Edge computing unmanned aerial vehicle meteorological device replacement method and system

Abstract

This invention provides a method and system for replacing meteorological equipment on an edge computing drone, belonging to the field of meteorological equipment operation and maintenance technology. The method includes: acquiring meteorological parameter data at the edge computing node corresponding to each meteorological device, and performing preprocessing on the meteorological parameter data locally on the corresponding edge computing node to generate an effective deviation data sequence for each meteorological device; calculating the degradation state parameters for each meteorological device and generating degradation state characterization results for each meteorological device; constructing a replacement benefit function and determining the replacement trigger result and task priority parameters for each meteorological device, outputting a drone replacement command when preset trigger conditions are met; and controlling the drone to execute the meteorological equipment replacement operation. This invention achieves accurate identification and early judgment of meteorological equipment anomaly types under complex meteorological environments and terrain conditions, thereby improving the accuracy of replacement decisions and reducing false triggers and delayed replacements.

Description

Technical Field

[0001] This invention relates to the field of meteorological equipment operation and maintenance technology, and specifically to a method and system for replacing meteorological equipment on an edge computing drone. Background Technology

[0002] In existing meteorological monitoring networks, especially in mountainous, coastal, or distributed deployment scenarios, meteorological equipment is typically characterized by its large number, wide distribution, and complex maintenance conditions. To ensure the continuity and accuracy of monitoring data, drones are gradually being introduced into engineering projects to inspect and replace faulty or abnormal equipment, replacing manual inspections and thus improving operational efficiency. However, a significant practical problem remains: equipment replacement is primarily triggered by single-point data anomalies or simple threshold judgments. While this approach is usable in stable environments, it becomes problematic under complex meteorological conditions, such as gusts, short-duration heavy rainfall, or sudden changes in local temperature and humidity. These conditions can easily misinterpret transient disturbances as equipment malfunctions, leading to frequent drone deployments and increased unnecessary maintenance costs.

[0003] On the other hand, some equipment often exhibits slow drift during actual degradation. While the deviation may not be noticeable in the short term, it gradually affects monitoring accuracy over the long term. Existing methods struggle to identify such progressive failures in a timely manner, leading to delayed replacements. Furthermore, since meteorological equipment is typically deployed in regional networks, there is a certain spatial correlation between multiple devices. However, current technologies often focus on individual devices, lacking comprehensive analysis of consistent changes in neighboring devices, further exacerbating the risk of misjudgment.

[0004] More importantly, while edge computing nodes have been gradually applied to meteorological monitoring systems in actual deployments, their role is mostly limited to data acquisition and simple preprocessing. They have not yet played a core role in equipment replacement decisions, resulting in decision-making still relying on cloud processing. This not only leads to communication latency issues but also makes it difficult to meet the rapid response requirements of drones. Therefore, how to build a decision-making mechanism at the edge that can comprehensively consider equipment deviation, degradation trends, spatial correlation, and execution costs, accurately determine whether equipment needs to be replaced, and rationally schedule drones to perform replacement tasks has become an urgent technical problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for replacing meteorological equipment on edge computing drones, so as to at least solve the problems in the prior art where replacement is determined based on single-point anomalies, which is easily affected by transient weather fluctuations, leading to drone misdeployment and untimely equipment replacement.

[0006] To achieve the above objectives, a first aspect of the present invention provides a method for replacing meteorological equipment on an edge computing drone. The method includes: acquiring meteorological parameter data at the edge computing node corresponding to each meteorological device, and performing preprocessing on the meteorological parameter data locally on the corresponding edge computing node to generate an effective deviation data sequence for each meteorological device; calculating degradation state parameters for each meteorological device based on the effective deviation data sequence on the corresponding edge computing node, and generating degradation state characterization results for each meteorological device by combining pre-stored neighboring meteorological device association data; constructing a replacement benefit function based on the degradation state characterization results, and determining the replacement trigger result and task priority parameters for each meteorological device according to the replacement benefit function, and outputting a drone replacement command when a preset trigger condition is met; and controlling the drone to perform a meteorological equipment replacement operation based on the drone replacement command.

[0007] Optionally, meteorological parameter data is acquired at the edge computing nodes corresponding to each meteorological device, and preprocessing is performed on the meteorological parameter data locally at the corresponding edge computing nodes to generate effective deviation data sequences for each meteorological device. This includes: constructing a sliding time window data sequence for the meteorological parameter data within the corresponding edge computing node according to a preset sampling time interval, and calculating the short-term fluctuation energy parameter and long-term fluctuation energy parameter for each meteorological parameter based on the sliding time window data sequence; determining the transient disturbance discrimination result for each meteorological parameter based on the ratio relationship between the short-term fluctuation energy parameter and the long-term fluctuation energy parameter, and performing a removal process on the sliding time window data sequence when it is determined to be a transient disturbance to generate a data sequence with transient disturbance removed; calculating the original deviation data for each meteorological parameter based on the difference relationship between the data sequence with transient disturbance removed and the preset reference meteorological parameter data, and performing normalization processing on the original deviation data to generate effective deviation data sequences for each meteorological device.

[0008] Optionally, the degradation status parameters of each meteorological device are calculated at the corresponding edge computing node based on the effective deviation data sequence, including: constructing time series difference data for the effective deviation data sequence within the corresponding edge computing node, and calculating the deviation change rate data sequence for each meteorological device based on the time series difference data; calculating the degradation rate parameter for each meteorological device based on the deviation change rate data sequence and the effective deviation data sequence, and determining the remaining available time parameter for each meteorological device based on the difference relationship between the degradation rate parameter and a preset failure threshold; and generating the degradation status parameters for each meteorological device based on the effective deviation data sequence, the degradation rate parameter, and the remaining available time parameter.

[0009] Optionally, calculating the degradation rate parameter for each meteorological device based on the deviation change rate data sequence and the effective deviation data sequence includes: constructing a change rate fluctuation amplitude parameter for each meteorological device based on the deviation change rate data sequence within the corresponding edge computing node, and determining a change stability parameter for each meteorological device based on the change rate fluctuation amplitude parameter; performing weighted processing on the deviation change rate data sequence based on the current deviation value of the effective deviation data sequence and the change stability parameter to generate a weighted change rate data sequence for each meteorological device; and calculating the degradation rate parameter for each meteorological device based on the weighted change rate data sequence.

[0010] Optionally, the degradation status characterization results of each meteorological device are generated by combining the pre-stored neighboring meteorological device association data, including: determining the neighboring meteorological device set of each meteorological device based on the neighboring meteorological device association data within the corresponding edge computing node, and extracting the effective deviation data sequence corresponding to the neighboring meteorological device set; calculating the deviation consistency parameter between each meteorological device and its neighboring meteorological devices based on the effective deviation data sequence and the effective deviation data sequence corresponding to the neighboring meteorological device set; and performing correction processing on the degradation status parameters of each meteorological device based on the deviation consistency parameter to generate the degradation status characterization results of each meteorological device.

[0011] Optionally, the replacement benefit function is: ; in, Let be the value of the replacement benefit function for the i-th meteorological device; This represents the effective deviation value of the i-th meteorological device. The remaining available time parameter for the i-th meteorological device; It is a non-zero constant; This is the trend amplification factor; Let be the degradation rate parameter of the i-th meteorological device; For reference degradation rate parameters; Let be the stability parameter of the i-th meteorological device; Let be the spatial consistency parameter of the i-th meteorological device; Weights for transient disturbance correction coefficients; This is the transient disturbance correction factor; , , This is the cost weighting coefficient; Flight distance; For flight time; This refers to energy consumption parameters.

[0012] Optionally, the replacement trigger result and task priority parameters for each meteorological device are determined according to the replacement benefit function, and a UAV replacement command is output when a preset trigger condition is met. This includes: obtaining the replacement benefit function value of each meteorological device, comparing the replacement benefit function value with a preset benefit threshold, and generating a replacement trigger result for each meteorological device; calculating the task priority parameters for each meteorological device based on the replacement benefit function value, sorting the meteorological devices according to the task priority parameters, and generating a UAV replacement task sequence; when the replacement trigger result meets the preset trigger condition, generating a corresponding UAV replacement command based on the UAV replacement task sequence and outputting it to the UAV control terminal to control the UAV to perform the meteorological device replacement operation.

[0013] Optionally, controlling the UAV to perform a meteorological equipment replacement operation based on the UAV replacement command includes: parsing the corresponding target meteorological equipment location information and task sequence based on the UAV replacement command, and generating UAV flight path parameters according to the task sequence; controlling the UAV to fly to the location of the target meteorological equipment based on the flight path parameters, and performing the disassembly and replacement operation of the meteorological equipment after reaching the target location, generating replacement completion status information; after the replacement completion status information is generated, sending the replacement completion status information back to the corresponding edge computing node, and triggering the edge computing node to obtain updated meteorological parameter data for closed-loop updates of subsequent replacement decisions.

[0014] A second aspect of the present invention provides an edge computing drone meteorological equipment replacement system, the system comprising: a data acquisition unit, configured to acquire meteorological parameter data at the edge computing nodes corresponding to each meteorological device, and perform preprocessing on the meteorological parameter data locally at the corresponding edge computing nodes to generate an effective deviation data sequence for each meteorological device; a characterization result determination unit, configured to calculate degradation state parameters for each meteorological device at the corresponding edge computing nodes based on the effective deviation data sequence, and generate degradation state characterization results for each meteorological device by combining pre-stored neighboring meteorological device association data; an instruction generation unit, configured to construct a replacement benefit function based on the degradation state characterization results, and determine the replacement trigger result and task priority parameters for each meteorological device according to the replacement benefit function, and output a drone replacement instruction when a preset trigger condition is met; and an instruction execution unit, configured to control the drone to perform meteorological equipment replacement operations based on the drone replacement instruction.

[0015] On the other hand, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described edge computing drone weather equipment replacement method.

[0016] Through the above technical solution, the present invention preprocesses meteorological parameter data locally at the edge computing node and generates an effective deviation data sequence, avoiding dependence on the cloud and improving the real-time performance of data processing. Furthermore, it calculates degradation state parameters based on the effective deviation data sequence and corrects the degradation state by combining the correlation with neighboring meteorological equipment, making the equipment status judgment more consistent with actual operating conditions. On this basis, a replacement benefit function is constructed to comprehensively evaluate equipment replacement triggering and task priority, thereby achieving reasonable generation and scheduling control of UAV replacement commands. Finally, by having UAVs execute meteorological equipment replacement operations, the accuracy and efficiency of equipment replacement decisions are improved, and false triggering and delayed replacements are reduced.

[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0018] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of the steps of an edge computing UAV meteorological equipment replacement method according to one embodiment of the present invention; Figure 2 This is a system structure diagram of an edge computing UAV meteorological equipment replacement system provided in one embodiment of the present invention; Figure 3 This is an internal structural diagram of a computer device provided in one embodiment of the present invention. Detailed Implementation

[0019] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0020] like Figure 1 As shown, this invention provides a method for replacing meteorological equipment on an edge computing drone, the method comprising: Step S10: Obtain meteorological parameter data at the edge computing node corresponding to each meteorological device, and perform preprocessing on the meteorological parameter data locally at the corresponding edge computing node to generate the effective deviation data sequence corresponding to each meteorological device.

[0021] Specifically, within the corresponding edge computing node, a sliding time window data sequence is constructed for the meteorological parameter data according to a preset sampling time interval. Based on the sliding time window data sequence, short-term fluctuation energy parameters and long-term fluctuation energy parameters for each meteorological parameter are calculated. The transient disturbance discrimination result for each meteorological parameter is determined based on the ratio of the short-term and long-term fluctuation energy parameters. When a transient disturbance is identified, the sliding time window data sequence is removed to generate a data sequence with transient disturbances removed. Based on the difference between the data sequence with transient disturbances removed and the preset reference meteorological parameter data, the original deviation data for each meteorological parameter is calculated. The original deviation data is then normalized to generate an effective deviation data sequence for each meteorological device.

[0022] In this embodiment of the invention, meteorological equipment is mostly distributed in mountainous areas, coastal areas, or unattended areas. Communication links suffer from instability, limited bandwidth, and uncontrollable transmission delays. Relying on cloud-based unified processing not only introduces data transmission delays but may also result in data loss at critical moments, making it difficult to support drone scheduling decisions in a timely manner. Furthermore, meteorological parameters themselves have obvious short-term fluctuation characteristics, such as gusts, instantaneous rainfall, or local temperature and humidity disturbances, the duration of which is usually on the order of seconds or minutes. If data is uploaded first and then processed, it is easily masked by the time averaging effect, leading to the loss of transient characteristics and making it impossible to accurately distinguish between environmental disturbances and equipment malfunctions.

[0023] From an engineering implementation perspective, drone replacement operations have certain execution costs and response constraints, requiring trigger determination and path decision-making to be completed within a short period. This necessitates that data processing and decision-making logic be completed as close to the data source as possible. By performing preprocessing and bias construction locally on edge computing nodes, not only can the amount of data uploaded be reduced, lowering the system communication burden, but validity screening can also be performed immediately upon data generation, ensuring that subsequent degradation analysis is based on more stable and reliable data. In other words, the edge computing node not only acts as a data relay but also directly participates in the pre-processing of equipment status determination, providing real-time and reliable input conditions for subsequent replacement benefit assessment and drone scheduling.

[0024] Specifically, meteorological parameter data is acquired at the edge computing nodes corresponding to each meteorological device, and preprocessing is performed locally on the corresponding edge computing nodes to generate effective deviation data sequences for each meteorological device. It should be noted that the stability and reliability of these effective deviation data sequences, which serve as the input basis for subsequent degradation state parameter calculations and the construction of replacement benefit functions, directly affect the subsequent decision-making results. Therefore, this implementation does not employ simple filtering or threshold removal methods, but rather uses a combination of time-scale decomposition and energy characterization to identify and process transient disturbances in the meteorological parameter data, thereby ensuring that the effective deviation data sequences accurately reflect changes in device status.

[0025] Within the corresponding edge computing node, a sliding time window data sequence is first constructed from the meteorological parameter data according to a preset sampling time interval. This sliding time window data sequence is used to centrally represent the changes in meteorological parameters over a continuous time period, and its window length can be set according to the sampling frequency and the processing capability of the edge computing node. In some implementations, the sliding time window can cover multiple sampling periods to balance short-term fluctuation identification with overall trend stability. For example, in scenarios with drastic wind speed changes, the sliding time window length can be appropriately shortened to improve the response capability to rapid changes; while in scenarios with relatively gentle temperature changes, the sliding time window length can be appropriately extended to enhance the stability of the statistical results.

[0026] After constructing the sliding time window data sequence, for each type of meteorological parameter, the corresponding short-term fluctuation energy parameter and long-term fluctuation energy parameter are calculated. The short-term fluctuation energy parameter is used to characterize the intensity of change of the meteorological parameter within a short time scale, and the long-term fluctuation energy parameter is used to characterize the overall fluctuation of the meteorological parameter within a longer time scale. Its calculation logic can be expressed as follows: ; in, This represents the short-term fluctuation energy parameter of the i-th meteorological parameter; This represents the corresponding long-term fluctuation energy parameter; This represents the value of the i-th meteorological parameter collected at time t; Indicates a short sliding time window; Indicates a long sliding time window; and These represent the average values ​​within the corresponding windows.

[0027] After obtaining the short-term and long-term fluctuation energy parameters, the ratio between the two is further constructed to determine whether the current meteorological parameter change belongs to a transient disturbance. The discrimination logic can be expressed as follows: ; in, This represents the energy ratio parameter of the i-th meteorological parameter; It is a non-zero constant used to avoid the denominator being zero.

[0028] In engineering applications, when A significant increase indicates that short-term fluctuation energy accounts for a higher proportion of long-term fluctuation energy. In this case, changes in meteorological parameters are more likely to originate from transient meteorological disturbances, such as gusts, short-term rainfall, or local turbulence. If such data is directly used for subsequent deviation calculations, environmental changes may be misjudged as equipment malfunctions, leading to unnecessary replacement operations. Therefore, when a transient disturbance is identified, a removal process is performed on the sliding time window data sequence to generate a data sequence free of transient disturbances. It should be noted that the removal process is not limited to directly deleting data from the corresponding time segment; it can also be achieved by reducing weights or using interpolation smoothing. Any method that effectively weakens the impact of transient disturbances falls within the scope of this embodiment.

[0029] After obtaining the data sequence with transient disturbances removed, the original deviation data is further calculated based on the difference between this data sequence and the preset reference meteorological parameter data. The preset reference meteorological parameter data can be derived from historical statistical models, average values ​​of neighboring devices, or calibrated standard device output values, and its function is to provide a stable comparison benchmark for the current device output. The calculation logic for the original deviation data can be expressed as follows: ; in, This represents the raw deviation data of the i-th meteorological parameter at time t; This represents meteorological parameter data after removing transient disturbances; This indicates the corresponding reference meteorological parameter data.

[0030] Considering the differences in the dimensions and ranges of various meteorological parameters, such as the different numerical ranges of temperature and wind speed, directly using the raw deviation data for subsequent processing may lead to uneven weighting of different parameters in the decision-making process. Therefore, in this embodiment, the raw deviation data is normalized to generate an effective deviation data sequence at a uniform scale. The calculation logic can be expressed as follows: ; in, This represents the effective deviation value of the i-th meteorological parameter at time t; The reference scale parameter represents the corresponding meteorological parameter and is used to standardize the original deviation.

[0031] Through the above steps, the effective deviation data sequence for each meteorological device is finally generated. During the construction process, transient disturbance removal and scale unification have been performed on the effective deviation data sequence, ensuring that it retains the stable offset characteristics caused by changes in device status while effectively suppressing the influence of transient environmental disturbances. In practical applications, such as in coastal areas, wind speed sensors may experience short-term, severe fluctuations due to gusts. The energy discrimination and removal mechanism described above can prevent such fluctuations from being misjudged as device malfunctions. Furthermore, persistent deviations caused by sensor aging are continuously reflected in the effective deviation data sequence, thus providing reliable input for subsequent calculations of degradation state parameters.

[0032] Step S20: Calculate the degradation state parameters of each meteorological device at the corresponding edge computing node based on the effective deviation data sequence, and generate the degradation state characterization results of each meteorological device by combining the pre-stored neighboring meteorological device association data.

[0033] Specifically, the degradation status parameters of each meteorological device are calculated at the corresponding edge computing node based on the effective deviation data sequence, including: constructing time series difference data for the effective deviation data sequence within the corresponding edge computing node, and calculating the deviation change rate data sequence for each meteorological device based on the time series difference data; calculating the degradation rate parameter for each meteorological device based on the deviation change rate data sequence and the effective deviation data sequence, and determining the remaining available time parameter for each meteorological device based on the difference relationship between the degradation rate parameter and a preset failure threshold; and generating the degradation status parameters for each meteorological device based on the effective deviation data sequence, the degradation rate parameter, and the remaining available time parameter.

[0034] Furthermore, calculating the degradation rate parameter for each meteorological device based on the deviation change rate data sequence and the effective deviation data sequence includes: constructing a change rate fluctuation amplitude parameter for each meteorological device based on the deviation change rate data sequence within the corresponding edge computing node, and determining a change stability parameter for each meteorological device based on the change rate fluctuation amplitude parameter; performing weighted processing on the deviation change rate data sequence based on the current deviation value of the effective deviation data sequence and the change stability parameter to generate a weighted change rate data sequence for each meteorological device; and calculating the degradation rate parameter for each meteorological device based on the weighted change rate data sequence.

[0035] Furthermore, by combining pre-stored neighboring meteorological equipment association data, the degradation status characterization results for each meteorological equipment are generated, including: determining the neighboring meteorological equipment set for each meteorological equipment within the corresponding edge computing node based on the neighboring meteorological equipment association data, and extracting the effective deviation data sequence corresponding to the neighboring meteorological equipment set; calculating the deviation consistency parameter between each meteorological equipment and its neighboring meteorological equipment based on the effective deviation data sequence and the effective deviation data sequence corresponding to the neighboring meteorological equipment set; and performing correction processing on the degradation status parameters of each meteorological equipment based on the deviation consistency parameter to generate the degradation status characterization results for each meteorological equipment.

[0036] In this embodiment of the invention, time-series differential data is constructed based on the effective deviation data sequence within the corresponding edge computing node. Considering that the output data of meteorological equipment is continuous in time, the deviation value at a single time point is difficult to directly reflect the trend of equipment status changes. Therefore, the deviation sequence is transformed into a change sequence through differential operations, thereby extracting its temporal evolution characteristics. Specifically, for the th meteorological equipment, its effective deviation data sequence is denoted as . Then the corresponding time series difference data can be represented as: ; in, This represents the change in deviation at time t. This indicates the preset time step. This difference processing can eliminate static components in the deviation sequence, allowing subsequent calculations to focus more on the trend itself.

[0037] After obtaining the time series difference data, the deviation change rate data series corresponding to each meteorological device is further calculated. The calculation logic is as follows: ; in, This represents the data sequence of the deviation change rate of the i-th meteorological device. This sequence is used to characterize the rate of deviation change and is the basis for subsequent calculation of degradation rate parameters.

[0038] However, in real-world engineering environments, despite transient disturbance removal, the deviation change rate data sequence may still exhibit some fluctuations, especially noticeable with highly sensitive parameters such as wind speed and humidity. Therefore, if directly based on... Calculating the degradation rate is easily affected by local fluctuations, leading to instability in the assessment of the degradation trend. Therefore, this embodiment further introduces a change rate fluctuation amplitude parameter and a change stability parameter to modulate the deviation change rate.

[0039] Specifically, within the corresponding edge computing node, a change rate fluctuation amplitude parameter is constructed based on the deviation change rate data sequence, and its calculation logic is as follows: ; in, This parameter represents the amplitude of the rate of change fluctuation. Let W represent the average rate of change, and W represent the time window. Further, the fluctuation amplitude parameter of the rate of change is mapped to a stability parameter, defined as: ; The stability parameter of change It is used to reflect the stability of the deviation change process; the larger the value, the more unstable the change.

[0040] Based on this, and in conjunction with the current deviation value of the effective deviation data sequence, a weighted processing is performed on the deviation change rate data sequence to generate a weighted change rate data sequence. The calculation logic is as follows: ; in, This is a preset adjustment coefficient. This weighting mechanism can strengthen stable but large-deviation trends while suppressing highly volatile changes, thereby improving the robustness of degradation rate calculation.

[0041] Based on the weighted rate of change data sequence, the uncorrected form of the degradation rate parameter is further calculated: ; in, This represents the degradation rate parameter before correction.

[0042] After obtaining the degradation rate parameter, the remaining usable time parameter is calculated in conjunction with the preset failure threshold. Its uncorrected form is as follows: ; in, To preset the failure threshold, It is a non-zero constant.

[0043] Thus, the construction of the degradation state parameters based on the time dimension was completed, and the parameter set before correction was obtained. .

[0044] Based on this, spatial dimension information is introduced for correction. Within the corresponding edge computing node, the set of neighboring meteorological devices for each meteorological device is determined based on pre-stored neighboring meteorological device association data. And extract the corresponding effective deviation data sequence. Then, the deviation consistency parameter is constructed, and its calculation logic is as follows: ; in, This represents the spatial consistency parameter.

[0045] Based on the spatial consistency parameter, a correction process is performed on the degenerate state parameter before correction, and the result is defined as the final parameter: ; At the same time, the final effective deviation will be uniformly recorded as: ; It is important to emphasize that the function used in the subsequent calculation of the return function... , , All parameters have been corrected for spatial consistency.

[0046] Through the above processing, a complete mapping from the initial deviation to the final degradation state characterization result is achieved. In practical applications, such as when multiple meteorological devices in the same area are simultaneously affected by environmental changes, their deviation consistency parameters... The larger the value, the lower the degradation rate and the less likely misjudgment; however, when a single device exhibits an abnormal deviation, The smaller the size, the stronger the degradation trend becomes, thus improving recognition accuracy.

[0047] To further clarify, the process of constructing degradation state parameters based on the effective deviation data sequence and performing corrections in conjunction with spatial consistency is not limited to the specific calculation methods described above. Its core lies in achieving a stable characterization of the meteorological equipment's state through collaborative modeling of the time and spatial dimensions. In specific implementations, the construction method of the time series difference data can adopt forward differencing, backward differencing, or central differencing, depending on the sampling characteristics; the deviation change rate data sequence can also be obtained based on multi-step differencing or moving regression. As long as it can reflect the trend of effective deviation changes over time, it falls within the protection scope of this embodiment.

[0048] Step S30: Construct a replacement benefit function based on the degradation state characterization results, and determine the replacement trigger result and task priority parameters for each meteorological device according to the replacement benefit function. Output the UAV replacement command when the preset trigger conditions are met.

[0049] Specifically, the replacement benefit function is: ; in, Let be the value of the replacement benefit function for the i-th meteorological device; This represents the effective deviation value of the i-th meteorological device. The remaining available time parameter for the i-th meteorological device; It is a non-zero constant; This is the trend amplification factor; Let be the degradation rate parameter of the i-th meteorological device; For reference degradation rate parameters; Let be the stability parameter of the i-th meteorological device; Let be the spatial consistency parameter of the i-th meteorological device; Weights for transient disturbance correction coefficients; This is the transient disturbance correction factor; , , This is the cost weighting coefficient; Flight distance; For flight time; This refers to energy consumption parameters.

[0050] Furthermore, based on the replacement benefit function, the replacement trigger result and task priority parameters for each meteorological device are determined, and a UAV replacement command is output when a preset trigger condition is met. This includes: obtaining the replacement benefit function value for each meteorological device, comparing the replacement benefit function value with a preset benefit threshold, and generating a replacement trigger result for each meteorological device; calculating the task priority parameters for each meteorological device based on the replacement benefit function value, sorting the meteorological devices according to the task priority parameters, and generating a UAV replacement task sequence; when the replacement trigger result meets the preset trigger condition, generating a corresponding UAV replacement command based on the UAV replacement task sequence and outputting it to the UAV control terminal to control the UAV to perform the meteorological device replacement operation.

[0051] In this embodiment of the invention, the first part of the profit function is replaced. Characterizing the coupling relationship between current deviation and remaining life essentially reflects the degree of risk growth per unit time. Part Two This is the degradation trend modulation term, used to comprehensively consider the impact of degradation rate and change stability on equipment condition. Part Three Used to suppress misjudgments caused by regionally consistent changes; Part Four This is used to correct for transient disturbances. The last part is the execution cost item, which quantifies the cost of the drone performing the replacement mission.

[0052] Furthermore, within the edge computing node, based on the aforementioned replacement benefit function Calculate the replacement trigger results for each meteorological device. Specifically, the replacement benefit function value... Compared with the preset revenue threshold Compare, when satisfied When the system determines that the corresponding meteorological equipment needs to be replaced, a replacement trigger result is generated. It should be noted that the preset revenue threshold can be set according to different scenarios. For example, in areas with high maintenance costs, the threshold can be appropriately increased to reduce unnecessary replacement operations.

[0053] While determining the replacement trigger result, the task priority parameters for each meteorological device are further calculated based on the replacement benefit function value. In this embodiment, the task priority parameters can be directly constructed based on the replacement benefit function value, for example... Alternatively, the replacement benefit function value can be normalized according to actual needs and used as a priority parameter. Subsequently, the meteorological equipment that meets the replacement triggering conditions is sorted according to the task priority parameter to generate a UAV replacement task sequence.

[0054] After generating the UAV replacement task sequence, a corresponding UAV replacement instruction is generated based on the task sequence. During this process, it is necessary to further determine parameters such as the path and time for the UAV to execute the task to ensure task executability.

[0055] Specifically, regarding flight distance parameters This information originates from the edge computing nodes' calculation of the spatial location of the meteorological equipment. The spatial location information of the meteorological equipment can be obtained through pre-stored equipment coordinate data, while the current location of the drone is also obtained in real time by the edge nodes. Based on the spatial coordinate relationship between the two, the corresponding flight distance is calculated, which can be expressed as: ; in, Indicates the current position coordinates of the drone. This represents the location coordinates of the i-th meteorological device.

[0056] Furthermore, flight time parameters Based on the aforementioned flight distance parameters and the UAV's flight speed, it can be expressed as: ; Where v represents the average flight speed of the UAV. It should be noted that in practical applications, the impact of environmental factors such as wind speed and air pressure on flight time can also be considered, and the flight time can be corrected accordingly.

[0057] For energy consumption parameters It is calculated based on flight time and UAV power consumption models. In one implementation, it can be expressed as: ; in, This represents the average power consumption of the drone. Furthermore, the energy consumption can be compensated for by incorporating factors such as takeoff and landing energy consumption and hovering energy consumption, thereby obtaining more accurate energy consumption parameters.

[0058] In obtaining flight distance Flight time and energy consumption parameters Then, it is substituted into the replacement benefit function to achieve quantitative constraints on execution costs.

[0059] When generating the UAV replacement command, the UAV replacement task sequence is combined with the corresponding flight path parameters to generate a control command containing the target equipment location, task sequence and path information, and output to the UAV control terminal to control the UAV to perform the meteorological equipment replacement operation.

[0060] It should be further explained that, in this embodiment, the replacement benefit function is not only used for triggering judgment, but also for task sorting and path decision-making. Its essence is to integrate the device status and execution cost through a unified evaluation index, thereby avoiding the problems of traditional methods that only consider the device status without considering the execution cost or only consider the distance while ignoring the urgency of the device.

[0061] Furthermore, the specific form of the aforementioned replacement benefit function is not limited to the above expression. Without changing its core idea, various terms can be adjusted or replaced. For example, the degradation trend modulation term can adopt other nonlinear function forms, and more influencing factors can be introduced into the cost term, such as the remaining battery power of the drone and the degree of task concurrency. These are all within the protection scope of this implementation method.

[0062] Step S40: Control the drone to perform meteorological equipment replacement operation based on the drone replacement command.

[0063] Specifically, based on the UAV replacement command, the corresponding target meteorological equipment location information and task sequence are parsed, and UAV flight path parameters are generated according to the task sequence; based on the flight path parameters, the UAV is controlled to fly to the location of the target meteorological equipment, and after reaching the target location, the disassembly and replacement operation of the meteorological equipment is performed, generating replacement completion status information; after the replacement completion status information is generated, the replacement completion status information is sent back to the corresponding edge computing node, and the edge computing node is triggered to obtain updated meteorological parameter data for closed-loop updates of subsequent replacement decisions.

[0064] In this embodiment of the invention, after generating the UAV replacement command, the UAV is further controlled to perform a meteorological equipment replacement operation based on the UAV replacement command, thereby forming an execution closed loop driven by the edge computing node. It should be noted that the UAV replacement operation includes an integrated execution process including task parsing, path generation, flight control, equipment replacement, and status feedback. Its core is to ensure that the replacement task can be completed in an orderly and reliable manner according to the predetermined priority.

[0065] Specifically, after receiving the drone replacement command, the drone parses the command to extract the corresponding target meteorological equipment location information and task sequence. The target meteorological equipment location information can come from the equipment deployment coordinate data pre-stored on the edge computing node, or be obtained through real-time positioning information; the task sequence is determined by the aforementioned replacement benefit function calculation and sorting results, and is used to indicate the order in which the drone performs multiple replacement tasks.

[0066] After instruction parsing is completed, UAV flight path parameters are generated based on the task sequence. It should be noted that these flight path parameters are not limited to simple straight-line distance paths, but are constructed by comprehensively considering factors such as UAV flight performance, environmental constraints, and task priority. In one implementation, an optimal or suboptimal flight path covering all target devices can be generated using a path optimization algorithm based on the spatial distribution of equipment in the task sequence, thereby reducing flight distance and energy consumption. In another implementation, the path can be dynamically adjusted in conjunction with real-time weather conditions (such as wind speed and air pressure) to ensure flight safety and execution stability.

[0067] After obtaining the flight path parameters, the UAV is controlled to fly to the location of the target meteorological equipment based on these parameters. During flight, the UAV can track its own path using its navigation module and adjust its flight attitude according to real-time environmental information. Once the UAV reaches the target location, it performs the disassembly and replacement of the meteorological equipment. The disassembly and replacement can be performed by a robotic arm, gripping device, or other actuators; the specific implementation is not limited, as long as it can replace the target meteorological equipment, it falls within the scope of protection of this embodiment.

[0068] After the meteorological equipment replacement operation is completed, corresponding replacement completion status information is generated. This status information may include the equipment number, replacement time, execution status, and simple self-check results, characterizing the execution status of the replacement task. Subsequently, the replacement completion status information is transmitted back to the corresponding edge computing node.

[0069] After receiving the replacement completion status information, the edge computing node triggers a re-acquisition process of meteorological parameter data for the corresponding meteorological equipment, i.e., to obtain updated meteorological parameter data. Based on the updated meteorological parameter data, the effective deviation data sequence construction and subsequent degradation status analysis are re-executed, thereby realizing the verification of the equipment replacement effect and the closed-loop update of subsequent replacement decisions.

[0070] like Figure 2 As shown, this invention provides an edge computing drone meteorological equipment replacement system. The system includes: a data acquisition unit, used to acquire meteorological parameter data at the edge computing nodes corresponding to each meteorological device, and perform preprocessing on the meteorological parameter data locally at the corresponding edge computing nodes to generate effective deviation data sequences for each meteorological device; a characterization result determination unit, used to calculate degradation state parameters for each meteorological device at the corresponding edge computing nodes based on the effective deviation data sequences, and generate degradation state characterization results for each meteorological device by combining pre-stored neighboring meteorological device association data; an instruction generation unit, used to construct a replacement benefit function based on the degradation state characterization results, and determine the replacement trigger result and task priority parameters for each meteorological device according to the replacement benefit function, and output a drone replacement instruction when a preset trigger condition is met; and an instruction execution unit, used to control the drone to perform meteorological equipment replacement operations based on the drone replacement instruction.

[0071] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described edge computing drone weather equipment replacement method.

[0072] In another possible implementation, to address the situation where meteorological equipment in high-altitude or wind-prone areas is prone to structural loosening but the data has not yet shown obvious anomalies, an auxiliary discrimination mechanism based on flight disturbance response is introduced. During the UAV's routine replacement mission flight, attitude disturbance data of the UAV as it approaches the target meteorological equipment area is simultaneously collected, including roll angle change, pitch angle change rate, and propulsion power fluctuation parameters, and local airflow interference intensity parameters are constructed based on the disturbance data.

[0073] Furthermore, the local airflow disturbance intensity parameter is correlated with the effective deviation value of the corresponding meteorological equipment. When an abnormal airflow disturbance intensity is detected but the equipment deviation has not yet increased significantly, it is determined that the meteorological equipment has a potential structural failure risk, and the degradation rate parameter of the corresponding equipment is pre-corrected, thereby triggering a replacement decision in advance. This implementation utilizes accompanying perception information during UAV flight to supplement the equipment status judgment, avoiding the problem of delayed identification caused by relying solely on meteorological data. It is particularly suitable for the detection of hidden faults in tower-type meteorological equipment in strong wind areas.

[0074] In another possible implementation, the physical coupling relationship between multiple sensing parameters (such as temperature, humidity, and air pressure) of the same meteorological device is modeled, and correlation response coefficients between the parameters are constructed. During real-time operation, based on the changes in the effective deviation value, the multi-parameter consistency deviation is calculated in conjunction with the correlation response coefficients. When a deviation is detected in a certain parameter but its coupling relationship with other parameters deviates abnormally, it is determined that the meteorological device has a problem with blocked sensing channels or local contamination.

[0075] Furthermore, the stability parameters of the corresponding equipment are increased, thereby amplifying their impact in the replacement benefit function and enabling such atypical degradation to be prioritized for identification and replacement. This implementation method, by introducing physical relationship constraints between parameters, distinguishes the sources of sensor anomalies and is suitable for equipment health assessment under complex climatic conditions.

[0076] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The network interface A02 is used for communication with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements a method for replacing meteorological equipment on an edge computing UAV.

[0077] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor 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 a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0078] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details described above. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe the various possible combinations.

[0079] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the embodiments of the present invention, they should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. A method for replacing meteorological equipment on an edge computing drone, characterized in that, The method includes: Meteorological parameter data is acquired at the edge computing nodes corresponding to each meteorological device, and the meteorological parameter data is preprocessed locally on the corresponding edge computing nodes to generate effective deviation data sequences for each meteorological device. At the corresponding edge computing node, the degradation state parameters of each meteorological device are calculated based on the effective deviation data sequence, and the degradation state characterization results of each meteorological device are generated by combining the pre-stored neighboring meteorological device association data. Based on the degradation state characterization results, a replacement benefit function is constructed, and the replacement trigger result and task priority parameters of each meteorological device are determined according to the replacement benefit function. When the preset trigger conditions are met, the UAV replacement command is output. Based on the aforementioned drone replacement command, the drone is controlled to perform meteorological equipment replacement operations.

2. The method for replacing meteorological equipment on an edge computing drone according to claim 1, characterized in that, Meteorological parameter data is acquired at the edge computing nodes corresponding to each meteorological device, and preprocessed locally on the corresponding edge computing nodes to generate effective deviation data sequences for each meteorological device, including: Within the corresponding edge computing node, a sliding time window data sequence is constructed for the meteorological parameter data according to a preset sampling time interval, and the short-term fluctuation energy parameter and long-term fluctuation energy parameter of each meteorological parameter are calculated based on the sliding time window data sequence. Based on the ratio of the short-term fluctuation energy parameter and the long-term fluctuation energy parameter, the transient disturbance discrimination result of each meteorological parameter is determined, and when a transient disturbance is determined, the sliding time window data sequence is removed to generate a data sequence with transient disturbance removed. Based on the difference between the data sequence after removing transient disturbances and the preset reference meteorological parameter data, the original deviation data of each meteorological parameter is calculated, and the original deviation data is normalized to generate the effective deviation data sequence of each meteorological device.

3. The method for replacing meteorological equipment on an edge computing drone according to claim 1, characterized in that, The corresponding edge computing nodes calculate the degradation state parameters of each meteorological device based on the effective deviation data sequence, including: Within the corresponding edge computing node, time series differential data is constructed from the effective deviation data sequence, and deviation change rate data sequence for each meteorological device is calculated based on the time series differential data. The degradation rate parameter of each meteorological device is calculated based on the deviation change rate data sequence and the effective deviation data sequence, and the remaining usable time parameter of each meteorological device is determined based on the difference between the degradation rate parameter and the preset failure threshold. Based on the effective deviation data sequence, the degradation rate parameter, and the remaining available time parameter, degradation status parameters corresponding to each meteorological device are generated.

4. The method for replacing meteorological equipment on an edge computing drone according to claim 3, characterized in that, Based on the deviation change rate data sequence and the effective deviation data sequence, the degradation rate parameters of each meteorological device are calculated, including: Within the corresponding edge computing node, the rate of change fluctuation amplitude parameter of each meteorological device is constructed based on the deviation change rate data sequence, and the change stability parameter of each meteorological device is determined based on the rate of change fluctuation amplitude parameter. Based on the current deviation value of the effective deviation data sequence and the change stability parameter, the deviation change rate data sequence is weighted to generate a weighted change rate data sequence corresponding to each meteorological device; The degradation rate parameters of each meteorological device are calculated based on the weighted rate of change data sequence.

5. The method for replacing meteorological equipment on an edge computing drone according to claim 3, characterized in that, By combining pre-stored correlation data of neighboring meteorological equipment, the degradation status characterization results of each meteorological equipment are generated, including: Within the corresponding edge computing node, the set of neighboring meteorological devices for each meteorological device is determined based on the association data of the neighboring meteorological devices, and the effective deviation data sequence corresponding to the set of neighboring meteorological devices is extracted; Based on the effective deviation data sequence and the effective deviation data sequence corresponding to the set of neighboring meteorological devices, calculate the deviation consistency parameter between each meteorological device and its neighboring meteorological devices; Based on the aforementioned deviation consistency parameter, the degradation state parameters of each meteorological device are corrected to generate the degradation state characterization results of each meteorological device.

6. The method for replacing meteorological equipment on an edge computing drone according to claim 1, characterized in that, The replacement benefit function is: ； in, Let be the value of the replacement benefit function for the i-th meteorological device; This represents the effective deviation value of the i-th meteorological device. The remaining available time parameter for the i-th meteorological device; It is a non-zero constant; This is the trend amplification factor; Let be the degradation rate parameter of the i-th meteorological device; For reference degradation rate parameters; Let be the stability parameter of the i-th meteorological device; Let be the spatial consistency parameter of the i-th meteorological device; Weights for transient disturbance correction coefficients; This is the transient disturbance correction factor; , , This is the cost weighting coefficient; Flight distance; For flight time; This refers to energy consumption parameters.

7. The method for replacing meteorological equipment on an edge computing drone according to claim 1, characterized in that, Based on the replacement benefit function, the replacement trigger result and task priority parameters for each meteorological device are determined. When the preset trigger conditions are met, a UAV replacement command is output, including: Obtain the replacement benefit function value of each meteorological device, and compare the replacement benefit function value with a preset benefit threshold to generate the corresponding replacement trigger result for each meteorological device; The task priority parameters for each meteorological device are calculated based on the replacement benefit function value of each meteorological device, and the meteorological devices are sorted according to the task priority parameters to generate a UAV replacement task sequence. When the replacement trigger result meets the preset trigger conditions, a corresponding UAV replacement command is generated based on the UAV replacement task sequence and output to the UAV control terminal to control the UAV to perform the meteorological equipment replacement operation.

8. The method for replacing meteorological equipment on an edge computing drone according to claim 7, characterized in that, Based on the aforementioned drone replacement command, the drone is controlled to perform a meteorological equipment replacement operation, including: Based on the UAV replacement command, the corresponding target meteorological equipment location information and task sequence are parsed, and the UAV flight path parameters are generated according to the task sequence; Based on the flight path parameters, the UAV is controlled to fly to the location of the target meteorological equipment, and after reaching the target location, the meteorological equipment is disassembled and replaced, generating replacement completion status information; After the replacement completion status information is generated, the replacement completion status information is sent back to the corresponding edge computing node, and the edge computing node is triggered to obtain the updated meteorological parameter data for closed-loop updates in subsequent replacement decisions.

9. An edge computing drone meteorological equipment replacement system, characterized in that, The system includes: The data acquisition unit is used to acquire meteorological parameter data at the edge computing nodes corresponding to each meteorological device, and perform preprocessing on the meteorological parameter data locally at the corresponding edge computing node to generate a valid deviation data sequence for each meteorological device. The characterization result determination unit is used to calculate the degradation state parameters of each meteorological device based on the effective deviation data sequence at the corresponding edge computing node, and generate the degradation state characterization result of each meteorological device by combining the pre-stored neighboring meteorological device association data. The instruction generation unit is used to construct a replacement benefit function based on the degradation state characterization result, and determine the replacement trigger result and task priority parameters of each meteorological device according to the replacement benefit function, and output the UAV replacement instruction when the preset trigger condition is met. The instruction execution unit is used to control the UAV to perform meteorological equipment replacement operations based on the UAV replacement instruction.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the edge computing drone weather equipment replacement method as described in any one of claims 1-8.

Images