An intelligent operation management method for a UAV

Abstract

The present application relates to the field of unmanned aerial vehicle operation management, and particularly relates to an intelligent operation management method for unmanned aerial vehicle, which extracts the growth distribution characteristics of crops in each sub-planting area by collecting crop growth data of the crop planting area and execution data of the unmanned aerial vehicle for spraying operation; combines the growth distribution characteristics and the crop compactness to calculate the distribution shielding representation parameters of the sub-planting area, sets the growth state label for each sub-planting area; determines the spraying scheme of the corresponding sub-planting area according to the growth state label; obtains the wind speed variation range and the maximum wind speed of the crop planting area within a predetermined time, determines whether it meets the flight environment benchmark, controls the unmanned aerial vehicle to perform spraying operation on the sub-planting area according to the spraying scheme, and then analyzes the spraying situation of the crops. The present application improves the accuracy and effectiveness of the spraying operation, and reduces resource waste.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) operation management, and more particularly to an intelligent operation management method for UAVs. Background Technology

[0002] With the rapid development of smart agriculture technology, drones, due to their advantages such as high efficiency, flexibility, and strong adaptability, are widely used in pesticide spraying in crop planting areas and are gradually becoming one of the core tools for modern agricultural pesticide spraying. By combining technologies such as remote sensing monitoring, intelligent control, big data analysis, and automated operation, precision spraying can be achieved, pesticide utilization can be improved, environmental pollution can be reduced, and agricultural production costs can be lowered.

[0003] Chinese Patent Application Publication No. CN108945469A discloses a pesticide spraying management system based on unmanned aerial vehicles (UAVs), relating to the field of agricultural plant protection technology. The invention includes a UAV body, an information acquisition unit, and an information analysis and control unit. A pesticide storage tank is installed on the bottom of the UAV body, and spraying devices are installed on both sides of the UAV body. Power supply equipment is installed inside the UAV body. The information acquisition unit includes a wind speed sensor, a flow sensor, an altitude sensor, an image acquisition sensor, a light intensity sensor, and a float level gauge. The wind speed sensor and light intensity sensor are installed at the top of the UAV body. A wireless transceiver is installed on the top of the UAV body next to the wind speed sensor. The flow sensor is installed on the spraying device, and the altitude sensor and image acquisition sensor are installed at the bottom of the UAV body. This invention can comprehensively understand the growth status and pest and disease information of crops and carry out targeted pesticide spraying, resulting in good application effects.

[0004] However, the following problems still exist in the existing technology.

[0005] When spraying pesticides on crops in fields, using a standardized spraying plan (such as fixed spray flow rate and fixed flight altitude) is less flexible and cannot adapt to the needs of crops in different sub-regions, thus reducing the effectiveness of pesticide spraying. Summary of the Invention

[0006] Therefore, this invention provides an intelligent operation management method for drones to overcome the problems in the prior art where a uniform spraying scheme is used when spraying crops in fields, resulting in low flexibility, inability to adapt to the needs of crops in different sub-regions, and reduced control effect of pesticide spraying.

[0007] To achieve the above objectives, the present invention provides an intelligent operation management method for unmanned aerial vehicles (UAVs), comprising:

[0008] Crop growth data from crop planting areas and execution data from drone spraying operations are collected to extract the growth distribution characteristics of crops in each sub-planting area. The growth distribution characteristics include canopy void area and canopy overlap area.

[0009] Based on the growth distribution characteristics and crop compaction, the distribution shading characterization parameters of the sub-planting areas are calculated, and growth status labels are set for each sub-planting area.

[0010] Based on the growth status labels, determine the spraying plan for the corresponding sub-planting areas;

[0011] The system obtains the wind speed variation range and maximum wind speed of the crop planting area within a predetermined time, determines whether it meets the flight environment benchmark, and controls the drone to carry out spraying operations on the sub-planting area according to the spraying plan.

[0012] The drone's flight trajectory is used to determine the maximum height difference of crop growth in the sub-planting areas along the flight trajectory and the spray coverage rate to evaluate the spraying quality characterization value of the drone, so as to determine whether the spraying of the sub-planting areas meets the standards.

[0013] Construct a time-domain variation curve of spray flow rate, determine the stage of flow rate change, call up the image of crops in the sub-planting area of ​​the flow rate change stage, identify the spray adhesion characteristics of the crops, and determine whether the sub-planting area needs to be compensated with spraying.

[0014] The spray adhesion characteristics include the average droplet accumulation profile ratio at the crop edge and the average area of ​​the unattached sprayed area.

[0015] Furthermore, the process of calculating the distribution shading characterization parameters of the sub-planting region includes:

[0016] The sum of the ratio of the canopy void area to the canopy void area threshold and the ratio of the canopy overlap area to the canopy overlap area threshold is used as the first distribution occlusion feature.

[0017] The ratio of crop compactness to crop compactness threshold is used as the second distribution occlusion feature;

[0018] The weighted sum of the first distribution occlusion feature and the second distribution occlusion feature is used to determine the distribution occlusion characterization parameter.

[0019] Furthermore, the process of setting growth status tags for each of the aforementioned sub-planting areas includes:

[0020] The correspondence between growth status labels and predetermined distribution occlusion characterization parameter ranges is pre-defined;

[0021] Determine the distribution occlusion characterization parameter interval to which the corresponding sub-planting area belongs in order to determine the corresponding growth status label;

[0022] Among them, the growth status label corresponds one-to-one with the distribution occlusion characterization parameter range.

[0023] Further, based on the growth status label, the spraying plan for the corresponding sub-planting area is determined, including:

[0024] The spraying plan corresponds one-to-one with the growth status labels of the sub-planting areas;

[0025] The spraying scheme is preset.

[0026] Further, determining whether the flight environment standards are met includes:

[0027] If the wind speed change in the crop planting area is less than the wind speed change threshold and the maximum wind speed is less than the maximum wind speed threshold within the predetermined time, then it is determined that the flight environment benchmark is met.

[0028] Furthermore, controlling the drone to spray the sub-planting area according to the spraying plan includes:

[0029] If the flight environment criteria are met, the drone is controlled to spray the sub-planting area according to the spraying plan.

[0030] Furthermore, the process of evaluating the spraying quality characterization values ​​of the drone includes:

[0031] The ratio of the maximum height difference of crop growth in the sub-planting area to the threshold of the maximum height difference of crop growth is used as the first spraying quality characteristic;

[0032] The ratio of the spray coverage threshold to the spray coverage rate is used as the second spray quality characteristic;

[0033] The sum of the first spraying quality characteristic and the second spraying quality characteristic is taken as the spraying quality characterization value.

[0034] Further, determining whether the spraying of the sub-planting area meets the standards includes:

[0035] If the spraying quality characterization value of the drone is less than the spraying quality characterization threshold, then the spraying of the sub-planting area is determined to meet the standard.

[0036] Furthermore, the process of determining the flow mutation phase includes:

[0037] If there exists a time domain segment with a slope greater than or equal to a slope threshold, then the time domain segment is determined as the flow mutation stage.

[0038] Further, determining whether compensatory spraying is needed for the sub-planting areas includes:

[0039] If the average droplet accumulation profile ratio at the edge of the crop within any sub-planting area is greater than the droplet accumulation profile ratio threshold or / and the average area of ​​the non-attached sprayed area is greater than the non-attached sprayed area threshold, then it is determined that the sub-planting area needs to be compensated for.

[0040] Compared with existing technologies, this invention extracts the growth distribution characteristics of crops in each sub-planting area by collecting crop growth data from the crop planting area and execution data of drone spraying operations. It then calculates distribution shading characterization parameters for each sub-planting area based on the growth distribution characteristics and crop compaction, and sets growth status labels for each sub-planting area. Based on the growth status labels, it determines the spraying plan for the corresponding sub-planting area; it acquires the wind speed variation and maximum wind speed in the crop planting area within a predetermined time period to determine whether it meets flight environment benchmarks, and controls the drone to spray the sub-planting area according to the spraying plan, thereby analyzing the crop spraying situation. This invention improves the accuracy and effectiveness of spraying operations and reduces resource waste.

[0041] In particular, before using drones to spray pesticides on crops in fields, this invention prioritizes the growth status of crops within the sub-planting area. This facilitates the adaptive selection of spraying schemes and quantifies crop growth status. The canopy void area reflects the sparseness of crops; for example, a larger canopy void area indicates a sparser crop distribution, a higher probability of "dry spraying" of droplets during drone spraying, and even pesticide residues in the soil, which can easily damage the soil's aggregate structure and reduce soil fertility. Simultaneously, the invention extracts the area of ​​overlapping crop canopies within the sub-planting area, i.e., the area where the canopies of different crops intersect, reflecting the degree of crop shading. For example, a larger overlapping area of ​​different crop canopies indicates a denser crop distribution and more severe mutual shading. During subsequent spraying, droplets need to penetrate the overlapping layers to reach the lower crops. Furthermore, while analyzing the overall growth status of crops in the sub-planting areas, this invention also considers the morphological density of individual crops. For example, higher crop compactness indicates a more concentrated canopy and denser foliage, resulting in more significant self-shading. During subsequent drone spraying, the compact foliage structure will cause more obstruction, potentially reducing droplet adhesion to lower leaves or crop roots and affecting droplet penetration. Therefore, this invention quantifies the degree of shading by the drone sprayed by crops in the sub-planting areas by calculating distribution shading characterization parameters. This provides data support for setting growth status labels for each sub-planting area. This invention improves the accuracy and effectiveness of spraying operations and reduces resource waste.

[0042] In particular, under the premise that environmental factors meet the flight environment benchmarks for drones, the drone is controlled to perform spraying operations. By quantifying the height differences of crops within the sub-planting area, the greater the height difference between crops, the more uneven the crop distribution. When the drone sprays along a fixed trajectory, the problem of "sufficient coverage of the top of tall plants and insufficient coverage of short plants or sunken areas" may occur. Furthermore, the spray coverage rate directly reflects the degree of matching between the actual spray droplet coverage range of the drone and the target area. Therefore, this invention evaluates the spraying quality characterization value based on the maximum height difference of crop growth and the spray coverage rate to characterize the coverage integrity and spraying quality of the drone spraying operation on the sub-planting area. This provides data support for subsequent determination of whether the drone spraying of the sub-planting area meets the standards. This invention improves the accuracy and effectiveness of spraying operations and reduces resource waste.

[0043] In particular, this invention achieves targeted and efficient compensatory spraying by accurately locating abnormal phases of flow rate changes during drone spraying and combining this with the actual adhesion effect of pesticide droplets on crops within sub-planting areas. It pinpoints the flow rate change phase, quickly identifies sub-planting areas requiring special attention, and avoids indiscriminate inspection of the entire planting area, thus improving problem-solving efficiency. Furthermore, it analyzes the pesticide adhesion effect in these key sub-planting areas. The droplet accumulation profile at crop edges reflects whether droplets are excessively accumulated; excessive local spraying could lead to pesticide waste or crop damage. The area of ​​unattached areas quantifies the size of the unpowder-covered areas on the crop surface. Excessive unattached areas indicate insufficient spraying, facilitating subsequent determination of whether compensatory spraying is needed in sub-planting areas. Based on this, this invention, through the logic of "abnormal location - effect verification - on-demand supplementary spraying," ensures the quality of drone spraying while avoiding the waste of pesticides, time, and energy caused by blind supplementary spraying. This improves the accuracy and effectiveness of spraying operations and reduces resource waste. Attached Figure Description

[0044] Figure 1 This is a schematic diagram illustrating the steps of an intelligent operation management method for unmanned aerial vehicles (UAVs) according to an embodiment of the invention.

[0045] Figure 2 A logic diagram for determining whether a flight environment standard is met in an embodiment of the invention;

[0046] Figure 3 A logic diagram for determining whether the spraying of a sub-planting area meets the standards in an embodiment of the invention;

[0047] Figure 4 A logic decision diagram for determining the flow mutation stage in an embodiment of the invention. Detailed Implementation

[0048] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0049] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0050] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0051] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0052] Please see Figure 1 The diagram illustrates the steps of an intelligent operation management method for unmanned aerial vehicles (UAVs) according to an embodiment of the present invention. The intelligent operation management method for UAVs according to an embodiment of the present invention includes:

[0053] Step S1: Collect crop growth data of the crop planting area and execution data of the drone spraying operation to extract the growth distribution characteristics of crops in each sub-planting area. The growth distribution characteristics include the canopy void area and the canopy overlap area.

[0054] Step S2: Calculate the distribution shading characterization parameters of the sub-planting areas based on the growth distribution characteristics and crop compactness, and set growth status labels for each sub-planting area;

[0055] Step S3: Determine the spraying plan for the corresponding sub-planting area based on the growth status label;

[0056] Step S4: Obtain the wind speed change range and maximum wind speed of the crop planting area within a predetermined time, determine whether it meets the flight environment benchmark, and control the drone to spray the sub-planting area according to the spraying plan.

[0057] Step S5: Call the flight trajectory of the drone, determine the maximum height difference of crop growth in the sub-planting area on the flight trajectory and the spray coverage rate to evaluate the spraying quality characterization value of the drone, so as to determine whether the spraying of the sub-planting area meets the standard.

[0058] Step S6: Construct a time-domain variation curve of spray flow rate, determine the stage of flow rate change, call up the image of the crop in the sub-planting area of ​​the flow rate change stage, identify the spray adhesion characteristics of the crop, and determine whether the sub-planting area needs to be compensated with spraying.

[0059] The spray adhesion characteristics include the average droplet accumulation profile ratio at the crop edge and the average area of ​​the unattached sprayed area.

[0060] Specifically, there is no limitation on the way sub-planting areas are divided; they can be divided according to the growth cycle of the crop, which will not be elaborated further.

[0061] Specifically, the crop growth data includes the growth distribution characteristics of crops in each sub-planting area, crop compactness, and the maximum height difference of crop growth in the sub-planting areas; the execution data includes the wind speed variation range and maximum wind speed in the crop planting area, the flight trajectory of the drone, spraying flow rate, spraying coverage, and the spraying adhesion characteristics of the crops.

[0062] The crop compactness is defined as the ratio of the projected area of ​​a single plant canopy (the effective space it actually occupies) to the area of ​​the plant's largest circumscribed rectangle (the theoretical maximum boundary space).

[0063] Specifically, the acquisition of crop growth data and crop spray adhesion characteristics can be achieved by using a drone equipped with a visual sensor, combined with image analysis algorithms. This is existing technology and will not be elaborated further.

[0064] Specifically, to predict the wind speed variation range and maximum wind speed in the crop planting area, agricultural meteorological stations can be set up according to the structure of the field. For example, two agricultural meteorological stations can be set up in the center of the field, and one agricultural meteorological station can be set up in each of the four meteorological directions. One agricultural meteorological station can be set up 10m upwind of the field to predict the wind speed variation range and maximum wind speed in the crop planting area within a predetermined time period, with the predetermined time period set at 20 minutes.

[0065] Specifically, the spray flow rate can be obtained by using a drone equipped with a flow sensor to capture the flow rate of the pesticide passing through the nozzle per unit time. Combined with the drone trajectory determined by GPS, it can also be used to locate the spraying area and determine the spraying coverage.

[0066] Among them, the drone is equipped with an adjustable spraying system to perform spraying operations, and the drone's flight trajectory is obtained through the drone's GPS positioning function.

[0067] Specifically, the process of calculating the distribution shading characterization parameters of the sub-planting area includes:

[0068] The sum of the ratio of the canopy void area to the canopy void area threshold and the ratio of the canopy overlap area to the canopy overlap area threshold is used as the first distribution occlusion feature.

[0069] The ratio of crop compactness to crop compactness threshold is used as the second distribution occlusion feature;

[0070] The weighted sum of the first distribution occlusion feature and the second distribution occlusion feature is used to determine the distribution occlusion characterization parameter.

[0071] Specifically, the canopy void area and canopy overlap area of ​​each sub-planting area visually reflect the spatial distribution density and mutual shading relationship of crops within each sub-planting area. A larger void area increases the probability of "dry spraying" of mist droplets during drone spraying, easily leading to resource waste and increased costs. Furthermore, "dry spraying" residues may remain in the soil; long-term dry spraying may exceed the soil's natural degradation capacity, causing the accumulation of heavy metals and chemicals in the soil, altering its physicochemical properties (such as pH and organic matter content), damaging soil aggregate structure, and reducing soil fertility. The overlap area directly reflects the "percentage of areas where crops mutually cover each other" within the sub-planting area; a larger overlap area indicates a denser crop layer. The higher the degree of overlap, the more "multiple layers of obstruction" the droplets need to penetrate when falling from the air, and the more difficult it is for the underlying crops to be covered. While analyzing the overall effect of the sub-planting area on the received pesticide spraying, the crop compactness reflects the morphological density of individual crops, and the obstruction situation is quantified in detail. The impact of regional obstruction on pesticide spraying is comprehensively captured. Therefore, in implementation, the growth distribution characteristics, namely the canopy void area and the canopy overlap area, are given priority. Thus, the first distribution obstruction feature calculated based on the growth distribution characteristics is given a slightly higher weight. Therefore, when performing weighted summation, the weight of the first distribution obstruction feature is set to 0.6, and the weight of the second distribution obstruction feature is set to 0.4.

[0072] In this embodiment, the purpose of setting thresholds for canopy void area, canopy overlap area, and crop compaction is to characterize situations where the growth distribution of crops within a sub-planting area significantly obstructs droplets, leading to frequent "dry spraying" and affecting the effectiveness of pesticide spraying. By acquiring historical data from several instances of drone-based pesticide spraying of the same crop at the same growth stage, and by calling historical data on canopy void area, canopy overlap area, and crop compaction, the average values ​​of canopy void area, canopy overlap area, and crop compaction are calculated and used as baseline values ​​under normal conditions. Based on the purpose of setting the above three thresholds, the canopy void area threshold is determined as the product of the average canopy void area and the void deviation coefficient; the canopy overlap area threshold is determined as the product of the average canopy overlap area and the overlap deviation coefficient; and the crop compactness threshold is determined as the product of the average crop compactness and the compactness deviation coefficient. The void deviation coefficient is in the range [1.1, 1.15], preferably 1.1 in practice; the overlap deviation coefficient is selected within the range [1.15, 1.25], preferably 1.15 in practice; and the compactness deviation coefficient is selected within the range [1.1, 1.2], preferably 1.1 in practice.

[0073] Among these methods, the height of the canopy is detected using millimeter-wave radar carried by drones.

[0074] Specifically, before using drones to spray pesticides on crops in fields, this invention prioritizes the growth status of crops within the sub-planting area. This facilitates the adaptive selection of spraying schemes and quantifies crop growth status. The canopy void area reflects the sparseness of the crops; for example, a larger canopy void area indicates a sparser crop distribution, increasing the probability of "dry spraying" of droplets during drone spraying. Furthermore, pesticide residues on the soil can easily damage the soil's aggregate structure and reduce soil fertility. Simultaneously, the invention extracts the overlapping area of ​​crop canopies within the sub-planting area—the area where different crop canopies intersect—to reflect the degree of crop shading. For example, a larger overlapping area indicates a denser crop distribution and more severe shading. Subsequently… During spraying, droplets need to penetrate overlapping layers to reach the underlying crops. Furthermore, this invention analyzes the overall growth status of crops in sub-planting areas while also considering the morphological density of individual crops. For example, higher crop compactness indicates a more concentrated canopy, denser foliage, and more significant self-shading (such as leaves overlapping). During subsequent drone spraying, the compact foliage structure will cause more obstruction, potentially reducing droplet adhesion to lower leaves or crop roots and affecting droplet penetration. Therefore, this invention quantifies the degree of shading by the drone sprayed by crops in sub-planting areas by calculating distribution shading characterization parameters. This provides data support for setting growth status labels for each sub-planting area. This invention improves the accuracy and effectiveness of spraying operations and reduces resource waste.

[0075] Specifically, the process of setting growth status tags for each of the aforementioned sub-planting areas includes:

[0076] The correspondence between growth status labels and predetermined distribution occlusion characterization parameter ranges is pre-defined;

[0077] Determine the distribution occlusion characterization parameter interval to which the corresponding sub-planting area belongs in order to determine the corresponding growth status label;

[0078] Among them, the growth status label corresponds one-to-one with the distribution occlusion characterization parameter range.

[0079] In this embodiment, the growth status labels for each sub-planting area are set in the following manner:

[0080] The distribution occlusion characterization parameters are divided into three preset intervals, and three levels of growth status labels are set.

[0081] If the distribution occlusion characterization parameter corresponding to the sub-planting area is within the first preset interval (0, 1.65), then the first growth status label 1 is set.

[0082] If the distribution occlusion characterization parameter corresponding to the sub-planting area is within the second preset interval [1.65, 1.72), then the second growth status label 2 is set;

[0083] If the distribution occlusion characterization parameter corresponding to the sub-planting area is within the third preset interval [1.72, +∞), then the third growth state label 3 is set.

[0084] Specifically, based on the growth status labels, the spraying plan for the corresponding sub-planting areas is determined, including:

[0085] The spraying plan corresponds one-to-one with the growth status labels of the sub-planting areas;

[0086] The spraying scheme is preset.

[0087] During implementation, three spraying plans were pre-set, each corresponding to a growth status label, including:

[0088] The first spraying scheme corresponds to the first growth state label 1, and the first spraying scheme includes:

[0089] The system employs a first spray velocity S1, a first flight altitude H1, a first flight speed A1, and a first nozzle angle R1.

[0090] The second spraying scheme corresponds to the second growth state label 2, and the second spraying scheme includes:

[0091] The system employs a second spray velocity S2, a second flight altitude H2, a second flight speed A2, and a second nozzle angle R2.

[0092] The third spraying scheme corresponds to the third growth state label 3, and the third spraying scheme includes:

[0093] The system employs a third spray velocity S3, a third flight altitude H3, a third flight speed A3, and a third nozzle angle R3.

[0094] Understandably, the impact of environmental factors on the spraying operation of the drone is given priority in the implementation. Under the premise of meeting the flight environment benchmark, the drone is controlled to perform the spraying operation. Based on this, for cases where the crop distribution in the sub-planting area has a low degree of obstruction of the drone spray droplets, the first nozzle angle R1 of the drone is selected in the range [0°, 5°) to ensure a stable spray width. For areas where the distribution between crops is more obstructed, in order to guide the pesticide to penetrate into the middle and lower layers of the crops and avoid the droplets drifting to the ground, causing damage to the soil and wasting the pesticide, the nozzle angle can be adjusted appropriately. Based on this, the second nozzle angle R2 is selected in the range [5°, 10°), and the third nozzle angle R3 is selected in the range [10°, 15°), where the nozzle angle is the angle between the nozzle and the vertical direction.

[0095] Specifically, for cases where the crop distribution in the sub-planting area has a low degree of obstruction to the droplets sprayed by the drone, the first flight speed A1 of the drone can be determined according to industry-standard criteria. For conventional field crops, in order to balance the spraying efficiency and uniformity of the pesticide, the first flight speed A1 of the drone can be selected in the range of [3m / s, 5m / s]. In order to ensure the coverage of pesticide spraying in areas where the distribution between crops is more obstructed, enhance the penetration of the pesticide solution, and reduce droplet drift, the flight speed of the drone should be appropriately reduced. Therefore, the second flight speed A2 is selected in the range of [0.7A1, 0.8A1], and the third flight speed A3 is selected in the range of [0.5A1, 0.6A1].

[0096] Understandably, when using drones to spray pesticides on crops in fields, the drone's flight altitude, i.e., the vertical distance between the drone and the crop canopy, should ensure the penetration of the sprayed droplets into the crops and reduce droplet drift (the higher the flight altitude, the greater the risk of drift). Therefore, when determining the drone's flight altitude, if the crop distribution in the sub-planting area has a low degree of obstruction to the sprayed droplets, the drone should be controlled to use a first flight altitude H1 (2m~3m) for spraying. Since the degree of obstruction varies between crops, to ensure the quality and effectiveness of pesticide spraying and increase the vertical penetration of the droplets, the drone's flight altitude should be appropriately reduced, but not too low, otherwise it may cause crop damage or flight risks. Based on this, the second flight altitude H2 is selected within the range [0.8H1, 0.85H1]; and the third flight altitude H3 is selected within the range [0.65H1, 0.7H1].

[0097] In this embodiment, the spraying flow rate of the drug, that is, the amount of drug sprayed per unit time, can be calculated by those skilled in the art using industry-standard formulas. When the crop distribution in the sub-planting area has a low degree of obstruction to the droplets sprayed by the drone, the first spraying flow rate S1 of the drone is determined. However, when the obstruction between crops increases, in order to compensate for the flow gap caused by the decrease in drone flight speed and to compensate for the reduced amount of pesticide sprayed per unit area due to the decrease in flight speed, the spraying flow rate is increased to ensure that the pesticide can penetrate multiple layers of the canopy and achieve effective pesticide deposition. Based on this, the second spraying flow rate S2 is selected in the range [10%S1, 15%S1], and the third spraying flow rate S3 is selected in the range [20%S1, 25%S1].

[0098] The amount of spray per acre can be determined based on the drug label, and the spray width can be determined based on the maximum physical spray width corresponding to the model of the selected drone used to perform the spraying operation. In actual use, the spray width is usually selected within the range of [70% of the maximum physical spray width, 80% of the maximum physical spray width].

[0099] Specifically, please refer to Figure 2 As shown, this is a logic diagram for determining whether a flight environment benchmark is met according to an embodiment of the present invention. The determination of whether a flight environment benchmark is met includes:

[0100] If the wind speed change in the crop planting area is less than the wind speed change threshold and the maximum wind speed is less than the maximum wind speed threshold within the predetermined time, then it is determined that the flight environment benchmark is met.

[0101] In this embodiment, the purpose of setting the wind speed variation threshold and the maximum wind speed threshold is to characterize the situation where environmental factors have little impact on the normal flight of the drone and can ensure that the drone can perform spraying operations smoothly. Based on this, in practice, the maximum wind speed threshold is set to 3m / s.

[0102] The system acquires historical data on several instances of pesticide spraying of the same crop with the same growth cycle using drones. It also retrieves historical data on wind speed variation in the crop planting area within a predetermined time period, calculates the average wind speed variation, and uses it as a benchmark value under normal conditions. Based on the purpose of setting a wind speed variation threshold, the average wind speed variation is set as the wind speed variation threshold.

[0103] Specifically, controlling the drone to spray the sub-planting area according to the spraying plan includes:

[0104] If the flight environment criteria are met, the drone is controlled to spray the sub-planting area according to the spraying plan.

[0105] Specifically, the process of evaluating the spraying quality characterization values ​​of the drone includes:

[0106] The ratio of the maximum height difference of crop growth in the sub-planting area to the threshold of the maximum height difference of crop growth is used as the first spraying quality characteristic;

[0107] The ratio of the spray coverage threshold to the spray coverage rate is used as the second spray quality characteristic;

[0108] The sum of the first spraying quality characteristic and the second spraying quality characteristic is taken as the spraying quality characterization value.

[0109] In this embodiment, the purpose of setting the maximum height difference threshold for crop growth is to characterize the poor flatness of crop distribution in the sub-planting area, which easily leads to "sufficient coverage of the top of tall plants and insufficient coverage of short plants or sunken areas". By acquiring historical data of several times when the same crop with the same growth cycle was sprayed with pesticides by drone, the historical data of the maximum height difference of crop growth in the sub-planting area is called to solve the mean of the maximum height difference of crop growth, and it is used as the benchmark value under normal conditions. Based on the purpose of setting the maximum height difference threshold for crops, the maximum height difference threshold for crops is determined to be the product of the mean of the maximum height difference of crops and the height deviation coefficient. The height deviation coefficient is selected in the interval [1.1, 1.2], and is preferably 1.1 in practice.

[0110] The purpose of setting the spray coverage threshold is to characterize situations where the crop has low coverage integrity of the spray droplets, resulting in poor pesticide application and an increased likelihood of local pests and diseases, further exacerbating crop damage. It also reflects the spatial distribution of the spray droplets on the crop surface. Under normal circumstances, the spray droplets from the drone should completely cover the crop surface to achieve the desired spraying effect. Based on this, in practice, the spray coverage threshold is set to 1, which will not be elaborated further.

[0111] Specifically, under the premise that environmental factors meet the flight environment benchmarks for drones, the drone is controlled to perform spraying operations. By quantifying the height differences of crops within the sub-planting area (e.g., some plants are too tall, some are too short), the greater the height difference between crops, the more uneven the crop distribution. When the drone sprays along a fixed trajectory, there may be problems such as "sufficient coverage of the top of tall plants, and insufficient coverage of short plants or sunken areas." Therefore, the spray coverage rate directly reflects the degree of matching between the actual spray droplet coverage range of the drone and the target area. Thus, this invention evaluates the spraying quality characterization value based on the maximum height difference of crop growth and the spray coverage rate to characterize the coverage integrity and spraying quality of the drone spraying operation on the sub-planting area. This provides data support for subsequent determination of whether the drone spraying of the sub-planting area meets the standards. This invention improves the accuracy and effectiveness of spraying operations and reduces resource waste.

[0112] Specifically, please refer to Figure 3As shown, this is a logic diagram for determining whether the spraying of a sub-planting area meets the standards according to an embodiment of the present invention. Determining whether the spraying of the sub-planting area meets the standards includes:

[0113] If the spraying quality characterization value of the drone is less than the spraying quality characterization threshold, then the spraying of the sub-planting area is determined to meet the standard.

[0114] If the spraying quality characterization value of the drone is greater than or equal to the spraying quality characterization threshold, then the spraying of the sub-planting area is determined to be substandard.

[0115] The spraying quality characterization threshold is predetermined. The spraying quality characterization value calculated under the conditions that the maximum height difference of crop growth in the planting area is equal to the maximum height difference threshold of crop growth, and the spraying coverage threshold is equal to the spraying coverage, is determined as the spraying quality characterization threshold.

[0116] Specifically, the process of constructing the time-domain variation curve of the spray flow rate includes:

[0117] A rectangular coordinate system is constructed with time as the horizontal axis and the spraying flow rate of the drone as the vertical axis;

[0118] The coordinates of the spray flow rate at each moment are marked in the rectangular coordinate system.

[0119] Connect the coordinate points with a smooth curve to obtain the time-domain variation curve of the spray flow rate.

[0120] Specifically, there are no restrictions on the method for constructing the time-domain variation curve of the spray flow rate. For example, the time-domain variation curve can be fitted using MATLAB correlation fitting software, which will not be elaborated further here.

[0121] Specifically, please refer to Figure 4 As shown, this is a logic decision diagram for determining the traffic mutation stage in an embodiment of the present invention. The process of determining the traffic mutation stage includes:

[0122] If there exists a time domain segment with a slope greater than or equal to a slope threshold, then the time domain segment is determined as the flow mutation stage.

[0123] In this embodiment, the purpose of setting the slope threshold is to identify the stage where the spraying flow of the drone is abnormal. The fluctuation of the spraying flow of the drone can reflect the fluctuation of the efficacy of the sprayed drug. When the spraying operation is in this stage, it may cause either the risk of pesticide residue or the consequence of insufficient prevention effect. Based on this, the slope threshold is selected in the range [0.35, 0.45].

[0124] Specifically, determining whether compensatory spraying is needed for the sub-planting areas includes:

[0125] If the average droplet accumulation profile ratio at the edge of the crop within any sub-planting area is greater than the droplet accumulation profile ratio threshold or / and the average area of ​​the non-attached sprayed area is greater than the non-attached sprayed area threshold, then it is determined that the sub-planting area needs to be compensated for.

[0126] In this embodiment, the purpose of setting the droplet accumulation profile ratio threshold and the sprayed non-attached area threshold is to characterize the poor adhesion effect of crops to droplets. By acquiring historical data of several times that the same crop with the same growth cycle was sprayed with pesticides by drone, the historical data of the average droplet accumulation profile ratio and the average sprayed non-attached area of ​​the crop edge in the sub-planting area are called. The average values ​​of the average droplet accumulation profile ratio and the average sprayed non-attached area are calculated and used as the benchmark quantities under normal conditions. Based on the purpose of setting the above two thresholds, the droplet accumulation profile ratio threshold is determined to be the product of the average droplet accumulation profile ratio and the accumulation deviation coefficient, and the sprayed non-attached area threshold is determined to be the product of the average sprayed non-attached area and the adhesion deviation coefficient. The accumulation deviation coefficient is selected in the interval [1.1, 1.15], preferably 1.1 in practice, and the adhesion deviation coefficient is selected in the interval [1.15, 1.2], preferably 1.15 in practice.

[0127] Specifically, this invention achieves targeted and efficient compensatory spraying by precisely locating abnormal phases of flow rate changes during drone spraying and combining this with the actual adhesion effect of pesticide droplets on crops within sub-planting areas. It pinpoints the flow rate change phase, quickly identifies sub-planting areas requiring special attention, and avoids indiscriminate inspection of the entire planting area, thus improving problem-solving efficiency. Furthermore, it analyzes the pesticide adhesion effect in these key sub-planting areas. The droplet accumulation profile at crop edges reflects whether droplets are excessively accumulated; excessive local spraying could lead to pesticide waste or crop damage. The area of ​​unattached areas quantifies the size of the unpowder-covered areas on the crop surface. Excessive unattached areas indicate insufficient spraying, facilitating subsequent determination of whether compensatory spraying is needed in sub-planting areas. Based on this, this invention, through the logic of "abnormal location - effect verification - on-demand supplementary spraying," ensures the quality of drone spraying while avoiding the waste of pesticides, time, and energy caused by blind supplementary spraying. This improves the accuracy and effectiveness of spraying operations and reduces resource waste.

[0128] Specifically, it also includes issuing a compensation prompt signal if any sub-planting area requires compensation spraying.

[0129] If the intelligent operation management method for unmanned aerial vehicles of the present invention is implemented in the form of 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, 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. The computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0130] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for intelligent operation management of unmanned aerial vehicles (UAVs), characterized in that, include: Crop growth data from crop planting areas and execution data from drone spraying operations are collected to extract the growth distribution characteristics of crops in each sub-planting area. The growth distribution characteristics include canopy void area and canopy overlap area. Based on the growth distribution characteristics and crop compaction, the distribution shading characterization parameters of the sub-planting areas are calculated, and growth status labels are set for each sub-planting area. Based on the growth status labels, determine the spraying plan for the corresponding sub-planting areas; The system obtains the wind speed variation range and maximum wind speed of the crop planting area within a predetermined time, determines whether it meets the flight environment benchmark, and controls the drone to carry out spraying operations on the sub-planting area according to the spraying plan. The drone's flight trajectory is used to determine the maximum height difference of crop growth in the sub-planting areas along the flight trajectory and the spray coverage rate to evaluate the spraying quality characterization value of the drone, so as to determine whether the spraying of the sub-planting areas meets the standards. Construct a time-domain variation curve of spray flow rate, determine the stage of flow rate change, call up the image of crops in the sub-planting area of ​​the flow rate change stage, identify the spray adhesion characteristics of the crops, and determine whether the sub-planting area needs to be compensated with spraying. The spray adhesion characteristics include the average droplet accumulation profile ratio at the crop edge and the average area of ​​the unattached sprayed area.

2. The intelligent operation management method for unmanned aerial vehicles according to claim 1, characterized in that, The process of calculating the distribution shading characterization parameters of the sub-planting area includes: The sum of the ratio of the canopy void area to the canopy void area threshold and the ratio of the canopy overlap area to the canopy overlap area threshold is used as the first distribution occlusion feature. The ratio of crop compactness to crop compactness threshold is used as the second distribution occlusion feature; The weighted sum of the first distribution occlusion feature and the second distribution occlusion feature is used to determine the distribution occlusion characterization parameter.

3. The intelligent operation management method for unmanned aerial vehicles according to claim 2, characterized in that, The process of setting growth status tags for each of the aforementioned sub-planting areas includes: The correspondence between growth status labels and predetermined distribution occlusion characterization parameter ranges is pre-defined; Determine the distribution occlusion characterization parameter interval to which the corresponding sub-planting area belongs in order to determine the corresponding growth status label; Among them, the growth status label corresponds one-to-one with the distribution occlusion characterization parameter range.

4. The intelligent operation management method for unmanned aerial vehicles according to claim 1, characterized in that, Based on the growth status labels, determine the spraying plan for the corresponding sub-planting areas, including: The spraying plan corresponds one-to-one with the growth status labels of the sub-planting areas; The spraying scheme is preset.

5. The intelligent operation management method for unmanned aerial vehicles according to claim 1, characterized in that, Determining whether flight environment standards are met includes: If the wind speed change in the crop planting area is less than the wind speed change threshold and the maximum wind speed is less than the maximum wind speed threshold within the predetermined time, then it is determined that the flight environment benchmark is met.

6. The intelligent operation management method for unmanned aerial vehicles according to claim 5, characterized in that, Controlling the drone to spray the sub-planting area according to the spraying plan includes: If the flight environment criteria are met, the drone is controlled to spray the sub-planting area according to the spraying plan.

7. The intelligent operation management method for unmanned aerial vehicles according to claim 1, characterized in that, The process of evaluating the spraying quality characterization values ​​of the drone includes: The ratio of the maximum height difference of crop growth in the sub-planting area to the threshold of the maximum height difference of crop growth is used as the first spraying quality characteristic; The ratio of the spray coverage threshold to the spray coverage rate is used as the second spray quality characteristic; The sum of the first spraying quality characteristic and the second spraying quality characteristic is taken as the spraying quality characterization value.

8. The intelligent operation management method for unmanned aerial vehicles according to claim 7, characterized in that, Determining whether the spraying of the sub-planting area meets the standards includes: If the spraying quality characterization value of the drone is less than the spraying quality characterization threshold, then the spraying of the sub-planting area is determined to meet the standard.

9. The intelligent operation management method for unmanned aerial vehicles according to claim 1, characterized in that, The process of determining the flow change phase includes: If there exists a time domain segment with a slope greater than or equal to a slope threshold, then the time domain segment is determined as the flow mutation stage.

10. The intelligent operation management method for unmanned aerial vehicles according to claim 1, characterized in that, Determining whether compensatory spraying is needed for the sub-planting area includes: If the average droplet accumulation profile ratio at the edge of the crop within any sub-planting area is greater than the droplet accumulation profile ratio threshold or / and the average area of ​​the non-attached sprayed area is greater than the non-attached sprayed area threshold, then it is determined that the sub-planting area needs to be compensated for.

Images