Automatic order dispatching method based on civil aviation airport aircraft ground guarantee

Abstract

The invention relates to an automatic order dispatching method based on civil aviation airport aircraft ground support, which adopts a dynamic causal relationship identification module based on a Bayesian network, and combines a context awareness module of a convolutional neural network (CNN) and a long short-term memory (LSTM) network to improve prediction accuracy and task allocation efficiency. An improved multi-objective optimization algorithm is combined with a genetic algorithm and a particle swarm optimization algorithm, and a dynamic weight adjustment mechanism is introduced, so that self-adaptive optimization configuration of resources is realized. A path planning algorithm combining multi-level A * search and deep reinforcement learning can adjust a path in real time and dynamically avoid obstacles, and the system enhances real-time response capability and decision accuracy through a self-learning algorithm based on a depth deterministic policy gradient (DDPG) and a comprehensive decision support system based on a graph neural network (GNN). According to the method, the operation efficiency, the safety and the emergency response capability of the airport ground guarantee service are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of civil aviation, and in particular relates to an automatic dispatching method based on ground support for aircraft at a civil aviation airport. Background Art

[0002] With the rapid development of civil aviation transportation, airport ground support services play a vital role in ensuring flight punctuality, improving passenger satisfaction and improving the overall operational efficiency of airports. In order to cope with the growing demand for ground support, the automatic dispatch system has become one of the key technologies to improve ground service efficiency.

[0003] In the prior art, Chinese invention patent CN118134207B discloses a production scheduling method and system in the scenario of automatic allocation of civil airport guide vehicles. This method constructs an initial population set, obtains and analyzes the current flight data to be allocated and the data of guide vehicles and personnel, and uses genetic algorithms to generate a more adaptable initial population, thereby providing optimized genetic algorithm support for airport guide vehicle allocation. However, this method has certain limitations in processing multi-source data fusion, real-time task adjustment, and path planning in complex environments, and it is difficult to fully respond to dynamic changes and emergencies in airport operations.

[0004] Another Chinese invention patent, CN118114952B, discloses a method and system for dynamically allocating boarding tasks in a rolling time domain at a civil airport. This method initializes the task list, receives and parses historical operation data, constructs a dynamic allocation judgment structure, and adjusts the task allocation ratio according to the rolling time interval. It can achieve automatic rolling allocation of boarding tasks and improve allocation efficiency and effectiveness. However, this method is mainly aimed at boarding task allocation, lacks comprehensive management of the entire airport ground support tasks, and is insufficiently considered in terms of data security, equipment maintenance management, and personnel training, and is unable to comprehensively improve the overall efficiency and safety of airport ground support services.

[0005] The above design improves the automation and allocation efficiency of ground support tasks by introducing genetic algorithms and rolling allocation mechanisms, but it still has the following limitations: Insufficient multi-source data fusion: The existing methods lack advanced technical support in the integration of multi-source data and the identification of causal relationships, resulting in limited prediction accuracy and task allocation accuracy. Lack of real-time feedback and dynamic optimization: The lack of effective real-time monitoring and feedback mechanisms makes it difficult to adjust task allocation and resource allocation in a timely manner according to dynamic changes. Insufficient data security: In the process of multi-source data transmission, there is a lack of effective data security protection measures, and there is a risk of data tampering and unauthorized access. Imperfect equipment maintenance management: Failure to predictively maintain ground support equipment can easily affect mission execution due to equipment failure. Summary of the invention

[0006] In order to solve the above problems, the present invention provides an automatic dispatching method based on civil aviation airport aircraft ground support, comprising the following steps:

[0007] S1. Use the time series prediction model to fuse the multi-source data of historical flight data, weather forecasts, and air traffic control instructions, and use the dynamic causal relationship identification module based on the Bayesian network to identify the causal relationship between different data sources in real time to accurately predict flight arrival times;

[0008] S2. Based on the prediction results of step S1, combined with real-time monitoring data, including flight dynamics, vehicle location, and equipment status, a context-aware module based on a convolutional neural network (CNN) and a long short-term memory network (LSTM) is used to dynamically adjust the priority of tasks and perform dynamic task allocation;

[0009] S3. Use an improved multi-objective optimization algorithm to adaptively optimize resource allocation based on the urgency of the task and the type of equipment required. This optimization algorithm combines the global search capability of the genetic algorithm with the fast convergence characteristics of the particle swarm optimization algorithm, and introduces a dynamic weight adjustment mechanism and real-time feedback loop. It has self-learning capabilities and can continuously optimize decision logic based on historical data and real-time feedback.

[0010] S4. Use an improved path planning algorithm to plan the optimal path for each execution unit. The path planning algorithm is based on a model that combines multi-level A* search with deep reinforcement learning. It can be updated in real time and adapt to the dynamic changes of the airport environment. At the same time, it is combined with an energy management algorithm based on a predictive model to optimize energy consumption and ensure that the electric vehicle has enough energy to return to the base or reach the next charging point before completing the mission;

[0011] S5. Through real-time monitoring and feedback mechanisms, a feedback loop is established to feed back real-time monitoring data to the system's learning module. The self-learning algorithm based on deep deterministic policy gradient (DDPG) and the comprehensive decision support system based on graph neural network (GNN) are used to dynamically adjust task allocation and path planning to ensure the overall progress of the system in emergency situations. The improved rapid response and resource allocation mechanism, including a priority-based dynamic resource allocation algorithm, a machine learning-based early warning model, a knowledge graph-based automated review system, a collaborative filtering-based task allocation system, and an augmented reality (AR)-based intelligent scheduling assistant, can be used to quickly respond to emergencies and reasonably allocate resources.

[0012] S6. Use a blockchain-based secure data transmission module to ensure data integrity and security during multi-source data fusion and real-time data transmission, and prevent data tampering and unauthorized access;

[0013] S7. Integrated predictive maintenance module, based on real-time monitoring data and historical maintenance records, predicts potential failures of ground support equipment, schedules maintenance tasks in advance, and reduces the impact of equipment failures on ground support tasks;

[0014] S8. Through the user behavior analysis module, analyze the operating habits and task execution efficiency of ground staff, optimize the task allocation strategy, and improve the overall efficiency of human-machine collaboration;

[0015] S9. Adopt operator training modules based on virtual reality (VR) and augmented reality (AR) technologies to provide ground staff with an immersive training environment to improve their proficiency in operating the automatic dispatch system and their emergency response capabilities;

[0016] S10. Use big data analysis and machine learning technology to conduct in-depth mining of historical task execution data, optimize task allocation models and resource allocation strategies, and continuously improve the overall performance and service quality of the system.

[0017] The multi-source data fusion in step S1 includes time series data, meteorological image data and air traffic control instruction text data. It adopts a multimodal data fusion algorithm based on deep learning for deep integration, and uses an adaptive weight allocation mechanism to optimize the fusion ratio of different data sources.

[0018] The situational awareness module in step S2 adopts a multimodal data fusion algorithm based on convolutional neural network (CNN) and long short-term memory network (LSTM), and uses the Internet of Things (IoT) technology and sensor networks to acquire and integrate relevant data in real time to accurately perceive the current operating status of the airport and changes in the external environment.

[0019] The improved multi-objective optimization algorithm in step S3 combines the global search capability of the genetic algorithm with the fast convergence characteristics of the particle swarm optimization algorithm, and introduces a dynamic weight adjustment mechanism to improve the optimization calculation efficiency and solution accuracy, and adapt to the complex and changeable ground support mission requirements.

[0020] The improved path planning algorithm in step S4 combines the heuristic search of the multi-level A* search algorithm with the strategy optimization of the deep reinforcement learning method. It can plan and adjust the path in real time in a complex airport environment, dynamically avoid static and dynamic obstacles, and improve the efficiency and accuracy of path planning through hierarchical path segmentation optimization.

[0021] The energy consumption optimization in step S4 further includes real-time monitoring of the battery status of the electric vehicle, dynamically adjusting the path planning using an energy management algorithm based on a predictive model to minimize energy consumption and charging times, and ensuring that the vehicle has enough energy to return to the base or reach the next charging point before completing the mission.

[0022] The improved rapid response and resource allocation mechanism in step S5 includes:

[0023] a. A hierarchical response system that divides ground support tasks into different levels based on flight delay time, passenger demand, and weather conditions, and introduces a priority-based dynamic resource allocation algorithm;

[0024] b. Real-time monitoring and early warning platform, which uses IoT technology and sensor networks to monitor the status of all ground support vehicles and service facilities in real time, and identifies potential risks through early warning models based on machine learning;

[0025] c. Standardized operating procedures (SOPs), which set detailed operating requirements, time limits, and quality standards for each type of ground support mission, and ensure the strict implementation of SOPs through an automated review system based on knowledge graphs;

[0026] d. Multidisciplinary collaborative teams (MDTs), composed of multiple related departments, are responsible for handling major events or complex tasks, and optimize team collaboration efficiency through a task allocation system based on collaborative filtering;

[0027] e. Automated and intelligent auxiliary tools, including intelligent dispatch assistant software and wearable devices based on augmented reality (AR) technology, provide real-time guidance and mission status display for ground crew.

[0028] The self-learning algorithm in step S5 is selected from a reinforcement learning algorithm based on deep deterministic policy gradient (DDPG), which can continuously optimize the scheduling strategy and path planning algorithm according to historical and real-time data, thereby improving the intelligence level and response capability of the system.

[0029] The comprehensive decision support system integrates information from modules such as intelligent prediction, resource optimization, path planning, and real-time adjustment, adopts a unified decision-making framework based on graph neural network (GNN), and uses big data analysis and machine learning technology to improve the overall coordination of emergency response and the accuracy of decision-making.

[0030] The automatic dispatch system further includes the formulation of standardized operating procedures (SOPs) and ground crew training modules to ensure that various ground support tasks are efficiently carried out in accordance with predetermined standards. It also provides an immersive training environment for ground crew through operator training modules based on virtual reality (VR) and augmented reality (AR) technologies to improve their operational proficiency and emergency response capabilities of the automatic dispatch system.

[0031] In summary, this application has the following beneficial effects:

[0032] 1. By using a time series prediction model combined with a dynamic causal relationship identification module based on a Bayesian network, we deeply integrated and analyzed multi-source data such as historical flight data, weather forecasts, and air traffic control instructions, significantly improving the accuracy of flight arrival time predictions. Accurate prediction results provide a reliable data basis for subsequent task allocation, making task allocation more accurate and efficient, and reducing resource waste and task delays caused by prediction errors.

[0033] 2. Through the situational awareness module based on convolutional neural network (CNN) and long short-term memory network (LSTM), the airport's operating status and external environment changes can be perceived in real time. Combined with real-time monitoring data, the system can dynamically adjust the priority of tasks and perform intelligent task allocation to ensure that key tasks are given priority, thereby improving overall work efficiency and service quality.

[0034] 3. Improve the multi-objective optimization algorithm, combine the advantages of genetic algorithm and particle swarm optimization algorithm, and introduce dynamic weight adjustment mechanism and real-time feedback loop to achieve adaptive optimization configuration of resources. This algorithm can efficiently allocate limited resources to meet the complex and changing needs of ground support tasks. At the same time, the improved path planning algorithm combines multi-level A* search and deep reinforcement learning methods to plan and adjust the optimal path of the execution unit in real time, dynamically avoid obstacles, and optimize the energy consumption of electric vehicles through energy management algorithms. While ensuring efficient completion of tasks, it reduces energy consumption and charging times, and extends the service life of the vehicle.

[0035] 4. By introducing an improved rapid response and resource allocation mechanism, a hierarchical response system, a real-time monitoring and early warning platform, standardized operating procedures (SOPs), multidisciplinary collaborative teams (MDTs), and automated and intelligent auxiliary tools have been established, significantly improving the system's response speed in emergencies and the rationality of resource allocation. The self-learning algorithm based on deep deterministic policy gradient (DDPG) and the comprehensive decision support system based on graph neural network (GNN) enable the system to continuously optimize scheduling strategies and path planning based on historical and real-time data, improving the accuracy of decision-making and overall coordination.

[0036] 5. The blockchain-based secure data transmission module ensures data integrity and security during multi-source data fusion and real-time data transmission, prevents data tampering and unauthorized access, and ensures the reliability of system operation. In addition, the integrated predictive maintenance module can predict potential equipment failures in advance based on real-time monitoring data and historical maintenance records, and schedule maintenance tasks in a timely manner, reducing the impact of equipment failures on ground support tasks and improving equipment reliability and the overall stability of the system.

[0037] 6. Through the user behavior analysis module, the operating habits and task execution efficiency of ground staff are deeply analyzed, the task allocation strategy is optimized, and the overall efficiency of human-machine collaboration is improved. At the same time, the operator training module based on virtual reality (VR) and augmented reality (AR) technology is adopted to provide ground staff with an immersive training environment, improve their operational proficiency and emergency response capabilities of the automatic dispatch system, ensure that ground staff can efficiently and accurately perform various ground support tasks, and further improve user experience and service quality.

[0038] 7. Through big data analysis and machine learning technology, we conduct in-depth mining and analysis of historical task execution data, continuously optimize task allocation models and resource allocation strategies, ensure that the system can continuously adapt to changing airport operation needs, and continuously improve overall performance and service quality. The system's self-learning ability and feedback optimization mechanism enable it to have the ability to self-improve and self-optimize, and maintain efficient and intelligent operation in the long run. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The workflow for this application Figure 1 ;

[0040] Figure 2 The workflow for this application Figure 2 . DETAILED DESCRIPTION

[0041] In order to make the objectives, technical solutions and beneficial effects of the present invention more clear, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings to facilitate understanding by technicians.

[0042] Embodiment 1:

[0043] like Figure 1 to Figure 2 As shown, this embodiment introduces in detail an automatic dispatching method based on civil aviation airport aircraft ground support, and the core automatic dispatching process, covering key technical steps such as time series prediction, multi-source data fusion, causal inference, situational awareness, multi-objective optimization, and path planning. Through this method, efficient and intelligent allocation and execution of civil aviation airport ground support tasks can be achieved, ensuring smooth and efficient airport operations.

[0044] Step S1: Multi-source data fusion and flight arrival time prediction

[0045] In the initial stage of automatic dispatching of ground support tasks, the system first needs to accurately predict the arrival time of the upcoming flights. To this end, a time series prediction model is used to deeply integrate multi-source data such as historical flight data, weather forecasts, and air traffic control instructions. Specifically, multi-source data fusion includes time series data, meteorological image data, and air traffic control instruction text data, and a multimodal data fusion algorithm based on deep learning is used for deep integration. In order to further improve the accuracy of the prediction, the system introduces a dynamic causal relationship identification module based on the Bayesian network to identify the causal relationship between different data sources in real time, and uses an adaptive weight allocation mechanism to optimize the fusion ratio of different data sources. In this way, the system can accurately predict the arrival time of flights and provide a reliable data basis for subsequent task allocation.

[0046] In the initial stage of automatic dispatching of ground support tasks, the system first needs to accurately predict the arrival time of the upcoming flights. To this end, a time series prediction model is used to deeply integrate multi-source data such as historical flight data, weather forecasts, and air traffic control instructions.

[0047] Multi-source data fusion

[0048] Multi-source data fusion includes time series data, meteorological image data and air traffic control instruction text data. Settings:

[0049] The time series data set is T = {T1, T2, ..., T n}, where T i Represents the historical data of the i-th dirty shift.

[0050] The meteorological image dataset is I = {I1, I2, ..., I m}, where I j Represents the weather image of the jth day.

[0051] The air traffic control instruction text dataset is C = {C1, C2, ..., C k}, where C l Represents the air traffic instructions for flight l.

[0052] A multimodal data fusion algorithm based on deep learning is used to deeply integrate different types of data. The specific fusion process is as follows:

[0053] F = Fusion (T, I, C)

[0054] Among them, Fusion(·) represents the multimodal data fusion function, which generates the fused feature vector F.

[0055] Dynamic causal relationship identification based on Bayesian network

[0056] In order to further improve the accuracy of prediction, the system introduces a dynamic causal relationship identification module based on Bayesian network to identify the causal relationship between different data sources in real time. Bayesian network is a directed acyclic graph (DAG) used to represent the conditional dependency relationship between variables. Its structure can be expressed as:

[0057] G=(V,E)

[0058] Among them, V represents the variable set, E represents the directed edge set, and represents the causal relationship between variables.

[0059] Through the Bayesian network, the conditional probability distribution P(X i ∣Parents(X i )), where Parents(X i ) represents node X i The dynamic causal relationship identification process includes:

[0060] Structural learning: Based on historical data, the structure of the Bayesian network is learned through algorithms (such as greedy search, genetic algorithm, etc.).

[0061] Parameter learning: After determining the network structure, the conditional probability distribution of each node is learned using maximum likelihood estimation or Bayesian estimation methods.

[0062] Ultimately, Bayesian networks are used to identify causal relationships in multi-source data, thereby improving the interpretability and accuracy of predictive models.

[0063] Adaptive weight allocation mechanism

[0064] In order to optimize the fusion ratio of different data sources, an adaptive weight allocation mechanism is introduced. The weight of each modal data in the fused feature vector F is set to w = [w T ,w I ,w C ],in:

[0065] w T +w I +w C =1

[0066] The weight distribution mechanism dynamically adjusts the weights through the following formula:

[0067]

[0068] Among them, α m It is a learnable parameter that is optimized and adjusted according to the prediction error through the back propagation algorithm.

[0069] Flight arrival time prediction model

[0070] After completing the fusion of multi-source data and the identification of causal relationships, the system uses the time series prediction model to process the fused feature vectors and predict the flight arrival time. The prediction model is set to the long short-term memory network (LSTM) or Transformer, and the prediction process can be expressed as:

[0071]

[0072] in, is the predicted flight arrival time, and θ is the model parameter, which is optimized through the training process.

[0073] Working process

[0074] Data collection and fusion: The system collects historical flight data, weather forecasts, air traffic control instructions and other multi-source data in real time through the Internet of Things (IoT) technology and sensor networks. Using a multimodal data fusion algorithm based on deep learning, the time series data, meteorological image data and air traffic control instruction text data are deeply integrated to generate a fused feature vector F.

[0075] Causal relationship identification: Through the dynamic causal relationship identification module based on the Bayesian network, the causal relationship map between multi-source data is identified and updated in real time to ensure the relevance of the fused data and the accuracy of the prediction model.

[0076] Weight optimization: The adaptive weight allocation mechanism dynamically adjusts the weight w of each modal data according to real-time data and causal analysis results, optimizes the data fusion ratio, and improves the performance of the prediction model.

[0077] Time series prediction: Use LSTM or Transformer model to process the fused feature vector F and predict the flight arrival time Provide a reliable data basis for subsequent task allocation.

[0078] Step S2: Situational awareness and dynamic task allocation

[0079] Based on the flight arrival time prediction results of step S1, the system combines real-time monitoring data, including flight dynamics, vehicle location, equipment status, etc., and uses a situational awareness module based on a convolutional neural network (CNN) and a long short-term memory network (LSTM) to accurately perceive the current airport's operating status and external environmental changes. Specifically, the situational awareness module uses a multimodal data fusion algorithm, Internet of Things (IoT) technology and sensor networks to acquire and integrate relevant data in real time, thereby dynamically adjusting the priority of tasks and performing real-time task allocation. In this way, the system can flexibly adjust resource allocation according to actual conditions, ensure that key tasks are given priority, and improve overall work efficiency.

[0080] Real-time data collection and preprocessing

[0081] The system uses the Internet of Things (IoT) technology and sensor networks to collect the following data in real time:

[0082] Flight dynamic data f ={d f1 , d f2 , ..., d fn}

[0083] Vehicle location data D v ={d v1 , d v2 , ..., d vm}

[0084] Equipment status data D e ={d e1 , d e2 , ..., d ek}

[0085] The data are first preprocessed, including steps such as data cleaning and normalization, to ensure data quality and consistency.

[0086] Multimodal data fusion

[0087] The context awareness module uses a multimodal data fusion algorithm to integrate different types of data into a unified feature representation:

[0088] F s =Fusion(D f ,D v ,D e )

[0089] Where Fusion(·) represents the multimodal data fusion function, generating the fused feature vector F s .

[0090] Convolutional Neural Network (CNN) Feature Extraction

[0091] For flight dynamic data and equipment status data, CNN is used for feature extraction:

[0092] F cnn =CNN(D f , D e θ cnn )

[0093] Among them, θ cnn is the parameter of CNN, F cnn is the extracted feature vector.

[0094] Long Short-Term Memory Network (LSTM) Sequence Modeling

[0095] For vehicle location data, LSTM is used for sequence modeling:

[0096] F lstm =LSTM(D v θ lstm )

[0097] Among them, θ lstm is the parameter of LSTM, F lstm is the extracted time series feature vector.

[0098] Situational feature fusion and perception

[0099] The feature vectors extracted by CNN and LSTM are combined to generate a comprehensive context feature vector:

[0100] F context =Concat(F cnn , F lstm )

[0101] Among them, Concat(·) represents the concatenation operation of feature vectors.

[0102] Task priority adjustment

[0103] Based on the comprehensive context features, the system calculates the priority score of each task through a fully connected layer:

[0104] p i =σ(W·F context +b)

[0105] Among them, p i is the priority score of the i-th task, W and b are the weight and bias of the fully connected layer, and σ(·) is the activation function (such as the Sigmoid function).

[0106] Dynamic task allocation

[0107] Based on the calculated task priority scores, the system uses a sorting and allocation algorithm to assign tasks to the most appropriate resources (such as guide vehicles, personnel, equipment):

[0108]

[0109] Among them, T i represents the i-th task, R j represents the j-th resource, and Compatibility(·) represents the compatibility scoring function between tasks and resources.

[0110] Step S3: Multi-objective optimization and resource allocation

[0111] After the task allocation is completed, the system needs to optimally configure the available resources to meet the needs of different tasks. To this end, an improved multi-objective optimization algorithm is adopted, combining the global search capability of the genetic algorithm with the fast convergence characteristics of the particle swarm optimization algorithm, and introducing a dynamic weight adjustment mechanism and a real-time feedback loop. The optimization algorithm has self-learning capabilities and can continuously optimize the decision logic based on historical data and real-time feedback. By comprehensively considering factors such as the urgency of the task and the type of equipment required, the system realizes adaptive optimization of resources to ensure maximum resource utilization and efficient task execution.

[0112] After the task allocation is completed, the system needs to optimally configure the available resources to meet the needs of different tasks. To this end, an improved multi-objective optimization algorithm is adopted, combining the global search capability of the genetic algorithm (GA) with the fast convergence characteristics of the particle swarm optimization algorithm (PSO), and introducing a dynamic weight adjustment mechanism and a real-time feedback loop. The optimization algorithm has self-learning capabilities and can continuously optimize the decision logic based on historical data and real-time feedback. By comprehensively considering factors such as the urgency of the task and the type of equipment required, the system realizes adaptive optimization of resources to ensure maximum resource utilization and efficient task execution.

[0113] Multi-objective optimization problems usually involve multiple conflicting objective functions. In the present invention, the following two objectives are mainly considered:

[0114] The mathematical expression of minimizing resource usage cost C and maximizing task completion efficiency E is as follows:

[0115]

[0116] in:

[0117] N is the total number of resources, and M is the total number of tasks.

[0118] ·c i is the usage cost of the i-th resource.

[0119] ·x i is the allocation status of resource i (0 means unallocated, 1 means allocated).

[0120] ·e j is the completion efficiency of the jth task.

[0121] ·y j is the completion status of task j (0 means unfinished, 1 means completed).

[0122] Combination of Genetic Algorithm and Particle Swarm Optimization Algorithm

[0123] In order to combine the global search capability of GA with the fast convergence characteristics of PSO, a hybrid optimization algorithm (Hybrid GA-PSO) is designed. The specific steps are as follows:

[0124] Initialize the population: Generate an initial population P = {p1, p2, ..., p G}, where each individual p g Represents a resource allocation scheme.

[0125] ·Evaluate fitness: Calculate the fitness value F(p g ), based on the objective functions C and E.

[0126] Selection operation: Roulette wheel selection or tournament selection is used to select individuals with higher fitness from the population.

[0127] Crossover and mutation: Perform crossover and mutation operations on the selected individuals to generate a new generation of population.

[0128] Particle swarm optimization: The new generation population generated by GA is used as the initial particle swarm of PSO, and the resource allocation is further optimized by updating the speed and position of the particles.

[0129]

[0130] in:

[0131] · is the velocity of particle i in the kth generation.

[0132] · is the position of particle i in the kth generation.

[0133] w is the inertia weight.

[0134] c1, c2 are acceleration constants.

[0135] r1, r2 are random numbers.

[0136] ·pbest i is the best position of particle i so far.

[0137] gbest is the global best position.

[0138] Dynamic weight adjustment mechanism

[0139] In order to adapt to the dynamic changes of different tasks and resources, the system introduces a dynamic weight adjustment mechanism. The weights α and β are dynamically adjusted to balance the cost and efficiency goals:

[0140] α(t+1)=α(t)+Δα

[0141] β(t+1)=β(t)-Δβ

[0142] Among them, Δα and Δβ are adjusted according to real-time feedback to ensure the target balance during the optimization process.

[0143] Real-time feedback loop

[0144] The system monitors the execution of tasks in real time, feeds the actual execution data back to the optimization algorithm, and adjusts the optimization strategy in real time. The specific steps include:

[0145] Monitor execution data: collect real-time data of task execution exec .

[0146] Update optimization parameters: Adjust the optimization parameters θ based on the execution data.

[0147] Re-optimize resource configuration: Re-run the optimization algorithm based on the latest parameters and data to update the resource allocation plan.

[0148] θ new =θ old +Δθ

[0149] Among them, Δθ is calculated through feedback data and is used to adjust the operating parameters of the optimization algorithm.

[0150] Step S4: Path planning and energy consumption optimization

[0151] In order to ensure that each execution unit can complete the task efficiently, the system uses an improved path planning algorithm to plan the optimal path for each execution unit. The path planning algorithm is based on a model that combines multi-level A* search with deep reinforcement learning. It can plan and adjust the path in real time in a complex airport environment and dynamically avoid static and dynamic obstacles. In addition, combined with an energy management algorithm based on a predictive model, the system optimizes the energy consumption of electric vehicles, monitors the battery status in real time, and dynamically adjusts the path planning to minimize energy consumption and charging times, ensuring that the vehicle has enough energy to return to the base or reach the next charging point before completing the mission.

[0152] After the task allocation is completed, the system needs to optimally configure the available resources to meet the needs of different tasks. To this end, an improved multi-objective optimization algorithm is adopted, combining the global search capability of the genetic algorithm (GA) with the fast convergence characteristics of the particle swarm optimization algorithm (PSO), and introducing a dynamic weight adjustment mechanism and a real-time feedback loop. The optimization algorithm has self-learning capabilities and can continuously optimize the decision logic based on historical data and real-time feedback. By comprehensively considering factors such as the urgency of the task and the type of equipment required, the system realizes adaptive optimization of resources to ensure maximum resource utilization and efficient task execution.

[0153] Multi-objective optimization problems usually involve multiple conflicting objective functions. In the present invention, the following two objectives are mainly considered:

[0154] The mathematical expression of minimizing resource usage cost C and maximizing task completion efficiency E is as follows:

[0155]

[0156] in:

[0157] N is the total number of resources, and M is the total number of tasks.

[0158] ·c i is the usage cost of the i-th resource.

[0159] ·x i is the allocation status of resource i (0 means unallocated, 1 means allocated).

[0160] ·e j is the completion efficiency of the jth task.

[0161] ·y j is the completion status of task j (0 means unfinished, 1 means completed).

[0162] Combination of Genetic Algorithm and Particle Swarm Optimization Algorithm

[0163] In order to combine the global search capability of GA with the fast convergence characteristics of PSO, a hybrid optimization algorithm (Hybrid GA-PSO) is designed. The specific steps are as follows:

[0164] Initialize the population: Generate an initial population P = {p1, p2, ..., p G}, where each individual p g Represents a resource allocation scheme.

[0165] ·Evaluate fitness: Calculate the fitness value F(p g), based on the objective functions C and E.

[0166] Selection operation: Roulette wheel selection or tournament selection is used to select individuals with higher fitness from the population.

[0167] Crossover and mutation: Perform crossover and mutation operations on the selected individuals to generate a new generation of population.

[0168] Particle swarm optimization: The new generation population generated by GA is used as the initial particle swarm of PSO, and the resource allocation is further optimized by updating the speed and position of the particles.

[0169] The particle swarm optimization update formula is as follows:

[0170]

[0171] in:

[0172] · is the velocity of particle i in the kth generation.

[0173] · is the position of particle i in the kth generation.

[0174] w is the inertia weight.

[0175] c1, c2 are acceleration constants.

[0176] r1, r2 are random numbers.

[0177] ·pbest i is the best position of particle i so far.

[0178] gbest is the global best position.

[0179] Dynamic weight adjustment mechanism

[0180] In order to adapt to the dynamic changes of different tasks and resources, the system introduces a dynamic weight adjustment mechanism. The weights α and β are dynamically adjusted to balance the cost and efficiency goals:

[0181] α(t+1)=α(t)+Δα

[0182] β(t+1)=β(t)-Δβ

[0183] Among them, Δα and AP are adjusted according to real-time feedback to ensure the target balance in the optimization process.

[0184] Real-time feedback loop

[0185] The system monitors the execution of tasks in real time, feeds the actual execution data back to the optimization algorithm, and adjusts the optimization strategy in real time. The specific steps include:

[0186] Monitor execution data: collect real-time data of task execution exec .

[0187] Update optimization parameters: Adjust the optimization parameters θ based on the execution data.

[0188] Re-optimize resource configuration: Re-run the optimization algorithm based on the latest parameters and data to update the resource allocation plan.

[0189] θ new =θ old +Δθ

[0190] Among them, Δθ is calculated through feedback data and is used to adjust the operating parameters of the optimization algorithm.

[0191] Step S5: Real-time monitoring and feedback optimization

[0192] During the task execution process, the system establishes a feedback loop through a real-time monitoring and feedback mechanism, and feeds back the real-time monitoring data to the system's learning module. Using a self-learning algorithm based on Deep Deterministic Policy Gradient (DDPG) and a comprehensive decision support system based on Graph Neural Network (GNN), the system can dynamically adjust task allocation and path planning to ensure the stability of the overall progress in emergencies. At the same time, the system responds quickly to emergencies and reasonably allocates resources through an improved rapid response and resource allocation mechanism, including a priority-based dynamic resource allocation algorithm, a machine learning-based early warning model, an automated review system based on knowledge graphs, a collaborative filtering-based task allocation system, and an intelligent scheduling assistant based on augmented reality (AR) technology, thereby improving the overall response speed and decision-making accuracy of the system.

[0193] Create a feedback loop

[0194] The system collects real-time data by monitoring the execution of tasks in real time. monitor , and feed it back into the learning module:

[0195] D feedback =D monitor

[0196] Self-learning algorithm (DDPG)

[0197] The DDPG algorithm is used to optimize scheduling strategies and path planning. DDPG consists of an actor network μ(s|θ μ ) and a critic network

[0198] Q(s,a|θQ ), wherein:

[0199]

[0200] Among them, s t is the state, a t For action, r t is the reward, γ is the discount factor, is the noise, θ μ and θ Q are the parameters of the actor and critic networks, respectively.

[0201] General Decision Support System (GNN)

[0202] The GNN-based decision support system processes multi-source data through a graph structure G = (V, E), where nodes V represent tasks and resources, and edges E represent the relationship between them:

[0203] H (l+1) =σ(D -1 / 2 AD -1 / 2 H (l) w (l) )

[0204] Among them, A is the adjacency matrix, D is the degree matrix, and H (l) is the node feature of the lth layer, W (l) is the weight matrix of the lth layer, and σ is the activation function.

[0205] Dynamic resource allocation algorithm

[0206] Priority-based dynamic resource allocation optimizes the objective function:

[0207]

[0208] Among them, p i is the priority of task i, x i Assign a decision variable (0 or 1) to a resource.

[0209] Early warning model

[0210] The machine learning-based early warning model uses classification algorithms to predict potential risks:

[0211]

[0212] in The risk prediction results.

[0213] Automated review system

[0214] The automated audit system based on knowledge graph verifies the compliance of task assignment with operating procedures:

[0215]

[0216] Step S6: Secure Data Transmission

[0217] In order to ensure the integrity and security of data during multi-source data fusion and real-time data transmission, the system uses a secure data transmission module based on blockchain. This module uses the immutability and distributed storage characteristics of blockchain technology to prevent data from being tampered with and unauthorized access during transmission, ensuring the security and reliability of system data.

[0218] Blockchain network construction

[0219] Building a private blockchain network Where N represents the node set and E represents the connection between nodes.

[0220]

[0221] Data Sharding and Hashing

[0222] Divide the multi-source data into D = {D1, D2, ..., D n}, and hash each data shard:

[0223] H(D i )=Hash(D i )

[0224] Among them, H(D i ) is the data shard D i The hash value of .

[0225] Block generation and chain linking

[0226] The hash value H(D i ) are packaged into block B in chronological order k And ensure the immutability of data through chain links:

[0227] B k ={H(D1),H(D2),...,H(D k ),H(B k-1 )}

[0228] Among them, H(B k-1 ) is the hash value of the previous block.

[0229] Step S7: Predictive Maintenance

[0230] The system integrates a predictive maintenance module to predict potential failures of ground support equipment based on real-time monitoring data and historical maintenance records. By scheduling maintenance tasks in advance, the impact of equipment failures on ground support tasks is reduced, ensuring efficient operation of equipment and continuity of airport ground services.

[0231] Data collection and preprocessing

[0232] Collect real-time monitoring data of ground support equipment real ={d real1 , d real2 , ..., d realn} and historical maintenance records D hist ={d hist1 , d hist2 , ..., d histm}, and perform data cleaning and normalization:

[0233] D clean =Preprocess(D real , D hist )

[0234] Failure prediction model

[0235] Construct a fault prediction model PredictFault (D clean θ pf ), predict the probability of equipment failure P(F j ):

[0236] P(F j )=PredictFault(D clean，j θ pf )

[0237] Among them, F j represents the failure event of the jth device, θ pf is the model parameter.

[0238] Maintenance task scheduling

[0239] According to the fault prediction results, the maintenance task M is scheduled in advance j :

[0240]

[0241] Among them, τ is the failure probability threshold.

[0242] Optimize maintenance resource allocation

[0243] Use optimization algorithms to allocate maintenance resources and minimize maintenance costs C m and maximize equipment availability e :

[0244]

[0245] Among them, c j is the cost of the jth maintenance task, m j is the allocation status of the maintenance task (0 or 1), u j Increase the value of equipment availability.

[0246] Step S8: User behavior analysis and optimization

[0247] Through the user behavior analysis module, the system analyzes the operating habits and task execution efficiency of ground staff, optimizes task allocation strategies, and improves the overall efficiency of human-machine collaboration. This module uses big data analysis and machine learning technology to mine user behavior patterns and provide a more accurate basis for task allocation.

[0248] Behavioral data collection

[0249] Collect operational data from ground crew user ={d u1 , d u2 , ..., d un}, including task completion time, operation steps, resource usage and other information:

[0250] D user ={d u1 , d u2 , ..., d un}

[0251] Feature extraction and representation

[0252] Extract features from the collected user behavior data to form a user behavior feature vector F user :

[0253] F user =FeatureExtraction(D user )

[0254] Behavioral pattern recognition

[0255] Use clustering algorithms (such as K-Means) to identify the operating habits and behavior patterns of ground staff:

[0256] C=Cluster(F user ; K)

[0257] Among them, C is the clustering result and K is the number of clusters.

[0258] Task allocation optimization

[0259] Based on the identified behavior patterns, the task allocation strategy is optimized and tasks are allocated through a weighted scoring mechanism:

[0260] Score(T i , U j )=α·Efficiency(U j )+β·Preference(U j )

[0261] Among them, T i For the mission, U j is the ground crew, α and β are weight coefficients.

[0262] Machine Learning Model Application

[0263] Apply supervised learning models (such as random forests) to predict the ground crew’s fitness for the task:

[0264]

[0265] in, For ground staff j For task T i The fitness score, θ ml is the model parameter.

[0266] Step S9: Operator Training

[0267] The system uses an operator training module based on virtual reality (VR) and augmented reality (AR) technology to provide an immersive training environment for ground staff. Through virtual scene simulation and real-time guidance, the ground staff's operational proficiency and emergency response capabilities for the automatic dispatch system are improved, ensuring that they can efficiently deal with various complex situations in actual operations.

[0268] Step S10: Continuous system optimization

[0269] Using big data analysis and machine learning technology, the system conducts in-depth mining of historical mission execution data, optimizes the task allocation model and resource allocation strategy, and continuously improves the overall performance and service quality of the system. Through continuous data accumulation and analysis, the system can improve itself and adapt to the ever-changing needs of airport operations.

[0270] Data Collection and Storage

[0271] The system continuously collects historical task execution data D history ={D1, D2, ..., D n}, including task type, execution time, resource usage, etc., and stored in the big data platform:

[0272] D history ={D1,D2,...,Dn}

[0273] Data preprocessing and feature engineering

[0274] Clean and normalize historical data and extract key features F history :

[0275] F history =FeatureExtraction(D history )

[0276] Machine Learning Model Training

[0277] Use supervised learning algorithms (such as random forests and gradient boosting trees) to train the task allocation model TA and resource configuration model RC :

[0278] Model TA =Train(F history θ TA )

[0279] Model RC =Train(F history θ RC )

[0280] Among them, θ TA and θ RC They are the parameters of the task allocation and resource configuration models respectively.

[0281] Model evaluation and optimization

[0282] Evaluate model performance through cross-validation and performance indicators (such as accuracy, F1-score), and perform parameter tuning:

[0283]

[0284] Working process

[0285] Data collection and fusion: The system collects historical flight data, weather forecasts, air traffic control instructions and other multi-source data in real time through the Internet of Things (IoT) technology and sensor networks. The system uses a multimodal data fusion algorithm based on deep learning and combines it with a dynamic causal relationship recognition module based on a Bayesian network to deeply integrate different data sources, optimize the data fusion ratio, and ensure the comprehensiveness and accuracy of the data.

[0286] Flight arrival time prediction: Based on the integrated multi-source data, the system uses a time series prediction model combined with causal inference to accurately predict the arrival time of flights and provide basic data for subsequent task allocation.

[0287] Situational awareness and task allocation: Combining prediction results and real-time monitoring data, the situational awareness module uses the multimodal data fusion algorithm of CNN and LSTM to accurately perceive the current airport operation status and external environment changes, dynamically adjust task priorities, and allocate tasks to ensure that key tasks are handled first.

[0288] Resource optimization configuration: Through the improved multi-objective optimization algorithm, the system adaptively optimizes resource configuration according to the task urgency and equipment requirements, thereby improving resource utilization efficiency and task execution accuracy.

[0289] Path planning and energy management: An improved path planning algorithm is used to plan the optimal path for each execution unit, and real-time adjustments are made to adapt to the dynamically changing airport environment. At the same time, the energy management algorithm is combined to optimize the energy consumption of electric vehicles to ensure that when the mission is completed, the vehicle has enough energy to return to the base or reach the next charging point.

[0290] Real-time monitoring and feedback optimization: The system uses the real-time monitoring and feedback mechanism, the DDPG self-learning algorithm and the GNN comprehensive decision support system to dynamically adjust task allocation and path planning to ensure that the overall progress of the system is not affected in emergencies, and through the improved rapid response and resource allocation mechanism, it can respond quickly and allocate resources reasonably.

[0291] Data security and maintenance management: Blockchain technology is used to ensure the security of data transmission, and a predictive maintenance module is integrated to predict potential equipment failures in advance, schedule maintenance tasks, and reduce the impact of equipment failures on ground support.

[0292] User behavior optimization and training: Through the user behavior analysis module, the task allocation strategy is optimized to improve the efficiency of human-machine collaboration; the operator training module using VR and AR technology is used to improve the operational proficiency and emergency response capabilities of ground staff.

[0293] Continuous system optimization: Utilize big data analysis and machine learning technology to conduct in-depth mining of historical task execution data, optimize task allocation models and resource allocation strategies, and continuously improve system performance and service quality.

[0294] Multi-source data fusion and causal relationship identification based on Bayesian networks improve the accuracy of flight arrival time prediction and provide a reliable data basis for subsequent task allocation.

[0295] The situational awareness module based on CNN and LSTM can accurately perceive the real-time operating status of the airport and changes in the external environment, dynamically adjust task priorities, and ensure that key tasks are given priority.

[0296] The improved multi-objective optimization algorithm combines the advantages of genetic algorithm and particle swarm optimization algorithm, improves the computational efficiency of resource allocation and the accuracy of the solution, and adapts to the complex and changeable needs of ground support missions.

[0297] The path planning algorithm that combines multi-level A* search with deep reinforcement learning can adjust the path in real time to avoid obstacles, and optimize the energy consumption of electric vehicles through energy management algorithms to ensure efficient completion of tasks.

[0298] Through the DDPG self-learning algorithm and GNN comprehensive decision support system, the system can dynamically adjust task allocation and path planning based on real-time data to ensure that the overall progress of the system is not affected in emergency situations and improve emergency response capabilities.

[0299] The blockchain-based secure data transmission module ensures the integrity and security of data transmission; the predictive maintenance module predicts equipment failures in advance, reduces the impact of equipment failures on ground support missions, and improves system reliability.

[0300] The user behavior analysis module optimizes the task allocation strategy and improves the efficiency of human-machine collaboration; the operator training module based on VR and AR technology improves the operational proficiency and emergency response capabilities of ground staff, ensuring the efficient operation of the system.

[0301] Through big data analysis and machine learning technology, the system can continuously optimize task allocation models and resource allocation strategies, improve overall performance and service quality, and ensure that the system can adapt to the ever-changing needs of airport operations.

[0302] In summary, this embodiment provides a comprehensive, intelligent and efficient automatic dispatching method for civil aviation airport aircraft ground support, which significantly improves the overall operational efficiency, safety and emergency response capabilities of airport ground support services, and meets the efficient and intelligent ground support needs of modern civil aviation airports.

[0303] Embodiment 2:

[0304] like Figure 1 to Figure 2 As shown, this embodiment introduces in detail a method for further enhancing the security and maintenance management functions of the system based on Embodiment 1. By introducing an improved rapid response and resource allocation mechanism, a self-learning algorithm, a comprehensive decision support system, and a standardized operating procedure and ground crew training module, the system can respond quickly to emergencies, allocate resources reasonably, and ensure the reliability of equipment and the efficiency of operators.

[0305] Step S5: Improve rapid response and resource allocation mechanisms

[0306] During the execution of ground support tasks, unexpected events and emergencies may occur at any time. In order to ensure that the system can respond quickly to these changes, Example 2 introduces an improved rapid response and resource allocation mechanism, which specifically includes the following sub-steps:

[0307] a. Hierarchical response system

[0308] The system divides ground support tasks into different levels (such as emergency, high priority, and regular) based on factors such as flight delay time, passenger demand, and weather conditions. Each level corresponds to a different resource allocation strategy to ensure that key tasks are handled first when resources are limited. By introducing a priority-based dynamic resource allocation algorithm, the system can automatically adjust resource allocation according to the task level and improve resource utilization efficiency.

[0309] b. Real-time monitoring and early warning platform

[0310] Using Internet of Things (IoT) technology and sensor networks, the system monitors the status of all ground support vehicles and service facilities in real time, including location, operating status, equipment health, etc. Through machine learning-based early warning models, the system can analyze monitoring data, identify potential risks (such as vehicle failures, equipment abnormalities, traffic congestion, etc.), and issue early warnings in a timely manner to prevent problems from occurring or mitigate their impact.

[0311] c. Standardized Operating Procedures (SOPs)

[0312] Detailed operational requirements, time limits and quality standards are formulated for each type of ground support mission to ensure that the mission is carried out efficiently according to the predetermined standards. Through the automated review system based on the knowledge graph, the system can monitor and review the execution of operating procedures in real time, ensure that all links strictly abide by SOPs, and improve the standardization and consistency of mission execution.

[0313] d. Multidisciplinary Teams (MDTs)

[0314] When dealing with major events or complex tasks, the system will form a multidisciplinary collaborative team (MDTs) consisting of multiple relevant departments. Through the task allocation system based on collaborative filtering, the system can optimize the collaborative efficiency of team members, ensure information sharing and collaborative work between departments, and thus solve emergencies quickly and efficiently.

[0315] e.Automation and intelligent auxiliary tools

[0316] The system is equipped with intelligent dispatch assistant software and wearable devices based on augmented reality (AR) technology to provide real-time guidance and task status display for ground staff. The intelligent dispatch assistant can automatically recommend the optimal resource allocation plan based on the current task and environmental conditions; the wearable devices provide ground staff with real-time task guidance and operation feedback to improve work efficiency and accuracy.

[0317] Step S8: Application of self-learning algorithm

[0318] In order to improve the intelligence level and response capability of the system, Example 2 introduces a reinforcement learning algorithm based on deep deterministic policy gradient (DDPG) in step S5. The algorithm can continuously optimize the scheduling strategy and path planning algorithm based on historical data and real-time data. Specifically, the system can adapt to different operating environments and emergencies through continuous learning and adjustment, and improve the decision-making ability and response speed of the system in complex and dynamic environments.

[0319] Step S9: Integrated decision support system

[0320] The system integrates a comprehensive decision support system based on graph neural network (GNN), which can integrate information from modules such as intelligent prediction, resource optimization, path planning and real-time adjustment. Using big data analysis and machine learning technology, the comprehensive decision support system can deeply analyze and correlate the data of each module to improve the overall coordination of emergency response and the accuracy of decision-making. The system can generate comprehensive decision-making suggestions based on multi-source data to assist managers in making the best decision.

[0321] Step S10: Standardized operating procedures and ground staff training

[0322] In order to ensure the efficient execution of ground support tasks and the operational proficiency of personnel, the system further includes the formulation of standardized operating procedures (SOPs) and ground staff training modules. Through the operator training module based on virtual reality (VR) and augmented reality (AR) technology, ground staff can conduct simulated training on system operation in an immersive training environment to improve their operational proficiency and emergency response capabilities for the automatic dispatching system. In addition, the system ensures that ground staff can master the latest operating procedures and technical requirements through regular training and assessment, and maintain a high level of work efficiency and service quality.

[0323] Working process

[0324] Task classification and resource allocation:

[0325] Based on real-time data analysis, the system classifies ground support tasks according to urgency and priority.

[0326] The priority-based dynamic resource allocation algorithm automatically adjusts resource allocation to ensure that high-priority tasks are processed first.

[0327] Real-time monitoring and risk warning: Through IoT technology and sensor networks, the system monitors the status of all ground support vehicles and equipment in real time. The early warning model based on machine learning analyzes monitoring data, identifies potential risks and issues early warnings in a timely manner.

[0328] Standardized operation and audit: The system formulates detailed operation requirements according to SOPs to ensure that tasks are performed according to standards. The automated audit system based on knowledge graph monitors the operation process in real time to ensure the strict implementation of SOPs.

[0329] Collaborative team formation and task allocation: When major incidents occur, the system forms multidisciplinary collaborative teams (MDTs). The task allocation system based on collaborative filtering optimizes team collaboration efficiency and ensures that problems are solved quickly and efficiently.

[0330] Smart dispatch and real-time guidance: The smart dispatch assistant based on augmented reality (AR) technology provides real-time guidance for ground staff. Wearable devices display task status in real time, improving the work efficiency and accuracy of ground staff.

[0331] Self-learning and strategy optimization: The DDPG-based reinforcement learning algorithm continuously optimizes the scheduling strategy and path planning algorithm based on historical and real-time data. The system improves its decision-making ability and response speed in complex and dynamic environments through continuous learning.

[0332] Comprehensive decision support: The comprehensive decision support system integrates data from various modules, conducts in-depth analysis through graph neural networks (GNN), and generates comprehensive decision recommendations. Managers make optimal decisions based on the system recommendations, improving the overall coordination and accuracy of emergency response.

[0333] Standardized operation and training: The system formulates detailed SOPs and trains ground staff through operator training modules using VR and AR technologies. Regular assessments ensure that ground staff are proficient in operating procedures and technical requirements and maintain a high level of work efficiency and service quality.

[0334] The hierarchical response system and priority-based dynamic resource allocation algorithm enable the system to prioritize key tasks and improve resource utilization efficiency when resources are limited.

[0335] The real-time monitoring and early warning platform identifies potential risks through machine learning models, takes preventive measures in advance, and reduces the impact of emergencies on ground support missions.

[0336] Standardized operating procedures (SOPs) ensure that ground support tasks are performed according to uniform standards, and the execution status is monitored through an automated audit system to improve the standardization and consistency of task execution.

[0337] Multidisciplinary teams (MDTs) optimize team collaboration efficiency through a collaborative filtering task allocation system to ensure that problems can be solved quickly and efficiently in major events or complex tasks.

[0338] Intelligent dispatch assistants and wearable devices based on augmented reality (AR) technology provide ground crew with real-time guidance and task status display, improving work efficiency and accuracy.

[0339] The comprehensive decision support system based on DDPG's self-learning algorithm and graph neural network (GNN) enables the system to continuously optimize scheduling strategies and path planning based on historical and real-time data, thereby improving the system's intelligence level and response capabilities.

[0340] The blockchain-based secure data transmission module ensures the integrity and security of data transmission, and the predictive maintenance module predicts equipment failures in advance, reduces the impact of equipment failures on ground support missions, and improves system reliability.

[0341] The user behavior analysis module optimizes the task allocation strategy and improves the overall efficiency of human-machine collaboration; the operator training module based on VR and AR technology provides an immersive training environment to improve the operational proficiency and emergency response capabilities of ground staff and ensure the efficient operation of the system.

[0342] By implementing this embodiment 2, the system not only has the core automatic dispatch function, but also has been significantly enhanced in terms of security, equipment maintenance management and personnel training. The improved rapid response and resource allocation mechanism, self-learning algorithm and comprehensive decision support system enable the system to respond quickly to emergencies, reasonably allocate resources, and ensure the efficient execution of airport ground support tasks. In addition, the introduction of standardized operating procedures and immersive training modules has improved the operational proficiency and emergency response capabilities of ground staff, and further ensured the reliability and service quality of the system. In summary, this embodiment 2 has comprehensively improved the safety, reliability and intelligence level of the automatic dispatch method based on civil aviation airport aircraft ground support through a number of technological innovations, meeting the needs of modern civil aviation airports for efficient, safe and intelligent ground support services.

[0343] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.

Claims

1. An automatic dispatching method based on civil aviation airport aircraft ground support, characterized by: The following steps are involved: S1. Use the time series prediction model to fuse the multi-source data of historical flight data, weather forecasts, and air traffic control instructions, and use the dynamic causal relationship identification module based on the Bayesian network to identify the causal relationship between different data sources in real time to accurately predict flight arrival times; S2. Based on the prediction results of step S1, combined with real-time monitoring data, including flight dynamics, vehicle location, and equipment status, a context-aware module based on convolutional neural network (CNN) and long short-term memory network (LSTM) is used to dynamically adjust the priority of tasks and perform dynamic task allocation; S3. Adopt an improved multi-objective optimization algorithm to adaptively optimize resource allocation based on the urgency of the task and the type of equipment required. This optimization algorithm combines the global search capability of the genetic algorithm with the fast convergence characteristics of the particle swarm optimization algorithm, and introduces a dynamic weight adjustment mechanism and real-time feedback loop. It has self-learning capabilities and can continuously optimize decision-making logic based on historical data and real-time feedback. S4. Use an improved path planning algorithm to plan the optimal path for each execution unit. The path planning algorithm is based on a model that combines multi-level A* search with deep reinforcement learning, which can be updated in real time and adapt to the dynamic changes of the airport environment. At the same time, it is combined with an energy management algorithm based on a predictive model to optimize energy consumption and ensure that the electric vehicle has enough energy to return to the base or reach the next charging point before completing the mission; S5. Through real-time monitoring and feedback mechanisms, a feedback loop is established to feed back real-time monitoring data to the system's learning module. The self-learning algorithm based on deep deterministic policy gradient (DDPG) and the comprehensive decision support system based on graph neural network (GNN) are used to dynamically adjust task allocation and path planning to ensure the overall progress of the system in emergency situations. The improved rapid response and resource allocation mechanism, including a priority-based dynamic resource allocation algorithm, a machine learning-based early warning model, a knowledge graph-based automated review system, a collaborative filtering-based task allocation system, and an augmented reality (AR)-based intelligent scheduling assistant, can be used to quickly respond to emergencies and reasonably allocate resources. S6. Adopt a blockchain-based secure data transmission module to ensure the integrity and security of data during multi-source data fusion and real-time data transmission, and prevent data tampering and unauthorized access; S7. Integrated predictive maintenance module, based on real-time monitoring data and historical maintenance records, predicts potential failures of ground support equipment, schedules maintenance tasks in advance, and reduces the impact of equipment failures on ground support tasks; S8. Through the user behavior analysis module, the operating habits and task execution efficiency of ground staff are analyzed, the task allocation strategy is optimized, and the overall efficiency of human-machine collaboration is improved; S9. Operator training modules based on virtual reality (VR) and augmented reality (AR) technologies are used to provide ground staff with an immersive training environment to improve their proficiency in operating the automatic dispatch system and their emergency response capabilities; S10. Use big data analysis and machine learning technology to conduct in-depth mining of historical task execution data, optimize task allocation models and resource allocation strategies, and continuously improve the overall performance and service quality of the system.

2. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The multi-source data fusion in step S1 includes time series data, meteorological image data and air traffic control instruction text data, and is deeply integrated using a multimodal data fusion algorithm based on deep learning, and an adaptive weight allocation mechanism is used to optimize the fusion ratio of different data sources.

3. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The situational awareness module in step S2 adopts a multimodal data fusion algorithm based on a convolutional neural network (CNN) and a long short-term memory network (LSTM), and uses the Internet of Things (IoT) technology and sensor networks to acquire and integrate relevant data in real time to accurately perceive the current operating status of the airport and changes in the external environment.

4. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The improved multi-objective optimization algorithm in step S3 combines the global search capability of the genetic algorithm with the fast convergence characteristics of the particle swarm optimization algorithm, and introduces a dynamic weight adjustment mechanism, thereby improving the optimization calculation efficiency and solution accuracy, and adapting to the complex and changeable ground support mission requirements.

5. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The improved path planning algorithm in step S4 combines the heuristic search of the multi-level A* search algorithm with the strategy optimization of the deep reinforcement learning method, so as to plan and adjust the path in real time in a complex airport environment, dynamically avoid static and dynamic obstacles, and improve the efficiency and accuracy of path planning through hierarchical path segmentation optimization.

6. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The energy consumption optimization in step S4 further includes real-time monitoring of the battery status of the electric vehicle, dynamically adjusting the path planning using an energy management algorithm based on a predictive model to minimize energy consumption and charging times, and ensuring that the vehicle has enough energy to return to the base or reach the next charging point before completing the mission.

7. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The improved rapid response and resource allocation mechanism in step S5 includes: a. A hierarchical response system that divides ground support tasks into different levels based on flight delay time, passenger demand, and weather conditions, and introduces a priority-based dynamic resource allocation algorithm; b. Real-time monitoring and early warning platform, which uses IoT technology and sensor networks to monitor the status of all ground support vehicles and service facilities in real time, and identifies potential risks through early warning models based on machine learning; c. Standardized operating procedures (SOPs), which set detailed operating requirements, time limits, and quality standards for each type of ground support mission, and ensure the strict implementation of SOPs through an automated review system based on knowledge graphs; d. Multidisciplinary teams (MDTs), composed of multiple related departments, are responsible for handling major events or complex tasks, and optimize team collaboration efficiency through a task allocation system based on collaborative filtering; e. Automated and intelligent assistance tools, including smart dispatch assistant software and wearable devices based on augmented reality (AR) technology, provide real-time guidance and mission status display for ground crew.

8. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The self-learning algorithm in step S5 is selected from a reinforcement learning algorithm based on deep deterministic policy gradient (DDPG), which can continuously optimize the scheduling strategy and path planning algorithm according to historical and real-time data, thereby improving the intelligence level and response capability of the system.

9. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1 is characterized by: The comprehensive decision support system integrates information from modules of intelligent prediction, resource optimization, path planning, and real-time adjustment, adopts a unified decision-making framework based on graph neural network (GNN), and uses big data analysis and machine learning technology to improve the overall coordination of emergency response and the accuracy of decision-making.

10. The automatic dispatching method based on civil aviation airport aircraft ground support according to claim 1, characterized in that: The automatic dispatch system further includes the formulation of standardized operating procedures (SOPs) and ground crew training modules to ensure that various ground support tasks are efficiently carried out in accordance with predetermined standards, and through operator training modules based on virtual reality (VR) and augmented reality (AR) technologies, an immersive training environment is provided for ground crew to improve their operational proficiency and emergency response capabilities of the automatic dispatch system.

Images