Unmanned aerial vehicle battery charging scheduling method and device, terminal and medium

Abstract

The invention discloses an unmanned aerial vehicle battery charging scheduling method and device, a terminal and a medium, according to the scheme, battery health state data and task attributes are introduced to serve as decision-making bases, dynamic matching logic and hierarchical charging conditions are combined, and collaborative optimization of task requirements, battery states and power grid loads is achieved. The problem that charging scheduling and task requirements are disjointed in the prior art is solved, delay of emergency tasks due to battery charging is avoided, the charging behavior is optimized to reduce the operation cost and guarantee the stability of a power grid, dynamic matching and global optimization of battery resources, operation tasks and power grid energy are achieved, and the service life of the power grid is prolonged. Therefore, the operation safety is synchronously guaranteed on the system level, the operation and maintenance efficiency is improved, and the comprehensive cost is reduced.

Description

Technical Field

[0001] This application relates to the field of automated inspection technology for unmanned aerial vehicles (UAVs), and in particular to a method, device, terminal, and medium for scheduling battery charging for UAVs. Background Technology

[0002] With the large-scale and routine deployment of drones in industrial scenarios such as power line inspection and emergency mapping, drone hangars need to collaboratively manage dozens to hundreds of drones and their battery clusters. Against this backdrop, the operation and maintenance model is evolving from the traditional "single-machine, single-task" approach to "clustered, high-concurrency, and unattended" models. This places new system-level requirements on battery management systems: not only must the individual safety and health of each battery be guaranteed, but the entire battery cluster must also be ensured to have continuous availability, rapid response, and dynamic adaptability to support 24 / 7 uninterrupted operation.

[0003] To address these challenges, it is crucial to build an intelligent charging scheduling mechanism that can dynamically adjust according to mission requirements. The goal is to ensure that, when a mission is triggered, drones with sufficient power and matching status are available for deployment. However, existing mainstream charging scheduling strategies are mostly driven by simple rules, such as "charge when battery is low," and charging queues typically follow "first-come, first-served" or static priority rules. This approach leads to a severe disconnect between the charging process and mission requirements: on the one hand, urgent missions are often delayed because critical batteries are in the charging queue, affecting response time; on the other hand, disorderly concentrated charging behavior can easily create load shocks during peak grid periods, not only increasing operating costs but also putting additional pressure on the local power grid and affecting its stability. Summary of the Invention

[0004] This application provides a method, apparatus, terminal, and medium for scheduling battery charging for unmanned aerial vehicles (UAVs), which addresses the technical problem of the disconnect between charging scheduling and mission requirements in the prior art.

[0005] To address the aforementioned technical problems, the first aspect of this application provides a method for scheduling the charging of a drone battery, comprising:

[0006] Acquire the battery status data of the drone battery and the drone mission to be assigned, wherein the battery status data includes: battery health status data and battery power data;

[0007] Based on the battery status data of each drone battery and the mission attributes of each drone mission, and combined with the preset battery mission matching logic, the pairing relationship between each drone battery and the drone mission is determined.

[0008] Based on the battery status data of the drone battery and the mission attributes of the paired drone mission, combined with preset battery charging grading conditions, the charging priority level of the drone battery is determined, and the charging scheduling strategy of the drone battery is determined according to the charging priority level and the real-time grid load status.

[0009] Preferably, determining the pairing relationship between each drone battery and a drone mission based on the battery status data of each drone battery and the mission attributes of each drone mission, combined with a preset battery-mission matching logic, includes:

[0010] Based on the battery status data and the mission attributes of the drone mission, the mission matching degree between the battery status data and the drone mission is calculated using an association algorithm;

[0011] Based on the task matching degree, a greedy algorithm is used to optimize the dynamic task allocation, and the pairing relationship between each drone battery and the drone task is determined based on the optimal allocation scheme based on the output.

[0012] Preferably, the method for obtaining the battery health status data includes:

[0013] Collect multi-source monitoring data of the drone battery, including: voltage, current, internal resistance, temperature, charge / discharge cycles and capacity decay rate;

[0014] Based on the multi-source monitoring data and the influence weights of each multi-source monitoring data on the battery health status, a battery health index of the drone battery is calculated using a preset weighted fusion model, which serves as the battery health status data.

[0015] Preferably, the charging priority level of the drone battery is determined based on the battery status data of the drone battery and the mission attributes of the paired drone mission, combined with preset battery charging grading conditions, including:

[0016] If the drone mission paired with the drone battery is an emergency mission and the remaining power is below a preset power threshold, the charging priority of the drone battery is determined to be the highest charging priority.

[0017] If the battery health status data of the drone battery is lower than a preset threshold, the charging priority of the drone battery is determined to be low charging priority, and the charging priority of the remaining drone batteries is determined to be medium charging priority.

[0018] Preferably, determining the charging scheduling strategy for the UAV battery based on the charging priority level and real-time grid load status includes:

[0019] When the charging priority of the drone battery is the highest, the drone battery is fast charged.

[0020] When the charging priority of the drone battery is medium charging priority, the drone battery is charged in real time or during off-peak hours, depending on the mission status of the paired drone battery.

[0021] When the charging priority of the drone battery is low, the drone battery will be charged uniformly during low-load periods.

[0022] Preferably, it further includes:

[0023] The multi-source monitoring data and the battery health status data are input into a preset fault prediction model to obtain the potential fault prediction result of the UAV battery through the operation of the fault prediction model. The fault prediction model is trained based on historical multi-source monitoring data and historical battery health status data, combined with an LSTM network model.

[0024] Preferably, it further includes:

[0025] Based on the potential fault prediction results, the fault cause corresponding to the potential fault prediction results is determined through a preset fault tracing model, wherein the fault tracing model is obtained by training a decision tree network model based on battery life cycle data and a preset fault feature database.

[0026] A second aspect of this application provides a drone battery charging scheduling device, comprising:

[0027] The data acquisition unit is used to acquire battery status data of the drone battery and drone tasks to be assigned, wherein the battery status data includes: battery health status data and battery power data.

[0028] The battery task matching unit is used to determine the pairing relationship between each drone battery and the drone task based on the battery status data of each drone battery and the task attributes of each drone task, combined with the preset battery task matching logic.

[0029] The battery charging classification and charging scheduling unit is used to determine the charging priority level of the drone battery based on the battery status data of the drone battery and the task attributes of the paired drone mission, combined with preset battery charging classification conditions, so as to determine the charging scheduling strategy of the drone battery based on the charging priority level and the real-time grid load status.

[0030] A third aspect of this application provides a drone battery charging scheduling terminal, including: a memory and a processor;

[0031] The memory is used to store program code, which corresponds to the UAV battery charging scheduling method provided in the first aspect of this application.

[0032] The processor is used to read and execute the program code.

[0033] The fourth aspect of this application provides a computer-readable storage medium storing program code, which is read and executed by a processor to implement the UAV battery charging scheduling method provided in the first aspect of this application.

[0034] As can be seen from the above technical solutions, this application has the following advantages:

[0035] The solution provided in this application first acquires the battery status data of drone batteries and the drone tasks to be assigned. Then, based on the battery status data of each drone battery and the task attributes of each drone task, combined with a preset battery-task matching logic, the pairing relationship between each drone battery and drone task is determined. This dynamically links task requirements with battery status. Next, based on the battery status data of the drone batteries and the task attributes of the paired drone tasks, combined with preset battery charging grading conditions, the charging priority level of the drone batteries is determined. Simultaneously, a charging scheduling strategy is formulated based on real-time grid load status. By differentiating the charging methods of batteries with different priorities, the impact of concentrated charging on the grid during peak hours is mitigated. The overall solution deeply couples task requirements, battery status, and grid conditions, achieving dynamic matching and global optimization of battery resources, operational tasks, and grid energy. This solves the problem of the disconnect between drone battery charging scheduling and task requirements, ensuring operational safety, improving maintenance efficiency, and reducing overall costs. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating an embodiment of a drone battery charging scheduling method provided in this application.

[0038] Figure 2 This is a schematic diagram of the architecture of an embodiment of a drone battery charging scheduling device provided in this application.

[0039] Figure 3This is a schematic diagram of the architecture of an embodiment of a drone battery charging scheduling terminal provided in this application. Detailed Implementation

[0040] This application provides a method, apparatus, terminal, and medium for scheduling battery charging for unmanned aerial vehicles (UAVs), aiming to solve the technical problem of the disconnect between charging scheduling and mission requirements in the prior art.

[0041] To make the inventive objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] First, a detailed description of an embodiment of a drone battery charging scheduling method provided in this application is as follows:

[0043] Please see Figure 1 This application provides an embodiment of a drone battery charging scheduling method, the steps of which include:

[0044] Step 101: Obtain the battery status data of the drone battery and the drone tasks to be assigned;

[0045] The battery status data includes: battery health status data and battery power data;

[0046] Step 102: Based on the battery status data of each drone battery and the mission attributes of each drone mission, and combined with the preset battery mission matching logic, determine the pairing relationship between each drone battery and the drone mission.

[0047] Step 103: Based on the battery status data of the drone battery and the mission attributes of the paired drone mission, and combined with the preset battery charging grading conditions, determine the charging priority level of the drone battery, so as to determine the charging scheduling strategy of the drone battery according to the charging priority level and the real-time grid load status.

[0048] It's important to note that acquiring drone battery status data can be understood as the process of extracting battery operating parameters from the battery management system or sensor devices. This could involve receiving data uploaded by the battery monitoring unit via a wireless communication module or manually entering the battery's current status information. The primary goal is to achieve a comprehensive understanding of the battery's condition. Battery health status data can be generated by analyzing historical usage records and current performance indicators, such as calculations based on the trend of the battery's charge / discharge curve or internal resistance growth. Its purpose is to assess the battery's long-term reliability. Drone mission attributes can include mission type, execution time requirements, and mission importance. This information can be obtained through the mission management system interface or manually configured by the operator, providing a basis for subsequent mission matching. Preset battery mission matching logic can be implemented using a rule engine or scoring mechanism, such as a multi-dimensional scoring model based on weighted allocation or a constraint-based filtering algorithm. Its purpose is to achieve a reasonable allocation of batteries and missions. Preset battery charging grading conditions can be defined by setting threshold ranges or classification labels. For example, different charging priorities can be divided based on the percentage of charge, or dynamic adjustment rules can be set based on the urgency of the mission. Its purpose is to guide the allocation of charging resources.

[0049] The working principle of this application embodiment is as follows: By acquiring the battery status data of the drone battery and the drone tasks to be assigned, whereby the battery status data includes battery health status data and battery power data, a comprehensive understanding of the individual battery status is achieved. Furthermore, based on the battery status data of each drone battery and the task attributes of each drone task, combined with a preset battery task matching logic, the pairing relationship between each drone battery and the drone task is determined, thereby dynamically associating task requirements with battery status. Specifically, task attributes such as urgency and job type are combined with the battery status data, and the matching logic filters out the battery resources most suitable for performing specific tasks, thus avoiding the task response delay problem caused by relying solely on power thresholds in traditional methods. Based on this, according to the drone battery status data and the task attributes of the paired drone tasks, combined with preset battery charging grading conditions, the charging priority level of the drone battery is determined. By differentiating the charging methods of batteries with different priorities, such as fast charging, off-peak charging, or low-load charging, the impact of concentrated charging on the power grid during peak hours is effectively mitigated. The overall solution achieves dynamic matching and global optimization of battery resources, operational tasks, and grid energy by deeply coupling task requirements, battery status, and grid conditions. This solves the problem of the disconnect between UAV battery charging scheduling and task requirements, ensuring operational safety, improving maintenance efficiency, and reducing overall costs.

[0050] Based on the above basic embodiments, this application further proposes to determine the pairing relationship between each drone battery and the drone mission, including: calculating the task matching degree between the battery status data and the drone mission through an association algorithm based on the battery status data and the task attributes of the drone mission; and performing dynamic task allocation optimization through a greedy algorithm based on the task matching degree, so as to determine the pairing relationship between each drone battery and the drone mission based on the optimal allocation scheme of the output.

[0051] Association algorithms are mathematical tools that quantify the correlation between different data. Their purpose is to calculate a matching score (0-100 points) based on data such as battery health index, remaining power, charge / discharge efficiency, and temperature adaptability, combined with drone operation parameters. Based on the score, a three-level recommendation is output: 80 points or above is "Recommended Use" (battery fully meets mission requirements); 60-79 points is "Restricted Use" (battery can be used but load should be reduced or duration shortened); and below 60 points is "Prohibited Use" (battery cannot meet mission requirements, posing a risk of power outage). This achieves precise matching between battery and mission. Greedy algorithms, on the other hand, employ a strategy of choosing the optimal solution at each step, approximating a globally optimal solution through rapid iteration of local optima. Their aim is to improve mission allocation efficiency and ensure priority response to urgent missions.

[0052] For example, based on the health index, remaining power, charge / discharge cycles, and historical task adaptation records of each battery within the cluster, combined with the queue of pending tasks, a greedy algorithm dynamically allocates tasks. High-priority tasks are prioritized for allocation to batteries with a health index ≥ 80 and remaining power ≥ 70%; low-priority tasks can be allocated to batteries with a health index 60-79 and remaining power ≥ 50%; high-load tasks are avoided for allocation to batteries with a health index below 60. Simultaneously, the task execution status of each battery is recorded, forming a task adaptation history database for continuous optimization of the scheduling strategy.

[0053] In detail, this technical solution fundamentally solves the matching rigidity problem caused by static pairing logic by introducing a collaborative mechanism of association algorithm and greedy algorithm, achieving dynamic and accurate adaptation of battery and task relationship. First, the task matching degree is calculated based on battery status data and drone task attributes. This process uses multi-dimensional data such as battery health status and power level to quantitatively correlate with attributes such as task urgency and duration, so that the matching degree calculation is no longer limited to a single power level indicator, but comprehensively reflects the degree of fit between battery availability and task requirements, thereby avoiding matching deviations caused by single data dimensions. On this basis, dynamic task allocation optimization is performed based on the task matching degree using a greedy algorithm. This process quickly converges to a globally better solution by selecting the local optimum with the highest matching degree at each step. Its dynamism is reflected in its ability to respond in real time to changes in the task queue and fluctuations in battery status, effectively avoiding the risk of urgent tasks being blocked by low-priority tasks under the "first-come, first-served" rule, ensuring that batteries with high matching degrees serve critical tasks first, while improving overall resource scheduling efficiency. Ultimately, the pairing relationship is determined based on the optimal allocation scheme, and the dynamic optimization results are transformed into executable scheduling instructions, enabling millisecond-level response between battery resource allocation and task requirements, reducing the risk of task delays and alleviating grid load pressure.

[0054] Furthermore, by combining the above-mentioned solution with the technical content of acquiring the battery status data of the drone battery and the drone tasks to be assigned, the accuracy of task matching and the utilization rate of battery resources are further improved by dynamically adjusting the matching strategy, thereby effectively addressing the problems of emergency task response delays and grid load fluctuations.

[0055] In some embodiments, this application further proposes a method for obtaining battery health status data, including: collecting multi-source monitoring data of the drone battery, wherein the multi-source monitoring data includes: voltage, current, internal resistance, temperature, charge / discharge cycles and capacity decay rate; based on the multi-source monitoring data, and combining the influence weights of each multi-source monitoring data on the battery health status, calculating the battery health index of the drone battery through a preset weighted fusion model, as the battery health status data.

[0056] Specifically, multi-source monitoring data refers to a collection of various types of state parameters collected from the drone battery, which can be implemented using sensor arrays or embedded monitoring modules. Voltage and current are key indicators reflecting the battery's real-time operating state and can be measured using high-precision sampling circuits; internal resistance reflects the battery's internal impedance characteristics and can be detected using AC impedance methods or pulse discharge methods; temperature, as an important factor affecting battery performance, can be monitored using thermistors; and the number of charge-discharge cycles and capacity decay rate are core parameters characterizing the degree of battery aging and can be obtained through historical data analysis and capacity calibration experiments. The purpose of introducing this multi-source monitoring data is to comprehensively cover multi-dimensional information such as the battery's electrochemical characteristics, thermal management status, and aging process, thereby avoiding the one-sided evaluation problem caused by traditional methods relying on only a single indicator.

[0057] In practical applications, the weighted fusion model refers to a comprehensive evaluation tool based on mathematical algorithms, which can be implemented using linear weighted models, nonlinear regression models, or machine learning models. This model assigns different weight coefficients to different monitoring parameters to reflect the differences in the actual contribution of each parameter in the health assessment. For example, internal resistance and capacity decay rate have a more significant impact on the long-term reliability of the battery, and therefore are given higher weights in the model, while transient parameters such as voltage and current may have lower weights. The purpose of this weighting mechanism is to improve the accuracy of the quantitative results of the health status, ensuring that subsequent task matching and charging scheduling can be dynamically adjusted based on more reliable input data.

[0058] Specifically, the above solution effectively addresses the issue of one-sided battery health status assessment through multi-source data fusion and weighted quantization mechanisms. First, it collects multi-source monitoring data, including voltage, current, internal resistance, temperature, charge / discharge cycles, and capacity decay rate. These parameters cover multiple dimensions of battery information, such as electrochemical characteristics, thermal management status, and aging process, ensuring the comprehensiveness of the basic data for health assessment. Then, based on this multi-source monitoring data, a weighted average is applied to each parameter's impact on health status, reflecting the differences in the actual contributions of different parameters in the health assessment. Finally, a pre-defined weighted fusion model calculates the battery health index, integrating multi-dimensional data into a standardized indicator. This not only simplifies the input complexity of subsequent scheduling algorithms but also preserves key health characteristics, enabling charging scheduling strategies to be dynamically adjusted based on more reliable health status data, ultimately ensuring the safety of task execution and the efficiency of system operation.

[0059] Building upon this foundation, the aforementioned solution forms a close technical link with the task matching and charging scheduling decisions for drone batteries. By providing accurate and reliable battery health status data, this solution offers crucial support for the rationality of task allocation and the accuracy of charging priority determination, thereby achieving a simultaneous improvement in operational safety and maintenance efficiency at the system level.

[0060] In some embodiments, this application further proposes determining the charging priority level of a drone battery based on the battery status data of the drone battery and the mission attributes of the paired drone mission, combined with preset battery charging grading conditions, including: if the paired drone mission is an emergency mission and the remaining battery power is lower than a preset battery power threshold, the charging priority level of the drone battery is determined to be the highest charging priority; if the battery health status data of the drone battery is lower than the preset threshold, the charging priority level of the drone battery is determined to be low charging priority, and the charging priority level of the remaining drone battery is determined to be medium charging priority.

[0061] Specifically, battery status data refers to a set of key indicators reflecting the current operating status of a drone battery. This data can include multi-dimensional information such as voltage, current, internal resistance, and temperature, aiming to comprehensively assess the battery's real-time performance and availability. Battery health status data refers to quantitative indicators calculated based on multi-source monitoring data, used to characterize the battery's aging level or potential risk level. This can be achieved through a weighted fusion model combined with historical data analysis. Furthermore, the preset power threshold refers to a lower limit value for power consumption set according to mission requirements and battery characteristics. Its purpose is to determine whether the battery has the minimum power required to complete a specific task.

[0062] Specifically, the above solution achieves dynamic adaptation between task requirements and battery status by constructing a multi-layered charging priority determination mechanism. First, when a drone task is identified as an urgent task and the battery's remaining power is below a preset threshold, the system automatically assigns that battery the highest charging priority. This design ensures that urgent tasks can quickly obtain power support, thereby improving the system's responsiveness. Second, for batteries with health status data below a preset threshold, the system lowers their charging priority to a lower level, preventing batteries in poor health from participating in high-load tasks or concentrated charging, thus effectively reducing safety hazards and extending the overall lifespan of the battery cluster. Finally, other batteries are uniformly set to medium priority, ensuring the continuity of non-urgent tasks while avoiding resource waste. Overall, this mechanism, through multi-dimensional coupling of task urgency, power threshold, and health status, achieves refined management of charging scheduling, while optimizing grid load distribution and improving overall system stability and task execution efficiency.

[0063] For example, a charging priority scheme is formulated based on grid load, remaining battery power, and task urgency: batteries with urgent tasks and less than 30% remaining power are given the highest priority (Level 1); batteries with no urgent tasks but good health and less than 50% remaining power are given Level 2; and aging batteries are given Level 3 (charging is avoided during peak grid load periods). By staggering charging times and dynamically adjusting charging power, grid load fluctuations caused by concentrated charging are avoided, while ensuring that batteries needed for urgent tasks are fully charged in a timely manner. Charging progress is synchronized to the cloud platform in real time, allowing managers to remotely view the charging queue and estimated completion time.

[0064] Based on this, this application further proposes a charging scheduling strategy for drone batteries based on charging priority levels and real-time grid load status, including: when the charging priority level of the drone battery is the highest, the drone battery is fast-charged; when the charging priority level of the drone battery is medium, the drone battery is charged in real-time or during off-peak hours, depending on the task status of the paired drone battery; when the charging priority level of the drone battery is low, the drone battery is charged uniformly during low-load periods.

[0065] In detail, this scheme constructs a hierarchical charging scheduling mechanism by dynamically coupling charging priority levels with real-time grid load status. First, for batteries with the highest charging priority, the system directly triggers a fast charging mechanism; this immediate response ensures zero-delay initiation of emergency tasks. Second, for batteries with medium charging priority, the system comprehensively considers the status information of paired tasks, such as task start time or execution window, and intelligently selects real-time charging or off-peak charging modes, thereby meeting task requirements while avoiding peak grid load. Finally, for batteries with low charging priority, the system strictly limits their charging behavior to periods of low grid load; this mandatory constraint effectively reduces overall charging costs and maintains grid stability. Through this technical solution, not only is the disconnect between charging behavior and task urgency resolved, but a two-way balance between task requirements and grid resources is also achieved.

[0066] In some embodiments, the method proposed in this application may further include: inputting multi-source monitoring data and battery health status data into a preset fault prediction model, so as to obtain the potential fault prediction result of the UAV battery through the operation of the fault prediction model, wherein the fault prediction model is trained based on historical multi-source monitoring data and historical battery health status data, combined with an LSTM network model.

[0067] In practical applications, multi-source monitoring data refers to a set of various real-time dynamic parameters reflecting the operating status of a drone battery. This data can include key indicators such as voltage, current, internal resistance, and temperature, comprehensively capturing the changing trends of the battery's state. Battery health status data refers to a comprehensive indicator characterizing the overall degradation level of the battery, which can be obtained through weighted fusion calculation of multi-source monitoring data. Fault prediction models can be implemented using time series prediction models based on LSTM networks. Their purpose is to identify potential battery failure risks in advance by using deep learning to study degradation patterns in historical data.

[0068] Specifically, the above solution first requires collecting multi-source monitoring data and battery health status data for the drone battery. This data forms the basic input for fault prediction. By inputting this data into a pre-trained fault prediction model, the model can predict potential future battery failures based on its learned historical degradation patterns. This model employs an LSTM network structure, which effectively processes time-series data and captures long-term dependencies in battery state changes. During this process, the model comprehensively considers the correlation between multi-source monitoring data and battery health status data, thereby generating more accurate potential fault prediction results. This prediction mechanism, combined with the aforementioned battery task matching and charging grading strategies, can proactively identify and avoid high-risk batteries before task allocation, ensuring the safe and stable operation of the system while improving overall operational efficiency.

[0069] The above technical solutions can not only provide early warning of potential battery failures, but also fully consider battery health status in the charging scheduling and task allocation process, thereby ensuring operational safety while reducing the risk of task interruption and maintenance costs caused by sudden failures.

[0070] Based on this, the method proposed in this application may further include: determining the cause of the potential fault based on the potential fault prediction result through a preset fault tracing model, wherein the fault tracing model is obtained by training a decision tree network model based on battery life cycle data and a preset fault feature database.

[0071] Specifically, a fault tracing model refers to an algorithmic model capable of in-depth analysis of potential fault prediction results and outputting specific fault causes. It can be implemented using rule-based reasoning, machine learning classification, or expert systems. The purpose of introducing this model is to transform abstract fault predictions into actionable maintenance guidance information, thereby improving operational efficiency. Battery lifecycle data can be understood as covering all monitoring and operational data of the drone battery from manufacturing to disposal, including but not limited to multi-source monitoring data such as voltage, current, internal resistance, and temperature, as well as key indicators such as charge / discharge cycles and capacity decay rate. The introduction of this data aims to ensure that the model can identify performance degradation characteristics at different stages, thereby enhancing its adaptability to complex fault scenarios. A pre-defined fault feature database refers to a database integrating standard feature parameters from historical fault cases. It can be constructed through labeling, classifying, and standardizing historical fault data, aiming to provide a benchmark for the model and avoid subjective misjudgments. A decision tree network model is a machine learning model with hierarchical decision-making characteristics. It can decompose the logical relationship between multi-source monitoring data and fault causes, generating clear reasoning paths, facilitating intuitive understanding of fault causes by maintenance personnel.

[0072] In detail, the above solution addresses the lack of targeted maintenance strategies by constructing a fault tracing mechanism that transforms fault prediction results into actionable fault cause information. In practical applications, potential fault prediction results are input into the fault tracing model. Since the prediction results identify high-risk batteries and their fault types, the tracing process can focus on the actual risky objects, avoiding indiscriminate analysis of all batteries and improving resource utilization efficiency. The fault tracing model, pre-trained and validated, can quickly respond to prediction results and output structured causes, providing clear guidance to maintenance personnel without relying on experience-based judgment. For example, when the prediction result shows an abnormally high temperature in a battery, the model will further analyze whether it is caused by poor heat dissipation, excessive internal resistance, or other factors, and propose specific maintenance suggestions, such as optimizing the heat dissipation design rather than blindly replacing the battery. Furthermore, this solution, combined with the aforementioned LSTM network-based fault prediction model, forms a complete chain from prediction to tracing, which not only improves the accuracy of fault handling but also effectively reduces maintenance costs and task delay risks, ultimately achieving a simultaneous improvement in maintenance efficiency and safety.

[0073] The above is a detailed description of an embodiment of a drone battery charging scheduling method provided in this application. The following is a detailed description of an embodiment of a drone battery charging scheduling device provided in this application.

[0074] Please see Figure 2 The present application provides an embodiment of a drone battery charging scheduling device, the main components of which include:

[0075] The data acquisition unit 201 is used to acquire battery status data of the drone battery and drone tasks to be assigned, wherein the battery status data includes: battery health status data and battery power data.

[0076] The battery task matching unit 202 is used to determine the pairing relationship between each drone battery and the drone task based on the battery status data of each drone battery and the task attributes of each drone task, combined with the preset battery task matching logic.

[0077] The battery charging classification and charging scheduling unit 203 is used to determine the charging priority level of the drone battery based on the battery status data of the drone battery and the mission attributes of the paired drone mission, combined with preset battery charging classification conditions, so as to determine the charging scheduling strategy of the drone battery based on the charging priority level and the real-time grid load status.

[0078] Furthermore, such as Figure 3 As shown, the embodiment of a UAV battery charging scheduling terminal provided in this application mainly includes: a memory 33 and a processor 31, which can be connected to each other via a communication bus 34;

[0079] Memory 33 is used to store program code, which corresponds to the UAV battery charging scheduling method provided in the above embodiments;

[0080] The processor 31 is used to read and execute the program code, thereby implementing the UAV battery charging scheduling method provided in the above embodiments.

[0081] This embodiment solves the problem of the disconnect between the charging process and mission requirements in UAV battery charging scheduling by combining the memory and processor in a specific way and introducing an intelligent scheduling algorithm that deeply integrates battery health status data, battery power data, mission attributes, and grid load status. Simultaneously, by dynamically generating charging strategies, such as responding quickly when an emergency mission is triggered or scheduling charging during periods of low grid load, it effectively avoids situations where emergency missions are forced to be delayed due to critical batteries being in the charging queue, and significantly alleviates the load impact on the grid during peak hours caused by disordered centralized charging, thereby improving the overall operating efficiency of the system.

[0082] Furthermore, this application provides an embodiment of a computer-readable storage medium, in which program code is stored, which is used to be read and executed by a processor to implement the UAV battery charging scheduling method provided in the above embodiments.

[0083] This embodiment utilizes a computer-readable storage medium as the physical carrier of the program code to achieve reliable deployment and dynamic execution of the UAV battery charging scheduling method in a real-world system. This deeply couples task collaborative scheduling with overall charging optimization, resolving the issues of disconnect between the charging process and task requirements, as well as grid load impacts. Specifically, this scheme significantly improves the overall system efficiency by introducing battery health status data, task attributes, and real-time grid load status as decision-making criteria, combined with dynamic matching logic and tiered charging conditions. Furthermore, the program code encapsulates core algorithms such as battery status data acquisition, task matching logic, and tiered charging conditions, ensuring the persistence and distributability of the scheduling method, avoiding redundancy from repeated development, and improving system maintainability and scalability.

[0084] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the terminals, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0086] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0087] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0088] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0090] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for scheduling battery charging for unmanned aerial vehicles (UAVs), characterized in that, include: Acquire the battery status data of the drone battery and the drone mission to be assigned, wherein the battery status data includes: battery health status data and battery power data; Based on the battery status data of each drone battery and the mission attributes of each drone mission, and combined with the preset battery mission matching logic, the pairing relationship between each drone battery and the drone mission is determined. Based on the battery status data of the drone battery and the mission attributes of the paired drone mission, combined with preset battery charging grading conditions, the charging priority level of the drone battery is determined, and the charging scheduling strategy of the drone battery is determined according to the charging priority level and the real-time grid load status.

2. The method for scheduling battery charging of a drone according to claim 1, characterized in that, The step of determining the pairing relationship between each drone battery and a drone mission based on the battery status data of each drone battery and the mission attributes of each drone mission, combined with a preset battery mission matching logic, includes: Based on the battery status data and the mission attributes of the drone mission, the mission matching degree between the battery status data and the drone mission is calculated using an association algorithm; Based on the task matching degree, a greedy algorithm is used to optimize the dynamic task allocation, and the pairing relationship between each drone battery and the drone task is determined based on the optimal allocation scheme based on the output.

3. The method for scheduling battery charging for unmanned aerial vehicles according to claim 1, characterized in that, The battery health status data is obtained through the following methods: Collect multi-source monitoring data of the drone battery, including: voltage, current, internal resistance, temperature, charge / discharge cycles and capacity decay rate; Based on the multi-source monitoring data and the influence weights of each multi-source monitoring data on the battery health status, a battery health index of the drone battery is calculated using a preset weighted fusion model, which serves as the battery health status data.

4. The method for scheduling battery charging for unmanned aerial vehicles according to claim 1, characterized in that, Based on the battery status data of the drone battery and the mission attributes of the paired drone mission, combined with preset battery charging priority conditions, the charging priority level of the drone battery is determined, including: If the drone mission paired with the drone battery is an emergency mission and the remaining power is below a preset power threshold, the charging priority of the drone battery is determined to be the highest charging priority. If the battery health status data of the drone battery is lower than a preset threshold, the charging priority of the drone battery is determined to be low charging priority, and the charging priority of the remaining drone batteries is determined to be medium charging priority.

5. The UAV battery charging scheduling method according to claim 4, characterized in that, Based on the charging priority level and real-time grid load status, the charging scheduling strategy for the drone battery is determined as follows: When the charging priority of the drone battery is the highest, the drone battery is fast charged. When the charging priority of the drone battery is medium charging priority, the drone battery is charged in real time or during off-peak hours, depending on the mission status of the paired drone battery. When the charging priority of the drone battery is low, the drone battery will be charged uniformly during low-load periods.

6. The UAV battery charging scheduling method according to claim 3, characterized in that, Also includes: The multi-source monitoring data and the battery health status data are input into a preset fault prediction model to obtain the potential fault prediction result of the UAV battery through the operation of the fault prediction model. The fault prediction model is trained based on historical multi-source monitoring data and historical battery health status data, combined with an LSTM network model.

7. A method for scheduling the charging of a UAV battery according to claim 6, characterized in that, Also includes: Based on the potential fault prediction results, the fault cause corresponding to the potential fault prediction results is determined through a preset fault tracing model, wherein the fault tracing model is obtained by training a decision tree network model based on battery life cycle data and a preset fault feature database.

8. A drone battery charging scheduling device, characterized in that, include: The data acquisition unit is used to acquire battery status data of the drone battery and drone tasks to be assigned, wherein the battery status data includes: battery health status data and battery power data. The battery task matching unit is used to determine the pairing relationship between each drone battery and the drone task based on the battery status data of each drone battery and the task attributes of each drone task, combined with the preset battery task matching logic. The battery charging classification and charging scheduling unit is used to determine the charging priority level of the drone battery based on the battery status data of the drone battery and the task attributes of the paired drone mission, combined with preset battery charging classification conditions, so as to determine the charging scheduling strategy of the drone battery based on the charging priority level and the real-time grid load status.

9. A drone battery charging scheduling terminal, characterized in that, include: Memory and processor; The memory is used to store program code, which corresponds to the UAV battery charging scheduling method as described in any one of claims 1 to 7; The processor is used to read and execute the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that is read and executed by a processor to implement the UAV battery charging scheduling method as described in any one of claims 1 to 7.

Images