Highway tunnel fan dispatching system based on multi-device collaborative optimization control

Abstract

The present invention discloses a highway tunnel fan dispatching system with collaborative optimization control of multiple devices, which relates to the technical field of fan dispatching and is used to solve the problems that traditional methods usually control fans independently, lack consideration of collaborative dispatching between fans, lack scientific basis when selecting important positions, and fail to fully consider the real-time load problem of fans during important periods, which may cause some fans to be overloaded or operate inefficiently; the objective function is comprehensively constructed, which enables fan dispatching to not only pursue energy conservation, but also take into account environmental quality and fan operation stability, and has a global optimization effect. By setting the initial yin and yang adjustment points and combining the needs of different time periods, precise control of fan dispatching is achieved, and the dispatching plan is more timely and economical. By coordinating the start and stop and operating status between each fan, unnecessary fan starts or stops can be effectively reduced, reducing the operational instability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of fan dispatching, and more particularly to a highway tunnel fan dispatching system with multi-device collaborative optimization control. Background Art

[0002] Highway tunnels are densely populated, resulting in high exhaust emissions and fire risks. An effective ventilation system can promptly expel harmful gases, reduce pollutant concentrations, and safeguard tunnel air quality and driving safety. Tunnel ventilation systems consume a lot of energy, especially in long tunnels. Reducing energy consumption while ensuring effective ventilation is a key research topic in tunnel ventilation control. Traditional methods typically employ fixed fan start-stop strategies, which are unable to dynamically adjust fan operation based on real-time changes in tunnel traffic flow, pollutant concentrations, and environmental conditions. This results in inefficient ventilation and energy waste.

[0003] The existing technology has the following deficiencies:

[0004] Traditional methods typically control fans independently, lack consideration for coordinated scheduling between them, and typically employ fixed scheduling strategies, making them difficult to adapt to the dynamically changing environmental conditions within tunnels. Traditional methods lack a scientific basis for selecting key fan locations, potentially leading to overuse or idleness of some fans. They also fail to fully consider the real-time load of fans during critical periods, potentially causing some fans to overload or operate inefficiently. Traditional methods also struggle to accurately determine convergence speed during the optimization process, potentially leading to premature cessation or excessive iterations.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a highway tunnel fan dispatching system with multi-device collaborative optimization control to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A highway tunnel fan dispatching system with multi-device collaborative optimization control includes: a comprehensive adjustment module, a yin-yang selection module, an interval calculation module, and a weight reset module, with signal connections between each module;

[0009] Comprehensive Regulation Module: This module constructs a comprehensive objective function based on energy consumption, comprehensive environmental parameters, and the number of fan starts and stops. It uses a particle swarm optimization algorithm to simulate the movement of a group of particles to determine the optimal solution for fan scheduling in highway tunnels. It then sets an initial yin-yang regulation point, coordinates the fan scheduling, and iteratively updates the optimal speed and position solutions obtained by the particle swarm optimization algorithm.

[0010] Yin-Yang Selection Module: This module uses streamline tracking to select key fan locations for longitudinal and transverse ventilation in highway tunnels, taking into account the pollutant concentration change rate and airflow uniformity. This module maintains real-time loads for these locations during the Yang period, and uses a particle swarm optimization algorithm to simultaneously adjust the energy consumption of these locations and the availability of other locations.

[0011] Interval calculation module: determines the starting Yin-Yang regulation point based on the electricity price adjustment time and the comprehensive parameters of environmental conditions, and obtains the Yin-Yang interval time and the ending Yin-Yang regulation point based on the seasonal change function and the Yin-Yang regulation intensity;

[0012] Weight reset module: According to the curve of the optimal solution value changing with iteration, the convergence speed of particle swarm optimization is obtained, and the proportional weight adjustment or linear weight adjustment strategy is selected based on the yin-yang regulation strength to modify the corresponding weights of energy consumption, environmental conditions and the number of fan starts and stops.

[0013] In a preferred embodiment, the comprehensive adjustment module includes the following contents.

[0014] Construct a comprehensive objective function, combining energy consumption, comprehensive environmental parameters, and the number of fan starts and stops, reasonably schedule fan operation, and determine the acquisition of various variables and parameters:

[0015] Energy consumption ( ): Calculate the energy consumption of each fan, assuming the power of the fan is , the running time is , the electricity price is , then the energy consumption of fan i in a certain period of time is: ;

[0016] Comprehensive parameters of environmental conditions ( ): Get the wind speed in the environment ,temperature ,humidity Data, the impact of comprehensive environmental conditions on fan load requirements, the comprehensive parameters of environmental conditions are expressed as: ;in, :time wind speed, :time temperature, :time humidity;

[0017] Number of fan starts and stops ( ): is the fan i in the time period Operating status, number of start and stop events It can be expressed as: ;in, Indicates fan In time In running state, Indicates that the fan is stopped;

[0018] Taking the above variables into consideration, the target parameters are expressed as: ;in, is the energy consumption of each fan, is the comprehensive parameter of the environmental conditions of the fan i, is the number of starts and stops of fan i, 、 、 They are the weights corresponding to energy consumption, environmental impact and the number of starts and stops of the fan;

[0019] The coordinated scheduling between fans coordinates the working status of the fans to reduce energy consumption and improve the working efficiency of the fans. The synergistic effect between fans is defined as follows:

[0020] Each particle represents a fan scheduling plan, including the start / stop status and speed of each fan;

[0021] Initialize the particle's speed and position. The position represents the wind turbine's scheduling plan, and the speed represents the magnitude of the particle's change in the scheduling plan. For each particle, calculate its corresponding objective function value to indicate the quality of the scheduling plan. Update the particle's speed and position based on the particle's historical optimal position and the global optimal position: ; in, is the velocity of the particle, is the position of the particle, is the particle's best historical position, is the global optimal position of the group, is the learning factor, is a random number, is the inertia weight;

[0022] By iteratively updating the position and velocity of the particles, the stopping condition is set until the maximum number of iterations is reached or the change of the global optimal solution is less than the threshold;

[0023] The initial yin-yang adjustment point is set, the working strategies of multiple wind turbines cooperate with each other, and the wind turbines are coordinated and dispatched to improve the overall power generation efficiency and optimize resource allocation. Particle swarm optimization should adjust the speed and position of each particle under the premise of meeting the constraints, and continuously approach the optimal solution.

[0024] In a preferred embodiment, the yin-yang selection module includes the following contents.

[0025] In the embodiment of the present invention, a reasonable combination of ventilation fans for longitudinal ventilation and transverse ventilation is used;

[0026] Select important ventilation fan locations using streamline tracking method based on the pollutant concentration change rate of each ventilation fan and the uniformity of airflow;

[0027] Computational fluid dynamics software is used to simulate the airflow and pollutant propagation process. In the simulation model, different fan operating conditions, flow field distribution, pollutant source terms, and other conditions are set. The change of pollutant concentration over time is simulated. Multiple sensors are deployed in the actual environment to monitor the pollutant concentration at the outlet of each ventilation fan or at different locations in the space in real time. The rate of change of concentration over time is calculated based on the sensor data, and the rate of change of pollutant concentration is derived using a mathematical model.

[0028] Through CFD simulation, the wind speed distribution at different locations in the ventilation system is obtained, and the uniformity of the airflow in the flow field is calculated through CFD simulation;

[0029] Set different thresholds for longitudinal and transverse ventilation respectively and select appropriate positions: when setting the change rate for longitudinal ventilation, the threshold is recorded as , the threshold value of airflow uniformity setting is recorded as , and under cross ventilation, the threshold value of the pollutant concentration change rate is recorded as , the threshold value set for airflow uniformity is , making ; , if and only if the threshold of pollutant concentration change rate and airflow uniformity is exceeded at the same time, the aircraft position is recorded as an important aircraft position;

[0030] The Yin-Yang adjustment point is used as a division. The period before the Yin-Yang adjustment point is called the Yang period, and the period after the Yin-Yang adjustment point is called the Yin period. The real-time load of important positions is maintained during the Yang period.

[0031] The pollutant concentration change rate, airflow uniformity, and fan energy consumption are used as optimization parameters of the objective function to obtain the energy consumption of each fan. The pollutant concentration change rate, airflow uniformity, and fan energy consumption are weighted to obtain the objective function. The objective function is expressed as: ;in, It is a function of the rate of change of pollutant concentration, which measures the impact of fan operation on pollutant diffusion. It is a function of airflow uniformity, which measures the uniformity of airflow distribution when the fan is running. It is a function of energy consumption, which measures the energy consumption of the fan during operation. 、 、 are the weights of pollutant concentration change rate, airflow uniformity, and fan energy consumption;

[0032] The dimension of each particle represents the working state of the fan, including load and on or off state. There are N fans, and each fan has two control variables including load and on state. The dimension of the particle is 2N;

[0033] The particle velocity and position update rules are expressed as: ;in, is the velocity of the particle, is the position of the particle, is the particle's best historical position, is the global optimal position of the group, is the learning factor, is a random number, is the inertia weight;

[0034] Constraints are set based on the fan load threshold and ventilation volume threshold. If the constraints are not met, iterations are performed until the maximum number of iterations is reached or the optimization result meets the constraints. The fan load threshold and ventilation volume threshold settings and rules are as follows:

[0035] Fan load threshold constraint: The maximum load of each fan is recorded as , then the load value of the corresponding fan in the particle Must satisfy: 0≤ ≤ ;

[0036] Ventilation volume threshold constraint: set a minimum ventilation volume threshold , the threshold should be set according to the fan's workload, environment and demand, then the corresponding ventilation volume in the particle is greater than or equal to the minimum ventilation volume threshold .

[0037] In a preferred embodiment, the interval calculation module includes the following contents.

[0038] Get the timetable for electricity price adjustment and use it as the basis for electricity price adjustment. Set the starting point of yin and yang adjustment based on the basis, which is recorded as , an adjustment factor is defined based on the electricity price adjustment time and the comprehensive parameters of environmental conditions, which can be expressed as: ;in, is the weight of the electricity price adjustment time, is the weight of the comprehensive parameters of environmental conditions, It is a comprehensive adjustment factor of electricity price and environmental conditions, according to The value of can determine the time point to start the yin and yang regulation;

[0039] According to the adjustment factor , set a threshold , When the threshold is exceeded, the Yin-Yang adjustment point is corrected, and the rules are as follows: ;in, is the time offset corrected for environmental conditions and electricity prices, It is the time for electricity price adjustment. It is the final calculated starting point of yin and yang adjustment;

[0040] Obtain the changes in historical nighttime duration and use a sine-like function to model seasonal changes in nighttime length. The seasonal change function is expressed as: ;in, It's in time The length of night at 9 o'clock (hours), A is the amplitude of night length, reflecting the biggest difference between summer and winter seasons, is the periodic coefficient, which is related to the seasonal changes in a year, is the time offset, used to adjust the starting point of seasonal changes, It is the benchmark value of night length, representing the length of night in spring and autumn;

[0041] The Yin-Yang regulation intensity is calculated based on the change in the wind turbine's power load and is expressed as: ;in, is the initial power, is the adjusted power;

[0042] The seasonal variation function of the Yin-Yang interval and the Yin-Yang regulation intensity is expressed as: = ×(1+ );in, It's in time The length of night when Q is the wind turbine power load change calculation to obtain the regulation intensity;

[0043] The end Yin-Yang adjustment point is the time point after the Yin-Yang interval time of the start Yin-Yang adjustment point, expressed as: .

[0044] In a preferred embodiment, the weight resetting module includes the following contents.

[0045] The convergence curve is a graph showing how the optimal solution value changes with the number of iterations. As the iterations proceed, the optimal solution value gradually decreases, indicating that the particle swarm has found a better solution. Until the algorithm converges, the convergence rate is calculated based on the convergence curve.

[0046] After receiving the convergence speed and the yin-yang adjustment strength, the convergence speed and the yin-yang adjustment strength are defined as input variables and divided into different fuzzy sets respectively;

[0047] The weight adjustment strategy is defined as the output variable, which is divided into fuzzy sets;

[0048] Formulate fuzzy rules to describe the impact of convergence speed and the definition of yin-yang regulation strength on the weight adjustment strategy;

[0049] Perform fuzzy reasoning based on fuzzy rules to determine the weight adjustment strategy of power banks;

[0050] Select the corresponding weight adjustment strategy based on fuzzy reasoning;

[0051] The proportional weight adjustment is expressed as: ;in, It is The inertia weight of the iteration, and are the maximum and minimum values ​​of the inertia weight, is the optimal solution value of the current iteration, is the maximum value of the optimal solution;

[0052] The linear weight adjustment algorithm calculation is expressed as: ;in, It is The inertia weight of the iteration, and are the maximum and minimum values ​​of the inertia weight, is the current iteration number, is the total number of iterations;

[0053] Use the corresponding weight adjustment strategy to modify the corresponding weights of energy consumption, environmental conditions and the number of fan starts and stops.

[0054] The technical effects and advantages of the highway tunnel fan dispatching system with multi-device collaborative optimization control of the present invention are as follows:

[0055] The scheme comprehensively constructs an objective function, which enables wind turbine scheduling to not only pursue energy savings, but also take into account environmental quality and the stability of wind turbine operation, achieving a global optimization effect. The particle swarm optimization algorithm simulates the movement and collaboration of particle groups in nature and has strong global optimization capabilities. By setting the initial yin and yang adjustment points, precise control of wind turbine scheduling is achieved in combination with the needs of different time periods. The yin and yang adjustment points are calculated based on factors such as electricity prices, environmental conditions, and seasonal changes, making the scheduling scheme more timely and economical. By coordinating the start and stop and operating status of each wind turbine, unnecessary wind turbine starts or stops can be effectively reduced, thereby avoiding frequent switching operations on the equipment, reducing wind turbine wear and maintenance costs, and also reducing system operational instability. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a structural diagram of the highway tunnel fan dispatching system with multi-device collaborative optimization control according to the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0058] Example 1: Please refer to Figure 1 As shown, the present invention discloses a highway tunnel fan dispatching system with multi-device collaborative optimization control, including: a comprehensive adjustment module, a yin and yang selection module, an interval calculation module and a weight reset module, and signal connections between each module.

[0059] Comprehensive Regulation Module: This module constructs a comprehensive objective function based on energy consumption, comprehensive environmental parameters, and the number of fan starts and stops. It uses a particle swarm optimization algorithm to simulate the movement of a group of particles to determine the optimal solution for fan scheduling in highway tunnels. It then sets an initial yin-yang regulation point, coordinates the fan scheduling, and iteratively updates the optimal speed and position solutions obtained by the particle swarm optimization algorithm.

[0060] Yin-Yang Selection Module: This module uses streamline tracking to select key fan locations for longitudinal and transverse ventilation in highway tunnels, taking into account the pollutant concentration change rate and airflow uniformity. This module maintains real-time loads for these locations during the Yang period, and uses a particle swarm optimization algorithm to simultaneously adjust the energy consumption of these locations and the availability of other locations.

[0061] Interval calculation module: determines the starting Yin-Yang regulation point based on the electricity price adjustment time and the comprehensive parameters of environmental conditions, and obtains the Yin-Yang interval time and the ending Yin-Yang regulation point based on the seasonal change function and the Yin-Yang regulation intensity;

[0062] Weight reset module: According to the curve of the optimal solution value changing with iteration, the convergence speed of particle swarm optimization is obtained, and the proportional weight adjustment or linear weight adjustment strategy is selected based on the yin-yang regulation strength to modify the corresponding weights of energy consumption, environmental conditions and the number of fan starts and stops.

[0063] In the comprehensive regulation module, a comprehensive objective function is constructed by combining energy consumption, comprehensive environmental parameters, and the number of fan starts and stops. A particle swarm optimization algorithm is used to simulate the movement of a group of particles to obtain the optimal solution for fan scheduling in highway tunnels. Initial yin-yang regulation points are set, and fans are coordinated and scheduled. The optimal speed and position solutions obtained by the particle swarm optimization are then iteratively updated. The specific contents include:

[0064] Construct a comprehensive objective function, combining energy consumption, comprehensive environmental parameters, and the number of fan starts and stops, reasonably schedule fan operation, and determine the acquisition of various variables and parameters:

[0065] Energy consumption ( ): Calculate energy consumption based on the operating status of the fan and the difference in electricity prices. Calculate the energy consumption of each fan. Suppose the power of the fan is , the running time is , the electricity price is , then the energy consumption of fan i in a certain period of time is:

[0066] Comprehensive parameters of environmental conditions ( ): Consider the influence of environmental conditions and the impact of environmental conditions on fan operation, and obtain the wind speed in the environment ,temperature ,humidity Data, the impact of comprehensive environmental conditions on fan load requirements, the comprehensive parameters of environmental conditions are expressed as: ;in, :time wind speed, :time temperature, :time humidity.

[0067] Number of fan starts and stops ( ): Number of starts and stops of the fan It will affect the life of the fan and the extra energy consumption. Frequent fan start and stop increases the extra energy consumption and affects the mechanical performance of the fan. The number of fan starts and stops is measured by counting the number of start and stop events of each fan in a time period. Assuming is the fan i in the time period Operating status, number of start and stop events It can be expressed as: ;in, Indicates fan In time In running state, Indicates that the fan is stopped.

[0068] Taking the above variables into consideration, the target parameters are expressed as: ;in, is the energy consumption of each fan, is the comprehensive parameter of the environmental conditions of the fan i, is the number of starts and stops of fan i, 、 、 They are the weights corresponding to energy consumption, environmental impact and the number of starts and stops of the fan. By adjusting the parameters, the energy consumption, environmental impact and the number of starts and stops of the fan of the entire system can be minimized, so as to achieve efficient, energy-saving and long-term stable operation of the fan system, and reasonably schedule the operation of the fan to achieve the optimal system operation effect.

[0069] The coordinated scheduling between fans coordinates the working status of the fans to reduce energy consumption and improve the working efficiency of the fans. The synergistic effect between fans is defined as follows:

[0070] When multiple fans are started at the same time, their operating efficiency will be affected by each other. The scheduling algorithm can avoid too many fans starting and stopping at the same time. The particle swarm optimization algorithm is used to coordinate the start and stop of multiple fans, making the fan group of the entire tunnel run more efficiently.

[0071] The particle swarm optimization algorithm is an optimization algorithm based on swarm intelligence. It simulates the movement of a group of particles in the search space to find the optimal solution. The particle swarm optimization algorithm is carried out in the following steps:

[0072] Each particle represents a fan scheduling plan, including the start and stop status and speed of each fan.

[0073] Initialize the particle's speed and position. The position represents the wind turbine's scheduling plan, and the speed represents the extent to which the particle changes the scheduling plan. For each particle, calculate its corresponding objective function value to indicate the quality of the scheduling plan. Update the particle's speed and position based on the particle's historical optimal position and the global optimal position: ;in, is the velocity of the particle, is the position of the particle, is the particle's best historical position, is the global optimal position of the group, is the learning factor, is a random number, is the inertia weight.

[0074] By iteratively updating the position and velocity of the particles, the particle swarm continuously converges toward the global optimal solution, and a stopping condition is set when the maximum number of iterations is reached or the change in the global optimal solution is less than a threshold.

[0075] The particle swarm optimization algorithm has strong global search capabilities and can effectively avoid falling into local optimal solutions, thereby finding the global optimal scheduling plan. As the algorithm iterates, the particle swarm will continue to approach the optimal solution and can quickly find a scheduling plan that meets actual needs.

[0076] The initial yin and yang adjustment points are set to represent the initial state or boundary conditions of the system. In wind turbine scheduling, they represent the working state of each wind turbine in the system at a certain moment or under certain conditions. The initial yin and yang adjustment points can be defined based on factors such as wind forecast data, meteorological conditions, and load demand, and can be specifically set by professionals in this field.

[0077] In particle swarm optimization, each particle represents a solution. Each solution contains the wind turbine scheduling strategy and scheduling time. The position is the scheduling strategy, and the speed represents the pace of adjusting these strategies in the search space.

[0078] The working strategies of multiple wind turbines cooperate with each other to achieve coordinated scheduling between wind turbines, improve overall power generation efficiency and optimize resource allocation. The particle swarm optimization algorithm plays an important role in this process. For each particle, the particle swarm optimization algorithm needs to judge the synergistic effect between each wind turbine. Particle swarm optimization must adjust the speed and position of each particle under the premise of meeting the constraints to continuously approach the optimal solution.

[0079] In the Yin-Yang selection module, the streamline tracking method is used to select important fan locations for longitudinal and transverse ventilation of highway tunnels, combining the pollutant concentration change rate and airflow uniformity. The real-time load of important fan locations is maintained during the Yang period. The particle swarm optimization algorithm is used to simultaneously adjust the energy consumption of important fan locations and the opening status of other fan locations. The specific contents include:

[0080] In the embodiment of the present invention, a reasonable combination of longitudinal ventilation and transverse ventilation is used to make the air flow more uniform and reduce the accumulation of pollutants in certain areas. The appropriate fan layout is selected according to the actual situation, and the start and stop and operating load are adjusted:

[0081] Longitudinal ventilation is used to push air flow directly through the tunnel along the length of the tunnel. It has strong directionality and is used to improve the overall air exchange efficiency of the tunnel and quickly discharge pollutants. Transverse ventilation uses fans to send air into or out of the tunnel, affecting the air flow in local areas and helping to regulate the airflow uniformity and pollutant concentration in certain key areas.

[0082] The streamline tracking method is used to select important machine positions based on the pollutant concentration change rate of each ventilation fan and the uniformity of the airflow. The streamline tracking method is an important tool for studying the propagation of airflow and pollutants in the ventilation system. Selecting important machine positions based on the pollutant concentration change rate of the ventilation fan and the uniformity of the airflow can optimize the ventilation system design and improve the pollutant emission efficiency.

[0083] Computational fluid dynamics software is used to simulate the airflow and pollutant propagation process. Within the simulation model, various fan operating conditions, flow field distribution, and pollutant source terms are set to simulate how pollutant concentrations change over time. Multiple sensors are deployed in a real-world environment to monitor pollutant concentrations at each fan outlet or at different locations in the space. The rate of change of concentration over time is calculated based on sensor data, and this rate of change is derived using a mathematical model.

[0084] The wind speed distribution at different locations within the ventilation system is obtained through CFD simulation or wind speed sensor measurements. Areas with better airflow uniformity have more stable wind speed distributions. CFD simulation is used to calculate the uniformity of airflow in the flow field.

[0085] According to the characteristics of longitudinal and transverse ventilation, different thresholds are set respectively to select appropriate positions; in longitudinal ventilation, more attention is paid to the rate of change of pollutant concentration, so a smaller threshold is set for the rate of change of pollutant concentration, and a larger threshold is set for the uniformity of airflow, so that the selection is more inclined to select positions that are more affected by the rate of change of pollutant concentration, while in transverse ventilation, more attention is paid to the uniformity of airflow, a larger threshold is set for the rate of change of pollutant concentration, and a smaller threshold is set for the uniformity of airflow, so that the selection is more inclined to select positions that are more affected by the uniformity of airflow. In summary, the threshold for setting the rate of change during longitudinal ventilation is recorded as , the threshold value of airflow uniformity setting is recorded as , and under cross ventilation, the threshold value of the pollutant concentration change rate is recorded as , the threshold value set for airflow uniformity is , making ; If and only if both the pollutant concentration change rate threshold and the airflow uniformity threshold are exceeded simultaneously, the station is marked as an important station. The period before the Yin-Yang adjustment point is called the Yang period, and the period after the Yin-Yang adjustment point is called the Yin period. The real-time load of the important station is maintained during the Yang period.

[0086] The pollutant concentration change rate, airflow uniformity, and fan energy consumption are used as optimization parameters of the objective function to obtain the energy consumption of each fan. The pollutant concentration change rate, airflow uniformity, and fan energy consumption are weighted to obtain the objective function. The objective function is expressed as: ;in, It is a function of the rate of change of pollutant concentration, which measures the impact of fan operation on pollutant diffusion. It is a function of airflow uniformity, which measures the uniformity of airflow distribution when the fan is running. It is a function of energy consumption, which measures the energy consumption of the fan during operation. 、 、 are the weights of the pollutant concentration change rate, airflow uniformity, and fan energy consumption respectively.

[0087] The dimension of each particle represents the working state of the fan, including load and on or off state. There are N fans, and each fan has two control variables including load and on state. The dimension of the particle is 2N;

[0088] The particle velocity and position update rules are expressed as: ;in, is the velocity of the particle, is the position of the particle, is the particle's best historical position, is the global optimal position of the group, is the learning factor, is a random number, is the inertia weight.

[0089] The constraints in particle swarm optimization ensure that the operating status of the fan does not exceed a reasonable range. The fan load threshold and ventilation volume threshold are combined to ensure that the position and velocity of each particle meet the constraints. If the constraints are not met, iterations are performed until the maximum number of iterations is reached or the optimization result meets the constraints. The maximum number of iterations can be set by professionals. The fan load threshold and ventilation volume threshold settings and rules are as follows:

[0090] Fan load threshold constraint: The load of each fan cannot exceed its maximum load capacity. The maximum load of each fan is recorded as , then the load value of the corresponding fan in the particle Must satisfy: 0≤ ≤ ;

[0091] Ventilation volume threshold constraint: The working state of the fan should ensure the uniformity of air flow and set a minimum ventilation volume threshold , the threshold should be set according to the fan's workload, environment and demand, then the corresponding ventilation volume in the particle should be greater than or equal to the minimum ventilation volume threshold .

[0092] In the interval calculation module, the starting Yin-Yang regulation point is determined based on the electricity price adjustment time and the comprehensive parameters of environmental conditions. The Yin-Yang interval time and the ending Yin-Yang regulation point are obtained based on the seasonal change function and the Yin-Yang regulation intensity. The specific contents include:

[0093] Get the timetable for electricity price adjustment and use it as the basis for electricity price adjustment. Set the starting point of yin and yang adjustment based on the basis, which is recorded as , an adjustment factor is defined based on the electricity price adjustment time and the comprehensive parameters of environmental conditions, which can be expressed as: ;in, is the weight of the electricity price adjustment time, is the weight of the comprehensive parameters of environmental conditions, It is a comprehensive adjustment factor of electricity price and environmental conditions, according to The value of can determine the time point to start Yin-Yang regulation.

[0094] According to the adjustment factor , set a threshold , When the threshold is exceeded, the Yin-Yang adjustment point is corrected, and the rules are as follows: ;in, It is the time offset corrected according to environmental conditions and electricity prices, and can be set according to specific needs. It is the time for electricity price adjustment. It is the final calculated starting point of yin and yang adjustment.

[0095] Obtain historical changes in nighttime, including seasonal nighttime length, based on sunrise and sunset times and the relationship between latitude and season. Calculate the difference between sunrise and sunset times as the nighttime duration, and extrapolate the seasonal nighttime changes based on geographic latitude and season. Construct a seasonal variation function. Seasonal variations are cyclical, and a sine-like function is used to model seasonal nighttime changes. The seasonal variation function is expressed as: ;in, It's in time The length of night at 9 o'clock (hours), A is the amplitude of night length, reflecting the biggest difference between summer and winter seasons, is the periodic coefficient, which is related to the seasonal changes in a year, is the time offset, used to adjust the starting point of seasonal changes, It is the benchmark value for night length, representing the length of night in spring and autumn.

[0096] The Yin-Yang regulation intensity is calculated based on the change in the wind turbine's power load and is expressed as: ;in, is the initial power, is the adjusted power.

[0097] The seasonal variation function of the Yin-Yang interval and the Yin-Yang regulation intensity is expressed as: = ×(1+ );in, It's in time The length of the night is Q, and Q is the regulation intensity calculated by the change of the wind turbine's power load.

[0098] The end Yin-Yang adjustment point is the time point after the Yin-Yang interval time of the start Yin-Yang adjustment point, expressed as: .

[0099] In the weight reset module, based on the curve of the optimal solution value changing with iteration, the convergence speed of the particle swarm optimization is obtained. The proportional weight adjustment or linear weight adjustment strategy is selected based on the yin-yang regulation intensity to modify the corresponding weights of energy consumption, environmental conditions, and the number of fan starts and stops. The specific contents include:

[0100] The convergence curve is a graph showing how the optimal solution value changes with the number of iterations. As the iterations proceed, the optimal solution value should gradually decrease, indicating that the particle swarm has found a better solution. Until the algorithm converges, the convergence rate is calculated based on the convergence curve.

[0101] After receiving the convergence speed and the yin-yang adjustment strength, the convergence speed and the yin-yang adjustment strength are defined as input variables, and they are divided into different fuzzy sets respectively.

[0102] For example, "Slow", "Normal", "Fast" for convergence speed, "Low", "Medium", "High" for Yin-Yang regulation strength.

[0103] Define the weight adjustment strategy as the output variable, partitioning it into fuzzy sets, for example, "Linear", "Proportion" for the weight adjustment strategy.

[0104] Formulate a set of fuzzy rules to describe the impact of different input variables on the output variable. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0105] The convergence speed is marked as F, the yin-yang adjustment strength is marked as Q, and the weight adjustment strategy is marked as (Adj can be defined

[0106] Rule 1: IF (T is Slow) AND (B is Low) THEN (Adj is Linear)

[0107] Rule 2: IF (T is "Fast) AND (B is High) THEN (Adj is Proportion) ...

[0108] Perform fuzzy reasoning based on fuzzy rules to determine the weight adjustment strategy.

[0109] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes three fuzzy sets as an example, the convergence speed, yin and yang adjustment strength, and weight adjustment strategy can actually be divided into more than three sets to facilitate better precise adjustment according to different temperatures.

[0110] The key to proportional weight adjustment is to dynamically adjust the inertia weight according to the changes in the current optimal solution value, thereby affecting the search behavior of the particles. During the optimization process, a better solution value will cause the weight to decrease, allowing the particles to converge more quickly. When using proportional weight adjustment, the proportional weight adjustment is expressed as: ;in, It is The inertia weight of the iteration, and are the maximum and minimum values ​​of the inertia weight, is the optimal solution value of the current iteration, is the maximum value of the optimal solution.

[0111] Linear weight adjustment adjusts the inertia weight in a linear decreasing manner, so that as the number of iterations increases, the inertia weight gradually decreases. The adjustment method is relatively simple, but its convergence speed may not be as flexible as proportional weight adjustment. It is a simple and direct adjustment strategy that adjusts the inertia weight and learning factor in a linear relationship based on the progress of the current number of iterations. The linear weight adjustment algorithm is calculated as follows: ;in, It is The inertia weight of the iteration, and are the maximum and minimum values ​​of the inertia weight, is the current iteration number, is the total number of iterations.

[0112] Through weight adjustment strategies, weights can be adjusted based on the optimization objective, influencing particle search behavior and further optimizing metrics such as energy consumption, environmental conditions, and the number of wind turbine starts and stops. For example, when using proportional weight adjustment, when the current optimal solution approaches the global optimum, the inertia weight is reduced, and particles tend to conduct more refined local searches, thereby accelerating convergence. With linear weight adjustment, the inertia weight decreases linearly, making it suitable for simpler optimization problems.

[0113] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0114] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0115] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0116] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0117] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0118] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A highway tunnel fan dispatching system with multi-device collaborative optimization control is characterized by: include: Comprehensive adjustment module, yin and yang selection module, interval calculation module and weight reset module, and signal connections between each module; Comprehensive Regulation Module: This module constructs a comprehensive objective function based on energy consumption, comprehensive environmental parameters, and the number of fan starts and stops. It uses a particle swarm optimization algorithm to simulate the movement of a group of particles to determine the optimal solution for fan scheduling in highway tunnels. It then sets an initial yin-yang regulation point, coordinates the fan scheduling, and iteratively updates the optimal speed and position solutions obtained by the particle swarm optimization algorithm. Yin-Yang Selection Module: This module uses streamline tracking to select key fan locations for longitudinal and transverse ventilation in highway tunnels, taking into account the pollutant concentration change rate and airflow uniformity. This module maintains real-time loads for these locations during the Yang period, and uses a particle swarm optimization algorithm to simultaneously adjust the energy consumption of these locations and the availability of other locations. Interval calculation module: determines the starting Yin-Yang regulation point based on the electricity price adjustment time and the comprehensive parameters of environmental conditions, and obtains the Yin-Yang interval time and the ending Yin-Yang regulation point based on the seasonal change function and the Yin-Yang regulation intensity; Weight reset module: Based on the curve of the optimal solution value changing with iteration, the convergence speed of particle swarm optimization is obtained, and the proportional weight adjustment or linear weight adjustment strategy is selected based on the yin-yang regulation strength to modify the corresponding weights of energy consumption, environmental conditions and the number of fan starts and stops; Specifically: The coordinated scheduling between fans coordinates the working status of the fans to reduce energy consumption and improve the working efficiency of the fans. The synergistic effect between fans is defined as follows: Each particle represents a fan scheduling plan, including the start / stop status and speed of each fan; Initialize the particle's speed and position. The position represents the wind turbine's scheduling plan, and the speed represents the magnitude of the particle's change in the scheduling plan. For each particle, calculate its corresponding objective function value to indicate the pros and cons of the scheduling plan. Update the particle's speed and position based on the particle's historical optimal position and the global optimal position: ;in, is the particle's velocity, is the particle's best historical position, is the global optimal position of the group, is the learning factor, is a random number, is the inertia weight, ;in, is the position of the particle; By iteratively updating the position and velocity of the particles, the stopping condition is set until the maximum number of iterations is reached or the change of the global optimal solution is less than the threshold; The initial yin-yang adjustment point is set, the working strategies of multiple wind turbines cooperate with each other, and the wind turbines are coordinated and dispatched to improve the overall power generation efficiency and optimize resource allocation. Particle swarm optimization should adjust the speed and position of each particle under the premise of meeting the constraints, and continuously approach the optimal solution.

2. The highway tunnel fan dispatching system with multi-device collaborative optimization control according to claim 1 is characterized by: Construct a comprehensive objective function, combining energy consumption, comprehensive environmental parameters, and the number of fan starts and stops, reasonably schedule fan operation, and determine the acquisition of various variables and parameters: Energy consumption ( ): Calculate the energy consumption of each fan, assuming the power of the fan is , the running time is , the electricity price is , then the energy consumption of fan i in a certain period of time is: ; Comprehensive parameters of environmental conditions ( ): Get the wind speed in the environment ,temperature ,humidity Data, the impact of comprehensive environmental conditions on fan load requirements, the comprehensive parameters of environmental conditions are expressed as: ;in, It's time wind speed, It's time temperature, It's time humidity; Number of fan starts and stops ( ): is the fan i in the time period Operating status, number of start and stop events Expressed as: ;in, Indicates fan In time In running state, Indicates that the fan is stopped; Taking the above variables into consideration, the target parameters are expressed as: ;in, is the energy consumption of each fan, is the comprehensive parameter of the environmental conditions of the fan i, is the number of starts and stops of fan i, 、 、 They are the weights corresponding to energy consumption, environmental impact and the number of starts and stops of the fan.

3. The highway tunnel fan dispatching system with multi-device collaborative optimization control according to claim 1 is characterized by: Use a reasonable combination of ventilation fans for longitudinal ventilation and transverse ventilation; Select important ventilation fan locations using streamline tracking method based on the pollutant concentration change rate of each ventilation fan and the uniformity of airflow; Computational fluid dynamics software is used to simulate the airflow and pollutant propagation process. In the simulation model, different fan operating conditions, flow field distribution, pollutant source terms, and other conditions are set. The change of pollutant concentration over time is simulated. Multiple sensors are deployed in the actual environment to monitor the pollutant concentration at the outlet of each ventilation fan or at different locations in the space in real time. The rate of change of concentration over time is calculated based on the sensor data, and the rate of change of pollutant concentration is derived using a mathematical model. Through CFD simulation, the wind speed distribution at different locations in the ventilation system is obtained, and the uniformity of the airflow in the flow field is calculated through CFD simulation; Set different thresholds for longitudinal and transverse ventilation respectively and select appropriate positions: when setting the change rate for longitudinal ventilation, the threshold is recorded as , the threshold value of airflow uniformity setting is recorded as , and under cross ventilation, the threshold value of the pollutant concentration change rate is recorded as , the threshold value set for airflow uniformity is , making ; , if and only if the threshold of pollutant concentration change rate and airflow uniformity is exceeded at the same time, the aircraft position is recorded as an important aircraft position; The Yin-Yang adjustment point is used as a dividing point. The period before the Yin-Yang adjustment point is called the Yang period, and the period after the Yin-Yang adjustment point is called the Yin period. The important machine positions are kept in real-time load during the Yang period.

4. The highway tunnel fan dispatching system with multi-device collaborative optimization control according to claim 3 is characterized by: The pollutant concentration change rate, airflow uniformity, and fan energy consumption are used as optimization parameters of the objective function to obtain the energy consumption of each fan. The pollutant concentration change rate, airflow uniformity, and fan energy consumption are weighted to obtain the objective function. The objective function is expressed as: ;in, It is a function of the rate of change of pollutant concentration, which measures the impact of fan operation on pollutant diffusion. It is a function of airflow uniformity, which measures the uniformity of airflow distribution when the fan is running. It is a function of energy consumption, which measures the energy consumption of the fan during operation. 、 、 are the weights of pollutant concentration change rate, airflow uniformity, and fan energy consumption; The dimension of each particle represents the working state of the fan, including load and on or off state. There are N fans, and each fan has two control variables including load and on state. The dimension of the particle is 2N; The particle velocity and position update rules are expressed as: ； in, is the velocity of the particle, is the position of the particle, is the particle's best historical position, is the global optimal position of the group, is the learning factor, is a random number, is the inertia weight; Constraints are set based on the fan load threshold and ventilation volume threshold. If the constraints are not met, iterations are performed until the maximum number of iterations is reached or the optimization result meets the constraints. The fan load threshold and ventilation volume threshold settings and rules are as follows: Fan load threshold constraint: The maximum load of each fan is recorded as , then the load value of the corresponding fan in the particle Must satisfy: 0≤ ≤ ; Ventilation volume threshold constraint: set a minimum ventilation volume threshold , the threshold should be set according to the fan's workload, environment and demand, then the corresponding ventilation volume in the particle is greater than or equal to the minimum ventilation volume threshold .

5. The highway tunnel fan dispatching system with multi-device collaborative optimization control according to claim 4 is characterized by: Get the timetable for electricity price adjustment and use it as the basis for electricity price adjustment. Set the starting point of yin and yang adjustment based on the basis, which is recorded as , an adjustment factor is defined based on the electricity price adjustment time and the comprehensive parameters of environmental conditions, which can be expressed as: ;in, is the weight of the electricity price adjustment time, is the weight of the comprehensive parameters of environmental conditions, It is a comprehensive adjustment factor of electricity price and environmental conditions, according to The value of determines the time point to start the yin and yang adjustment; According to the adjustment factor , set a threshold , When the threshold is exceeded, the Yin-Yang adjustment point is corrected, and the rules are as follows: ;in, is the time offset corrected for environmental conditions and electricity prices, It is the time for electricity price adjustment. It is the final calculated starting point of yin and yang adjustment.

6. The highway tunnel fan dispatching system with multi-device collaborative optimization control according to claim 5 is characterized by: Obtain the changes in historical nighttime duration and use a sine-like function to model seasonal changes in nighttime length. The seasonal change function is expressed as: ;in, It's in time The length of night at 9 o'clock (hours), A is the amplitude of night length, reflecting the biggest difference between summer and winter seasons, is the periodic coefficient, which is related to the seasonal changes in a year, is the time offset, used to adjust the starting point of seasonal changes, It is the benchmark value of night length, representing the length of night in spring and autumn; The Yin-Yang regulation intensity is calculated based on the change in the wind turbine's power load and is expressed as: ;in, is the initial power, is the adjusted power; The seasonal variation function of the Yin-Yang interval and the Yin-Yang regulation intensity is expressed as: = ×(1+ );in, It's in time The length of night when Q is the wind turbine power load change calculation to obtain the regulation intensity; The end Yin-Yang adjustment point is the time point after the Yin-Yang interval time of the start Yin-Yang adjustment point, expressed as: 。 7. The highway tunnel fan dispatching system with multi-device collaborative optimization control according to claim 6 is characterized by: The convergence curve is a graph showing how the optimal solution value changes with the number of iterations. As the iterations proceed, the optimal solution value gradually decreases, indicating that the particle swarm has found a better solution. Until the algorithm converges, the convergence rate is calculated based on the convergence curve. After receiving the convergence speed and the yin-yang adjustment strength, the convergence speed and the yin-yang adjustment strength are defined as input variables and divided into different fuzzy sets respectively; The weight adjustment strategy is defined as the output variable, which is divided into fuzzy sets; Formulate fuzzy rules to describe the impact of convergence speed and the definition of yin-yang regulation strength on the weight adjustment strategy; Perform fuzzy reasoning based on fuzzy rules to determine the weight adjustment strategy of power banks; Select the corresponding weight adjustment strategy based on fuzzy reasoning.

8. The highway tunnel fan dispatching system with multi-device collaborative optimization control according to claim 7 is characterized by: The proportional weight adjustment is expressed as: ;in, It is The inertia weight of the iteration, and are the maximum and minimum values ​​of the inertia weight, is the optimal solution value of the current iteration, is the maximum value of the optimal solution; The linear weight adjustment algorithm calculation is expressed as: ;in, It is The inertia weight of the iteration, and are the maximum and minimum values ​​of the inertia weight, is the current iteration number, is the total number of iterations; Use the corresponding weight adjustment strategy to modify the corresponding weights of energy consumption, environmental conditions and the number of fan starts and stops.

Images