A high performance ventilation system based on digital model design

Abstract

The application belongs to the technical field of tunnel ventilation, and in particular to a high-performance ventilation system based on digital model design, which comprises a data analysis and processing module: using a digital model to perform real-time processing and analysis of data and predict ventilation demand; and a decision and control module: according to the analysis results, controlling the start and stop of the fan, air volume, and ensuring air quality. The high-performance ventilation system based on digital model design integrates multiple modules such as data acquisition, analysis and processing, decision control, etc., and the system can dynamically adjust according to real-time air quality, traffic volume, speed, etc. in the tunnel, optimize ventilation flow and fan operating state, and this intelligent adjustment can ensure that the air quality in the tunnel is always within a safe range, avoiding energy waste caused by excessive ventilation, improving air quality, and ensuring the safety and comfort of personnel.

Description

Technical Field

[0001] This invention relates to the field of tunnel ventilation technology, and in particular to a high-performance ventilation system based on digital model design. Background Technology

[0002] Compared to single-point access tunnels, multi-point access urban underground roads are significantly more complex in terms of airflow characteristics due to the influence of their diversion and merging ramp structures. This results in several key features: substantial changes in the morphology and dynamic effects of the network of urban underground roads, making their safe operation crucial for urban road traffic safety. Furthermore, the presence of multiple ramps, numerous nodes and branches, and complex airflow organization significantly impacts the ventilation environment of underground roads, affecting longitudinal ventilation based on the piston effect and smoke extraction systems operating under non-blocking conditions.

[0003] Current research on underground interchange technology primarily focuses on structural design and construction techniques, with a relative lack of research on ventilation systems. While some studies have proposed ventilation network analysis methods for underground interchanges, these are still in the exploratory stage. Furthermore, most of the engineering structures relied upon in these studies are simple, consisting only of a main tunnel and a few ramps leading directly to the surface. The ventilation network has few airflow convergence points and inlets / outlets, resulting in a relatively simple structure. Therefore, the research findings are not applicable to the ventilation design of complex underground interchanges. Consequently, developing reasonable ventilation control schemes under different natural wind and traffic flow conditions, and establishing digital models of the tunnel ventilation system to achieve on-demand airflow in each tunnel section, have become critical and challenging issues that urgently need to be addressed for the operational ventilation of underground interchanges. Summary of the Invention

[0004] Based on the aforementioned technical problems, this invention proposes a high-performance ventilation system designed based on a digital model.

[0005] This invention proposes a high-performance ventilation system based on digital model design. The ventilation system includes: a data acquisition module responsible for collecting vehicle data, air quality data, and pedestrian traffic information from the tunnel; a data analysis and processing module that uses the digital model to process and analyze the data in real time and predict ventilation demand; a decision-making and control module that controls the start / stop and airflow of the fans based on the analysis results to ensure air quality; specifically, it adjusts the working state of the ventilation equipment, including fan speed and airflow distribution, based on control signals provided by the data analysis and processing module and through control algorithms; a feedback and optimization module that provides feedback and optimization based on actual conditions and maintenance data; and an environmental simulation and prediction module that simulates and predicts air quality and traffic flow in the tunnel over a future period based on the digital model and historical data, providing optimization suggestions to the decision-making module.

[0006] Preferably, the data acquisition module includes vehicle type recognition: combining lidar and high-definition cameras installed at the tunnel entrance and middle, using computer vision technology to classify and identify vehicles in the tunnel, and using radar technology to measure vehicle speed. At the same time, the sensors equipped on each vehicle acquire vehicle speed data through the tunnel's lane monitoring system.

[0007] Traffic flow identification: High-definition cameras and infrared sensors are used to identify the number of vehicles passing through the tunnel and estimate the number of people in the flow.

[0008] Air quality identification: via , , Gas concentration sensors monitor the air quality inside the tunnel in real time and provide pollutant concentration data. Then, temperature and humidity sensors monitor the temperature and humidity inside the tunnel in real time, and the data is used to assess the impact of airflow and exhaust demand.

[0009] Through the above technical solution, vehicle types are mainly divided into light vehicles, heavy vehicles and other special vehicles, and the identified vehicle type information will be used to analyze ventilation requirements.

[0010] Preferably, the data analysis and processing module includes,

[0011] a1. Pollutant Emission and Vehicle Speed ​​Relationship Model: Based on the combination of different vehicle types and vehicle speeds, a pollutant emission model is constructed to control ventilation flow to emit these gases. The pollutant emission model is as follows: ,

[0012] in, This indicates the amount of pollutants emitted by a single vehicle. and It is a coefficient related to vehicle type. Used to adjust the impact of vehicle speed on pollutant emissions. This indicates the baseline pollutant emissions specific to vehicle type; for example, if we consider light vehicles... and heavy vehicles For two vehicle types, the formula can be expressed as: , ;

[0013] in, and These are the speed coefficients for each vehicle type. and These are the baseline emissions for their respective vehicle types.

[0014] a2. Accumulation Effect of Emissions: Vehicle emissions are not only related to vehicle speed but also closely related to the accumulation effect. Factors contributing to the accumulation effect include: vehicle flow rate (higher vehicle flow rate leads to higher total pollutant emissions); vehicle density (higher vehicle density increases the amount of pollutants emitted per unit time); and airflow effect (airflow within tunnels can influence the diffusion and accumulation of pollutants). At low speeds, weaker airflow makes it difficult for pollutants to be quickly emitted, leading to easier accumulation of pollutants within the tunnel, thus increasing pollutant concentration. The formula for the accumulation effect is: ,

[0015] in, It refers to the concentration of pollutants per unit volume. It represents the number of vehicles passing through per unit of time. The volume of the tunnel is the key factor. This formula reflects the impact of factors such as vehicle speed, traffic flow, and tunnel volume on pollutant concentration. The greater the traffic flow and the smaller the tunnel volume, the higher the pollutant concentration.

[0016] a3. Calculate ventilation volume: The ventilation volume is calculated based on the concentration of emissions, using the following formula:

[0017] ;in, That is the required ventilation volume. It is a coefficient related to the efficiency of ventilation equipment and tunnel structure.

[0018] Through the above technical solution, the data analysis and processing module comprehensively considers various factors such as pollutant emissions, vehicle speed, traffic density, and personnel flow, and optimizes the air quality in the tunnel through automatic adjustments to ensure personnel safety.

[0019] Preferably, the decision and control module includes b1, fan start / stop control: it is mainly based on the real-time changes in vehicle speed, pollutant concentration and vehicle flow to make adjustments. The specific control logic is: when the pollutant concentration exceeds the set threshold, that is, when the accumulation effect of emissions causes the pollutant concentration to reach a certain critical value, the fan will be started; conversely, when the concentration is lower than the threshold, the fan will be shut down.

[0020] b2. Fan Flow Regulation: Fan flow regulation depends on pollutant concentration, vehicle speed, and traffic volume within the tunnel. The fan volume is precisely adjusted via a variable frequency drive. When pollutant concentration is too high, the fan flow increases to quickly expel pollutants. When vehicle speed is low, pollutant accumulation is significant, and the fan flow increases to accelerate pollutant discharge. The fan flow regulation formula is as follows:

[0021] ,

[0022] in, and It is an adjustment coefficient related to fan efficiency and tunnel volume; for example, assuming: pollutant concentration = 150 mg / m³, vehicle flow rate = 1000 vehicles / hour, =2, =0.1, then the fan flow rate is: In this way, the airflow regulation of the fan can be dynamically adjusted according to real-time data changes in the tunnel, which can both ensure air quality and save energy.

[0023] b3. Regional ventilation control: By setting up local fans at different locations in the tunnel, the air volume in specific areas is adjusted according to real-time pollutant concentration and vehicle speed data. Specific control methods include: entrance area: when the traffic flow is greater than the set threshold and the pollutant concentration is higher than the set high threshold, the air volume is increased; otherwise, the air volume is maintained or moderately adjusted.

[0024] Mid-range zone: When the traffic flow is less than the set threshold and the pollutant concentration is lower than the set low threshold, the air volume is reduced; otherwise, the air volume is adjusted according to the traffic flow and pollutant concentration.

[0025] Terminal area: Dynamically adjust air volume to avoid pollutant accumulation or excessive emissions, i.e., flexibly control based on the instability of traffic flow and pollutant concentration.

[0026] b4. Dynamic Adjustment and Adaptive Control: To cope with the constantly changing tunnel environment, the control module adopts an adaptive control algorithm, namely, using a PID control algorithm to continuously monitor vehicle speed, flow rate, and pollutant concentration parameters within the tunnel, and adjust the fan's operating status in real time according to environmental changes. The calculation formula for the PID control algorithm is:

[0027] ,in, These are the control parameters of the fan. It is the error, that is, the difference between the set pollutant concentration and the current pollutant concentration. It is proportional gain. It is integral gain. It is the differential gain. It is an error function. Represents the error function Integrating from time 0 to time t calculates the cumulative sum of errors during this period.

[0028] When using a PID control algorithm to adjust the airflow of a fan, the input is:

[0029] Set pollutant concentration: This refers to the set safe concentration of pollutants.

[0030] Actual pollutant concentration: This refers to the actual concentration of pollutants measured inside the tunnel.

[0031] Error calculation: .

[0032] PID controller output: The control parameters of the fan are calculated based on the error and the PID formula. This allows it to control the airflow or start / stop status of the fan; specifically, the error... A large value indicates that the pollutant concentration deviates significantly from the target, and the PID controller will output a larger air volume or a strong fan start signal. With a smaller error, the air volume or status of the fan will tend to stabilize.

[0033] The above technical solution, through the PID control algorithm, can realize the automatic adjustment of tunnel fans, ensuring that the concentration of pollutants is always within a safe range, thereby improving the efficiency and stability of the tunnel ventilation system.

[0034] Preferably, the feedback and optimization module includes:

[0035] c1. Optimization and Scheduling Module: The main objective is to schedule wind turbines using the ant colony algorithm to determine their optimal operating mode, running time, and intensity. This simulates the process of ants searching for food, calculating the scheduling path for the turbines, and optimizing the start-up, shutdown, and running time cycles. During operation, the ant colony algorithm shares optimization experience through pheromone transmission, thereby accelerating the search for the optimal solution. By setting the pheromone evaporation rate, it avoids prematurely falling into local optima. The ant colony algorithm can simultaneously optimize multiple objectives, such as reducing energy consumption, reducing turbine failure rate, and improving ventilation efficiency, ensuring optimal overall system performance.

[0036] c2. Digital Model Module: The core task is to use computational fluid dynamics, or CFD technology, to simulate and analyze the ventilation system, thereby optimizing the design of the ventilation system.

[0037] Through the above technical solutions, the digital model module optimizes the design and operation of the ventilation system through CFD analysis models, ensuring that the system can work efficiently under various environmental conditions. The optimized scheduling strategies and design schemes are implemented and continuously optimized through feedback mechanisms.

[0038] Preferably, the environmental simulation and prediction module includes:

[0039] d1. Data Acquisition and Fusion: Collect real-time environmental data within the tunnel, including air quality, traffic flow, temperature, and humidity; integrate past operational data, including historical air quality and traffic flow data, to provide training samples for deep learning models; clean, denoise, and normalize the data to ensure accuracy and consistency, making it suitable for input into deep learning models.

[0040] d2. Deep Learning Model: LSTM network is used to model time series data to capture long-term dependencies and predict air quality and traffic flow in the future. The input data is appropriately transformed and processed to extract useful features, ensuring that the model learns the temporal patterns of the data. The LSTM model is trained with historical data to continuously optimize network parameters and improve prediction accuracy.

[0041] d3. Simulation and Prediction Results: Predict the air quality in the tunnel over a future period, predict changes in traffic flow within the tunnel, and make accurate predictions based on traffic and air quality requirements at different times.

[0042] d4. Predictive Analysis and Optimization Suggestions: Based on air quality forecasts, provide optimization suggestions for the ventilation system, predict the periods when ventilation needs to be strengthened, and provide traffic flow scheduling suggestions based on traffic flow forecasts to help traffic management personnel achieve efficient traffic control.

[0043] The above technical solutions provide an optimized basis for ventilation and traffic management strategies, ensuring that the tunnel maintains good air quality while achieving efficient traffic flow, and improving the safety and comfort of tunnel operation.

[0044] Preferably, the fan is a jet fan, which is installed in the entrance area, middle section area and end area of ​​the tunnel respectively. The outer surface of the casing of the jet fan is provided with an angle adjustment mechanism, and the inside of the jet fan is provided with a linkage mechanism to control the angle deflection of the fan blades.

[0045] Preferably, the angle adjustment mechanism controls the overall angle adjustment of the jet fan, wherein the angle adjustment mechanism includes a mounting frame fixedly wrapped around the outer surface of the jet fan housing, and movable joints are symmetrically distributed on the outer surface of the mounting frame. A rotating rod is fixedly connected to one end of the movable joint. The rotating rod consists of two upper and lower support rods and a connecting pipe rotatably sleeved on the outer surface of the two support rods. Another movable joint on the free end of the rotating rod is fixedly installed on the inner wall of the tunnel through a mounting plate.

[0046] Preferably, the angle adjustment mechanism further includes a support base fixedly connected to the upper surface of the jet fan housing. A half gear plate is fixedly connected to the upper surface of the middle part of the support base. A rotating shaft is arranged directly above the support base. A U-shaped support beam is fixedly connected to the lower surface of the rotating shaft. A mounting block with a movable groove is fixedly connected to the inner top surface of the support beam. A rack rod is arranged inside the mounting block, and the rack rod meshes with the half gear plate.

[0047] Preferably, the angle adjustment mechanism further includes a threaded sleeve fixedly connected to the upper surface of the rack rod, an adjusting screw rotatably connected to the inner surface of the mounting block via a bearing, the threaded sleeve being threaded onto the outer surface of the adjusting screw, a drive motor fixedly mounted on the outer surface of the mounting block, and the outer surface of the output shaft of the drive motor being fixedly connected to the outer surface of the adjusting screw via a coupling.

[0048] Preferably, the linkage mechanism includes a drive seat for rotating the fan blades, and the drive seat has a hollow interior. A drive head is fixedly connected to one side surface of one of the drive seats. A main bevel gear is rotatably connected to the cavity of the drive seat via a bearing. The outer surface of the output shaft of the drive head passes through both drive seats and is fixedly connected to the surface of the main bevel gear. A driven bevel gear is meshed in a circular array on the outer surface of the main bevel gear. The surface of the driven bevel gear is fixedly connected to the mounting shaft corresponding to the fan blades.

[0049] The beneficial effects of this invention are as follows:

[0050] 1. By integrating multiple modules such as data acquisition, analysis and processing, and decision control, the system can dynamically adjust based on real-time data such as air quality, traffic flow, and vehicle speed inside the tunnel, optimizing ventilation flow and fan operation. This intelligent adjustment ensures that the air quality inside the tunnel is always within a safe range, avoiding energy waste caused by excessive ventilation, improving air quality, and ensuring the safety and comfort of personnel.

[0051] 2. By using a model based on vehicle speed, pollutant emissions, and accumulation effects, the required ventilation volume is accurately calculated. At the same time, adaptive control algorithms, such as PID control algorithms, are used to dynamically adjust the operation of the fans. This not only ensures the maximization of ventilation efficiency, but also optimizes the ventilation strategy for different time periods and traffic flow changes through adaptive control, thereby improving the overall operating efficiency and stability of the system.

[0052] 3. Through feedback and optimization modules, such as using ant colony algorithms for fan scheduling and CFD technology for design optimization, the system can continuously adjust its operating strategy based on real-time data and environmental changes. The introduction of the feedback mechanism enables the system to self-optimize during long-term operation, ensuring minimal energy consumption, reduced fan failure rate, and consistently high and stable ventilation performance.

[0053] 4. By setting up an angle adjustment mechanism and a linkage mechanism, the ventilation effect of the jet fan can be adjusted. During the adjustment process, the rack moves horizontally in the movable slot of the mounting block, thereby causing the meshing half gear plate to drive the support seat to rotate. This causes the jet fan to adjust its overall angle under the hoisting connection of the rotating rod, so that it can provide precise ventilation to the target point. At the same time, the motor in the drive head drives the main bevel gears in the two drive seats to rotate, which in turn causes multiple slave bevel gears to rotate, changing the deflection angle of the fan blades to adapt to the airflow in the tunnel and make it rotate at a uniform speed to quickly adjust the ventilation in the tunnel. Attached Figure Description

[0054] Figure 1 This is a schematic diagram of a high-performance ventilation system based on digital model design proposed in this invention;

[0055] Figure 2 This is a flowchart of a data acquisition module for a high-performance ventilation system based on digital model design proposed in this invention;

[0056] Figure 3 This is a flowchart of a regional ventilation control system based on digital model design proposed in this invention.

[0057] Figure 4 This is a logic block diagram of ventilation volume regulation for a high-performance ventilation system based on digital model design proposed in this invention;

[0058] Figure 5 This is a block diagram of an ant colony algorithm for a high-performance ventilation system based on a digital model, as proposed in this invention.

[0059] Figure 6 This is a schematic diagram of a tunnel layout for a high-performance ventilation system based on digital model design proposed in this invention;

[0060] Figure 7 This is a three-dimensional view of the jet fan structure of a high-performance ventilation system based on digital model design proposed in this invention;

[0061] Figure 8 This is a three-dimensional view of the rotating rod structure of a high-performance ventilation system based on digital model design proposed in this invention;

[0062] Figure 9This is a three-dimensional view of the support beam structure of a high-performance ventilation system based on digital model design proposed in this invention;

[0063] Figure 10 This is a three-dimensional view of the regulating screw structure of a high-performance ventilation system based on digital model design proposed in this invention;

[0064] Figure 11 This is a three-dimensional view of a half-gear plate structure of a high-performance ventilation system based on digital model design proposed in this invention;

[0065] Figure 12 This is a three-dimensional view of the fan blade structure of a high-performance ventilation system based on digital model design proposed in this invention;

[0066] Figure 13 This is a three-dimensional view of the main bevel gear structure of a high-performance ventilation system based on digital model design proposed in this invention.

[0067] In the diagram: 1. Jet fan; 11. Fan blade; 2. Angle adjustment mechanism; 21. Mounting bracket; 22. Movable joint; 23. Rotating rod; 24. Support base; 25. Half gear plate; 26. Rotating shaft; 27. Support beam; 28. Mounting block; 29. ​​Rack and pinion; 30. Threaded sleeve; 31. Adjusting screw; 32. Drive motor; 4. Linkage mechanism; 41. Drive base; 42. Drive head; 43. Main bevel gear; 44. Driven bevel gear. Detailed Implementation

[0068] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0069] Reference Figure 1 As shown, a high-performance ventilation system based on digital model design is disclosed. The ventilation system includes,

[0070] Data acquisition module: responsible for collecting vehicle data, air quality data, and pedestrian traffic information from the tunnel.

[0071] Data Analysis and Processing Module: Utilizes digital models to process and analyze data in real time to predict ventilation demand.

[0072] Decision and control module: Based on the analysis results, it controls the start and stop of the fan and the air volume to ensure air quality. That is, it is used to adjust the working status of the ventilation equipment, including fan speed and air volume distribution, based on the control signals provided by the data analysis and processing module and through control algorithms.

[0073] Feedback and Optimization Module: Provides feedback and optimization based on actual conditions and maintenance data.

[0074] Environmental Simulation and Prediction Module: Based on digital models and historical data, it simulates and predicts air quality and traffic flow in the tunnel over a future period, providing optimization suggestions for the decision-making module.

[0075] By integrating multiple modules such as data acquisition, analysis and processing, and decision control, the system can dynamically adjust based on real-time data such as air quality, traffic flow, and vehicle speed inside the tunnel, optimizing ventilation flow and fan operation. This intelligent adjustment ensures that the air quality inside the tunnel is always within a safe range, avoiding energy waste caused by excessive ventilation, improving air quality, and ensuring the safety and comfort of personnel.

[0076] Reference Figure 2 As shown, the data acquisition module includes,

[0077] Vehicle type recognition: Combining lidar and high-definition cameras installed at the tunnel entrance and middle, computer vision technology is used to classify and identify vehicles in the tunnel, and radar technology is used to measure vehicle speed. At the same time, sensors equipped on each vehicle obtain vehicle speed data through the tunnel's lane monitoring system.

[0078] Traffic flow identification: High-definition cameras and infrared sensors are used to identify the number of vehicles passing through the tunnel and estimate the number of people in the flow.

[0079] Air quality identification: via , , Gas concentration sensors monitor the air quality inside the tunnel in real time and provide pollutant concentration data. Then, temperature and humidity sensors monitor the temperature and humidity inside the tunnel in real time, and the data is used to assess the impact of airflow and exhaust demand.

[0080] Vehicle types are mainly divided into light vehicles, heavy vehicles, and other special vehicles. The identified vehicle type information will be used to analyze ventilation needs, especially when there are many heavy vehicles, such as trucks, which may require stronger ventilation to remove exhaust gases. Vehicle speed information is crucial for the ventilation system because different vehicle speeds affect pollutant emissions. At the same time, the identification of the number of people passing through will help assess the load on the ventilation system, especially during high-flow periods.

[0081] The data analysis and processing module includes: a1. A pollutant emission and vehicle speed relationship model: Based on the combination of different types of vehicles and vehicle speeds, a pollutant emission model is constructed to control ventilation flow to emit these gases. The pollutant emission model is as follows: .

[0082] in, This indicates the amount of pollutants emitted by a single vehicle. and It is a coefficient related to vehicle type. Used to adjust the impact of vehicle speed on pollutant emissions. This indicates the baseline pollutant emissions specific to vehicle type; for example, if we consider light vehicles... and heavy vehicles For two vehicle types, the formula can be expressed as: , ;

[0083] in, and These are the speed coefficients for each vehicle type. and These are the baseline emissions for their respective vehicle types;

[0084] a2. Accumulation Effect of Emissions: Vehicle emissions are not only related to vehicle speed but also closely related to the accumulation effect. Factors contributing to the accumulation effect include: vehicle flow rate (higher vehicle flow rate leads to higher total pollutant emissions); vehicle density (higher vehicle density increases the amount of pollutants emitted per unit time); and airflow effect (airflow within tunnels can influence the diffusion and accumulation of pollutants). At low speeds, weaker airflow makes it difficult for pollutants to be quickly emitted, leading to easier accumulation of pollutants within the tunnel, thus increasing pollutant concentration. The formula for the accumulation effect is: ,

[0085] in, It refers to the concentration of pollutants per unit volume. It represents the number of vehicles passing through per unit of time. The volume of the tunnel is the key factor. This formula reflects the impact of factors such as vehicle speed, traffic flow, and tunnel volume on pollutant concentration. The greater the traffic flow and the smaller the tunnel volume, the higher the pollutant concentration.

[0086] a3. Calculate ventilation volume: The ventilation volume is calculated based on the concentration of emissions, using the following formula:

[0087] ,in, That is the required ventilation volume. It is a coefficient related to the efficiency of ventilation equipment and tunnel structure.

[0088] The data analysis and processing module comprehensively considers various factors such as pollutant emissions, vehicle speed, traffic density, and personnel flow. It uses machine learning and pollutant emission models to predict the ventilation demand of tunnels. This module can provide real-time ventilation volume prediction, provide a scientific basis for the tunnel ventilation system, and optimize the air quality in the tunnel through automatic adjustments to ensure personnel safety.

[0089] The decision-making and control module includes, as referenced Figure 4As shown, b1, fan start / stop control: It is mainly based on the real-time changes in vehicle speed, pollutant concentration and vehicle flow to make adjustments. The specific control logic is: when the pollutant concentration exceeds the set threshold, that is, when the accumulation effect of emissions causes the pollutant concentration to reach a certain critical value, the fan will be started; conversely, when the concentration is lower than the threshold, the fan will be shut down.

[0090] b2. Fan Flow Regulation: Fan flow regulation depends on pollutant concentration, vehicle speed, and traffic volume within the tunnel. The fan volume is precisely adjusted via a variable frequency drive. When pollutant concentration is too high, the fan flow increases to quickly expel pollutants. When vehicle speed is low, pollutant accumulation is significant, and the fan flow increases to accelerate pollutant discharge. The fan flow regulation formula is as follows:

[0091] ,

[0092] in, and It is an adjustment coefficient related to fan efficiency and tunnel volume; for example, assuming: pollutant concentration = 150 mg / m³, vehicle flow rate = 1000 vehicles / hour, =2, =0.1, then the fan flow rate is:

[0093] In this way, the airflow regulation of the fan can be dynamically adjusted according to real-time data changes in the tunnel, which can both ensure air quality and save energy.

[0094] Reference Figure 3 As shown in Figure b3, regional ventilation control: by setting local fans at different locations in the tunnel, the air volume in specific areas is adjusted according to real-time pollutant concentration and vehicle speed data. Specific control methods include: entrance area: when the traffic flow is greater than the set threshold and the pollutant concentration is higher than the set high threshold, the air volume is increased; otherwise, the air volume is maintained or moderately adjusted.

[0095] Mid-range zone: When the traffic flow is less than the set threshold and the pollutant concentration is lower than the set low threshold, the air volume is reduced; otherwise, the air volume is adjusted according to the traffic flow and pollutant concentration.

[0096] Terminal area: Dynamically adjust air volume to avoid pollutant accumulation or excessive emissions, i.e., flexibly control based on the instability of traffic flow and pollutant concentration.

[0097] b4. Dynamic Adjustment and Adaptive Control: To cope with the constantly changing tunnel environment, the control module adopts an adaptive control algorithm, namely, using a PID control algorithm to continuously monitor vehicle speed, flow rate, and pollutant concentration parameters within the tunnel, and adjust the fan's operating status in real time according to environmental changes. The calculation formula for the PID control algorithm is:

[0098] ,in, These are the control parameters of the fan. It is the error, that is, the difference between the set pollutant concentration and the current pollutant concentration. It is proportional gain. It is integral gain. It is the differential gain. It is an error function. Represents the error function Integrating from time 0 to time t calculates the cumulative sum of errors during this period.

[0099] When using a PID control algorithm to adjust the airflow of a fan, the input is:

[0100] Set pollutant concentration: This refers to the set safe concentration of pollutants.

[0101] Actual pollutant concentration: This refers to the actual concentration of pollutants measured inside the tunnel.

[0102] Error calculation: .

[0103] PID controller output: The control parameters of the fan are calculated based on the error and the PID formula. This allows it to control the airflow or start / stop status of the fan; specifically, the error... A large value indicates that the pollutant concentration deviates significantly from the target, and the PID controller will output a larger air volume or a strong fan start signal. With a smaller error, the air volume or status of the fan will tend to stabilize.

[0104] The control system also needs to consider real-time vehicle speed and traffic flow. The lower the vehicle speed, the more significant the accumulation effect, and the more frequently the system should start and stop the fans to ensure ventilation. The fan start-stop frequency is higher at low vehicle speeds or high traffic flow. At high vehicle speeds, pollutant emissions are lower, and the fan start-stop frequency can be appropriately reduced. At the same time, through PID control algorithms, the tunnel fans can be automatically adjusted to ensure that the pollutant concentration is always within a safe range, thereby improving the efficiency and stability of the tunnel ventilation system.

[0105] By using a model based on vehicle speed, pollutant emissions, and accumulation effects, the required ventilation volume is accurately calculated. At the same time, adaptive control algorithms, such as PID control algorithms, are used to dynamically adjust the operation of the fans. This not only ensures the maximization of ventilation efficiency, but also optimizes the ventilation strategy for different time periods and traffic flow changes through adaptive control, thereby improving the overall operational efficiency and stability of the system.

[0106] The feedback and optimization module includes: references Figure 5 As shown, c1, the optimization scheduling module, primarily aims to schedule wind turbines using the ant colony algorithm to determine their optimal operating mode, running time, and intensity. This simulates the process of ants searching for food, calculating the turbine scheduling path, and optimizing the turbine start-up, shutdown, and running time cycles. During operation, the ant colony algorithm shares optimization experience through pheromone transmission, thereby accelerating the search for the optimal solution. By setting the pheromone evaporation rate, it avoids prematurely falling into local optima. The ant colony algorithm can simultaneously optimize multiple objectives, such as reducing energy consumption, reducing turbine failure rates, and improving ventilation efficiency, ensuring optimal overall system performance.

[0107] c2. Digital Model Module: The core task is to use computational fluid dynamics, or CFD technology, to simulate and analyze the ventilation system, thereby optimizing the design of the ventilation system.

[0108] The system continuously collects data through real-time sensors. This data is fed back to the optimization scheduling module and the digital model module. The optimization scheduling module uses intelligent algorithms to process this real-time data and adjusts the fan operation strategy according to the current environment and needs, ensuring the lowest energy consumption and the highest ventilation efficiency. The digital model module uses CFD analysis models to optimize the design and operation of the ventilation system, ensuring that the system can work efficiently under various environmental conditions. The optimized scheduling strategy and design scheme are implemented and continuously optimized through the feedback mechanism. For example, if the pollutant concentration in a certain area is high, the system will automatically adjust the fan operating mode to better meet the ventilation requirements.

[0109] The environmental simulation and prediction module includes: d1, data acquisition and fusion: collecting real-time environmental data in the tunnel, including air quality, traffic flow, temperature and humidity, integrating past operational data, including historical air quality and traffic flow data, providing training samples for deep learning models, cleaning, denoising and normalizing the data to ensure accuracy and consistency, making it suitable for input to deep learning models.

[0110] d2. Deep Learning Model: LSTM network is used to model time series data to capture long-term dependencies and predict air quality and traffic flow in the future. The input data is appropriately transformed and processed to extract useful features, ensuring that the model learns the temporal patterns of the data. The LSTM model is trained with historical data to continuously optimize network parameters and improve prediction accuracy.

[0111] d3. Simulation and Prediction Results: Predict the air quality in the tunnel over a future period, predict changes in traffic flow within the tunnel, and make accurate predictions based on traffic and air quality requirements at different times.

[0112] d4. Predictive Analysis and Optimization Suggestions: Based on air quality forecasts, provide optimization suggestions for the ventilation system, predict the periods when ventilation needs to be strengthened, and provide traffic flow scheduling suggestions based on traffic flow forecasts to help traffic management personnel achieve efficient traffic control.

[0113] The environmental simulation and prediction module uses deep learning algorithms, especially LSTM models, combined with real-time and historical data to accurately predict changes in air quality and traffic flow inside the tunnel. These prediction results not only help to understand the environmental conditions inside the tunnel in a timely manner, but also provide an optimization basis for ventilation and traffic management strategies, ensuring that the tunnel maintains good air quality while achieving efficient traffic flow, thereby improving the safety and comfort of tunnel operation.

[0114] Reference Figures 7-13 As shown, in order to control the regional fans to quickly meet their ventilation needs, the fans are jet fans 1, which are installed in the entrance area, middle section area and end area of ​​the tunnel respectively. The outer surface of the casing of the jet fan 1 is provided with an angle adjustment mechanism 2. The inside of the jet fan 1 is provided with a linkage mechanism 4 that controls the angle deflection of the fan blades 11. According to the adjustment signal, the angle adjustment mechanism 2 adjusts the installation angle of the jet fan 1 so that its ventilation effect is adapted to the conditions in the tunnel at that time. At the same time, in order to adjust the air volume of the jet fan 1, the linkage mechanism 4 adjusts the deflection angle of the fan blades 11 so that it can quickly output the required air volume when rotating at high speed.

[0115] To enable angle-adjustable installation of the jet fan 1, the angle adjustment mechanism 2 controls the overall angle adjustment of the jet fan 1. The angle adjustment mechanism 2 includes a mounting frame 21 fixedly wrapped around the outer surface of the jet fan 1 housing. Movable joints 22 are symmetrically distributed on the outer surface of the mounting frame 21. A rotating rod 23 is fixedly connected to one end of the movable joint 22. The rotating rod 23 consists of two upper and lower support rods and a connecting pipe rotatably sleeved on the outer surface of the two support rods. Another movable joint 22 on the free end of the rotating rod 23 is fixedly installed on the inner wall of the tunnel through a mounting plate. The rotating rod 23 hoists the jet fan 1 with the mounting frame 21. At the same time, the connection point is connected by the movable joint 22, that is, the connection angle at both ends of the rotating rod 23 can be arbitrarily adjusted. Moreover, the rotating rod 23 adopts a multi-section structure, so it can rotate to satisfy the angle adjustment mechanism 2.

[0116] To drive the jet fan 1 to adjust its tilt angle and precisely ventilate the target point, the angle adjustment mechanism 2 also includes a support base 24 fixedly connected to the upper surface of the jet fan 1 housing. A half-gear plate 25 is fixedly connected to the upper surface of the middle part of the support base 24. A rotating shaft 26 is set directly above the support base 24. A U-shaped support beam 27 is fixedly connected to the lower surface of the rotating shaft 26. An installation block 28 with a movable groove is fixedly connected to the inner top surface of the support beam 27. A rack rod 29 is set inside the installation block 28. The rack rod 29 meshes with the half-gear plate 25. By moving the rack rod 29 horizontally within the movable groove of the installation block 28, the meshing half-gear plate 25 drives the support base 24 to rotate, thereby driving the jet fan 1 to adjust its overall angle under the hoisting connection of the rotating rod 23. At the same time, a drive component is installed on the tunnel ceiling to control the rotation of the rotating shaft 26, thereby driving the jet fan 1 to rotate circumferentially within a limited range, adjusting the ventilation direction angle to meet the ventilation requirements inside the tunnel.

[0117] To control the jet fan 1 for precise angle adjustment, the angle adjustment mechanism 2 also includes a threaded sleeve 30 fixedly connected to the upper surface of the rack 29. The inner surface of the mounting block 28 is rotatably connected to the adjusting screw 31 via a bearing. The threaded sleeve 30 is threaded onto the outer surface of the adjusting screw 31. The outer surface of the mounting block 28 is fixedly mounted with a drive motor 32. The outer surface of the output shaft of the drive motor 32 is fixedly connected to the outer surface of the adjusting screw 31 via a coupling. The decision and control module controls the drive motor 32 so that it controls the adjusting screw 31 to rotate, thereby driving the threaded sleeve 30 to move horizontally within the movable groove of the mounting block 28, which in turn drives the rack 29 to move and thus deflects the half gear plate 25.

[0118] To regulate the airflow of the jet fan 1, the linkage mechanism 4 includes a drive seat 41 for rotating the fan blade 11. The drive seat 41 has a hollow interior. A drive head 42 is fixedly connected to one side surface of one of the drive seats 41. A main bevel gear 43 is rotatably connected to the cavity of the drive seat 41 via a bearing. The outer surface of the output shaft of the drive head 42 passes through the two drive seats 41 and is fixedly connected to the surface of the main bevel gear 43. The outer surface of the main bevel gear 43 is arranged in a ring array with driven bevel gears 44 meshing with it. The surface of the driven bevel gears 44 is fixedly connected to the mounting shaft of the corresponding fan blade 11. The motor in the drive head 42 drives the main bevel gears 43 in the two drive seats 41 to rotate, thereby causing the multiple driven bevel gears 44 to rotate, changing the deflection angle of the fan blade 11, thus adapting to the airflow in the tunnel and allowing it to rotate at a uniform speed to quickly adjust the ventilation in the tunnel.

[0119] By setting the angle adjustment mechanism 2 and the linkage mechanism 4, the ventilation effect of the jet fan 1 can be adjusted. During the adjustment process, the rack rod 29 moves horizontally in the movable groove of the mounting block 28, thereby causing the meshing half gear plate 25 to drive the support base 24 to rotate. This causes the jet fan 1 to adjust its overall angle under the hoisting connection of the rotating rod 23, so that it can accurately ventilate the target point. At the same time, the motor in the drive head 42 drives the main bevel gears 43 in the two drive seats 41 to rotate, which in turn causes multiple slave bevel gears 44 to rotate, changing the deflection angle of the fan blades 11, thereby adapting to the airflow in the tunnel and making it rotate at a uniform speed to quickly adjust the ventilation in the tunnel.

[0120] Working principle: In a specific embodiment of the present invention, the jet fan 1 with the mounting bracket 21 is hoisted by the rotating rod 23. When the ventilation system needs to adjust the installation angle of the jet fan 1 to meet the ventilation requirements in the tunnel, the decision and control module controls the drive motor 32 to control the adjusting screw 31 to rotate, which drives the threaded sleeve 30 to move horizontally in the movable groove of the mounting block 28, thereby driving the rack rod 29 to move and realize the deflection of the half gear plate 25. This drives the jet fan 1 to make overall angle adjustment under the hoisting connection of the rotating rod 23. At the same time, a drive component is installed on the top wall of the tunnel to control the rotating shaft 26 to rotate, thereby driving the jet fan 1 to rotate circumferentially within a limited range, so as to adjust the ventilation direction angle and meet the ventilation requirements in the tunnel.

[0121] In order to adjust the airflow of the jet fan 1, the motor in the head 42 drives the main bevel gear 43 in the two drive seats 41 to rotate, which in turn causes multiple slave bevel gears 44 to rotate, thereby changing the deflection angle of the fan blades 11 to adapt to the airflow in the tunnel and make them rotate at a uniform speed to quickly adjust the ventilation in the tunnel.

[0122] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A high-performance ventilation system based on digital model design, characterized in that: The ventilation system includes, Data acquisition module: responsible for collecting vehicle data, air quality data, and pedestrian traffic information from the tunnel; Data Analysis and Processing Module: Utilizes digital models to process and analyze data in real time to predict ventilation demand; Decision and control module: Based on the analysis results, control the start and stop of the fan and the air volume to ensure air quality; Feedback and Optimization Module: Provides feedback and optimization based on actual conditions and maintenance data; Environmental Simulation and Prediction Module: Based on digital models and historical data, it simulates and predicts air quality and traffic flow in the tunnel over a period of time in the future, providing optimization suggestions for the decision-making module; The feedback and optimization module includes: c1. Optimization and scheduling module: The main goal is to schedule wind turbines using the ant colony algorithm to determine the optimal working mode, running time and intensity of the wind turbines. That is, to simulate the process of ants looking for food, calculate the scheduling path of the wind turbines, and optimize the time cycle of wind turbine start-up, shutdown and operation. c2. Digital Model Module: The core task is to use computational fluid dynamics, or CFD technology, to simulate and analyze the ventilation system, thereby optimizing the design of the ventilation system. The environmental simulation and prediction module includes: d1. Data Acquisition and Fusion: Collect real-time environmental data inside the tunnel, including air quality, traffic flow, temperature and humidity, integrate past operational data, including historical air quality and traffic flow data, provide training samples for deep learning models, and clean, denoise and normalize the data to ensure the accuracy and consistency of the data, making it suitable for input to deep learning models; d2. Deep learning model: LSTM network is used to model time series data to capture long-term dependencies and predict air quality and traffic flow in the future. The input data is appropriately transformed and processed to extract useful features, ensuring that the model learns the temporal patterns of the data. The LSTM model is trained with historical data to continuously optimize the network parameters and improve prediction accuracy. d3. Simulation and Prediction Results: Predict the air quality in the tunnel over a future period, predict changes in traffic flow within the tunnel, and make accurate predictions based on traffic and air quality requirements at different time periods. d4. Predictive Analysis and Optimization Suggestions: Based on air quality forecasts, provide optimization suggestions for the ventilation system, predict the periods when ventilation needs to be strengthened, and provide traffic flow scheduling suggestions based on traffic flow forecasts to help traffic management personnel achieve efficient traffic control. The fan is a jet fan (1), which is installed in the entrance area, middle section area and end area of ​​the tunnel respectively. An angle adjustment mechanism (2) is provided on the outer surface of the casing of the jet fan (1). A linkage mechanism (4) for controlling the angle deflection of the fan blades (11) is provided inside the jet fan (1). The angle adjustment mechanism (2) controls the overall angle adjustment of the jet fan (1). The angle adjustment mechanism (2) includes a mounting frame (21) fixedly wrapped around the outer surface of the jet fan (1) housing. Movable joints (22) are symmetrically distributed on the outer surface of the mounting frame (21). A rotating rod (23) is fixedly connected to one end of the movable joint (22). The rotating rod (23) consists of two upper and lower support rods and a connecting pipe rotatably sleeved on the outer surface of the two support rods. The other movable joint (22) on the free end of the rotating rod (23) is fixedly installed on the inner wall of the tunnel by a mounting plate.

2. The high-performance ventilation system based on digital model design according to claim 1, characterized in that: The data acquisition module includes, Vehicle type recognition: Combining LiDAR and high-definition cameras installed at the tunnel entrance and middle, computer vision technology is used to classify and identify vehicles in the tunnel, and radar technology is used to measure vehicle speed. At the same time, the sensors equipped on each vehicle obtain vehicle speed data through the tunnel's lane monitoring system. Traffic flow identification: Using high-definition cameras and infrared sensors, the number of vehicles passing through the tunnel is identified, and the number of people in the flow is estimated; Air quality identification: via , , Gas concentration sensors monitor the air quality inside the tunnel in real time and provide pollutant concentration data. Then, temperature and humidity sensors monitor the temperature and humidity inside the tunnel in real time, and the data is used to assess the impact of airflow and exhaust demand.

3. A high-performance ventilation system based on digital model design according to claim 2, characterized in that: The data analysis and processing module includes, a1. Pollutant Emission and Vehicle Speed ​​Relationship Model: Based on the combination of different vehicle types and vehicle speeds, a pollutant emission model is constructed to control ventilation flow to emit these gases. The pollutant emission model is as follows: in, This indicates the amount of pollutants emitted by a single vehicle. and It is a coefficient related to vehicle type. Used to adjust the impact of vehicle speed on pollutant emissions. This indicates the baseline pollutant emissions specific to the vehicle type; a2. Accumulation Effect of Emissions: Vehicle emissions are not only related to vehicle speed, but also closely related to the accumulation effect of emissions. Factors contributing to the accumulation effect include vehicle flow, vehicle density, and airflow effects. The formula for the accumulation effect is: ,in, It is the concentration of pollutants per unit volume. It represents the number of vehicles passing through per unit of time. It is the volume of the tunnel; a3. Calculate ventilation volume: The ventilation volume is calculated based on the concentration of emissions, using the following formula: in, That is the required ventilation volume. It is a coefficient related to the efficiency of ventilation equipment and tunnel structure.

4. A high-performance ventilation system based on digital model design according to claim 3, characterized in that: The decision-making and control module includes, b1. Fan start / stop control: It is mainly based on the real-time changes in vehicle speed, pollutant concentration and vehicle flow. The specific control logic is: when the pollutant concentration exceeds the set threshold, that is, when the accumulation effect of emissions causes the pollutant concentration to reach a certain critical value, the fan will be started; conversely, when the concentration is lower than the threshold, the fan will be shut down. b2. Fan Flow Regulation: Fan flow regulation depends on pollutant concentration, vehicle speed, and traffic volume within the tunnel. The fan volume is precisely adjusted via a variable frequency drive. When pollutant concentration is too high, the fan flow increases to quickly expel pollutants. When vehicle speed is low, pollutant accumulation is significant, and the fan flow increases to accelerate pollutant discharge. The fan flow regulation formula is as follows: in, and It is an adjustment coefficient related to the efficiency of the fan and the volume of the tunnel; b3. Regional ventilation control: By installing local fans at different locations in the tunnel, the air volume in specific areas is adjusted based on real-time pollutant concentration and vehicle speed data. Specific control methods include... Entrance area: When the traffic flow exceeds the set threshold and the pollutant concentration is higher than the set high threshold, increase the air volume; otherwise, maintain the air volume or make appropriate adjustments. Mid-range zone: When the traffic flow is less than the set threshold and the pollutant concentration is lower than the set low threshold, reduce the air volume; otherwise, adjust the air volume according to the traffic flow and pollutant concentration. Terminal area: Dynamically adjust air volume to avoid pollutant accumulation or excessive emissions, i.e., flexibly control according to the instability of traffic flow and pollutant concentration; b4. Dynamic Adjustment and Adaptive Control: To cope with the constantly changing tunnel environment, the control module adopts an adaptive control algorithm, namely, using a PID control algorithm to continuously monitor vehicle speed, flow rate, and pollutant concentration parameters within the tunnel, and adjust the fan's operating status in real time according to environmental changes. The calculation formula for the PID control algorithm is: ,in, These are the control parameters of the fan. It is the error, that is, the difference between the set pollutant concentration and the current pollutant concentration. It is proportional gain. It is integral gain. It is the differential gain. It is an error function. Represents the error function Integrating from time 0 to time t calculates the cumulative sum of errors during this time period. When using a PID control algorithm to adjust the airflow of a fan, the input is: Set pollutant concentration: That is, the set safe concentration of pollutants; Actual pollutant concentration: That is, the actual concentration of pollutants measured inside the tunnel; Error calculation: ; PID controller output: The control parameters of the fan are calculated based on the error and the PID formula. This allows it to control the airflow or start / stop status of the fan; specifically, the error... A large value indicates that the pollutant concentration deviates significantly from the target, and the PID controller will output a larger air volume or a strong fan start signal. With a smaller error, the air volume or status of the fan will tend to stabilize.

5. A high-performance ventilation system based on digital model design according to claim 4, characterized in that: The angle adjustment mechanism (2) further includes a support base (24) fixedly connected to the upper surface of the casing of the jet fan (1). A half gear plate (25) is fixedly connected to the upper surface of the middle part of the support base (24). A rotating shaft (26) is provided directly above the support base (24). A U-shaped support beam (27) is fixedly connected to the lower surface of the rotating shaft (26). An installation block (28) with a movable groove is fixedly connected to the inner top surface of the support beam (27). A rack rod (29) is provided inside the installation block (28). The rack rod (29) meshes with the half gear plate (25).

6. A high-performance ventilation system based on digital model design according to claim 5, characterized in that: The angle adjustment mechanism (2) further includes a threaded sleeve (30) fixedly connected to the upper surface of the rack (29), an adjusting screw (31) rotatably connected to the inner surface of the mounting block (28) via a bearing, the threaded sleeve (30) being threaded onto the outer surface of the adjusting screw (31), a drive motor (32) being fixedly mounted on the outer surface of the mounting block (28), and the outer surface of the output shaft of the drive motor (32) being fixedly connected to the outer surface of the adjusting screw (31) via a coupling.

7. A high-performance ventilation system based on digital model design according to claim 6, characterized in that: The linkage mechanism (4) includes a drive seat (41) for rotating the fan blade (11), and the interior of the drive seat (41) is hollow. A drive head (42) is fixedly connected to one side surface of one of the drive seats (41). A main bevel gear (43) is rotatably connected to the cavity of the drive seat (41) through a bearing. The outer surface of the output shaft of the drive head (42) passes through the two drive seats (41) and is fixedly connected to the surface of the main bevel gear (43). The outer surface of the main bevel gear (43) is arranged in a ring array with driven bevel gears (44) meshing with it. The surface of the driven bevel gear (44) is fixedly connected to the mounting shaft of the corresponding fan blade (11).

Images