Bidirectional loading test device of tunnel supporting mechanism

Abstract

The invention discloses a bidirectional loading test device of a tunnel supporting mechanism, and relates to the technical field of loading test, the bidirectional loading test device comprises a test box, the inner side of the test box is provided with a support frame, and the inner side of the test box is respectively provided with a first cylinder and a second cylinder; a first loading plate and a second loading plate are installed at the output end of the first air cylinder and the output end of the second air cylinder respectively, an environment simulation system is arranged on the test box and comprises an environment monitoring module used for monitoring data of an experimental environment in the test box in real time, and the data comprise humidity, temperature, wind speed and illumination intensity; the control decision module is used for establishing a partial differential equation model to describe the interaction relation between humidity and temperature according to data transmitted by the environment monitoring module, the environment simulation system is arranged to quickly simulate the environment in the actual tunnel and then carry out the loading test, the environment simulation test can highly restore the environment in the actual tunnel, and the test efficiency is improved. And the accuracy and reliability of test results are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of loading tests, and particularly to a two-way loading test device for a tunnel support mechanism. Background Technique

[0002] The tunnel support structure refers to an artificial structure set up during and after the tunnel excavation process to ensure the stability of the tunnel surrounding rock, prevent the deformation or collapse of the surrounding rock. It plays a role in supporting the surrounding rock, controlling the deformation of the surrounding rock, and protecting the safety of the internal space of the tunnel. The design and construction of the support structure are key links in tunnel engineering, directly related to the long-term stability and use safety of the tunnel. The loading test is an important means to test and evaluate the performance of the tunnel support structure under simulated or actual stress conditions. Through the loading test, the rationality of the support structure design, construction quality, and safety can be verified to ensure that it can withstand the surrounding rock pressure and other external loads during actual use.

[0003] In actual use, the tunnel support structure is affected by the coupling of various factors, such as changes in material properties caused by temperature and humidity changes, the influence of wind speed and light on the support structure, etc. The conventional loading test is to directly apply a loading force to the support mechanism through a driving device for the test, which easily leads to a deviation between the test results and actual applications. Therefore, a two-way loading test device for a tunnel support mechanism is proposed. Summary of the Invention

[0004] The purpose of the present invention is to solve the drawback that in the prior art, the conventional loading test directly applies a loading force to the support mechanism through a driving device, which is different from the actual use environment and easily leads to a deviation between the test results and actual applications, and to propose a two-way loading test device for a tunnel support mechanism.

[0005] In order to achieve the above purpose, the present invention adopts the following technical scheme:

[0006] A two-way loading test device for a tunnel support mechanism, including a test chamber. A support frame is installed inside the test chamber. A first cylinder and a second cylinder are respectively installed inside the test chamber. A first loading plate and a second loading plate are respectively installed at the output ends of the first cylinder and the second cylinder. An environment simulation system is provided on the test chamber. The environment simulation system includes:

[0007] An environment monitoring module for real-time monitoring of data on the experimental environment inside the test chamber. The data includes humidity, temperature, wind speed, and light intensity;

[0008] A control decision-making module, which is used to establish a partial differential equation model based on the data transmitted by the environmental monitoring module to describe the interaction relationship between humidity and temperature, calculate the collaborative control problem of multiple environmental factors through an autoregressive integrated moving average model, and generate control instructions according to the calculation results;

[0009] A temperature regulation module, which adjusts the humidity of the experimental environment according to the instructions of the control decision-making module; a humidity regulation module, which adjusts the temperature of the experimental environment according to the instructions of the control decision-making module; a wind speed regulation module, which adjusts the wind speed of the experimental environment according to the instructions of the control decision-making module; a light regulation module, which adjusts the light intensity of the experimental environment according to the instructions of the control decision-making module;

[0010] A data recording and analysis module, which is used to record all the data during the experiment and conduct analysis and processing;

[0011] A real-time simulation and visualization module, which is used to simulate the stress state and deformation of the tunnel support structure during the loading process in real time and display it through visualization means;

[0012] A human-computer interaction module, which is used to provide an interaction interface between the user and the system.

[0013] The above technical solution further includes:

[0014] A transparent window is installed on the side of the test chamber.

[0015] The environmental monitoring module includes a humidity monitoring unit, a temperature monitoring unit, a wind speed monitoring unit, and a light monitoring unit. The humidity monitoring unit is responsible for collecting the humidity data of the experimental environment in the test chamber, the temperature monitoring unit is responsible for collecting the temperature data of the experimental environment in the test chamber, the wind speed monitoring unit is responsible for collecting the wind speed data of the experimental environment in the test chamber, and the light monitoring unit is responsible for collecting the light intensity data of the experimental environment in the test chamber.

[0016] The control decision-making module includes a temperature-humidity coupling model unit, a multivariable collaborative control algorithm unit, and a control instruction generation unit. The temperature-humidity coupling model unit establishes a partial differential equation model based on the principles of thermodynamics and fluid mechanics to describe the interaction relationship between humidity and temperature. The multivariable collaborative control algorithm unit processes the collaborative control problem of multiple environmental factors through an autoregressive integrated moving average model. The control instruction generation unit generates control instructions according to the calculation results of the multivariable collaborative control algorithm unit.

[0017] The implementation steps of the partial differential equation model are as follows:

[0018] Model construction:

[0019] A partial differential equation model based on the principles of thermodynamics and fluid mechanics is adopted, where the humidity is H(x,t), the temperature is T(x,t), and the wind speed is V(x,t), with x being the spatial position and t being the time;

[0020] Establish equations:

[0021] Humidity diffusion equation: where DH is the humidity diffusion coefficient, and S H (T, V) is the source term related to temperature and wind speed;

[0022] Temperature diffusion equation: where DT is the temperature diffusion coefficient, and S T (H, V) is the source term related to humidity and wind speed;

[0023] Numerical solution:

[0024] Using the finite difference method, the space is divided into grids and the time is divided into small time steps. The Crank - Nicolson method is adopted to solve the above partial differential equations for each time step and spatial grid point;

[0025] Model verification and calibration:

[0026] The collected data is divided into a training set and a test set. Using the training set data, the model parameters are adjusted to minimize the prediction error. Using the test set data to evaluate the model performance, the mean square error is calculated. According to the test results, the model parameters are further adjusted to improve the model accuracy;

[0027] Model integration:

[0028] Develop a model interface to enable it to receive real - time environmental data and output the predicted humidity and temperature values. Integrate the temperature - humidity coupling model to provide data support.

[0029] The implementation steps of the autoregressive integrated moving average model are as follows:

[0030] Determine the control objective:

[0031] Control objective: Clearly define the target values that humidity, temperature, wind speed, and light need to reach;

[0032] Establish a prediction model:

[0033] Select the autoregressive integrated moving average model and use historical environmental data to train the prediction model to enable it to have the ability to predict the changes in environmental parameters over a period of time in the future;

[0034] Design a control algorithm:

[0035] The model predictive control algorithm is adopted. At each control moment, an optimization problem is defined based on the output of the prediction model and the current environmental state, aiming to minimize the control error;

[0036] At each control moment k, according to the current environmental state x(k) and the output of the prediction model, an optimization problem is defined to minimize the control error and control cost:

[0037]

[0038] u(k): The control input vector, including control variables such as the power of the fan, lighting device, and humidifier, and the temperature setting value of the cooler;

[0039] x(k): The current environmental state vector, including state variables such as humidity, temperature, wind speed, and light intensity;

[0040] xtarget: The target environmental state vector;

[0041] N: The prediction horizon length;

[0042] J(x(k),u(k)): The optimization objective function, including a control error term and a control cost term;

[0043] Solve the optimization problem:

[0044] Solver selection: A quadratic programming solver or a nonlinear programming solver is selected. At each control moment, the optimization problem is solved to obtain the optimal control input;

[0045] Implementation of the control strategy:

[0046] The optimal control input is converted into a control instruction. In each control cycle, based on the real-time environmental data and the output of the prediction model, the optimal control input is calculated and sent to the corresponding device.

[0047] After receiving the control instruction issued by the control decision module, the temperature adjustment module adjusts the humidity of the experimental environment in the test chamber through the humidifier and dehumidifier. After receiving the control instruction issued by the control decision module, the humidity adjustment module adjusts the temperature of the experimental environment in the test chamber through the heater and cooler. After receiving the control instruction issued by the control decision module, the wind speed adjustment module adjusts the wind speed of the experimental environment in the test chamber through the fan. After receiving the control instruction issued by the control decision module, the light adjustment module adjusts the light intensity of the experimental environment through the lighting device.

[0048] The data recording and analysis module includes a data storage unit and a data analysis unit. The data storage unit is responsible for storing all the data collected during the experiment. The data analysis unit analyzes and processes the stored data through data analysis software to generate an experimental report.

[0049] The real-time simulation and visualization module includes a finite element analysis unit and a visualization display unit. The finite element analysis unit performs real-time simulation using a simulation algorithm, and the visualization display unit displays the simulation results through virtual reality technology.

[0050] The algorithm formula of the simulation algorithm is:

[0051] Ku = F

[0052] K: The total stiffness matrix, assembled from the stiffness matrices of all elements;

[0053] u: The nodal displacement vector, representing the displacements of all nodes;

[0054] F: The nodal force vector, representing the external forces on all nodes.

[0055] The present invention has the following beneficial effects:

[0056] In the present invention, by setting up an environment simulation system, the environment in the actual tunnel can be quickly simulated and then the installation test can be carried out. The simulated environment test can highly restore the environment in the actual tunnel, including various factors such as temperature, humidity, wind speed, and light, making the test results closer to the real situation and ensuring the accuracy and reliability of the test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a schematic diagram of the overall structure of a two-way loading test device for a tunnel support mechanism proposed by the present invention;

[0058] Figure 2 is a schematic diagram of the environment simulation system in the present invention.

[0059] In the figure: 1, test chamber; 2, transparent window; 3, support frame; 4, first cylinder; 5, first loading plate; 6, second cylinder; 7, second loading plate; 8, environment monitoring module; 9, control and decision-making module; 10, temperature adjustment module; 11, humidity adjustment module; 12, wind speed adjustment module; 13, light adjustment module; 14, data recording and analysis module; 15, real-time simulation and visualization module; 16, human-computer interaction module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0061] Such as Figure 1 - Figure 2As shown in the figure, a bidirectional loading test device for a tunnel support mechanism proposed by the present invention includes a test chamber 1. A support frame 3 is installed inside the test chamber 1. A first cylinder 4 and a second cylinder 6 are respectively installed inside the test chamber 1. A first loading plate 5 and a second loading plate 7 are respectively installed at the output ends of the first cylinder 4 and the second cylinder 6. An environment simulation system is provided on the test chamber 1, and the environment simulation system includes:

[0062] An environment monitoring module 8 for real-time monitoring of data on the experimental environment inside the test chamber 1, and the data includes humidity, temperature, wind speed, and light intensity;

[0063] A control decision-making module 9 for establishing a partial differential equation model to describe the interaction relationship between humidity and temperature based on the data transmitted by the environment monitoring module 8, calculating the cooperative control problem of multiple environmental factors through an autoregressive integrated moving average model, and generating a control instruction according to the calculation result;

[0064] A temperature adjustment module 10 for adjusting the humidity of the experimental environment according to the instruction of the control decision-making module 9; a humidity adjustment module 11 for adjusting the temperature of the experimental environment according to the instruction of the control decision-making module 9; a wind speed adjustment module 12 for adjusting the wind speed of the experimental environment according to the instruction of the control decision-making module 9; a light intensity adjustment module 13 for adjusting the light intensity of the experimental environment according to the instruction of the control decision-making module 9;

[0065] A data recording and analysis module 14 for recording all data during the experiment and performing analysis and processing;

[0066] A real-time simulation and visualization module 15 for real-time simulating the stress state and deformation of the tunnel support structure during the loading process and displaying it through visualization means;

[0067] A human-computer interaction module 16 for providing an interaction interface between the user and the system.

[0068] In this embodiment, when a loading test is required, first place the support mechanism on the support frame 3, and then the user sets the experimental parameters and control instructions through the human-machine interaction module 16. The environmental monitoring module 8 continuously collects the humidity, temperature, wind speed, and light intensity data of the experimental environment and transmits them to the control decision-making module 9. The control decision-making module 9 calculates the values of humidity, temperature, wind speed, and light intensity that need to be adjusted based on the received data and generates control instructions. The temperature adjustment module 10 receives the control instructions from the control decision-making module 9, adjusts the humidity of the experimental environment, and feeds back the adjustment result to the control decision-making module 9. The humidity adjustment module 11 receives the control instructions from the control decision-making module 9, adjusts the temperature of the experimental environment, and feeds back the adjustment result to the control decision-making module 9. The wind speed adjustment module 12 receives the control instructions from the control decision-making module 9, adjusts the wind speed of the experimental environment, and feeds back the adjustment result to the control decision-making module 9. The light adjustment module 13 receives the control instructions from the control decision-making module 9, adjusts the light intensity of the experimental environment, and feeds back the adjustment result to the control decision-making module 9. When the experimental environment in the test chamber 1 reaches the preset range, the second cylinder 6 can be started at this time. The second cylinder 6 drives the second loading plate 7 to move downward, so that the second loading plate 7 applies a loading force to the support mechanism. The first cylinder 4 can also be started, and the first cylinder 4 drives the first loading plate 5 to move, and the first loading plate 5 applies a loading force to the support mechanism, so as to conduct a loading test. At the same time, the data recording and analysis module 14 receives the data from each module, stores and analyzes them, and generates an experimental report. And the real-time simulation and visualization module 15 real-time simulates the stress state and deformation conditions of the tunnel support structure during the loading process according to the loading test situation. The user can wear an AR device and then display it through a visualization means. At the same time, the human-machine interaction module 16 displays various data and charts during the experiment, which is convenient for the user to monitor the experiment process and analyze the experiment results.

[0069] In one embodiment, a transparent window 2 is installed on the side of the test chamber 1, and the loading test can be observed with the naked eye.

[0070] In one embodiment, the environmental monitoring module 8 includes a humidity monitoring unit, a temperature monitoring unit, a wind speed monitoring unit, and a light monitoring unit. The humidity monitoring unit is responsible for collecting the humidity data of the experimental environment in the test chamber 1. The temperature monitoring unit is responsible for collecting the temperature data of the experimental environment in the test chamber 1. The wind speed monitoring unit is responsible for collecting the wind speed data of the experimental environment in the test chamber 1. The light monitoring unit is responsible for collecting the light intensity data of the experimental environment in the test chamber 1.

[0071] In one embodiment, the control decision-making module 9 includes a temperature-humidity coupling model unit, a multivariable collaborative control algorithm unit, and a control instruction generation unit. The temperature-humidity coupling model unit establishes a partial differential equation model based on the principles of thermodynamics and fluid mechanics to describe the interaction relationship between humidity and temperature. The multivariable collaborative control algorithm unit processes the collaborative control problem of multiple environmental factors through an autoregressive integrated moving average model. The control instruction generation unit generates control instructions according to the calculation results of the multivariable collaborative control algorithm unit.

[0072] In one embodiment, the implementation steps of the partial differential equation model are as follows:

[0073] Model construction:

[0074] Adopt a partial differential equation model based on the principles of thermodynamics and fluid mechanics, where the humidity is H(x,t), the temperature is T(x,t), and the wind speed is V(x,t), where x is the spatial position and t is the time;

[0075] Establish equations:

[0076] Humidity diffusion equation: where DH is the humidity diffusion coefficient, S H (T,V) is the source term related to temperature and wind speed;

[0077] Temperature diffusion equation: where DT is the temperature diffusion coefficient, S T (H,V) is the source term related to humidity and wind speed;

[0078] Numerical solution:

[0079] Use the finite difference method, divide the space into grids, divide the time into small time steps, and adopt the Crank-Nicolson method to solve the above partial differential equations for each time step and spatial grid point;

[0080] Model verification and calibration:

[0081] Divide the collected data into a training set and a test set. Use the training set data to adjust the model parameters to minimize the prediction error. Use the test set data to evaluate the model performance, calculate the mean square error, and further adjust the model parameters according to the test results;

[0082] Model integration:

[0083] Develop a model interface so that it can receive real-time environmental data and output the predicted humidity and temperature values, and integrate the temperature-humidity coupling model to provide data support.

[0084] In one embodiment, the implementation steps of the autoregressive integrated moving average model are as follows:

[0085] Determine the control objective:

[0086] Control objective: Define the target values that humidity, temperature, wind speed, and light intensity need to reach;

[0087] Establish a prediction model:

[0088] Select an autoregressive integrated moving average model and use historical environmental data to train the prediction model so that it has the ability to predict changes in environmental parameters over a period of time in the future;

[0089] Design a control algorithm:

[0090] Adopt a model predictive control algorithm. At each control moment, based on the prediction model output and the current environmental state, define an optimization problem aiming to minimize the control error;

[0091] At each control moment k, according to the current environmental state x(k) and the prediction model output, define an optimization problem to minimize the control error and control cost:

[0092]

[0093] u(k): Control input vector, including control variables such as the power of the fan, lighting equipment, and humidifier, and the temperature set value of the cooler;

[0094] x(k): Current environmental state vector, including state variables such as humidity, temperature, wind speed, and light intensity;

[0095] xtarget: Target environmental state vector;

[0096] N: Prediction horizon length;

[0097] J(x(k),u(k)): Optimization objective function, including control error term and control cost term;

[0098] Solve the optimization problem:

[0099] Solver selection: Select a quadratic programming solver or a nonlinear programming solver. At each control moment, solve the optimization problem to obtain the optimal control input;

[0100] Implement the control strategy:

[0101] Convert the optimal control input into a control command. At each control cycle, calculate the optimal control input based on the real-time environmental data and the prediction model output, and send it to the corresponding device.

[0102] In one embodiment, after receiving the control instruction sent by the control decision module 9, the temperature adjustment module 10 adjusts the humidity of the experimental environment in the test chamber 1 through a humidifier and a dehumidifier. After receiving the control instruction sent by the control decision module 9, the humidity adjustment module 11 adjusts the temperature of the experimental environment in the test chamber 1 through a heater and a cooler. After receiving the control instruction sent by the control decision module 9, the wind speed adjustment module 12 adjusts the wind speed of the experimental environment in the test chamber 1 through a fan. After receiving the control instruction sent by the control decision module 9, the light intensity adjustment module 13 adjusts the light intensity of the experimental environment through lighting equipment.

[0103] In one embodiment, the data recording and analysis module 14 includes a data storage unit and a data analysis unit. The data storage unit is responsible for storing all the data collected during the experiment. The data analysis unit analyzes and processes the stored data through data analysis software to generate an experiment report.

[0104] In one embodiment, the real-time simulation and visualization module 15 includes a finite element analysis unit and a visualization display unit. The finite element analysis unit uses simulation algorithms for real-time simulation, and the visualization display unit displays the simulation results through virtual reality technology.

[0105] In one embodiment, the algorithm formula of the simulation algorithm is:

[0106] Ku = F

[0107] K: total stiffness matrix, assembled from the stiffness matrices of all elements;

[0108] u: nodal displacement vector, representing the displacements of all nodes;

[0109] F: nodal force vector, representing the external forces on all nodes.

[0110] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A two-way loading test device for a tunnel support mechanism, comprising a test box (1), characterized in that, A support frame (3) is installed inside the test chamber (1). A first cylinder (4) and a second cylinder (6) are respectively installed inside the test chamber (1). A first loading plate (5) and a second loading plate (7) are respectively installed at the output ends of the first cylinder (4) and the second cylinder (6). An environmental simulation system is provided on the test chamber (1), and the environmental simulation system includes: An environmental monitoring module (8) for real-time monitoring of data of the experimental environment inside the test chamber (1), and the data includes humidity, temperature, wind speed, and light intensity; A control decision-making module (9) for establishing a partial differential equation model to describe the interaction relationship between humidity and temperature based on the data transmitted by the environmental monitoring module (8), calculating the collaborative control problem of multiple environmental factors through an autoregressive integrated moving average model, and generating a control instruction according to the calculation result; A temperature adjustment module (10) for adjusting the humidity of the experimental environment according to the instruction of the control decision-making module (9); a humidity adjustment module (11) for adjusting the temperature of the experimental environment according to the instruction of the control decision-making module (9); a wind speed adjustment module (12) for adjusting the wind speed of the experimental environment according to the instruction of the control decision-making module (9); a light intensity adjustment module (13) for adjusting the light intensity of the experimental environment according to the instruction of the control decision-making module (9); A data recording and analysis module (14) for recording all data during the experiment and performing analysis and processing; A real-time simulation and visualization module (15) for real-time simulating the stress state and deformation of the tunnel support structure during the loading process and displaying it through a visualization means; A human-computer interaction module (16) for providing an interaction interface between the user and the system.

2. The bidirectional loading test device for a tunnel support mechanism according to claim 1, wherein, A transparent window (2) is installed on the side of the test chamber (1).

3. The two-way loading test device for a tunnel support mechanism according to claim 2, characterized in that The environmental monitoring module (8) includes a humidity monitoring unit, a temperature monitoring unit, a wind speed monitoring unit, and a light intensity monitoring unit. The humidity monitoring unit is responsible for collecting humidity data of the experimental environment inside the test chamber (1), the temperature monitoring unit is responsible for collecting temperature data of the experimental environment inside the test chamber (1), the wind speed monitoring unit is responsible for collecting wind speed data of the experimental environment inside the test chamber (1), and the light intensity monitoring unit is responsible for collecting light intensity data of the experimental environment inside the test chamber (1).

4. The bidirectional loading test device for a tunnel support mechanism according to claim 1, characterized in that, The control decision-making module (9) includes a temperature-humidity coupling model unit, a multi-variable collaborative control algorithm unit, and a control instruction generation unit. The temperature-humidity coupling model unit establishes a partial differential equation model based on the principles of thermodynamics and fluid mechanics to describe the interaction relationship between humidity and temperature. The multi-variable collaborative control algorithm unit processes the collaborative control problem of multiple environmental factors through an autoregressive integrated moving average model. The control instruction generation unit generates a control instruction according to the calculation result of the multi-variable collaborative control algorithm unit.

5. The two-way loading test device for a tunnel support mechanism according to claim 4, characterized in that, The implementation steps of the partial differential equation model are as follows: Model construction: Adopt a partial differential equation model based on the principles of thermodynamics and fluid mechanics, where the humidity is H(x,t), the temperature is T(x,t), and the wind speed is V(x,t), where x is the spatial position and t is the time; Establish an equation: Humidity diffusion equation: where DH is the humidity diffusion coefficient, S H (T, V) is the source term related to temperature and wind speed; Temperature diffusion equation: where DT is the temperature diffusion coefficient, S T (H, V) is the source term related to humidity and wind speed; Numerical solution: Using the finite difference method, the space is divided into grids and the time is divided into small time steps. The Crank-Nicolson method is adopted to solve the above partial differential equation for each time step and spatial grid point; Model Validation and Calibration: The collected data is divided into a training set and a test set. Using the training set data, the model parameters are adjusted to minimize the prediction error. The test set data is used to evaluate the model performance, the mean square error is calculated, and according to the test results, the model parameters are further adjusted; Model Integration: A model interface is developed to enable it to receive real-time environmental data and output the predicted humidity and temperature values. The temperature-humidity coupling model is integrated to provide data support.

6. The two-way loading test device for a tunnel support mechanism according to claim 4, characterized in that, The implementation steps of the autoregressive integrated moving average model are as follows: Determine the control objective: Control objective: Clearly define the target values that humidity, temperature, wind speed, and light need to reach; Establish a prediction model: Select the autoregressive integrated moving average model and use historical environmental data to train the prediction model to enable it to have the ability to predict changes in environmental parameters over a period of time in the future; Design a control algorithm: Adopt the model predictive control algorithm. At each control moment, based on the prediction model output and the current environmental state, an optimization problem is defined to minimize the control error; At each control moment k, according to the current environmental state x(k) and the prediction model output, an optimization problem is defined to minimize the control error and control cost: u(k): Control input vector, including control variables such as the power of the fan, lighting equipment, humidifier, and the temperature setting value of the cooler; x(k): Current environmental state vector, including state variables such as humidity, temperature, wind speed, and light intensity; xtarget: Target environmental state vector; N: Prediction horizon length; J(x(k),u(k)): Optimization objective function, including a control error term and a control cost term; Solve the optimization problem: Solver selection: Select a quadratic programming solver or a nonlinear programming solver. At each control moment, solve the optimization problem to obtain the optimal control input; Implementation of the control strategy: Convert the optimal control input into a control instruction. In each control cycle, calculate the optimal control input based on the real-time environmental data and the prediction model output, and send it to the corresponding device.

7. The bidirectional loading test device for a tunnel support mechanism according to claim 1, characterized in that, After receiving the control instruction sent by the control decision module (9), the temperature adjustment module (10) adjusts the humidity of the experimental environment in the test chamber (1) through the humidifier and dehumidifier. After receiving the control instruction sent by the control decision module (9), the humidity adjustment module (11) adjusts the temperature of the experimental environment in the test chamber (1) through the heater and cooler. After receiving the control instruction sent by the control decision module (9), the wind speed adjustment module (12) adjusts the wind speed of the experimental environment in the test chamber (1) through the fan. After receiving the control instruction sent by the control decision module (9), the light adjustment module (13) adjusts the light intensity of the experimental environment through the lighting equipment.

8. A two-way loading test device for a tunnel support mechanism according to claim 1, characterized in that, The data recording and analysis module (14) includes a data storage unit and a data analysis unit. The data storage unit is responsible for storing all the data collected during the experiment. The data analysis unit analyzes and processes the stored data through data analysis software to generate an experimental report.

9. The bi-directional loading test device for a tunnel support mechanism according to claim 1, characterized in that, The real-time simulation and visualization module (15) includes a finite element analysis unit and a visualization display unit. The finite element analysis unit performs real-time simulation using a simulation algorithm, and the visualization display unit displays the simulation results through virtual reality technology.

10. The two-way loading test device for a tunnel support mechanism according to claim 1, characterized in that, The algorithm formula of the simulation algorithm is as follows: Ku = F K: total stiffness matrix, assembled from the stiffness matrices of all elements; u: nodal displacement vector, representing the displacements of all nodes; F: nodal force vector, representing the external forces on all nodes.

Images