A plant protection operation management system based on data analysis

Abstract

The application relates to the field of plant protection operation management, in particular to a plant protection operation management system based on data analysis, which comprises a sub-region division unit used for uniformly partitioning or correlatively partitioning a target operation region in response to operation conditions; a UAV matching unit used for matching UAVs according to quantity ratio values; an operation optimization unit used for optimizing parameters of abnormal time points corresponding to each UAV according to wind speed abnormality degrees and route deviation coefficients; a scheduling unit used for determining a processing mode as a charging period according to an adjustment coefficient and a charging uniformity degree under a preset instability condition, or performing paired region scheduling or scheduling UAV optimization according to a scheduling region distribution coefficient and a reference quantity value; and a scheduling region setting unit used for setting a scheduling region according to a comparison reference value or an operation deviation degree in response to a setting condition. The application can improve the plant protection operation efficiency of the UAV.

Description

Technical Field

[0001] The present invention relates to the field of plant protection operation management, and in particular to a plant protection operation management system based on data analysis. Background Art

[0002] With the acceleration of agricultural modernization, drone-based crop protection technology has become a key tool for improving agricultural production efficiency and ensuring the healthy growth of crops. However, as the scale of drone-based crop protection operations expands and the application scenarios become increasingly complex, the issue of drone allocation has become increasingly prominent. Therefore, how to optimize the allocation and efficient scheduling of drone resources has become a pressing issue for those skilled in the art.

[0003] Chinese Patent Publication No. CN106125762A discloses an internet-based drone plant protection management system and method. The system includes a ground station system and a flight control system, as well as a cloud network data operation and control platform. The cloud network data operation and control platform includes a task allocation module for assigning tasks to each drone plant protection operation team based on the location information of the plant protection area; a route planning module for planning the drone's route within the plant protection area based on the terrain information of the plant protection area; and a flight monitoring module for real-time monitoring of the drone's flight trajectory and storing the drone's flight trajectory information and drone operation information. However, the above solution has the following problems: it is unable to perform refined dynamic scheduling and operation mode optimization of drones, and it is difficult to adapt to complex and changing operating environments, resulting in low operating efficiency. Summary of the Invention

[0004] To this end, the present invention provides a plant protection operation management system based on data analysis to overcome the problems in the prior art that drones cannot be dynamically scheduled and optimized for operation modes, and are difficult to adapt to complex and changing operating environments, resulting in low operating efficiency.

[0005] To achieve the above objectives, the present invention provides a plant protection operation management system based on data analysis, comprising:

[0006] A sub-area division unit is used to evenly partition or correlate the target operating area to obtain a number of sub-areas in response to operating conditions;

[0007] a drone matching unit, connected to the sub-area division unit, for matching drones based on the quantity comparison value;

[0008] An operation optimization unit, connected to the drone matching unit, is used to optimize parameters for each drone at the abnormal time point according to the wind speed anomaly and the route deviation coefficient, including adjusting the flight altitude or spraying amount according to the thermal influence coefficient and adjusting the axial debugging ratio according to the evaluation threshold;

[0009] a scheduling unit connected to the drone matching unit and configured to determine, under a preset instability condition, a processing method such as setting a charging cycle based on an adjustment coefficient and a charging consistency, or performing paired area scheduling or scheduling drone optimization based on a scheduling area distribution coefficient and a reference quantity value;

[0010] The scheduling area setting unit is connected to the operation optimization unit and the scheduling unit respectively, and is used to respond to the setting conditions to determine the scheduling area according to the comparison reference value or the operation deviation.

[0011] Furthermore, the sub-area division unit performs uniform partitioning or associated partitioning on the target operating area in response to the operating conditions, including:

[0012] The sub-area division unit evenly divides the target operation area in response to the operation conditions that the operation complexity is less than the preset operation complexity and the community structure change value is less than the preset community structure change value;

[0013] The sub-area division unit responds to the operation conditions that the operation complexity is greater than or equal to the preset operation complexity or the community structure change value is greater than or equal to the preset community structure change value, and associates the target operation area with the sub-area division unit. Furthermore, the drone matching unit performs drone matching based on the quantity comparison value, including:

[0014] If the quantity comparison value is greater than or equal to the standard comparison value, matching is performed based on the power reference value;

[0015] If the quantitative alignment value is less than the standard alignment value, matching is performed based on the proximity correlation coefficient.

[0016] Furthermore, the operation optimization unit performs parameter optimization for each UAV's corresponding abnormal time point according to the wind speed abnormality and the route deviation coefficient, including:

[0017] Parameter optimization is performed for each UAV’s corresponding abnormal time point, and for a single abnormal time point corresponding to a single UAV,

[0018] If the wind speed anomaly is greater than or equal to the preset wind speed anomaly and the route deviation coefficient is less than the preset route deviation coefficient, the flight altitude or spraying amount is adjusted according to the thermal influence coefficient;

[0019] If the wind speed anomaly is less than the preset wind speed anomaly or the route deviation coefficient is greater than or equal to the preset route deviation coefficient, the axial debugging ratio is adjusted according to the evaluation threshold.

[0020] Furthermore, the operation optimization unit adjusts the flight height or spraying amount according to the thermal influence coefficient, including:

[0021] If the thermal influence coefficient is greater than or equal to the preset thermal influence coefficient, the flight altitude is adjusted downward;

[0022] If the thermal influence coefficient is less than the preset thermal influence coefficient, the spraying amount is increased and adjusted.

[0023] Furthermore, the operation optimization unit increases and adjusts the axial debugging ratio according to the evaluation threshold;

[0024] The increase in the axial adjustment ratio is positively correlated with the evaluation threshold.

[0025] Furthermore, the scheduling unit determines a processing method according to the adjustment coefficient and the charging consistency, including:

[0026] If the adjustment coefficient is less than the preset adjustment coefficient and the charging constant is greater than or equal to the preset charging constant, the processing method is to set the charging cycle;

[0027] If the adjustment coefficient is greater than or equal to the preset adjustment coefficient or the charging consistency is less than the preset charging consistency, the processing method is to perform paired area scheduling or scheduling drone optimization based on the scheduling area distribution coefficient and the reference quantity value.

[0028] Furthermore, the scheduling unit performs pairing area scheduling when the pairing permission is greater than or equal to a preset pairing permission and the reference quantity value is equal to a preset reference quantity value.

[0029] Furthermore, the scheduling unit performs scheduling optimization of the drones when the pairing permission is less than a preset pairing permission or the reference quantity is less than a preset reference quantity.

[0030] Furthermore, the scheduling area setting unit responds to the setting conditions to determine the scheduling area according to the comparison reference value or the operation deviation, including:

[0031] The dispatch area setting unit responds to the setting condition that the sub-area fluctuation coefficient is greater than or equal to the preset sub-area fluctuation coefficient or the adjustment fluctuation value is greater than or equal to the preset adjustment fluctuation value, and determines the dispatch area according to the comparison reference value;

[0032] The scheduling area setting unit responds to the setting conditions that the sub-area fluctuation coefficient is less than the preset sub-area fluctuation coefficient and the adjustment fluctuation value is less than the preset adjustment fluctuation value, and determines the scheduling area according to the operation deviation degree.

[0033] Compared with the prior art, the beneficial effect of the present invention lies in that, in the technical solution of the present invention, the comprehensive characteristics of the target operation area are effectively reflected through the operation complexity and the community structure change value, and then different partitioning methods are adaptively selected according to the operation complexity and the community structure change value, so that the selection of the partitioning method is more in line with the actual application scenario. When the operation complexity and the community structure change value are small, uniform partitioning is fast and efficient. When the operation complexity and the community structure change value are large, the associated partitions can be finely managed. The diversified partitioning methods enable the drone operation system to cope with various complex operation scenarios and ensure the efficiency and stability of the operation.

[0034] Furthermore, when the present invention matches drones according to the quantity comparison value, the quantity comparison value is used to effectively reflect the sufficiency of the drones, and then the matching is adaptively performed according to the power reference value or the proximity correlation coefficient based on the quantity comparison value. When the number of drones is sufficient, matching is performed according to the power reference value, which can ensure that a large area has sufficient power to complete the operation, avoiding task interruption or repeated charging due to insufficient power, thereby improving overall operation efficiency. When the number of drones is insufficient, matching is performed according to the proximity correlation coefficient, which can reduce the moving distance of drones between different sub-areas, reduce energy consumption and time costs, and balance the difficulty of the operation at the same time, avoiding task delays due to excessive regional difficulty.

[0035] Furthermore, the present invention effectively reflects the wind speed anomaly and route deviation through the wind speed anomaly and route deviation coefficient, and then optimizes the parameters according to the wind speed anomaly and route deviation coefficient, and uses the thermal influence coefficient to adjust the flight altitude or spraying amount. The UAV can more accurately control the spraying range, reduce the drift and waste of the agent, and improve the spraying efficiency and quality. By adjusting the axial debugging ratio to optimize the performance of the PID controller, it helps to improve the response speed and stability of the UAV, so that it can adapt to environmental changes more quickly and maintain a stable flight state, thereby improving work efficiency.

[0036] Furthermore, the present invention effectively reflects the operating status and charging status of the drone through the adjustment coefficient and the charging consistency, and then adaptively selects different processing methods according to the adjustment coefficient and the charging consistency. When the adjustment coefficient is low and the charging consistency is high, setting the charging cycle can ensure that the drone is regularly replenished with power during the operation process, avoiding interruption of the mission due to insufficient power, helping to improve the continuity and stability of the operation, and ensuring that the mission can be completed on time. When the adjustment coefficient is high or the charging consistency is low, the scheduling unit performs paired area scheduling or scheduling drone optimization according to the scheduling area distribution coefficient and the reference quantity value, realizing flexible allocation of drone resources, and helping to improve operation efficiency.

[0037] Furthermore, the present invention uses pairing permission and reference quantity values ​​to effectively reflect the system's scheduling flexibility and resource utilization, and performs paired area scheduling, so that drones with sufficient power can support areas with insufficient power, achieving balanced resource utilization, reducing operation interruptions caused by insufficient power, and improving overall operation efficiency. Rescheduling drones that have completed their tasks or have completed charging can avoid idleness and waste of resources, ensure that all drones can play their full role, monitor the operating status and power status of drones in real time, and provide real-time feedback and adjustments based on actual conditions, thereby improving operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a unit connection diagram of the plant protection operation management system based on data analysis of the present invention;

[0039] Figure 2 This is a flow chart of evenly partitioning or correlatively partitioning a target operating area according to operating conditions according to the present invention;

[0040] Figure 3 This is a flow chart of the present invention for optimizing parameters for abnormal time points corresponding to each UAV based on wind speed anomaly and route deviation coefficient;

[0041] Figure 4 This is a flow chart of the present invention for determining a processing method based on an adjustment coefficient and a charging degree. DETAILED DESCRIPTION

[0042] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0043] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0044] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0045] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0046] See also Figures 1 to 4 As shown, the present invention provides a plant protection operation management system based on data analysis, comprising:

[0047] A sub-area division unit is used to evenly partition or correlate the target operating area to obtain a number of sub-areas in response to operating conditions;

[0048] a drone matching unit, connected to the sub-area division unit, for matching drones based on the quantity comparison value;

[0049] An operation optimization unit, connected to the drone matching unit, is used to optimize parameters for each drone at the abnormal time point according to the wind speed anomaly and the route deviation coefficient, including adjusting the flight altitude or spraying amount according to the thermal influence coefficient and adjusting the axial debugging ratio according to the evaluation threshold;

[0050] a scheduling unit connected to the drone matching unit and configured to determine, under a preset instability condition, a processing method such as setting a charging cycle based on an adjustment coefficient and a charging consistency, or performing paired area scheduling or scheduling drone optimization based on a scheduling area distribution coefficient and a reference quantity value;

[0051] The scheduling area setting unit is connected to the operation optimization unit and the scheduling unit respectively, and is used to respond to the setting conditions to determine the scheduling area according to the comparison reference value or the operation deviation.

[0052] Among them, the application scenario of the present invention is the scheduling and optimization of drones in plant protection operations. In the present invention, several historical records are correspondingly set up, and any historical record records the number of community areas, time fluctuation value, operation complexity, community structure change value, wind speed anomaly, route deviation coefficient and thermal influence coefficient in the historical process of scheduling and optimization of drones in at least one plant protection operation, and each historical record corresponds to a qualified mark, which records whether the scheduling and optimization process of drones in plant protection operations meets user needs. The qualified mark can be recorded manually. It can be understood that the user can determine whether the scheduling and optimization process of drones in plant protection operations meets the needs based on self-set indicators. The self-set indicators can be but not limited to operation time, which will not be elaborated here. Among them, the operation time is the total time from the start of spraying operation to the completion of spraying operation of the drone in the target operation area;

[0053] The present invention provides a target coefficient and a related threshold value. The corresponding relationship between the target coefficient and the related threshold value is expressed by a weight formula, which is: target coefficient = weight coefficient × related threshold value. Specifically, the present invention records the reduction in flight altitude, the increase in spray volume, the increase in axial adjustment ratio, and the duration of a single charging cycle as different target coefficients, and records the thermal influence coefficient, the evaluation threshold, and the instability reference value as related threshold values. It can be understood that each target coefficient has a corresponding related threshold value. For example, the reduction in flight altitude has a positive correlation with the thermal influence coefficient, and the positive correlation between the reduction in flight altitude and the thermal influence coefficient is expressed by the weight formula. The value of the weight coefficient can be determined based on the user's historical experience according to the degree of influence of the thermal influence coefficient on the reduction in flight altitude. The value of the weight coefficient can also be optimized by a multi-layer perceptron based on the historical records of drone scheduling and optimization in multiple plant protection operations. The use of a multi-layer perceptron to optimize the value of the weight coefficient is well understood by those skilled in the art and will not be described in detail. The principles for determining the values ​​of the weight coefficients corresponding to other target coefficients and related threshold values ​​are the same and will not be described in detail here.

[0054] The present invention is also provided with an information collection unit and a number of drones;

[0055] an information collection unit connected to the sub-area division unit and used for collecting plant protection information;

[0056] a plurality of drones, each of which is connected to the drone matching unit, the operation optimization unit, and the scheduling unit, for spraying the drug, wherein each drone is provided with a communication module for real-time communication, a temperature collection module for collecting temperature, and a wind speed collection module for collecting wind speed;

[0057] The communication module uses wireless communication technology to communicate in real time with the drone matching unit, the operation optimization unit and the scheduling unit to spray the medicine. The wireless communication technology includes but is not limited to Wi-Fi, Bluetooth and ZigBee. Users can choose according to actual needs. The details are not described here. The temperature acquisition module and the wind speed acquisition module use temperature sensors and wind speed sensors to collect temperature and wind speed respectively.

[0058] Plant protection information includes but is not limited to DEM data corresponding to the target operation area, the sowing time of each crop in the target operation area, and the area of ​​the target operation area;

[0059] The preset instability condition is that the reference time period ends and the estimated processing coefficient at the reference time point is greater than the preset estimated processing coefficient. The estimated processing coefficient = adjustment coefficient / preset adjustment coefficient + instability reference value / average value of instability reference values ​​corresponding to historical records that can meet user needs; the instability reference value is the absolute value of the difference between the maximum and minimum values ​​of the sub-region reference values ​​corresponding to each sub-region;

[0060] The reference time period is the time from the earliest moment the drone starts working to the time when the cumulative time reaches 30 minutes.

[0061] The reference time point is the earliest time when the drone starts working, and the timing starts until the cumulative time reaches 30 minutes; the target operation area is the area where plant protection operations need to be carried out.

[0062] Specifically, the sub-area division unit performs uniform partitioning or associated partitioning on the target operating area in response to the operating conditions, including:

[0063] The sub-area division unit evenly divides the target operation area in response to the operation conditions that the operation complexity is less than the preset operation complexity and the community structure change value is less than the preset community structure change value;

[0064] The sub-area division unit performs associated partitioning on the target operation area in response to an operation condition in which the operation complexity is greater than or equal to a preset operation complexity or the community structure change value is greater than or equal to a preset community structure change value.

[0065] Among them, operation complexity = operation area / preset operation area + terrain change / preset terrain change,

[0066] The operating area is the area of ​​the target operating area, and the terrain variation is the standard deviation of the elevation reference value corresponding to each pixel in the DEM data corresponding to the target operating area;

[0067] Obtain the DEM data corresponding to the target operation area and load the DEM data into the GIS software to obtain the elevation reference value corresponding to each pixel in the DEM data. The elevation reference value corresponding to a single pixel is the elevation of the center point of the square area corresponding to the pixel. It can be understood that the DEM data is measured by a satellite sensor. The satellite sensor can be SRTM or ASTER, and there is no specific limitation. The DEM data includes several pixels, each of which represents a 1m×1m square area on the ground.

[0068] Community structure change value = number of community areas / preset number of community areas + time fluctuation value / preset time fluctuation value;

[0069] A single community area contains several crops, and the sowing time length of each crop is the same. The sowing time lengths of any two adjacent community areas are different. The sowing time length of a single crop is the cumulative number of days from the sowing of the crop to the current time. The sowing time length of a single community area is the same as the sowing time length of the crops planted in the community area.

[0070] The number of community areas is the total number of community areas contained in the target operation area, and the time fluctuation value is the standard deviation of the sowing time length corresponding to each community area in the target operation area;

[0071] The values ​​of the preset number of community areas and the preset time fluctuation value can be determined by the user according to the actual application scenario. The greater the user's demand for improving the sensitivity of the community structure change value judgment, the smaller the values ​​of the preset number of community areas and the preset time fluctuation value will be. The average value of the number of community areas and the average value of the time fluctuation value corresponding to the historical records that can meet the user's needs are detected and recorded as the preset number of community areas and the preset time fluctuation value respectively.

[0072] The values ​​of the preset operation complexity and the preset community structure change value can be determined by the user according to the actual application scenario. The larger the values ​​of the preset operation complexity and the preset community structure change value are, the greater the user's demand for uniform partitioning. A method for determining the values ​​of the preset operation complexity and the preset community structure change value is provided. The historical records of the user uniformly partitioning the target operation area are detected, and the average values ​​of the operation complexity and the average values ​​of the community structure change values ​​corresponding to the historical records that can meet the user's needs are recorded as the preset operation complexity and the preset community structure change value respectively;

[0073] The values ​​of the preset working area and the preset terrain variability can be determined by the user according to the actual application scenario. The greater the user's demand for improving the sensitivity of the determination of the complexity of the work, the smaller the values ​​of the preset working area and the preset terrain variability will be. Provided are values ​​of the preset working area and the preset terrain variability, and the average values ​​of the working area and the average values ​​of the terrain variability in the historical records that can meet the user's needs are recorded as the average values ​​of the working area and the average values ​​of the terrain variability, respectively.

[0074] In the uniform partitioning of the target operation area, the target operation area is divided into several sub-areas of equal area and the same shape. The shape of each sub-area is rectangular, and the number of sub-areas is the same as the number of drones.

[0075] For the target operation area association partition, for a single sub-area, the sub-area is recorded as the target sub-area. The target sub-area contains several cluster areas. The correlation coefficients corresponding to any two cluster areas in the target sub-area are greater than or equal to the preset correlation coefficient. The cluster areas adjacent to the target sub-area are recorded as adjacent cluster areas. The correlation coefficients of any adjacent cluster area with any cluster area in the target sub-area are less than the preset correlation coefficient.

[0076] The correlation coefficient between any two community areas = 1-(the absolute value of the difference between the regional reference values ​​of the two community areas / the larger value of the regional reference values ​​of the two community areas);

[0077] The value of the preset correlation coefficient can be determined by the user according to the actual application scenario. The greater the user's demand for improving work efficiency, the larger the value of the preset correlation coefficient. A value of the preset correlation coefficient is provided, and the preset correlation coefficient is 70%.

[0078] Specifically, the drone matching unit performs drone matching based on the quantity comparison value, including:

[0079] If the quantity comparison value is greater than or equal to the standard comparison value, matching is performed based on the power reference value;

[0080] If the quantitative alignment value is less than the standard alignment value, matching is performed based on the proximity correlation coefficient.

[0081] Among them, the quantity comparison value = the number of drones - the number of sub-areas, and the standard comparison value is 0.

[0082] The reference value of power for a single drone = the remaining power of the drone before it starts working / the power of the drone when it is fully charged;

[0083] When matching based on the power reference value, the matching priority coefficient corresponding to each sub-area is determined based on the area characteristic value. When matching a single sub-area, the sub-area is recorded as the target sub-area, and drones that do not match a corresponding sub-area are recorded as unmatched drones. The drone with the largest power reference value is selected as the operating drone in the target sub-area, and matching continues for sub-areas without operating drones until the preset conditions are met.

[0084] If the preset condition is that there are operating drones in each sub-area and the number of unmatched drones is 0, then the matching is stopped;

[0085] If the preset condition is that there are operating drones in each sub-area and the number of unmatched drones is greater than 0, then secondary matching is performed for each unmatched drone. When secondary matching is performed for a single unmatched drone, the unmatched drone is used as the working sub-area of ​​the secondary matching sub-area with the largest area eigenvalue, and secondary matching is continued for the unmatched drones until each drone has a matching sub-area.

[0086] The sub-region with the least number of working drones is recorded as the secondary matching sub-region;

[0087] It can be understood that when matching based on the power reference value, the number of working drones corresponding to a single sub-area is greater than or equal to 1;

[0088] The matching priority coefficient corresponding to a single sub-region is positively correlated with the area characteristic value corresponding to the sub-region;

[0089] The larger the matching priority coefficient corresponding to a single sub-region, the higher the priority of drone matching for that sub-region;

[0090] The area characteristic value corresponding to a single sub-region = the area of ​​the sub-region / the area of ​​the target operation area;

[0091] When matching based on the proximity correlation coefficient, the matching priority coefficient corresponding to each sub-region is determined based on the area characteristic value. When matching a single sub-region, the sub-region is recorded as the target sub-region, and the drones that are not matched with the corresponding sub-region are recorded as unmatched drones. The drone with the largest power reference value is selected as the operating drone in the target sub-region, and matching is continued for sub-regions without operating drones until all drones are matched with corresponding sub-regions. Then, matching analysis is performed for each second sub-region. When matching analysis is performed for a single second sub-region, the operating drone in the first sub-region with the largest proximity correlation coefficient with the second sub-region is selected as the operating drone in the second sub-region, and matching analysis is continued for the second sub-regions without working drones until there are operating drones in each second sub-region.

[0092] The sub-region that is not matched with a drone is recorded as the second sub-region, and the sub-region that is matched with a drone is recorded as the first sub-region.

[0093] The proximity correlation coefficient between any first sub-region and any second sub-region = the task difficulty value corresponding to the first sub-region × (the shortest distance from the first sub-region to the second sub-region / the average of the shortest distances from the second sub-region to each first sub-region);

[0094] The operation difficulty value corresponding to a single first sub-area = the area characteristic value corresponding to the first sub-area / the power reference value of the drone corresponding to the first sub-area;

[0095] When matching based on the proximity correlation coefficient, the number of sub-areas corresponding to a single drone is greater than or equal to 1. If the number of sub-areas corresponding to a drone is greater than 1, operations are performed on each sub-area in descending order of area characteristic values.

[0096] It can be understood that the quantity comparison value effectively reflects the comparison between the number of drones and the number of sub-areas. When the value is greater than or equal to the standard comparison value, it indicates that the number of drones is relatively large or equal to the number of sub-areas. At this time, more attention is paid to the operating endurance of the drones, so the power reference value is used as the matching basis; when the quantity comparison value is less than the standard comparison value, it means that the number of drones is relatively small and the operating pressure is greater. At this time, it is more necessary to consider the operating efficiency and operation continuity, so matching is performed based on the proximity correlation coefficient, and the drones are allowed to operate in their adjacent areas as much as possible to reduce flight energy consumption and time costs.

[0097] Specifically, the operation optimization unit performs parameter optimization for each UAV's corresponding abnormal time point according to the wind speed abnormality and the route deviation coefficient, including:

[0098] Parameter optimization is performed for each UAV’s corresponding abnormal time point, and for a single abnormal time point corresponding to a single UAV,

[0099] If the wind speed anomaly is greater than or equal to the preset wind speed anomaly and the route deviation coefficient is less than the preset route deviation coefficient, the flight altitude or spraying amount is adjusted according to the thermal influence coefficient;

[0100] If the wind speed anomaly is less than the preset wind speed anomaly or the route deviation coefficient is greater than or equal to the preset route deviation coefficient, the axial debugging ratio is adjusted according to the evaluation threshold.

[0101] For a single UAV, the starting point is the moment when the UAV starts working, and an interval point is set every 5 minutes until the UAV finishes working. The starting point and each interval point are recorded as the time point;

[0102] It is understandable that each drone corresponds to a number of time points;

[0103] For a single time point, if the evaluation threshold corresponding to the time point is greater than the preset evaluation threshold, the time point is recorded as an abnormal time point;

[0104] The evaluation threshold corresponding to a single time point = wind speed anomaly / preset wind speed anomaly + route deviation coefficient / preset route deviation coefficient;

[0105] The wind speed anomaly corresponding to a single time point is the maximum wind speed detected by the drone at that time point.

[0106] The route deviation coefficient corresponding to a single time point is the shortest distance between the UAV and the initial route at that time point;

[0107] The initial route is the drone route of a single sub-area determined by the A-star algorithm.

[0108] When determining a drone route for a single sub-area using the A-star algorithm, the input parameters are the drone's starting point, destination point, and flight altitude within that sub-area. The A-star algorithm performs a path search and generates the optimal path from the starting point to the destination point. This is well understood by those skilled in the art and will not be described in detail here. The flight altitude is 10 meters, and the starting and destination points can be set by the user based on actual needs, with no specific restrictions.

[0109] The values ​​of the preset wind speed anomaly and the preset route deviation coefficient can be determined by the user according to the actual application scenario. The smaller the value of the preset wind speed anomaly and the larger the value of the preset route deviation coefficient, the greater the user's need to adjust the flight altitude or spraying amount according to the thermal influence coefficient. A method for determining the values ​​of the preset wind speed anomaly and the preset route deviation coefficient is provided. The historical records of the user adjusting the flight altitude or spraying amount according to the thermal influence coefficient are detected, and the average values ​​of the wind speed anomaly and the average value of the route deviation coefficient corresponding to the historical records that can meet the user's needs are recorded as the preset wind speed anomaly and the preset route deviation coefficient, respectively.

[0110] The value of the preset evaluation threshold can be determined by the user based on the actual application scenario. The greater the user's demand for improving the efficiency of plant protection operations, the smaller the value of the preset evaluation threshold. A method for determining the value of the preset evaluation threshold is provided, and the average value of the evaluation threshold corresponding to each abnormal time point in the historical records that can meet the user's needs is recorded as the preset evaluation threshold.

[0111] Specifically, the operation optimization unit adjusts the flight height or spraying amount according to the thermal influence coefficient, including:

[0112] If the thermal influence coefficient is greater than or equal to the preset thermal influence coefficient, the flight altitude is adjusted downward;

[0113] If the thermal influence coefficient is less than the preset thermal influence coefficient, the spraying amount is increased and adjusted.

[0114] For a single time point, this time point is recorded as the target time point. The thermal influence coefficient corresponding to the target time point = the temperature detected by the drone at the target time point - the maximum value of the temperatures detected by the drone at each time point before the target time point. It should be noted that if there is no time point before the target time point, the thermal influence coefficient corresponding to the target time point = the temperature detected by the drone at the target time point - the average temperature detected by each drone at each time point in the historical records that can meet the user's requirements;

[0115] The value of the preset thermal influence coefficient can be determined by the user according to the actual application scenario. The larger the value of the preset thermal influence coefficient, the greater the user's need to increase the spraying amount. A preset thermal influence coefficient value is provided, and the historical records of the user's increase in the spraying amount are detected. The average value of the thermal influence coefficients corresponding to the historical records that can meet the user's needs is recorded as the preset thermal influence coefficient;

[0116] The flight altitude is the height of the drone from the ground; the spraying volume is the volume of the agent sprayed by the drone per unit time; the initial flight altitude, spraying volume, and axial adjustment ratio can be set by the user according to actual needs, and there are no specific restrictions;

[0117] When adjusting the flight altitude, the reduction value of the flight altitude is positively correlated with the thermal influence coefficient;

[0118] When the spraying amount is increased and adjusted, the increase value of the spraying amount is positively correlated with the evaluation threshold corresponding to the target time point.

[0119] Specifically, the operation optimization unit increases and adjusts the axial debugging ratio according to the evaluation threshold;

[0120] The increase in the axial adjustment ratio is positively correlated with the evaluation threshold.

[0121] Among them, the axial debugging ratio = kp / ki, kp is the proportional gain coefficient in the UAV's PID controller, ki is the integral gain coefficient in the UAV's PID controller, and the axial debugging ratio is used to adjust the balance between the system's response speed and stability. It can optimize the system's control performance so that it can respond to errors quickly while maintaining stability.

[0122] It is understandable that when wind speed has a greater impact on operations and route deviation has a smaller impact, the flight altitude or spraying volume is adjusted according to the thermal influence coefficient to reduce the interference of wind speed on operation quality; conversely, if the wind speed anomaly is low or the route deviation coefficient is large, it indicates that route deviation is the main problem. At this time, the axial debugging ratio is adjusted according to the evaluation threshold to enable the UAV to fly more accurately along the predetermined route, thereby improving operation accuracy and consistency. The core is to adjust the UAV parameters in a targeted manner according to different operation abnormal conditions to ensure operation quality.

[0123] Specifically, the scheduling unit determines a processing method according to the adjustment coefficient and the charging consistency, including:

[0124] If the adjustment coefficient is less than the preset adjustment coefficient and the charging constant is greater than or equal to the preset charging constant, the processing method is to set the charging cycle;

[0125] If the adjustment coefficient is greater than or equal to the preset adjustment coefficient or the charging consistency is less than the preset charging consistency, the processing method is to perform paired area scheduling or scheduling drone optimization based on the scheduling area distribution coefficient and the reference quantity value.

[0126] Wherein, the adjustment coefficient = the number of drones with abnormal time points in the reference time period / the total number of drones;

[0127] Charging uniformity = 1 / (standard deviation of the reference power values ​​of each drone in the dispatch area + 1);

[0128] The values ​​of the preset adjustment coefficient and the preset charging consistency can be determined by the user according to the actual application scenario. The larger the value of the preset adjustment coefficient and the smaller the value of the preset charging consistency, the greater the user's demand for setting a charging cycle. The values ​​of the preset adjustment coefficient and the preset charging consistency are provided, and the historical records of the charging cycles set by the user are detected. The average values ​​of the adjustment coefficient and the average value of the charging consistency corresponding to the historical records that can meet the user's needs are recorded as the preset adjustment coefficient and the preset charging consistency, respectively.

[0129] Setting a charging cycle includes: setting a cyclic charging cycle after the end of a reference time period, the duration of a single charging cycle is negatively correlated with the instability reference value, and at the end of a single charging cycle, selecting a preset number of drones for charging, and at the end of the charging cycle, selecting drones in order from small to large according to the power of the drones at that moment until the preset number is reached. The value of the preset number can be determined by the user according to the actual application scenario, and a preset number value is provided, which is 5% of the total number of drones.

[0130] Understandably, if the number of drones operating at unusual times within the reference time period is small and the differences in the power reference values ​​of each drone in the dispatch area are small, overall drone operation stability is good and power distribution is relatively uniform. By setting a cyclic charging cycle, drones can maintain stable power support during subsequent operations, maintaining operational continuity and efficiency. If the adjustment coefficient is greater than or equal to the preset adjustment coefficient or the charge consistency is less than the preset charge consistency, this indicates operational instability. Under these conditions, there may be a large number of unusual drones or uneven power distribution, necessitating optimization of the matching between drones and dispatch areas. When the pairing tolerance is greater than or equal to the preset pairing tolerance and the reference quantity is equal to the preset reference quantity, paired area scheduling is performed to improve operational coordination and efficiency. If the pairing tolerance is less than the preset value or the reference quantity is less than the preset value, drone scheduling is optimized, reallocating drones to dispatch areas with greater support to ensure overall operational efficiency. These optimization measures aim to better adapt to changing operating conditions, rationally allocate drone resources, and improve operational stability and efficiency.

[0131] Specifically, the scheduling unit performs pairing area scheduling when the pairing permission is greater than or equal to a preset pairing permission and the reference quantity value is equal to a preset reference quantity value.

[0132] The pairing tolerance = |the average value of the representative coefficients corresponding to each matching area - the preset representative coefficient|. The historical records of matching area scheduling are examined, and the average value of the representative coefficients corresponding to each matching area in the historical records that meet the user's needs is recorded as the preset representative coefficient.

[0133] Reference quantity value = number of multi-UAV dispatch areas / total number of dispatch areas. A multi-UAV dispatch area is a dispatch area where the number of working UAVs is greater than 1. The preset reference quantity value is 1.

[0134] The value of the preset pairing tolerance can be determined by the user based on the actual application scenario. The larger the value of the preset pairing tolerance, the greater the user's demand for pairing area scheduling. A value of the preset pairing tolerance is provided, and the historical records of the user's pairing area scheduling are detected. The average value of the pairing tolerance corresponding to the historical records that can meet the user's needs is recorded as the preset pairing tolerance;

[0135] Paired area scheduling includes: after the end of the reference time period, pairing the scheduling areas in descending order of representative coefficients; when pairing a single scheduling area, recording the scheduling area as the target scheduling area; recording the scheduling area that is not recorded in the pairing combination and has the smallest representative coefficient into a pairing combination with the target scheduling area; and continuing to pair the scheduling areas that are not recorded in the pairing combination until a preset reference condition is met;

[0136] The preset reference condition is that there is no dispatch area that is not recorded in the pairing combination or there is only one dispatch area that is not recorded in the pairing combination. If there is only one, then the dispatch area is recorded in the pairing combination with the smallest combined pairing reference value and recorded as the reference paired combination; the combined pairing reference value is the average value of the representative coefficients corresponding to each dispatch area in a single paired combination;

[0137] The representative coefficient corresponding to a single scheduling area = comparison reference value + operation deviation;

[0138] For a single pairing combination, the exchange duration is determined based on the combined pairing reference value, and at the exchange time, the drone with the largest battery in the dispatch area with the largest representative coefficient is exchanged with the drone with the smallest battery in the dispatch area with the smallest representative coefficient;

[0139] For the reference scheduling combination, at the exchange time point, the drone with the largest battery in the scheduling area with the largest representative coefficient is exchanged with the drone with the smallest battery in the scheduling area with the smallest representative coefficient, and the drone with the largest battery in the intermediate scheduling area is exchanged with the drone with the largest battery in the scheduling area with the smallest representative coefficient.

[0140] The middle scheduling area is the scheduling area in the middle after sorting the scheduling areas in the reference scheduling combination from large to small according to the representative coefficient;

[0141] The exchange time corresponding to a single pairing combination is the time interval between the reference time point and the exchange time point corresponding to the pairing combination; the exchange time point is the moment when the single pairing combination exchanges drones.

[0142] Specifically, the scheduling unit performs scheduling optimization of the drones when the pairing allowance is less than a preset pairing allowance or the reference quantity value is less than a preset reference quantity value.

[0143] In the optimization of dispatching drones, after the reference time period ends, for a single drone, the drone is recorded as the target drone. If the target drone is fully charged within the target monitoring period after working until the battery is exhausted, and there are other working drones in the sub-area where the target drone is working, the target drone is recorded as the first drone; the drone that has completed its operation in the dispatching area is recorded as the second drone, and both the first drone and the second drone are recorded as dispatching drones.

[0144] For a single dispatched drone, the dispatched drone is assigned to the dispatch area with the smallest representative coefficient.

[0145] Specifically, the scheduling area setting unit responds to the setting conditions to determine the scheduling area according to the comparison reference value or the operation deviation, including:

[0146] The dispatch area setting unit responds to the setting condition that the sub-area fluctuation coefficient is greater than or equal to the preset sub-area fluctuation coefficient or the adjustment fluctuation value is greater than or equal to the preset adjustment fluctuation value, and determines the dispatch area according to the comparison reference value;

[0147] The scheduling area setting unit responds to the setting conditions that the sub-area fluctuation coefficient is less than the preset sub-area fluctuation coefficient and the adjustment fluctuation value is less than the preset adjustment fluctuation value, and determines the scheduling area according to the operation deviation degree.

[0148] Wherein, the sub-area reference value = the sum of the power reference values ​​corresponding to each drone operating in the sub-area / [(the area of ​​all sub-areas where drones operating in the sub-area have operated before the sub-area + the area of ​​the sub-area) / the area of ​​the target operation area];

[0149] The sub-region fluctuation coefficient is the standard deviation of the sub-region reference value corresponding to each sub-region;

[0150] The adjustment fluctuation value is the standard deviation of the adjustment reference value corresponding to each sub-area. The adjustment reference value corresponding to a single sub-area is the average number of abnormal time points that exist in the reference time period when each working drone in the sub-area is working in the sub-area.

[0151] The values ​​of the preset sub-region fluctuation coefficient and the preset adjustment fluctuation value can be determined by the user according to the actual application scenario. The smaller the values ​​of the preset sub-region fluctuation coefficient and the preset adjustment fluctuation value, the greater the user's demand for determining the scheduling area based on the comparison reference value. Provided are values ​​of the preset sub-region fluctuation coefficient and the preset adjustment fluctuation value, detect the historical records of the user determining the scheduling area based on the comparison reference value, and record the average values ​​of the sub-region fluctuation coefficient and the average value of the adjustment fluctuation value corresponding to the historical records that can meet the user's needs as the preset sub-region fluctuation coefficient and the preset adjustment fluctuation value, respectively;

[0152] When determining the dispatch area according to the comparison reference value, the sub-area whose comparison reference value is greater than the preset comparison reference value is used as the dispatch area;

[0153] The comparison reference value corresponding to a single subregion = |the regional coefficient corresponding to the subregion - the average of the regional coefficients corresponding to all subregions|; the regional coefficient corresponding to a single subregion = the adjustment reference value corresponding to the subregion / the average of the adjustment reference values ​​corresponding to all subregions - the subregion reference value corresponding to the subregion / the average of the subregion reference values ​​corresponding to all subregions;

[0154] When determining the scheduling area based on the operation deviation, the sub-area with an operation deviation greater than the preset operation deviation is used as the scheduling area;

[0155] The operation deviation corresponding to a single sub-area = |the comparison reference value corresponding to the sub-area - the average comparison reference value corresponding to the historical records that can meet user needs|;

[0156] The values ​​of the preset comparison reference value and the preset operation deviation degree can be determined by the user according to the actual application scenario. The greater the user's demand for improving operation efficiency, the smaller the values ​​of the preset comparison reference value and the preset operation deviation degree. A preset comparison reference value and a preset operation deviation degree are provided, and the average value of the comparison reference value and the average value of the operation deviation degree corresponding to each scheduling area in the historical records that can meet the user's needs are detected, and they are recorded as the preset comparison reference value and the preset operation deviation degree respectively.

[0157] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0158] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A plant protection operation management system based on data analysis, characterized in that: include: A sub-area division unit is used to evenly partition or correlate the target operating area to obtain a number of sub-areas in response to operating conditions; a drone matching unit, connected to the sub-area division unit, for matching drones based on the quantity comparison value; An operation optimization unit, connected to the drone matching unit, is used to optimize parameters for each drone at the abnormal time point according to the wind speed anomaly and the route deviation coefficient, including adjusting the flight altitude or spraying amount according to the thermal influence coefficient and adjusting the axial debugging ratio according to the evaluation threshold; a scheduling unit connected to the drone matching unit and configured to determine, under a preset instability condition, a processing method such as setting a charging cycle based on an adjustment coefficient and a charging consistency, or performing paired area scheduling or scheduling drone optimization based on a scheduling area distribution coefficient and a reference quantity value; a scheduling area setting unit, connected to the operation optimization unit and the scheduling unit respectively, for responding to setting conditions to determine a scheduling area according to a comparison reference value or an operation deviation degree; The operation optimization unit optimizes parameters for each UAV's corresponding abnormal time point according to the wind speed abnormality and the route deviation coefficient, including: Parameter optimization is performed for each UAV’s corresponding abnormal time point, and for a single abnormal time point corresponding to a single UAV, If the wind speed anomaly is greater than or equal to the preset wind speed anomaly and the route deviation coefficient is less than the preset route deviation coefficient, the flight altitude or spraying amount is adjusted according to the thermal influence coefficient; If the wind speed anomaly is less than the preset wind speed anomaly or the route deviation coefficient is greater than or equal to the preset route deviation coefficient, the axial debugging ratio is adjusted according to the evaluation threshold; The operation optimization unit adjusts the flight height or spraying amount according to the thermal influence coefficient, including: If the thermal influence coefficient is greater than or equal to the preset thermal influence coefficient, the flight altitude is adjusted downward; If the thermal influence coefficient is less than the preset thermal influence coefficient, the spraying amount is increased and adjusted; The operation optimization unit increases and adjusts the axial debugging ratio according to the evaluation threshold; The increase in the axial adjustment ratio is positively correlated with the evaluation threshold.

2. The plant protection operation management system based on data analysis according to claim 1, characterized in that: The sub-area division unit performs uniform or associated partitioning on the target operating area in response to the operating conditions, including: The sub-area division unit evenly divides the target operation area in response to the operation conditions that the operation complexity is less than the preset operation complexity and the community structure change value is less than the preset community structure change value; The sub-area division unit performs associated partitioning on the target operation area in response to an operation condition in which the operation complexity is greater than or equal to a preset operation complexity or the community structure change value is greater than or equal to a preset community structure change value.

3. The plant protection operation management system based on data analysis according to claim 2, characterized in that: The drone matching unit performs drone matching according to the quantity comparison value, including: If the quantity comparison value is greater than or equal to the standard comparison value, matching is performed based on the power reference value; If the quantitative alignment value is less than the standard alignment value, matching is performed based on the proximity correlation coefficient.

4. The plant protection operation management system based on data analysis according to claim 1, characterized in that: The scheduling unit determines a processing method according to the adjustment coefficient and the charging consistency, including: If the adjustment coefficient is less than the preset adjustment coefficient and the charging constant is greater than or equal to the preset charging constant, the processing method is to set the charging cycle; If the adjustment coefficient is greater than or equal to the preset adjustment coefficient or the charging consistency is less than the preset charging consistency, the processing method is to perform paired area scheduling or scheduling drone optimization based on the scheduling area distribution coefficient and the reference quantity value.

5. The plant protection operation management system based on data analysis according to claim 4, characterized in that: The scheduling unit performs pairing area scheduling when the pairing permission is greater than or equal to a preset pairing permission and the reference quantity value is equal to a preset reference quantity value.

6. The plant protection operation management system based on data analysis according to claim 5, characterized in that: The scheduling unit performs scheduling drone optimization when the pairing allowance is less than a preset pairing allowance or the reference quantity value is less than a preset reference quantity value.

7. The plant protection operation management system based on data analysis according to claim 6, characterized in that: The scheduling area setting unit responds to the setting conditions to determine the scheduling area according to the comparison reference value or the operation deviation, including: The dispatch area setting unit responds to the setting condition that the sub-area fluctuation coefficient is greater than or equal to the preset sub-area fluctuation coefficient or the adjustment fluctuation value is greater than or equal to the preset adjustment fluctuation value, and determines the dispatch area according to the comparison reference value; The scheduling area setting unit responds to the setting conditions that the sub-area fluctuation coefficient is less than the preset sub-area fluctuation coefficient and the adjustment fluctuation value is less than the preset adjustment fluctuation value, and determines the scheduling area according to the operation deviation degree.

Images