High-cold high-altitude tunnel lining-heating-thermal insulation integrated self-adaptive green intelligent anti-freezing regulation method

Abstract

The application provides a high-cold high-altitude tunnel lining-heating-thermal insulation integrated self-adaptive green intelligent anti-freezing regulation method, comprising: constructing a material parameter database; constructing a tunnel model and a tunnel heat balance model, conducting a scale experiment on the tunnel model to obtain an experimental result, conducting multi-parameter coupling numerical simulation on the tunnel heat balance model to obtain a simulation result, comparing the experimental result with the simulation result, verifying and expanding the environmental parameters of the tunnel heat balance model; matching the tunnel model with the environmental parameters to obtain an optimized interval of material parameters and thicknesses of each layer of the tunnel; constructing a heat load prediction model to obtain required heat exchange loads under different environmental parameters; obtaining on-site measurement data, constructing a data-physical dual driving model, and calculating heating power and flow parameters, so that the application mines the nonlinear relationship between environmental parameters and heat loads, improves the prediction effect and adaptability, significantly reduces the anti-freezing energy consumption of the tunnel, and improves the efficiency of the frost damage treatment.

Description

Technical Field

[0001] This invention relates to the field of ground source heat pump system optimization technology, specifically to an adaptive, green, intelligent antifreeze control method for integrated heating and insulation of tunnel lining in cold and high-altitude areas. Background Technology

[0002] Tunnels traversing high-altitude and frigid regions are susceptible to frost damage at their entrances. Traditional solutions often involve short-term protection using insulation materials or active protection via electric heating, which are conservative and inefficient, and consume significant energy when using electric heating. However, tunnels using ground source heat pumps can utilize the higher ground temperature in the tunnel's midsection to insulate the tunnel entrance, providing passive protection. Furthermore, only a small amount of energy is needed for circulation to achieve the same effect as electric heating. Using a ground source heat pump requires adding a heating layer to the tunnel lining to achieve heat collection and dissipation. To achieve the desired effect, reliable prediction of the tunnel's heat load is essential, along with timely adjustments to the circulation based on the heat load, to avoid falling into the trap of conservative design and excessive energy consumption.

[0003] Currently, the use of ground source heat pumps for tunnel protection in high-altitude and cold regions still faces the following problems: First, the tunnel's heat load is affected by various environmental parameters such as temperature and geological conditions, making it difficult to predict accurately and leading to conservative initial designs. Second, the addition of ground source heat pumps makes the tunnel structure more complex, and the thermal effects between layers require consideration of more dimensions. In addition, existing numerical simulation models (such as finite element analysis) are unable to dynamically quantify the impact of different geological conditions on the tunnel's heat load. Finally, there is currently no intelligent assessment and control system that can combine with actual data for rapid and timely judgment, and decision-making relies on prior experience, resulting in overly conservative and inefficient designs. Summary of the Invention

[0004] This invention is made to solve the above-mentioned problems, and aims to provide an adaptive, green, intelligent antifreeze control method for tunnel lining, heating, and insulation in high-altitude and cold regions.

[0005] This invention provides an integrated adaptive, green, and intelligent anti-freezing control method for lining, heating, and insulation of tunnels in high-altitude and cold regions. The method includes the following steps: Step S1, constructing a material parameter database for the multi-layered structure of high-altitude and cold-region tunnels; Step S2, using the material parameter database to construct a tunnel model and a tunnel thermal equilibrium model, conducting scaled-down experiments on the tunnel model to obtain experimental results, performing multi-parameter coupled numerical simulations on the tunnel thermal equilibrium model to obtain simulation results, comparing the experimental results with the simulation results to verify and expand the environmental parameters of the tunnel thermal equilibrium model, and obtaining the temperature distribution of the tunnel model; Step S3, inputting material parameters and tunnel thermal equilibrium parameters into the tunnel thermal equilibrium model. Step S4: Based on the material parameter database of the multi-layer structure of the high-altitude tunnel, a heat load prediction model is constructed to obtain the required heat exchange load under different environmental parameters. Step S5: On-site measurement data is acquired, including environmental parameters and temperature distribution. A data-physical dual-drive model is constructed based on the tunnel thermal equilibrium model and the heat load prediction model, and integrated with the cloud intelligent platform. The on-site measurement data is input into the data-physical dual-drive model, and the environmental parameters and temperature distribution of the data-physical dual-drive model are updated in real time. The heating power and flow parameters are calculated online.

[0006] The adaptive green intelligent antifreeze control method for high-altitude and cold-climate tunnel lining-heating-insulation integration provided by this invention may also have the following features: the material parameter database of the multi-layer structure of high-altitude and cold-climate tunnel is constructed through laboratory testing, literature integration and collection of material thermophysical parameters.

[0007] The adaptive green intelligent antifreeze control method for the integrated heating and insulation of high-altitude and cold-climate tunnel lining provided by this invention may also have the following feature: the environmental parameters of the material parameter database of the multi-layer structure of the high-altitude and cold-climate tunnel are cleaned and processed.

[0008] The integrated adaptive green intelligent anti-freezing control method for tunnel lining-heating-insulation in high-altitude and cold regions provided by this invention may also have the following features: the tunnel model is made of transparent acrylic material, the outer geotextile material is used to simulate the heating and insulation layers, the interior is filled with sand and gravel mixture to simulate the stratum material, and a fluid circulation system is set up to simulate the heat exchange process. Temperature sensors and heat flow meters are set up to monitor the temperature distribution and heat flow changes of the tunnel model.

[0009] The integrated adaptive green intelligent antifreeze control method for high-altitude and cold-climate tunnel lining-heating-insulation provided by this invention may also have the following features: the multi-parameter coupled numerical simulation uses numerical simulation software, configures multi-physics field coupling analysis, establishes a tunnel thermal equilibrium model based on the material parameter database of the multi-layer structure of high-altitude and cold tunnels, simulates the heat transfer process, and sets boundary conditions, including constant heat flow input and adiabatic boundary.

[0010] The adaptive green intelligent antifreeze control method for the integrated lining-heating-insulation of high-altitude and cold-climate tunnels provided by this invention may also have the following features: the heat load prediction model is constructed by learning the nonlinear relationship between environmental parameters and heat exchange load from the material parameter database of the multi-layer structure of high-altitude and cold-climate tunnels using machine learning algorithms.

[0011] The integrated adaptive green intelligent antifreeze control method for tunnel lining-heating-insulation in cold and high-altitude regions provided by this invention may also have the following features: the machine learning algorithm includes random forest and neural network.

[0012] The integrated adaptive green intelligent antifreeze control method for tunnel lining-heating-insulation in cold and high-altitude regions provided by this invention may also have the following features: the SHAP value is applied to analyze the heat load prediction model, quantify the specific contribution of environmental parameters to the heat exchange load, and determine the key environmental parameters.

[0013] The integrated adaptive green intelligent antifreeze control method for tunnel lining-heating-insulation in cold and high-altitude regions provided by this invention may also have the following features: the cloud intelligent platform includes an intelligent database and a cloud computing platform, and the intelligent database supports real-time data updates and multi-terminal access.

[0014] The role and effect of invention

[0015] The adaptive green intelligent antifreeze control method for high-altitude and cold-climate tunnel lining-heating-insulation integration according to the present invention includes: Step S1, constructing a material parameter database for the multi-layer structure of a high-altitude and cold-climate tunnel; Step S2, using the material parameter database to construct a tunnel model and a tunnel thermal equilibrium model, conducting scaled-down experiments on the tunnel model to obtain experimental results, performing multi-parameter coupled numerical simulations on the tunnel thermal equilibrium model to obtain simulation results, comparing the experimental results with the simulation results, verifying and expanding the environmental parameters of the tunnel thermal equilibrium model, and obtaining the temperature distribution of the tunnel model; Step S3, inputting material parameters and the thickness of each tunnel layer into the tunnel thermal equilibrium model, matching the tunnel model with environmental parameters, and obtaining the optimization range of material parameters and the thickness of each tunnel layer; S4. Based on the material parameter database of the multi-layered structure of high-altitude tunnels, a heat load prediction model is constructed to obtain the required heat exchange load under different environmental parameters. S5. On-site measurement data is acquired, including environmental parameters and temperature distribution. A data-physical dual-drive model is constructed based on the tunnel thermal equilibrium model and the heat load prediction model, and integrated with a cloud-based intelligent platform. The on-site measurement data is input into the data-physical dual-drive model, which updates the environmental parameters and temperature distribution in real time. Heating power and flow parameters are calculated online. Therefore, the integrated adaptive green intelligent anti-freezing control method for high-altitude and cold-climate tunnel lining-heating-insulation of this invention deeply explores the nonlinear relationship between environmental parameters and heat load, constructs a heat load prediction model, and improves prediction effectiveness and adaptability. It significantly reduces the anti-freezing energy consumption of high-altitude and cold-climate tunnels and improves the efficiency of controlling frost damage in high-altitude and cold-climate tunnels. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the process of the integrated adaptive green intelligent antifreeze control method for tunnel lining-heating-insulation in cold and high-altitude regions according to an embodiment of the present invention. Detailed Implementation

[0017] To make the technical means, creative features, objectives and effects of this invention easy to understand, the following embodiments, in conjunction with the accompanying drawings, specifically illustrate the adaptive green intelligent antifreeze control method for tunnel lining-heating-insulation integration in cold and high-altitude regions.

[0018] Example

[0019] Figure 1 This is a schematic diagram of the process of the integrated adaptive green intelligent antifreeze control method for tunnel lining-heating-insulation in cold and high-altitude regions according to an embodiment of the present invention.

[0020] like Figure 1 As shown, this embodiment provides an integrated adaptive, green, and intelligent antifreeze control method for tunnel lining, heating, and insulation in cold and high-altitude environments, including:

[0021] Step S1: Construct a material parameter database for the multi-layered structure of high-altitude tunnels.

[0022] The environmental parameters of the material parameter database for multi-layered structures in high-altitude and cold-weather tunnels were cleaned and processed. This database was constructed through laboratory testing, literature review, and collection of material thermophysical properties.

[0023] When collecting thermal property parameters of materials, samples of tunnel lining, surrounding rock, insulation materials, heat exchange pipes and geotechnical materials are collected. Physical parameters such as thermal conductivity, specific heat capacity and density are measured using standardized testing equipment such as thermal conductivity meters and specific heat capacity meters. Experimental standards (such as temperature, humidity and pressure) are established during laboratory testing to ensure the repeatability and comparability of data.

[0024] Step S2: Construct a tunnel model and a tunnel thermal equilibrium model using the material parameter database of the multi-layer structure of the high-altitude tunnel. Conduct a scaled-down experiment on the tunnel model to obtain experimental results. Perform multi-parameter coupled numerical simulation on the tunnel thermal equilibrium model to obtain simulation results. Compare the experimental results with the simulation results to verify and expand the environmental parameters of the tunnel thermal equilibrium model and obtain the temperature distribution of the tunnel model.

[0025] The tunnel model is made of transparent acrylic material, with an outer geotextile material to simulate the heating and insulation layers, and an internal sand and gravel mixture to simulate the geological materials. A fluid circulation system is set up to simulate the heat exchange process, and temperature sensors and heat flow meters are installed to monitor the temperature distribution and heat flow changes of the tunnel model.

[0026] Multi-parameter coupled numerical simulation uses numerical simulation software, configures multi-physics field coupling analysis, establishes a tunnel thermal equilibrium model based on the material parameter database of the multi-layer structure of high-altitude cold tunnel, simulates the heat transfer process, and sets boundary conditions, including constant heat flux input and adiabatic boundary.

[0027] Step S3: Input material parameters and the thickness of each layer of the tunnel into the tunnel thermal equilibrium model, match the tunnel model with environmental parameters, and obtain the optimization range of material parameters and the thickness of each layer of the tunnel.

[0028] Step S4: Construct a heat load prediction model based on the material parameter database of the multi-layered structure of the high-altitude tunnel to obtain the required heat transfer load under different environmental parameters. These environmental parameters include, but are not limited to, climate and seepage conditions.

[0029] The heat load prediction model utilizes machine learning algorithms, including random forests and neural networks, to learn the nonlinear relationship between environmental parameters and heat transfer load from a database of material parameters for multi-layered high-altitude tunnels. The model is trained using a training dataset from this database to fine-tune hyperparameters. The performance of the model is evaluated through cross-validation and a test set.

[0030] The SHAP value was used to analyze the heat load prediction model, quantify the specific contribution of environmental parameters to the heat exchange load, and determine the key environmental parameters.

[0031] By analyzing the importance of features, a heat load impact scoring model is established based on the specific contribution weights of environmental parameters.

[0032] In this embodiment, when simulating the regional tunnel, the outside air temperature is set to -40℃ to 0℃, the inside temperature of the tunnel is 5℃, and there is no seepage in the surrounding strata. After calculating the required heat exchange load, the influence contribution of each environmental parameter (0~100 points) is output. The weight of the parameter adjustment is set according to the magnitude of the influence contribution (e.g., outside air temperature weight 0.6, inside tunnel temperature weight 0.3, seepage condition weight 0.1).

[0033] Step S5: Obtain on-site measurement data, including environmental parameters and temperature distribution. Construct a data-physical dual-drive model based on the tunnel thermal equilibrium model and heat load prediction model, and integrate it with the cloud intelligent platform. Input the on-site measurement data into the data-physical dual-drive model, update the environmental parameters and temperature distribution of the data-physical dual-drive model in real time, and calculate the heating power and flow parameters online.

[0034] Monitoring equipment is installed in the area where the tunnel is located to collect data on climate conditions and seepage. The collected field measurement data is imported into the data-physical dual-drive model in real time for calculation. The data-physical dual-drive model calculates the most recommended multi-layer structure design for the tunnel under the current conditions. Secondly, thermocouples, flow meters and other equipment are installed on the tunnel to obtain the temperature distribution at the tunnel entrance and the temperature and velocity of the circulating liquid in the heating layer. The heating power and flow parameters are changed by adjusting the circulation pump.

[0035] The cloud-based intelligent platform includes an intelligent database and a cloud computing platform. The intelligent database supports real-time data updates and multi-terminal access. Multi-terminal access allows for setting data access permissions, enhancing security.

[0036] The role and effect of the embodiments

[0037] The adaptive green intelligent antifreeze control method for high-altitude and cold-climate tunnel lining-heating-insulation integration involved in this embodiment includes: Step S1, constructing a material parameter database for the multi-layer structure of the high-altitude and cold-climate tunnel; Step S2, using the material parameter database to construct a tunnel model and a tunnel thermal equilibrium model, conducting scaled-down experiments on the tunnel model to obtain experimental results, performing multi-parameter coupled numerical simulations on the tunnel thermal equilibrium model to obtain simulation results, comparing the experimental results with the simulation results to verify and expand the environmental parameters of the tunnel thermal equilibrium model, and obtaining the temperature distribution of the tunnel model; Step S3, inputting material parameters and the thickness of each tunnel layer into the tunnel thermal equilibrium model, matching the tunnel model with environmental parameters, and obtaining the optimization range of material parameters and the thickness of each tunnel layer; Step S4 4. Based on the material parameter database of the multi-layered structure of high-altitude tunnels, a heat load prediction model is constructed to obtain the required heat exchange load under different environmental parameters. Step S5: Acquire field measurement data, including environmental parameters and temperature distribution. A data-physical dual-drive model is constructed based on the tunnel thermal equilibrium model and the heat load prediction model, and integrated with a cloud-based intelligent platform. The field measurement data is input into the data-physical dual-drive model, which updates the environmental parameters and temperature distribution in real time. Heating power and flow parameters are calculated online. Therefore, the integrated adaptive green intelligent anti-freezing control method for high-altitude and cold-climate tunnel lining-heating-insulation of this invention deeply explores the nonlinear relationship between environmental parameters and heat load, constructs a heat load prediction model, and improves prediction effectiveness and adaptability. It significantly reduces the anti-freezing energy consumption of high-altitude and cold-climate tunnels and improves the efficiency of controlling frost damage in high-altitude and cold-climate tunnels.

[0038] This embodiment constructs a systematic and comprehensive material parameter database for multi-layered structures of high-altitude and cold-weather tunnels through laboratory testing and literature integration, thereby improving the reliability and usability of the data.

[0039] This embodiment reduces construction risks and improves the effectiveness of frost damage control at tunnel entrances by using closed-loop verification of on-site measurement data and models.

[0040] Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for integrated adaptive, green, and intelligent antifreeze control of tunnel lining, heating, and insulation in cold and high-altitude environments, characterized in that: include: Step S1: Construct a material parameter database for the multi-layered structure of high-altitude tunnels; Step S2: Construct a tunnel model and a tunnel thermal equilibrium model using the material parameter database of the multi-layer structure of the high-altitude cold tunnel. Conduct a scaled-down experiment on the tunnel model to obtain experimental results. Perform multi-parameter coupled numerical simulation on the tunnel thermal equilibrium model to obtain simulation results. Compare the experimental results with the simulation results to verify and expand the environmental parameters of the tunnel thermal equilibrium model and obtain the temperature distribution of the tunnel model. Step S3: Input material parameters and the thickness of each layer of the tunnel into the tunnel thermal equilibrium model, match the tunnel model with the environmental parameters, and obtain the optimization range of the material parameters and the thickness of each layer of the tunnel. Step S4: Construct a heat load prediction model based on the material parameter database of the multi-layer structure of the high-altitude tunnel to obtain the required heat exchange load under different environmental parameters; Step S5: Obtain on-site measurement data, including environmental parameters and temperature distribution. Construct a data-physical dual-drive model based on the tunnel thermal equilibrium model and the heat load prediction model, and integrate it with a cloud-based intelligent platform. Input the on-site measurement data into the data-physical dual-drive model, update the environmental parameters and temperature distribution of the data-physical dual-drive model in real time, and calculate the heating power and flow parameters online.

2. The integrated adaptive green intelligent anti-freezing control method for high-altitude and cold-climate tunnel lining-heating-insulation as described in claim 1, characterized in that: in, The material parameter database for the multi-layered structure of the high-altitude tunnel was constructed through laboratory testing, literature integration, and collection of material thermophysical parameters.

3. The integrated adaptive green intelligent antifreeze control method for tunnel lining, heating, and insulation in cold and high-altitude environments as described in claim 1, characterized in that: in, The environmental parameters of the material parameter database of the multi-layered structure of the high-altitude tunnel are cleaned and processed.

4. The integrated adaptive green intelligent antifreeze control method for high-altitude and cold-climate tunnel lining-heating-insulation as described in claim 1, characterized in that: in, The tunnel model is made of transparent acrylic material, with an outer geotextile material to simulate the heating and insulation layers, and an internal sand and gravel mixture to simulate the geological strata. A fluid circulation system is set up to simulate the heat exchange process, and temperature sensors and heat flow meters are installed to monitor the temperature distribution and heat flow changes of the tunnel model.

5. The integrated adaptive green intelligent anti-freezing control method for high-altitude and cold-climate tunnel lining-heating-insulation as described in claim 1, characterized in that: in, The multi-parameter coupled numerical simulation uses numerical simulation software, configures multi-physics field coupling analysis, establishes the tunnel thermal equilibrium model based on the material parameter database of the multi-layer structure of the high-altitude tunnel, simulates the heat transfer process, and sets boundary conditions, including constant heat flux input and adiabatic boundary.

6. The integrated adaptive green intelligent antifreeze control method for tunnel lining-heating-insulation in cold and high-altitude areas according to claim 1, characterized in that: in, The heat load prediction model is constructed by using machine learning algorithms to learn the nonlinear relationship between environmental parameters and heat exchange load from the material parameter database of the multi-layer structure of the high-altitude tunnel.

7. The integrated adaptive green intelligent antifreeze control method for high-altitude and cold-climate tunnel lining-heating-insulation as described in claim 6, characterized in that: in, The machine learning algorithms include random forests and neural networks.

8. The adaptive green intelligent antifreeze control method for integrated lining-heating-insulation of high-altitude and cold-climate tunnels according to claim 1, characterized in that: in, The SHAP value is applied to analyze the heat load prediction model to quantify the specific contribution of the environmental parameters to the heat exchange load and determine the key environmental parameters.

9. The integrated adaptive green intelligent antifreeze control method for high-altitude and cold-climate tunnel lining-heating-insulation as described in claim 1, characterized in that: in, The cloud-based intelligent platform includes an intelligent database and a cloud computing platform. The intelligent database supports real-time data updates and multi-terminal access.

Images