A Tunnel Fan Energy Saving Control Method, System, Storage Medium and Program Product

Abstract

A tunnel fan energy-saving control method, system, storage medium and program product, which relates to the field of general control or regulation systems. In this method, historical train flow data is obtained, and the predicted train flow in the next time period is calculated based on the historical train flow data; real-time gas concentration data and wind speed and direction data are collected; based on the aerodynamic model, predicted train flow, real-time gas concentration data and wind speed and direction data, the theoretical gas concentration increment is calculated; according to the theoretical gas concentration increment and the pollutant diffusion model, the pollutant diffusion trend is calculated; the target section is determined according to the pollutant diffusion trend and the preset gas concentration threshold; according to the position information of the target section and the pollutant diffusion trend, the minimum number of tunnel fans to be turned on and the corresponding minimum rotation speed are calculated; a fan control instruction is generated according to the minimum number of fans to be turned on and the minimum rotation speed. This application achieves the effect of reducing the energy consumption of tunnel fans while maintaining the ventilation effect of the tunnel.

Description

Technical Field

[0001] This application belongs to the field of general control or regulation systems, and particularly relates to an energy-saving control method, system, storage medium, and program product for tunnel fans. Background Art

[0002] During the construction and operation of tunnels, it is necessary to ventilate through fans to ensure the air quality and construction environment inside the tunnels. Currently, existing tunnel fans generally operate at a fixed frequency and are controlled by manually or remotely issuing opening or closing commands. This control method is difficult to optimize the exhaust efficiency of the shafts and is also difficult to perform intelligent control based on factors such as gas concentration, wind speed and direction, train type, and traffic flow, resulting in low ventilation efficiency and high energy consumption.

[0003] In related technologies, gas concentration sensors, wind speed and direction sensors, etc. can be set inside the tunnels to collect the environmental parameters inside the tunnels in real time, and the operating state of the fans can be automatically adjusted according to the collected data, realizing the automatic control of tunnel ventilation and improving the ventilation efficiency.

[0004] However, in situations such as when a train passes through, since the train will compress the air inside the tunnel when passing through, accelerating the air circulation rate, it is difficult to predict the changing trend of pollutant concentration, and thus it is difficult to maintain the ventilation effect of the tunnel in the most energy-saving way, increasing the energy consumption of the tunnel fans. Summary of the Invention

[0005] This application provides an energy-saving control method, system, storage medium, and program product for tunnel fans, which is used to reduce the energy consumption of tunnel fans while maintaining the ventilation effect of the tunnels.

[0006] In a first aspect, this application provides an energy-saving control method for tunnel fans, which obtains historical train flow data within a preset time period from a database and calculates the predicted train flow for the next time period based on the historical train flow data;

[0007] Collect real-time gas concentration data and wind speed and direction data within a preset time period, and the real-time gas concentration data includes carbon monoxide concentration, nitrogen dioxide concentration, ozone concentration, and dust concentration;

[0008] Calculate the theoretical gas concentration increment for the next time period based on the aerodynamic model, predicted train flow, real-time gas concentration data, and wind speed and direction data;

[0009] Calculate the pollutant diffusion trend in different sections of the tunnel according to the theoretical gas concentration increment and the pollutant diffusion model;

[0010] Compare the gas concentration values corresponding to the pollutant diffusion trend with the preset gas concentration threshold to obtain the target section that needs to adjust ventilation;

[0011] According to the position information of the target section and the pollutant diffusion trend, calculate the minimum number of tunnel fans to be turned on and the corresponding minimum rotation speed.

[0012] Generate a fan control instruction based on the minimum number of fans to be turned on and the minimum rotation speed, so that the tunnel fans with the minimum number of fans to be turned on control the gas concentration in the target section not to exceed the preset gas concentration threshold according to the fan control instruction.

[0013] Adopting the above technical solution, by obtaining historical train flow data from the database to calculate the predicted train flow, combining the real-time collected gas concentration and wind speed and direction data, calculating the theoretical gas concentration increment in the next time period based on the aerodynamic model, and then using the pollutant diffusion model to analyze the pollutant diffusion trend in each section of the tunnel, the system can predict in advance the distribution change of pollutants. On this basis, determine the target section by comparing the pollutant diffusion trend with the preset gas concentration threshold, and calculate the minimum number of fans to be turned on and the minimum rotation speed according to the position information of the target section and the pollutant diffusion trend, so as to generate an accurate fan control instruction. This prediction-based control method makes the adjustment of the ventilation volume more accurate. While ensuring that the gas concentration in the target section does not exceed the preset threshold, it reduces the energy consumption by minimizing the number of fans turned on and the rotation speed, and thus achieves the effect of reducing the energy consumption of the tunnel fans while maintaining the ventilation effect of the tunnel.

[0014] Combined with some embodiments of the first aspect, in some embodiments, calculating the theoretical gas concentration increment in the next time period based on the aerodynamic model, predicted train flow, real-time gas concentration data and wind speed and direction data specifically includes:

[0015] Determine the train operation plan in the next time period according to the predicted train flow, and the train operation plan includes the train passing time, train type and running speed;

[0016] Based on the aerodynamic model, calculate the waveform parameters of the air compression wave and expansion wave generated by each train type at different running speeds, and the waveform parameters include the wave peak value, wave valley value and duration;

[0017] According to the waveform parameters of the air compression wave and expansion wave, combined with the geometric characteristics of the tunnel, calculate the instantaneous air velocity field at each moment in the next time period;

[0018] Overlay and calculate the instantaneous air velocity field with the real-time gas concentration data and wind speed and direction data to obtain the convective diffusion field of the gas;

[0019] Establish a mass conservation equation according to the convective diffusion field, and obtain the theoretical predicted value of the gas concentration in each section of the tunnel in the next time period by solving the mass conservation equation;

[0020] The difference between the theoretically predicted gas concentration value and the currently measured concentration value is used as the theoretical gas concentration increment.

[0021] With the above technical solution, by determining the train operation plan according to the predicted train flow, calculating the waveform parameters of the air compression wave and expansion wave under different train types and operating speeds based on the aerodynamic model, calculating the instantaneous air velocity field in combination with the tunnel geometric characteristics, and superimposing and calculating with the real-time gas concentration data and wind speed and direction data to obtain the convective diffusion field, and finally obtaining the theoretical gas concentration increment by solving the mass conservation equation. This calculation method takes into account the influence of the dynamic air flow changes caused by train operation on pollutant diffusion, making the prediction of gas concentration increment more accurate. By establishing a physical model to describe the essential process of pollutant diffusion, the calculation results can reflect the actual influence of factors such as train operation and tunnel structure on gas concentration distribution, improving the pertinence and effectiveness of subsequent ventilation control, being able to better adapt to the influence brought by train speed and vehicle type changes, and improving the adaptability of the control system to dynamic working conditions.

[0022] Combined with some embodiments of the first aspect, in some embodiments, the pollutant diffusion trends in different sections of the tunnel are calculated according to the theoretical gas concentration increment and the pollutant diffusion model, specifically including:

[0023] The tunnel is divided into several calculation sections according to the structural characteristics of the tunnel, and a pollutant transfer network model of the calculation section is established, and virtual monitoring points are set at the boundaries of each calculation section;

[0024] For each calculation section, the initial diffusion rate of pollutants is calculated based on the theoretical gas concentration increment;

[0025] According to the pollutant diffusion model, transfer functions of various pollutants between adjacent calculation sections are constructed, and the transfer functions include temperature gradient coefficients, humidity influence factors, and wall adsorption coefficients;

[0026] The pollutant concentrations at each virtual monitoring point are iteratively calculated using the transfer function to obtain the diffusion law of pollutants;

[0027] Based on the diffusion law, the pollutant concentration change trend curves of each calculation section are fitted by the least square method;

[0028] According to the slope and curvature of the pollutant concentration change trend curve, the pollutant diffusion trends of each calculation section are determined.

[0029] Adopting the above technical solution, by dividing the tunnel into calculation sections and establishing a pollutant transmission network model, calculating the initial diffusion rate of pollutants at virtual monitoring points, using a transfer function including a temperature gradient coefficient, a humidity influence factor, and a wall adsorption coefficient to describe the transfer law of pollutants between adjacent sections, obtaining the pollutant diffusion trend through iterative calculation and curve fitting, considering the influence of environmental factors such as temperature, humidity, and wall adsorption on pollutant diffusion, making the prediction of the diffusion trend more in line with the actual situation. By setting virtual monitoring points at the boundaries of the calculation sections for iterative calculation, the number of actual monitoring points required is reduced, while ensuring the calculation accuracy. The pollutant concentration change trend curve obtained by fitting with the least squares method can smooth the noise influence in the discrete data and extract the main law of pollutant diffusion, providing a reliable basis for subsequent ventilation control, reducing the limitation of the traditional diffusion model that ignores the influence of environmental factors, and improving the accuracy of diffusion trend prediction.

[0030] Combined with some embodiments of the first aspect, in some embodiments, the method for establishing the pollutant transmission network model is as follows: The space of the tunnel is divided into multiple grid nodes at a preset interval to form calculation units, and the historical monitoring data of the calculation units are collected, including historical monitoring data of gas concentration data, air flow parameter data, and environmental parameter data. The historical monitoring data are divided into a training data set and a verification data set according to a preset ratio. Based on the training data set, with the gas concentration data, air flow parameter data, and environmental parameter data at the current moment as input features and the gas concentration data at the next moment as the output feature, a pollutant transmission network model is trained, and the pollutant transmission network model is verified using the verification data set. When the root mean square error between the prediction result and the measured result of the pollutant transmission network model is less than the preset error value, the pollutant transmission network model is output.

[0031] Adopting the above technical solution, by dividing the tunnel space into grid nodes to form calculation units, training the pollutant transmission network model using the gas concentration data, air flow parameter data, and environmental parameter data in the historical monitoring data, and verifying the model using the verification data set to ensure that the root mean square error of the model prediction result meets the accuracy requirements. This data-driven modeling method captures the non-linear characteristics and complex correlation relationships in the pollutant transmission process through learning a large amount of historical data. Compared with the simplified theoretical model, this method makes full use of the information contained in the measured data, making the model more suitable for the actual working conditions. The root mean square error is used as an evaluation index in the model verification process, establishing a clear accuracy control standard, improving the reliability of the model in practical applications, and thus improving the accuracy of pollutant transmission characteristic prediction.

[0032] In combination with some embodiments of the first aspect, in some embodiments, according to the position information of the target section and the pollutant diffusion trend, the minimum number of tunnel fans to be turned on and the corresponding minimum speed are calculated, specifically including:

[0033] Obtain the fan distribution information upstream and downstream of the target section, where the fan distribution information includes the position coordinates, rated power, and maximum air volume of the fans;

[0034] Determine the minimum ventilation volume of the target section according to the pollutant diffusion trend;

[0035] Calculate the ventilation volume - energy consumption relationship curve of a single fan at different speeds;

[0036] According to the minimum ventilation volume requirement, use the dynamic programming method to calculate the total energy consumption of different fan combination schemes;

[0037] Select the fan combination scheme with the minimum total energy consumption to obtain the minimum number of fans to be turned on and the minimum speed.

[0038] By adopting the above - mentioned technical solution, by obtaining the fan distribution information upstream and downstream of the target section and determining the minimum ventilation volume according to the pollutant diffusion trend, combining the ventilation volume - energy consumption relationship curve of a single fan at different speeds, and using the dynamic programming method to calculate the total energy consumption of different fan combination schemes, and then selecting the fan combination scheme with the minimum total energy consumption, the optimal control of fan operation can be achieved on the premise of meeting the ventilation requirements. By considering the spatial distribution characteristics and performance parameters of the fans, a mapping relationship between the ventilation volume demand and the fan operation parameters is established, reducing the energy waste caused by excessive fan opening quantity or too high speed. By optimizing different fan combination schemes through the dynamic programming algorithm, the most energy - efficient operation scheme that can meet the minimum ventilation volume requirement of the target section can be found, reducing the system operation cost while ensuring the ventilation effect.

[0039] In combination with some embodiments of the first aspect, in some embodiments, after generating the fan control instruction according to the minimum number of fans to be turned on and the minimum speed, the method further includes:

[0040] Collect the real - time gas concentration change rate in the target section after the tunnel fan adjustment;

[0041] When the real - time gas concentration change rate is greater than the preset change rate threshold, calculate the pulsation period and pulsation amplitude of the gas concentration in the target section;

[0042] In the case of determining that there is an eddy dead zone in the target section according to the pulsation period and pulsation amplitude, determine the fan group to be adjusted according to the position of the eddy dead zone;

[0043] Adopt an alternating start - stop method to perform pulsed ventilation control on the fan group to be adjusted to eliminate the eddy dead zone.

[0044] With the above technical solution, by collecting the real-time gas concentration change rate in the target section after the fan adjustment and calculating the pulsation characteristics of the gas concentration when the change rate exceeds the threshold, the problem of ventilation dead zones can be detected in a timely manner. When it is determined that there is an eddy current dead zone, an alternating start-stop pulse ventilation control method is adopted, which can break the eddy current structure and improve the ventilation effect. By monitoring the dynamic change characteristics of the gas concentration, a quantitative index for identifying the eddy current dead zone is established. The pulse ventilation control can change the airflow field structure periodically, generate a forced disturbance effect, destroy the stable existence conditions of the eddy current dead zone, promote gas mixing and diffusion, improve the control accuracy and ventilation efficiency of the ventilation system, and ensure the uniformity of the air quality in the tunnel space.

[0045] Combined with some embodiments of the first aspect, in some embodiments, a pulse ventilation control is performed on the fan group to be adjusted in an alternating start-stop manner, which specifically includes:

[0046] The fan group is divided into several fan subgroups, and each fan subgroup includes at least two adjacent tunnel fans;

[0047] Calculate one-fourth of the pulsation period as the basic switching time;

[0048] The fan subgroups are alternately operated in sequence according to a preset sequence, and the alternate operation is repeated until the eddy current dead zone is eliminated. The alternate operation of each fan subgroup is to increase the speed of the fan subgroup to the maximum speed and run for a basic switching time, and then reduce the speed of the fan subgroup to the minimum speed and run for a basic switching time.

[0049] With the above technical solution, by dividing the fan group into subgroups containing adjacent fans, determining the basic switching time based on the pollutant concentration pulsation period, and performing alternate operations on the fan subgroups using a preset sequence, precise control of the eddy current dead zone is achieved. By coordinating the speed changes of multiple fan subgroups, an orderly airflow pulsation is formed in terms of time and space, generating a directional airflow disturbance effect. Using one-fourth of the pulsation period as the basic switching time ensures that the disturbance intensity matches the inherent characteristics of the eddy current structure, improving the eddy current breaking efficiency. The alternate operation mode of the fan subgroups maintains sufficient disturbance intensity, realizing reasonable utilization of energy while ensuring the ventilation effect.

[0050] In a second aspect, an embodiment of the present application provides a tunnel fan energy-saving control system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions to cause the system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0051] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions that, when running on a system, cause the system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0052] In a fourth aspect, an embodiment of the present application provides a computer program product, characterized in that when the computer program product runs on a system, it causes the system to execute the method described in any possible implementation manner in the first aspect.

[0053] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0054] 1. The present application provides a method for energy-saving control of tunnel fans. By obtaining historical train flow data from a database to calculate the predicted train flow, combining the gas concentration and wind speed and direction data collected in real time, calculating the theoretical gas concentration increment in the next time period based on the aerodynamic model, and then using the pollutant diffusion model to analyze the pollutant diffusion trend in each section of the tunnel, the system can predict in advance the distribution change of pollutants. On this basis, by comparing the pollutant diffusion trend with the preset gas concentration threshold to determine the target section, and calculating the minimum number of fans to be turned on and the minimum speed according to the position information of the target section and the pollutant diffusion trend, an accurate fan control instruction is generated. This prediction-based control method makes the adjustment of the ventilation volume more accurate. While ensuring that the gas concentration in the target section does not exceed the preset threshold, it reduces energy consumption by minimizing the number of fans turned on and the speed, and thus achieves the effect of reducing the energy consumption of tunnel fans while maintaining the ventilation effect of the tunnel.

[0055] 2. The present application provides a method for energy-saving control of tunnel fans. By obtaining the fan distribution information upstream and downstream of the target section and determining the minimum ventilation volume according to the pollutant diffusion trend, combining the ventilation volume and energy consumption relationship curve of a single fan at different speeds, and using the dynamic programming method to calculate the total energy consumption of different fan combination schemes, the fan combination scheme with the minimum total energy consumption is selected, which can achieve the optimal control of fan operation on the premise of meeting the ventilation requirements. By considering the spatial distribution characteristics and performance parameters of the fans, a mapping relationship between the ventilation volume demand and the fan operation parameters is established, reducing the energy waste caused by too many fans being turned on or too high a speed. By optimizing different fan combination schemes through the dynamic programming algorithm, the most energy-saving operation scheme that can meet the minimum ventilation volume requirement of the target section can be found, reducing the system operation cost while ensuring the ventilation effect.

[0056] 3. The present application provides an energy-saving control method for tunnel fans. By collecting the real-time gas concentration change rate in the target section after the fan adjustment and calculating the pulsation characteristics of the gas concentration when the change rate exceeds the threshold, the problem of ventilation dead zones can be detected in a timely manner. When it is determined that there is an eddy dead zone, an alternating start-stop pulse ventilation control method is adopted, which can break the eddy structure and improve the ventilation effect. By monitoring the dynamic change characteristics of the gas concentration, a quantitative index for identifying the eddy dead zone is established. The pulse ventilation control can change the airflow field structure periodically, generate a forced disturbance effect, destroy the stable existence conditions of the eddy dead zone, promote gas mixing and diffusion, improve the control accuracy and ventilation efficiency of the ventilation system, and ensure the uniformity of the air quality in the tunnel space. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 FIG. is a schematic flowchart of an energy-saving control method for tunnel fans in an embodiment of the present application.

[0058] Figure 2 FIG. is a schematic flowchart of a control method based on the identification and elimination of eddy dead zones in an embodiment of the present application.

[0059] Figure 3 FIG. is a schematic structural diagram of an entity device of an energy-saving control system for tunnel fans provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular forms "a", "an", "the", "above", "said", "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any and all possible combinations including one or more of the listed items.

[0061] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0062] The following uses an embodiment and combines Figure 1 to describe an energy-saving control method for tunnel fans in an embodiment of the present application:

[0063] Please refer to Figure 1, which is a schematic flow chart of an energy-saving control method for a tunnel fan in an embodiment of the present application.

[0064] S101. Obtain historical train flow data within a preset time period from a database, and calculate the predicted train flow for the next time period based on the historical train flow data;

[0065] The system obtains historical train flow data within a preset time period from the database, and calculates the predicted train flow for the next time period based on the historical train flow data. Specifically, the system can set a preset time period, such as 1 hour, 2 hours, etc., and then query the number of trains passing through at each moment within the preset time period from the database to form historical train flow data. Then, the system can use time series prediction algorithms to model the historical train flow data. Commonly used time series prediction algorithms include autoregressive moving average model (ARMA), autoregressive integrated moving average model (ARIMA), long short-term memory network (LSTM), etc. By training, a train flow prediction model is obtained. Inputting the time interval of the next time period, the predicted train flow for the next time period can be obtained.

[0066] In practical applications, the operation of tunnel trains usually has certain periodic rules. For example, trains are dense during peak hours in the morning and evening, and sparse during non-peak hours. Therefore, it is feasible and accurate to use historical data for flow prediction. However, sudden events (such as train failures, bad weather, etc.) will disrupt the normal train operation rules, resulting in large deviations in train flow prediction. To solve this problem, the system can introduce an emergency detection mechanism to monitor the train operation status in real time. If abnormal situations such as train delays and suspensions are detected, the parameter adaptive adjustment of the prediction model is triggered to generate an updated train flow prediction result.

[0067] S102. Collect real-time gas concentration data and wind speed and direction data within a preset time period;

[0068] The system collects real-time gas concentration data and wind speed and direction data within a preset time period. The real-time gas concentration data includes carbon monoxide concentration, nitrogen dioxide concentration, ozone concentration, and dust concentration.

[0069] The system collects real-time gas concentration data and wind speed and direction data within a preset time period. The real-time gas concentration data includes carbon monoxide concentration, nitrogen dioxide concentration, ozone concentration, and dust concentration. Specifically, the system can deploy several sensors in the tunnel, including CO sensors, NO2 sensors, O3 sensors, PM2.5 sensors, and wind speed and direction sensors, to collect various parameters at a certain time interval (such as 1 minute) to form real-time environmental monitoring data. The collected data is uploaded to the tunnel environment monitoring platform in real time through a wireless communication network for subsequent data analysis and processing.

[0070] To ensure the reliability and integrity of the monitoring data, the system can regularly calibrate and maintain the sensors, and replace the aging or damaged sensors in a timely manner. Meanwhile, the system can adopt multi-sensor data fusion technology to perform weighted averaging on the data of multiple sensors for the same monitoring index, reducing the measurement error of a single sensor. When there is data missing from a certain sensor, the system can also repair the data through interpolation methods to ensure the continuity of the data.

[0071] S103. Calculate the theoretical gas concentration increment for the next time period based on the aerodynamic model, predicted train flow, real-time gas concentration data, and wind speed and direction data.

[0072] The system calculates the theoretical gas concentration increment for the next time period based on the aerodynamic model, predicted train flow, real-time gas concentration data, and wind speed and direction data, specifically including: determining the train operation plan for the next time period according to the predicted train flow, where the train operation plan includes the train passing time, train type, and running speed; calculating the waveform parameters of the air compression wave and expansion wave generated by each train type at different running speeds based on the aerodynamic model, where the waveform parameters include the wave peak value, wave trough value, and duration; calculating the instantaneous air velocity field at each moment within the next time period according to the waveform parameters of the air compression wave and expansion wave, combined with the geometric characteristics of the tunnel; superimposing and calculating the instantaneous air velocity field with the real-time gas concentration data and wind speed and direction data to obtain the convective diffusion field of the gas; establishing a mass conservation equation based on the convective diffusion field and solving the mass conservation equation to obtain the theoretical predicted value of the gas concentration in each section of the tunnel for the next time period; taking the difference between the theoretical predicted value of the gas concentration and the current measured concentration value as the theoretical gas concentration increment.

[0073] This step uses the aerodynamic model, combined with the predicted train flow, real-time gas concentration data, and wind speed and direction data, to calculate the theoretical gas concentration increment in each area of the tunnel for the next time period. Specifically, the system first determines the train operation plan for the next time period according to the predicted train flow, including parameters such as the passing time, train type, and running speed of each train. Then, the system calculates the waveform characteristics of the air compression wave and expansion wave generated by different types of trains at different speeds based on the aerodynamic model, including the wave peak value, wave trough value, and duration. Next, the system calculates the distribution of the instantaneous air velocity field inside the tunnel at each moment within the next time period according to the waveform parameters of the compression wave and expansion wave, combined with the geometric characteristics of the tunnel. Finally, the system performs superimposed analysis on the instantaneous air flow field with the real-time gas concentration data and wind speed and direction data, establishes and solves the mass conservation equation, obtains the theoretical predicted value of the gas concentration in each section of the tunnel for the next time period, and takes the difference between it and the current measured concentration value as the theoretical gas concentration increment.

[0074] In the implementation of this step, the selection and parameter setting of the aerodynamic model are crucial. Commonly used tunnel air flow models include one-dimensional unsteady flow models, three-dimensional turbulence models, etc. Different models have their own advantages and disadvantages in terms of calculation accuracy and efficiency. The system needs to select a suitable aerodynamic model according to the actual situation of the tunnel, such as cross-sectional shape, length, fan layout, etc., and determine and verify the model parameters through on-site measured data. At the same time, the aerodynamic characteristics of the train also need to be modeled separately according to different vehicle types and speed grades. For complex train formations and passing scenarios, the system also needs to consider the aerodynamic interference effects between vehicles.

[0075] The theoretical calculation results of this step provide important prior knowledge for the subsequent analysis of pollutant diffusion trends. However, due to the complexity of the actual situation, there may be certain deviations between the calculation results and the real situation. To improve the prediction accuracy, the system can introduce data assimilation technology to dynamically fuse the model calculation results with the measured data and continuously update and correct the model parameters. In addition, for the special environments in local areas inside the tunnel, such as the tunnel entrance, slope, and obstacles, the system can also make targeted corrections to the airflow parameters to improve the reliability of the overall calculation results.

[0076] S104. Calculate the pollutant diffusion trends in different sections of the tunnel according to the theoretical gas concentration increment and the pollutant diffusion model;

[0077] The system calculates the pollutant diffusion trends in different sections of the tunnel according to the theoretical gas concentration increment and the pollutant diffusion model, specifically including: dividing the tunnel into several calculation sections according to the structural characteristics of the tunnel and establishing a pollutant transfer network model for the calculation sections, with virtual monitoring points set at the boundaries of each calculation section; for each calculation section, calculating the initial diffusion rate of pollutants based on the theoretical gas concentration increment; constructing transfer functions for various pollutants between adjacent calculation sections according to the pollutant diffusion model, where the transfer functions include temperature gradient coefficients, humidity influence factors, and wall adsorption coefficients; using the transfer functions to perform iterative calculations on the pollutant concentrations at each virtual monitoring point to obtain the diffusion law of pollutants; based on the diffusion law, using the least squares method to fit and obtain the pollutant concentration change trend curves for each calculation section; and determining the pollutant diffusion trends for each calculation section according to the slopes and curvatures of the pollutant concentration change trend curves.

[0078] Among them, the method for establishing the pollutant transmission network model is as follows: The space of the tunnel is divided into multiple grid nodes at a preset interval to form calculation units, and historical monitoring data of the calculation units are collected, including historical monitoring data of gas concentration data, air flow parameter data, and environmental parameter data. The historical monitoring data are divided into a training data set and a validation data set according to a preset ratio. Based on the training data set, with the gas concentration data, air flow parameter data, and environmental parameter data at the current moment as input features and the gas concentration data at the next moment as the output feature, a pollutant transmission network model is trained, and the validation data set is used to verify the pollutant transmission network model. When the root mean square error between the prediction result and the measured result of the pollutant transmission network model is less than the preset error value, the pollutant transmission network model is output.

[0079] In this step, the system needs to predict the pollutant diffusion trend in different sections of the tunnel according to the theoretical gas concentration increment calculated in the previous step and in combination with the pollutant diffusion model. First, the system divides the tunnel into several calculation sections according to the structural characteristics of the tunnel, such as length, cross-section, bifurcation, etc., and sets virtual monitoring points at the boundaries of each section. Then, the system calculates the initial diffusion rate of pollutants in each section based on the theoretical gas concentration increment. Next, the system constructs a mathematical function for pollutant transfer between adjacent sections according to the pollutant diffusion model, which comprehensively considers various influencing factors such as temperature gradient, humidity, and wall adsorption. Finally, the system uses the transfer function to perform iterative calculations on the pollutant concentrations at each virtual monitoring point to obtain the diffusion law of pollutants in space and time, and further fits to obtain the pollutant concentration change trend curve for each section, and judges the pollutant diffusion trend according to the slope and curvature of the curve.

[0080] In the selection of the pollutant diffusion model, the system can adopt theoretical models such as classical convection-diffusion equations and concentration kinetics equations, or can combine the actual monitoring data of the tunnel environment and apply machine learning algorithms to construct a data-driven diffusion prediction model. For example, the system can use algorithms such as support vector machines and random forests, with the historical concentration data and wind speed and direction data at each monitoring point inside the tunnel as features, to train a spatio-temporal prediction model of pollutant concentration. At the same time, in order to improve the generalization performance of the model, the system can also introduce transfer learning technology and use the monitoring data in other similar tunnel environments to pre-train and fine-tune the model.

[0081] The predicted pollutant diffusion trend in this step is crucial for subsequent ventilation control strategies. However, due to the dynamic changes and complexity of the internal environmental parameters in the tunnel, static pollutant diffusion models may be difficult to accurately depict the actual situation. To address this issue, the system can introduce an online learning mechanism to continuously optimize and update the model based on real-time monitoring data. For example, when an abnormal change in pollutant concentration is detected in a certain section, the system can appropriately adjust the transfer function parameters of that section to reflect the effects of factors such as wall adsorption and chemical reactions. In addition, the system can also use incremental learning algorithms to quickly update local model parameters without retraining the entire model to adapt to the dynamic changes in the tunnel environment.

[0082] S105. Compare the gas concentration value corresponding to the pollutant diffusion trend with a preset gas concentration threshold to obtain the target section that needs ventilation adjustment;

[0083] In this step, the system compares the pollutant diffusion trends of each section predicted in the previous step with the preset gas concentration threshold, identifies the sections that exceed the threshold, and determines them as the target sections that need to be focused on for ventilation adjustment. The preset gas concentration threshold is usually set according to industry standards. The system can set different concentration thresholds for different types of pollutants (such as carbon monoxide, nitrogen dioxide, etc.).

[0084] When the system performs the threshold comparison, it can adopt various judgment criteria. For example, it can compare the average value or maximum value of the pollutant concentration in the section with the threshold, or consider factors such as the duration and frequency of exceeding the standard. For sections where the pollutant concentration shows a rapid upward trend, even if the current concentration does not exceed the standard, the system can mark them as potential target sections and initiate ventilation measures in advance. In addition, for multiple adjacent target sections, the system can perform a merging process and formulate a unified ventilation strategy to reduce the frequent start and stop of the fans and improve energy efficiency.

[0085] S106. Calculate the minimum number of tunnel fans to be turned on and the corresponding minimum speed according to the location information of the target section and the pollutant diffusion trend;

[0086] The system calculates the minimum number of tunnel fans to be turned on and the corresponding minimum speed according to the location information of the target section and the pollutant diffusion trend, specifically including: obtaining the fan distribution information upstream and downstream of the target section, where the fan distribution information includes the location coordinates, rated power, and maximum air volume of the fans; determining the minimum ventilation volume of the target section according to the pollutant diffusion trend; calculating the relationship curve between the ventilation volume and energy consumption of a single fan at different speeds; using the dynamic programming method to calculate the total energy consumption of different fan combination schemes according to the minimum ventilation volume requirement; and selecting the fan combination scheme with the minimum total energy consumption to obtain the minimum number of fans to be turned on and the minimum speed.

[0087] Based on the target section information identified in the previous step, this step optimizes the opening plan of the tunnel fans. On the premise of meeting the ventilation requirements, it minimizes the number of fan startups and operating power as much as possible to achieve the purpose of energy conservation and efficiency improvement. First, the system obtains the fan distribution information upstream and downstream of the target section, including parameters such as the installation location, rated power, and maximum output of each fan. Then, the system estimates the minimum ventilation volume required in this section in the next time period according to the pollutant diffusion trend in the target section, such as the diffusion direction and rate. Next, the system calculates the ventilation volume - energy consumption curve of a single fan at different speeds, which reflects the energy-saving characteristics of the fan. Finally, the system uses the dynamic programming algorithm to solve the fan combination optimization problem, obtains the fan opening plan with the minimum total energy consumption, and determines the minimum number of fans to be started and the lowest operating speed of each fan.

[0088] In practical applications, multiple constraints need to be considered for fan combination optimization. For example, the startup and shutdown processes of fans usually require a certain amount of time and energy consumption, and frequent startup and shutdown operations will shorten the service life of the fans. Therefore, when formulating the fan opening plan, the system needs to reasonably set the minimum operating time and minimum shutdown time of the fans to reduce the frequency of startup and shutdown. At the same time, for long tunnels with multiple fan installation points, the system needs to comprehensively consider the synergy effect between the fans to optimize the ventilation effect of the entire tunnel. In some cases, starting a fan farther away from the target section may be more energy-efficient than starting a fan nearby.

[0089] S107. Generate a fan control instruction according to the minimum number of fans to be started and the lowest speed, so that the tunnel fans with the minimum number of fans to be started control the gas concentration in the target section not to exceed the preset gas concentration threshold according to the fan control instruction.

[0090] In this step, the system generates the corresponding fan control instruction according to the optimal fan opening plan calculated in the previous step and sends it to the fan control unit in the tunnel. The control instruction includes parameters such as the startup and shutdown status, operating speed, and operating time of the fan. After receiving the instruction, the fan control unit transmits the control signal to the frequency converter to adjust the working state of the motor, thereby changing the ventilation volume of the fan. Through this process, the system realizes the precise ventilation control of the target section, maintaining the pollutant concentration in this section below the preset threshold.

[0091] During the generation and distribution of control instructions, the system needs to ensure the accuracy and timeliness of the instructions. On the one hand, the parameters of the control instructions need to match the actual working characteristics of the fan to avoid situations beyond the working range of the fan. Therefore, the system needs to calibrate and verify the rated parameters and operating curves of the fan to ensure the executability of the control instructions. On the other hand, due to the rapid changes in the internal environment of the tunnel, the control instructions need to be transmitted and executed in a timely manner to ensure the ventilation effect. The system can adopt communication protocols such as industrial Ethernet and fieldbus to achieve real-time communication and data interaction between the fan control unit and the central control system.

[0092] At the same time, to ensure the reliability and stability of ventilation control, the system can also monitor the operating status of the fan in real time and perform feedback control. The fan control unit needs to be equipped with corresponding sensors, such as speed sensors, vibration sensors, etc., to collect the operating parameters of the fan in real time and upload them to the central control system. The system analyzes the working status of the fan based on the monitored data. If abnormal situations are found, such as speed deviation, fault alarm, etc., the control strategy is adjusted in a timely manner or the standby fan is started to ensure the continuous operation of the ventilation system.

[0093] In the above embodiments, the predicted train flow is calculated by obtaining historical train flow data from the database, combined with the gas concentration and wind speed and direction data collected in real time. Based on the aerodynamic model, the theoretical gas concentration increment in the next time period is calculated, and then the pollutant diffusion trend in each section of the tunnel is analyzed using the pollutant diffusion model, enabling the system to predict in advance the distribution changes of pollutants. On this basis, the target section is determined by comparing the pollutant diffusion trend with the preset gas concentration threshold, and the minimum number of fans to be turned on and the lowest speed are calculated according to the position information of the target section and the pollutant diffusion trend, thereby generating accurate fan control instructions. This prediction-based control method makes the adjustment of the ventilation volume more accurate. While ensuring that the gas concentration in the target section does not exceed the preset threshold, the energy consumption is reduced by minimizing the number of fans turned on and the speed, and thus the effect of reducing the energy consumption of the tunnel fan while maintaining the ventilation effect of the tunnel is achieved.

[0094] The above embodiments mainly describe the basic process of the prediction-based energy-saving control method for tunnel fans. Through the analysis and prediction of data such as train flow, gas concentration, and wind speed and direction, the optimized control of fan operation is achieved. However, in actual applications, due to the complexity of the tunnel structure and the uneven distribution of airflows, local eddy dead zones may still occur, affecting the ventilation effect. To solve this problem, a control method based on the identification and elimination of eddy dead zones is introduced below. As a supplement and improvement to the basic control process, this method can further improve the control accuracy and efficiency of the ventilation system. The following combines Figure 2 , to describe a control method based on the identification and elimination of eddy dead zones in the embodiments of the present application: Please refer toFigure 2 , which is a schematic flowchart of a control method based on eddy current dead zone identification and elimination in an embodiment of the present application.

[0095] S201. Collect the real-time gas concentration change rate in the target section after the tunnel fan is adjusted.

[0096] The system collects the real-time gas concentration change rate in the target section after the tunnel fan is adjusted. Specifically, after performing step S107 to optimize the control of the fan in the target section, the system continuously monitors the change of the gas concentration in this section, calculates the change rate of the gas concentration per unit time, and uses it as a dynamic index to evaluate the ventilation effect. Since the adjustment of the fan will cause the redistribution of the air flow in the tunnel, resulting in fluctuations in the pollutant concentration in the local area, the gas concentration change rate can more sensitively reflect the air flow disturbance in the section.

[0097] To calculate the real-time gas concentration change rate, the system can adopt the method of a sliding window. Taking a fixed time interval (such as 1 minute) as the window length, continuously collect the gas concentration values at multiple moments, and obtain the average change rate in this time period through the ratio of the difference between the concentration means of two adjacent time windows to the time interval. Considering the randomness of the gas concentration fluctuations, the system can also set a smoothing coefficient for the change rate, perform weighted averaging on the change rates of multiple consecutive time windows, and reduce the influence of accidental factors.

[0098] S202. When the real-time gas concentration change rate is greater than the preset change rate threshold, calculate the pulsation period and pulsation amplitude of the gas concentration in the target section.

[0099] When the real-time gas concentration change rate is greater than the preset change rate threshold, the system calculates the pulsation period and pulsation amplitude of the gas concentration in the target section. Among them, the preset change rate threshold is a reference value set according to the tunnel ventilation design standard and operation experience, which represents the gas concentration fluctuation range under normal ventilation conditions. When the actual change rate exceeds this threshold, it means that there may be abnormal situations such as air flow disorder or pollutant aggregation in the target section, and it is necessary to further analyze the change law of the gas concentration.

[0100] The pulsation period refers to the time interval in which the gas concentration shows periodic fluctuations on a relatively stable time scale, reflecting the circulation period of pollutants inside the tunnel. The pulsation amplitude refers to the concentration difference between two adjacent wave peaks (or wave troughs), reflecting the fluctuation range of the pollutant concentration. The system can adopt the method of spectrum analysis, convert the time series data of the gas concentration to the frequency domain space, obtain the dominant frequency component through power spectral density estimation, and then calculate the corresponding pulsation period according to the dominant frequency. At the same time, the system can adopt the peak-valley detection algorithm to automatically identify the local extreme points of the concentration sequence data, and calculate the pulsation amplitude through the concentration difference between adjacent extreme points.

[0101] In practical applications, since air flow pulsation is a complex fluid mechanics phenomenon, it is affected by many factors (such as tunnel section shape, fan layout, traffic conditions, etc.), and its manifestations and laws may be diverse. In order to improve the recognition accuracy of pulsation characteristics, the system can establish a pulsation feature library for different working conditions and use pattern matching methods to achieve automatic recognition. For example, clustering algorithms are used to classify historical data and extract typical features of various pulsation patterns. When new detection data arrives, its similarity with various patterns is calculated and assigned to the category with the greatest similarity. In addition, the system can also use machine learning algorithms (such as support vector machines, random forests, etc.) to establish a discriminant model for pulsation characteristics, and dynamically update the judgment rules for pulsation characteristics through continuous training and optimization of the model.

[0102] S203, when it is determined that there is an eddy current dead zone in the target section according to the pulsation period and the pulsation amplitude, determining the wind turbine group to be adjusted according to the position of the eddy current dead zone;

[0103] When judging the existence of eddy current dead zone in the target section based on the pulsation period and pulsation amplitude, the system determines the fan group to be adjusted based on the location of the eddy current dead zone. Among them, the eddy current dead zone refers to a closed or semi-closed airflow loop formed in a local area of ​​the tunnel, which leads to insufficient gas exchange in the area, difficulty in the diffusion of pollutants, and continuous increase in concentration. The causes of the formation of eddy current dead zones are relatively complex, which are related to structural factors such as the slope and corners of the tunnel, as well as dynamic factors such as vehicle operation and fan layout.

[0104] The general basis for judging the existence of eddy dead zones is: long pulsation period (such as more than 10 minutes) and large pulsation amplitude (such as peak-to-valley difference exceeding 50%). This means that the pollutants have been circulating in this area for a long time and the cumulative effect is more significant, and it is likely that a relatively stable eddy structure has been formed. In addition, the system can also comprehensively consider the temperature and humidity distribution in the section, and analyze the airflow streamlines and flow velocity distribution in the section in combination with the fluid mechanics model to further verify the existence and scope of the eddy dead zone.

[0105] The following methods can be used to locate the eddy current dead zone: deploy a high-density sensor network in the target section to achieve refined monitoring of gas concentration; perform three-dimensional spatial interpolation on the gas concentration distribution in the section to obtain a continuous concentration distribution surface; use image processing methods (such as threshold segmentation, edge detection, etc.) to analyze the concentration distribution surface to identify high-value and low-value areas of pollutant concentration; match the high-value concentration area with the tunnel CAD model to determine the specific location and range of the eddy current dead zone.

[0106] On this basis, the system can combine the layout of the fans adjacent to the eddy current area and preferably select the fans that have the greatest impact on the ventilation effect in this area as the fan groups to be adjusted. For example, the fans closest to the upstream and downstream of the eddy current area, the fans at the corner positions of the eddy current area, etc. By focusing on controlling these fans, the local ventilation effect can be improved to the greatest extent.

[0107] S204. Perform pulsating ventilation control on the fan groups to be adjusted in an alternating start-stop manner to eliminate the eddy current dead zone.

[0108] The system performs pulsating ventilation control on the fan groups to be adjusted in an alternating start-stop manner to eliminate the eddy current dead zone, which specifically includes: dividing the fan groups into several fan subgroups, each fan subgroup including at least two adjacent tunnel fans; calculating one-fourth of the pulsation period as the basic switching time; performing rotation operations on each fan subgroup in sequence according to a preset sequence, and repeating the rotation operations until the eddy current dead zone is eliminated. The rotation operation of each fan subgroup is to increase the rotation speed of the fan subgroup to the maximum rotation speed and run for a basic switching time, and then reduce the rotation speed of the fan subgroup to the minimum rotation speed and run for a basic switching time.

[0109] The system performs pulsating ventilation control on the fan groups to be adjusted in an alternating start-stop manner to eliminate the eddy current dead zone. It specifically includes the following steps: dividing the fan groups into several fan subgroups, each fan subgroup including at least two adjacent tunnel fans; calculating one-fourth of the pulsation period as the basic switching time; performing rotation operations on each fan subgroup in sequence according to a preset sequence, and repeating the rotation operations until the eddy current dead zone is eliminated. The rotation operation of each fan subgroup is to increase the rotation speed of the fan subgroup to the maximum rotation speed and run for a basic switching time, and then reduce the rotation speed of the fan subgroup to the minimum rotation speed and run for a basic switching time.

[0110] The basic idea is to form an alternating pressure field and flow velocity field around the eddy current area through the pulsating operation of the fan group, break the original eddy current balance structure, and promote the accelerated diffusion of pollutants in the dead zone. Due to the inertial effect of the eddy current, the continuous operation of a single fan is difficult to completely eliminate the eddy current dead zone. Therefore, the alternating start-stop control of the combined fans is adopted, and the air flow effects in multiple positions and directions can be used to improve the local ventilation condition more efficiently and flexibly.

[0111] In practical applications, the division of the fan subgroups needs to take into account the feasibility and economy of variable-frequency speed regulation to avoid losses caused by frequent start-stop of the equipment. The selection of the basic switching time needs to balance the requirements of pulse effect and energy consumption optimization. That is, the fan operation time should be long enough to form an effective local air flow impact, and at the same time, the high-speed operation time of the fan should be shortened as much as possible to save power consumption. In addition, the system can dynamically adjust the switching frequency and switching amplitude (such as the rotational speed change gradient) of the fan subgroups according to the pollutant concentration level in the eddy current area to achieve more refined ventilation control.

[0112] On this basis, the system can further optimize the rotation order and combination mode of the fan subgroups. For example, according to the relative relationship between the eddy current area and the fan position, different control strategies are adopted for the upstream and downstream fans. The downstream fans focus on eliminating the eddy current wake, and the upstream fans focus on blocking the root cause of the eddy current. Another example is to match different scales of fan combinations for different intensity levels of eddy current dead zones. More fan combinations are enabled in the strong eddy current area, and fewer fan combinations are enabled in the weak eddy current area, etc. The system can establish an optimal fan combination model, and through statistical analysis of historical control effects, train the best fan combination schemes for various eddy current dead zones to form an intelligent strategy library, which can be quickly matched and called according to the real-time monitored eddy current state information.

[0113] In the above embodiments, by collecting the real-time gas concentration change rate in the target section after the fan adjustment and calculating the pulsation characteristics of the gas concentration when the change rate exceeds the threshold, the ventilation dead zone problem can be detected in time. When it is judged that there is an eddy current dead zone, the pulse ventilation control method of alternating start-stop is adopted, which can break the eddy current structure and improve the ventilation effect. By monitoring the dynamic change characteristics of the gas concentration, a quantitative index for eddy current dead zone identification is established. The pulse ventilation control can change the air flow field structure periodically, generate a forced disturbance effect, and can destroy the stable existence conditions of the eddy current dead zone, promote gas mixing and diffusion, improve the control accuracy and ventilation efficiency of the ventilation system, and ensure the uniformity of the air quality in the tunnel space.

[0114] The following describes the system in the embodiments of the present invention application from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of a tunnel fan energy-saving control system provided by the embodiments of the present application.

[0115] It should be noted that Figure 3 The structure of the system shown is only an example and should not bring any restrictions to the functions and usage scopes of the embodiments of the present invention.

[0116] Such as Figure 3As shown, the system includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the Read-Only Memory (ROM) 302 or the program loaded from the storage section 308 into the Random Access Memory (RAM) 303, such as executing the method in the above embodiment. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An Input / Output (I / O) interface 305 is also connected to the bus 304.

[0117] The following components are connected to the I / O interface 305: an input section 306 including a camera, an infrared sensor, etc.; an output section 307 including a Liquid Crystal Display (LCD) and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage section 308 as needed.

[0118] Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the Central Processing Unit (CPU) 301, various functions defined in the present invention are executed.

[0119] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0121] As another aspect, the present invention also provides a computer-readable storage medium, which may be included in the system described in the above embodiments; or may exist alone without being assembled into the system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of a system, the system implements the method provided in the above embodiments.

[0122] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0123] As used in the above embodiments, depending on the context, the term "when..." can be interpreted to mean "if...", or "after...", or "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" can be interpreted to mean "if determining...", or "in response to determining...", or "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

[0124] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive), etc.

[0125] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by relevant hardware instructed by a computer program. This program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The aforementioned storage media include: various media such as ROM, random access memory (RAM), magnetic disks, or optical discs that can store program codes.

Claims

1. A tunnel fan energy-saving control method, characterized in that: include: Acquire historical train flow data within a preset time period from a database, and calculate the predicted train flow for the next time period based on the historical train flow data; Collecting real-time gas concentration data and wind speed and direction data within the preset time period, wherein the real-time gas concentration data includes carbon monoxide concentration, nitrogen dioxide concentration, ozone concentration and dust concentration; The theoretical gas concentration increment for the next time period is calculated based on an aerodynamic model, the predicted train flow, the real-time gas concentration data and the wind speed and direction data, wherein the aerodynamic model is a one-dimensional unsteady flow model or a three-dimensional turbulence model; The pollutant diffusion trends in different sections of the tunnel are calculated based on the theoretical gas concentration increment and the pollutant diffusion model, wherein the pollutant diffusion model is a convection diffusion equation theoretical model or a concentration kinetic equation theoretical model; Comparing the gas concentration value corresponding to the pollutant diffusion trend with the preset gas concentration threshold to obtain the target section that needs to adjust ventilation; According to the location information of the target section and the diffusion trend of the pollutants, the minimum number of tunnel fans to be opened and the corresponding minimum speed are calculated; A fan control instruction is generated according to the minimum number of opened fans and the minimum rotation speed, so that the tunnel fans with the minimum number of opened fans control the gas concentration in the target section according to the fan control instruction so that the gas concentration does not exceed the preset gas concentration threshold.

2. The method according to claim 1, characterized in that The step of calculating the theoretical gas concentration increment for the next time period based on the aerodynamic model, the predicted train flow, the real-time gas concentration data and the wind speed and direction data specifically includes: Determine the train operation plan for the next period according to the predicted train flow, wherein the train operation plan includes train passing time, train type and running speed; Calculate the waveform parameters of air compression waves and expansion waves generated by each type of train at different running speeds based on the aerodynamic model, wherein the waveform parameters include wave peak value, wave trough value and duration; Calculating the instantaneous airflow velocity field at each moment in the next time period according to the waveform parameters of the air compression wave and the expansion wave and in combination with the geometric characteristics of the tunnel; The instantaneous airflow velocity field is superimposed and calculated with the real-time gas concentration data and the wind speed and direction data to obtain a gas convection diffusion field; A mass conservation equation is established according to the convection diffusion field, and a theoretical predicted value of the gas concentration in each section of the tunnel in the next time period is obtained by solving the mass conservation equation; The difference between the theoretical predicted value of the gas concentration and the current measured concentration value is taken as the theoretical gas concentration increment.

3. The method according to claim 1, characterized in that The pollutant diffusion trends in different sections of the tunnel are calculated based on the theoretical gas concentration increment and the pollutant diffusion model, specifically including: Dividing the tunnel into a number of calculation sections according to the structural characteristics of the tunnel, and establishing a pollutant transmission network model of the calculation sections, with a virtual monitoring point being set at the boundary of each calculation section; For each of the calculation sections, calculating the initial diffusion rate of the pollutant based on the theoretical gas concentration increment; Constructing a transfer function of each type of pollutant between adjacent calculation sections according to the pollutant diffusion model, wherein the transfer function includes a temperature gradient coefficient, a humidity influence factor, and a wall adsorption coefficient; Iteratively calculating the pollutant concentration of each virtual monitoring point using the transfer function to obtain the diffusion law of the pollutant; Based on the diffusion law, the least square method is used to fit the pollutant concentration change trend curve of each calculation section; The pollutant diffusion trend of each of the calculation sections is determined according to the slope and curvature of the pollutant concentration change trend curve.

4. The method according to claim 3, characterized in that The method for establishing the pollutant transmission network model is as follows: dividing the space of the tunnel into multiple grid nodes according to a preset spacing to form a computing unit, collecting historical monitoring data of the computing unit, the historical monitoring data including gas concentration data, airflow parameter data and environmental parameter data, dividing the historical monitoring data into a training data set and a verification data set according to a preset ratio, based on the training data set, taking the gas concentration data, airflow parameter data and environmental parameter data at the current moment as input features, and taking the gas concentration data at the next moment as output features, training to obtain the pollutant transmission network model, and using the verification data set to verify the pollutant transmission network model, when the root mean square error between the predicted result of the pollutant transmission network model and the measured result is less than a preset error value, outputting the pollutant transmission network model.

5. The method according to claim 1, characterized in that The step of calculating the minimum number of tunnel fans to be opened and the corresponding minimum speed according to the location information of the target section and the diffusion trend of the pollutants specifically includes: Obtaining wind turbine distribution information upstream and downstream of the target section, wherein the wind turbine distribution information includes location coordinates, rated power, and maximum air volume of the wind turbine; Determining the minimum ventilation volume of the target section according to the pollutant diffusion trend; Calculate the relationship curve between ventilation volume and energy consumption of a single fan at different speeds; According to the minimum ventilation volume requirement, a dynamic programming method is used to calculate the total energy consumption of different fan combination schemes; the fan combination scheme with the minimum total energy consumption is selected to obtain the minimum number of units opened and the minimum speed.

6. The method according to claim 1, characterized in that After generating the fan control instruction according to the minimum number of units started and the minimum speed, the method further includes: Collecting the real-time gas concentration change rate of the target section after the tunnel fan is adjusted; When the real-time gas concentration change rate is greater than a preset change rate threshold, calculating the pulsation period and pulsation amplitude of the gas concentration in the target section; In the case where it is determined that there is an eddy current dead zone in the target section according to the pulsation period and the pulsation amplitude, determining the wind turbine group to be adjusted according to the position of the eddy current dead zone; The fan unit to be adjusted is subjected to pulse ventilation control by alternately starting and stopping to eliminate the eddy current dead zone.

7. The method according to claim 6, characterized in that The pulse ventilation control of the fan group to be adjusted by using an alternating start-stop method specifically includes: Divide the fan group into a plurality of fan subgroups, each of which includes at least two adjacent tunnel fans; calculate one quarter of the pulsation period as the basic switching time; The fan sub-groups are rotated in turn according to a preset sequence, and the rotation operation is repeated until the eddy current dead zone is eliminated. The rotation operation of each fan sub-group is to increase the speed of the fan sub-group to the maximum speed and run it for a basic switching time, and then reduce the speed of the fan sub-group to the minimum speed and run it for a basic switching time.

8. A tunnel fan energy-saving control system, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to execute the method according to any one of claims 1 to 7.

Images