A method for constructing a control system model for the area of ​​a flood discharge tunnel and air supply tunnel

Abstract

The present invention discloses a method for constructing a control system model for the area of ​​a flood discharge tunnel air supply hole, including the steps of collecting relevant parameters of the air supply hole and transmitting them to a controller, constructing a system mathematical model, the controller using an adaptive PID control model, and adjusting the area of ​​the air supply hole. By constructing a control system model for the area of ​​a flood discharge tunnel air supply hole, accurate dynamic control of the area of ​​the air supply hole is achieved. By combining the partial differential equations of fluid motion and the deep learning model, the physical model parameters are optimized, and an adaptive control algorithm is constructed through the organic combination of a model predictive control module, an online parameter adjustment module, and a performance evaluation module to achieve dynamic adaptive adjustment of PID parameters, which not only takes into account the real-time performance feedback of the system, but also can automatically optimize the control parameters to cope with environmental changes and changes in the internal characteristics of the system, thereby achieving efficient and accurate control of complex dynamic systems.

Description

Technical Field

[0001] The invention relates to the technical field of water conservancy engineering control, and in particular to a method for constructing a flood discharge tunnel air supply tunnel area control system model. Background Art

[0002] The area control system of the flood discharge tunnel and air supply tunnel is an important field in water conservancy projects, which aims to effectively manage water flow and air flow to ensure the normal operation and safety of water conservancy facilities. In order to better control the water flow and improve the efficiency and safety of water conservancy facilities, the area control system of the flood discharge tunnel and air supply tunnel came into being. In the early stages of water conservancy projects, the flow control in water conservancy projects mainly relied on manual operation or simple mechanical adjustment devices. This method has problems such as inconvenient operation and slow response speed, and is not suitable for the needs of large-scale water conservancy projects. With the development of automation technology, water conservancy projects began to introduce automated control systems. The initial automated control system was mainly based on the traditional PID control method, which controlled the water flow by adjusting valves or gates. However, this method has certain limitations when dealing with complex water flow conditions and changes, and it is difficult to achieve precise control. In order to solve the limitations of the traditional PID control method, water conservancy projects began to introduce intelligent control technology, which can better adapt to complex water flow environments and improve the accuracy and response speed of the control system.

[0003] In recent years, although the relevant technologies of the flood discharge tunnel air supply tunnel area control system have been continuously improved, there are still many technical defects, including at least the following aspects: 1. The flood discharge tunnel air supply tunnel system may have nonlinearity and time-varying properties, which will affect the performance of the PID control algorithm. Appropriate measures need to be taken to overcome these problems. 2. The traditional PID control algorithm may fall into the local optimal solution, making it difficult to find the global optimal solution, and has poor robustness to parameter changes and system disturbances. 3. If the parameters of the PID controller are improperly set or the environment changes greatly, it may cause the system to over-adjust or oscillate, affecting the stability and performance of the system. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for constructing a control system model for an area of ​​a flood discharge tunnel and an air supply tunnel in view of various deficiencies in the prior art.

[0005] In order to solve the above technical problems, the technical solutions adopted by the present invention are as follows.

[0006] A method for constructing a flood discharge tunnel air supply tunnel area control system model comprises the following steps:

[0007] S1: Collect relevant parameters of the air filling hole and transmit them to the controller;

[0008] S2: Constructing a mathematical model of the system;

[0009] S3: The controller uses an adaptive PID control model to calculate a control signal based on the received parameters;

[0010] S4: According to the calculated control signal, the area of ​​the air supply hole is adjusted by controlling the actuator.

[0011] As a preferred technical solution of the present invention, the construction process of the system mathematical model is as follows:

[0012] A. Establish a preliminary physical model based on the partial differential equations of fluid motion

[0013]

[0014] Among them, ρ is density, v is velocity field, p is pressure, μ is dynamic viscosity coefficient, f is external force, represents the gradient operator, which is used to describe the rate of change of a function in space; Δ represents the Laplace operator;

[0015] B. Define boundary conditions and initial conditions: According to the specific structure and environment of the air injection hole, set the boundary conditions and give the initial state of the flow field including the initial velocity field and pressure distribution at time t = 0;

[0016] C. Apply numerical methods to discretize and solve equations;

[0017] D. Analyze the stability and dynamic behavior of the system by combining nonlinear dynamics theory;

[0018] E. Collect experimental data, use deep learning models to learn airflow dynamics, and optimize the parameters of the physical model;

[0019] F. Through an iterative algorithm, the output of the machine learning model is fed back into the physical model to achieve more accurate prediction and control.

[0020] As a preferred technical solution of the present invention, the process of discretizing and solving the equations using numerical methods in step C of the system mathematical model is:

[0021] A. The finite volume method is used to discretize the equations and mesh the computational domain. The equations are solved on these discrete units. For complex air filling hole structures, unstructured meshes are required to adapt to the geometric shape.

[0022] B. Convert the continuous partial differential equation into a set of algebraic equations, and use the finite volume method to integrate the flow rate and external force in the control volume to obtain a set of linear and nonlinear algebraic equations;

[0023] C. Define boundary conditions and initial conditions including no-slip conditions at the solid wall, velocity and pressure conditions at the inlet, and pressure conditions at the outlet; use a direct solver for small-scale problems and an iterative solver for large-scale problems to solve the discretized equations.

[0024] As a preferred technical solution of the present invention, step D of the system mathematical model combines the bifurcation theory and chaos theory in the dynamic system theory to analyze the system behavior, specifically:

[0025] A. Identify the key parameters of the control system behavior including Reynolds number and the strength of the external driving force;

[0026] B. Determine the critical value of the system parameters, i.e., the bifurcation point; identify the type of bifurcation based on the behavior of the system near the bifurcation point by performing local analysis on the system equations;

[0027] C. Use numerical simulation and theoretical analysis to identify the chaotic behavior of the system. By performing long-term numerical simulation of the system trajectory, analyze its behavior in the phase space and identify strange attractors. Quantitatively describe the degree of chaos by calculating the system's Lyapunov exponent. A positive Lyapunov exponent indicates that the system has the characteristic of being sensitive to initial conditions.

[0028] D. Verify the predictions from theory and numerical analysis through experimental data, and identify nonlinear dynamics and chaotic characteristics from experimental data; adjust and optimize the parameters of the dynamic model based on experimental observations to more accurately reflect the behavior of the actual system.

[0029] As a preferred technical solution of the present invention, the adaptive PID control model in step S3 further optimizes the control signal through a model prediction control module, an online parameter adjustment module and a performance evaluation module.

[0030] As a preferred technical solution of the present invention, the construction process of the adaptive PID control model is as follows:

[0031] A. Set a baseline for performance indicators including expected overshoot, steady-state error, and rise time;

[0032] B. Implement the operation of the controlled system and collect system response data;

[0033] C. The model predictive control module combines the current system behavior data to optimize future control signals and predict the best PID parameters;

[0034] D. The online parameter adjustment module constructs an adaptive control algorithm based on the result of step C, and adjusts the PID parameters according to the real-time performance indicators fed back by the system, so that when the system performance does not meet the predetermined target, the gain parameters are automatically adjusted to adapt to environmental changes.

[0035] As a preferred technical solution of the present invention, an adaptive rule is designed to construct a neural network or fuzzy logic controller with system error E and error change rate ΔE as inputs and Kp, Ki, Kd adjustment values ​​as outputs.

[0036] As a preferred technical solution of the present invention, the adaptive control algorithm is as follows:

[0037] Three fuzzy sets are set to describe the changes of error E and error change rate ΔE, which are negative, zero, and positive. Three more fuzzy sets are defined to represent the adjustment amount of each PID parameter: decrease, maintain, and increase.

[0038] The adjustment formula can be written as:

[0039] Kp'=Kp+ΔKp

[0040] Ki'=Ki+ΔKi

[0041] Kd'=Kd+ΔKd

[0042] Through fuzzy logic control, the adaptive rules are converted into specific PID parameter adjustment amounts. Assuming that the PID parameters are Kp, Ki, and Kd, the adjustment amounts calculated according to the fuzzy rules are ΔKp, ΔKi, and ΔKd.

[0043] As a preferred technical solution of the present invention, the least square method and reinforcement learning technology are applied to gradually adjust and optimize the parameters of the PID controller to reduce the system error; the performance evaluation module evaluates the adjusted performance and compares it with the preset performance indicators until the performance requirements are met.

[0044] As a preferred technical solution of the present invention, the established system model is used to apply MPC to predict and optimize future behaviors. MPC calculates a set of optimal control actions in each control cycle to minimize future prediction errors.

[0045] The beneficial effect of adopting the above technical solution is that the present invention realizes accurate dynamic control of the area of ​​the air supply hole by constructing a control system model of the area of ​​the flood discharge tunnel and adopting an adaptive PID control model. By combining the partial differential equations of fluid motion and the deep learning model, the physical model parameters are optimized and a more accurate system mathematical model is established. Not only the basic dynamic characteristics of the fluid are considered, but also the prediction accuracy of the model is optimized in a data-driven manner. By organically combining the model predictive control module, the online parameter adjustment module and the performance evaluation module, an adaptive control algorithm is constructed to realize dynamic adaptive adjustment of the PID parameters. It not only considers the real-time performance feedback of the system, but also can automatically optimize the control parameters to cope with environmental changes and changes in the internal characteristics of the system, thereby realizing efficient and accurate control of complex dynamic systems.

[0046] The following embodiments describe in detail the technical advantages and beneficial effects of various technical details of the present invention. DETAILED DESCRIPTION

[0047] The following examples describe the present invention in detail. In the description of the following examples, specific details such as specific system structures, technologies, etc. are proposed for illustration rather than limitation, so as to provide a thorough understanding of the present application embodiments. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed description of well-known systems, devices, circuits and methods is omitted to prevent unnecessary details from hindering the description of the present application.

[0048] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or their collections. It should also be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0049] As used in the specification of this application and the appended claims, the term "if" may be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [the described condition or event] is detected" may be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context. In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0050] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0051] Example 1

[0052] The method for constructing a control system model for the area of ​​the air supply hole in a flood discharge tunnel comprises the following steps: collecting relevant parameters of the air supply hole and transmitting them to a controller, constructing a system mathematical model, the controller using an adaptive PID control model and calculating a control signal based on the received parameters (PID control is proportional-integral-differential control), and adjusting the area of ​​the air supply hole according to the calculated control signal and through a control actuator.

[0053] The step of collecting the relevant parameters of the air-filling hole and transmitting them to the controller requires collecting the key parameters of the air-filling hole operation, including but not limited to the temperature, pressure, flow rate of the fluid, and the size and shape of the air-filling hole. These parameters can be obtained by real-time measurement by sensors. The collected parameters are transmitted to the controller in real time through the network or other communication methods. To ensure the reliability and real-time performance of data transmission, industrial Ethernet or wireless communication technology can be used.

[0054] The steps of constructing the mathematical model of the system are as follows: first, a preliminary physical model is established based on the partial differential equation of fluid motion. This equation describes the motion state of the fluid, taking into account the viscosity effect and external force of the fluid. Secondly, according to the specific structure and operating environment of the air filling hole, appropriate boundary conditions and initial conditions are defined, including the no-slip condition of the solid wall, the pressure and velocity conditions at the inlet and outlet, etc. Thirdly, numerical methods are applied to discretize the partial differential equations and the computational domain is appropriately meshed. The discretized algebraic equations are solved using direct solvers and iterative solvers.

[0055] The adaptive PID control model is used in the following steps. First, the expected overshoot, steady-state error, rise time and other performance indicators are set according to the control target. Then, the model predictive control method MPC is used to optimize the future control signal and predict the optimal PID parameters in combination with the behavior data of the current system. Based on the results of the model predictive control, an adaptive control algorithm is constructed to adjust the PID parameters according to the real-time performance indicators to automatically adapt to environmental and system changes. The least squares method, reinforcement learning and other technologies are applied to further adjust and optimize the parameters of the PID controller to reduce the system error. The performance evaluation module evaluates the performance of the adjusted system, compares it with the preset performance indicators, and adjusts the control strategy according to the results.

[0056] The step of controlling the actuator to adjust the area of ​​the air-supply hole operates the control actuator, such as an electric valve, a regulating valve, etc., to adjust the area of ​​the air-supply hole according to the control signal calculated by the adaptive PID control model. The actuator accurately adjusts the opening degree of the air-supply hole according to the instruction of the control signal to control the amount of fluid flowing through the air-supply hole and achieve the control target.

[0057] In order to further improve the adaptability and accuracy of the control system, a neural network or fuzzy logic controller is designed with system error E and error change rate ΔE as input and Kp, Ki, Kd adjustment as output. These controllers can intelligently adjust PID parameters according to complex input conditions to achieve more sophisticated and flexible control.

[0058] By setting fuzzy sets to describe the changes in error and error change rate, and calculating the adjustment amount of PID parameters based on fuzzy logic, real-time adaptive adjustment of control parameters can be achieved.

[0059] Example 2

[0060] A data processing model for the control system of the air supply hole area in the flood discharge tunnel is established to describe the dynamic relationship between the air supply hole area, wind speed and air supply volume. First, it is assumed that the gas flow in the air supply hole can be regarded as a continuous medium and its flow satisfies the Navier-Stokes equation. Considering the nonlinear and time-varying characteristics of the air flow in the air supply hole, the model also needs to incorporate elements of nonlinear dynamics and appropriate treatment of boundary conditions and initial conditions.

[0061] The construction process of the system mathematical model is as follows:

[0062] 1. Consider the airflow in the air replenishment hole as an incompressible fluid, ignore the effect of temperature change on the flow, and establish a preliminary physical model based on the partial differential equation of fluid motion:

[0063]

[0064] Among them, ρ is density, v is velocity field, p is pressure, μ is dynamic viscosity coefficient, f is external force, represents the gradient operator, which is used to describe the rate of change of a function in space; Δ represents the Laplace operator;

[0065] 2. According to the specific structure and environment of the air replenishment hole, the boundary conditions are appropriately set, such as setting the boundary values ​​of velocity and pressure at the inlet and outlet; the initial conditions are set, and the initial state of the flow field including the initial velocity field and pressure distribution at the given time t=0 is determined.

[0066] 3. Apply numerical methods to discretize and solve the equations. Use the finite volume method to discretize the equations and divide the computational domain into grids. The equations will be solved on these discrete units. For complex air filling hole structures, unstructured grids are required to adapt to the geometric shape. The continuous partial differential equations are converted into a set of algebraic equations. The flow rate and external force in the control volume are integrated using the finite volume method to obtain a set of linear and nonlinear algebraic equations. Define boundary conditions and initial conditions including the no-slip condition of the solid wall, the velocity and pressure conditions at the inlet, and the pressure conditions at the outlet. For small-scale problems, use a direct solver, and for large-scale problems, use an iterative solver to solve the discretized equations.

[0067] 4. Considering the possible nonlinear stability and periodic behavior of the system, the bifurcation theory and chaos theory in the theory of applied dynamic systems are combined to analyze the system behavior, specifically: identify the key parameters of the control system behavior, including the Reynolds number and the intensity of the external driving force; determine the critical values ​​of the system parameters, that is, the bifurcation point; identify the type of bifurcation based on the behavior of the system near the bifurcation point by performing local analysis on the system equations; use numerical simulation and theoretical analysis to identify the chaotic behavior of the system, analyze its behavior in the phase space by performing long-term numerical simulation of the system trajectory, and identify strange attractors; quantitatively describe the degree of chaos by calculating the Lyapunov exponent of the system, and a positive Lyapunov exponent indicates that the system has the characteristic of being sensitively dependent on the initial conditions; verify the predictions in the theory and numerical analysis through experimental data, and identify nonlinear dynamics and chaotic characteristics from the experimental data; adjust and optimize the parameters of the dynamic model based on experimental observations to more accurately reflect the behavior of the actual system. Among them, the Lyapunov exponent is an indicator of the local stability of the system. It is a mathematical tool used to describe the stability and chaotic properties of dynamic systems (such as nonlinear systems). A positive Lyapunov exponent means that small disturbances will amplify over time, indicating that the system may be in a chaotic state; a negative Lyapunov exponent means that the disturbance will decay over time and the system is stable; a zero Lyapunov exponent indicates that the disturbance remains unchanged and the system may be in a boundary area.

[0068] 5. Collect experimental data, use deep learning models to learn airflow dynamics, and optimize the parameters of the physical model; use airflow dynamics test equipment and sensors to obtain real-time data, and collect data related to the airflow dynamics of the air filling hole, including the changes in airflow velocity, temperature, humidity and other parameters over time. Based on the collected experimental data, establish a deep learning model, such as a convolutional neural network or a recurrent neural network, to learn and capture the complex patterns and features in the airflow dynamics, and provide strong support for optimizing the parameters of the physical model. Train the constructed deep learning model, and continuously adjust the model parameters through the back propagation algorithm and optimization algorithm to minimize the error between the model prediction output and the actual observation data.

[0069] 6. Compare and analyze the output of the trained deep learning model with the prediction based on the physical model to evaluate the consistency and accuracy of the two to determine the difference between the two. Based on the results of the comparative analysis, the output of the deep learning model is fused with the physical model through an iterative algorithm to achieve more accurate prediction and control.

[0070] Example 3

[0071] The adaptive PID control model further optimizes the control signal through a model predictive control module, an online parameter adjustment module, and a performance evaluation module. First, it is necessary to clarify the desired performance indicators, such as overshoot, steady-state error, rise time, etc., which will be used as the goal of control system optimization. Set the baseline values ​​of these indicators, that is, the optimal performance level expected to be achieved. Operate the controlled system and collect system response data, including control signals, system outputs, errors and other information. Through these data, the actual behavior of the system can be understood, providing a basis for subsequent control optimization. Based on the collected system behavior data, a model predictive control module is established using prediction methods such as predictions based on physical models and data-driven machine learning models. Use the prediction model to optimize future control signals to predict the optimal PID parameters.

[0072] The online parameter adjustment module builds an adaptive control algorithm based on the results of model prediction and adjusts the PID parameters according to the real-time performance of the system. Create a neural network or fuzzy logic controller whose input is the system error E and the error change rate ΔE, and whose output is the PID parameter adjustment amount ΔKp, ΔKi, ΔKd. Use three fuzzy sets to describe the error E and the error change rate ΔE (negative large, zero, positive large), and three fuzzy sets to describe the adjustment amount of the PID parameters (decrease, maintain, increase). According to the real-time error and error change rate of the system, the adjustment amount of the PID parameters ΔKp, ΔKi, ΔKd is dynamically calculated through fuzzy logic control or neural network to adapt to changes in system performance.

[0073] The adjustment formula can be written as:

[0074] Kp'=Kp+ΔKp

[0075] Ki'=Ki+ΔKi

[0076] Kd'=Kd+ΔKd.

[0077] The performance evaluation module is used to monitor and evaluate the performance of the control system, collect system feedback data in real time, and calculate the actual performance index value. The actual performance index value is compared with the set baseline to evaluate whether the system has achieved the expected performance level. If the system performance does not meet the predetermined target, the online parameter adjustment module will automatically adjust the PID parameters to adapt to environmental changes and optimize the control signal.

[0078] In each embodiment, the hardware implementation of the technology can directly adopt existing intelligent devices, including but not limited to industrial computers, PCs, smart phones, handheld stand-alone machines, floor-standing stand-alone machines, etc. Its input device preferably adopts a screen keyboard, its data storage and calculation module adopts existing memory, calculator, controller, its internal communication module adopts existing communication ports and protocols, and its remote communication adopts existing GPRS networks, World Wide Internet, etc. It can be clearly understood by technicians in the relevant field that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the above-mentioned method embodiment, and will not be repeated here. In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal equipment and method can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. The functional units in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0079] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for constructing a flood discharge tunnel air supply tunnel area control system model, characterized in that: The following steps are involved: S1: Collect relevant parameters of the air filling hole and transmit them to the controller; S2: Constructing a mathematical model of the system; S3: The controller uses an adaptive PID control model; S4: Adjust the area of ​​the air-inflation hole; The construction process of the system mathematical model is as follows: A. Establish a preliminary physical model based on the partial differential equations of fluid motion Where ρ is the density, v is the velocity field, p is the pressure, μ is the dynamic viscosity coefficient, and f is the external force. represents the gradient operator, which is used to describe the rate of change of a function in space; Δ represents the Laplace operator; B. Define boundary conditions and initial conditions: According to the specific structure and environment of the air injection hole, set the boundary conditions and give the initial state of the flow field including the initial velocity field and pressure distribution at time t = 0; C. Apply numerical methods to discretize and solve equations; D. Analyze the stability and dynamic behavior of the system by combining nonlinear dynamics theory; E. Collect experimental data, use deep learning models to learn airflow dynamics, and optimize the parameters of the physical model; F. Through an iterative algorithm, the output of the machine learning model is fed back into the physical model to achieve more accurate prediction and control.

2. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 1, characterized in that: The process of applying numerical methods to discretize and solve the equation is as follows: A. The finite volume method is used to discretize the equations and mesh the computational domain. The equations are solved on these discrete units. For complex air filling hole structures, unstructured meshes are required to adapt to the geometric shape. B. Convert the continuous partial differential equation into a set of algebraic equations, and use the finite volume method to integrate the flow rate and external force in the control volume to obtain a set of linear and nonlinear algebraic equations; C. Define boundary conditions and initial conditions including no-slip conditions at the solid wall, velocity and pressure conditions at the inlet, and pressure conditions at the outlet; use a direct solver for small-scale problems and an iterative solver for large-scale problems to solve the discretized equations.

3. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 1, characterized in that: Step D combines bifurcation theory and chaos theory in dynamical system theory to analyze system behavior, specifically: A. Identify the key parameters of the control system behavior including Reynolds number and the strength of the external driving force; B. Determine the critical value of the system parameters, i.e., the bifurcation point; identify the type of bifurcation based on the behavior of the system near the bifurcation point by performing local analysis on the system equations; C. Use numerical simulation and theoretical analysis to identify the chaotic behavior of the system. By performing long-term numerical simulation of the system trajectory, analyze its behavior in the phase space and identify strange attractors. Quantitatively describe the degree of chaos by calculating the system's Lyapunov exponent. A positive Lyapunov exponent indicates that the system has the characteristic of being sensitive to initial conditions. D. Verify the predictions from theory and numerical analysis through experimental data and identify nonlinear dynamics and chaotic features from experimental data; Based on experimental observations, the parameters of the kinetic model are adjusted and optimized to more accurately reflect the behavior of the actual system.

4. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 1, characterized in that: In the step S3, the adaptive PID control model further optimizes the control signal through a model prediction control module, an online parameter adjustment module and a performance evaluation module.

5. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 4, characterized in that: The construction process of the adaptive PID control model is as follows: A. Set a baseline for performance indicators including expected overshoot, steady-state error, and rise time; B. Implement the operation of the controlled system and collect system response data; C. The model predictive control module combines the current system behavior data to optimize future control signals and predict the best PID parameters; D. The online parameter adjustment module constructs an adaptive control algorithm based on the result of step C, and adjusts the PID parameters according to the real-time performance indicators fed back by the system, so that when the system performance does not meet the predetermined target, the gain parameters are automatically adjusted to adapt to environmental changes.

6. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 5, characterized in that: Design adaptive rules and construct a neural network or fuzzy logic controller with system error E and error change rate ΔE as input and Kp, Ki, Kd adjustment values ​​as output.

7. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 5, characterized in that: The adaptive control algorithm in step D is as follows: Three fuzzy sets are set to describe the changes of error E and error change rate ΔE, which are negative, zero, and positive. Three more fuzzy sets are defined to represent the adjustment amount of each PID parameter: decrease, maintain, and increase. The adjustment formula can be written as: Kp'=Kp+ΔKp Ki'=Ki+ΔKi Kd'=Kd+ΔKd Through fuzzy logic control, the adaptive rules are converted into specific PID parameter adjustment amounts. Assuming that the PID parameters are Kp, Ki, and Kd, the adjustment amounts calculated according to the fuzzy rules are ΔKp, ΔKi, and ΔKd.

8. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 7, characterized in that: The least square method and reinforcement learning technology are applied to gradually adjust and optimize the parameters of the PID controller to reduce the system error; the performance evaluation module evaluates the adjusted performance and compares it with the preset performance indicators until the performance requirements are met.

9. The method for constructing a flood discharge tunnel air supply tunnel area control system model according to claim 1, characterized in that: Using the established system model, the model predictive control method is applied to predict and optimize future behaviors. The model predictive control method calculates a set of optimal control actions in each control cycle to minimize future prediction errors.

Images