Tunnel sectional exhaust method, system, medium and product based on train working conditions

Abstract

A tunnel sectional exhaust air method, system, medium and product based on train operating conditions, which relates to the technical field of ventilation. The method includes: dividing a target tunnel into multiple control sections according to the fan installation configuration of the target tunnel; obtaining the train passing data and train configuration information of the control sections, and calculating the smoke growth value of the control sections within a preset time period; collecting the smoke concentration data of the control sections, and calculating the ventilation demand index of the control sections in combination with the smoke growth value; collecting the wind direction parameters of the control sections, and determining the ventilation control relationship between adjacent control sections based on the ventilation demand index and the wind direction parameters, and generating a ventilation cooperation plan; according to the ventilation cooperation plan, calculating the operating parameters of the tunnel fans in each control section, and sending control instructions corresponding to the operating parameters to the tunnel fans. Implementing this application can adjust the operation of the fans according to the actual train operation conditions and optimize the ventilation effect.

Description

Technical Field

[0001] This application relates to the field of ventilation technology, and particularly to a method, system, medium, and product for sectional exhaust in a tunnel based on train operating conditions. Background Art

[0002] With the rapid development of the railway transportation industry, tunnels, as an important part of railway lines, the performance of their ventilation systems directly affects the safety of train operation and the comfort of passengers. Especially in long tunnels, the exhaust gas and dust emitted by trains will affect the tunnel safety, making the control of the tunnel ventilation system an urgent technical problem to be solved.

[0003] In the related art, the tunnel ventilation control system mainly adopts a timing control method, turning on or off the ventilation equipment according to a preset time period. This control method installs a fixed number of axial fans in the tunnel and conducts ventilation operations according to a preset operation schedule. At the same time, some systems are also equipped with simple environmental monitoring devices. When the detected air quality index exceeds the threshold, the ventilation equipment in the corresponding area is started for ventilation.

[0004] However, since the operation of the ventilation equipment completely depends on the preset schedule or a single environmental parameter threshold, the ventilation pressure will increase sharply during peak train operation periods, and the ventilation capacity of the ventilation equipment is insufficient in a short time, resulting in poor ventilation effect. Summary of the Invention

[0005] This application provides a method, system, medium, and product for sectional exhaust in a tunnel based on train operating conditions, which is used to adjust the operation of fans and optimize the ventilation effect.

[0006] In a first aspect, this application provides a method for sectional exhaust in a tunnel based on train operating conditions, which is applied to a ventilation control system. The method includes: dividing a target tunnel into multiple control sections according to the fan installation configuration of the target tunnel; obtaining the train passing data and train configuration information of the control section, and calculating the flue gas growth value of the control section within a preset time period; collecting the flue gas concentration data of the control section, and calculating the ventilation demand index of the control section in combination with the flue gas growth value; collecting the wind direction parameters of the control section, and determining the ventilation control relationship between adjacent control sections based on the ventilation demand index and the wind direction parameters to generate a ventilation coordination plan; calculating the operation parameters of the tunnel fans in each control section according to the ventilation coordination plan, and sending control instructions corresponding to the operation parameters to the tunnel fans.

[0007] In the above embodiments, the ventilation control system divides the tunnel into multiple control sections, and performs ventilation control by combining train passing data, flue gas data, and wind direction parameters. This distributed control method achieves the effect of dynamically adjusting the operation of the fans according to the actual ventilation requirements, can accurately calculate the ventilation requirements of each section, and through the collaborative control between sections, ensures the optimization of the ventilation effect, avoiding the problem of unsatisfactory ventilation effect caused by the traditional fixed-time and fixed-quantity control method.

[0008] Combined with some embodiments of the first aspect, in some embodiments, the step of dividing the target tunnel into multiple control sections according to the fan installation configuration of the target tunnel specifically includes: determining the installation positions and rated power parameters of each tunnel fan unit in the target tunnel according to the fan installation configuration of the target tunnel; calculating the installation spacing and ventilation coverage range of each tunnel fan unit based on the installation position and rated power parameters; taking adjacent tunnel fan units with an installation spacing less than a preset distance threshold and overlapping ventilation coverage ranges as a fan control group, and dividing all tunnel fan units into multiple fan control groups; dividing the target tunnel into multiple control sections based on the multiple fan control groups.

[0009] In the above embodiments, the ventilation control system divides the control sections based on the fan installation position, power parameters, installation spacing, and ventilation coverage range, so that the fans in each control section can form an effective ventilation collaborative working group, ensuring the effective superposition of the ventilation effects between adjacent fans and improving the overall ventilation efficiency.

[0010] Combined with some embodiments of the first aspect, in some embodiments, the step of collecting the wind direction parameters of the control section, determining the ventilation control relationship between adjacent control sections based on the ventilation demand index and the wind direction parameters, and generating a ventilation collaboration plan specifically includes: sorting the control sections in descending order according to the ventilation demand index to determine the target control section with the largest ventilation demand; collecting the wind direction parameters of the target control section, determining the ventilation air flow direction of the target control section between adjacent control sections, and determining multiple collaborative control sections based on the ventilation air flow direction; calculating the demand index difference between the target control section and the collaborative control sections based on the ventilation demand index; when the demand index difference is greater than a preset difference threshold, adjusting the ventilation demand indexes of the target control section and the collaborative control sections to generate a ventilation collaboration plan.

[0011] In the above embodiments, the ventilation control system focuses on controlling the section with the largest ventilation demand and performs collaborative adjustment in combination with the ventilation air flow direction of adjacent sections, achieving the optimal allocation of ventilation resources. When the demand index deviation is large, the system will adjust the ventilation plan to ensure that the high-demand sections obtain sufficient ventilation support.

[0012] In some embodiments in combination with some embodiments of the first aspect, the steps of obtaining the train passing data and train configuration information of the control section and calculating the smoke growth value of the control section within a preset time period specifically include: obtaining the train operation data on the rail transit dispatching system, and determining the train passing data and train configuration information of the control section based on the train operation data; when determining that the passing train is a diesel locomotive based on the train passing data, determining the smoke emission rate of the diesel locomotive based on the train configuration information; and calculating the smoke growth value of the control section within the preset time period according to the train passing data and the smoke emission rate.

[0013] In the above embodiments, the ventilation control system accurately calculates the smoke growth value by analyzing the smoke emission of diesel locomotives, provides reliable data support for ventilation control, and can adopt corresponding ventilation control strategies according to the characteristics of different types of trains, improving the accuracy of ventilation.

[0014] In some embodiments in combination with some embodiments of the first aspect, after the steps of obtaining the train operation data on the rail transit dispatching system and determining the train passing data and train configuration information of the control section based on the train operation data, the method further includes: when determining that the passing train is an electric locomotive based on the train passing type, determining the running speed and vehicle type information of the electric locomotive based on the train configuration information; determining the air flow disturbance coefficient of the electric locomotive based on the running speed and vehicle type information; collecting the smoke concentration data of the control section, and calculating the smoke growth value of the control section within the preset time period according to the smoke concentration data and the air flow disturbance coefficient.

[0015] In the above embodiments, the ventilation control system calculates the impact of the air flow disturbance effect generated by the operation of the electric locomotive on the smoke diffusion, realizing a more comprehensive assessment of ventilation requirements.

[0016] In some embodiments in combination with some embodiments of the first aspect, after the steps of calculating the operation parameters of the tunnel fans in each control section according to the ventilation cooperation plan and sending control commands corresponding to the operation parameters to the tunnel fans, the method further includes: obtaining the real-time smoke concentration in each control section and constructing a smoke change curve; calculating the ventilation effect score of each control section based on the smoke change curve; taking the control section with the ventilation effect score lower than the preset score threshold as an abnormal control section, and detecting the fan operation status of all tunnel fans in the abnormal control section; and when the fan operation status is abnormal, sending a maintenance prompt message to the management terminal.

[0017] In the above embodiments, the ventilation control system realizes the intelligent monitoring and timely maintenance of the ventilation system by real-time monitoring of the smoke change curve and ventilation effect scoring, discovers abnormal situations in time and conducts fan status detection, can prevent ventilation failures, and ensure the continuous and stable operation of the ventilation system.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the steps of calculating the operating parameters of the tunnel fans in each control section according to the ventilation cooperation plan and sending control instructions corresponding to the operating parameters to the tunnel fans, the method further includes: obtaining the operating duration and energy consumption data of each tunnel fan in the target control section; calculating the performance degradation coefficient of the tunnel fans based on the operating duration and energy consumption data; calculating the estimated maintenance time of the tunnel fans according to the performance degradation coefficient and the maintenance records of the tunnel fans, and generating a maintenance plan.

[0019] In the above embodiments, the ventilation control system formulates a maintenance plan by analyzing the operating duration of the fans, energy consumption data, and performance degradation, realizes preventive maintenance of the fan equipment, can reduce maintenance costs, and improve the reliability of the ventilation system.

[0020] In a second aspect, an embodiment of the present application provides a ventilation 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, and the one or more processors call the computer instructions to enable the ventilation control system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product containing instructions, which, when the computer program product runs on a ventilation control system, enables the ventilation control system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions, which, when the instructions run on a ventilation control system, enable the ventilation control system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the ventilation control system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. Due to the adoption of the distributed ventilation control method based on section division, by obtaining train passing data, smoke concentration and wind direction parameters in real time and carrying out collaborative control in combination with the ventilation demand index, it is possible to flexibly adjust the operation parameters of the fan according to the actual operating conditions, effectively solving the problem in the related technology that the ventilation effect is not ideal due to simply relying on timing control or single environmental parameter threshold control. Furthermore, the reasonable allocation of ventilation resources and the optimization of ventilation effect are realized, enabling the ventilation system to accurately obtain and process the actual ventilation demands of each section, and avoiding unnecessary energy waste.

[0026] 2. Due to the adoption of the section collaborative control method based on the ventilation demand index, by determining the target section with the largest ventilation demand, analyzing the ventilation air flow direction and the difference in demand index between it and adjacent sections, and dynamically adjusting the ventilation plan, it is possible to achieve the precise allocation of ventilation resources, realize the overall collaborative optimization of the ventilation system, ensure that the high-demand sections can obtain sufficient ventilation support, and at the same time improve the overall ventilation efficiency through the ventilation air flow guidance between sections.

[0027] 3. Due to the adoption of the ventilation control method for analyzing the air flow disturbance effect of electric locomotives, by analyzing the train running speed and vehicle type information, calculating the air flow disturbance coefficient, and carrying out ventilation demand assessment in combination with the smoke concentration data, it is possible to more accurately reflect the impact of train operation on the tunnel environment, effectively solving the problem in the related technology that the ventilation control accuracy is insufficient due to ignoring the air flow disturbance effect of electric locomotives. Furthermore, more precise and scientific ventilation control is realized, improving the accuracy and efficiency of ventilation control. Brief Description of the Drawings

[0028] Figure 1 is a flowchart of a method for sectional exhaust ventilation in a tunnel based on train conditions in an embodiment of the present application;

[0029] Figure 2 is another flowchart of a method for sectional exhaust ventilation in a tunnel based on train conditions in an embodiment of the present application;

[0030] Figure 3 is a schematic structural diagram of an entity device of a ventilation control system in an embodiment of the present application. Detailed Embodiments

[0031] 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 of the present application, the singular forms "a", "one", "above-mentioned", "the", and "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.

[0032] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating 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 specified, the meaning of "a plurality" is two or more.

[0033] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0034] A certain extra-long railway tunnel is 15 kilometers in total length, with an average of 180 trains passing through daily. Among them, diesel locomotives account for 30%. There are 24 groups of axial fans installed in the tunnel for ventilation. Due to the extremely long tunnel length and the piston effect caused by the dense passing of trains, it is difficult to control the air quality inside the tunnel. Especially during the summer peak period, when multiple diesel locomotives pass through in a short time, the CO concentration in some sections once reached 150 ppm, far exceeding the safety standard of 100 ppm, seriously threatening the safety of train operation.

[0035] In the related art, basic ventilation in the tunnel can be achieved by adopting a fixed-mode ventilation control based on threshold triggering. The scenario of using the tunnel sectional exhaust air method based on train conditions in the related art is introduced below.

[0036] A single-track railway tunnel adopts a traditional fixed-time and fixed-quantity ventilation control method. The system starts the ventilation equipment once every 2 hours during the period from 7:00 am to 11:00 pm every day according to the preset schedule, and each operation lasts for 30 minutes. At the same time, a CO concentration detector is installed every 500 meters in the tunnel. When the CO concentration at a certain point exceeds 120 ppm, the two nearest groups of axial fans are started for ventilation. However, due to the fixed ventilation time and parameters, the ventilation cannot be adjusted according to the actual train operation density, resulting in insufficient ventilation during the peak period and energy waste during the low period.

[0037] By adopting the tunnel sectional exhaust air method based on train conditions in the embodiments of the present application, accurate ventilation adjustment is achieved by calculating the ventilation demand index of each section in real time and dynamically adjusting the fan operation parameters, improving the ventilation efficiency and reducing the energy consumption. The scenario of using the tunnel sectional exhaust air method based on train conditions in the present application is introduced below.

[0038] A certain double-track railway tunnel adopts this solution to achieve intelligent ventilation control. The system obtains train scheduling information in real time, calculates the exhaust gas emissions of diesel locomotives and the piston effect generated by electric locomotives in advance, and conducts accurate ventilation demand prediction. For example, when the system detects that two diesel freight trains will pass through Section 3 successively within 10 minutes, it calculates that the predicted flue gas growth value in this section is 25 ppm / min. At the same time, through the distributed sensing network, it is monitored that the current air flow direction in this section shows a north-south flow, and the ventilation demand index of the adjacent Section 4 is relatively low. The system generates a coordinated solution: reduce the operating power of the north-side fan in Section 3 to 60% in advance, and at the same time adjust the south-side fan in Section 3 to operate at 90% power, avoiding the diffusion of pollutants to Section 4 while ensuring the ventilation effect. During the whole process, the system continuously monitors the real-time concentration changes in each section to ensure that the ventilation effect is always in the optimal state.

[0039] It can be seen that by adopting the tunnel sectional exhaust air method based on train conditions in the embodiment of this application, while achieving effective ventilation, it can also effectively solve the problem of poor ventilation effect in the traditional solution, thereby realizing the optimization of ventilation effect and energy utilization.

[0040] For the convenience of understanding, the method provided in this embodiment will be described in terms of its process in combination with the above scenario. Please refer to Figure 1 , which is a process schematic diagram of the tunnel sectional exhaust air method based on train conditions in the embodiment of this application.

[0041] S101. Divide the target tunnel into multiple control sections according to the fan installation configuration of the target tunnel.

[0042] Among them, the target tunnel refers to a specific tunnel that needs ventilation control; the fan installation configuration refers to information such as the installation location, power parameters, and quantity distribution of the fans in the tunnel; the control section refers to an independent ventilation control unit divided based on the fan distribution characteristics, and each control section contains one or more fan units that work together.

[0043] When initializing the tunnel ventilation control plan, the ventilation control system needs to first establish the division of control sections. Specifically, the system first obtains the installation information of all the fans in the tunnel, analyzes the spacing between adjacent fans and the overlap of ventilation coverage, and divides adjacent fans with similar ventilation capabilities and overlapping coverage into the same control section, finally forming multiple relatively independent control sections.

[0044] In some embodiments, the division of control sections can be achieved in various ways: Optionally, the system can calculate the effective ventilation radius of each fan based on the rated power and installation location of the fans, group adjacent fans with an overlap of ventilation radius exceeding a preset threshold, and complete the section division by traversing all fans; Optionally, the system can perform the division according to the geometric characteristics of the tunnel (such as slope, bend, etc.) and the distribution characteristics of ventilation requirements, combined with the installation location of the fans and manual settings, and then verify and optimize the section division plan through the actual ventilation effect. It can be understood that other division methods based on fan characteristics or tunnel characteristics can also be adopted, which are not limited herein.

[0045] S102. Obtain the train passing data and train configuration information of the control section, and calculate the smoke growth value in the control section within a preset time period.

[0046] Among them, the train passing data represents the operation status information of the trains in the control section, including train position, running speed, passing time, etc.; the train configuration information refers to the basic parameters such as the type, power system, emission standard, etc. of the trains; the preset time period represents a fixed time cycle for calculating the smoke growth value; the smoke growth value refers to the expected increase in the smoke concentration in the section due to the train operation within the preset time period.

[0047] When the ventilation control system conducts ventilation demand assessment, it is necessary to predict the impact of train operation on the air quality in the section. Specifically, the system first obtains the real-time train operation data from the rail transit dispatching system, determines the emission characteristics of each train in combination with the train configuration information, then calculates the cumulative growth of smoke within a preset time period (such as 15 minutes) based on the residence time and operation status of the trains in the section, and finally obtains the smoke growth prediction value of this section.

[0048] In some embodiments, the calculation of the smoke growth value can be achieved in various ways: Optionally, the system can establish an emission model based on the train type and operation status, obtain the cumulative emissions within the time period through integral calculation, and then calculate the concentration growth value in combination with the spatial volume of the section. It can be understood that other mathematical models or statistical methods can also be used for smoke growth prediction, which are not limited herein.

[0049] S103. Collect the smoke concentration data of the control section, and calculate the ventilation demand index of the control section in combination with the smoke growth value.

[0050] Among them, the smoke concentration data represents the smoke content information in the section collected in real time by sensors; the ventilation demand index is a dimensionless index that quantitatively represents the urgency of section ventilation after comprehensively considering the current smoke concentration and the expected growth value.

[0051] The ventilation control system needs to evaluate the ventilation requirements of a section based on real-time monitoring and prediction data. Specifically, the system collects real-time flue gas concentration data through a sensor network distributed in the section, combines these data with the flue gas growth value calculated in the previous step through weighted combination, and obtains a quantitative index reflecting the current ventilation urgency of this section through a preset demand index calculation model.

[0052] In some embodiments, the calculation of the ventilation demand index can be achieved in various ways: Optionally, the system can adopt the method of weighted summation, assign different weights to the current flue gas concentration value and the predicted growth value respectively, and obtain the final demand index through normalization processing; Optionally, the system can establish a multi-factor evaluation model, take multiple indicators such as flue gas concentration, growth prediction, and air quality standard as benchmarks, and obtain the demand index through comprehensive scoring. It can be understood that other quantitative analysis methods can also be used to calculate the ventilation demand index, which is not limited here.

[0053] Among them, when the ventilation demand index is calculated by the method of weighted summation, first, a mathematical model is established to integrate three key indicators of flue gas concentration, growth prediction, and train speed into a unified evaluation index. The system uses the exponential normalization function f(x)=100*(1-e^(-1.5x)) to map the parameter values to the range of 0-100. This function has the characteristic of gradually slowing down as the input value increases, and can better reflect the actual influence law of parameter changes on ventilation demand.

[0054] In the specific calculation, first, the current flue gas concentration C is divided by the safety concentration threshold Cs (100 ppm) to obtain the relative concentration value, the predicted 15-minute flue gas growth value ΔC is divided by the allowable growth threshold ΔCs (30 ppm) to obtain the relative growth rate, and the train speed V is divided by the tunnel speed limit value Vs (80 km / h) to obtain the relative speed value, and they are respectively substituted into the normalization function to obtain the corresponding scores. Then, according to the influence degree of each factor on ventilation demand, the corresponding weight coefficients are assigned: the current concentration and growth prediction each account for 40%, reflecting their leading role in ventilation control; the train speed accounts for 20%, reflecting its auxiliary influence on ventilation demand.

[0055] Finally, the ventilation demand index is obtained through weighted summation:

[0056] NDI=w1*f(C / Cs)+w2*f(ΔC / ΔCs)+w3*f(V / Vs).

[0057] For example, when the flue gas concentration measured at a certain moment is 75 ppm, the predicted growth value in 15 minutes is 20 ppm, and the train speed is 60 km / h, substituting into the calculation gives: f(75 / 100)=68.32, f(20 / 30)=63.21, f(60 / 80)=68.32. Finally, the ventilation demand index NDI = 0.4 * 68.32 + 0.4 * 63.21 + 0.2 * 68.32 = 66.21. The value of this index is in the medium demand range (50 - 80), indicating that the current section needs to maintain the normal ventilation mode.

[0058] The system continuously evaluates the change of ventilation demand by updating the calculation every 5 minutes. When the index exceeds 80, it promptly activates the emergency ventilation mode, and when it is below 50, it can appropriately reduce the ventilation intensity to save energy. This evaluation method based on a mathematical model not only ensures the objectivity and accuracy of the evaluation but also realizes the intelligence and precision of ventilation control.

[0059] S104. Collect the wind direction parameters of the control section. Based on the ventilation demand index and the wind direction parameters, determine the ventilation control relationship between adjacent control sections and generate a ventilation cooperation plan.

[0060] Among them, the wind direction parameters represent the direction and speed information of the air flow within the section; the ventilation control relationship refers to the ventilation air flow exchange method and influence degree between adjacent sections; the ventilation cooperation plan refers to the overall ventilation regulation strategy formulated based on the ventilation demands and air flow characteristics of multiple sections.

[0061] The ventilation control system needs to coordinate the ventilation relationships between sections to achieve overall optimal control. Specifically, the system first collects the wind direction sensor data of each section, analyzes the air flow characteristics between sections, then combines the ventilation demand index of each section, and considering the influence of the air flow direction on the ventilation effect, establishes a ventilation cooperation relationship model between sections, and finally generates an overall control plan that can achieve multi-section cooperative ventilation.

[0062] Among them, the ventilation cooperation plan constructs a mathematical model based on the pressure gradient control theory, transforming the ventilation cooperation problem of multiple sections into a pressure balance control problem.

[0063] The system determines the required fan power through the section pressure difference calculation model ΔP = ΔPf + ΔPk + ΔPw. Among them, the total pressure difference ΔP consists of the frictional pressure loss along the way ΔPf, the local pressure loss ΔPk, and the pressure increment provided by the fan ΔPw.

[0064] The pressure increment ΔPw that the fan needs to provide can be calculated by ΔPw = ΔP - (ΔPf + ΔPk). Since the relationship between the fan power P and the pressure increment and air volume is P = ΔPw·Q / η (η is the fan efficiency), the power ratio between adjacent sections can be expressed as:

[0065] Pi / Pj=(ΔPwi·Qi) / (ΔPwj·Qj);

[0066] The system relates this power ratio to the ventilation demand index (NDI): Pi / Pj=(NDIi / NDIj)^α By combining the above equations, the relationship between pressure increment and ventilation demand can be obtained:

[0067] ΔPwi / ΔPwj=(NDIi / NDIj)^α·(Qj / Qi).

[0068] For example, when the ventilation demand index of the core section is 85 and that of the adjacent section is 45, assuming that the air volume ratio of the two sections is Qj / Qi=0.8 and α is 1.5, then: ΔPwi / ΔPwj=(85 / 45)^1.5·0.8=2.31 Based on this pressure proportional relationship, combined with the measured pressure losses ΔPf and ΔPk, the system can accurately calculate the pressure increment required by the fan in each section, and then determine the required fan power. This collaborative control method based on pressure balance ensures that the pressure gradient between the sections of the ventilation system is maintained within a reasonable range of 5-10Pa, achieving the optimal allocation of ventilation resources.

[0069] S105. According to the ventilation coordination plan, the operating parameters of the tunnel fans in each control section are calculated, and control instructions corresponding to the operating parameters are sent to the tunnel fans.

[0070] Among them, the operating parameters refer to the specific parameter indicators for controlling the operation of the fan, including speed, power, start and stop status, etc.; the control instructions refer to the specific execution commands used to adjust the operating status of the fan.

[0071] The ventilation control system needs to convert the ventilation plan into specific equipment control instructions. Specifically, the system calculates the specific operating parameters that need to be adjusted for each fan based on the ventilation requirements of each section specified in the ventilation coordination plan, combined with the performance characteristics and working curve of the fan, and then converts these parameters into a standard control instruction format, which is sent to the control unit of each fan through the communication network to achieve precise adjustment of the fan's operating status.

[0072] In some embodiments, the system may adopt a fuzzy control method to dynamically adjust the operating parameters of the fan according to the degree of ventilation demand, and use a feedback control method, that is, continuously optimize the control effect through real-time feedback.

[0073] Among them, the feedback control method adopts the closed-loop control principle to achieve precise regulation of the fan. The ventilation control system first establishes a dynamic model of the ventilation effect, takes the flue gas concentration as the control target, and the fan speed as the control variable. The controller calculates the deviation from the target value by collecting the data of the flue gas sensor in real time, and calculates the required control variable adjustment value according to the proportional-integral-derivative (PID) control algorithm. Among them, the proportional term is used to quickly respond to the deviation, the integral term eliminates the steady-state error, and the derivative term improves the dynamic characteristics. The controller continuously adjusts the PID parameters according to the actual ventilation effect. When it detects that the ventilation effect is not ideal, the system will automatically increase the control action to improve the response characteristics. The whole process forms a closed-loop control by calculating the deviation, the control variable and performing the adjustment, realizing the dynamic optimization of the ventilation effect.

[0074] For example, in the actual ventilation control process, the system adopts a numerical control method based on iterative calculation to achieve precise regulation. The control process first establishes the fan characteristic equation: ΔP = k * Q², where k is the system characteristic coefficient (determined by the tunnel geometric parameters and air physical property parameters), and Q is the air volume. At the same time, there is a functional relationship between the air volume and the fan power: Q = a * P^0.5, where a is the fan characteristic coefficient.

[0075] Through these two basic equations, the system can accurately calculate the pressure distribution under different power configurations. In the tunnel space, the pressure at any position y can be calculated by the linear distribution model P(y) = P0 - ΔP * (y / L), where P0 is the starting pressure and L is the section length. The system calculates the pressure distribution every 30 seconds and adjusts the fan power in real time through the proportional-integral-derivative (PID) control algorithm.

[0076] The control equation is: P(t) = Kp * e(t) + Ki * ∫e(t)dt + Kd * de(t) / dt, where e(t) is the pressure deviation, and Kp, Ki, and Kd are the proportional, integral, and derivative coefficients respectively.

[0077] Taking a certain typical control scenario as an example, when the demand index of section 3 reaches 85, and the system detects the current flue gas concentration of 85 ppm and the air flow velocity of 3.5 m / s, first, according to the characteristic coefficient k = 0.024 Pa / (m³ / s)² and the fan coefficient a = 50 m³ / s, it is calculated that: at 90% power, the main fan can provide an air volume of 47.4 m³ / s and generate a pressure rise of 53.8 Pa; while at 60% power, the auxiliary fan provides an air volume of 38.7 m³ / s and generates a pressure rise of 35.9 Pa.

[0078] The system dynamically adjusts these parameters to ensure that the pressure difference between sections is stable at about 7.2 Pa, achieving precise ventilation control. This refined control method based on the mathematical model not only ensures the accuracy of the ventilation effect but also realizes the optimization of energy utilization.

[0079] In the above embodiment, accurate prediction of ventilation demand is achieved through comprehensive analysis of train operation data and environmental monitoring data. In practical applications, the fan of the ventilation control system also needs to be maintained predictively to ensure the normal operation of the ventilation function. The following is a supplement to the scenario of this embodiment.

[0080] The intelligent ventilation system based on this solution further introduces the function of predictive maintenance of equipment. The system continuously tracks the operating data of 12 groups of fans to establish a performance attenuation model. On one occasion, the system detected that the energy consumption data of fan No. 2 in section 5 had abnormal fluctuations in recent operation: the power consumption at the same speed increased by 15% compared with the standard value, and the amplitude of the vibration spectrum in the characteristic frequency band increased. The system calculated that the performance attenuation coefficient of the fan has reached 0.82, and predicted that a bearing failure may occur in the next 72 hours. The system adjusted the ventilation coordination plan in advance, appropriately increased the load sharing of adjacent fans, and automatically generated a maintenance work order, suggesting that the bearing be replaced during the nearest off-peak period of train operation. This predictive maintenance strategy not only avoids the ventilation risks caused by unexpected equipment shutdown, but also achieves the optimal coordination between maintenance work and train operations.

[0081] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the tunnel segmented exhaust method based on train conditions in an embodiment of the present application.

[0082] S201. Determine the installation position and rated power parameters of each tunnel fan unit in the target tunnel according to the fan installation configuration of the target tunnel.

[0083] Among them, the fan installation configuration represents the installation details of all fans in the tunnel; the tunnel fan unit refers to a single complete ventilation equipment and its supporting control device; the installation position represents the specific spatial coordinates of the fan in the tunnel; the rated power parameter refers to the designed operating power value of the fan under standard working conditions.

[0084] Before the ventilation control system starts to divide the sections, it needs to obtain the basic configuration information of the fans. Specifically, the system first reads the overall structural information of the tunnel and the fan installation drawings from the engineering database, extracts the installation coordinates, height, direction and other location information of each fan, and obtains the fan model specifications, rated power, maximum air volume and other technical parameters to establish a complete fan basic information database.

[0085] S202. Based on the installation position and rated power parameters, calculate the installation spacing and ventilation coverage of each tunnel fan unit.

[0086] Among them, the installation spacing refers to the straight-line distance between adjacent fans; the ventilation coverage range refers to the spatial range that can be reached by a single fan for effective ventilation.

[0087] The ventilation control system needs to evaluate the spatial characteristics and ventilation capacity of the fan distribution. Specifically, the system calculates the three-dimensional spatial distance between any two adjacent fans based on the fan position coordinates obtained in the previous step. At the same time, based on the rated power and installation angle of each fan, combined with the geometric characteristics of the tunnel (such as cross-sectional area, slope, etc.), the effective ventilation coverage of each fan is calculated to form a complete fan spatial distribution characteristic map.

[0088] Among them, the calculation of the effective ventilation coverage range can adopt the attenuation model based on fluid mechanics, and the effective range of the fan can be determined by establishing the velocity field distribution function.

[0089] The system uses the axial velocity attenuation formula v(x)=v0*(d0 / x)^n to describe the change of air flow velocity with distance, where v0 is the outlet velocity, d0 is the fan impeller diameter, x is the axial distance from the fan, and n is the attenuation index (generally 1.2-1.5, related to the cross-sectional characteristics of the tunnel).

[0090] When the airflow velocity decays to the specified critical value vc (usually 0.5m / s), it is defined as the boundary of the effective coverage range. In the calculation of the lateral coverage range, the system uses a Gaussian distribution model to describe the diffusion characteristics of the velocity field: v(r)=v(x)*exp(-r² / 2σ²), where r is the radial distance to the axis and σ is the diffusion coefficient (related to the fan power and installation height). By combining the axial and radial velocity distribution equations, the three-dimensional coverage model of the fan can be obtained.

[0091] For example, for an axial fan with a rated power of 75kW and an impeller diameter of 2.8m, when the outlet velocity is 25m / s, its effective axial coverage distance is about 120m, and the maximum lateral coverage radius is about 30m. The system simplifies the coverage range into an ellipsoid for numerical expression, which is convenient for subsequent segment division calculations.

[0092] In order to realize the constraint effect of the tunnel wall, the system also introduces a wall correction coefficient:

[0093] λw=1+(A0 / AT)^0.5, where A0 is the wind outlet area of ​​the fan and AT is the cross-sectional area of ​​the tunnel.

[0094] The final effective coverage range is obtained by multiplying the original calculation result by the wall correction coefficient. The correction realizes the influence of tunnel limit on airflow diffusion, making the calculation result more consistent with the actual situation.

[0095] S203. Take adjacent tunnel fan units with an installation spacing less than a preset distance threshold and overlapping ventilation coverage ranges as a fan control group, and divide all tunnel fan units into multiple fan control groups.

[0096] Among them, the preset distance threshold represents the standard value for determining whether the fan spacing is too close; a fan control group refers to a set of fans that can work together; overlapping ventilation coverage ranges means that there is an intersection in the effective ventilation areas of adjacent fans.

[0097] The ventilation control system needs to group the fans based on the spatial distribution characteristics. Specifically, the system first compares the installation spacings of all adjacent fan pairs, selects the fan pairs with spacings less than the preset threshold, then analyzes the overlapping situation of the ventilation coverage ranges of these fan pairs, divides the adjacent fans that meet the overlapping conditions into the same control group, and finally forms multiple relatively independent fan control groups. In some embodiments, the ventilation control system can give a grouping reference for the tunnel fan units, and then perform grouping settings and adjustments based on the user's input control on the graphical interface.

[0098] S204. Based on multiple fan control groups, divide the target tunnel into multiple control sections.

[0099] Among them, a control section represents a tunnel space unit that needs to be uniformly ventilated; multiple fan control groups refer to the set of fans obtained through the previous step of division.

[0100] The ventilation control system needs to convert the division result of the fan control groups into a zoning scheme for the tunnel space. Specifically, the system analyzes the spatial distribution range and ventilation coverage area of each fan control group, and combines the structural characteristics of the tunnel (such as key nodes like cross passages and emergency exits) to determine the specific boundary positions of each control section, forming a complete tunnel zoning control scheme.

[0101] In some embodiments, the division of the control sections can be achieved in multiple ways: Optionally, the system can determine the optimal demarcation points between adjacent sections through a boundary optimization algorithm based on the coverage range of the fan control groups to achieve the balance and rationality of the section division; Optionally, the system can combine the natural segmentation of the tunnel (such as slope change points, cross passage positions, etc.) and the distribution characteristics of the fan control groups to determine the control sections. It can be understood that other spatial division methods can also be used to determine the boundaries of the control sections, which are not limited here.

[0102] S205. Obtain the train operation data on the rail transit dispatching system, and determine the train passing data and train configuration information of the control section based on the train operation data.

[0103] Among them, the rail transit dispatching system refers to the central control system for managing train operations; train operation data represents information such as the real-time position, speed, and direction of the train; train passing data refers to records such as the time and speed when the train passes through a specific section; train configuration information includes basic parameters such as train type, length, and weight.

[0104] The ventilation control system needs to obtain real-time train operation status information. Specifically, the system obtains real-time train operation data, including train position, running speed, estimated arrival time, etc., through the data interface with the rail transit dispatching system, then filters out the train passing records related to this section according to the spatial range of the control section, and at the same time extracts the basic configuration information of these trains to prepare for subsequent ventilation demand calculation.

[0105] S206. When determining that the passing train is a diesel locomotive based on train passing data, determine the flue gas emission rate of the diesel locomotive based on train configuration information.

[0106] Among them, a diesel locomotive refers to a train that uses fuels such as diesel and gasoline; the flue gas emission rate represents the amount of flue gas generated per unit time; train configuration information includes engine parameters and emission standards, etc.

[0107] The ventilation control system needs to evaluate the pollutant emissions of diesel locomotives. Specifically, the system first identifies diesel locomotives through train passing data, and then calculates the real-time flue gas emission rate of the locomotive based on the engine model, power level, and emission standards in its configuration information, combined with the current operating conditions (such as idling, accelerating, and cruising).

[0108] The calculation of the flue gas emission rate uses a dynamic model based on engine operating conditions. The system first establishes an emission benchmark equation for diesel locomotives: E = Ef * P * L, where E is the emission amount (g / h), Ef is the emission factor (g / kWh), P is the engine power (kW), and L is the load factor. The emission factor represents the mass of pollutants generated when consuming 1 kilowatt-hour (kWh) of energy, and different pollutants have different emission factor values. For example: CO (carbon monoxide): 3.0 - 4.0 g / kWh; NOx (nitrogen oxides): 4.5 - 5.5 g / kWh; PM (particulate matter): 0.2 - 0.4 g / kWh; HC (hydrocarbons): 0.5 - 0.8 g / kWh.

[0109] The load factor of the engine under different operating conditions is described by a piecewise function: L = 0.2 at idling, L = 0.8 - 1.0 during acceleration, and L = 0.5 - 0.7 during cruising. The specific values are calculated in real time through train speed and gradient data.

[0110] The system uses the modified Euler method for numerical integration, and the calculation time step is taken as 1 second:

[0111] Et+1 = Et + ΔE * Δt. Among them, the emission increment ΔE needs to consider the temperature correction coefficient KT = (T / T0)^0.5 and the altitude correction coefficient KH = (P / P0)^1.2, where T and P are the real-time temperature and atmospheric pressure respectively, and T0 and P0 are the standard state parameters.

[0112] For example, for a certain type of diesel locomotive with a power of 2000 kW, its CO emission factor is 3.5 g / kWh. When it runs at a constant speed of 60 km / h on a 3-degree slope and the load factor is 0.65, after considering the corrections for a temperature of 28°C and an altitude of 500 m, the calculated emission rate is approximately 4.8 kg / h.

[0113] To improve the calculation accuracy, the system also introduces an engine warm-up correction coefficient Kw = 1 + 0.3 * exp(-t / τ), where t is the running time after the engine starts, and τ is the characteristic time constant (about 300 seconds).

[0114] The final emission rate is obtained by multiplying the reference value by each correction coefficient. This dynamic calculation method based on the influence of multiple factors can accurately reflect the emission characteristics of diesel locomotives during actual operation.

[0115] S207. Calculate the flue gas growth value in the control section within a preset time period according to the train passing data and the flue gas emission rate.

[0116] Among them, the preset time period represents the fixed time interval for calculating the flue gas growth; the flue gas growth value refers to the expected increase in the flue gas concentration within the section; the train passing data is used to determine the residence time and operating status of the train within the section.

[0117] The ventilation control system needs to predict the cumulative effect of air pollution caused by the operation of diesel locomotives. Specifically, the system determines the operation trajectory and time distribution of the locomotive within the section according to the train passing data, combines with the flue gas emission rate calculated in the previous step, calculates the cumulative emissions within the preset time period (such as 15 minutes) through time integration, and then combines with the sectional space volume and the natural ventilation effect to finally obtain the expected growth value of the flue gas concentration.

[0118] In some embodiments, the calculation of the flue gas growth value can be achieved in multiple ways: Optionally, the system can establish a flue gas diffusion model based on mass conservation, and obtain the concentration growth value through numerical integration based on the emission source intensity and the ventilation dilution effect.

[0119] Among them, the flue gas diffusion model solves the convection-diffusion control equation:

[0120] c / The pollutant concentration distribution is predicted by \(t+\nabla\cdot(uc)=\nabla\cdot(D\nabla c)+S\). Among them, the diffusion coefficient tensor \(D\) adopts an expression based on the k-ε turbulence model \(D_{ij}=C_{\mu}(k^{2} / \varepsilon)S_{ij}\), enabling the model to accurately describe the turbulent diffusion characteristics in complex flow fields. The turbulent kinetic energy \(k\) and dissipation rate \(\varepsilon\) are solved through additional transport equations, and the model constant \(C_{\mu}\) takes the standard value of 0.09. The strain rate tensor \(S_{ij}\) is calculated based on the spatial gradient of the velocity field, reflecting the deformation characteristics of the local flow field.

[0121] In numerical processing, the time term of the governing equation is discretized using an explicit format with second-order accuracy, and the spatial term selects an appropriate discretization format according to physical characteristics. Due to its hyperbolic characteristics, the upwind scheme is used for the convection term to avoid numerical oscillations; the central difference is used for the diffusion term to ensure calculation accuracy. The computational domain adopts a non-uniform grid division strategy, which is appropriately refined in the near-wall region and near the pollution source, ensuring both calculation accuracy and efficiency.

[0122] The treatment of boundary conditions also fully considers physical characteristics: the measured concentration distribution is given at the inlet, the free outflow condition is adopted at the outlet, and the zero flux condition is applied to the wall. Such boundary condition settings conform to the actual engineering situation. The source term model particularly considers the influence of train movement and describes the emission source as a three-dimensional Gaussian distribution moving with the train. The distribution function \(G(x,y,z)\) contains diffusion parameters \(\sigma_{x}\), \(\sigma_{y}\), \(\sigma_{z}\) in three directions, and these parameters are dynamically adjusted according to local airflow conditions, enabling the model to accurately reflect the diffusion process of pollutants in the tunnel space.

[0123] For example, when a certain type of diesel locomotive passes through the tunnel at a speed of 60 km / h, the system uses a non-uniform grid of \(100\times20\times20\) and a time step of 0.5 seconds for calculation. Through this numerical simulation, the predicted values of pollutant concentrations at any position in the tunnel within the next 15 minutes can be obtained, and the relative error of the prediction results can usually be controlled within 10%, providing a reliable basis for ventilation control decisions.

[0124] S208. When it is determined that the passing train is an electric locomotive based on the train passing type, the running speed and model information of the electric locomotive are determined based on the train configuration information.

[0125] Among them, an electric locomotive refers to a train driven by electric energy; the running speed refers to the real-time driving speed of the locomotive in the section; the model information includes parameters such as the external dimensions and aerodynamic characteristics of the locomotive.

[0126] The ventilation control system needs to evaluate the impact of the operation of electric locomotives on tunnel ventilation. Specifically, the system first identifies the type of electric locomotive, then extracts the key parameters of this type of locomotive from the train configuration information, and combines the real-time running speed to prepare for subsequent calculations of the airflow disturbance effect.

[0127] S209. Determine the air flow disturbance coefficient of the electric locomotive based on the running speed and vehicle type information.

[0128] Among them, the air flow disturbance coefficient represents the degree of influence of the locomotive operation on the tunnel air flow; the running speed is used to calculate the piston effect intensity; the vehicle type information is used to determine the aerodynamic characteristics of the locomotive.

[0129] The ventilation control system needs to quantify the ventilation effect generated by the operation of the electric locomotive. Specifically, based on the running speed and vehicle type parameters of the locomotive, combined with the ratio of the tunnel cross-sectional area to the locomotive cross-sectional area, the system calculates the piston effect intensity generated by the locomotive operation and converts it into a standardized air flow disturbance coefficient for evaluating its impact on tunnel ventilation.

[0130] In some embodiments, the calculation of the air flow disturbance coefficient can be achieved in various ways: Optionally, the system can obtain an accurate disturbance coefficient through a computational fluid dynamics model in combination with the aerodynamic effects of the locomotive movement; Optionally, the system can adopt a simplified empirical formula to quickly estimate the disturbance intensity based on the speed and cross-sectional ratio. It can be understood that other calculation methods can also be used to determine the air flow disturbance coefficient, which is not limited here.

[0131] Among them, a specific calculation method adopts a modified aerodynamic model. First, establish a basic disturbance coefficient expression: γ=(1-β)^(-2)·(v / v0)^α, where β is the cross-sectional blockage ratio (the ratio of the locomotive cross-sectional area to the tunnel cross-sectional area), v is the train speed, v0 is the characteristic speed (take 15m / s), and α is the speed exponent (default take 1.6). This expression reflects the basic physical mechanism of the piston effect: the disturbance intensity increases with the increase of the cross-sectional blockage ratio and increases in a power-law manner with the increase of the speed.

[0132] The basic disturbance coefficient also needs to be aerodynamically corrected, and the correction terms include the head shape coefficient Kh and the tail interference coefficient Kt: γ'=γ(1+Kh+Kt). Among them, the head shape coefficient is calculated by the ratio of the locomotive head length to the equivalent diameter: Kh=0.5(L / D)^(-0.2), which reflects the weakening effect of the head streamlined design on the disturbance; the tail interference coefficient is related to the wake region characteristics: Kt=0.3Re^(-0.1), and Re is the Reynolds number based on the vehicle length.

[0133] For example, for a certain type of locomotive, the blockage ratio of the cross-section is 0.6. When running at a speed of 80 km / h, the calculated basic disturbance coefficient is approximately 2.8, and the final disturbance coefficient after aerodynamic correction is 3.5, indicating that the locomotive operation under this condition has a significant disturbing effect on the tunnel airflow. To improve the calculation accuracy, the model can also analyze the influence of the tunnel wall roughness. By introducing the friction correction coefficient Kf = 1 + 0.15(ε / D)^0.3, where ε is the equivalent roughness, the disturbance coefficient is further adjusted.

[0134] Finally, the model will use the actually measured data as a reference for verification and correction. The system collects the measured data through the airflow velocity sensors installed in the tunnel, and calculates the actual disturbance coefficient γr = (vr - v0) / v0, where vr is the measured airflow velocity when the train passes, and v0 is the background airflow velocity. By comparing the deviation between the theoretical calculated value γ' and the measured value γr, a correction function μ = γr / γ' is established. This correction function will be updated with the continuous accumulation of data, enabling the model to continuously optimize itself during long-term operation and improve the prediction accuracy.

[0135] S210. Collect the smoke concentration data of the control section, and calculate the smoke growth value of the control section within a preset time period according to the smoke concentration data and the airflow disturbance coefficient.

[0136] Among them, the smoke concentration data represents the real-time pollutant concentration measured by the sensor; the preset time period also represents a fixed calculation cycle.

[0137] The ventilation control system needs to evaluate the comprehensive impact of the electric locomotive operation on the air quality. Specifically, the system collects the real-time smoke concentration data through the sensor network distributed in the control section, combines the airflow disturbance coefficient calculated in the previous step, and combines the local ventilation effect and dust lifting effect brought by the locomotive operation to calculate the change trend of the smoke concentration within the preset time period.

[0138] In some embodiments, the calculation of the smoke growth value can be achieved in various ways: Optionally, the system can establish a concentration change model based on airflow disturbance and predict the concentration change trend through numerical calculation; Optionally, the system can establish a statistical relationship model between the electric locomotive operation and the smoke concentration change based on historical data analysis. It can be understood that other prediction methods can also be used to calculate the smoke growth value, which is not limited here.

[0139] Among them, the calculation of the smoke growth value can adopt the dual-model fusion method, and use the airflow disturbance coefficient γ obtained in step S209 as the key input parameter.

[0140] The first model is a kinetic model based on airflow disturbance: dc / dt = -v·▽c + D▽²c + S(t). Here, c is the flue gas concentration, v is the airflow velocity field (v = v0 + γΔv, where v0 is the background airflow velocity and Δv is the velocity change caused by the disturbance), D is the turbulent diffusion coefficient, which is determined by D = νt / Sct, νt is the turbulent viscosity coefficient, Sct is the turbulent Schmidt number (taking 0.7), and S(t) is the pollutant source term, representing the pollutant generation rate per unit time. The disturbance coefficient γ directly uses the result calculated in S209 and is used to characterize the influence intensity of train movement on the airflow field.

[0141] The second model is a time series prediction model based on historical data, which constructs a mapping relationship using support vector regression (SVR): c(t + τ) = f(c(t), v(t), γ), where τ is the prediction time step (usually taking 60s); c(t) is the flue gas concentration (ppm) at time t; v(t) is the airflow velocity (m / s) at time t. The model takes the current flue gas concentration, airflow velocity, and disturbance coefficient as input variables to predict the concentration value at a future time. The kernel function uses the radial basis function: K(x, y) = exp(-||x - y||² / 2σ²), where σ is the kernel width parameter, which is determined by cross-validation (typical value is 0.8 - 1.2); ||x - y|| represents the Euclidean distance of the input vector.

[0142] The prediction results of the two models are combined through adaptive weights: c_pred = w1c_physics + w2c_svr.

[0143] The weight update equation is:

[0144] w1(k + 1) = w1(k) + η[c_true(k) - c_pred(k)]·[c_physics(k) - c_svr(k)];

[0145] w2(k + 1) = 1 - w1(k + 1).

[0146] Among them: k represents the discrete time step; η is the learning rate (taking 0.01 - 0.05); c_true is the measured concentration value; c_physics and c_svr are the prediction values of the kinetic model and the SVR model respectively.

[0147] For example, when a certain type of locomotive passes through a tunnel at a speed of 60 km / h, the airflow disturbance coefficient γ calculated in step S209 is 2.6. At this time, the measured flue gas concentration is 40 ppm. Based on this disturbance coefficient, the kinetic model predicts that the concentration will rise to 48 ppm after 15 minutes, and the predicted value of the SVR model is 45 ppm. Considering the current weights w1 = 0.45 and w2 = 0.55, the fused predicted value is 46.35 ppm, and the measured value is 47 ppm, with the prediction error within 5%.

[0148] S211. Collect the flue gas concentration data of the control section, and calculate the ventilation demand index of the control section in combination with the flue gas growth value.

[0149] Referring to step S103, the ventilation control system calculates the ventilation demand index of the control section.

[0150] S212. Collect the wind direction parameters of the control section. Based on the ventilation demand index and the wind direction parameters, determine the ventilation control relationship between adjacent control sections, and generate a ventilation cooperation plan.

[0151] Referring to step S104, the ventilation control system generates a ventilation cooperation plan.

[0152] In some embodiments, the ventilation control system performs segmented cooperation processing based on the ventilation demand, that is, sorts the control sections in descending order according to the ventilation demand index to determine the target control section with the highest ventilation demand; collects the wind direction parameters of the target control section, determines the ventilation air flow direction of the target control section between adjacent control sections, and determines multiple cooperative control sections based on the ventilation air flow direction; calculates the demand index difference between the target control section and the cooperative control sections based on the ventilation demand index; when the demand index difference is greater than the preset difference threshold, adjusts the ventilation demand indexes of the target control section and the cooperative control sections to generate a ventilation cooperation plan.

[0153] Among them, the ventilation demand index represents the real-time demand intensity of the ventilation volume in the section; the target control section refers to the section with the highest current ventilation demand; the wind direction parameter is used to represent the direction and speed of air flow; the cooperative control section represents the adjacent section that has air flow exchange with the target section; the demand index difference refers to the relative difference degree of ventilation demand between different sections; the preset difference threshold represents the standard value for triggering cooperative control.

[0154] After the ventilation system has been running for some time, it is necessary to evaluate and optimize the ventilation effect. Specifically, the system first sorts and analyzes the ventilation requirements of all control sections to find the target section with the highest ventilation demand. Then, it obtains the air flow direction information of this section through the sensor network, and combines it with the spatial structure characteristics of the tunnel to determine the upstream and downstream collaborative sections that have a ventilation coupling relationship with the target section. The system further calculates the demand difference degree between the target section and the collaborative sections. When the difference exceeds the threshold preset by the system, it indicates that the ventilation demands between sections are seriously unbalanced. At this time, the system will generate a collaborative control plan that can balance the ventilation effects of each section by adjusting the ventilation parameter configurations of each section, such as the operating power and the number of fans turned on.

[0155] For example, the ventilation system fault diagnosis adopts a multi-layer detection framework based on deep learning. The first layer uses a convolutional neural network (CNN) to extract time-frequency features. The network structure includes 3 convolutional layers (with convolutional kernel sizes of 5×5, 3×3, and 3×3 respectively) and 2 pooling layers. The input is the time-frequency diagram of the fan vibration signal (obtained by short-time Fourier transform, with a time window of 1024 points and an overlap rate of 50%). The second layer uses a long short-term memory network (LSTM) to identify time-series fault patterns, including 2 LSTM layers (each with 128 units) and 1 fully connected layer (with 64 neurons). The fault diagnosis accuracy is evaluated through a confusion matrix.

[0156] Taking the fault of a certain fan bearing as an example, the system first converts the collected vibration signal into a 64×64 time-frequency diagram, and extracts a 128-dimensional feature vector through CNN. These features are fed into the LSTM network, and the probabilities of 8 possible fault types are output. The training data set contains 1000 groups of samples for each of the normal operation and 7 typical fault states, and is trained using the Adam optimizer (learning rate 0.001, batch size 32). On the validation set, the system's recognition accuracy for the inner ring fault of the bearing reaches 96.5%, the outer ring fault 95.8%, and the rolling element fault 94.2%.

[0157] The system also introduces a confidence evaluation mechanism: calculate the information entropy H = -∑pi·log(pi) according to the probability distribution output by the network. When H is greater than the threshold Hc (taking 1.5), the system will maintain an observation state and not alarm immediately. At the same time, the model parameters are continuously updated through online learning: incremental training is performed every 24 hours using the newly added labeled data, and the learning rate is dynamically adjusted to η = η0 / (1 + kt), where k is the decay coefficient (taking 0.1).

[0158] S213. According to the ventilation collaboration plan, calculate the operating parameters of the tunnel fans in each control section, and send control instructions corresponding to the operating parameters to the tunnel fans.

[0159] Referring to step S105, the ventilation control system sends a control instruction to the tunnel fan.

[0160] In some embodiments, the ventilation control system also checks the ventilation effect, that is, obtains the real-time flue gas concentration in each control section, constructs a flue gas change curve; calculates the ventilation effect score of each control section based on the flue gas change curve; takes the control section with the ventilation effect score lower than the preset score threshold as an abnormal control section, and detects the fan operation status of all tunnel fans in the abnormal control section; when the fan operation status is abnormal, sends a maintenance prompt message to the management terminal.

[0161] Among them, the flue gas change curve represents the change trend of pollutant concentration over time; the ventilation effect score is a comprehensive index for quantitatively evaluating the ventilation effect; the preset score threshold is a standard value for judging whether the ventilation effect meets the standard; the abnormal control section represents the section that needs to be focused on because the ventilation effect does not meet the standard; the fan operation status is used to describe the working condition of the equipment; the maintenance prompt message is an alarm notice for equipment maintenance; the management terminal represents an operation platform for receiving and displaying system information.

[0162] The ventilation system needs to establish a real-time monitoring and effect evaluation mechanism to ensure the continuous and efficient operation of the system. Specifically, the system continuously collects flue gas concentration data through a sensor network distributed in each control section, records data points at fixed time intervals (such as 5 minutes), and forms a time series curve reflecting the change law of pollutants. The system calculates the ventilation effect score from multiple dimensions such as the concentration decline rate, control stability, and target value achievement degree according to the preset scoring rules. When it is found that the score of a certain section is lower than the threshold set by the system, an abnormal diagnosis program is started to comprehensively detect all fan equipment in this section, including electrical parameters, mechanical characteristics, control response, etc. If an abnormality is detected in the fan, the system generates a detailed maintenance prompt message including the fault type, severity, recommended measures, and expected impact, and pushes it to the relevant maintenance personnel in real time through the management terminal.

[0163] Among them, the ventilation effect score adopts a percentage weighted calculation method, mainly aggregating three core indicators. First is the concentration decline efficiency, which is obtained by calculating the reduction amplitude of the pollutant concentration per unit time. The system uses an exponential decay model to fit the measured data, converts the ratio of the actual decline rate to the theoretical optimal rate into a score, and the weight accounts for 40%. Second is the control stability, which is evaluated by calculating the standard deviation of the concentration fluctuation. The system sets ±5% of the target concentration as the stable interval, and determines the score according to the proportion of the time when the measured value is within the stable interval, and the weight accounts for 35%. Finally is the energy consumption efficiency, which is calculated by comparing the ratio of the actual energy consumption to the theoretical minimum energy consumption. The system calculates the theoretical minimum energy consumption based on the thermodynamic model, maps the actual energy consumption to the score interval after comparison, and the weight accounts for 25%. For example, if the concentration in a certain section drops from 100 ppm to 30 ppm within 15 minutes, the standard deviation during this period is 2 ppm, and the energy consumption ratio is 1.2, then the final score is 85 points.

[0164] Among them, the training of the exponential decay model is based on historical ventilation data. The inputs include the initial pollutant concentration, the fan operation parameters, and the measured concentration change curve. The decay coefficient and the time constant are determined by least squares fitting. The training objective is to minimize the mean square error between the model prediction value and the measured value. The exponential decay model adopts the mathematical form of C(t)=C0*e^(-λt), where C(t) is the pollutant concentration at time t, C0 is the initial concentration, and λ is the decay coefficient. By inputting the current pollutant concentration and the fan parameters, the exponential decay model can output the predicted concentration change curve for evaluating the ventilation effect.

[0165] In addition, the abnormal diagnosis program activated when the score is low adopts a multi-level progressive diagnosis strategy, gradually analyzing in depth from the device layer to the system layer. This abnormal diagnosis program will first collect the basic operation data of the fan, including electrical parameters such as current, voltage, and power factor, and mechanical parameters such as rotational speed, vibration, and temperature, and extract the characteristic spectrum through fast Fourier transform. Then the program compares these characteristics with the pre-established normal operation mode library and calculates the deviation values of each parameter. When it is found that a certain parameter exceeds the normal range, the program starts the in-depth diagnosis module, which analyzes the correlation between parameters through a neural network model and combines with the expert rule library to infer the possible fault types and causes. Finally, the program generates a diagnosis report containing specific maintenance suggestions according to the nature and severity of the fault. For example, when it is detected that the fan vibration spectrum has an abnormal peak in a specific frequency band and is accompanied by an increase in bearing temperature, the system will judge it as a bearing fault and recommend replacement.

[0166] S214. Obtain the operation duration and energy consumption data of each tunnel fan in the target control section.

[0167] Among them, the running duration represents the cumulative working time of the fan; the energy consumption data represents the power consumption during the operation of the fan; the target control section refers to a specific section that needs to be maintained and evaluated.

[0168] The ventilation control system needs to collect the fan operation status data for performance evaluation. Specifically, the system collects the running time statistics and real-time power data of each fan through the fan controller, records the energy consumption change trend of the fan under different working conditions, and establishes a complete operation status database to provide basic data support for subsequent performance evaluation.

[0169] In some embodiments, the collection and processing of operation data can be achieved in various ways: Optionally, the system can record the running time and power curve of the fan through real-time monitoring equipment, and evaluate the energy consumption trend through data analysis; Optionally, the system can establish an equipment operation log and regularly count the cumulative working time and average energy consumption level of the fan.

[0170] S215. Calculate the performance decay coefficient of the tunnel fan based on the running duration and energy consumption data.

[0171] Among them, the performance decay coefficient represents the degree of reduction of the actual performance of the fan relative to the rated performance; the running duration is used to evaluate the service life of the equipment; the energy consumption data is used to judge the change of operating efficiency.

[0172] The ventilation control system needs to evaluate the performance status of the fan. Specifically, the system calculates the performance decay degree, that is, the performance decay coefficient, by comparing the actual operating efficiency of the fan with the rated efficiency based on the collected running duration and energy consumption data, and comprehensively determines the performance decay coefficient of each fan in combination with the service life of the equipment and working environment factors.

[0173] Among them, the calculation of the performance decay coefficient is mainly based on the energy efficiency comparison method and the state parameter analysis method. The energy efficiency comparison method quantifies the performance decay by calculating the ratio of the actual operating efficiency to the theoretical efficiency. This method is simple and intuitive to calculate, but is easily affected by environmental factors and measurement errors. The state parameter analysis method analyzes the change trend of operating parameters such as vibration, temperature, and noise by establishing a multi-dimensional evaluation index system, and calculates the decay coefficient using the weighted summation or fuzzy evaluation method. This method has a more comprehensive and accurate evaluation result, but requires more sensor support and a more complex data processing process. In engineering practice, the two methods are usually combined. For example, during the operation of a certain fan, the energy efficiency comparison shows a 12% performance decline, while the state parameter analysis shows a 15% decay. The system will obtain the final decay coefficient through weighted average and correct it in combination with expert experience to improve the accuracy and reliability of the evaluation.

[0174] In addition, for the collection of energy consumption data, the ventilation control system will install an electric energy metering device in the power line of the fan to collect electrical parameters such as voltage, current, and power factor in real time. The system first obtains the instantaneous power value, calculates the cumulative energy consumption through integral operation, and at the same time records the corresponding relationship between the operating conditions of the fan (such as speed, air volume, etc.) and the energy consumption. In practical applications, the system usually uses 15 minutes as the basic statistical period, calculates the average power and energy consumption per unit time, and compares these data with the rated parameters of the fan to establish an energy consumption characteristic curve. For example, for a fan with a rated power of 75 kW, the measured power during operation under standard conditions is 78 kW. Through continuous monitoring, it can be found that the energy consumption shows a gradually increasing trend, and this abnormal increase often indicates a decline in equipment performance.

[0175] S216. Calculate the estimated maintenance time of the tunnel fan according to the performance decay coefficient and the maintenance record of the tunnel fan, and generate a maintenance plan.

[0176] Among them, the estimated maintenance time represents the time point when it is recommended to carry out the next maintenance; the maintenance record includes the time, content, and effect of each previous maintenance; the maintenance plan refers to the equipment maintenance arrangement within a certain period in the future.

[0177] The ventilation control system needs to formulate a scientific equipment maintenance plan. Specifically, based on the performance decay coefficient calculated in the previous step and combined with the historical maintenance record of the fan, the system analyzes the maintenance cycle law of the equipment, predicts the best time point for the next maintenance, and at the same time makes a reasonable allocation of maintenance resources to generate a detailed maintenance plan arrangement.

[0178] Among them, the calculation of the estimated maintenance time adopts a dynamic programming model based on equipment health. The equipment health index HDI is obtained through multi-parameter weighted fusion: HDI = ∑wiPi, where Pi is the health score of each monitoring parameter (vibration, temperature, current, etc.), and the weight wi is determined through fuzzy hierarchical analysis. The score of each parameter adopts an exponential decay function: Pi = 100·exp(-λi·ti), where λi is the deterioration rate parameter and ti is the operating time.

[0179] The prediction of the maintenance time adopts a two-stage method. In the first stage, the Wiener process model is used to predict the health decay trajectory: dHDI = (μ + σB(t))dt, where μ is the drift parameter, σ is the diffusion coefficient, and B(t) is the standard Brownian motion. The parameters μ and σ are obtained through maximum likelihood estimation: after logarithmic transformation of the historical data, linear regression is used to estimate μ, and the residual standard deviation is σ.

[0180] In the second stage, the optimal maintenance time point is determined through first passage time analysis: Define the failure threshold HDIf of HDI (usually taken as 60), and calculate the expected time E[T] to reach this threshold as E[T] = (HDI0 - HDIf) / |μ|. Considering cost optimization, a maintenance decision-making model is introduced: C(t) = cp·P(t < T) + cu·P(t > T) + cm·e^(-rt), where cp is the preventive maintenance cost, cu is the unplanned downtime cost, cm is the regular maintenance cost, and r is the discount rate. The optimal maintenance time t* is determined by minimizing the total cost C(t).

[0181] For example, the current health status of a certain fan is 85, and through fitting historical data, μ = -0.015 / day and σ = 0.008 are obtained. It is predicted that without maintenance, the health status will drop to the failure threshold after about 180 days. Considering cp = 5000 yuan, cu = 20000 yuan, cm = 8000 yuan, and r = 0.1 / year, the calculated optimal maintenance time should be around 150 days.

[0182] In the embodiments of the present application, due to the adoption of a ventilation demand prediction mechanism based on train operation data, a distributed ventilation control strategy between sections is established, and a device performance evaluation and predictive maintenance function is introduced, so it is possible to achieve accurate prediction of ventilation demand, coordinated control between sections, and intelligent maintenance of devices, effectively solving the problems existing in the traditional fixed-mode ventilation scheme, such as unsatisfactory ventilation effect, serious energy waste, and passive device maintenance, realizing the improvement of ventilation effect and the reduction of operation energy consumption, and ensuring the reliable operation of the system.

[0183] The ventilation control system in the embodiments of the present invention will be described from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the ventilation control system in the embodiments of the present application.

[0184] It should be noted that Figure 3 the structure of the ventilation control system shown is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present invention.

[0185] Such as Figure 3As shown, the ventilation control system includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes according to a program stored in a Read-Only Memory (ROM) 302 or a program loaded from a storage section 308 into a Random Access Memory (RAM) 303, such as executing the method described in the above embodiments. 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.

[0186] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a Liquid Crystal Display (LCD), an audio output device, an indicator light, 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.

[0187] 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 a network via the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by a Central Processing Unit (CPU) 301, various functions defined in the present invention are executed.

[0188] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0189] 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 may 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 the 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.

[0190] Specifically, the ventilation control system of this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, the tunnel sectional exhaust air method based on the train operating conditions provided in the above-mentioned embodiment is realized.

[0191] On the other hand, the present invention also provides a computer-readable storage medium, which may be included in the ventilation control system described in the above-mentioned embodiment; or it may exist separately and not be assembled into the ventilation control system. The above-mentioned storage medium carries one or more computer programs. When the one or more computer programs are executed by a processor of the ventilation control system, the ventilation control system realizes the tunnel sectional exhaust air method based on the train operating conditions provided in the above-mentioned embodiment.

[0192] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than 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 recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the various embodiments of the present application.

[0193] As used in the foregoing embodiments, depending on the context, the term "when" may be construed to mean "if", "after", "in response to determining", or "in response to detecting". Similarly, depending on the context, the phrase "upon determining" or "if (the stated condition or event) is detected" may be construed to mean "if determined", "in response to determining", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0194] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by a computer program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the foregoing method embodiments. The foregoing storage media include various media that can store program codes, such as ROM, random access memory (RAM), magnetic disks, or optical discs.

Claims

1. A tunnel segmented exhaust method based on train working conditions, characterized in that: Applied to a ventilation control system, the method comprises: Dividing the target tunnel into a plurality of control sections according to the fan installation configuration of the target tunnel; Acquire train operation data on the rail transit dispatching system, and determine the train traffic data and train configuration information of the control section based on the train operation data; When it is determined based on the train travel data that the passing train is a diesel locomotive, determining a smoke emission rate of the diesel locomotive based on the train configuration information; Calculating the smoke growth value of the control section within a preset time period according to the train passage data and the smoke emission rate; When it is determined based on the train passage data that the passing train is an electric locomotive, the running speed and vehicle type information of the electric locomotive are determined based on the train configuration information; Determining an airflow disturbance coefficient of the electric locomotive based on the running speed and the vehicle type information; Collecting smoke concentration data of the control section, and calculating the smoke growth value of the control section within a preset time period based on the smoke concentration data and the airflow disturbance coefficient based on a dual-model fusion method; the models used in the dual-model fusion method include a dynamic model based on airflow disturbance and a time series prediction model based on historical data; Collecting smoke concentration data of the control section, and calculating the ventilation demand index of the control section in combination with the smoke growth value; Collecting the wind direction parameters of the control section, determining the ventilation control relationship between adjacent control sections based on the ventilation demand index and the wind direction parameters, and generating a ventilation coordination plan; According to the ventilation coordination scheme, the operating parameters of the tunnel fans in each of the control sections are calculated, and control instructions corresponding to the operating parameters are sent to the tunnel fans.

2. The method according to claim 1, characterized in that The step of dividing the target tunnel into a plurality of control sections according to the fan installation configuration of the target tunnel specifically comprises: Determine the installation position and rated power parameters of each tunnel fan unit in the target tunnel according to the fan installation configuration of the target tunnel; Based on the installation position and the rated power parameter, calculating the installation spacing and ventilation coverage of each of the tunnel fan units; Adjacent tunnel fan units whose installation spacing is less than a preset distance threshold and whose ventilation coverage areas overlap are defined as one fan control group, and all tunnel fan units are divided into a plurality of fan control groups; Based on the multiple fan control groups, the target tunnel is divided into multiple control sections.

3. The method according to claim 1, characterized in that The step of collecting the wind direction parameters of the control section, determining the ventilation control relationship between adjacent control sections based on the ventilation demand index and the wind direction parameters, and generating a ventilation coordination plan specifically includes: Sorting the control sections in descending order according to the ventilation demand index to determine the target control section with the largest ventilation demand; Collecting wind direction parameters of the target control section, determining the ventilation airflow direction of the target control section between adjacent control sections, and determining a plurality of coordinated control sections based on the ventilation airflow direction; Based on the ventilation demand index, calculating a demand index difference between the target control section and the coordinated control section; When the demand index difference is greater than a preset difference threshold, the ventilation demand indexes of the target control section and the cooperative control section are adjusted to generate a ventilation coordination plan.

4. The method according to claim 1, characterized in that: After the step of calculating the operating parameters of the tunnel fans in each of the control sections according to the ventilation coordination scheme, and sending control instructions corresponding to the operating parameters to the tunnel fans, the method further includes: Obtaining the real-time smoke concentration in each of the control sections and constructing a smoke change curve; Calculating the ventilation effect score of each of the control sections based on the smoke change curve; The control section where the ventilation effect score is lower than the preset score threshold is taken as the abnormal control section, and the fan operation status of all tunnel fans in the abnormal control section is detected; When the operation state of the fan is abnormal, a maintenance reminder message is sent to the management terminal.

5. The method according to claim 1, characterized in that After the step of calculating the operating parameters of the tunnel fans in each of the control sections according to the ventilation coordination scheme, and sending control instructions corresponding to the operating parameters to the tunnel fans, the method further includes: Obtaining the operating time and energy consumption data of each tunnel fan in the target control section; Calculating a performance attenuation coefficient of the tunnel fan based on the operating time and the energy consumption data; According to the performance attenuation coefficient and the maintenance record of the tunnel fan, the estimated maintenance time of the tunnel fan is calculated and a maintenance plan is generated.

6. A ventilation control system, characterized in that: The ventilation control system includes: 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 enable the ventilation control system to execute the method described in any one of claims 1-5.

7. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a ventilation control system, the ventilation control system is caused to execute the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that When the computer program product is run on a ventilation control system, the ventilation control system is caused to perform the method according to any one of claims 1 to 5.

Images