Tunnel fan group cooperative control dynamic optimization method and system

Abstract

The application provides a tunnel fan group cooperative control dynamic optimization method and system. In the application, the dynamic data of vehicles in the tunnel is tracked through the lightning and vision fusion technology, the data is analyzed by the edge computing node, and the environmental monitoring index is combined to construct a multi-dimensional game parameter set. Based on the dynamic game theory model, the fan cooperative response strength is dynamically adjusted, the smoke exhaust efficiency and the evacuation passage wind speed constraint are balanced, the fan control priority is calculated, the differentiated rotating speed and deflection angle control are driven, the environmental feedback data is generated, and the game strategy weight is iteratively optimized, so that the rolling time domain control is realized until the vehicle movement and the environmental index reach the stable interval. The technical scheme provided by the application realizes the dynamic cooperative optimization of tunnel smoke exhaust and evacuation safety, and improves the ventilation response efficiency and evacuation passage safety in emergency scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cooperative control, and in particular to a tunnel fan group cooperative control dynamic optimization method and system. BACKGROUND

[0002] With the acceleration of urbanization and the continuous expansion of the transportation network, as an important part of modern transportation, the safety of the tunnel, especially the fire safety, is particularly important. Once a fire occurs in the tunnel, due to the closed space and poor ventilation conditions, smoke and toxic gases are not easy to diffuse, which can pose a serious threat to the safety of internal personnel and can cause huge losses of property. Therefore, how to effectively control the air flow in the tunnel, quickly remove smoke and harmful gases, and ensure the safety and smoothness of the evacuation passage has become the key to improving the response capability of the tunnel fire. It is urgent to develop an efficient and reliable fan group cooperative control dynamic optimization method to achieve the above-mentioned goal.

[0003] In the prior art, a control strategy based on preset rules is usually used to operate the fan group, for example, according to the position information of the fire detector and the size of the fire, a corresponding number of fans are started according to the preset speed gear, so as to achieve the effect of rapid smoke exhaust.

[0004] However, the prior art has obvious defects, that is, it is difficult to make the optimal response to different fire sizes and positions, resulting in waste of resources or poor control effect. The preset rules usually cannot cover all possible fire scenarios, resulting in slow or inaccurate response when facing unforeseen situations. SUMMARY

[0005] The present application provides a tunnel fan group cooperative control dynamic optimization method and system to solve the problem of poor coordination control accuracy in the prior art.

[0006] In a first aspect, the present application provides a tunnel fan group cooperative control dynamic optimization method, comprising:

[0007] Obtaining dynamic position, speed and traffic density information of multiple types of vehicles in the tunnel based on a radar and vision fusion vehicle tracking database;

[0008] Parsing the information obtained from the radar and vision fusion vehicle tracking database by an edge computing node deployed in the tunnel section, performing simulation of the ventilation and evacuation combined strategy, extracting vehicle position distribution and motion trend characteristics, and combining carbon monoxide concentration, visibility index and fire smoke diffusion and vehicle evacuation path conflict probability calculation results in the tunnel environment monitoring data to construct a game parameter set;

[0009] The coordinated response intensity among the fans is dynamically adjusted according to the set of game parameters. In the dynamic game theory model, the control command priority of each fan in the fan group is calculated by balancing the smoke exhaust efficiency and the evacuation channel wind speed constraint.

[0010] Based on the priority of the control commands, differentiated speed and deflection angle control is performed on the wind turbine group to generate tunnel environment feedback data after the wind turbine group has executed the control commands.

[0011] Based on the feedback data from the tunnel environment, the game strategy weights in the dynamic game theory model are iteratively updated, and the control commands for the wind turbine group are optimized in the rolling time domain by combining edge computing nodes until the vehicle movement trend and environmental indicators reach the preset coordinated stability range.

[0012] Optionally, the coordinated response intensity among the fans is dynamically adjusted based on the set of game parameters. In the dynamic game theory model, the control command priority of each fan in the fan group is calculated by balancing smoke extraction efficiency and evacuation channel wind speed constraints, including:

[0013] The vehicle location distribution, movement trend characteristics, carbon monoxide concentration, visibility index, and probability of conflict between smoke diffusion and evacuation routes in the game parameter set are mapped to environmental state parameters, vehicle state parameters, and risk parameters related to wind turbine control in the dynamic game theory model according to preset priority rules.

[0014] Based on the variation range of environmental state parameters and vehicle state parameters, the coordinated response intensity between wind turbines is dynamically adjusted. The coordinated response intensity is quantified by the coupling relationship of the local action range overlap between different wind turbines, the complementarity of the smoke exhaust direction of adjacent wind turbine groups, and the wind speed gradient constraint in the evacuation channel.

[0015] In the dynamic game theory model, a game relationship between smoke exhaust efficiency and evacuation channel wind speed constraint is constructed. The smoke exhaust efficiency is calculated by the correlation between the smoke diffusion rate and the negative pressure gradient of the area covered by the fan group. The evacuation channel wind speed constraint is limited by the angle threshold between the evacuation path direction in the vehicle motion trend characteristics and the local wind speed direction generated by the fan group.

[0016] Based on the weight of smoke exhaust efficiency and the weight of wind speed constraint in the evacuation channel in the game relationship, the priority of control commands for each fan in the fan group is calculated. The priority parameter is jointly determined by the environmental state parameters of the fan's location, the fan's coverage contribution to the smoke diffusion path, and the matching degree between the fan and the wind speed direction and vehicle movement trend in the evacuation channel.

[0017] Optionally, in the dynamic game theory model, a game relationship is constructed between smoke extraction efficiency and evacuation route wind speed constraints, including:

[0018] The smoke diffusion rate is dynamically correlated with the negative pressure gradient of the area covered by the fan group. The negative pressure gradient is calculated based on the position distribution and rotation speed parameters of each fan in the fan group. The smoke diffusion rate is jointly derived from the smoke concentration distribution gradient in the tunnel and the direction of change in traffic density in the vehicle movement trend characteristics. The dynamic correlation result is used as the quantitative basis for smoke exhaust efficiency.

[0019] Based on the angle threshold between the evacuation path direction and the local wind speed direction generated by the wind turbine group, a quantitative rule for evacuation channel wind speed constraint is constructed. The angle threshold is segmented and corrected according to the dynamic deviation between the evacuation path direction and the local wind speed direction within the coverage area of ​​the wind turbine group in the vehicle motion trend characteristics. The correction coefficient is dynamically adjusted by the conflict probability between the evacuation path and the smoke diffusion path.

[0020] The quantitative results of smoke exhaust efficiency and the quantitative rules of evacuation channel wind speed constraints are respectively mapped to the objective function and constraint conditions in the dynamic game theory model. The objective function is generated by the dynamic correlation between smoke diffusion rate and negative pressure gradient, and the constraint conditions are generated by the dynamic deviation between the included angle threshold and the evacuation path direction.

[0021] In the dynamic game theory model, the objective function and the constraints are constructed through a game relationship. The optimization direction of the objective function and the range of the constraints are dynamically balanced through the game strategy weights. The game strategy weights are dynamically adjusted by the change range of carbon monoxide concentration and visibility index in the tunnel environmental monitoring data. The objective function is constrained and corrected by applying the quantitative rules of the evacuation channel wind speed constraint.

[0022] Based on the results of the game relationship construction, a set of game strategies for smoke exhaust efficiency and evacuation channel wind speed constraints is generated. The set of game strategies is jointly determined by the optimization results of the objective function and the constraint conditions, and serves as the basis for calculating the priority of the wind turbine group control commands.

[0023] Optionally, by using edge computing nodes deployed within the tunnel section to parse the information obtained from the radar-visual fusion vehicle tracking database, simulation of the joint ventilation and evacuation strategy is performed, and vehicle location distribution and movement trend characteristics are extracted. Combined with the carbon monoxide concentration, visibility index, and the probability calculation results of fire smoke diffusion and vehicle evacuation path conflicts from tunnel environmental monitoring data, a set of game parameters is constructed, including:

[0024] Dynamic trajectory data of various types of vehicles in the tunnel are extracted from the radar-visual fusion vehicle tracking database, parsed into structured information of vehicle position coordinates, instantaneous speed and direction of motion, and mapped into a heat map of vehicle distribution and motion trend vector field in the tunnel section based on the tunnel topology.

[0025] Based on the distribution heat map and motion trend vector field, the simulation of the joint ventilation and evacuation strategy is performed in the edge computing node. The simulation process simulates the conflict probability of smoke diffusion path and vehicle evacuation path under different ventilation modes by dynamically adjusting the candidate control instruction set of the fan group, and extracts the clustering characteristics of vehicle position distribution and the continuity characteristics of motion trend in the simulation results.

[0026] The carbon monoxide concentration and visibility index in the tunnel environmental monitoring data are mapped to dynamic influencing factors of smoke diffusion rate and air pollutant concentration, respectively. Combined with the conflict probability calculation results of fire smoke diffusion path and vehicle evacuation path, the threat level parameter of smoke diffusion to evacuation path is generated.

[0027] Based on the clustering characteristics of vehicle location distribution, the continuity characteristics of movement trends, and the threat level parameters of smoke diffusion, a set of game parameters for a dynamic game theory model is constructed. The set of game parameters includes environmental state parameters, vehicle state parameters, and risk parameters. The environmental state parameters are jointly defined by carbon monoxide concentration, visibility index, and smoke diffusion rate. The vehicle state parameters are jointly defined by the clustering degree of the distribution heatmap and the continuity of the movement trend vector field. The risk parameters are jointly defined by the conflict probability between the smoke diffusion path and the evacuation path and the threat level parameters.

[0028] Optionally, based on the clustering characteristics of the vehicle location distribution, the continuity characteristics of the movement trend, and the threat level parameters of smoke diffusion, a set of game parameters for a dynamic game theory model is constructed, including:

[0029] The carbon monoxide concentration, visibility index, and smoke diffusion rate are respectively mapped to the pollutant concentration parameter, visibility impact parameter, and smoke diffusion rate parameter in the environmental state parameters. The pollutant concentration parameter is defined by the change range of carbon monoxide concentration, the visibility impact parameter is defined by the change gradient of visibility index, and the smoke diffusion rate parameter is defined by the matching degree between the change direction of smoke diffusion rate and the tunnel topology.

[0030] The clustering degree of the distribution heatmap and the continuity of the motion trend vector field are respectively mapped to the vehicle clustering degree parameter and the motion continuity parameter in the vehicle state parameters. The vehicle clustering degree parameter is defined by the ratio of the area of ​​the high-value region of vehicle density in the distribution heatmap to the volume of the tunnel section, and the motion continuity parameter is defined by the local consistency feature of the vehicle motion direction in the motion trend vector field.

[0031] The conflict probability and threat level parameters of the smoke diffusion path and evacuation path are mapped to the path conflict parameter and threat level parameter in the risk parameters, respectively. The path conflict parameter is defined by the ratio of the area of ​​the intersection region of the smoke diffusion path and the evacuation path to the total area of ​​the tunnel section, and the threat level parameter is defined by the product of the threat level parameter and the smoke diffusion rate.

[0032] Based on the pollutant concentration parameters, visibility impact parameters, and smoke diffusion rate parameters, an environmental state parameter set is constructed. The environmental state parameter set is defined by a weighted sum of the pollutant concentration parameters, visibility impact parameters, and smoke diffusion rate parameters, and the weights are dynamically adjusted by the change range of the tunnel environmental monitoring data.

[0033] Based on the vehicle clustering parameters and motion continuity parameters, a vehicle state parameter set is constructed, wherein the vehicle state parameter set is defined by the weighted sum of the vehicle clustering parameters and motion continuity parameters, and the weights are dynamically adjusted by the change amplitude in the vehicle motion trend characteristics.

[0034] Based on the path conflict parameters and threat level parameters, a risk parameter set is constructed, wherein the risk parameter set is defined by the weighted sum of the path conflict parameters and threat level parameters, and the weights are dynamically adjusted by the change in the probability of conflict between the smoke diffusion path and the evacuation path.

[0035] The environmental state parameter set, vehicle state parameter set, and risk parameter set are jointly constructed into a game parameter set for a dynamic game theory model, wherein the game parameter set is dynamically updated by the change range of the environmental state parameter set, vehicle state parameter set, and risk parameter set.

[0036] Optionally, based on tunnel environment feedback data, the game strategy weights in the dynamic game theory model are iteratively updated, and the control commands for the wind turbine group are optimized in the rolling time domain using edge computing nodes until the vehicle movement trend and environmental indicators reach a preset cooperative stability range, including:

[0037] The carbon monoxide concentration, visibility index, local wind speed direction, and vehicle movement trend characteristics in the tunnel environment feedback data are decomposed into environmental state deviation parameters and vehicle state deviation parameters. The environmental state deviation parameters are defined by the change gradient of carbon monoxide concentration and visibility index, and the vehicle state deviation parameters are defined by the angle deviation between the evacuation path direction and the local wind speed direction in the vehicle movement trend characteristics.

[0038] Based on the environmental state deviation parameters and vehicle state deviation parameters, the game strategy weights in the dynamic game theory model are iteratively updated. The game strategy weights are jointly calculated by the influence weight of the environmental state deviation parameters on the smoke exhaust efficiency and the conflict weight of the vehicle state deviation parameters on the wind speed constraint of the evacuation channel, and are dynamically corrected using the attenuation coefficient of the historical game strategy weights.

[0039] Based on the updated game strategy weights, a candidate instruction set for wind turbine group control commands is generated in the edge computing nodes. The candidate instruction set is dynamically generated by combining the priority parameters of wind turbine speed, deflection angle and coverage area. The priority parameters are defined by the contribution of the wind turbine to the smoke exhaust efficiency and the wind speed constraint of the evacuation passage.

[0040] Rolling time-domain optimization is performed on the candidate instruction set, wherein the time window length of the rolling time-domain optimization is defined by the dynamic adjustment amplitude of the evacuation path in the vehicle motion trend characteristics, and the optimization objective is to minimize the weighted cumulative value of the environmental state deviation parameter and the vehicle state deviation parameter within the time window until the vehicle motion trend and environmental indicators reach a preset cooperative stability range.

[0041] Optionally, based on the priority of the control commands, differentiated speed and deflection angle control is performed on the wind turbine group to generate tunnel environment feedback data after the wind turbine group has executed the control commands, including:

[0042] The control command priority is mapped to the speed and deflection angle parameters of each fan in the fan group. The speed parameter is defined by the contribution of the fan to the smoke exhaust efficiency and the negative pressure gradient of the covered area. The deflection angle parameter is defined by the matching degree of the fan to the wind speed direction in the evacuation channel and the consistency coefficient of the local wind speed direction.

[0043] Based on the aforementioned speed and deflection angle parameters, a differentiated control instruction set is generated for each wind turbine in the wind turbine group. The differentiated control instruction set is dynamically generated by combining the adjustment range of the wind turbine speed and the adjustment angle of the deflection angle, and is rolled over using the historical control instruction set of the wind turbine group.

[0044] The differentiated control instruction set is executed to control each fan in the fan group. The control process is achieved by dynamically superimposing the adjustment range of the fan speed and the adjustment angle of the deflection angle, and the negative pressure gradient change rate and the consistency coefficient of the local wind speed direction in the fan coverage area are monitored.

[0045] Based on the operating status of the wind turbine group after executing differentiated control command sets, tunnel environment feedback data is generated. The tunnel environment feedback data includes carbon monoxide concentration, visibility index, local wind speed direction, and vehicle movement trend characteristics. The carbon monoxide concentration is defined by the correlation result between the negative pressure gradient change rate of the wind turbine coverage area and the smoke diffusion rate. The visibility index is defined by the correlation result between the consistency coefficient of the local wind speed direction and the smoke diffusion rate. The local wind speed direction is defined by the matching degree between the adjustment angle of the wind turbine deflection angle and the tunnel topology. The vehicle movement trend characteristics are defined by the angular deviation between the evacuation path direction and the local wind speed direction.

[0046] Secondly, the present invention provides a dynamic optimization system for collaborative control of tunnel ventilation fan groups, comprising:

[0047] The acquisition module obtains dynamic location, speed, and traffic density information of various types of vehicles in the tunnel based on the radar-visual fusion vehicle tracking database;

[0048] The computing module parses the information obtained from the radar-visual fusion vehicle tracking database through edge computing nodes deployed in the tunnel section, performs simulation of the ventilation and evacuation joint strategy, extracts the vehicle position distribution and movement trend characteristics, and constructs a set of game parameters by combining the carbon monoxide concentration, visibility index and fire smoke diffusion and vehicle evacuation path conflict probability calculation results in the tunnel environmental monitoring data.

[0049] The calculation module is also used to dynamically adjust the intensity of the coordinated response between the fans according to the weight of the game parameter set. In the dynamic game theory model, the priority of the control command for each fan in the fan group is calculated by balancing the smoke exhaust efficiency and the wind speed constraint of the evacuation channel.

[0050] The generation module performs differentiated speed and deflection angle control on the wind turbine group based on the priority of the control command, and generates tunnel environment feedback data after the wind turbine group has been executed.

[0051] The optimization module iteratively updates the game strategy weights in the dynamic game theory model based on tunnel environment feedback data, and performs rolling time-domain optimization of the wind turbine group control commands through edge computing nodes until the vehicle movement trend and environmental indicators reach a preset coordinated stability range.

[0052] Thirdly, embodiments of the present invention provide a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are to be invoked and executed by the processing component to implement a dynamic optimization method for collaborative control of a tunnel ventilation fan group as described in the first aspect above.

[0053] Fourthly, embodiments of the present invention provide a computer storage medium storing a computer program, which, when executed by a computer, implements a dynamic optimization method for collaborative control of a tunnel ventilation fan group as described in the first aspect.

[0054] This invention employs a radar-visual fusion vehicle tracking database to acquire dynamic position, speed, and traffic density information of various vehicle types within a tunnel. Edge computing nodes deployed within the tunnel section parse the information from this database, simulate a combined ventilation and evacuation strategy, and extract vehicle position distribution and movement trend characteristics. A game theory parameter set is constructed by combining carbon monoxide concentration, visibility indicators, and the probability of conflict between fire smoke diffusion and vehicle evacuation paths from tunnel environmental monitoring data. The coordinated response intensity among the fans is dynamically adjusted based on the weights of this parameter set. In a dynamic game theory model, the priority of control commands for each fan in the fan group is calculated by balancing smoke extraction efficiency and evacuation channel wind speed constraints. Based on these priority commands, differentiated speed and deflection angle control is implemented on the fan group, generating tunnel environmental feedback data after the fan group's execution. The game strategy weights in the dynamic game theory model are iteratively updated based on the tunnel environmental feedback data, and the control commands for the fan group are continuously optimized over time using edge computing nodes until the vehicle movement trend and environmental indicators reach a preset coordinated stability range.

[0055] The technical solution of this invention has the following beneficial effects:

[0056] By employing radar-visual fusion technology to capture dynamic vehicle information within tunnels, the accuracy and reliability of vehicle position and movement trend monitoring are improved. Integrating vehicle distribution, environmental indicators, and smoke path conflict probabilities enables multi-dimensional data collaborative modeling, supporting multi-objective constraint balance in dynamic game theory strategies. Based on game parameter weights, the efficiency of smoke extraction and evacuation wind speed constraints are dynamically balanced, optimizing the priority of coordinated response for fan groups. Differentiated speed and deflection angle control precisely adjusts local ventilation intensity, ensuring wind speed balance between smoke extraction and evacuation channels. The game theory strategy is continuously updated based on environmental feedback data, enhancing the model's adaptability to dynamic scenarios and driving the system towards a stable state.

[0057] By using spatiotemporal correlation modeling and dynamic weight correction, the adaptability and computational efficiency of the game strategy to complex scenarios are improved; the rolling time-domain optimization mechanism enables dynamic adjustment of fan control commands, ensuring a precise balance between smoke exhaust and evacuation wind speed constraints; and the closed-loop control of the collaborative stability interval significantly shortens the system response delay, ensuring the dynamic unity of tunnel environmental safety and vehicle evacuation efficiency.

[0058] These or other aspects of the invention will become more apparent from the following description of the embodiments. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 A flowchart of a dynamic optimization method for collaborative control of tunnel ventilation fan groups provided by the present invention is shown;

[0061] Figure 2 This invention provides a schematic diagram of the structure of a dynamic optimization system for collaborative control of tunnel ventilation fan groups.

[0062] Figure 3 A schematic diagram of the structure of a computing device provided by the present invention is shown. Detailed Implementation

[0063] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0064] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0065] This invention uses radar-visual fusion technology to collect dynamic position, speed, and traffic density data of vehicles in tunnels. It analyzes and simulates joint ventilation and evacuation strategies through edge computing nodes to extract vehicle distribution trend characteristics. Combining carbon monoxide concentration, visibility, and the probability of conflict between smoke diffusion and evacuation paths, a multi-dimensional game parameter set is constructed. The coordinated response intensity of the fans is dynamically adjusted according to parameter weights. In the dynamic game model, smoke extraction efficiency and evacuation channel wind speed constraints are balanced, and fan control priorities are calculated. Differential speed and deflection angle control is executed based on priorities. After generating environmental feedback data, the game strategy weights are iteratively updated. Fan commands are continuously adjusted through rolling time-domain optimization until vehicle movement and environmental indicators reach a coordinated stable state.

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] Figure 1 A flowchart of a dynamic optimization method for collaborative control of a tunnel ventilation fan group is provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:

[0068] 101. Based on the radar-visual fusion vehicle tracking database, obtain dynamic position, speed and traffic density information of various types of vehicles in the tunnel;

[0069] Radar-Vision Fusion Vehicle Tracking Database: Integrates radar and video recognition data to dynamically track vehicle 3D coordinates, velocity vectors, and distances between adjacent vehicles. Traffic Density: Number of vehicles per unit tunnel length, inferred from vehicle spacing. Dynamic Location: Includes vehicle latitude, longitude, elevation, and lane departure data.

[0070] In step 101, the system deploys a multimodal perception network consisting of a millimeter-wave radar array (operating frequency 76-81GHz) and a 4K infrared camera. It uses a spatiotemporal alignment algorithm to eliminate data latency between devices and leverages YOLOv7+DeepSORT (where YOLOv7 and DeepSORT are two widely used technologies in computer vision and target tracking, which are usually used together to achieve efficient and accurate detection and tracking of objects in video streams) to achieve cross-modal target association between radar point clouds and video images. The system calculates the instantaneous vehicle speed through displacement difference of three consecutive frames and calculates the traffic flow density by combining an improved kernel density estimation algorithm (the bandwidth parameter is dynamically adjusted according to the tunnel curvature). Finally, the system aggregates the vehicle's three-dimensional coordinates (including latitude, longitude, elevation, and lane offset), velocity vector, and density data to the central database through a 5G private network.

[0071] Inside a 3-kilometer-long tunnel, radar-camera arrays are deployed every 50 meters along the tunnel arch to capture vehicle movement trajectories. When truck A travels at 60 km / h, the system identifies the vehicle type using radar cross-section characteristics, verifies the license plate information using video streams, and calculates the current traffic density of 28 vehicles / km based on the distance between vehicles in front and behind, with a data update frequency of 20Hz.

[0072] 102. By using edge computing nodes deployed in the tunnel section to parse the information obtained from the radar-visual fusion vehicle tracking database, the simulation of the ventilation and evacuation joint strategy is performed and the characteristics of vehicle position distribution and movement trend are extracted. Combined with the carbon monoxide concentration, visibility index and the probability calculation results of the conflict between fire smoke diffusion and vehicle evacuation path in the tunnel environmental monitoring data, a set of game parameters is constructed.

[0073] Joint ventilation and evacuation strategy: Considering the dynamic equations of smoke exhaust fan power, escape route wind speed threshold, and vehicle evacuation paths. Conflict probability: The spatial overlap between the trajectory of fire smoke particles and the planned vehicle paths. Game parameter set: Includes 12-dimensional feature vectors such as environmental threat level (0-1), evacuation efficiency weight (0.5-2), and equipment energy consumption coefficient.

[0074] In step 102, the edge computing node (equipped with NVIDIA Jetson AGX Xavier) first parses the database data, calls the FDS fire dynamics simulation software to simulate the smoke diffusion path under different ventilation strategies, and simultaneously constructs a discrete event model through Anylogic to simulate vehicle evacuation paths. It uses the attention mechanism LSTM to extract the movement trend features of vehicle clusters (such as the rate of change of acceleration and the degree of steering concentration), combines the Gaussian plume model to predict the smoke concentration distribution, and then calculates the spatial overlap probability between the smoke front and the vehicle path through Monte Carlo simulation (5000 iterations). Finally, it normalizes 12-dimensional indicators such as carbon monoxide concentration gradient (ppm / m), visibility decay rate (m / s), and conflict probability (0-1 scale) into a set of game parameters.

[0075] When the CO concentration in the middle section of the tunnel suddenly increased to 800 ppm, the edge nodes initiated a joint simulation: first, the evacuation path network was reconstructed based on vehicle GPS data, and then the smoke diffusion rate under different fan combinations was simulated. One simulation showed that when fans #5 and #7 were turned on, the probability of heavy-duty trucks encountering the smoke front decreased from 43% to 19%. This result was encoded as game parameters [0.73, 1.2, 0.88...].

[0076] 103. The coordinated response intensity among the fans is dynamically adjusted according to the weight of the game parameter set. In the dynamic game theory model, the control command priority of each fan in the fan group is calculated by balancing the smoke exhaust efficiency and the evacuation channel wind speed constraint.

[0077] Coordinated Response Strength: Power coupling coefficient of the wind turbine group, ranging from 0 (independent operation) to 1 (fully synchronized). Smoke Exhaust Efficiency: CO concentration decrease gradient per unit time (ppm / s). Escape Route Wind Speed ​​Constraints: Axial wind speed along escape routes must be maintained within the range of 2-5 m / s.

[0078] Step 103 employs a dynamic game theory model to construct an asymmetric payoff matrix (rows represent wind turbine control strategies, and columns correspond to environmental threat levels). The Pareto optimal solution is iteratively solved using an improved Nash-Q learning algorithm. The priority of control commands is calculated by combining the historical contribution of the wind turbine (output percentage over the past 30 minutes) and the spatial influence radiation range (flow field influence radius based on CFD pre-calculation) using the Shapley value allocation method. This achieves a dynamic balance between smoke exhaust efficiency (CO concentration decrease gradient) and evacuation channel wind speed constraints (2-5 m / s range).

[0079] When the fire occurred, the game theory model calculated that the priority of fan #3 (120m from the fire source) was increased to 0.92, requiring it to operate at 2800rpm; the weight of fan #6 (located downwind) was reduced to 0.35, maintaining 1500rpm. Calculations confirmed that the combined strategy could achieve a smoke extraction efficiency of 42ppm / s while ensuring a stable wind speed of 3.2m / s in the escape routes.

[0080] 104. Based on the priority of the control commands, perform differentiated speed and deflection angle control on the wind turbine group, and generate tunnel environment feedback data after the wind turbine group has executed the control commands.

[0081] Differentiated speed control: Each fan is independently PID-regulated, with a speed range of 800-3000 rpm. Deflection angle control: Motorized guide vanes can be adjusted within ±30° to change the airflow vector direction. Environmental feedback data: Includes verification indicators such as CO concentration gradient, visibility recovery rate, and actual wind speed distribution.

[0082] Step 104, based on the priority list, converts the instructions into specific parameters through a distributed robust control strategy: the speed control adopts PID closed-loop regulation (set value error ±50rpm), the deflection angle control matches the pre-stored airflow pattern library (containing 16 typical CFD operating conditions), and after execution, the actual CO concentration distribution, visibility recovery curve and wind speed field data are collected as feedback data through a laser anemometer array (accuracy ±0.1m / s) and a spectroscopic gas analyzer (sampling rate 1Hz).

[0083] During the execution phase, the #2 fan was adjusted to a 15° deflection angle to guide airflow around the stagnant vehicle cluster; the #4 fan was increased to 2500 rpm to address the upstream smoke accumulation. Feedback data showed that the CO concentration in the target area decreased by 62% within 10 seconds, but the wind speed at the E34 measuring point exceeded the limit to 5.8 m / s, triggering a constraint alarm.

[0084] 105. Based on the feedback data of the tunnel environment, iteratively update the game strategy weights in the dynamic game theory model, and perform rolling time-domain optimization of the wind turbine group control commands through edge computing nodes until the vehicle movement trend and environmental indicators reach the preset coordinated stability range.

[0085] Game strategy weights: Includes 6 adjustable parameters such as environmental threat response coefficient (0.8-1.5) and equipment lifespan loss factor (0.6-1.2). Rolling time-domain optimization: Replans the control sequence for the next 150 seconds every 30 seconds. Cooperative stability range: Defined as a multi-objective Pareto front with CO < 300 ppm, visibility > 50 m, and evacuation route wind speed of 2.8-4.5 m / s.

[0086] Step 105 establishes a two-layer optimization loop. The inner loop uses LSTM to predict the environmental state for the next 150 seconds, while the outer loop uses Bayesian optimization to adjust the weight parameters of the game model (including the weight coefficient of smoke emission efficiency, equipment life loss factor, etc.). The control sequence is recalculated every 30 seconds. The optimization is terminated when the variance of the fitness function (calculated based on KL divergence to determine the strategy bias) for three consecutive iterations is less than 0.05 and all environmental indicators enter the cooperative stability range (CO < 300 ppm, visibility > 50 m, wind speed 2.8-4.5 m / s).

[0087] After the initial control, visibility in zone E22 only improved to 45m, and the system automatically increased the smoke extraction efficiency weight by 15%. After the second optimization, the high-frequency pulse mode of fan #1 was activated, and fan #5 was deflected by -10°, enabling visibility to reach the standard within 18 seconds. After four rounds of rolling optimization, all indicators entered the green stable range and remained there.

[0088] This solution constructs a closed-loop control system encompassing "perception, decision-making, execution, and evolution," achieving a four-dimensional improvement in tunnel emergency response: vehicle positioning errors are controlled to ±15cm through radar-visual fusion; a game theory model improves smoke extraction efficiency by 37% while reducing energy consumption by 22%; a rolling optimization mechanism shortens environmental compliance time by 58%; and differentiated control reduces the risk of secondary accidents caused by airflow disturbances. The data coupling degree across all stages reaches 92%, and the system response latency is <800ms, meeting the stringent requirements of the EN50545 standard for intelligent tunnel control.

[0089] To achieve dynamic optimization of the coordinated control of wind turbine groups, a multi-source data fusion and dynamic game theory model are constructed. First, the vehicle location distribution, motion trend characteristics, carbon monoxide concentration, visibility index, and the probability of smoke diffusion and evacuation path conflict in the game parameter set are mapped to environmental state parameters, vehicle state parameters, and risk parameters in the dynamic game theory model according to preset priority rules, ensuring the structured nature and scenario adaptability of the input data. Second, based on the changes in environmental and vehicle state parameters, the intensity of the coordinated response among wind turbines is dynamically adjusted to ensure the flexibility and effectiveness of the wind turbine control strategy. Next, a game relationship between smoke extraction efficiency and evacuation path wind speed constraints is constructed in the dynamic game theory model. By balancing the weights of smoke extraction efficiency and evacuation path wind speed constraints, the priority of control commands for each wind turbine in the wind turbine group is calculated, providing a scientific basis for differentiated control of the wind turbine group. In some embodiments, the coordinated response intensity among the wind turbines is dynamically adjusted based on the set of game parameters. In the dynamic game theory model, the priority of control commands for each wind turbine in the wind turbine group is calculated by balancing smoke extraction efficiency and evacuation channel wind speed constraints, including:

[0090] 201. The vehicle location distribution, motion trend characteristics, carbon monoxide concentration, visibility index, and probability of conflict between smoke diffusion and evacuation path in the game parameter set are mapped to environmental state parameters, vehicle state parameters and risk parameters related to wind turbine control in the dynamic game theory model according to the preset priority rules.

[0091] The game parameter set includes vehicle location distribution (vehicle positions within the tunnel), motion trend characteristics (vehicle direction and speed), carbon monoxide concentration (concentration of air pollutants within the tunnel), visibility index (visual clarity within the tunnel), and the probability of conflict between smoke diffusion and evacuation paths (the probability of intersection between smoke diffusion paths and vehicle evacuation paths). Environmental state parameters are jointly defined by carbon monoxide concentration, visibility index, and smoke diffusion rate, used to describe the environmental state within the tunnel. Vehicle state parameters are jointly defined by the clustering degree of vehicle location distribution and the continuity of the motion trend vector field, used to describe the distribution and motion characteristics of vehicles within the tunnel. Risk parameters are jointly defined by the probability of conflict between smoke diffusion paths and evacuation paths and threat level parameters, used to describe the threat posed by smoke diffusion to vehicle evacuation.

[0092] In this embodiment of the invention, firstly, vehicle location distribution data is extracted from the game parameter set, parsed into vehicle location coordinates within the tunnel, and combined with the tunnel topology to generate a vehicle location distribution heatmap. Next, motion trend feature data is extracted, parsed into vehicle motion direction and speed, and a motion trend vector field is generated. Then, carbon monoxide concentration and visibility indicators are mapped to pollutant concentration parameters and visibility impact parameters in the environmental state parameters, respectively, and smoke diffusion rate is mapped to a smoke diffusion rate parameter. Finally, based on the conflict probability between smoke diffusion paths and evacuation paths, path conflict parameters and threat level parameters are generated in the risk parameters. Through preset priority rules, the above parameters are mapped to environmental state parameters, vehicle state parameters, and risk parameters, respectively, as input data for the dynamic game theory model.

[0093] 202. Based on the variation range of environmental state parameters and vehicle state parameters, dynamically adjust the coordinated response intensity between wind turbines;

[0094] The intensity of the coordinated response is quantified by the coupling relationship of the overlap of the local action range between different fans, the complementarity of the smoke exhaust direction of adjacent fan groups, and the wind speed gradient constraint in the evacuation channel. The change range of environmental state parameters and vehicle state parameters describes the dynamic changes of environmental state parameters (such as carbon monoxide concentration and visibility index) and vehicle state parameters (such as vehicle aggregation degree and motion continuity).

[0095] In this embodiment of the invention, firstly, based on the variation range of environmental state parameters, the dynamic variation gradients of pollutant concentration parameters, visibility impact parameters, and smoke diffusion rate parameters are calculated. Next, based on the variation range of vehicle state parameters, the dynamic variation gradients of vehicle aggregation parameters and motion continuity parameters are calculated. Then, according to the aforementioned variation gradients, the cooperative response intensity among the fans is dynamically adjusted, wherein the cooperative response intensity is quantified by the overlap of the local action range of the fan group, the complementarity of smoke exhaust directions, and the wind speed gradient constraints within the evacuation channels. Finally, the adjusted cooperative response intensity is used as the input parameter for the fan group control command.

[0096] 203. In the dynamic game theory model, construct the game relationship between smoke exhaust efficiency and evacuation channel wind speed constraints;

[0097] The smoke extraction efficiency is calculated by relating the smoke diffusion rate to the negative pressure gradient of the area covered by the fan group. The evacuation route wind speed constraint is limited by the angle threshold between the evacuation path direction in the vehicle motion trend characteristics and the local wind speed direction generated by the fan group. Control command priority: describes the control priority of each fan in the fan group, defined by the fan's contribution to the smoke extraction efficiency and the evacuation route wind speed constraint.

[0098] In this embodiment of the invention, firstly, the quantification of smoke extraction efficiency is the foundation for constructing the game theory relationship. Smoke extraction efficiency is calculated by dynamically correlating the smoke diffusion rate with the negative pressure gradient of the area covered by the fan group. The smoke diffusion rate reflects the speed at which smoke diffuses within the tunnel, while the negative pressure gradient describes the gradient of air pressure change within the area covered by the fan group. By dynamically correlating these two factors, a quantified result of the smoke extraction efficiency can be generated, serving as the objective function in the game theory relationship.

[0099] Among them, the optimization direction of the objective function is to maximize the smoke exhaust efficiency, that is, to minimize the spread of smoke in the tunnel through the coordinated control of the fan group. Secondly, the quantitative rules of the wind speed constraint of the evacuation channel are another key to the construction of the game relationship.

[0100] The evacuation route wind speed constraint is defined by an angle threshold between the evacuation path direction (as seen in vehicle movement trend characteristics) and the local wind speed direction generated by the fan group. The evacuation path direction describes the evacuation direction of vehicles within the tunnel, while the local wind speed direction describes the wind speed direction within the fan group's coverage area. By calculating the dynamic deviation between the two and combining it with the conflict probability between the evacuation path and the smoke diffusion path, the angle threshold can be dynamically adjusted to generate quantitative rules for the evacuation route wind speed constraint. These quantitative rules, as constraints in the game theory relationship, ensure the matching degree between the wind speed direction and vehicle movement trend within the evacuation route, thereby guaranteeing vehicle evacuation safety. In the dynamic game theory model, the game relationship between the objective function and the constraints is dynamically balanced through game strategy weights. The game strategy weights describe the relative importance of the objective function and constraints in the game relationship and are dynamically adjusted by the changes in tunnel environmental monitoring data and vehicle movement trend characteristics. Finally, based on the game relationship construction results, a set of game strategies for smoke extraction efficiency and evacuation route wind speed constraints is generated.

[0101] 204. Based on the weight of smoke exhaust efficiency and the weight of evacuation passage wind speed constraint in the game relationship, calculate the priority of control commands for each fan in the fan group;

[0102] The priority parameters are jointly determined by the environmental state parameters of the fan's location, the fan's contribution to the smoke diffusion path, and the fan's matching degree with the wind speed direction and vehicle movement trend within the evacuation passage. Control command priority: describes the control priority of each fan in the fan group, defined by the fan's contribution to smoke extraction efficiency and evacuation passage wind speed constraints. Smoke extraction efficiency weight and evacuation passage wind speed constraint weight: describes the relative importance of smoke extraction efficiency and evacuation passage wind speed constraints in the game theory relationship, dynamically adjusted by the changes in tunnel environmental monitoring data and vehicle movement trend characteristics.

[0103] In this embodiment of the invention, firstly, determining the weights of smoke extraction efficiency and evacuation channel wind speed constraints is the foundation for priority calculation. The smoke extraction efficiency weight describes the importance of the fan group in optimizing smoke extraction efficiency and is generated by the dynamic correlation between the smoke diffusion rate and the negative pressure gradient. The evacuation channel wind speed constraint weight describes the importance of the fan group in controlling the wind speed in the evacuation channel and is limited by the angle threshold between the evacuation path direction and the local wind speed direction. By monitoring tunnel environmental data and vehicle movement trend characteristics, the smoke extraction efficiency weight and the evacuation channel wind speed constraint weight are dynamically adjusted to ensure that their relative importance in the game relationship accurately reflects the needs within the tunnel. Secondly, calculating the control command priority of each fan in the fan group requires comprehensively considering the fan's contribution to both smoke extraction efficiency and evacuation channel wind speed constraints. For smoke extraction efficiency, the fan's contribution is defined by the matching degree between the negative pressure gradient and the smoke diffusion rate of its covered area. The larger the negative pressure gradient, the higher the fan's contribution to smoke extraction efficiency; the faster the smoke diffusion rate, the more urgent the fan's need for smoke extraction efficiency optimization. For evacuation route wind speed constraints, the contribution of the fans is defined by the consistency coefficient between the direction of the local wind speed they generate and the direction of the vehicle evacuation path. The more consistent the local wind speed direction is with the evacuation path direction, the higher the contribution of the fans to the evacuation route wind speed constraints; the smaller the included angle threshold, the more urgent the need for fans to control the evacuation route wind speed. In the priority calculation process, the control command priority for each fan is generated by weighting and summing the smoke extraction efficiency weight and the evacuation route wind speed constraint weight with the fan's contribution, respectively. Finally, the calculated control command priority is used as the basis data for differentiated control of the fan group, dynamically adjusting the speed and deflection angle of each fan. By updating the control command priority, it is ensured that the fan group can flexibly adjust its operating strategy according to changes in the tunnel environment and vehicle movement trends, achieving a scientific balance between smoke extraction efficiency and evacuation route wind speed constraints.

[0104] In summary, dynamic optimization of the coordinated control of tunnel ventilation fan groups has been achieved, ensuring an effective balance between the dual objectives of smoke extraction efficiency within the tunnel and wind speed constraints in evacuation routes. Through multi-source data fusion and the construction of a dynamic game theory model, the ventilation fan groups can respond to changes in the tunnel environment and vehicles, improving vehicle evacuation safety and fire control efficiency in tunnel fire emergency scenarios.

[0105] To establish a game theory relationship between smoke extraction efficiency and evacuation route wind speed constraints, a dynamic game theory model is used to construct this relationship, enabling scientific optimization of the coordinated control of the wind turbine group. First, the smoke diffusion rate is dynamically correlated with the negative pressure gradient of the area covered by the wind turbine group, serving as the quantification basis for smoke extraction efficiency. Next, the quantified results of smoke extraction efficiency and the quantification rules of evacuation route wind speed constraints are mapped to the objective function and constraints in the dynamic game theory model, ensuring a balance between the two within the model. Then, in the dynamic game theory model, a game theory relationship is constructed between the objective function and constraints, and the priority of smoke extraction efficiency and evacuation route wind speed constraints is dynamically adjusted through game strategy weights. Finally, based on the constructed game theory relationship, a set of game strategies for smoke extraction efficiency and evacuation route wind speed constraints is generated, providing a scientific basis for calculating the priority of wind turbine group control commands.

[0106] To achieve a scientific balance between vehicle evacuation safety and fire control efficiency within tunnels, some embodiments construct a game-theoretic relationship between smoke extraction efficiency and evacuation channel wind speed constraints within a dynamic game theory model, including:

[0107] 301. Dynamically correlate the smoke diffusion rate with the negative pressure gradient of the area covered by the fan group;

[0108] The negative pressure gradient is calculated based on the position distribution and rotation speed parameters of each fan in the fan group. The smoke diffusion rate is derived by combining the smoke concentration distribution gradient in the tunnel with the direction of traffic density change in the vehicle movement trend characteristics. The dynamic correlation results are used as the quantitative basis for smoke exhaust efficiency. Dynamic correlation: Matching the smoke diffusion rate with the negative pressure gradient is used as the quantitative basis for smoke exhaust efficiency.

[0109] In this embodiment of the invention, the smoke concentration distribution gradient within the tunnel is monitored, and the smoke diffusion rate is calculated based on the tunnel topology. Next, the negative pressure gradient of the fan-covered area is calculated according to the rotational speed and position distribution of each fan in the fan group. Then, the smoke diffusion rate and the negative pressure gradient are dynamically correlated to generate a quantitative result of the smoke extraction efficiency. Finally, the quantitative result of the smoke extraction efficiency is used as the input parameter for a dynamic game theory model.

[0110] 302. Based on the angle threshold between the evacuation path direction and the local wind speed direction generated by the wind turbine group, construct quantitative rules for evacuation channel wind speed constraints.

[0111] The included angle threshold is segmented and corrected based on the dynamic deviation between the evacuation path direction in the vehicle motion trend characteristics and the local wind speed direction within the fan group coverage area. The correction coefficient is dynamically adjusted based on the conflict probability between the evacuation path and the smoke diffusion path. Evacuation path direction: describes the evacuation direction of vehicles within the tunnel, defined by the evacuation path direction in the vehicle motion trend characteristics. Local wind speed direction: describes the wind speed direction within the fan group coverage area, jointly defined by the fan deflection angle and the tunnel topology. Included angle threshold: describes the maximum permissible deviation angle between the evacuation path direction and the local wind speed direction, used to limit the wind speed constraints of the evacuation passage. Correction coefficient: dynamically adjusts the included angle threshold based on the conflict probability between the evacuation path and the smoke diffusion path to ensure the adaptability of the wind speed constraints of the evacuation passage.

[0112] In this embodiment of the invention, the evacuation path direction is extracted from the vehicle motion trend characteristics and combined with the local wind speed direction within the coverage area of ​​the wind turbine group to calculate the dynamic deviation between the two. Next, based on the conflict probability between the evacuation path and the smoke diffusion path, a correction coefficient for the included angle threshold is dynamically adjusted. Then, the included angle threshold is segmented and corrected based on the correction coefficient to generate a quantification rule for the wind speed constraint of the evacuation channel. Finally, the quantification rule is used as the input parameter for a dynamic game theory model.

[0113] 303. Map the quantitative results of smoke exhaust efficiency and the quantitative rules of evacuation passage wind speed constraints to the objective function and constraint conditions in the dynamic game theory model, respectively.

[0114] The objective function is generated from the dynamic correlation between the smoke diffusion rate and the negative pressure gradient, and the constraints are generated from the dynamic deviation between the included angle threshold and the evacuation path direction. The quantified result of the smoke exhaust efficiency is generated from the dynamic correlation between the smoke diffusion rate and the negative pressure gradient, describing the control effect of the fan group on smoke diffusion. The quantified rule for the evacuation passage wind speed constraint is limited by the included angle threshold between the evacuation path direction and the local wind speed direction, describing the control effect of the fan group on the wind speed within the evacuation passage.

[0115] In this embodiment of the invention, the quantified result of smoke extraction efficiency is mapped to an objective function in a dynamic game theory model, with the optimization direction of the objective function being to maximize smoke extraction efficiency. Next, the quantified rules of evacuation route wind speed constraints are mapped to constraints in the dynamic game theory model, with the constraints limiting the scope to ensure the matching degree between the wind speed direction and vehicle movement trend within the evacuation route. Then, the objective function and constraints are used as input parameters of the dynamic game theory model, respectively. Finally, through the mapping of the objective function and constraints, the balance between smoke extraction efficiency and evacuation route wind speed constraints in the model is ensured.

[0116] 304. In dynamic game theory models, construct the game relationship between the objective function and the constraints;

[0117] The optimization direction of the objective function and the range of constraints are dynamically balanced through game strategy weights. The game strategy weights are dynamically adjusted by the changes in carbon monoxide concentration and visibility in the tunnel environmental monitoring data, and the objective function is constrained and corrected by applying the quantitative rules of evacuation channel wind speed constraints. Game relationship construction: In the dynamic game theory model, the priority of the objective function and constraints is balanced through game strategy weights.

[0118] In this embodiment of the invention, the definition of the objective function and constraints forms the basis for constructing the game relationship. The objective function describes the optimization direction of smoke extraction efficiency, dynamically generated by the correlation between the smoke diffusion rate and the negative pressure gradient of the area covered by the fan group. The optimization objective of smoke extraction efficiency is to maximize the control effect of the fan group on smoke diffusion, that is, to minimize the diffusion range of smoke in the tunnel by adjusting the fan speed and deflection angle. The constraints describe the limited range of wind speed in the evacuation channel, limited by the angle threshold between the evacuation path direction in the vehicle movement trend characteristics and the local wind speed direction generated by the fan group. The constraint objective of the evacuation channel wind speed is to ensure the consistency between the local wind speed direction and the vehicle evacuation path direction, thereby ensuring vehicle evacuation safety. During the construction of the game relationship, the objective function and constraints are dynamically balanced through game strategy weights. The game strategy weights describe the relative importance of the objective function and constraints in the game relationship, dynamically adjusted by the changes in tunnel environmental monitoring data and vehicle movement trend characteristics.

[0119] 305. Based on the results of constructing game relations, generate a set of game strategies for smoke exhaust efficiency and evacuation channel wind speed constraints;

[0120] The game strategy set is jointly determined by the optimization results of the objective function and the constraint conditions, and serves as the basis for calculating the priority of wind turbine group control commands.

[0121] In this embodiment of the invention, the game relationship construction result is the basis for generating the game strategy set. The game relationship construction result describes the balance relationship between the objective function and the constraints in the dynamic game theory model, where the objective function describes the optimization direction of smoke exhaust efficiency, and the constraints describe the limited range of wind speed in evacuation channels. Through dynamic adjustment of the game strategy weights, the game relationship construction result can flexibly adapt to the needs within the tunnel. During the generation of the game strategy set, based on the game relationship construction result, the optimization result of the objective function and the limitation result of the constraints are extracted. The optimization result of the objective function describes the contribution of the fan group to the smoke exhaust efficiency optimization, generated by the dynamic correlation between the smoke diffusion rate and the negative pressure gradient. The limitation result of the constraints describes the contribution of the fan group to the wind speed control in evacuation channels, limited by the angle threshold between the evacuation path direction and the local wind speed direction. By jointly generating the game strategy set with the optimization result and the limitation result, it is ensured that the game strategy set can accurately reflect the contribution of the fan group to the smoke exhaust efficiency and the wind speed constraints in evacuation channels.

[0122] In a tunnel fire emergency scenario, the smoke diffusion rate within the tunnel increases, and there is a high probability of conflict between vehicle evacuation paths and smoke diffusion paths. First, in step 301, the smoke concentration distribution gradient within the tunnel is monitored, and the smoke diffusion rate is calculated based on the tunnel topology. Next, the negative pressure gradient of the fan coverage area is calculated based on the rotational speed and position distribution of each fan in the fan group. Then, the smoke diffusion rate and negative pressure gradient are dynamically correlated to generate a quantified result of smoke extraction efficiency. Finally, the quantified result of smoke extraction efficiency is used as the input parameter of a dynamic game theory model. Next, in step 302, the quantified result of smoke extraction efficiency is mapped to the objective function in the dynamic game theory model, with the optimization direction of the objective function being to maximize smoke extraction efficiency. Next, the quantified rules of wind speed constraints in the evacuation routes are mapped to constraints in the dynamic game theory model, with the constraint scope limited to ensuring the matching degree between the wind speed direction and vehicle movement trend within the evacuation routes. Finally, the objective function and constraints are used as input parameters of the dynamic game theory model, respectively. Finally, by mapping the objective function to the constraints, the balance between smoke extraction efficiency and evacuation route wind speed constraints in the model is ensured. Then, in step 303, the quantified result of smoke extraction efficiency is mapped to the objective function in the dynamic game theory model, with the optimization direction of the objective function being to maximize smoke extraction efficiency. Next, the quantified rules of evacuation route wind speed constraints are mapped to constraints in the dynamic game theory model, with the constraint scope ensuring the matching degree between the wind speed direction and vehicle movement trend within the evacuation route. Then, the objective function and constraints are used as input parameters of the dynamic game theory model. Finally, by mapping the objective function to the constraints, the balance between smoke extraction efficiency and evacuation route wind speed constraints in the model is ensured. Next, in step 304, a game relationship is constructed between the objective function and constraints in the dynamic game theory model, where the optimization direction of the objective function is to maximize smoke extraction efficiency, and the constraint scope is to ensure the matching degree between the wind speed direction and vehicle movement trend within the evacuation route. Next, based on the changes in tunnel environmental monitoring data and vehicle movement trend characteristics, the weights of the game strategy are dynamically adjusted to ensure a balance between the priorities of the objective function and the constraints. Then, through the construction of game relationships, a set of game strategies for smoke extraction efficiency and evacuation channel wind speed constraints is generated. Finally, the game strategy set is used as the basis for calculating the priority of the fan group control commands. Finally, through step 305, based on the results of the game relationship construction, the optimization results of the objective function and the constraint results are extracted. Then, the optimization results and constraint results are jointly used to generate a set of game strategies for smoke extraction efficiency and evacuation channel wind speed constraints. Then, the game strategy set is used as the input parameter for calculating the priority of the fan group control commands. Finally, through the game strategy set, the rotational speed and deflection angle of each fan in the fan group are dynamically adjusted to ensure that the fan group can efficiently extract smoke and ensure vehicle evacuation safety.

[0123] In summary, a scientific balance between smoke extraction efficiency and evacuation channel wind speed constraints was achieved in the collaborative control of tunnel ventilation fan groups. By dynamically linking smoke diffusion rate and negative pressure gradient, constructing quantitative rules for evacuation channel wind speed constraints, and generating a game theory strategy set, the safety of vehicle evacuation and fire control efficiency within the tunnel were ultimately improved, providing theoretical support and practical basis for the intelligent control of tunnel ventilation fan groups.

[0124] To achieve a dynamic balance between fan group control and vehicle evacuation route optimization in tunnel fire emergency scenarios, some embodiments involve parsing information obtained from the radar-visual fusion vehicle tracking database using edge computing nodes deployed within the tunnel section. This process simulates the combined ventilation and evacuation strategy, extracts vehicle location distribution and movement trend characteristics, and combines this with calculations of carbon monoxide concentration, visibility indicators, and the probability of conflict between fire smoke diffusion and vehicle evacuation routes from tunnel environmental monitoring data to construct a set of game theory parameters, including:

[0125] 401. Extract dynamic trajectory data of multiple types of vehicles in the tunnel from the radar-visual fusion vehicle tracking database, parse it into structured information of vehicle position coordinates, instantaneous speed and direction of motion, and map the structured information into a heat map of vehicle distribution and motion trend vector field in the tunnel section based on the tunnel topology.

[0126] Rayvision Fusion Vehicle Tracking Database: Stores dynamic trajectory data of various vehicle types within the tunnel, including vehicle position coordinates, instantaneous speed, and direction of motion. Distribution Heatmap: Describes the distribution density of vehicles within the tunnel section, generated jointly from vehicle position coordinates and tunnel topology. Motion Trend Vector Field: Describes the direction and speed of vehicle motion within the tunnel section, generated jointly from instantaneous speed and direction of motion.

[0127] In this embodiment of the invention, dynamic trajectory data of various types of vehicles within a tunnel are extracted from a radar-visual fusion vehicle tracking database and parsed into structured information including vehicle position coordinates, instantaneous speed, and direction of motion. Next, based on the tunnel topology, the vehicle position coordinates are mapped into a distribution heatmap to describe the vehicle distribution density within the tunnel section. Then, the instantaneous speed and direction of motion are mapped into a motion trend vector field to describe the vehicle's direction and speed within the tunnel section. Finally, the distribution heatmap and motion trend vector field are used as input data for subsequent simulations of combined ventilation and evacuation strategies.

[0128] 402. Based on the aforementioned distribution heatmap and motion trend vector field, simulate the joint ventilation and evacuation strategy in the edge computing node;

[0129] The simulation process dynamically adjusts the candidate control command set of the fan group to simulate the probability of conflict between smoke diffusion paths and vehicle evacuation paths under different ventilation modes, and extracts the clustering characteristics and continuity characteristics of vehicle location distribution and movement trends from the simulation results. Simulation of the joint ventilation and evacuation strategy: Simulates the interaction between smoke diffusion and vehicle evacuation under different ventilation modes, providing a basis for the fan group control strategy. Edge computing nodes: Computing devices deployed within the tunnel section to perform simulation and optimization tasks.

[0130] In this embodiment of the invention, the generation of the distribution heatmap and the motion trend vector field is fundamental to the simulation execution. The distribution heatmap describes the location distribution of vehicles within the tunnel and is generated through cluster analysis and thermal rendering of vehicle location data. The motion trend vector field describes the direction and speed of vehicle movement within the tunnel and is generated through vector analysis and dynamic updates of vehicle motion data. By using the distribution heatmap and the motion trend vector field as input data, edge computing nodes can reflect the distribution and movement characteristics of vehicles within the tunnel, providing data support for the simulation of combined ventilation and evacuation strategies.

[0131] During the simulation, the ventilation strategy was based on a collaborative control model of the fan group. First, based on the distribution heatmap and motion trend vector field, the priority of the fan group's control commands was dynamically adjusted to ensure that the fans could flexibly adjust their operating parameters according to the distribution and movement characteristics of vehicles within the tunnel. Next, by simulating the changes in the fan group's rotational speed and deflection angle, the negative pressure gradient and local wind speed direction of the fan-covered area were calculated, generating the simulation results of the ventilation strategy. The simulation results of the ventilation strategy describe the control effect of the fan group on smoke diffusion, i.e., minimizing the smoke diffusion range within the tunnel by adjusting the fan operating parameters. The evacuation strategy simulation was based on an optimization model of vehicle evacuation paths.

[0132] First, based on the heat map and motion trend vector field, the planning priority of vehicle evacuation routes is dynamically adjusted to ensure that vehicles can flexibly choose the optimal evacuation route according to the smoke diffusion rate and local wind direction within the tunnel. Next, by simulating changes in vehicle evacuation routes, the evacuation time and path conflict probability are calculated, generating simulation results for the evacuation strategy. The simulation results describe the optimization effect of the vehicle evacuation routes, i.e., by adjusting the planning priority of evacuation routes, vehicle evacuation time and path conflict probability are minimized as much as possible. During the simulation of the combined ventilation and evacuation strategy, edge computing nodes dynamically adjust the priorities of ventilation and evacuation strategies by calculating the dynamic changes in the heat map and motion trend vector field, ensuring a balanced relationship between the two in the simulation. Finally, the simulation results of the combined ventilation and evacuation strategy are used as input data for tunnel fan group control and vehicle evacuation route planning, dynamically adjusting the operating parameters of the fan group and the planning priority of vehicle evacuation routes.

[0133] 403. The carbon monoxide concentration and visibility index in the tunnel environmental monitoring data are mapped to dynamic influencing factors of smoke diffusion rate and air pollutant concentration, respectively. Combined with the calculation results of the conflict probability between the fire smoke diffusion path and the vehicle evacuation path, the threat level parameter of smoke diffusion to evacuation path is generated.

[0134] Carbon monoxide concentration and visibility index: Describes the concentration of air pollutants and visual clarity within the tunnel, obtained from tunnel environmental monitoring data. Smoke diffusion rate: Describes the speed at which smoke diffuses within the tunnel, jointly defined by carbon monoxide concentration and visibility index. Threat level parameter: Describes the degree of threat posed by smoke diffusion to vehicle evacuation routes, generated from the probability calculation of conflict between smoke diffusion paths and evacuation paths.

[0135] In this embodiment of the invention, firstly, the carbon monoxide concentration and visibility index in the tunnel environmental monitoring data are mapped to dynamic influencing factors of smoke diffusion rate and air pollutant concentration, respectively. Carbon monoxide concentration, as the core pollutant in smoke diffusion, directly reflects the severity of smoke diffusion; the higher the concentration, the faster the smoke diffusion rate, and the greater the threat to the tunnel environment. The visibility index describes the visual clarity within the tunnel; its decrease indicates an increase in air pollutant concentration and reduced visibility of vehicle evacuation routes, further exacerbating evacuation difficulties. Next, the threat level of smoke diffusion to vehicle evacuation routes is quantified by calculating the conflict probability between the fire smoke diffusion path and the vehicle evacuation path. The smoke diffusion path is jointly generated by the smoke concentration distribution gradient and the tunnel topology, describing the direction and range of smoke diffusion within the tunnel; the vehicle evacuation path is defined by the evacuation path direction in the vehicle movement trend characteristics, describing the evacuation direction and range of vehicles within the tunnel. By calculating the intersection probability between the two, the threat level of smoke diffusion to vehicle evacuation paths can be dynamically assessed; the higher the intersection probability, the higher the threat level. Finally, the dynamic influencing factors of smoke diffusion rate and air pollutant concentration are weighted and fused with the calculated conflict probability between smoke diffusion path and vehicle evacuation path to generate a threat level parameter of smoke diffusion to evacuation paths. This parameter reflects the degree of threat posed by smoke diffusion to vehicle evacuation paths, providing a scientific basis for evacuation path optimization and wind turbine group control.

[0136] 404. Based on the clustering characteristics of the vehicle location distribution, the continuity characteristics of the movement trend, and the threat level parameters of smoke diffusion, construct a set of game parameters for a dynamic game theory model.

[0137] The game parameter set includes environmental state parameters, vehicle state parameters, and risk parameters. The environmental state parameters are jointly defined by carbon monoxide concentration, visibility index, and smoke diffusion rate. The vehicle state parameters are jointly defined by the clustering degree of the distribution heat map and the continuity of the motion trend vector field. The risk parameters are jointly defined by the conflict probability of the smoke diffusion path and the evacuation path and the threat level parameter.

[0138] In this embodiment of the invention, vehicle state parameters are constructed based on the clustering characteristics of vehicle location distribution and the continuity of movement trends. Next, environmental state parameters are constructed based on the smoke diffusion rate and air pollutant concentration. Then, risk parameters are constructed based on the threat level parameters of smoke diffusion to evacuation routes. Finally, the environmental state parameters, vehicle state parameters, and risk parameters are jointly constructed into a set of game parameters for a dynamic game theory model.

[0139] In a tunnel fire emergency scenario, carbon monoxide concentration rises and visibility drops sharply within the tunnel, creating a high probability of conflict between smoke diffusion paths and vehicle evacuation paths. First, in step 401, dynamic trajectory data of various vehicle types within the tunnel is extracted from the radar-visual fusion vehicle tracking database and parsed into structured information including vehicle position coordinates, instantaneous speed, and direction of motion. Next, based on the tunnel topology, vehicle position coordinates are mapped to a distribution heatmap, describing the density of vehicle positions within the tunnel section. Then, vehicle instantaneous speed and direction of motion are mapped to a motion trend vector field, describing the direction and speed of vehicle movement within the tunnel section. Finally, the distribution heatmap and motion trend vector field are used as input data for simulating a combined ventilation and evacuation strategy. Next, in step 402, based on the distribution heatmap and motion trend vector field, a simulation of the combined ventilation and evacuation strategy is executed in an edge computing node. The ventilation strategy calculates the negative pressure gradient and local wind speed direction in the fan-covered area by simulating changes in the fan group's rotational speed and deflection angle; the evacuation strategy calculates vehicle evacuation time and the probability of path conflict by simulating changes in vehicle evacuation paths. Next, by monitoring the dynamic changes in the distribution heatmap and motion trend vector field, the priorities of ventilation and evacuation strategies are dynamically adjusted to ensure a balance between the two in the simulation. Finally, the simulation results are used as input data for fan group control and vehicle evacuation path planning. Then, in step 403, the carbon monoxide concentration and visibility index in the tunnel environmental monitoring data are mapped to dynamic influence factors of smoke diffusion rate and air pollutant concentration, respectively, to quantify the impact of smoke diffusion on the tunnel environment. Next, the threat level of smoke diffusion to vehicle evacuation paths is quantified by calculating the conflict probability between fire smoke diffusion paths and vehicle evacuation paths. Then, the dynamic influence factors and conflict probabilities are weighted and fused to generate a threat level parameter for smoke diffusion on evacuation paths. Finally, the threat level parameter is used as input data for vehicle evacuation path optimization and fan group control. Finally, in step 404, based on the clustering characteristics of vehicle location distribution and the continuity characteristics of motion trends, a set of game parameters for a dynamic game theory model is constructed, where the clustering characteristics describe the distribution density of vehicles within the tunnel section, and the continuity characteristics describe the stability of vehicle motion trends. Next, the threat level parameter of smoke diffusion is used as the core parameter of the game parameter set to ensure that the dynamic game theory model can accurately reflect the degree of threat posed by smoke diffusion to vehicle evacuation routes. Finally, the game parameter set is used as input data for the dynamic game theory model to generate the priority of wind turbine group control commands and vehicle evacuation route optimization strategies.

[0140] In summary, the scientific optimization of multi-source data fusion and dynamic simulation in the collaborative control of tunnel ventilation fan groups has been achieved. By extracting vehicle trajectory data, simulating joint ventilation and evacuation strategies, generating smoke diffusion threat level parameters, and constructing a game theory parameter set, the safety of vehicle evacuation and the efficiency of fire control within the tunnel have been improved, providing theoretical support and practical basis for the intelligent control of tunnel ventilation fan groups.

[0141] To improve vehicle evacuation safety and fire control efficiency, in some embodiments, a set of game parameters for a dynamic game theory model is constructed based on the clustering characteristics of vehicle location distribution, the continuity characteristics of movement trends, and the threat level parameters of smoke diffusion. These parameters include:

[0142] 501. The carbon monoxide concentration, visibility index and smoke diffusion rate are respectively mapped to the pollutant concentration parameter, visibility impact parameter and smoke diffusion rate parameter in the environmental state parameters;

[0143] The pollutant concentration parameter is defined by the change range of carbon monoxide concentration, the visibility impact parameter is defined by the change gradient of visibility index, and the smoke diffusion rate parameter is defined by the matching degree between the change direction of smoke diffusion rate and the tunnel topology. The smoke diffusion rate parameter is defined by the matching degree between the change direction of smoke diffusion rate and the tunnel topology, and describes the state of smoke diffusion.

[0144] In this embodiment of the invention, carbon monoxide concentration and visibility indicators are extracted from tunnel environmental monitoring data and analyzed into pollutant concentration parameters and visibility impact parameters, respectively. Next, based on the smoke concentration distribution gradient and tunnel topology, the smoke diffusion rate is calculated and mapped to a smoke diffusion rate parameter. Then, the pollutant concentration parameter, visibility impact parameter, and smoke diffusion rate parameter are used as the basic data for an environmental state parameter set. Finally, the environmental state parameter set is updated to ensure it accurately reflects changes in the tunnel environment.

[0145] 502. The clustering degree of the distribution heatmap and the continuity of the motion trend vector field are respectively mapped to the vehicle clustering degree parameter and the motion continuity parameter in the vehicle state parameters;

[0146] The vehicle aggregation parameter is defined by the ratio of the area of ​​high-density vehicle regions in the distribution heatmap to the volume of the tunnel section. The motion continuity parameter is defined by the local consistency characteristics of the vehicle motion direction in the motion trend vector field. The distribution heatmap describes the distribution density of vehicles within the tunnel section and is generated jointly by the vehicle position coordinates and the tunnel topology. The motion trend vector field describes the motion direction and velocity of vehicles within the tunnel section and is generated jointly by the instantaneous velocity and motion direction.

[0147] In this embodiment of the invention, based on the distribution heatmap, the area of ​​high-density vehicle regions and the volume ratio of the tunnel section are calculated to generate vehicle aggregation parameters. Next, based on the motion trend vector field, local consistency features of vehicle motion directions are extracted to generate motion continuity parameters. Then, the vehicle aggregation parameters and motion continuity parameters are used as the basic data for the vehicle state parameter set. Finally, by updating the vehicle state parameter set, it is ensured that it accurately reflects the distribution and motion characteristics of vehicles within the tunnel.

[0148] 503. Map the conflict probability and threat level parameters of the smoke diffusion path and evacuation path to the path conflict parameter and threat level parameter in the risk parameters, respectively.

[0149] The path conflict parameter is defined by the ratio of the area of ​​the intersection of the smoke diffusion path and the evacuation path to the total area of ​​the tunnel section. The threat level parameter is defined by the product of the threat level parameter and the smoke diffusion rate. The smoke diffusion path describes the diffusion path of smoke within the tunnel and is jointly defined by the smoke concentration distribution gradient and the tunnel topology. The evacuation path describes the evacuation path of vehicles within the tunnel and is defined by the evacuation path direction in the vehicle movement trend characteristics.

[0150] In this embodiment of the invention, path conflict parameters are generated based on the ratio of the area of ​​the intersection region between the smoke diffusion path and the evacuation path to the total area of ​​the tunnel section. Next, threat level parameters are generated based on the product of threat level parameters and smoke diffusion rate. Then, the path conflict parameters and threat level parameters are used as the basis data for a risk parameter set. Finally, the risk parameter set is updated to ensure that it accurately reflects the threat of smoke diffusion to vehicle evacuation.

[0151] 504. Based on the pollutant concentration parameters, visibility impact parameters, and smoke diffusion rate parameters, construct an environmental state parameter set;

[0152] The environmental state parameter set is defined by a weighted sum of pollutant concentration parameters, visibility impact parameters, and smoke diffusion rate parameters, with the weights dynamically adjusted based on the changes in tunnel environmental monitoring data.

[0153] In this embodiment of the invention, pollutant concentration parameters, visibility impact parameters, and smoke diffusion rate parameters are jointly analyzed to update the environmental status and ensure that it accurately reflects changes in the tunnel environment. Finally, an environmental status parameter set is generated.

[0154] 505. Based on the vehicle aggregation degree parameter and motion continuity parameter, construct a vehicle state parameter set;

[0155] The vehicle state parameter set is defined by a weighted sum of vehicle clustering parameters and motion continuity parameters, with the weights dynamically adjusted by the magnitude of change in the vehicle motion trend characteristics.

[0156] In this embodiment of the invention, vehicle aggregation parameters and motion continuity parameters are jointly analyzed to generate a vehicle state parameter set. Then, the vehicle state parameter set is updated to ensure it accurately reflects the distribution and motion characteristics of vehicles within the tunnel. Finally, the vehicle state parameter set is used as input data for a dynamic game theory model.

[0157] 506. Based on the path conflict parameters and threat level parameters, construct a risk parameter set;

[0158] The risk parameter set is defined by a weighted sum of path conflict parameters and threat level parameters, with the weights dynamically adjusted by the change in the probability of conflict between the smoke diffusion path and the evacuation path.

[0159] In this embodiment of the invention, path conflict parameters and threat level parameters are jointly analyzed. By updating the threat of smoke diffusion to vehicle evacuation, a risk parameter set is generated, and the risk parameter set is used as input data for a dynamic game theory model.

[0160] 507. The environmental state parameter set, vehicle state parameter set, and risk parameter set are jointly constructed into a game parameter set for a dynamic game theory model;

[0161] The game parameter set is dynamically updated based on the changes in the environmental state parameter set, the vehicle state parameter set, and the risk parameter set.

[0162] In this embodiment of the invention, environmental state parameter sets, vehicle state parameter sets, and risk parameter sets are jointly analyzed to generate a game parameter set. Then, the game parameter set is updated to ensure it accurately reflects the state of the environment, vehicles, and risks within the tunnel. Finally, the game parameter set is used as input data for a dynamic game theory model, providing a scientific basis for optimizing subsequent wind turbine group control strategies.

[0163] In a tunnel fire emergency scenario, the carbon monoxide concentration inside the tunnel rises, visibility drops sharply, and there is a high probability of conflict between the smoke diffusion path and the vehicle evacuation path. First, in step 501, the carbon monoxide concentration is mapped to a pollutant concentration parameter, reflecting the changes in air pollutant concentration within the tunnel. Next, the visibility index is mapped to a visibility impact parameter, reflecting changes in visual clarity within the tunnel. Then, the smoke diffusion rate is mapped to a smoke diffusion rate parameter, reflecting the speed at which smoke diffuses within the tunnel. Finally, the pollutant concentration parameter, visibility impact parameter, and smoke diffusion rate parameter are used as the basic data for the environmental state parameter set. Next, in step 502, the clustering degree of the distribution heatmap is mapped to a vehicle clustering degree parameter, reflecting the distribution density of vehicles within the tunnel section. Then, the continuity of the motion trend vector field is mapped to a motion continuity parameter, reflecting the stability of vehicle motion trends. Finally, the vehicle clustering degree parameter and motion continuity parameter are used as the basic data for the vehicle state parameter set. Then, in step 503, the conflict probability between the smoke diffusion path and the evacuation path is mapped to a path conflict parameter, reflecting the degree of threat posed by smoke diffusion to vehicle evacuation paths. Next, the threat level parameter is mapped to a threat level parameter, reflecting the threat level of smoke diffusion to vehicle evacuation paths. Then, the path conflict parameter and threat level parameter are used as the basic data for the risk parameter set. Next, in step 504, the pollutant concentration parameter, visibility impact parameter, and smoke diffusion rate parameter are integrated into an environmental state parameter set, reflecting the state of the environment inside the tunnel. Then, the environmental state parameter set is used as input data for a dynamic game theory model for subsequent game relationship construction. Then, in step 505, the vehicle aggregation parameter and motion continuity parameter are integrated into a vehicle state parameter set, reflecting the state of vehicles inside the tunnel. Then, the vehicle state parameter set is used as input data for a dynamic game theory model for subsequent game relationship construction. Finally, in step 506, the path conflict parameter and threat level parameter are integrated into a risk parameter set, reflecting the degree of threat posed by smoke diffusion to vehicle evacuation paths. Next, the risk parameter set is used as input data for the dynamic game theory model, and is used for subsequent game relationship construction. Finally, through step 507, the environmental state parameter set, vehicle state parameter set, and risk parameter set are jointly constructed into the game parameter set of the dynamic game theory model, serving as the basic data for constructing game relationships. Then, the game parameter set is used as input data for the dynamic game theory model to generate wind turbine group control command priority and vehicle evacuation route optimization strategies.

[0164] In summary, a scientific optimization of multi-source data mapping and parameter set construction in the collaborative control of tunnel ventilation fan groups has been achieved. By defining environmental state parameter sets, vehicle state parameter sets, and risk parameter sets, and jointly constructing them into a game theory parameter set, the safety of vehicle evacuation and fire control efficiency within the tunnel are ultimately improved, providing theoretical support and practical basis for the intelligent control of tunnel ventilation fan groups.

[0165] To ensure vehicle evacuation safety and fire control efficiency, in some embodiments, the game strategy weights in the dynamic game theory model are iteratively updated based on tunnel environment feedback data, and the control commands for the wind turbine group are optimized in the rolling time domain using edge computing nodes until the vehicle movement trend and environmental indicators reach a preset cooperative stability range, including:

[0166] 601. The carbon monoxide concentration, visibility index, local wind speed direction, and vehicle movement trend characteristics in the tunnel environment feedback data are decomposed into environmental state deviation parameters and vehicle state deviation parameters.

[0167] The environmental state deviation parameter is defined by the gradient of changes in carbon monoxide concentration and visibility index, and the vehicle state deviation parameter is defined by the angle deviation between the evacuation path direction and the local wind speed direction in the vehicle motion trend characteristics; the tunnel environmental feedback data includes carbon monoxide concentration, visibility index, local wind speed direction and vehicle motion trend characteristics, describing the state of the environment and vehicles inside the tunnel.

[0168] In this embodiment of the invention, carbon monoxide concentration and visibility indices are extracted from tunnel environmental feedback data and analyzed as pollutant concentration deviation and visibility impact deviation in environmental state deviation parameters, respectively. Next, local wind speed direction and vehicle movement trend characteristics are extracted, and the angle deviation between the evacuation path direction and the local wind speed direction is calculated to generate vehicle state deviation parameters. Then, the environmental state deviation parameters and vehicle state deviation parameters are used as input data for a dynamic game theory model. Finally, by updating the environmental state deviation parameters and vehicle state deviation parameters, it is ensured that they accurately reflect the deviation states of the tunnel environment and vehicles.

[0169] 602. Based on the environmental state deviation parameters and vehicle state deviation parameters, the game strategy weights in the dynamic game theory model are iteratively updated;

[0170] The game strategy weights are calculated by combining the impact weight of environmental state deviation parameters on smoke exhaust efficiency and the conflict weight of vehicle state deviation parameters on evacuation channel wind speed constraints, and are dynamically corrected using the attenuation coefficient of historical game strategy weights; iterative update: the game strategy weights are dynamically adjusted according to the changes in environmental state deviation parameters and vehicle state deviation parameters to ensure the model's adaptability.

[0171] In this embodiment of the invention, the magnitude of change of the objective function is calculated based on the pollutant concentration deviation and visibility impact deviation in the environmental state deviation parameters. Next, the magnitude of change of the constraint conditions is calculated based on the angle deviation between the evacuation path direction and the local wind speed direction in the vehicle state deviation parameters. Then, the game strategy weights are dynamically adjusted according to the magnitudes of change of the objective function and the constraint conditions. Finally, the game strategy weights are iteratively updated to ensure that the dynamic game theory model can respond to the deviation states of the environment and vehicles within the tunnel.

[0172] 603. Based on the updated game strategy weights, generate a candidate instruction set for wind turbine group control commands in edge computing nodes;

[0173] The candidate instruction set is dynamically generated by combining the priority parameters of fan speed, deflection angle and coverage area. The priority parameters are defined by the contribution of the fan to the smoke exhaust efficiency and the wind speed constraint of the evacuation passage. Edge computing nodes are computing devices deployed in the tunnel section to generate candidate instruction sets and execute optimization tasks.

[0174] In this embodiment of the invention, based on the updated game strategy weights, the priority parameters in the candidate instruction set are dynamically adjusted by monitoring the consistency coefficient between the negative pressure gradient change rate and the local wind speed direction in the wind turbine coverage area. A candidate instruction set for wind turbine group control instructions is generated in the edge computing node. By updating the candidate instruction set, it is ensured that it can accurately reflect the control requirements of the wind turbine group.

[0175] 604. Perform rolling time-domain optimization on the candidate instruction set until the vehicle motion trend and environmental indicators reach a preset cooperative stability range;

[0176] The time window length for rolling time-domain optimization is defined by the dynamic adjustment amplitude of the evacuation path in the vehicle motion trend characteristics. The optimization objective is to minimize the weighted cumulative value of the environmental state deviation parameter and the vehicle state deviation parameter within the time window. Time window length: defined by the dynamic adjustment amplitude of the evacuation path in the vehicle motion trend characteristics, describing the time range of rolling time-domain optimization.

[0177] In this embodiment of the invention, the length of the rolling time-domain optimization time window is determined based on the dynamic adjustment amplitude of the evacuation path in the vehicle motion trend characteristics. Then, rolling time-domain optimization is performed on the candidate instruction set within the time window. The optimization objective is to minimize the weighted cumulative value of the environmental state deviation parameter and the vehicle state deviation parameter until the vehicle motion trend and environmental indicators reach a preset cooperative stability interval.

[0178] In a tunnel fire emergency scenario, carbon monoxide concentration rises and visibility drops sharply within the tunnel, creating a high probability of conflict between vehicle evacuation routes and smoke diffusion paths. First, in step 601, carbon monoxide concentration, visibility indicators, and local wind speed direction are extracted from tunnel environmental feedback data, and their deviations from preset target values ​​are calculated to generate environmental state deviation parameters. Next, vehicle movement direction and speed are extracted from vehicle movement trend characteristics, and their deviations from preset target values ​​are calculated to generate vehicle state deviation parameters. Finally, the environmental state deviation parameters and vehicle state deviation parameters are used as input data for iterative updates of a dynamic game theory model. Next, in step 602, based on the environmental state deviation parameters and vehicle state deviation parameters, the game strategy weights are dynamically adjusted to ensure the model can flexibly balance the priority of smoke extraction efficiency and evacuation channel wind speed constraints according to changes in the tunnel environment. Then, the game strategy weights are iteratively updated to ensure the model can adapt to changes in the tunnel environment and vehicle movement trends. Finally, the updated game strategy weights are used as input data for generating fan group control commands. Then, in step 603, based on the updated game strategy weights, a candidate instruction set for wind turbine group control commands is generated in the edge computing nodes. This candidate instruction set includes alternative schemes for wind turbine speed and deflection angle. Next, the optimal control command is selected by calculating the control effect of the candidate instruction set. Finally, the candidate instruction set is used as input data for rolling time-domain optimization. Finally, in step 604, rolling time-domain optimization is performed on the candidate instruction set, continuously adjusting the wind turbine speed and deflection angle to optimize the wind turbine group control commands. Next, the optimization effect is evaluated by monitoring vehicle motion trends and environmental indicators. Finally, the optimization continues until the vehicle motion trends and environmental indicators reach a preset cooperative stability range, ensuring a dynamic balance between wind turbine group control and vehicle evacuation path optimization.

[0179] In summary, the scientific optimization of environmental feedback data decomposition and rolling time-domain optimization in the collaborative control of tunnel ventilation fan groups has been achieved. By decomposing environmental state deviation parameters and vehicle state deviation parameters, iteratively updating the game strategy weights, generating candidate instruction sets, and performing rolling time-domain optimization, the safety of vehicle evacuation and fire control efficiency within the tunnel are ultimately improved, providing theoretical support and practical basis for the intelligent control of tunnel ventilation fan groups.

[0180] To improve vehicle evacuation safety and fire control efficiency, in some embodiments, differentiated speed and deflection angle control is performed on the fan group based on the priority of the control commands, generating tunnel environment feedback data after the fan group's execution, including:

[0181] 701. Map the priority of the control commands to the speed parameters and deflection angle parameters of each wind turbine in the wind turbine group;

[0182] The rotational speed parameter is defined by the contribution of the fan to the smoke exhaust efficiency and the negative pressure gradient of the covered area; the deflection angle parameter is defined by the matching degree of the fan to the wind speed direction in the evacuation channel and the consistency coefficient of the local wind speed direction; the control command priority describes the control priority of each fan in the fan group, which is defined by the contribution of the fan to the smoke exhaust efficiency and the wind speed constraint of the evacuation channel.

[0183] In this embodiment of the invention, the contribution of each wind turbine in the wind turbine group is calculated based on the priority of control commands. Next, rotational speed parameters are generated according to the negative pressure gradient of the wind turbine coverage area. Then, deflection angle parameters are generated based on the consistency coefficient of local wind speed direction. Finally, the rotational speed parameters and deflection angle parameters are used as the basic data for the differentiated control command set of the wind turbine group.

[0184] 702. Based on the aforementioned speed parameters and deflection angle parameters, generate a differentiated control instruction set for each wind turbine in the wind turbine group;

[0185] The differentiated control instruction set is generated by dynamically combining the adjustment range of the fan speed and the adjustment angle of the deflection angle, and is rolled over using the historical control instruction set of the fan group.

[0186] In this embodiment of the invention, based on rotational speed and deflection angle parameters, the priority parameters in the control command set are dynamically adjusted by monitoring the rate of change of negative pressure gradient and the consistency coefficient of local wind speed direction in the wind turbine coverage area. Then, a differentiated control command set is generated for each wind turbine in the wind turbine group. Finally, by updating the differentiated control command set, it is ensured that it accurately reflects the control requirements of the wind turbine group.

[0187] 703. Execute the differentiated control instruction set to control each wind turbine in the wind turbine group;

[0188] The control process is achieved by dynamically superimposing the adjustment range of the fan speed and the adjustment angle of the deflection angle, and by monitoring the negative pressure gradient change rate and the consistency coefficient of the local wind speed direction in the fan coverage area.

[0189] In this embodiment of the invention, a differentiated control instruction set is executed. This involves dynamically superimposing the adjustment range of the fan speed and the adjustment angle of the deflection angle, and then monitoring the rate of change of the negative pressure gradient and the consistency coefficient of the local wind speed direction in the fan-covered area to dynamically adjust the operating status of the fan group. Each fan in the fan group is controlled. The control results are then used as input data for tunnel environmental feedback. Finally, by updating the operating status of the fan group, efficient smoke extraction and safe vehicle evacuation are ensured.

[0190] 704. Based on the operating status of the wind turbine group after executing the differentiated control instruction set, generate tunnel environment feedback data;

[0191] The tunnel environment feedback data includes carbon monoxide concentration, visibility index, local wind speed direction, and vehicle movement trend characteristics. The carbon monoxide concentration is defined by the correlation between the negative pressure gradient change rate of the fan coverage area and the smoke diffusion rate. The visibility index is defined by the correlation between the consistency coefficient of the local wind speed direction and the smoke diffusion rate. The local wind speed direction is defined by the matching degree between the fan deflection angle adjustment angle and the tunnel topology. The vehicle movement trend characteristics are defined by the angular deviation between the evacuation path direction and the local wind speed direction.

[0192] In this embodiment of the invention, based on the operating status of the wind turbine group after executing a differentiated control command set, the control strategy of the wind turbine group is dynamically adjusted by monitoring tunnel environment feedback data. Then, tunnel environment feedback data is generated and used as input data for a dynamic game theory model.

[0193] In a tunnel fire emergency scenario, carbon monoxide concentration rises sharply within the tunnel, visibility drops drastically, and there is a high probability of conflict between vehicle evacuation routes and smoke diffusion paths. First, in step 701, the contribution of each fan in the fan group is calculated based on control command priority. Next, rotational speed parameters are generated based on the negative pressure gradient of the fan coverage area. Then, deflection angle parameters are generated based on the consistency coefficient of local wind speed direction. Finally, the rotational speed and deflection angle parameters are used as the basis data for the differentiated control command set of the fan group. Next, in step 702, a differentiated control command set is generated for each fan in the fan group based on the rotational speed and deflection angle parameters. This control command set is dynamically generated by a combination of the fan rotational speed adjustment range and the deflection angle adjustment angle. Then, by monitoring the rate of change of the negative pressure gradient in the fan coverage area and the consistency coefficient of local wind speed direction, the priority parameters in the control command set are dynamically adjusted. Then, the differentiated control command set is used as input data for the fan group control. Finally, the differentiated control command set is updated to ensure it accurately reflects the control requirements of the fan group. Then, in step 703, a differentiated control instruction set is executed to control each fan in the fan group. This control process is achieved through the dynamic superposition of the fan speed adjustment range and the deflection angle adjustment angle. Next, the operating status of the fan group is dynamically adjusted by monitoring the negative pressure gradient change rate and the consistency coefficient of the local wind speed direction in the fan coverage area. The control results are then used as input data for tunnel environment feedback data. Finally, the operating status of the fan group is updated to ensure efficient smoke extraction and safe vehicle evacuation. Finally, in step 704, tunnel environment feedback data is generated based on the operating status of the fan group after executing the differentiated control instruction set. This feedback data includes carbon monoxide concentration, visibility index, local wind speed direction, and vehicle movement trend characteristics. The control strategy of the fan group is then dynamically adjusted by monitoring the tunnel environment feedback data. The tunnel environment feedback data is then used as input data for a dynamic game theory model. Finally, the tunnel environment feedback data is updated to ensure it accurately reflects the environment and vehicle status within the tunnel.

[0194] In summary, the scientific optimization of the mapping and control of fan operating parameters in the collaborative control of tunnel fan groups has been achieved. By generating and executing differentiated control command sets, the safety of vehicle evacuation and the efficiency of fire control within the tunnel have been improved, providing theoretical support and practical basis for the intelligent control of tunnel fan groups.

[0195] Figure 2 This invention provides a schematic diagram of a dynamic optimization system for collaborative control of tunnel ventilation fan groups, as shown in the embodiment of the invention. Figure 2 As shown, the system includes:

[0196] The acquisition module 21 acquires the dynamic position, speed and traffic density information of various types of vehicles in the tunnel based on the radar-visual fusion vehicle tracking database;

[0197] The calculation module 22 analyzes the information obtained from the radar-visual fusion vehicle tracking database through edge computing nodes deployed in the tunnel section, performs simulation of the ventilation and evacuation joint strategy, extracts the vehicle position distribution and movement trend characteristics, and constructs a set of game parameters by combining the carbon monoxide concentration, visibility index and fire smoke diffusion and vehicle evacuation path conflict probability calculation results in the tunnel environmental monitoring data.

[0198] The calculation module 22 is also used to dynamically adjust the intensity of the coordinated response between the fans according to the weight of the game parameter set. In the dynamic game theory model, the control command priority of each fan in the fan group is calculated by balancing the smoke exhaust efficiency and the evacuation channel wind speed constraint.

[0199] The generation module 23 performs differentiated speed and deflection angle control on the wind turbine group based on the priority of the control command, and generates tunnel environment feedback data after the wind turbine group has been executed.

[0200] The optimization module 24 iteratively updates the game strategy weights in the dynamic game theory model based on tunnel environment feedback data, and performs rolling time-domain optimization of the wind turbine group control commands through edge computing nodes until the vehicle movement trend and environmental indicators reach a preset coordinated stability range.

[0201] Figure 2 The aforementioned dynamic optimization system for collaborative control of tunnel ventilation fan groups can execute... Figure 1 The implementation principle and technical effects of the tunnel ventilation fan group collaborative control dynamic optimization method described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit performs operations in the tunnel ventilation fan group collaborative control dynamic optimization system described in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0202] In one possible design, Figure 2 The tunnel ventilation fan group collaborative control dynamic optimization system of the embodiment shown can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0203] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0204] The processing component 32 is used for the above Figure 1 The embodiment describes a dynamic optimization method for collaborative control of tunnel ventilation fan groups.

[0205] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0206] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0207] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0208] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0209] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0210] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0211] This invention also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The XX method of the illustrated embodiment.

[0212] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0213] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0214] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic optimization method for collaborative control of tunnel ventilation fan groups, characterized in that, include: Based on the radar-visual fusion vehicle tracking database, dynamic location, speed and traffic density information of various types of vehicles in the tunnel are obtained; By analyzing the information obtained from the radar-visual fusion vehicle tracking database through edge computing nodes deployed in the tunnel section, the simulation of the joint ventilation and evacuation strategy is performed and the characteristics of vehicle location distribution and movement trend are extracted. Combined with the carbon monoxide concentration, visibility index and the probability calculation results of the conflict between fire smoke diffusion and vehicle evacuation path in the tunnel environmental monitoring data, a set of game parameters is constructed. The coordinated response intensity among the fans is dynamically adjusted according to the set of game parameters. In the dynamic game theory model, the control command priority of each fan in the fan group is calculated by balancing the smoke exhaust efficiency and the evacuation channel wind speed constraint. Based on the priority of the control commands, differentiated speed and deflection angle control is performed on the wind turbine group to generate tunnel environment feedback data after the wind turbine group has executed the control commands. Based on the feedback data from the tunnel environment, the game strategy weights in the dynamic game theory model are iteratively updated, and the control commands for the wind turbine group are optimized in the rolling time domain by combining edge computing nodes until the vehicle movement trend and environmental indicators reach the preset coordinated stability range.

2. The method according to claim 1, characterized in that, The coordinated response intensity among the wind turbines is dynamically adjusted based on the set of game parameters. In the dynamic game theory model, the control command priority of each wind turbine in the wind turbine group is calculated by balancing smoke extraction efficiency and evacuation channel wind speed constraints, including: The vehicle location distribution, movement trend characteristics, carbon monoxide concentration, visibility index, and probability of conflict between smoke diffusion and evacuation routes in the game parameter set are mapped to environmental state parameters, vehicle state parameters, and risk parameters related to wind turbine control in the dynamic game theory model according to preset priority rules. Based on the changes in environmental and vehicle state parameters, the intensity of the coordinated response between wind turbines is dynamically adjusted. In the dynamic game theory model, a game relationship is constructed between smoke exhaust efficiency and evacuation channel wind speed constraints; Based on the weight of smoke exhaust efficiency and the weight of wind speed constraint in the evacuation channel in the game relationship, the priority of control commands for each fan in the fan group is calculated. The priority parameter is jointly determined by the environmental state parameters of the fan's location, the fan's coverage contribution to the smoke diffusion path, and the matching degree between the fan and the wind speed direction and vehicle movement trend in the evacuation channel.

3. The method according to claim 2, characterized in that, In the dynamic game theory model, the game relationship between smoke extraction efficiency and evacuation route wind speed constraints is constructed, including: The smoke diffusion rate is dynamically correlated with the negative pressure gradient of the area covered by the fan group, and the dynamic correlation results are used as the quantitative basis for smoke exhaust efficiency. Based on the angle threshold between the evacuation path direction and the local wind speed direction generated by the wind turbine group, a quantitative rule for evacuation channel wind speed constraint is constructed. The quantitative results of smoke exhaust efficiency and the quantitative rules of evacuation channel wind speed constraints are respectively mapped to the objective function and constraint conditions in the dynamic game theory model. In the dynamic game theory model, the objective function and the constraints are constructed through a game relationship, and the objective function is modified by applying the quantitative rules of the evacuation channel wind speed constraint. Based on the results of the game relationship construction, a set of game strategies is generated to constrain smoke exhaust efficiency and evacuation channel wind speed.

4. The method according to claim 1, characterized in that, By parsing information obtained from the radar-visual fusion vehicle tracking database through edge computing nodes deployed within the tunnel section, simulations of joint ventilation and evacuation strategies are performed, and vehicle location distribution and movement trend characteristics are extracted. Combined with calculations of carbon monoxide concentration, visibility indicators, and the probability of conflict between fire smoke diffusion and vehicle evacuation paths from tunnel environmental monitoring data, a set of game parameters is constructed, including: Dynamic trajectory data of various types of vehicles in the tunnel are extracted from the radar-visual fusion vehicle tracking database, parsed into structured information of vehicle position coordinates, instantaneous speed and direction of motion, and mapped into a heat map of vehicle distribution and motion trend vector field in the tunnel section based on the tunnel topology. Based on the aforementioned distribution heatmap and motion trend vector field, a simulation of a combined ventilation and evacuation strategy is performed in the edge computing node, and the clustering characteristics of vehicle location distribution and the continuity characteristics of motion trends are extracted from the simulation results. The carbon monoxide concentration and visibility index in the tunnel environmental monitoring data are mapped to dynamic influencing factors of smoke diffusion rate and air pollutant concentration, respectively. Combined with the conflict probability calculation results of fire smoke diffusion path and vehicle evacuation path, the threat level parameter of smoke diffusion to evacuation path is generated. Based on the clustering characteristics of vehicle location distribution, the continuity characteristics of movement trends, and the threat level parameters of smoke diffusion, a set of game parameters for a dynamic game theory model is constructed.

5. The method according to claim 4, characterized in that, Based on the clustering characteristics of vehicle location distribution, the continuity characteristics of movement trends, and the threat level parameters of smoke diffusion, a set of game parameters for a dynamic game theory model is constructed, including: The carbon monoxide concentration, visibility index, and smoke diffusion rate are respectively mapped to the pollutant concentration parameter, visibility impact parameter, and smoke diffusion rate parameter in the environmental state parameters. The clustering degree of the distribution heatmap and the continuity of the motion trend vector field are respectively mapped to the vehicle clustering degree parameter and the motion continuity parameter in the vehicle state parameters. The probability of conflict and the threat level parameters between the smoke diffusion path and the evacuation path are mapped to the path conflict parameter and the threat level parameter in the risk parameters, respectively. Based on the pollutant concentration parameters, visibility impact parameters, and smoke diffusion rate parameters, an environmental state parameter set is constructed. Based on the vehicle aggregation degree parameter and motion continuity parameter, a vehicle state parameter set is constructed; Based on the path conflict parameters and threat level parameters, a risk parameter set is constructed; The environmental state parameter set, vehicle state parameter set, and risk parameter set are jointly constructed into a game parameter set for a dynamic game theory model.

6. The method according to claim 1, characterized in that, Based on tunnel environment feedback data, the game strategy weights in the dynamic game theory model are iteratively updated, and the control commands for the wind turbine group are optimized in the rolling time domain using edge computing nodes until the vehicle movement trend and environmental indicators reach a preset cooperative stability range, including: The carbon monoxide concentration, visibility index, local wind speed direction, and vehicle movement trend characteristics in the tunnel environment feedback data are decomposed into environmental state deviation parameters and vehicle state deviation parameters. Based on the environmental state deviation parameters and vehicle state deviation parameters, the game strategy weights in the dynamic game theory model are iteratively updated. Based on the updated game strategy weights, a candidate instruction set for wind turbine group control commands is generated in the edge computing nodes; Rolling time-domain optimization is performed on the candidate instruction set, wherein the time window length of the rolling time-domain optimization is defined by the dynamic adjustment amplitude of the evacuation path in the vehicle motion trend characteristics, and the optimization objective is to minimize the weighted cumulative value of the environmental state deviation parameter and the vehicle state deviation parameter within the time window until the vehicle motion trend and environmental indicators reach a preset cooperative stability range.

7. The method according to claim 1, characterized in that, Based on the priority of the control commands, differentiated speed and deflection angle control is performed on the wind turbine group, generating tunnel environment feedback data after the wind turbine group's execution, including: The control command priority is mapped to the speed and deflection angle parameters of each wind turbine in the wind turbine group; Based on the aforementioned speed and deflection angle parameters, a differentiated set of control instructions is generated for each wind turbine in the wind turbine group; The differentiated control instruction set is executed to control each wind turbine in the wind turbine group and to monitor the consistency coefficient between the negative pressure gradient change rate and the local wind speed direction in the wind turbine coverage area. Based on the operating status of the wind turbine group after executing differentiated control command sets, tunnel environment feedback data is generated.

8. A dynamic optimization system for collaborative control of tunnel ventilation fan groups, characterized in that... Includes the following steps: The acquisition module obtains dynamic location, speed, and traffic density information of various types of vehicles in the tunnel based on the radar-visual fusion vehicle tracking database; The computing module parses the information obtained from the radar-visual fusion vehicle tracking database through edge computing nodes deployed in the tunnel section, performs simulation of the ventilation and evacuation joint strategy, extracts the vehicle position distribution and movement trend characteristics, and constructs a set of game parameters by combining the carbon monoxide concentration, visibility index and fire smoke diffusion and vehicle evacuation path conflict probability calculation results in the tunnel environmental monitoring data. The calculation module is also used to dynamically adjust the intensity of the coordinated response between the fans according to the weight of the game parameter set. In the dynamic game theory model, the priority of the control command for each fan in the fan group is calculated by balancing the smoke exhaust efficiency and the wind speed constraint of the evacuation channel. The generation module performs differentiated speed and deflection angle control on the wind turbine group based on the priority of the control command, and generates tunnel environment feedback data after the wind turbine group has been executed. The optimization module iteratively updates the game strategy weights in the dynamic game theory model based on tunnel environment feedback data, and performs rolling time-domain optimization of the wind turbine group control commands through edge computing nodes until the vehicle movement trend and environmental indicators reach a preset coordinated stability range.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the dynamic optimization method for collaborative control of tunnel ventilation fan groups as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a dynamic optimization method for collaborative control of tunnel ventilation fan groups as described in any one of claims 1 to 7.

Images