pressure, the seepage pressure of the surrounding rock, the surrounding rock strain, deformation and surrounding rock acceleration; the second sensor unit is used to monitor the axial force, acceleration, displacement and strain of the tunnel; the third sensor unit is used to monitor the strain and displacement of the surrounding rock surface and the temperature of the surrounding rock and lining.

9. The railway tunnel full life cycle model test system considering train vibration according to claim 8, characterized in that: The first sensor unit includes an earth pressure box, a piezometer, an accelerometer, a strain brick and a distributed optical fiber. The earth pressure box, the piezometer and the strain brick are arrayed and distributed in the surrounding rock physical similarity model around the tunnel physical similarity model. The accelerometer is arranged in the surrounding rock physical similarity model at the bottom of the tunnel physical similarity model. The distributed optical fiber is arranged around the tunnel physical similarity model and bends and extends in the surrounding rock physical similarity model. The second sensor unit includes an axial force meter, an accelerometer, a displacement meter and an FBG sensor, wherein the axial force meter is installed in the side wall of the tunnel physical similarity model, the accelerometer and the displacement meter are installed on the inner surface of the tunnel physical similarity model, and the FBG sensor is arranged on the inner surface of the tunnel physical similarity model; The third sensor unit includes a DIC system and an infrared thermal imaging camera arranged on the front side of the surrounding rock physical similarity model. The DIC system is used to monitor the strain changes and displacements of the surrounding rock surface, and the infrared thermal imaging camera monitors the temperature changes of the surrounding rock and lining during construction and operation.

10. A railway tunnel full life cycle model test method considering train vibration, characterized in that: The steps include: Laying the surrounding rock physical similarity model layer by layer in the box frame, and burying the first sensor unit at a predetermined position during the laying process of the surrounding rock physical similarity model; After the surrounding rock physical similarity model solidifies and hardens, a constant pressure loading module is installed on the box frame, a third sensor unit is designed on the front side of the surrounding rock physical similarity model, and a seepage system module maintains water pressure on the surrounding rock physical similarity model; The constant pressure loading module is used to apply pressure to the surrounding rock physical similarity model, a tunnel is excavated in the surrounding rock physical similarity model, a tunnel physical similarity model is installed in the tunnel after the tunnel excavation is completed, and a second sensor unit is installed in the tunnel physical similarity model; The excitation system module is installed on the box frame. The excitation system module outputs excitation loads to the tunnel physical similarity model cyclically according to the input customized train vibration waveform, so as to simulate the actual vibration conditions during tunnel operation.

Images