Unmanned aerial vehicle refueling flow control method and system based on intelligent interaction

Abstract

The invention relates to the field of intelligent interaction, in particular to an unmanned aerial vehicle refueling flow control method and system based on intelligent interaction, and the method comprises the steps: refueling an unmanned aerial vehicle through a flow controller, monitoring the flow data of the refueling flow in real time, analyzing the inertial characteristics of the refueling flow based on the flow data, and learning the inertial characteristics. The method comprises the steps of determining the advance of refueling flow control, respectively controlling a refueling valve and a refueling pump according to the valve advance and the pump advance, dynamically adjusting the opening degree of the refueling valve and the rotating speed of the refueling pump by utilizing an advance prediction model according to real-time flow data, and ensuring that the refueling process is always in a precise control state. The dynamic adjustment capability enables the refueling process to be more flexible, and accurate refueling control can ensure that the fuel quantity in the fuel tank of the unmanned aerial vehicle reaches the optimal state, so that the cruising ability of the unmanned aerial vehicle is optimized, intelligent decision support is provided for the refueling process of the unmanned aerial vehicle, and the safety and efficiency of the refueling process of the unmanned aerial vehicle are further improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent interaction, and in particular to a method and system for controlling the refueling flow of an unmanned aerial vehicle (UAV) based on intelligent interaction. Background Art

[0002] Traditional drone refueling methods typically rely on manual control or simple automated equipment. This results in low flow rate control precision, making over- or under-fueling a common problem. For example, during the refueling process, flow rate fluctuations or human error can cause the drone's fuel tank to overflow or remain partially filled, impacting the drone's flight endurance and flight safety. Drone fuel tanks have relatively small capacities, and refueling must be completed quickly and accurately. Furthermore, the complex refueling environments for drones, such as refueling in the field or on mobile platforms, place higher demands on the automation and intelligence of refueling equipment.

[0003] In recent years, intelligent interaction technology has been widely applied in various fields. Through sensors, data analysis, and machine learning, intelligent interaction technology can achieve intelligent coordination and automated control between devices. Applying intelligent interaction technology to drone refueling flow control enables precise refueling by real-time monitoring of flow data, analyzing flow inertia characteristics, and using machine learning models to predict and adjust refueling flow advances. This application of technology can significantly improve the efficiency and safety of drone refueling and reduce human error.

[0004] Chinese patent application publication number CN111352435A discloses a method for autonomous aerial refueling of a drone formation. Several refueling drones perform autonomous flight and are numbered so that the current refueling drone and the refueling drone arrive at an aerial convergence point. The refueling drone performs a self-check of its refueling system. If the current refueling drone is the first-numbered refueling drone or the previously numbered refueling drone has returned, the refueling drone refuels the current refueling drone. After refueling, the drone returns to the base. If the refueling drone is the last-numbered refueling drone, the refueling process is complete. This invention enables a drone formation to conduct autonomous refueling throughout the entire process, with excellent control stability, reliability, and operational safety. It utilizes the Harris-SIFT binocular visual feature point matching algorithm to effectively reduce image processing time. It also enables the drone group to maintain and coordinate aerial formation control. The interaction of drone formation information can effectively shorten refueling time.

[0005] Chinese Patent Authorization Announcement No.: CN221969792U discloses a UAV refueling system, including a fuel tank, a refueling pump and several refueling mechanisms. The several refueling mechanisms are arranged at several positions inside the machine nest. The refueling mechanisms correspond to the refueling ports of the UAV. The refueling pump is used to pump the fuel in the fuel tank to the refueling mechanism and then deliver it to the UAV through the refueling mechanism. The utility model can be flexibly arranged inside the machine nest without taking up too much internal space of the machine nest. It can refuel multiple UAVs inside the machine nest and ensure refueling safety, which is conducive to the overall automated control of the machine nest.

[0006] However, the above method has the following problems: it is unable to monitor and adjust the instantaneous value and average value of the refueling flow in real time, so as to make dynamic adjustments according to the flow changes during the actual refueling process. Summary of the Invention

[0007] To this end, the present invention provides a UAV refueling flow control method and system based on intelligent interaction to overcome the problem in the prior art that the instantaneous value and average value of the refueling flow cannot be monitored and adjusted in real time, thereby dynamically adjusting the flow according to the actual refueling process.

[0008] To achieve the above objectives, the present invention provides a method for controlling the refueling flow of a UAV based on intelligent interaction, comprising: Refueling the UAV using a flow controller and monitoring flow data of the refueling flow in real time, wherein the flow data includes an instantaneous value and an average value of the refueling flow; Analyzing the inertial characteristics of the refueling flow based on the flow data, wherein the inertial characteristics include flow rate change rate, flow fluctuation amplitude, and flow stabilization time; Learning the inertia characteristics to determine an advance amount for refueling flow control, wherein the advance amount includes a valve advance amount and a pump advance amount; The refueling valve and the refueling pump are controlled respectively according to the valve advance amount and the pump advance amount.

[0009] Furthermore, the step of analyzing the inertial characteristics of the refueling flow includes: Calculate the flow rate change rate, wherein the flow rate change rate is the change in the refueling flow rate per unit time; Determining the flow fluctuation amplitude, wherein the flow fluctuation amplitude is the difference between the maximum value and the minimum value of the refueling flow within a preset time; The flow stabilization time is measured, wherein the flow stabilization time is the length of time the refueling flow reaches a preset stable value and remains at the preset stable value.

[0010] Furthermore, the steps of learning the inertial features include: Preprocessing the inertial characteristics to form corresponding inertial pre-data; Build the corresponding advance quantity prediction model; The inertia advance data is learned using the advance prediction model to generate the valve advance and the pump advance.

[0011] Furthermore, the step of pre-processing the inertial features to form corresponding inertial pre-data includes: Filter outliers in the inertial features, pre-process the inertial features, and form corresponding inertial pre-data, wherein: The preprocessing is to segment the inertial features according to a standard learning rate; The standard learning rate is a learning rate that can be recognized by the advance prediction model, and for single learning, the corresponding standard learning rate is a single learning rate.

[0012] Furthermore, the steps of building an advance prediction model include: Collect historical inertial characteristics of the UAV refueling process; Performing Fourier transform on the historical inertia features to form corresponding transformation features, and using the transformation features as the input layer of the lead time prediction model; Determine the number of hidden layers of the lead prediction model, wherein the number of hidden layers is adjusted according to the complexity of the historical inertia characteristics.

[0013] Furthermore, in response to the input of the inertia prediction data, the learning process of the advance prediction model is mobilized, and the output of the advance prediction model includes the valve advance and the pump advance, wherein the valve advance is used to adjust the opening of the refueling valve, and the pump advance is used to adjust the speed of the refueling pump.

[0014] Furthermore, the refueling valve and the refueling pump are adjusted according to the valve advance and the pump advance, and when the refueling process is completed, it is detected whether the refueling amount reaches a preset full state, wherein the preset full state is that the oil level in the drone tank reaches a specified proportion of its maximum capacity.

[0015] Furthermore, when the refueling amount exceeds the preset full state, the refueling pump and the refueling valve are immediately closed, and the advance amount is determined again.

[0016] Furthermore, when the refueling amount does not reach the preset full state, a fuel tank leakage alarm is triggered and a fuel tank fault check is performed.

[0017] In another aspect, the present invention provides a UAV refueling flow control system based on intelligent interaction, comprising: A flow monitoring module, which is used to refuel the UAV using a flow controller and monitor the flow data of the refueling flow in real time, wherein the flow data includes the instantaneous value and average value of the refueling flow; an inertia analysis module connected to the flow monitoring module, configured to analyze the inertia characteristics of the refueling flow based on the flow data, wherein the inertia characteristics include flow rate change rate, flow fluctuation amplitude, and flow stabilization time; an advance learning module connected to the inertia analysis module, configured to learn the inertia characteristics to determine an advance for refueling flow control, wherein the advance includes a valve advance and a pump advance; The regulating module is connected to the advance learning module and is used to control the refueling valve and the refueling pump according to the valve advance and the pump advance.

[0018] Compared with the existing technology, the present invention refuels the UAV by using a flow controller to monitor the flow data of the refueling flow in real time. Based on the flow data, the inertial characteristics of the refueling flow are analyzed, and the inertial characteristics are learned to determine the advance amount of the refueling flow control. According to the valve advance amount and the pump advance amount, the refueling valve and the refueling pump are controlled respectively. Using the advance amount prediction model, the opening of the refueling valve and the speed of the refueling pump are dynamically adjusted according to the real-time flow data to ensure that the refueling process is always in a state of precise control. This dynamic adjustment capability makes the refueling process more flexible. Precise refueling control can ensure that the fuel amount in the UAV tank reaches the optimal state, thereby optimizing the UAV's endurance, providing intelligent decision-making support for the UAV refueling process, and further improving the safety and efficiency of the UAV refueling process.

[0019] Furthermore, by calculating the flow rate change rate, the increase or decrease trend of the flow rate can be predicted in advance, so that the parameters of the valves and pumps can be adjusted in advance to avoid the impact of flow fluctuations on the refueling process. By determining the flow fluctuation amplitude and flow stabilization time, the system can identify abnormal fluctuations in flow, which helps to achieve a smoother refueling process and reduce over- or under-refueling caused by unstable flow. By real-time monitoring and analysis of the inertial characteristics of the flow, abnormal situations can be automatically identified and adjusted in time.

[0020] Furthermore, by preprocessing and learning the inertial characteristics, accurate valve advance and pump advance are generated, thereby achieving precise control of the refueling process, improving refueling efficiency and safety, while reducing fuel waste and equipment wear.

[0021] Furthermore, by filtering outliers and segmenting inertial features according to the standard learning rate, the data quality can be effectively improved, ensuring that the input data of the lead prediction model is accurate and meets the requirements of the lead prediction model, thereby improving the prediction accuracy and stability of the lead prediction model and further optimizing the performance of refueling flow control.

[0022] Furthermore, through the dynamic learning and real-time output of the advance fuel prediction model, the parameters of the fueling valve and pump are precisely adjusted according to the flow inertia characteristics during the refueling process, ensuring the efficiency and accuracy of the refueling process. Upon completion of refueling, the system can promptly detect whether the fuel level has reached the preset full state and take appropriate measures based on the actual situation, effectively preventing fuel spills or leaks, ensuring refueling safety, and improving the overall reliability and intelligence level of drone refueling. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for controlling refueling flow of a UAV based on intelligent interaction according to an embodiment of the present invention; Figure 2 A flow chart illustrating analysis of inertial characteristics of refueling flow according to an embodiment of the present invention; Figure 3 A flowchart of learning inertial features according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of a UAV refueling flow control system based on intelligent interaction according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0025] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0026] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0027] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0028] See also Figure 1 As shown in FIG, which is a flow chart of a method for controlling refueling flow of a UAV based on intelligent interaction according to an embodiment of the present invention, including: Step S1, refueling the UAV using a flow controller and monitoring the flow data of the refueling flow in real time, wherein the flow data includes the instantaneous value and average value of the refueling flow; Step S2: analyzing the inertial characteristics of the refueling flow based on the flow data, wherein the inertial characteristics include the flow rate change rate, flow fluctuation amplitude, and flow stabilization time; Step S3, learning the inertia characteristics to determine the lead amount of refueling flow control, wherein the lead amount includes valve lead amount and pump lead amount; Step S4: Control the refueling valve and the refueling pump according to the valve advance amount and the pump advance amount respectively.

[0029] By using a flow controller to refuel the drone, the flow data of the refueling flow is monitored in real time. Based on the flow data, the inertial characteristics of the refueling flow are analyzed and the inertial characteristics are learned to determine the lead time of the refueling flow control. According to the valve lead time and pump lead time, the refueling valve and refueling pump are controlled respectively. Using the lead time prediction model, the opening of the refueling valve and the speed of the refueling pump are dynamically adjusted according to the real-time flow data to ensure that the refueling process is always in a state of precise control. This dynamic adjustment capability makes the refueling process more flexible. Accurate refueling control can ensure that the fuel amount in the drone's tank reaches the optimal state, thereby optimizing the drone's endurance and providing intelligent decision-making support for the drone refueling process, further improving the safety and efficiency of the drone refueling process.

[0030] See also Figure 2 As shown, it is a flow chart of analyzing the inertial characteristics of refueling flow according to an embodiment of the present invention, including: Step S11, calculating the flow rate change rate, wherein the flow rate change rate is the change in refueling flow rate per unit time; Step S12, determining the flow fluctuation amplitude, wherein the flow fluctuation amplitude is the difference between the maximum and minimum values ​​of the refueling flow within a preset time; Step S13, measuring the flow stabilization time, wherein the flow stabilization time is the length of time it takes for the refueling flow to reach a preset stable value and remain at the preset stable value.

[0031] In practice, when calculating the flow rate change rate, the first step is to determine the time interval per unit time, typically 1 second or 0.5 seconds. By comparing the instantaneous flow values ​​at two time points, the change in refueling flow per unit time is calculated.

[0032] To determine flow fluctuations, select a preset time (1 minute or 30 seconds) to analyze flow fluctuations. Record all instantaneous flow values ​​within the preset time. Find the maximum and minimum instantaneous flow values ​​within this timeframe, then calculate the difference between the two. This difference represents the refueling flow fluctuations and serves as a measure of refueling flow fluctuations within the preset timeframe.

[0033] When measuring flow stabilization time, first set a preset stabilization value. Depending on the characteristics of the refueling equipment and the drone's fuel tank, this value is typically set at 95% of the target flow rate. Monitor the refueling flow in real time to see if it reaches the preset stabilization value, and record the time when the flow reaches the preset stabilization value. The flow stabilization time is the time from the start of refueling flow monitoring to the time when the flow reaches and remains at the preset stabilization value.

[0034] By calculating the flow rate change rate, the increase or decrease trend of flow can be predicted in advance, so that the parameters of valves and pumps can be adjusted in advance to avoid the impact of flow fluctuations on the refueling process. By determining the flow fluctuation amplitude and flow stabilization time, the system can identify abnormal flow fluctuations, which helps to achieve a smoother refueling process and reduce over- or under-refueling caused by unstable flow. By real-time monitoring and analysis of the inertial characteristics of flow, abnormal situations can be automatically identified and adjusted in time.

[0035] See also Figure 3 As shown in FIG, it is a flow chart of learning inertial features according to an embodiment of the present invention, including: Step S21, pre-processing the inertial characteristics to form corresponding inertial pre-data; Step S22, building a corresponding advance prediction model; Step S23: Use the advance prediction model to learn the inertia prediction data to generate valve advance and pump advance.

[0036] In the specific implementation, the preprocessed inertial prediction data is input into the lead prediction model. During the learning process, the lead prediction model will continuously adjust the parameters to minimize the prediction error.

[0037] By preprocessing and learning inertial characteristics, accurate valve advance and pump advance are generated, thereby achieving precise control of the refueling process, improving refueling efficiency and safety, while reducing fuel waste and equipment wear.

[0038] Specifically, the steps of preprocessing the inertial features to form corresponding inertial pre-data include: Filter outliers in the inertial features, pre-process the inertial features, and form corresponding inertial pre-data, where: The preprocessing is to split the inertial features according to the standard learning rate; The standard learning rate is the learning rate that the advance prediction model can recognize, and for single-shot learning, the corresponding standard learning rate is a single learning rate.

[0039] In a specific implementation, when pre-processing the inertial characteristics, first identify and eliminate abnormal values ​​in the inertial characteristics, such as erroneous data caused by failure or interference of the flow controller. For missing inertial characteristic numerical points, interpolation or other statistical methods are used to fill in the gaps to ensure the integrity of the inertial characteristics. The inertial characteristic data is standardized to meet the input requirements of the lead prediction model. The standardization process includes scaling the inertial characteristics to between 0 and 1 so that the lead prediction model can better process them. According to the requirements of the lead prediction model, the inertial characteristic data is segmented according to the standard learning rate to form inertial pre-data suitable for model learning. The standard learning rate refers to the data granularity that the model can recognize and process. Preferably, when the standard learning rate is set to 1700 / second, the lead prediction model has the best effect on the generation of lead.

[0040] By filtering outliers and segmenting inertial features according to the standard learning rate, data quality can be effectively improved, ensuring that the input data of the lead prediction model is accurate and meets the requirements of the lead prediction model, thereby improving the prediction accuracy and stability of the lead prediction model and further optimizing the performance of refueling flow control.

[0041] Specifically, the steps to build an advance forecast model include: Collect historical inertial characteristics of the UAV refueling process; Perform Fourier transform on the historical inertia features to form corresponding transformation features, and use the transformation features as the input layer of the lead prediction model; The number of hidden layers of the lead prediction model is determined, wherein the number of hidden layers is adjusted according to the complexity of the historical inertia characteristics.

[0042] In specific implementation, when building a lead time prediction model, a machine learning model or a deep learning model is selected, such as a neural network, a support vector machine, or a decision tree. The input features of the lead time prediction model are designed based on the inertial characteristics to ensure that the lead time prediction model can effectively learn the relationship between the habitual characteristics and the lead time.

[0043] Initialize the parameters of the advance prediction model and set appropriate hyperparameters, such as the learning rate is set to 0.01 and the number of iterations is set to 10.

[0044] The Fourier transform algorithm is used to convert the time series data of each historical inertial feature into frequency domain data to form the corresponding transformation features. The key information in the transformation features, such as the main frequency components and amplitude, is extracted as the input features of the lead prediction model.

[0045] The number of hidden layers is determined based on the complexity of the historical inertia characteristics. For simple linear relationships, only 1-2 hidden layers are needed. For complex nonlinear relationships and periodic fluctuations, 3-5 or even more hidden layers are needed.

[0046] Specifically, the learning process of the advance prediction model is activated in response to the input of inertia prediction data, and the output of the advance prediction model includes valve advance and pump advance, wherein the valve advance is used to adjust the opening of the refueling valve, and the pump advance is used to adjust the speed of the refueling pump.

[0047] Specifically, the refueling valve and the refueling pump are adjusted according to the valve advance and the pump advance, and when the refueling process is completed, it is detected whether the refueling amount reaches the preset full state, where the preset full state is that the oil level in the drone's fuel tank reaches a specified proportion of its maximum capacity.

[0048] Specifically, when the refueling amount exceeds the preset full state, the refueling pump and the refueling valve are immediately closed, and the advance amount is determined again.

[0049] Specifically, when the refueling amount does not reach the preset full state, the fuel tank leakage alarm is triggered and the fuel tank fault is checked.

[0050] Through dynamic learning and real-time output from the advance fuel prediction model, the system precisely adjusts the parameters of the fuel valve and pump based on the flow inertia characteristics during the refueling process, ensuring efficient and accurate refueling. Upon completion of refueling, the system can promptly detect whether the fuel level has reached the preset full level and take appropriate measures based on the actual situation, effectively preventing fuel spills or leaks, ensuring refueling safety, and improving the overall reliability and intelligence level of drone refueling.

[0051] See also Figure 4 As shown in FIG, it is a schematic diagram of the structure of a UAV refueling flow control system based on intelligent interaction according to an embodiment of the present invention, including: A flow monitoring module, which is used to refuel the UAV using a flow controller and monitor the refueling flow data in real time, wherein the flow data includes the instantaneous value and average value of the refueling flow; An inertia analysis module, connected to the flow monitoring module, is used to analyze the inertia characteristics of the refueling flow based on the flow data, wherein the inertia characteristics include the flow rate change rate, flow fluctuation amplitude and flow stabilization time; An advance learning module, connected to the inertia analysis module, is used to learn the inertia characteristics to determine the advance of the refueling flow control, wherein the advance includes the valve advance and the pump advance; The regulating module is connected to the advance learning module and is used to control the refueling valve and the refueling pump according to the valve advance and the pump advance respectively.

[0052] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0053] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A UAV refueling flow control method based on intelligent interaction, characterized in that: include: Refueling the UAV using a flow controller and monitoring flow data of the refueling flow in real time, wherein the flow data includes an instantaneous value and an average value of the refueling flow; Analyzing the inertial characteristics of the refueling flow based on the flow data, wherein the inertial characteristics include flow rate change rate, flow fluctuation amplitude, and flow stabilization time; Learning the inertia characteristics to determine an advance amount for refueling flow control, wherein the advance amount includes a valve advance amount and a pump advance amount; The refueling valve and the refueling pump are controlled respectively according to the valve advance amount and the pump advance amount.

2. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 1 is characterized in that: The steps to analyze the inertial characteristics of refueling flow include: Calculate the flow rate change rate, wherein the flow rate change rate is the change in the refueling flow rate per unit time; Determining the flow fluctuation amplitude, wherein the flow fluctuation amplitude is the difference between the maximum value and the minimum value of the refueling flow within a preset time; The flow stabilization time is measured, wherein the flow stabilization time is the length of time the refueling flow reaches a preset stable value and remains at the preset stable value.

3. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 2 is characterized in that: The steps for learning inertial features include: Preprocessing the inertial characteristics to form corresponding inertial pre-data; Build the corresponding advance quantity prediction model; The inertia advance data is learned using the advance prediction model to generate the valve advance and the pump advance.

4. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 3 is characterized in that: The steps of preprocessing the inertial features to form corresponding inertial pre-data include: Filter outliers in the inertial features, pre-process the inertial features, and form corresponding inertial pre-data, wherein: The preprocessing is to segment the inertial features according to a standard learning rate; The standard learning rate is a learning rate that can be recognized by the advance prediction model, and for single learning, the corresponding standard learning rate is a single learning rate.

5. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 4 is characterized in that: The steps to build a lead time forecast model include: Collect historical inertial characteristics of the UAV refueling process; Performing Fourier transform on the historical inertia features to form corresponding transformation features, and using the transformation features as the input layer of the lead time prediction model; Determine the number of hidden layers of the lead prediction model, wherein the number of hidden layers is adjusted according to the complexity of the historical inertia characteristics.

6. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 5 is characterized in that: In response to the input of the inertia prediction data, the learning process of the advance prediction model is mobilized, and the output of the advance prediction model includes the valve advance and the pump advance, wherein the valve advance is used to adjust the opening of the refueling valve, and the pump advance is used to adjust the speed of the refueling pump.

7. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 6, characterized in that: The refueling valve and the refueling pump are adjusted according to the valve advance and the pump advance, and when the refueling process is completed, whether the refueling amount reaches a preset full state is detected, wherein the preset full state is that the oil level in the UAV fuel tank reaches a specified proportion of its maximum capacity.

8. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 7 is characterized in that: When the refueling amount exceeds the preset full state, the refueling pump and the refueling valve are immediately closed, and the advance amount is determined again.

9. The method for controlling the refueling flow of a UAV based on intelligent interaction according to claim 8, characterized in that: When the refueling amount does not reach the preset full state, a fuel tank leakage alarm is triggered and a fuel tank fault check is performed.

10. A system based on the intelligent interaction-based UAV refueling flow control method according to any one of claims 1 to 9, characterized in that: include: A flow monitoring module, which is used to refuel the UAV using a flow controller and monitor the flow data of the refueling flow in real time, wherein the flow data includes the instantaneous value and average value of the refueling flow; an inertia analysis module connected to the flow monitoring module, configured to analyze the inertia characteristics of the refueling flow based on the flow data, wherein the inertia characteristics include flow rate change rate, flow fluctuation amplitude, and flow stabilization time; an advance learning module connected to the inertia analysis module, configured to learn the inertia characteristics to determine an advance for refueling flow control, wherein the advance includes a valve advance and a pump advance; The regulating module is connected to the advance learning module and is used to control the refueling valve and the refueling pump according to the valve advance and the pump advance.

Images