Logistics aircraft network path optimization scheduling system based on dynamic data flow

Abstract

The invention discloses a logistics aircraft network path optimization scheduling system based on dynamic data flow, and belongs to the field of logistics distribution. The data acquisition module is used for acquiring and acquiring flight state data, cargo information data, traffic meteorological data, airspace control data and order demand data of the logistics aircraft in real time through various sensors, Internet of Things equipment and butt joint with an external data platform; according to the invention, data security is guaranteed through data encryption and block chain technologies, and the risk that cargo information and order data are stolen or tampered is reduced; meanwhile, according to real-time flight risk assessment, a safe flight path is planned, and the flight safety of the aircraft is improved; dynamic changes such as traffic meteorology, airspace control and order demands are sensed in real time, a flight path and a scheduling scheme are rapidly adjusted, and distribution delay caused by environment changes and order fluctuation is reduced; and through a multi-objective optimization algorithm and a dynamic scheduling strategy, the operation efficiency of the aircraft is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics distribution, and particularly relates to a logistics aircraft network path optimization scheduling system based on dynamic data flow. BACKGROUND

[0002] With the continuous progress of science and technology, the logistics industry gradually introduces new distribution tools such as unmanned aircraft to improve the efficiency and service quality of distribution.

[0003] The patent with the publication number CN120031223A "Unmanned aircraft logistics distribution receiving management system based on Internet of Things" configures the optimal order distribution path for the unmanned aircraft through the preset regional dynamic distribution network and the current distribution order information, to a certain extent, realizing intelligent logistics distribution management. However, the existing logistics aircraft network path optimization scheduling still has many deficiencies.

[0004] In terms of information security, although the above-mentioned comparative document uses a hash fingerprint to construct a security control key, the security and attack resistance of its encryption technology are limited when facing increasingly complex and variable network attack methods, making it difficult to fully protect the goods information and order data from being stolen or tampered with, which seriously affects the safety and reliability of logistics distribution. In terms of distribution efficiency, the current system does not respond in time and accurately to real-time changes in traffic and meteorological data, airspace control information, and fluctuations in order demand. For example, when encountering sudden severe weather such as strong winds and heavy rain, the existing system cannot quickly re-plan a safe and efficient flight path based on real-time weather data, resulting in delayed distribution; in the face of temporary airspace control, the aircraft flight plan cannot be adjusted in time, causing the aircraft to wait for a long time, reducing the overall distribution efficiency. Moreover, the existing system lacks effective dynamic scheduling strategies for orders of different emergency levels and distribution requirements, making it difficult to ensure timely distribution of high-priority orders while considering the reasonable arrangement of other orders. In addition, the existing system lacks effective prediction and avoidance mechanisms for conflicts between aircraft when multiple aircrafts are working together, which can easily lead to conflicts between aircraft routes, further affecting the efficiency of distribution.

[0005] Therefore, a logistics aircraft network path optimization scheduling system based on dynamic data flow is needed, which can realize accurate optimization and efficient scheduling of logistics aircraft paths by real-time collection, processing and analysis of multi-source dynamic data, and improve the safety, efficiency and service quality of logistics distribution. SUMMARY

[0006] To address the shortcomings of existing technologies, this invention provides a logistics aircraft network path optimization and scheduling system based on dynamic data flow. This system can perceive the dynamic changes in the logistics distribution environment in real time and optimize and rationally schedule logistics aircraft paths through efficient processing and analysis of multi-source data, thereby improving the safety, efficiency, and cost reduction of logistics distribution.

[0007] Technical Solution: To solve the above-mentioned technical problems, according to one aspect of the present invention, more specifically, a logistics aircraft network path optimization and scheduling system based on dynamic data flow, comprising:

[0008] Data Acquisition Module: This system is equipped with a comprehensive data acquisition module. Through various sensors and IoT devices mounted on the aircraft, as well as interfaces with external data platforms, it can acquire real-time flight status data, cargo information data, traffic and meteorological data, airspace control data, and order demand data of the logistics aircraft. Various sensors, such as GPS positioning sensors to obtain the aircraft's position, speed sensors to obtain speed information, power sensors to monitor the remaining power, and load sensors to sense the load status, can realize the real-time acquisition of the aircraft's flight status data.

[0009] a. Cargo information data: Information such as cargo weight, volume, and destination is obtained through electronic tags on cargo packaging and reading devices.

[0010] b. Traffic meteorological data: Connect with the meteorological department's data platform to obtain real-time meteorological information such as wind speed, wind direction, precipitation, and temperature. At the same time, cooperate with traffic management departments to obtain data on ground traffic congestion.

[0011] c. Airspace control data is obtained in real time through data interfaces with aviation management departments, including information on no-fly zones, restricted flight altitudes, and temporary controls.

[0012] d. Order demand data is read in real time from the logistics order management system, including order quantity, urgency level, and delivery time window. Comprehensive and real-time data collection provides a rich and accurate data foundation for subsequent analysis and decision-making.

[0013] Data Processing and Analysis Module: The collected multi-source heterogeneous data first enters the data processing and analysis module. Data cleaning algorithms remove duplicate data, and methods such as data interpolation and regression are used to fill in missing data. Errors are corrected based on data logical relationships. Then, a multi-source data fusion algorithm based on spatiotemporal correlation is employed to unify data from different formats and sources under the same spatiotemporal coordinate system for fusion analysis. Machine learning algorithms, such as time series analysis algorithms, are used to predict future trends in traffic and meteorological data. Based on historical order data and real-time order information, cluster analysis and regression analysis are used to predict changes in order demand. Simultaneously, by combining historical flight data and real-time environmental data, a risk assessment model is constructed to evaluate the flight risk levels of different regions, providing scientific data support for route optimization.

[0014] Path Optimization Module: This module operates based on the dynamic flight environment model, predicted data, and flight risk levels constructed by the data processing and analysis module. It employs an improved Non-Dominated Sorting Genetic Algorithm (NSGA-II), which introduces an adaptive crossover and mutation operator to dynamically adjust crossover and mutation probabilities according to the population's evolutionary stage, improving the algorithm's global search capability and convergence speed. Simultaneously, it uses an elite retention strategy to ensure that superior individuals in each generation are not lost, thereby improving the algorithm's solution accuracy. Optimization is performed with multiple objectives: shortest flight time, lowest energy consumption, lowest delivery cost, and highest flight safety, quickly finding a set of Pareto optimal solutions in complex dynamic environments. In the event of unforeseen circumstances, such as sudden weather changes or temporary airspace control, it can rapidly replan the path based on real-time feedback data, ensuring the aircraft always flies along the optimal or near-optimal path.

[0015] The scheduling decision module makes scheduling decisions based on the routes generated by the route optimization module, combined with the real-time status of the aircraft (such as remaining battery power, payload, and current location) and the urgency of the orders. A dynamic priority allocation strategy is adopted, assigning higher priority to urgent orders and high-value cargo orders, prioritizing their delivery by aircraft. The module also considers the aircraft's maintenance cycle and base location to rationally allocate tasks, avoiding overuse or prolonged idleness of aircraft. When multiple aircraft are operating collaboratively, a conflict prediction model is established to predict potential route conflicts between aircraft in advance. By adjusting parameters such as takeoff time, flight speed, and flight altitude, conflicts are avoided, achieving efficient logistics delivery task scheduling.

[0016] Communication and Monitoring Module: This module employs a hybrid communication approach combining satellite and terrestrial communication. In areas with good terrestrial signal coverage, it uses a low-cost terrestrial network for data transmission, including sending optimized paths and scheduling instructions to the aircraft and receiving flight status information from the aircraft. When the aircraft enters areas with signal obstruction or lack of terrestrial coverage, it automatically switches to satellite communication to ensure continuity and stability. Simultaneously, blockchain technology is used to encrypt and store communication data, ensuring data security during transmission and storage and preventing data tampering and theft. The module monitors the aircraft's entire flight process. When the aircraft deviates from its planned path, experiences equipment malfunctions, or other abnormalities, it promptly issues alarms and takes appropriate measures according to pre-set emergency strategies, such as guiding the aircraft to the nearest landing site for repairs or replanning a safe path.

[0017] The beneficial effects of the dynamic data stream-based logistics aircraft network path optimization and scheduling system of this invention are as follows:

[0018] (1) This invention uses data encryption and blockchain technology to ensure data security and reduce the risk of cargo information and order data being stolen or tampered with; at the same time, it plans a safe flight path based on real-time flight risk assessment to improve the flight safety of aircraft in complex environments.

[0019] (2) This invention can sense dynamic changes in traffic weather, airspace control and order demand in real time, and quickly adjust flight paths and scheduling schemes to reduce delivery delays caused by environmental changes and order fluctuations; through multi-objective optimization algorithms and dynamic scheduling strategies, it can improve the operating efficiency of aircraft and shorten delivery time.

[0020] (3) The present invention aims to minimize energy consumption and delivery costs by rationally planning routes and scheduling aircraft to reduce unnecessary flight distances and energy consumption, while optimizing the utilization efficiency of aircraft and reducing operating costs.

[0021] It can adapt to complex and ever-changing logistics and distribution environments, including different weather conditions, airspace control requirements, and diverse order demands, and has strong flexibility and scalability. Attached Figure Description

[0022] The present invention will now be described in further detail with reference to the accompanying drawings and specific implementation methods.

[0023] Figure 1 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0024] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0025] To make the technical solution of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] Reference Figure 1 A logistics aircraft network path optimization and scheduling system based on dynamic data flow includes a data acquisition module, a data processing and analysis module, a path optimization module, a scheduling decision module, and a communication and monitoring module.

[0027] The data acquisition module acquires real-time flight status data, cargo information data, traffic and meteorological data, airspace control data, and order demand data of the logistics aircraft through various sensors, IoT devices, and interfaces with external data platforms.

[0028] The data processing and analysis module is connected to the data acquisition module and is used to clean, fuse and analyze the acquired multi-source heterogeneous data, construct a dynamic flight environment model for logistics aircraft, use machine learning algorithms to predict traffic weather and order demand data for a period of time in the future, and assess the flight risk level of different regions based on historical and real-time data, providing a data foundation for route optimization.

[0029] The path optimization module, connected to the data processing and analysis module, uses a multi-objective optimization algorithm based on the dynamic flight environment model, predicted data, and flight risk level. The optimization objectives are to minimize flight time, energy consumption, delivery costs, and flight safety. It dynamically generates the optimal flight path for the logistics aircraft and can adjust the path online based on real-time feedback data. In the event of unforeseen circumstances such as severe weather changes or temporary airspace control, the path can be quickly replanned.

[0030] The scheduling decision module: Based on the path generated by the path optimization module, combined with the real-time status of the logistics aircraft and the urgency of the orders, it rationally schedules the aircraft, determines the take-off time, landing location, and task allocation of the aircraft, coordinates the flight plans of multiple logistics aircraft, avoids conflicts between aircraft, achieves efficient logistics delivery task arrangement, and also considers the maintenance cycle and base location of the aircraft to optimize the utilization efficiency of the aircraft.

[0031] The communication and monitoring module is responsible for enabling real-time communication between various modules within the system and with the logistics aircraft. It sends optimized paths and scheduling instructions to the logistics aircraft and receives flight status information from the logistics aircraft in real time. It monitors the entire flight process of the aircraft and issues timely alarms and takes corresponding emergency measures when the aircraft deviates from the predetermined path or experiences equipment failure. The communication and monitoring module also has data encryption capabilities to ensure data transmission security.

[0032] Example 1

[0033] Reference Figure 1 The implementation steps of the logistics aircraft network path optimization and scheduling system based on dynamic data flow are as follows:

[0034] S1. Data Acquisition: High-precision GPS positioning sensors, speed sensors, battery sensors, and load sensors are installed on the logistics aircraft. The GPS positioning sensor collects the aircraft's position information every second and transmits the data to the data processing and analysis module via a wireless communication module; the speed sensor monitors the aircraft's flight speed in real time, updating and transmitting data every 2 seconds; the battery sensor continuously monitors the battery level, immediately sending power data when the level change exceeds a certain threshold; the load sensor collects load data every 5 minutes after the aircraft is loaded with cargo and during flight.

[0035] Cargo information is collected by affixing RFID tags to the cargo packaging. Before the cargo is loaded onto the aircraft, RFID readers read information such as the cargo weight, volume, and destination from the tags and upload it to the data processing and analysis module.

[0036] We have established data cooperation with meteorological departments, obtaining the latest real-time meteorological data such as wind speed, wind direction, precipitation, and temperature every 10 minutes through a dedicated data interface. Simultaneously, we collaborate with traffic management departments, utilizing traffic flow monitoring systems to obtain ground traffic congestion data, updated every 15 minutes. Airspace control data is received in real-time through a data exchange platform with aviation management departments, receiving information on no-fly zones, restricted flight altitudes, and temporary controls; any updates are immediately pushed to the data processing and analysis module. Order demand data is read in real-time from the logistics companies' order management systems; when a new order is generated or the order status changes, the relevant data is immediately transmitted to the data processing and analysis module.

[0037] S2. Data Processing and Analysis: In a specific delivery area, the data acquisition module collects a large amount of meteorological data, traffic data, and aircraft flight status data over a period of time. The data processing and analysis module first cleans this data. For example, it discovers a set of wind speed data containing a significant error (wind speed far exceeding the historical maximum value for the area). By comparing and analyzing data from adjacent time periods, a data correction algorithm is used to correct this error value to a reasonable value. Then, a multi-source data fusion algorithm based on spatiotemporal correlation is employed to fuse meteorological data, traffic data, and aircraft position data from different time and spatial scales. Time series analysis algorithms are used to learn from and predict historical meteorological data, predicting that strong winds will occur in the area within the next two hours. By constructing a flight risk assessment model, combined with real-time meteorological data, airspace control data, and the terrain characteristics of the area, the flight risk level of some airspace in the area is assessed as high risk.

[0038] S3. Path Optimization: After receiving the dynamic flight environment model, predicted data, and flight risk level from the data processing and analysis module, the path optimization module uses an improved Non-Dominated Sorting Genetic Algorithm (NSGA-II) for path optimization. Taking a logistics aircraft delivering goods from location A to location B as an example, in the initial population generation stage, 100 feasible flight paths are randomly generated as the initial population based on the locations of locations A and B and the surrounding airspace information. During the evolution process, the adaptive crossover and mutation operator dynamically adjusts the crossover and mutation probabilities according to the fitness distribution of the population. For example, when the fitness values ​​of most individuals in the population are relatively similar, the crossover and mutation probabilities are appropriately increased to increase the diversity of the population and avoid the algorithm getting trapped in local optima; when individuals with good fitness values ​​have appeared in the population, the crossover and mutation probabilities are reduced to retain excellent individuals. After multiple generations of evolution, the algorithm finds a set of Pareto optimal solutions, one of which, considering factors such as flight time, energy consumption, and safety, is selected as the optimal path by the scheduling decision module. If, during flight, temporary airspace control information is suddenly issued for the area, the path optimization module immediately replans the path based on real-time feedback data, generates a new path that avoids the controlled area and has better overall performance in a short time, and sends it to the scheduling decision module.

[0039] S4. Scheduling Decision Execution: The scheduling decision module makes scheduling decisions based on the paths generated by the path optimization module and the real-time status of the aircraft. Assume there is a batch of orders, one of which is for the delivery of emergency medical supplies with a tight delivery window. The scheduling decision module assigns this order the highest priority according to a dynamic priority allocation strategy. Considering the current status of available aircraft, it finds that aircraft M has sufficient remaining power and is close to the order's delivery location, so it assigns aircraft M to perform the delivery task for this emergency order. Simultaneously, considering that aircraft M may have low remaining power after completing this task, and that its base is close to the destination, the scheduling decision module plans for aircraft M to return directly to the base for charging and maintenance after completing the task. For other ordinary orders, tasks are rationally allocated based on the number of orders, destination distribution, and the status of other aircraft to ensure that all orders can be delivered in the shortest possible time while avoiding conflicts between aircraft. During multi-aircraft collaborative operations, a conflict prediction model predicts in advance that aircraft N and aircraft P may have flight path conflicts in a certain area. The scheduling decision module avoids the conflict by adjusting the takeoff time of aircraft N to stagger its flight path with that of aircraft P.

[0040] S5. Communication and Monitoring Operations: In terms of communication, when the aircraft is flying in areas with good ground communication signals, such as city centers, the communication and monitoring module uses the terrestrial 4G communication network to interact with the aircraft. It sends the path generated by the path optimization module and the instructions from the scheduling decision module to the aircraft in encrypted form, while simultaneously receiving flight status information from the aircraft, including position, speed, battery level, and payload. This data is updated and displayed on the monitoring interface every 3 seconds. When the aircraft enters mountainous areas or other areas with obstructed ground communication signals, the communication and monitoring module automatically switches to satellite communication mode to ensure continuous communication. During monitoring, if the aircraft deviates from the predetermined path—for example, if the actual flight direction deviates from the predetermined path by more than 5 degrees—the communication and monitoring module immediately issues an alarm and sends a correction command to the aircraft via the communication link, guiding it back to the predetermined path. If the aircraft experiences equipment failure, such as an abnormal drop in battery power detected by the battery sensor, the communication and monitoring module reports to the scheduling decision module to reschedule the delivery task. Simultaneously, according to a preset emergency strategy, it guides the aircraft to find the nearest safe landing point for repairs, while sending the fault information and landing location to relevant maintenance personnel.

[0041] Through the above specific implementation methods, the logistics aircraft network path optimization and scheduling system based on dynamic data flow of the present invention can effectively optimize and schedule logistics aircraft paths, improve the safety and efficiency of logistics distribution, and reduce costs.

[0042] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A logistics aircraft network path optimization and scheduling system based on dynamic data flow, comprising a data acquisition module, a data processing and analysis module, a path optimization module, a scheduling decision module, and a communication and monitoring module, characterized in that: The data acquisition module acquires real-time flight status data, cargo information data, traffic and meteorological data, airspace control data, and order demand data of the logistics aircraft through various sensors, IoT devices, and interfaces with external data platforms. The data processing and analysis module is connected to the data acquisition module and is used to clean, fuse and analyze the acquired multi-source heterogeneous data, construct a dynamic flight environment model for logistics aircraft, use machine learning algorithms to predict traffic weather and order demand data for a period of time in the future, and assess the flight risk level of different regions based on historical and real-time data, providing a data foundation for route optimization. The path optimization module, connected to the data processing and analysis module, uses a multi-objective optimization algorithm based on the dynamic flight environment model, predicted data, and flight risk level. The optimization objectives are to minimize flight time, energy consumption, delivery costs, and flight safety. It dynamically generates the optimal flight path for the logistics aircraft and can adjust the path online based on real-time feedback data. In the event of unforeseen circumstances such as severe weather changes or temporary airspace control, the path can be quickly replanned. The scheduling decision module: Based on the path generated by the path optimization module, combined with the real-time status of the logistics aircraft and the urgency of the orders, it rationally schedules the aircraft, determines the take-off time, landing location, and task allocation of the aircraft, coordinates the flight plans of multiple logistics aircraft, avoids conflicts between aircraft, achieves efficient logistics delivery task arrangement, and also considers the maintenance cycle and base location of the aircraft to optimize the utilization efficiency of the aircraft. The communication and monitoring module is responsible for enabling real-time communication between various modules within the system and with the logistics aircraft. It sends optimized paths and scheduling instructions to the logistics aircraft and receives flight status information from the logistics aircraft in real time. It monitors the entire flight process of the aircraft and issues timely alarms and takes corresponding emergency measures when the aircraft deviates from the predetermined path or experiences equipment failure. The communication and monitoring module also has data encryption capabilities to ensure data transmission security.

2. The logistics aircraft network path optimization and scheduling system based on dynamic data flow according to claim 1, characterized in that: The flight status data includes the aircraft's position, speed, remaining battery power, and payload status; The cargo information data includes cargo weight, volume, and destination; The traffic meteorological data includes real-time wind speed, wind direction, precipitation, temperature, and ground traffic congestion. The airspace control data includes no-fly zones, restricted flight altitudes, and temporary control information. The order demand data includes the number of orders, urgency level, and delivery time window.

3. The logistics aircraft network path optimization and scheduling system based on dynamic data flow according to claim 1, characterized in that: The data cleaning methods used in the data processing and analysis module include removing duplicate data, filling in missing data, and correcting erroneous data. The data fusion method is a multi-source data fusion algorithm based on spatiotemporal correlation, which unifies data from different sources and in different formats into the same spatiotemporal coordinate system for analysis.

4. The logistics aircraft network path optimization and scheduling system based on dynamic data flow according to claim 1, characterized in that: The multi-objective optimization algorithm in the path optimization module is an improved non-dominated sorting genetic algorithm. By introducing an adaptive crossover mutation operator and an elite retention strategy, the convergence speed and solution accuracy of the algorithm are improved. It can quickly find a set of Pareto optimal solutions in complex dynamic environments for the scheduling decision module to select.

5. The logistics aircraft network path optimization and scheduling system based on dynamic data flow according to claim 1, characterized in that: The scheduling decision module adopts a dynamic priority allocation strategy, assigning higher priority to urgent orders and orders for high-value goods, and prioritizing the dispatch of aircraft for delivery. Furthermore, it dynamically adjusts the delivery tasks undertaken by the aircraft based on its remaining battery power and payload, ensuring that the aircraft operates in a safe and efficient manner.

6. The logistics aircraft network path optimization and scheduling system based on dynamic data flow according to claim 1, characterized in that: The communication and monitoring module adopts a hybrid communication method that combines satellite communication and terrestrial communication. In areas with good signal, terrestrial communication networks are used to reduce communication costs, while in areas with signal obstruction or no terrestrial communication coverage, it automatically switches to satellite communication to ensure the continuity and stability of communication. At the same time, blockchain technology is used to encrypt and store communication data to prevent data from being tampered with or stolen.

Images