An unmanned aerial vehicle logistics transportation intelligent management platform fusing multi-source data

Abstract

The application is suitable for the field of unmanned aerial vehicle energy consumption management and intelligent control technology, and provides an unmanned aerial vehicle logistics transportation intelligent management platform fusing multiple source data.The platform comprises a flux regulation module, which is used for predicting the gas release flux in the unmanned aerial vehicle cabin per unit time, and dynamically adjusting the ventilation flow rate of the ventilation system according to the gas release flux, so as to maintain the gas concentration in the cabin in a gas concentration steady state interval corresponding to the optimal period of thermal balance of the cabin gas.The technical scheme of the application not only discloses the influence law of the micro-thermal effect of volatile pollutants on the energy efficiency of the unmanned aerial vehicle battery, but also makes the unmanned aerial vehicle battery continuously run in the energy efficiency optimal state corresponding to the peak discharge efficiency interval through real-time trend correction, so as to significantly improve the energy utilization rate and flight stability of the unmanned aerial vehicle under the task of carrying recyclable materials.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of unmanned aerial vehicle energy consumption management and intelligent control, and particularly relates to an unmanned aerial vehicle logistics transportation intelligent management platform fusing multi-source data. BACKGROUND

[0002] The energy consumption management in the existing unmanned aerial vehicle logistics transportation mainly focuses on flight path optimization, battery remaining amount prediction and power distribution strategy, and usually prolongs the endurance time by improving the flight control algorithm or increasing the battery energy density. However, these schemes mostly assume that the cabin thermal environment is constant, and ignore the influence of the load characteristics on the battery working state. For agricultural or recycling unmanned aerial vehicles, volatile recycling materials such as pesticide bottles, fertilizer barrels or other chemical containers need to be carried back in the return phase. These carriers will release gas in the closed cabin, change the cabin temperature and gas composition, and thus potentially affect the battery discharge efficiency.

[0003] Some unmanned aerial vehicles have cabin temperature detection and basic ventilation systems, but the existing control methods mostly use fixed threshold triggering, which can only realize the control at the safety protection level, and cannot realize the precise regulation at the energy efficiency level combined with the nonlinear temperature response law of the battery discharge efficiency. Especially when the environmental temperature is close to the critical point of the battery performance, the slight temperature fluctuation caused by the volatile gas may significantly affect the discharge efficiency, and the existing control strategy cannot identify and dynamically respond to this micro-thermal effect.

[0004] Therefore, in the task of carrying volatile recycling materials, the unmanned aerial vehicle generally has problems such as inaccurate energy consumption regulation, environmental response lag and insufficient battery energy efficiency utilization, which limits its flight stability and energy management level in complex task environments. SUMMARY

[0005] The purpose of the present application is to provide an unmanned aerial vehicle logistics transportation intelligent management platform fusing multi-source data, which aims to solve the problems proposed in the background.

[0006] The present application is implemented as follows: an unmanned aerial vehicle logistics transportation intelligent management platform fusing multi-source data, the platform comprising:

[0007] A volatile feature identification module is configured to identify the volatile feature parameters of the current recycling material carried by the unmanned aerial vehicle in the transportation process, obtain the historical flight records of the unmanned aerial vehicle, and extract reference samples matched with the volatile feature parameters of the current recycling material and the flight environment parameters from the historical flight records.

[0008] The regularity analysis module is configured to analyze the reference sample, obtain discharge efficiency monitoring data of the unmanned aerial vehicle battery under different cabin residence durations of the historical recyclables, and determine whether the discharge efficiency presents a change trend of first increasing and then decreasing with the increase of the cabin residence duration, and identify a corresponding discharge efficiency peak interval in a case where the change trend is determined to exist.

[0009] The time period determination module is configured to confirm the cabin residence duration corresponding to the discharge efficiency peak interval as an optimal cabin gas heat balance time period, and control the ventilation system in the unmanned aerial vehicle cabin to enter a working state after the optimal cabin gas heat balance time period is reached during the process of transporting the current recyclable by the unmanned aerial vehicle.

[0010] The flux control module is configured to predict the gas release flux in the unmanned aerial vehicle cabin per unit time, and dynamically adjust the ventilation flow rate of the ventilation system according to the gas release flux, so as to maintain the gas concentration in the cabin in a gas concentration steady state interval corresponding to the optimal cabin gas heat balance time period.

[0011] As a further limitation of the technical scheme of the embodiment of the present application, the volatile characteristic parameters include: the type of volatile matter, the residual amount of volatile matter, and the opening characteristic parameters of the container.

[0012] As a further limitation of the technical scheme of the embodiment of the present application, the flight environment parameters include: external environment temperature, environment humidity, flight height, air pressure, and wind speed.

[0013] As a further limitation of the technical scheme of the embodiment of the present application, the cabin residence duration refers to the time that is continuously calculated since the recyclable is identified and placed in the unmanned aerial vehicle cabin space.

[0014] As a further limitation of the technical scheme of the embodiment of the present application, the regularity analysis module specifically includes:

[0015] The data extraction unit is configured to analyze the reference sample, and obtain discharge efficiency monitoring data of the unmanned aerial vehicle battery under different cabin residence durations of the historical recyclables corresponding to the reference sample.

[0016] The sequence construction unit is configured to sort the discharge efficiency of the unmanned aerial vehicle battery in an order of gradually increasing cabin residence duration, and obtain a discharge efficiency sequence.

[0017] The trend analysis unit is configured to perform trend analysis on the discharge efficiency sequence, determine whether the discharge efficiency presents a change feature of first increasing and then decreasing with the increase of the cabin residence duration, and identify a corresponding discharge efficiency peak interval in a case where the change feature is determined to exist.

[0018] As a further limitation of the technical scheme of the embodiment of the present application, the discharge efficiency peak interval refers to the interval range of the peak point and its adjacent discharge efficiency which remains relatively stable in the discharge efficiency sequence.

[0019] As a further limitation of the technical scheme of the embodiment of the present application, the unmanned aerial vehicle is provided with a ventilation system, and the ventilation system is in communication with the space in the cabin of the unmanned aerial vehicle, and the ventilation system has a gas flow adjustment and control function.

[0020] As a further limitation of the technical scheme of the embodiment of the present application, the flux control module specifically comprises:

[0021] A flux prediction unit is configured to call a pre-trained gas volatilization kinetics model, and predict the gas release flux of the current recyclable material per unit time in the cabin of the unmanned aerial vehicle according to the volatilization characteristic parameters and flight environment parameters of the current recyclable material;

[0022] An instruction generation unit is configured to generate a ventilation flow rate adjustment instruction after the duration of the current recyclable material carried by the unmanned aerial vehicle reaches the optimal period of the cabin gas heat balance, and send the instruction to the ventilation system;

[0023] An execution control unit is configured to control the ventilation system to perform ventilation operation according to the ventilation flow rate adjustment instruction, so as to discharge part of the gas generated by the volatilization of the current recyclable material in the cabin, and maintain the gas concentration in the cabin in a gas concentration steady state interval corresponding to the optimal period of the cabin gas heat balance.

[0024] As a further limitation of the technical scheme of the embodiment of the present application, the pre-trained gas volatilization kinetics model is established based on a composite mathematical model of gas molecular diffusion mechanism and heat conduction mechanism by collecting gas volatilization data of recyclable materials per unit time under different combinations of flight environment parameters and recyclable material volatilization characteristic parameters, and is used to predict the gas release flux of recyclable materials under specific flight environment parameters and volatilization characteristic parameters.

[0025] As a further limitation of the technical scheme of the embodiment of the present application, when the ventilation flow rate of the ventilation system is dynamically adjusted, the discharge efficiency monitoring data of the battery of the unmanned aerial vehicle is monitored in real time, and the ventilation flow rate is analyzed and dynamically corrected based on the change trend of the monitoring data, so as to maintain the battery of the unmanned aerial vehicle in the energy efficiency optimal state corresponding to the discharge efficiency peak interval.

[0026] Compared with the prior art, the present application has the following beneficial effects:

[0027] The application establishes the correlation mechanism between the volatilization behavior of recyclables, the change of the cabin thermal environment and the discharge efficiency of the unmanned aerial vehicle battery by fusing multi-source data analysis and gas dynamics modeling. By identifying the volatilization characteristic parameters of recyclables, extracting the historical flight data law, and determining the optimal period of cabin gas thermal balance based on the discharge efficiency peak interval, the system can dynamically regulate the ventilation system during the return process carrying recyclables, and realize the adaptive balance of the cabin gas concentration and temperature.

[0028] The technology not only reveals the influence law of the micro-thermal effect of volatile pollutants on the energy efficiency of the unmanned aerial vehicle battery, but also makes the unmanned aerial vehicle battery continuously run in the energy efficiency optimal state corresponding to the discharge efficiency peak interval through real-time trend correction, thereby significantly improving the energy utilization rate and flight stability of the unmanned aerial vehicle under the task of carrying recyclables. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 The application architecture diagram of the platform provided for the embodiments of the application is shown.

[0030] Figure 2 The structural block diagram of the flux regulation module in the platform provided for the embodiments of the application is shown.

[0031] Figure 3 The structural block diagram of the flux regulation module in the platform provided for the embodiments of the application is shown. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the application clearer, the application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0033] Figure 1 The application architecture diagram of the platform provided for the embodiments of the application is shown.

[0034] Specifically, a multi-source data fusion unmanned aerial vehicle logistics transportation intelligent management platform comprises:

[0035] The volatilization characteristic identification module 100 is configured to identify the volatilization characteristic parameters of the current recyclables carried by the unmanned aerial vehicle during transportation, obtain the historical flight records of the unmanned aerial vehicle, and extract reference samples matched with the volatilization characteristic parameters of the current recyclables and the flight environment parameters. The unmanned aerial vehicle is provided with a ventilation system, and the ventilation system is in communication with the cabin space of the unmanned aerial vehicle. The ventilation system has a gas flow regulation and control function.

[0036] The volatilization characteristic parameters include the type of volatilization, the residual amount of volatilization and the opening characteristic parameters of the container. The flight environment parameters include the external environment temperature, the environment humidity, the flight height, the air pressure and the wind speed.

[0037] In the embodiment of the present application, the unmanned aerial vehicle includes a cabin space arranged at the lower part of the body and a ventilation system communicating with the cabin space. The cabin space is used to accommodate the recyclables, and its structure is in a closed or semi-closed state to prevent gas leakage or external air disturbance during transportation. The ventilation system is arranged at one end of the cabin space and includes an air flow guide assembly, a fan assembly and a gas flow adjusting mechanism inside, which can adjust the ventilation flow rate according to the control instruction to regulate the gas condition in the cabin. The unmanned aerial vehicle can use existing automatic clamping mechanism or delivery device to realize the grabbing and loading of recyclables. Such structure belongs to the prior art, and the present application is not limited.

[0038] The unmanned aerial vehicle is particularly suitable for recycling transportation tasks during the return journey of farmland operation, and can collect and transport the recyclables such as empty pesticide bottles, fertilizer barrels or other recyclables with residual chemical components distributed in the farmland after completing the agricultural material distribution task. Such recyclables usually have volatility, and will continuously release gas after being placed in the cabin space, causing the temperature in the cabin to rise and the gas composition to change.

[0039] The volatility characteristic parameters include the type of volatile matter, the residual amount of volatile matter and the opening characteristic parameters of the container. The type of volatile matter is used to characterize the chemical properties of the gas and its vapor pressure characteristics, the residual amount reflects the total volume or mass of the volatile matter, and the opening characteristic parameters describe the geometric characteristics and sealing degree of the container opening, which directly affect the gas release rate. The recyclables usually have a multi-component chemical system, and the opening state and residual amount are uneven, resulting in a nonlinear change in the volatilization process in the cabin space.

[0040] When sample screening is performed on historical flight records, the matching relationship is not required to be completely consistent, but to meet the similar conditions within the preset parameter threshold range. The matching process comprehensively considers the volatility characteristic parameters and flight environment parameters, including external environment temperature, humidity, air pressure, flight height and wind speed, to ensure that the samples have comparability in main physical conditions. The purpose of multidimensional screening is to ensure the representativeness of the samples and reduce the deviation caused by environmental differences.

[0041] The reference sample is used to provide a historical flight data basis with similar volatilization conditions and flight environment. When there are multiple candidate samples, the system determines the sample with the highest comprehensive matching degree according to the preset similarity calculation model for subsequent rule analysis.

[0042] The historical flight record is derived from the data collection results of the unmanned aerial vehicle in the past transportation tasks, and specifically includes flight environment data (external temperature and humidity, air pressure, wind speed, flight height), cabin environment data (temperature, gas concentration, battery temperature), load data (recycled material type, quantity, loading time), and energy consumption data (current, voltage, discharge efficiency change).

[0043] The present application is aimed at the phenomenon that when carrying recycled materials with volatility, the recycled materials continue to release gas after entering the cabin space, causing the temperature in the cabin to rise. Since the cabin space is adjacent to the battery module, this temperature rise will affect the working temperature of the battery to some extent, thereby causing the discharge efficiency to change. The present application studies the influence law of the volatile process of the recycled material on the discharge efficiency of the battery through comparison and characteristic parameter analysis of the historical flight data, and provides a basis for energy efficiency regulation of the unmanned aerial vehicle in the task of carrying recycled materials.

[0044] Further, the unmanned aerial vehicle logistics transportation intelligent management platform fusing multi-source data further comprises:

[0045] The rule analysis module 200 is configured to analyze the reference sample, obtain the discharge efficiency monitoring data of the battery of the unmanned aerial vehicle under different cabin residence durations of the historical recycled material, and determine whether the discharge efficiency presents a first-increasing and then-decreasing change trend with the increase of the cabin residence duration based on the monitoring data. In a case where it is determined that the change trend exists, a corresponding discharge efficiency peak interval is identified.

[0046] The cabin residence duration refers to the time that is continuously calculated since the recycled material is identified and placed in the cabin space of the unmanned aerial vehicle.

[0047] Specifically, Figure 2 The structure block diagram of the rule analysis module 200 in the platform provided by the embodiment of the present application is shown.

[0048] In the preferred embodiment provided by the present application, the rule analysis module 200 specifically comprises:

[0049] The data extraction unit 201 is configured to analyze the reference sample, and obtain the discharge efficiency monitoring data of the battery of the unmanned aerial vehicle under different cabin residence durations of the historical recycled material corresponding to the reference sample.

[0050] The sequence construction unit 202 is configured to sort the discharge efficiency of the battery of the unmanned aerial vehicle in an order of gradually increasing cabin residence duration, and obtain a discharge efficiency sequence.

[0051] The trend analysis unit 203 is configured to perform trend analysis on the discharge efficiency sequence, determine whether the discharge efficiency increases first and then decreases with the increase of the cabin residence time, and identify the corresponding discharge efficiency peak interval when it is determined that the change characteristic exists. The discharge efficiency peak interval refers to a range of intervals in which the peak point and the adjacent discharge efficiency remain relatively stable in the discharge efficiency sequence.

[0052] In the embodiment of the present application, the research is based on the condition that the external environment temperature is close to the critical point of battery performance. At this time, the discharge efficiency of the battery is extremely sensitive to small temperature changes. Since the release amount of volatile gas of the recyclables in the cabin space is limited, the temperature change caused by it is usually only 2-3℃. When the ambient temperature is slightly lower than the optimal working temperature range of the battery, the slight warming effect will accelerate the chemical reaction rate inside the battery, reduce the ion migration resistance, and increase the discharge efficiency. When the cabin temperature further rises and exceeds the optimal working temperature range of the battery, the electrolyte viscosity decreases, the electrode polarization intensifies, and the internal resistance increases, and the discharge efficiency decreases. Therefore, the discharge efficiency increases first and then decreases with the increase of the cabin residence time, and the peak interval reflects the best state of the battery under the influence of the gas thermal effect to achieve thermal stability and energy efficiency balance.

[0053] The rule analysis module 200 identifies the peak interval through analysis and trend analysis of historical reference sample data. The specific implementation process is as follows:

[0054] The data extraction unit 201 analyzes the reference sample from the historical flight record and extracts the battery discharge efficiency monitoring data under different cabin residence times. The monitoring data can be obtained by calculating the voltage, current, temperature and capacity change in the battery management system (Battery Management System, BMS). The BMS system belongs to the prior art, and its data interface can record the battery discharge power and temperature change curve in real time, providing a data basis for subsequent calculation.

[0055] The sequence construction unit 202 sorts the extracted discharge efficiency values in the order of gradually increasing cabin residence time to form a continuous discharge efficiency sequence. This process can be realized by time series resampling or interpolation algorithm to ensure the uniformity and comparability of the sampling points. The sequence construction unit provides a clear time correlation structure for trend analysis after forming the discharge efficiency sequence.

[0056] The trend analysis unit 203 adopts an analysis method based on gradient change rate or curve fitting to identify the change trend of the discharge efficiency sequence. Specifically, the inflection point position of the discharge efficiency curve can be determined by using a polynomial fitting, a moving average or a second derivative analysis method. If it is identified that the curve presents a trend of first rising and then falling, the peak point and its adjacent relatively stable interval, i.e. the discharge efficiency peak interval, are further located. The algorithms used in the analysis process are all based on existing time series analysis and signal processing methods, and automatic identification can be realized through a built-in algorithm library.

[0057] The discharge efficiency peak interval represents a period in which the discharge efficiency of the unmanned aerial vehicle battery is optimal and relatively stable under the influence of the temperature change caused by the cabin gas volatilization. Identifying this interval is of great significance. On the one hand, it can be used to determine the beneficial balance stage of the cabin gas thermal effect, providing a basis for the timing of subsequent ventilation control; on the other hand, it can provide a reference for battery energy efficiency management, so that the unmanned aerial vehicle can maintain a high energy efficiency operating state when transporting recyclables, avoiding excessive heating and causing energy loss or potential thermal safety risks.

[0058] Further, the unmanned aerial vehicle logistics transportation intelligent management platform fusing multiple source data further comprises:

[0059] The period determination module 300 is configured to confirm the cabin residence duration corresponding to the discharge efficiency peak interval as the optimal cabin gas thermal balance period, and control the unmanned aerial vehicle cabin ventilation system to enter a working state after the optimal cabin gas thermal balance period is reached during the process of transporting the current recyclable by the unmanned aerial vehicle.

[0060] The flux regulation module 400 is configured to predict the gas release flux in the cabin of the unmanned aerial vehicle per unit time, and dynamically adjust the ventilation flow rate of the ventilation system according to the gas release flux, so as to maintain the gas concentration in the cabin in a gas concentration steady state interval corresponding to the optimal cabin gas thermal balance period.

[0061] Specifically, Figure 3 The structure block diagram of the flux regulation module 400 in the platform provided by the embodiment of the application is shown.

[0062] In the preferred embodiment provided by the application, the flux regulation module 400 specifically comprises:

[0063] The flux prediction unit 401 is configured to call a pre-trained gas volatilization kinetics model, and predict the gas release flux of the current recyclable per unit time in the cabin of the unmanned aerial vehicle according to the volatilization characteristic parameters and flight environment parameters of the current recyclable;

[0064] The instruction generation unit 402 is configured to generate a ventilation flow rate adjustment instruction after the duration of the current recyclable carried by the unmanned aerial vehicle reaches the optimal cabin gas thermal balance period, and send the ventilation flow rate adjustment instruction to the ventilation system;

[0065] The execution control unit 403 is configured to control the ventilation system to perform ventilation operation according to the ventilation flow rate adjustment instruction, so as to discharge part of the gas in the cabin generated by the current recovered object volatilization, and maintain the gas concentration in the cabin at the gas concentration steady state interval corresponding to the optimal period of thermal balance of the cabin gas.

[0066] The pre-trained gas volatilization kinetics model is trained by a large amount of historical experimental data and flight monitoring data. The data sources include the measured records of the gas volatilization amount of the recovered object per unit time under the combined conditions of different flight environment parameters (external temperature, humidity, air pressure, wind speed, flight height) and different recovered object volatilization characteristic parameters (volatile type, residual amount, opening characteristic parameter). Through regression analysis and parameter fitting of the above data, a composite mathematical model based on the gas molecular diffusion mechanism and the heat conduction mechanism is established. The model belongs to the mature existing technology category, and can be trained by means of machine learning algorithms (such as multiple regression, support vector regression or BP neural network) to predict the gas release flux under different conditions. On this basis, the model is embedded into the flux prediction unit as a functional component.

[0067] The period determination module 300 and the flux regulation module 400 jointly constitute the execution and control stage of the unmanned aerial vehicle in the process of carrying the recovered object. The former is used to determine the most suitable ventilation opportunity, and the latter is responsible for implementing the dynamic regulation of the gas concentration and the thermal environment after the opportunity is reached. The two work together to maintain the gas and thermal balance state of the cabin space, thereby ensuring the stability of the battery discharge efficiency.

[0068] In the embodiment of the present application, the pre-trained gas volatilization kinetics model is trained by a large amount of historical experimental data and flight monitoring data. The data sources include the measured records of the gas volatilization amount of the recovered object per unit time under the combined conditions of different flight environment parameters (external temperature, humidity, air pressure, wind speed, flight height) and different recovered object volatilization characteristic parameters (volatile type, residual amount, opening characteristic parameter). Through regression analysis and parameter fitting of the above data, a composite mathematical model based on the gas molecular diffusion mechanism and the heat conduction mechanism is established. The model belongs to the mature existing technology category, and can be trained by means of machine learning algorithms (such as multiple regression, support vector regression or BP neural network) to predict the gas release flux under different conditions. On this basis, the model is embedded into the flux prediction unit as a functional component.

[0069] In the execution process of the flux prediction unit 401, the volatilization characteristic parameters of the current recovered object are first obtained from the volatilization characteristic identification module, and the external flight environment parameters are read from the flight control system in real time. Then, the above parameters are input into the pre-trained gas volatilization kinetics model, and the gas release flux per unit time is calculated and output by the model. The prediction result can reflect the change trend of the gas concentration in the cabin space with time, and provide a quantitative basis for subsequent ventilation control.

[0070] The instruction generating unit 402 generates a ventilation flow rate adjustment instruction according to the gas release flux value output by the flux prediction unit 401 after the time length of the current recyclable object carried by the UAV reaches the optimal cabin gas heat balance period determined by the period determination module 300. The instruction includes control parameters such as ventilation opening time, target flow rate, and duration, and can be sent to the execution end of the ventilation system through the task control bus of the UAV main control chip. This process uses existing UAV task scheduling and communication control technology to ensure the real-time and accuracy of the transmission of the control instruction.

[0071] The execution control unit 403 receives the ventilation flow rate adjustment instruction sent by the instruction generating unit and drives the fan control module or air valve adjustment mechanism in the ventilation system to perform corresponding operations to realize dynamic adjustment of the ventilation flow. The execution control unit can collect real-time operation state parameters (fan speed, gas flow sensor signal, cabin gas concentration change, etc.) of the ventilation system and compare them with the set steady state interval value. When the gas concentration deviates from the steady state interval, the ventilation rate is automatically corrected to realize closed-loop control. This process can be realized based on the existing PID regulation algorithm or fuzzy control algorithm.

[0072] The flux regulation module 400 functions to, after determining the optimal cabin gas heat balance period, actively adjust the cabin gas concentration and temperature during the return process of the UAV through a combination of quantitative prediction and dynamic regulation, so as to maintain the battery in an energy efficiency optimal state corresponding to the peak discharge efficiency interval. This control process directly addresses the core research point of the present application, i.e., the influence of the change in the cabin microenvironment caused by the volatilization of recyclable objects on the battery discharge performance, realizes real-time identification and dynamic suppression of the influence, and ensures the energy utilization efficiency and flight safety of the UAV under the task of carrying recyclable objects.

[0073] Further, the UAV logistics transportation intelligent management platform fusing multi-source data further comprises:

[0074] When the ventilation flow rate of the ventilation system is dynamically adjusted, the discharge efficiency monitoring data of the UAV battery is monitored in real time, and the ventilation flow rate is analyzed and dynamically corrected based on the change trend of the monitoring data, so as to maintain the battery in an energy efficiency optimal state corresponding to the peak discharge efficiency interval.

[0075] In the embodiment of the present application, when the system dynamically adjusts the ventilation flow rate of the ventilation system, the system adaptively corrects the adjustment direction of the ventilation system based on the real-time monitoring result of the battery discharge efficiency of the unmanned aerial vehicle. Specifically, the system continuously collects the voltage, current and temperature parameters output by the battery management system, calculates the change rate of the instantaneous discharge efficiency, and compares it with the reference trend curve corresponding to the peak value interval of the discharge efficiency. When it is detected that the change trend of the discharge efficiency is approaching the rising interval before the peak point, it indicates that the cabin gas concentration is decreasing too fast and the ventilation volume is too large, and the system automatically reduces the ventilation flow rate to slow down the cabin gas discharge rate and restore the thermal balance. When it is detected that the change trend of the discharge efficiency is approaching the falling interval after the peak point, it indicates that the cabin gas concentration is not low enough and the ventilation volume is too small, and the system correspondingly increases the ventilation flow rate to speed up the gas discharge and reduce the cabin temperature.

[0076] Through the trend determination and dynamic correction mechanism, the system can continuously correct the working parameters of the ventilation system according to the real-time feedback of the battery working state during flight, so that the unmanned aerial vehicle battery always maintains the most energy-efficient state corresponding to the peak value interval of the discharge efficiency, and the adaptive closed-loop regulation and control of energy management can be realized without external intervention.

[0077] In summary, the overall beneficial effects of the present application are that by constructing an unmanned aerial vehicle logistics transportation intelligent management platform integrating multiple sources of data, dynamic coupling control between the volatile characteristics of recovered materials, the change of the cabin thermal environment and the battery energy efficiency management is achieved. The present application first models and controls the influence of the cabin micro-temperature change caused by volatile gases on the discharge efficiency of the unmanned aerial vehicle battery during the process of carrying volatile agricultural recovered materials (such as pesticide bottles, fertilizer barrels, etc.). Through the collaborative operation of the volatile characteristic identification module, the rule analysis module, the time period determination module and the flux regulation module, the platform can automatically extract the rule characteristics from the historical flight data, identify the optimal period of thermal balance of the cabin gas, and predict the cabin gas release flux based on the gas volatilization kinetics model, so as to actively control the ventilation system during the return journey, and maintain the cabin temperature and gas concentration in the optimal steady state interval.

[0078] The present application can realize adaptive optimization of energy management without the intervention of external sensors, and has good autonomous adjustment and energy efficiency stability characteristics. The core technical innovation is to establish a quantitative correlation model between gas volatilization, heat conduction and battery discharge behavior, and dynamically correct the ventilation control strategy using real-time monitoring data, which realizes intelligent energy efficiency management of the unmanned aerial vehicle when carrying complex chemical residue recovered materials. This method not only effectively avoids the performance degradation or safety hazards of the battery caused by heat accumulation in the cabin, but also maintains a high discharge efficiency within the peak value interval of energy efficiency, significantly improving the endurance performance and energy utilization rate of the unmanned aerial vehicle.

[0079] The application has wide application prospects. Firstly, it can be applied to an intelligent recycling return system of an agricultural unmanned aerial vehicle, realize efficient recycling and transportation of farmland waste, and give consideration to environmental protection and energy management; secondly, it can be extended to the unmanned recycling field of hazardous chemicals, small pollution sources or medical samples, and be used to solve the cabin thermal steady-state control problem when carrying substances with micro-volatility characteristics; thirdly, it can provide data support for the fusion optimization of the battery management system (BMS) and the flight control system of the unmanned aerial vehicle, and form an extensible energy efficiency regulation algorithm framework. Overall, the application has high engineering realizability and popularization value, and can play a significant technical advantage in the fields of low-altitude logistics transportation, intelligent recycling and unmanned transportation.

[0080] It should be understood that although each step in the flowchart of each embodiment of the application is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or sub-steps or stages of other steps.

[0081] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of each method. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0082] Any technical features in the above-described embodiments can be combined in any manner, and for the sake of brevity, not all possible combinations are described, however, as long as there is no contradiction, any technical features of the above-described embodiments can be combined.

[0083] The above-described embodiments only express several embodiments of the present application, which are described in a more specific and detailed manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the scope of protection of the patent of the present application should be subject to the appended claims.

[0084] The above-described embodiments are only the preferred embodiments of the present application, and are not used to limit the present application, and any modifications, equivalent replacements and improvements made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. An unmanned aerial vehicle logistics transportation intelligent management platform for fusing multi-source data, characterized in that, The platform comprises: a volatile feature identification module, configured to identify a volatile feature parameter of a current recyclable object carried by the UAV in the transportation process, acquire historical flight records of the UAV, and extract a reference sample matching the volatile feature parameter of the current recyclable object and flight environment parameters therefrom; a rule analysis module, configured to analyze the reference sample, acquire discharge efficiency monitoring data of the battery of the UAV under different cabin residence durations of historical recyclable objects, and determine whether the discharge efficiency presents a first-increasing-and-then-decreasing trend with the increase of the cabin residence duration based on the monitoring data, and identify a corresponding discharge efficiency peak interval in a case where the trend exists; a time period determination module, configured to confirm the cabin residence duration corresponding to the discharge efficiency peak interval as an optimal cabin gas thermal equilibrium time period, and control the ventilation system in the cabin of the UAV to enter a working state after the optimal cabin gas thermal equilibrium time period is reached in the process of transporting the current recyclable object by the UAV; a flux regulation module, configured to predict a gas release flux in the cabin of the UAV per unit time, and dynamically adjust a ventilation flow rate of the ventilation system based thereon to maintain a gas concentration in the cabin in a gas concentration steady state interval corresponding to the optimal cabin gas thermal equilibrium time period. 2.The unmanned aerial vehicle logistics transportation intelligent management platform fusing multi-source data according to claim 1, wherein, The volatile feature parameter comprises a type of volatile matter, a residual amount of the volatile matter, and an opening feature parameter of the container. 3.The UAV logistics transportation intelligent management platform fusing multi-source data according to claim 1, wherein, The flight environment parameter comprises an external environment temperature, an environment humidity, a flight height, an air pressure, and a wind speed. 4.The UAV logistics transportation intelligent management platform fusing multi-source data of claim 1, wherein, The cabin residence duration refers to a time counted continuously since the recyclable object is identified and placed in the cabin space of the UAV. 5.The UAV logistics transportation intelligent management platform fusing multi-source data of claim 1, wherein, The rule analysis module specifically comprises: a data extraction unit, configured to analyze the reference sample, and acquire discharge efficiency monitoring data of the battery of the UAV under different cabin residence durations of the historical recyclable object corresponding to the reference sample; a sequence construction unit, configured to sort the discharge efficiency of the battery of the UAV in an order of gradually increasing cabin residence duration to obtain a discharge efficiency sequence; a trend analysis unit, configured to perform trend analysis on the discharge efficiency sequence, determine whether the discharge efficiency presents a first-increasing-and-then-decreasing characteristic with the increase of the cabin residence duration, and identify a corresponding discharge efficiency peak interval in a case where the characteristic exists. 6.The UAV logistics transportation intelligent management platform fusing multi-source data of claim 5, wherein, The discharge efficiency peak interval refers to an interval range in which a peak point and adjacent discharge efficiencies of the discharge efficiency sequence remain relatively stable. 7.The UAV logistics transportation intelligent management platform fusing multi-source data of claim 1, wherein, The UAV is provided with a ventilation system, and the ventilation system is in communication with a cabin space of the UAV, and the ventilation system has a gas flow regulation and control function. 8.The UAV logistics transportation intelligent management platform fusing multi-source data of claim 7, wherein, The flux regulation module specifically comprises: a flux prediction unit, configured to call a pre-trained gas volatilization kinetics model, predict a gas release flux of the current recyclable object per unit time in the cabin of the UAV according to the volatile feature parameter of the current recyclable object and the flight environment parameter, and an instruction generation unit, configured to generate a ventilation flow rate adjustment instruction after a duration in which the UAV carries the current recyclable object reaches the optimal cabin gas thermal equilibrium time period, and send the instruction to the ventilation system. The execution control unit is configured to control the ventilation system to perform ventilation operation according to the ventilation flow rate adjustment instruction, so as to discharge part of the gas in the cabin generated by the current recovered object volatilization, and maintain the gas concentration in the cabin at a gas concentration steady state interval corresponding to the optimal period of thermal equilibrium of the gas in the cabin. 9.The UAV logistics transportation intelligent management platform fusing multi-source data of claim 8, wherein, The pre-training gas volatilization kinetics model is used to predict the gas release flux of the recovered object under specific flight environment parameters and volatilization characteristic parameters by collecting the gas volatilization amount data of the recovered object per unit time under different combinations of flight environment parameters and volatilization characteristic parameters, and establishing a composite mathematical model based on the gas molecule diffusion mechanism and the heat conduction mechanism. 10.The UAV logistics transportation intelligent management platform fusing multi-source data of claim 8, wherein, When the ventilation flow rate of the ventilation system is dynamically adjusted, the discharge efficiency monitoring data of the unmanned aerial vehicle battery is monitored in real time, and the ventilation flow rate is analyzed and dynamically corrected based on the change trend of the monitoring data, so as to maintain the unmanned aerial vehicle battery in the energy efficiency optimal state corresponding to the discharge efficiency peak interval.

Images