Vehicle control system

Abstract

The invention discloses a vehicle control system which comprises the following modules: a vehicle active safety system multi-source data acquisition module, a vehicle active safety system vertical architecture data distribution and construction module, a vehicle active safety system standard data set generation module and a vehicle active safety system vertical architecture data distribution and construction module, the construction module is used for constructing a vehicle active safety system vertical architecture data distribution model based on a vehicle active safety system standardized data set; the fractional order seagull optimization global path search module is used for forming a preliminarily optimized vehicle active safety system data transmission path set; the wolf pack search local path optimization module is used for generating a final optimized vehicle active safety system data transmission path; and the vehicle active safety system data distribution execution module is used for executing a vehicle active safety system data transmission task. A vertical framework is adopted, the shortest path from the data acquisition node to the execution module is directly established, data transmission delay caused by multi-stage transfer is avoided, and intermediate links of data transmission are remarkably reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control systems, and in particular to a vehicle control system. Background Art

[0002] With the development of intelligent connected vehicle technology, the role of vehicle active safety systems in modern traffic environments is becoming increasingly important. Vehicle active safety systems collect and process data in real time through sensors, communication modules and control units, enabling vehicles to perceive, judge and make decisions on the external environment, thereby improving driving safety.

[0003] At present, traditional vehicle active safety systems usually adopt a layered data transmission architecture, that is, data is transmitted from the perception layer to the decision-making layer and execution layer step by step after multi-level processing. Although the layered architecture helps the modular design of the system, its hierarchical structure leads to a long data transmission path and information is transferred between multiple nodes, which increases communication delays. Especially in emergency situations, such as sudden collision warnings or automatic emergency braking, the high latency of the layered architecture may cause safety decisions to lag, affecting the active safety performance of the vehicle.

[0004] On the other hand, the existing data distribution path optimization methods lack intelligence and real-time performance, and are difficult to adapt to the complex and changeable vehicle network environment. Currently, most common path optimization methods are based on static rules or simple heuristic search algorithms, which are difficult to dynamically adapt to the multi-source data distribution and real-time transmission requirements in the vehicle active safety system. With the popularization of intelligent connected vehicles, the vehicle network environment has become more complex, and the network load will change dynamically with road conditions, weather, and vehicle density factors. The existing static optimization methods are prone to data congestion under high load conditions, making the system unable to transmit important information in time at critical moments. In addition, some path optimization methods only focus on the shortest path search, while ignoring network congestion and node load balancing factors, resulting in data backlogs on certain high-load paths, reducing overall transmission efficiency.

[0005] In order to solve the problems existing in the existing technology, a new method for distributing data for vehicle active safety systems is urgently needed. A flat or vertical architecture should be used to replace the traditional layered architecture to reduce data transmission delays. At the same time, an intelligent optimization algorithm should be combined to improve the real-time optimization capability of the data transmission path, so that the system can always maintain efficient and stable data distribution capabilities in a complex and dynamic network environment. Summary of the invention

[0006] One purpose of the present invention is to propose a vehicle control system. The present invention adopts a vertical architecture to directly establish the shortest path from the data acquisition node to the execution module, avoiding the data transmission delay caused by multi-level transfer, and significantly reducing the intermediate links of data transmission by optimizing the data distribution topology.

[0007] A vehicle control system according to an embodiment of the present invention includes the following modules: The vehicle active safety system multi-source data acquisition module is used to obtain multi-source data involved in the operation of the vehicle active safety system and generate a standardized data set for the vehicle active safety system.

[0008] A vehicle active safety system vertical architecture data distribution construction module is used to construct a vehicle active safety system vertical architecture data distribution model based on a vehicle active safety system standardized data set; The fractional-order seagull optimization global path search module is used to perform global search and optimization of the data transmission path based on the vertical architecture data distribution model of the vehicle active safety system using the fractional-order seagull optimization algorithm to form a preliminary optimized vehicle active safety system data transmission path set; A wolf pack search local path optimization module is used to locally optimize the initially optimized vehicle active safety system data transmission path using a wolf pack search algorithm to generate a final optimized vehicle active safety system data transmission path; The vehicle active safety system data distribution execution module is used to execute the vehicle active safety system data transmission task according to the vehicle active safety system data transmission path that is finally optimized.

[0009] A vehicle control method, applied to a vehicle control system, comprises the following steps: S1. Collect multi-source data of the vehicle active safety system, and pre-process the collected multi-source data of the vehicle active safety system to generate a standardized data set of the vehicle active safety system; S2. Constructing a vertical architecture data distribution model for a vehicle active safety system based on a standardized data set for a vehicle active safety system, wherein the vertical architecture data distribution model for a vehicle active safety system adopts a flat data transmission structure; S3. Use the fractional-order Seagull optimization algorithm to perform global search and optimization on the multi-source data transmission paths of each vehicle active safety system in the vertical architecture data distribution model of the vehicle active safety system, and form a preliminary optimized set of vehicle active safety system data transmission paths; S4. Using a wolf pack search algorithm to perform local search optimization on the set of data transmission paths of the preliminary optimized vehicle active safety system, refine the data transmission path of the vehicle active safety system, and generate a final optimized data transmission path of the vehicle active safety system; S5. Based on the finally optimized vehicle active safety system data transmission path, implement real-time data transmission during the operation of the vehicle active safety system, dynamically collect the vehicle active safety system network status and vehicle active safety system operation status information, and perform real-time monitoring and dynamic adjustment of the vehicle active safety system data transmission path.

[0010] Optionally, the S1 includes the following steps: S11. Collect multi-source data of the vehicle active safety system, wherein the multi-source data of the vehicle active safety system includes data from vehicle sensors, environmental perception devices, vehicle control modules and network communication modules. Each multi-source data sample of the vehicle active safety system is represented as: ; in, For the Multi-source data samples of vehicle active safety systems, Indicates the timestamp of the multi-source data sample of the vehicle's active safety system, Represents the numerical information of the multi-source data samples of the vehicle's active safety system, It is the device identifier of the multi-source data source of the vehicle active safety system. is the data category label; S12. Construct a vehicle active safety system data set based on the collected vehicle active safety system multi-source data, set a sampling time window, sort the collected vehicle active safety system multi-source data in chronological order, and form an original vehicle active safety system data set ; S13. Clean the original vehicle active safety system data set, remove invalid data, duplicate data and abnormal data, and obtain a cleaned vehicle active safety system data set; S14. Perform data standardization on the cleaned vehicle active safety system data set and convert the data into intervals using a normalization method. , get the standardized vehicle active safety system data set; S15. Remove redundant information from the standardized vehicle active safety system data set and calculate the feature correlation matrix of the multi-source data of the vehicle active safety system , forming the final standardized data set for vehicle active safety systems .

[0011] Optionally, the feature correlation matrix of multi-source data of the vehicle active safety system is calculated for: ; in, Indicates Dimensional features and The correlation coefficient of the dimension feature, is the total number of data samples, and Respectively represent the mean of the k-th data sample on the i-th dimension feature and the j-th dimension feature, and Represent the standardized values ​​of the k-th data sample on the i-th dimension feature and the j-th dimension feature respectively. If the correlation coefficient Exceeding the set redundancy threshold , then remove the highly redundant dimensional data to form the final standardized data set for the vehicle active safety system: ; in, Standardized datasets for vehicle active safety systems, The multi-source data information of the vehicle active safety system after redundancy removal, For the final Multi-source data samples of vehicle active safety systems.

[0012] Optionally, S2 includes the following steps: S21. Based on the standardized data set of vehicle active safety system , define the mapping function , convert each vehicle active safety system standardized data sample into the corresponding data distribution node, where A collection of nodes for all data distribution; It is the mapping function from data samples to nodes; S22. Distribute node set according to data Build a collection of direct connections between nodes , define the similarity evaluation function : ; in, represents the set of positive real numbers, and are the timestamps of the corresponding data samples, and is a positive real weight coefficient. When the similarity evaluation function When With Node With direct transmission capability and establish direct connection , get the set of direct connections between nodes : ; in, is a preset similarity threshold; S23. For each direct connection , define the transmission weight function To quantify the latency or cost of data transmission: ; in, Represents a slave node To Node Data transmission delay, represents the data transmission cost on this direct connection, and are the weight coefficients corresponding to delay and cost respectively; S24. Using the results of steps S21 to S23, the vehicle active safety system vertical architecture data distribution model is constructed as a graph model: ; in, Represents the vertical architecture data distribution model of the vehicle active safety system. The vertical architecture data distribution model of the vehicle active safety system adopts a flat data transmission structure, and the node set Represents all data acquisition and control execution units, directly connected to the collection and its transmission weight function Enable data to go directly from the acquisition node to the control execution module.

[0013] Optionally, S3 includes the following steps: S31. Initialize fractional seagull population set based on the vertical architecture data distribution model M of vehicle active safety system , each fractional seagull individual It is expressed as: ; in, Indicates The path starts at the acquisition node and ends at the control execution module. Indicates the population size; S32. Define the load balancing fitness function of multi-source data transmission path of vehicle active safety system : ; in, For direct connection The data transmission weight is k, which is the number of direct connections in the data transmission path of the vehicle active safety system. For the path The data transmission load of each node is is the average value of the node data transmission load on the path, is the load balancing weight coefficient, which ensures that the path takes into account both the shortest transmission and load balancing performance; S33. Constructing the adaptive fractional-order seagull position update of the vehicle active safety system network state as follows: ; in, and Respectively Second and The individual path position of the seagull in the iterative fractional order, and is the position update step size and the global optimal guidance coefficient, is the adaptive dynamic fractional order of the network state of the vehicle active safety system, is the gamma function, It is the real-time network load dynamic adjustment factor of the vehicle active safety system; S34. Define the global optimal vehicle active safety system data transmission path update formula: ; in, For the The optimal path position during the iteration process; S35. Real-time adjustment of dynamic fractional order based on the dynamic feedback mechanism of vehicle active safety system network status Dynamic adjustment factor of network load : ; ; in, and are the minimum and maximum boundaries of the fractional order, and are the minimum and maximum boundaries of the network load dynamic adjustment factor, is the current real-time network load value of the vehicle active safety system, and is the historical minimum and maximum value of the network load, is the current real-time network delay value of the vehicle active safety system, and The historical minimum and maximum values ​​of network delay; S36. Repeat steps S33 to S35 until the iteration stop condition is reached to obtain a preliminary optimized vehicle active safety system data transmission path set : ; in, Indicates The optimal solution for the data transmission path of the vehicle active safety system after adaptive dynamic fractional-order optimization of individual fractional-order seagulls.

[0014] Optionally, S4 includes the following steps: S41. Data transmission path set of vehicle active safety system based on preliminary optimization Initialize the wolf pack individual set , each wolf pack individual is represented by: ; in, Indicates The initial search position of each wolf pack individual, is the wolf population size, The first step in the data transmission path of the vehicle active safety system is initially optimized. Direct connection; S42. Define the path refinement fitness function of the vehicle active safety system : ; in, Indicates direct connection The data transmission weight, For direct connection Dynamic stability coefficient in real-time network environment, For direct connection The real-time network load imbalance coefficient, Indicates direct connection Real-time data transmission bandwidth, is a positive real number weight coefficient; S43. Construct a dynamic memory tracking behavior location update mechanism for wolves, and implement refined search and optimization of the data transmission path of the vehicle active safety system: ; in, and Respectively Second and The individual positions of the wolves in the iteration, is the leader position of the wolf pack in the current iteration, representing the real-time local optimal path, The best path memory position for individual wolves in history. is the individual dynamic memory weight coefficient, , are the adjustment coefficients of the current optimal path guidance and historical path memory respectively; S44. Define a real-time update mechanism for the wolf pack leader position to achieve local optimization guidance of the vehicle active safety system data transmission path in a dynamic network environment: ; in, For the The real-time optimal path position determined based on the refined fitness function in the iteration; S45. Construct a network environment adaptive wolf pack intelligent reconnaissance mechanism for the vehicle active safety system, and define the wolf pack reconnaissance behavior update formula: ; in, represents the real-time optimal path position after reconnaissance, , are the random exploration coefficient and the optimal guidance coefficient of reconnaissance behavior, is the dynamic random disturbance coefficient of the reconnaissance behavior, which is adjusted according to the real-time network fluctuation amplitude of the vehicle active safety system. is the dynamic sensitivity coefficient of individual wolf pack reconnaissance, which changes dynamically with path stability and load fluctuation. To randomly select individual locations of wolves; S46. Repeat steps S43 to S45 until the local optimization iteration stop condition is reached, and the final optimized vehicle active safety system data transmission path is generated: ; in, Transmit optimal path position for final vehicle active safety system data.

[0015] The beneficial effects of the present invention are: 1. The present invention adopts a vertical architecture to directly establish the shortest path from the data acquisition node to the execution module, avoiding the data transmission delay caused by multi-level transfer. By optimizing the data distribution topology, the intermediate links of data transmission are significantly reduced, and the data transmission time in an emergency is shortened to less than 60% of the traditional layered architecture, effectively improving the response speed of the active safety system.

[0016] 2. The present invention combines the fractional-order Seagull optimization algorithm in the process of data distribution path optimization, and utilizes the memory characteristics and long-range correlation of fractional-order calculus to efficiently search for the global optimal data transmission path in a complex dynamic network environment. The dynamic fractional-order Seagull flight model enables the optimization algorithm to take into account both local and global search capabilities. In a complex and dynamic vehicle network environment, it can enhance the adaptive optimization capability of the data transmission path, improve the adaptability of path planning, and maintain high path stability even when the network load changes suddenly.

[0017] 3. The present invention combines the improved wolf pack search algorithm to locally optimize the initially optimized path, focusing on the real-time load balancing problem of the data transmission path. By introducing a dynamic memory tracking mechanism and an adaptive reconnaissance mechanism, it ensures that the data transmission path has a low network congestion rate while being the optimal short path. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 The present invention provides a flow chart of a vehicle control system. DETAILED DESCRIPTION

[0019] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0020] refer to Figure 1 , a vehicle control system, comprising the following modules: The vehicle active safety system multi-source data acquisition module is used to obtain multi-source data involved in the operation of the vehicle active safety system and generate a standardized data set for the vehicle active safety system.

[0021] A vehicle active safety system vertical architecture data distribution construction module is used to construct a vehicle active safety system vertical architecture data distribution model based on a vehicle active safety system standardized data set; The fractional-order seagull optimization global path search module is used to perform global search and optimization of the data transmission path based on the vertical architecture data distribution model of the vehicle active safety system using the fractional-order seagull optimization algorithm to form a preliminary optimized vehicle active safety system data transmission path set; A wolf pack search local path optimization module is used to locally optimize the initially optimized vehicle active safety system data transmission path using a wolf pack search algorithm to generate a final optimized vehicle active safety system data transmission path; The vehicle active safety system data distribution execution module is used to execute the vehicle active safety system data transmission task according to the vehicle active safety system data transmission path that is finally optimized.

[0022] A vehicle control method, applied to a vehicle control system, comprises the following steps: S1. Collect multi-source data of the vehicle active safety system, and pre-process the collected multi-source data of the vehicle active safety system to generate a standardized data set of the vehicle active safety system; S2. Construct a vertical architecture data distribution model for vehicle active safety system based on the standardized data set of vehicle active safety system. The vertical architecture data distribution model for vehicle active safety system adopts a flat data transmission structure. S3. Use the fractional-order Seagull optimization algorithm to perform global search and optimization on the multi-source data transmission paths of each vehicle active safety system in the vertical architecture data distribution model of the vehicle active safety system, and form a preliminary optimized set of vehicle active safety system data transmission paths; S4. Use the wolf pack search algorithm to perform local search optimization on the initially optimized vehicle active safety system data transmission path set, refine the vehicle active safety system data transmission path, and generate the final optimized vehicle active safety system data transmission path; S5. Based on the finally optimized data transmission path of the vehicle active safety system, real-time data transmission is implemented during the operation of the vehicle active safety system, and the network status of the vehicle active safety system and the operation status information of the vehicle active safety system are dynamically collected to monitor and dynamically adjust the data transmission path of the vehicle active safety system in real time.

[0023] In this implementation, S1 includes the following steps: S11. Collect multi-source data of vehicle active safety system. The multi-source data of vehicle active safety system includes data from vehicle sensors, environmental perception equipment, vehicle control module and network communication module. Each multi-source data sample of vehicle active safety system is represented as: ; in, For the Multi-source data samples of vehicle active safety systems, Indicates the timestamp of the multi-source data sample of the vehicle's active safety system, Represents the numerical information of the multi-source data samples of the vehicle's active safety system, It is the device identifier of the multi-source data source of the vehicle active safety system. is the data category label; S12. Construct a vehicle active safety system data set based on the collected vehicle active safety system multi-source data, set a sampling time window, sort the collected vehicle active safety system multi-source data in chronological order, and form an original vehicle active safety system data set ; S13. Clean the original vehicle active safety system data set, remove invalid data, duplicate data and abnormal data, and obtain a cleaned vehicle active safety system data set; S14. Perform data standardization on the cleaned vehicle active safety system data set and convert the data into intervals using a normalization method. , get the standardized vehicle active safety system data set; S15. Remove redundant information from the standardized vehicle active safety system data set and calculate the feature correlation matrix of the multi-source data of the vehicle active safety system , forming the final standardized data set for vehicle active safety systems .

[0024] In this embodiment, the characteristic correlation matrix of multi-source data of the vehicle active safety system is calculated for: ; in, Indicates Dimensional features and The correlation coefficient of the dimension feature, is the total number of data samples, and Respectively represent the mean of the k-th data sample on the i-th dimension feature and the j-th dimension feature, and Represent the standardized values ​​of the k-th data sample on the i-th dimension feature and the j-th dimension feature respectively. If the correlation coefficient Exceeding the set redundancy threshold , then remove the highly redundant dimensional data to form the final standardized data set for the vehicle active safety system: ; in, Standardized datasets for vehicle active safety systems, The multi-source data information of the vehicle active safety system after redundancy removal, For the final Multi-source data samples of vehicle active safety systems.

[0025] In this implementation, S2 includes the following steps: S21. Based on the standardized data set of vehicle active safety system , define the mapping function , convert each vehicle active safety system standardized data sample into the corresponding data distribution node, where A collection of nodes for all data distribution; It is the mapping function from data samples to nodes; S22. Distribute node set according to data Build a collection of direct connections between nodes , define the similarity evaluation function : ; in, represents the set of positive real numbers, and are the timestamps of the corresponding data samples, and is a positive real weight coefficient. When the similarity evaluation function When With Node Direct transmission capability and direct connection , get the set of direct connections between nodes : ; in, is a preset similarity threshold; S23. For each direct connection , define the transmission weight function To quantify the latency or cost of data transmission: ; in, Represents a slave node To Node Data transmission delay, represents the data transmission cost on this direct connection, and are the weight coefficients corresponding to delay and cost respectively; S24. Using the results of steps S21 to S23, the vehicle active safety system vertical architecture data distribution model is constructed as a graph model: ; in, Represents the vertical architecture data distribution model of the vehicle active safety system. The vertical architecture data distribution model of the vehicle active safety system adopts a flat data transmission structure, and the node set Represents all data acquisition and control execution units, directly connected to the collection and its transmission weight function Enable data to go directly from the acquisition node to the control execution module.

[0026] This implementation method proposes a new vertical architecture data distribution mode, which breaks through the problems of too many levels, long response time and high computational redundancy in the traditional layered data architecture during data transmission. The vertical architecture data distribution model of the vehicle active safety system is based on the principle of building the shortest path from the data acquisition end to the execution end, combined with the data distribution topology optimization strategy, to ensure that the data distribution process in the vehicle active safety system does not go through lengthy hierarchical transmission, but directly reaches the decision-making module and execution unit, thereby achieving a low-latency, highly stable data transmission path. In addition, the introduction of the data node similarity evaluation mechanism and the data transmission weight calculation strategy can make the data flow more intelligent according to different network environments and realities, and provide efficient data support for subsequent path optimization algorithms.

[0027] In this implementation, S3 includes the following steps: S31. Initialize fractional seagull population set based on the vertical architecture data distribution model M of vehicle active safety system , each fractional seagull individual It is expressed as: ; in, Indicates The path starts at the acquisition node and ends at the control execution module. Indicates the population size; S32. Define the load balancing fitness function of multi-source data transmission path of vehicle active safety system : ; in, For direct connection The data transmission weight is k, which is the number of direct connections in the data transmission path of the vehicle active safety system. For the path The data transmission load of each node is is the average value of the node data transmission load on the path, is the load balancing weight coefficient, which ensures that the path takes into account both the shortest transmission and load balancing performance; S33. Constructing the adaptive fractional-order seagull position update of the vehicle active safety system network state as follows: ; in, and Respectively Second and The individual path position of the seagull in the iterative fractional order, and is the position update step size and the global optimal guidance coefficient, is the adaptive dynamic fractional order of the network state of the vehicle active safety system, is the gamma function, It is the real-time network load dynamic adjustment factor of the vehicle active safety system; S34. Define the global optimal vehicle active safety system data transmission path update formula: ; in, For the The optimal path position during the iteration process; S35. Real-time adjustment of dynamic fractional order based on the dynamic feedback mechanism of vehicle active safety system network status Dynamic adjustment factor of network load : ; ; in, and are the minimum and maximum boundaries of the fractional order, and are the minimum and maximum boundaries of the network load dynamic adjustment factor, is the current real-time network load value of the vehicle active safety system, and is the historical minimum and maximum value of the network load, is the current real-time network delay value of the vehicle active safety system, and The historical minimum and maximum values ​​of network delay; S36. Repeat steps S33 to S35 until the iteration stop condition is reached to obtain a preliminary optimized vehicle active safety system data transmission path set : ; in, Indicates The optimal solution for the data transmission path of the vehicle active safety system after adaptive dynamic fractional-order optimization of individual fractional-order seagulls.

[0028] This embodiment constructs a globally optimized data transmission path for the vehicle active safety system, and uses the fractional order seagull optimization algorithm for global search optimization to find the globally optimal data transmission path set. Compared with the traditional optimization algorithm, the fractional order seagull optimization of the present invention introduces the fractional order calculus memory characteristics and long-range correlation, so that the algorithm has both global search capability and local convergence capability during the search process, avoiding the problem of falling into the local optimum. Through the dynamic adaptive fractional order adjustment mechanism, the fractional order seagull optimization algorithm can adjust the optimization strategy in real time according to the changes in the Internet of Vehicles environment (bandwidth fluctuations, data congestion, node failures), ensuring that the data distribution path is always optimal, improving the global optimization capability, stability and dynamic adaptability of the data transmission path, and providing more reliable data support for the vehicle active safety system.

[0029] In this implementation, S4 includes the following steps: S41. Data transmission path set of vehicle active safety system based on preliminary optimization Initialize the wolf pack individual set , each wolf pack individual is represented by: ; in, Indicates The initial search position of each wolf pack individual, is the wolf population size, The first step in the data transmission path of the vehicle active safety system is initially optimized. Direct connection; S42. Define the path refinement fitness function of the vehicle active safety system : ; in, Indicates direct connection The data transmission weight, For direct connection Dynamic stability coefficient in real-time network environment, For direct connection The real-time network load imbalance coefficient, Indicates direct connection Real-time data transmission bandwidth, is a positive real number weight coefficient; S43. Construct a dynamic memory tracking behavior location update mechanism for wolves, and implement refined search and optimization of the data transmission path of the vehicle active safety system: ; in, and Respectively Second and The individual positions of the wolves in the iteration, is the leader position of the wolf pack in the current iteration, representing the real-time local optimal path, The best path memory position for individual wolves in history. is the individual dynamic memory weight coefficient, , are the adjustment coefficients of the current optimal path guidance and historical path memory respectively; S44. Define a real-time update mechanism for the wolf pack leader position to achieve local optimization guidance of the vehicle active safety system data transmission path in a dynamic network environment: ; in, For the The real-time optimal path position determined based on the refined fitness function in the iteration; S45. Construct a network environment adaptive wolf pack intelligent reconnaissance mechanism for the vehicle active safety system, and define the wolf pack reconnaissance behavior update formula: ; in, represents the real-time optimal path position after reconnaissance, , are the random exploration coefficient and the optimal guidance coefficient of reconnaissance behavior, is the dynamic random disturbance coefficient of the reconnaissance behavior, which is adjusted according to the real-time network fluctuation amplitude of the vehicle active safety system. is the dynamic sensitivity coefficient of individual wolf pack reconnaissance, which changes dynamically with path stability and load fluctuation. To randomly select individual locations of wolves; S46. Repeat steps S43 to S45 until the local optimization iteration stop condition is reached, and the final optimized vehicle active safety system data transmission path is generated: ; in, Transmit optimal path position for final vehicle active safety system data.

[0030] Based on S3, this implementation method further introduces an improved wolf pack search algorithm in S4 to locally optimize the data transmission path, thereby further improving the local adaptability and load balancing ability of data transmission under the premise of ensuring global optimization. The vehicle network environment of the vehicle active safety system is highly dynamic, the data flow changes at any time, and the network congestion situation cannot be fully predicted. Therefore, it is difficult to adapt to complex environments by relying solely on global optimization path planning. Through the dynamic memory tracking mechanism and adaptive reconnaissance behavior update mechanism of the wolf pack search, the data transmission path can be adjusted at any time, and local congestion is reduced without increasing the overall path calculation overhead, and the balance of data flow is improved. This allows the data transmission of the vehicle active safety system to maintain low latency, low congestion, and high throughput in a highly dynamic environment, ensuring that key safety information can be transmitted to the execution module as soon as possible, and improving the real-time response capability of the active safety system.

[0031] Embodiment 1: On March 15, 2024, the present invention was tested at a certain intelligent connected vehicle testing base. The test scenarios included 15 safety events, including emergency braking response, sudden obstacle avoidance, and lane keeping system optimization. The goal was to verify the improvement effects of the present invention in data distribution architecture optimization, data transmission path optimization, and real-time response speed.

[0032] During the test, the experimenters deployed two systems on 80 test vehicles, one using the traditional layered data distribution architecture, and the other using the flat data distribution architecture of the present invention combined with fractional-order seagull optimization and wolfpack search algorithm. All test vehicles are equipped with high-precision lidar, millimeter-wave radar, front-view camera, ultrasonic sensor and V2X communication module, and connected to the 5G-V2X dedicated network of the test base, with a data transmission speed of 1Gbps.

[0033] Case 1: High-speed emergency brake response test: At 13:37:24 on March 15, 2024, on the G60 highway section of the test road, a test vehicle (No. T-A12) was traveling at a speed of 120km / h when a vehicle suddenly changed lanes 180 meters ahead. The system needed to complete data collection, path optimization, and brake command transmission in the shortest time possible to ensure safe braking.

[0034] Response to traditional methods: At 13:37:24.015, the car in front suddenly changed lanes. The millimeter-wave radar and camera of T-A12 detected the abnormality and the data was transmitted to the perception layer.

[0035] At 13:37:24.028, the perception layer transmits the data to the fusion layer for comprehensive data analysis.

[0036] 13:37:24.041, the fusion layer transmits data to the decision layer to calculate the braking strategy.

[0037] At 13:37:24.057, the decision layer sends a braking command to the execution layer, and the braking system performs the braking action after receiving the signal.

[0038] Total delay: 42ms, vehicle braking distance 4.1 meters, almost rear-ending the vehicle in front.

[0039] Response of the method of the present invention: At 13:37:24.015, the vehicle in front changed lanes, and the millimeter-wave radar and camera data were directly transmitted to the decision-making layer without the need for hierarchical transfer.

[0040] 13:37:24.021, the fractional-order Seagull optimization algorithm dynamically calculates the optimal data transmission path, and combines it with the wolf pack search algorithm to optimize transmission stability.

[0041] At 13:37:24.029, the data reaches the execution layer directly, triggering the braking system to intervene in advance.

[0042] Total delay: 14ms, vehicle braking distance 1.5 meters, successfully avoiding a rear-end collision.

[0043] Case 2: Avoiding sudden obstacles on urban roads: At 14:12:45 on March 15, 2024, on the urban road section of the test site, when the test vehicle (No. T-C37) was driving to the intersection at a speed of 50km / h, a pedestrian suddenly broke into the lane. The system needs to calculate the optimal lane change path in the shortest time and control the vehicle to change lanes to avoid the pedestrian.

[0044] Response to traditional methods: At 14:12:45.002, the front-view camera detected a pedestrian intruding and the data was uploaded to the fusion layer.

[0045] 14:12:45.018, the fusion layer analyzes the data and transmits it to the decision layer to calculate the lane change path.

[0046] At 14:12:45.037, the decision layer sends instructions to the control module to perform steering adjustments.

[0047] Total delay: 35ms. The delay in the vehicle changing lanes resulted in a near collision in the left lane.

[0048] Response of the method of the present invention: 14:12:45.002, the camera data is directly transmitted to the decision layer, omitting the intermediate fusion layer.

[0049] 14:12:45.008, the fractional-order Seagull optimization algorithm calculates the optimal trajectory for lane change within 7ms.

[0050] At 14:12:45.014, the data reached the execution layer directly and the lane change operation was completed 23ms ahead of schedule.

[0051] Total delay: 14ms, the vehicle changes lanes smoothly, avoiding collision with pedestrians while maintaining a safe distance from the vehicle on the left.

[0052] Case 3: Braking on slippery roads at night with low visibility: At 21:45:12 on March 15, 2024, the test vehicle (number T-N58) was driving on a city main road in a low-light environment (<50lux) at a speed of 65km / h. Due to the slippery road surface, the vehicle in front of it skidded out of control, and the test vehicle had to reduce its speed immediately to ensure safety.

[0053] Response to traditional methods: At 21:45:12.032, the camera and millimeter-wave radar detected abnormalities with the vehicle ahead.

[0054] At 21:45:12.048, data is transmitted to the fusion layer for processing, generating a risk warning.

[0055] At 21:45:12.061, the decision layer calculates the optimal braking strategy and sends instructions to the execution layer.

[0056] Total delay: 49ms. The vehicle completed braking 2.8 meters away from the out-of-control vehicle, but minor scratches still occurred.

[0057] Response of the method of the present invention: 21:45:12.032, sensor data is directly transmitted to the decision-making layer to reduce fusion calculation time.

[0058] 21:45:12.039, the data transmission path is dynamically adjusted in combination with fractional-order optimization, and the transmission time is reduced to 7ms.

[0059] At 21:45:12.047, the data reaches the execution layer directly and the brakes are applied in advance.

[0060] Total delay: 15ms. The vehicle stops in advance and maintains a safe distance of 0.8 meters from the vehicle in front to avoid scratches.

[0061] And the experimenters did data comparison and statistical analysis: Test items Traditional layered architecture (delay ms) The method of the present invention (delay ms) Optimization rate Actual Results High-speed emergency braking 42ms 14ms 66.7% Avoid rear-end collisions Sudden obstacle avoidance 35ms 14ms 60.0% Smooth lane change Nighttime low-visibility braking 49ms 15ms 69.4% Avoid scratches In the test of this embodiment, the experimenters verified the advantages of the vehicle active safety system vertical architecture data distribution method of the present invention in data transmission efficiency, path optimization calculation, and emergency response through real road events. The test data showed that: 1. The data transmission delay is reduced by an average of 63.7%, effectively improving the real-time performance of the active safety system; 2. After optimizing the data transmission path, information reaches the execution layer directly, avoiding the hierarchical data lag problem of the traditional architecture; 3. Combined with intelligent optimization algorithms, the adaptability of data transmission is improved to ensure optimal path transmission in complex vehicle network environments.

[0062] In summary, the technical solution of the present invention effectively improves the emergency response capability of the vehicle's active safety system, ensuring that it can still provide fast and accurate safety protection in low-visibility environments such as highways, urban roads and at night.

[0063] The present invention adopts a vertical architecture to directly establish the shortest path from the data acquisition node to the execution module, avoiding the data transmission delay caused by multi-level transfer. By optimizing the data distribution topology, the intermediate links of data transmission are significantly reduced, and the data transmission time in an emergency is shortened to less than 60% of the traditional layered architecture, effectively improving the response speed of the active safety system.

[0064] The present invention combines the fractional-order Seagull optimization algorithm in the process of data distribution path optimization, and utilizes the memory characteristics and long-range correlation of fractional-order calculus to efficiently search for the global optimal data transmission path in a complex dynamic network environment. The dynamic fractional-order Seagull flight model enables the optimization algorithm to take into account both local search capability and global search capability. In a complex dynamic vehicle network environment, the adaptive optimization capability of the data transmission path can be improved, the adaptability of path planning is improved, and high path stability can be maintained even when the network load changes suddenly.

[0065] The present invention combines the improved wolf pack search algorithm to locally optimize the initially optimized path, focusing on the real-time load balancing problem of the data transmission path. By introducing a dynamic memory tracking mechanism and an adaptive reconnaissance mechanism, it ensures that the data transmission path has a low network congestion rate while being the optimal short path.

[0066] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A vehicle control system, characterized in that: Includes the following modules: The vehicle active safety system multi-source data acquisition module is used to obtain multi-source data involved in the operation of the vehicle active safety system and generate a standardized data set for the vehicle active safety system; A vehicle active safety system vertical architecture data distribution construction module is used to construct a vehicle active safety system vertical architecture data distribution model based on a vehicle active safety system standardized data set; The fractional-order seagull optimization global path search module is used to perform global search and optimization of the data transmission path based on the vertical architecture data distribution model of the vehicle active safety system using the fractional-order seagull optimization algorithm to form a preliminary optimized vehicle active safety system data transmission path set; A wolf pack search local path optimization module is used to locally optimize the initially optimized vehicle active safety system data transmission path using a wolf pack search algorithm to generate a final optimized vehicle active safety system data transmission path; The vehicle active safety system data distribution execution module is used to execute the vehicle active safety system data transmission task according to the vehicle active safety system data transmission path that is finally optimized.

2. A vehicle control method, applied to a vehicle control system according to claim 1, characterized in that: The following steps are involved: S1. Collect multi-source data of the vehicle active safety system, and pre-process the collected multi-source data of the vehicle active safety system to generate a standardized data set of the vehicle active safety system; S2. Constructing a vertical architecture data distribution model for a vehicle active safety system based on a standardized data set for a vehicle active safety system, wherein the vertical architecture data distribution model for a vehicle active safety system adopts a flat data transmission structure; S3. Use the fractional-order Seagull optimization algorithm to perform global search and optimization on the multi-source data transmission paths of each vehicle active safety system in the vertical architecture data distribution model of the vehicle active safety system, and form a preliminary optimized set of vehicle active safety system data transmission paths; S4. Using a wolf pack search algorithm to perform local search optimization on the set of data transmission paths of the preliminary optimized vehicle active safety system, refine the data transmission path of the vehicle active safety system, and generate a final optimized data transmission path of the vehicle active safety system; S5. Based on the finally optimized vehicle active safety system data transmission path, implement real-time data transmission during the operation of the vehicle active safety system, dynamically collect the vehicle active safety system network status and vehicle active safety system operation status information, and perform real-time monitoring and dynamic adjustment of the vehicle active safety system data transmission path.

3. A vehicle control method according to claim 2, characterized in that: The S1 comprises the following steps: S11. Collect multi-source data of the vehicle active safety system, wherein the multi-source data of the vehicle active safety system includes data from vehicle sensors, environmental perception devices, vehicle control modules and network communication modules. Each multi-source data sample of the vehicle active safety system is represented as: ； in, For the Multi-source data samples of vehicle active safety systems, Indicates the timestamp of the multi-source data sample of the vehicle's active safety system, Represents the numerical information of the multi-source data samples of the vehicle's active safety system, It is the device identifier of the multi-source data source of the vehicle active safety system. is the data category label; S12. Construct a vehicle active safety system data set based on the collected vehicle active safety system multi-source data, set a sampling time window, sort the collected vehicle active safety system multi-source data in chronological order, and form an original vehicle active safety system data set ; S13. Clean the original vehicle active safety system data set, remove invalid data, duplicate data and abnormal data, and obtain a cleaned vehicle active safety system data set; S14. Perform data standardization on the cleaned vehicle active safety system data set and convert the data into intervals using a normalization method. , get the standardized vehicle active safety system data set; S15. Remove redundant information from the standardized vehicle active safety system data set and calculate the feature correlation matrix of the multi-source data of the vehicle active safety system , forming the final standardized data set for vehicle active safety systems .

4. A vehicle control method according to claim 3, characterized in that: The characteristic correlation matrix of multi-source data of the vehicle active safety system is calculated for: ； in, Indicates Dimensional features and The correlation coefficient of the dimension feature, is the total number of data samples, and Respectively represent the mean of the k-th data sample on the i-th dimension feature and the j-th dimension feature, and Represent the standardized values ​​of the k-th data sample on the i-th dimension feature and the j-th dimension feature respectively. If the correlation coefficient Exceeding the set redundancy threshold , then remove the highly redundant dimensional data to form the final standardized data set for the vehicle active safety system: ； in, Standardized datasets for vehicle active safety systems, The multi-source data information of the vehicle active safety system after redundancy removal, For the final Multi-source data samples of vehicle active safety systems.

5. A vehicle control method according to claim 4, characterized in that: The S2 comprises the following steps: S21. Based on the standardized data set of vehicle active safety system , define the mapping function , convert each vehicle active safety system standardized data sample into the corresponding data distribution node, where A collection of nodes for all data distribution; It is the mapping function from data samples to nodes; S22. Distribute node set according to data Build a collection of direct connections between nodes , define the similarity evaluation function : ； in, represents the set of positive real numbers, and are the timestamps of the corresponding data samples, and is a positive real weight coefficient. When the similarity evaluation function When With Node With direct transmission capability and establish direct connection , get the set of direct connections between nodes : ； in, is a preset similarity threshold; S23. For each direct connection , define the transmission weight function To quantify the latency or cost of data transmission: ； in, Represents a slave node To Node Data transmission delay, represents the data transmission cost on this direct connection, and are the weight coefficients corresponding to delay and cost respectively; S24. Using the results of steps S21 to S23, the vehicle active safety system vertical architecture data distribution model is constructed as a graph model: ； in, Represents the vertical architecture data distribution model of the vehicle active safety system. The vertical architecture data distribution model of the vehicle active safety system adopts a flat data transmission structure, and the node set Represents all data acquisition and control execution units, directly connected to the collection and its transmission weight function Enable data to go directly from the acquisition node to the control execution module.

6. A vehicle control method according to claim 5, characterized in that: The S3 comprises the following steps: S31. Initialize fractional seagull population set based on the vertical architecture data distribution model M of vehicle active safety system , each fractional seagull individual It is expressed as: ； in, Indicates The path starts at the acquisition node and ends at the control execution module. Indicates the population size; S32. Define the load balancing fitness function of multi-source data transmission path of vehicle active safety system : ； in, For direct connection The data transmission weight is k, which is the number of direct connections in the data transmission path of the vehicle active safety system. For the path The data transmission load of each node is is the average value of the node data transmission load on the path, is the load balancing weight coefficient, which ensures that the path takes into account both the shortest transmission and load balancing performance; S33. Constructing the adaptive fractional-order seagull position update of the vehicle active safety system network state as follows: ； in, and Respectively Second and Iteration fractional order seagull individual path position, and is the position update step size and the global optimal guidance coefficient, is the adaptive dynamic fractional order of the network state of the vehicle active safety system, is the gamma function, It is the real-time network load dynamic adjustment factor of the vehicle active safety system; S34. Define the global optimal vehicle active safety system data transmission path update formula: ； in, For the The optimal path position during the iteration process; S35. Real-time adjustment of dynamic fractional order based on the dynamic feedback mechanism of vehicle active safety system network status Dynamic adjustment factor of network load : ； ； in, and are the minimum and maximum boundaries of the fractional order, and are the minimum and maximum boundaries of the network load dynamic adjustment factor, is the current real-time network load value of the vehicle active safety system, and is the historical minimum and maximum value of the network load, is the current real-time network delay value of the vehicle active safety system, and The historical minimum and maximum values ​​of network delay; S36. Repeat steps S33 to S35 until the iteration stop condition is reached to obtain a preliminary optimized vehicle active safety system data transmission path set : ； in, Indicates The optimal solution for the data transmission path of the vehicle active safety system after adaptive dynamic fractional-order optimization of individual fractional-order seagulls.

7. A vehicle control method according to claim 2, characterized in that: The S4 comprises the following steps: S41. Data transmission path set of vehicle active safety system based on preliminary optimization Initialize the wolf pack individual set , each wolf pack individual is represented by: ； in, Indicates The initial search position of each wolf pack individual, is the wolf population size, The first step in the data transmission path of the vehicle active safety system is initially optimized. Direct connection; S42. Define the path refinement fitness function of the vehicle active safety system : ； in, Indicates direct connection The data transmission weight, For direct connection Dynamic stability coefficient in real-time network environment, For direct connection The real-time network load imbalance coefficient, Indicates direct connection Real-time data transmission bandwidth, is a positive real number weight coefficient; S43. Construct a dynamic memory tracking behavior location update mechanism for wolves, and implement refined search and optimization of the data transmission path of the vehicle active safety system: ； in, and Respectively Second and The individual positions of the wolves in the iteration, is the leader position of the wolf pack in the current iteration, representing the real-time local optimal path, The best path memory position for individual wolves in history. is the individual dynamic memory weight coefficient, , are the adjustment coefficients of the current optimal path guidance and historical path memory respectively; S44. Define a real-time update mechanism for the wolf pack leader position to achieve local optimization guidance of the vehicle active safety system data transmission path in a dynamic network environment: ； in, For the The real-time optimal path position determined based on the refined fitness function in the iteration; S45. Construct a network environment adaptive wolf pack intelligent reconnaissance mechanism for the vehicle active safety system, and define the wolf pack reconnaissance behavior update formula: ； in, represents the real-time optimal path position after reconnaissance, , are the random exploration coefficient and the optimal guidance coefficient of reconnaissance behavior, is the dynamic random disturbance coefficient of the reconnaissance behavior, which is adjusted according to the real-time network fluctuation amplitude of the vehicle active safety system. is the dynamic sensitivity coefficient of individual wolf pack reconnaissance, which changes dynamically with path stability and load fluctuation. To randomly select individual locations of wolves; S46. Repeat steps S43 to S45 until the local optimization iteration stop condition is reached, and generate the final optimized vehicle active safety system data transmission path: ； in, Transmit optimal path position for final vehicle active safety system data.

Images