Large unmanned aerial vehicle forestry spraying system control platform

Abstract

This invention discloses a control platform for a large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system, comprising: an agricultural and forestry data acquisition module for collecting agricultural and forestry information; a UAV data acquisition module for collecting UAV information; and an environmental data acquisition module for collecting environmental information. The control platform processes the agricultural and forestry information to generate first control information, processes the UAV information to generate second control information, and processes the environmental information to generate third control information. After the first, second, and third control information are generated, the control platform sends them to the corresponding receiving terminals. This invention integrates agricultural and forestry, UAV, and environmental data to achieve more comprehensive control of the large-scale UAV agricultural and forestry spraying system, effectively improving the operational efficiency of UAV agricultural and forestry spraying.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) control, and more specifically to a control platform for a large-scale UAV agricultural and forestry spraying system. Background Technology

[0002] With the accelerated transfer of rural land and the rise of new agricultural business entities such as family farms and large-scale growers, the problems of low efficiency and high cost of traditional manual or ground-based mechanical spraying have become increasingly prominent. For example, manual spraying can only cover 40 mu (approximately 6.6 acres) of land per day, while drones can cover 400-700 mu (approximately 66.7-87.4 acres). In addition, the migration of rural labor to urban areas has led to seasonal labor shortages, forcing agricultural production to transform towards mechanization and intelligentization.

[0003] In recent years, advancements in drone hardware (such as multi-rotor and fuel-powered models), sensors (such as infrared and multispectral sensors), and communication technologies (such as 5G and satellite positioning) have provided a technological foundation for building intelligent control platforms that integrate multi-source data. As a result, the use of drones for agricultural and forestry spraying has gradually become mainstream. In the process of controlling drone systems for agricultural and forestry spraying, drone agricultural and forestry spraying system control platforms are used.

[0004] Existing control platforms are ineffective in controlling drones for safe operations and have a low level of intelligence, which affects their usability. Therefore, a control platform for a large-scale drone agricultural and forestry spraying system is proposed. Summary of the Invention

[0005] The technical problem to be solved by this invention is: how to solve the problem that the existing safety protection system has a single protection type, resulting in poor protection effect and a certain impact on the use of the safety protection system. The invention provides a control platform for a large-scale UAV agricultural and forestry spraying system.

[0006] The present invention solves the above-mentioned technical problems through the following technical solutions, the present invention comprising:

[0007] The agricultural and forestry data collection module is used to collect agricultural and forestry information.

[0008] The drone data acquisition module is used to collect drone information.

[0009] The environmental data acquisition module is used to collect environmental information.

[0010] The control platform processes agricultural and forestry information to generate first control information, processes drone information to generate second control information, and processes environmental information to generate third control information.

[0011] After the first, second, and third control information are generated, the control platform sends them to the corresponding receiving terminals.

[0012] Furthermore, the specific process by which the agricultural and forestry data collection module collects agricultural and forestry information is as follows:

[0013] Agricultural and forestry information collection drones were set up. These drones are small drones with infrared image collection capabilities. They collect images of agricultural and forestry before the large drones begin spraying, i.e., images before spraying.

[0014] The drones take off before the large drones begin spraying, and real-time images of the agriculture and forestry are collected after the drones take off, i.e., images of the spraying process.

[0015] The collected agricultural and forestry information includes images before spraying and images during the spraying process.

[0016] Furthermore, the specific process of processing agricultural and forestry information to generate the first control information is as follows:

[0017] Images prior to spraying were extracted from agricultural and forestry information. These images were infrared images collected by an agricultural and forestry information collection drone.

[0018] The infrared model of the human body is imported into the infrared images collected by the drone to analyze whether a human body exists.

[0019] When a human body is detected in the infrared image captured by the drone, the location of the human body is extracted and analyzed to determine if the human body is on the preset spraying path. If the human body is on the preset spraying path, the first control information is generated, and the agricultural and forestry information collection drone is controlled to play a prompt message to remind personnel in the agricultural and forestry area to leave the spraying area.

[0020] The system extracts images of the spraying process and identifies preset target objects in the images. When a preset target object is abnormal, the system generates the first control information and sends control information to the spraying drone to control the spraying drone to slow down the spraying speed or change the spraying route.

[0021] Furthermore, the preset target object identification process and anomaly determination process are as follows:

[0022] The abnormal flying object models, including insect and bird models, were imported into the spraying process images.

[0023] When an abnormal flying object model is identified in the video of the spraying process, its flight altitude is monitored and it is marked as H;

[0024] When the number of abnormal flying objects exceeding the warning altitude exceeds the preset value, it indicates that the preset target object is abnormal;

[0025] Simultaneously, the number of abnormal flying objects within a unit range is collected. When the number of abnormal flying objects exceeds the warning number, it indicates that there is an anomaly in the preset target object.

[0026] Furthermore, it also performs behavior anomaly determination on preset target objects. When the preset target object exhibits behavior anomalies, it generates the first control information.

[0027] The process for determining abnormal behavior of a pre-defined target object is as follows:

[0028] Monitor abnormal flying objects; when the number of abnormal flying objects within the range exceeds a preset value, the abnormal flying objects are identified as an abnormal group.

[0029] Abnormal populations include bird groups and insect groups;

[0030] Extract the center position a1 of the abnormal group, then extract the position a2 of the spraying drone, and then connect a1 and a2 to obtain the evaluation line. When the position of a2 does not change, but the evaluation line gradually shrinks, it is determined that the preset target object has abnormal behavior and the first control information is generated.

[0031] When the abnormal group is a flock of birds, monitor a1 in real time. When a1 flies toward the area that has already been sprayed, it is determined that the preset target object has abnormal behavior and the first control information is generated.

[0032] When the abnormal group is an insect group, a1 is monitored in real time. When the position of a1 moves towards the edge of the spraying area, it is determined that the preset target object has abnormal behavior and the first control information is generated.

[0033] Furthermore, the specific process of processing the drone information to generate the second control information is as follows:

[0034] Extract drone information, including real-time remaining liquid in the tank, spraying flow rate, drone battery information, and drone location information;

[0035] The real-time remaining amount of medicine in the medicine tank and the spraying flow rate are processed to obtain the first parameter;

[0036] The second parameter is obtained by processing the drone battery information;

[0037] The drone's location information is processed to obtain the third parameter;

[0038] When any one of the first, second, or third parameters is abnormal, the second control information is generated.

[0039] Furthermore, the process for obtaining the first parameter and determining any anomalies is as follows:

[0040] Extract the real-time remaining amount of medicine in the medicine tank and the spraying flow rate, then collect the spraying time of the drone and mark it as t, mark the real-time remaining amount of medicine in the medicine tank as Z1, mark the spraying flow rate as Z2, and collect the amount of medicine when the drone takes off and mark it as Z3.

[0041] The first parameter Zz can be obtained by using the formula (Z3-Z1)-Z2*t=Zz, where t is a correction value, 0.95≤t≤1.05, and t is proportional to Z3.

[0042] When the first parameter Zz exceeds the preset range, it indicates that the first parameter is abnormal;

[0043] The process of obtaining the second parameter and determining the anomaly is as follows: extract the drone battery information, which is the real-time power information, and then collect the power consumption per unit time of the drone and the estimated task execution time.

[0044] Mark the real-time battery information as W1, mark the power consumption of the drone per unit time as W2, and mark the estimated mission execution time as R;

[0045] The second parameter Ww can be obtained by using the formula W2*R*α-W1=Ww. When the second parameter Ww is less than the preset value, the second parameter Ww is abnormal. α is the correction value, 1.01≤α≤1.1.

[0046] The process of obtaining the third parameter and the process of judging anomalies are as follows: The location information of the drone is extracted, a preset collection time point is set, and the location information of the drone is collected once every time the preset collection time point is reached. The collected drone location is marked as Ji, where i is the number of collections and Ji(xi, yi, zi) is the location coordinate of the drone.

[0047] Extract the standard position Bi(xi, yi, zi) for each preset collection time point;

[0048] Calculate the coordinate difference between Ji(xi, yi, zi) and Bi(xi, yi, zi) to obtain the coordinate difference (xi) of a single position. 差 yi 差 zi 差 When xi 差 ,yi 差 with zi 差 If any one of the parameters exceeds the preset range, it indicates a location anomaly. Then, the number of location anomalies is extracted to obtain the third parameter. When the third parameter is greater than i / 3, it indicates that the third parameter is anomaly.

[0049] Furthermore, the specific process of processing environmental information to generate third-party control information is as follows:

[0050] Environmental information is extracted, including wind speed, ambient temperature, ambient humidity, and light intensity.

[0051] The wind speed information is processed to obtain wind speed assessment parameters. If the wind speed assessment parameters are abnormal, third control information is generated.

[0052] The ambient temperature information is processed to obtain temperature assessment parameters. If the temperature assessment parameters are abnormal, third-party control information is generated.

[0053] The environmental humidity information is processed to obtain humidity assessment parameters. If the humidity assessment parameters are abnormal, third-party control information is generated.

[0054] The light intensity information is processed to obtain light assessment parameters. If the light assessment parameters are abnormal, third control information is generated.

[0055] When the wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters, and light intensity assessment parameters are all normal, the wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters, and light intensity assessment parameters are processed to obtain comprehensive assessment parameters. When the comprehensive assessment parameters are abnormal, third control information is generated.

[0056] Furthermore, the acquisition process and anomaly judgment process of wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters and light intensity assessment parameters are as follows: calculate the ratio of wind speed information to standard wind speed, that is, obtain wind speed assessment parameter D1. When wind speed assessment D1 exceeds the preset range, it indicates that there is an anomaly.

[0057] The ratio of the ambient temperature information to the standard temperature is calculated, which is the temperature assessment parameter D2. When the temperature assessment parameter D2 exceeds the preset range, it indicates that there is an anomaly.

[0058] The ratio of ambient humidity to standard humidity is calculated, which is the humidity assessment parameter D3. When the humidity assessment parameter D3 exceeds the preset range, it indicates that there is an abnormality.

[0059] The ratio of the light intensity information to the standard light intensity is calculated, which is the light evaluation parameter D4. When the light evaluation parameter D4 exceeds the preset range, it indicates that there is an anomaly.

[0060] Furthermore, the process for obtaining comprehensive evaluation parameters and determining anomalies is as follows:

[0061] Assign correction value β1 to D1, correction value β2 to D2, correction value β3 to D3, and correction value β4 to D4;

[0062] The comprehensive evaluation parameter Dd can be obtained by using the formula D1*β1+D2*β2+D2*β3+D4*β4=Dd. When the comprehensive evaluation parameter Dd is less than the preset value, it indicates that there is an anomaly.

[0063] Compared with existing technologies, this invention has the following advantages: The control platform of this large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system can detect the presence of human beings in the spraying area in advance by collecting infrared images of the UAV through agricultural and forestry information collection. If a human being is detected in the preset spraying path, a prompt message can be played in a timely manner to guide the person away, avoiding harm to personnel during spraying operations. Regarding operational accuracy and adaptability, the system performs preset target object identification on the spraying process images, which can promptly detect abnormal flying objects such as insects and birds. Based on the situation, the system can control the spraying UAV to slow down or change its route, making the spraying operation more targeted. Simultaneously, it can evaluate and adjust the UAV spraying operation based on environmental information such as wind speed, temperature, humidity, and light intensity, ensuring better spraying performance under different environmental conditions. In terms of UAV status monitoring, the system processes and monitors the remaining pesticide level, battery information, and location information of the UAV. When these information is abnormal, control information can be generated in a timely manner to ensure the UAV safely and stably completes the spraying task, improving operational efficiency and reliability, and realizing intelligent control of the large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system. Attached Figure Description

[0064] Figure 1 This is a structural block diagram of the present invention. Detailed Implementation

[0065] The embodiments of the present invention are described in detail below. These embodiments are implemented based on the technical solution of the present invention, and provide detailed implementation methods and specific operation processes. However, the scope of protection of the present invention is not limited to the following embodiments.

[0066] like Figure 1 As shown, this embodiment provides a technical solution: a control platform for a large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system, comprising:

[0067] The agricultural and forestry data collection module is used to collect agricultural and forestry information.

[0068] The drone data acquisition module is used to collect drone information.

[0069] The environmental data acquisition module is used to collect environmental information.

[0070] The control platform processes agricultural and forestry information to generate first control information, processes drone information to generate second control information, and processes environmental information to generate third control information.

[0071] After the first, second, and third control information are generated, the control platform sends them to the corresponding receiving terminals.

[0072] Furthermore, the specific process by which the agricultural and forestry data collection module collects agricultural and forestry information is as follows:

[0073] Agricultural and forestry information collection drones were set up. These drones are small drones with infrared image collection capabilities. They collect images of agricultural and forestry before the large drones begin spraying, i.e., images before spraying.

[0074] The drones take off before the large drones begin spraying, and real-time images of the agriculture and forestry are collected after the drones take off, i.e., images of the spraying process.

[0075] The collected agricultural and forestry information includes images before spraying and images during the spraying process.

[0076] Furthermore, the specific process of processing agricultural and forestry information to generate the first control information is as follows:

[0077] Images prior to spraying were extracted from agricultural and forestry information. These images were infrared images collected by an agricultural and forestry information collection drone.

[0078] The infrared model of the human body is imported into the infrared images collected by the drone to analyze whether a human body exists.

[0079] When a human body is detected in the infrared image captured by the drone, the location of the human body is extracted and analyzed to determine if the human body is on the preset spraying path. If the human body is on the preset spraying path, the first control information is generated, and the agricultural and forestry information collection drone is controlled to play a prompt message to remind personnel in the agricultural and forestry area to leave the spraying area.

[0080] The system extracts images of the spraying process and identifies preset target objects in the images. When a preset target object is abnormal, the system generates the first control information and sends control information to the spraying drone to control the spraying drone to slow down the spraying speed or change the spraying route.

[0081] Agricultural and forestry information collection drones take off in advance to collect infrared images before spraying, enabling the detection of personnel within the spraying area before operations begin. By analyzing the images using human infrared models, the drones accurately locate human positions. Once someone is detected in the pre-set spraying path, the drones immediately generate initial control information and play warning messages to guide personnel to evacuate, preventing unsuspecting individuals from being exposed to the sprayed pesticides and effectively preventing safety accidents.

[0082] Real-time image acquisition and target identification during spraying enable the system to promptly capture the dynamics of unusual targets such as insects and birds, and to identify potential hazards to the spraying drone. Upon detection of anomalies, the system generates initial control information to slow the drone down or change its route, ensuring precise spraying of the pesticide to the target area. This avoids spraying deviations caused by external interference, improves pesticide use efficiency, reduces pesticide waste and environmental pollution, and better guarantees the drone's flight safety, preventing damage caused by bird strikes or other incidents.

[0083] By collecting images before and during spraying in stages, the control platform can fully grasp the dynamic changes in the agricultural and forestry operation environment and adjust the control strategy in a timely manner according to the information at different stages. This allows the entire agricultural and forestry spraying system to flexibly cope with complex and ever-changing operation scenarios, improving the system's adaptability and reliability.

[0084] The preset target object identification process and anomaly determination process are as follows:

[0085] The abnormal flying object models, including insect and bird models, were imported into the spraying process images.

[0086] When an abnormal flying object model is identified in the video of the spraying process, its flight altitude is monitored and it is marked as H;

[0087] When the number of abnormal flying objects exceeding the warning altitude exceeds the preset value, it indicates that the preset target object is abnormal;

[0088] Simultaneously, the number of abnormal flying objects within a unit range is collected. When the number of abnormal flying objects exceeds the warning number, it indicates that the preset target object is abnormal.

[0089] By importing models of unusual flying objects such as insects and birds, the system can quickly and accurately identify potential threats, such as large-scale insect swarms or bird gatherings. Combining the dual criteria of flight altitude and number, the system can quantitatively assess the risk of pest and disease outbreaks, making pesticide spraying more targeted, improving control effectiveness, and reducing damage to agricultural and forestry crops.

[0090] By monitoring the altitude and number of unusual flying objects in real time, the system can adjust spraying strategies accordingly. For example, when the number of unusual flying objects in the high sky exceeds a threshold, it may indicate a trend of pest and disease spread. The system can then adjust the drone's flight path and spraying dosage to achieve dynamic and intelligent operation, avoiding insufficient control or waste of resources caused by mechanically executing fixed procedures.

[0091] Reducing ecological impact: Avoiding indiscriminate pesticide spraying, minimizing pesticide coverage in non-target areas, and reducing the impact on the surrounding ecological environment and beneficial organisms, thus practicing the concept of green agriculture. At the same time, precise spraying operations can reduce pesticide residues, ensure the quality and safety of agricultural products, and improve the overall efficiency of agricultural production.

[0092] If birds gather, the spraying drone needs to be slowed down and the spraying operation should be carried out after the birds disperse. This not only ensures the safety of the spraying drone, but also reduces the impact of the sprayed pesticides on the birds.

[0093] If insects are clustered, the spraying drone needs to be controlled to change its spraying route and fly to the area where the insects are clustered to spray, so as to achieve precise extermination and better ensure agricultural and forestry safety.

[0094] At the same time, it also performs behavior anomaly judgment on preset target objects. When the preset target object has behavior anomalies, the first control information is generated.

[0095] The process for determining abnormal behavior of a pre-defined target object is as follows:

[0096] Monitor abnormal flying objects; when the number of abnormal flying objects within the range exceeds a preset value, the abnormal flying objects are identified as an abnormal group.

[0097] Abnormal populations include bird groups and insect groups;

[0098] Extract the center position a1 of the abnormal group, and then extract the position a2 of the spraying drone. Then connect a1 and a2 to obtain the evaluation line. When the position of a2 does not change, but the evaluation line gradually shrinks, it is determined that the preset target object has abnormal behavior and the first control information is generated. The gradual shrinking of the evaluation line indicates that the flock of birds may be stimulated and fly towards the spraying drone. Therefore, it is necessary to control the accompanying drone to disperse the flock of birds to ensure the safety of the spraying drone.

[0099] When the abnormal group is a flock of birds, monitor a1 in real time. When a1 flies toward the area that has already been sprayed, it is determined that the preset target has abnormal behavior and the first control information is generated. The pesticide concentration in the area that has been sprayed is high, which may affect the birds. At this time, control the accompanying drone to drive away the flock of birds and make them leave the spraying area to ensure their safety.

[0100] When the abnormal group is an insect group, monitor a1 in real time. When the position of a1 keeps moving towards the edge of the spraying area, it is determined that the preset target object has abnormal behavior and the first control information is generated. When the abnormal group is an insect group and the position of a1 keeps moving towards the edge of the spraying area, it means that the insect group wants to escape. They may fly back to the target farmland after the pesticide spraying is completed. At this time, the first control information is generated to drive the insect group to the area that has been sprayed to achieve a better pest control effect.

[0101] The specific process of processing the drone information to generate the second control information is as follows:

[0102] Extract drone information, including real-time remaining liquid in the tank, spraying flow rate, drone battery information, and drone location information;

[0103] The real-time remaining amount of medicine in the medicine tank and the spraying flow rate are processed to obtain the first parameter;

[0104] The second parameter is obtained by processing the drone battery information;

[0105] The drone's location information is processed to obtain the third parameter;

[0106] When any one of the first, second, or third parameters is abnormal, the second control information is generated.

[0107] Furthermore, the process for obtaining the first parameter and determining any anomalies is as follows:

[0108] Extract the real-time remaining amount of medicine in the medicine tank and the spraying flow rate, then collect the spraying time of the drone and mark it as t, mark the real-time remaining amount of medicine in the medicine tank as Z1, mark the spraying flow rate as Z2, and collect the amount of medicine when the drone takes off and mark it as Z3.

[0109] The first parameter Zz can be obtained by using the formula (Z3-Z1)-Z2*t=Zz, where t is a correction value, 0.95≤t≤1.05, and t is proportional to Z3.

[0110] When the first parameter Zz exceeds the preset range, it indicates that the first parameter is abnormal;

[0111] The process of obtaining the second parameter and determining the anomaly is as follows: extract the drone battery information, which is the real-time power information, and then collect the power consumption per unit time of the drone and the estimated task execution time.

[0112] Mark the real-time battery information as W1, mark the power consumption of the drone per unit time as W2, and mark the estimated mission execution time as R;

[0113] The second parameter Ww can be obtained by using the formula W2*R*α-W1=Ww. When the second parameter Ww is less than the preset value, the second parameter Ww is abnormal. α is the correction value, 1.01≤α≤1.1.

[0114] The process of obtaining the third parameter and the process of judging anomalies are as follows: The location information of the drone is extracted, a preset collection time point is set, and the location information of the drone is collected once every time the preset collection time point is reached. The collected drone location is marked as Ji, where i is the number of collections and Ji(xi, yi, zi) is the location coordinate of the drone.

[0115] Extract the standard position Bi(xi, yi, zi) for each preset collection time point;

[0116] Calculate the coordinate difference between Ji(xi, yi, zi) and Bi(xi, yi, zi) to obtain the coordinate difference (xi) of a single position. 差 ,yi 差 zi 差 When xi 差 ,yi 差 with zi 差 If any one of them exceeds the preset range, it indicates a location abnormality. Then, the number of location abnormalities is extracted to obtain the third parameter. When the third parameter is greater than i / 3, it indicates that the third parameter is abnormal.

[0117] By monitoring the remaining amount of pesticide in the tank, spray flow rate, battery level, and location information in real time, problems such as pesticide depletion, insufficient power, or flight deviation can be predicted in advance. For example, when the pesticide remaining amount parameter calculated according to the formula is abnormal, the drone can be promptly dispatched to return to replenish the pesticide, avoiding operation interruption due to pesticide depletion and ensuring the continuity of the spraying mission.

[0118] Precise analysis of battery information, combined with power consumption per unit time and estimated mission duration, can effectively prevent drones from crashing due to insufficient power. Simultaneously, real-time location monitoring allows for immediate control measures to be generated and corrective actions taken if the drone deviates from its preset route, reducing the risk of collisions with obstacles or disorientation and ensuring the safety of the equipment and its surrounding environment.

[0119] Based on accurate parameter calculations and anomaly detection, the system can rationally plan the operation rhythm and path of the drone. For example, when there is sufficient remaining pesticide, the spraying speed can be appropriately increased; when the battery is low, the system prioritizes completing the operation in the nearest area, reducing unnecessary flights, optimizing the allocation of resources such as pesticides and battery power, and reducing operating costs.

[0120] By using quantitative parameter calculations and standardized anomaly detection rules, the system can quickly and objectively assess the status of drones and generate control commands, reducing human intervention, improving the timeliness and accuracy of control, and promoting the development of agricultural and forestry spraying operations towards intelligence and automation.

[0121] The specific process of processing environmental information to generate third-party control information is as follows:

[0122] Environmental information is extracted, including wind speed, ambient temperature, ambient humidity, and light intensity.

[0123] The wind speed information is processed to obtain wind speed assessment parameters. If the wind speed assessment parameters are abnormal, third control information is generated.

[0124] The ambient temperature information is processed to obtain temperature assessment parameters. If the temperature assessment parameters are abnormal, third-party control information is generated.

[0125] The environmental humidity information is processed to obtain humidity assessment parameters. If the humidity assessment parameters are abnormal, third-party control information is generated.

[0126] The light intensity information is processed to obtain light assessment parameters. If the light assessment parameters are abnormal, third control information is generated.

[0127] When the wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters, and light intensity assessment parameters are all normal, the wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters, and light intensity assessment parameters are processed to obtain comprehensive assessment parameters. When the comprehensive assessment parameters are abnormal, third control information is generated.

[0128] The system assesses individual environmental factors such as wind speed, temperature, humidity, and light intensity. When a factor becomes abnormal, such as excessive wind speed which may affect the stability of the drone, the system can promptly generate third-party control information and take measures such as reducing flight altitude and suspending operations to prevent accidents such as drone loss of control or crashes due to adverse environments, thus ensuring the safe operation of the equipment.

[0129] Adjust the spraying strategy according to parameters such as ambient temperature and humidity. For example, in a hot and dry environment, appropriately reduce the spraying speed or increase the spraying volume to prevent the pesticide from evaporating too quickly and affecting its efficacy. In a high humidity environment, choose a more suitable time to spray to avoid the pesticide being diluted or washed away, thereby improving the utilization rate of pesticides and the effect of pest and disease control.

[0130] By comprehensively evaluating parameters and taking into account multiple environmental factors, even if a single environmental parameter does not reach the abnormal threshold, the combined effect may affect the operation. In this case, the system can still generate third-party control information and flexibly adjust the operation plan, so that the drone can find the best operation mode under different weather and environmental conditions, ensuring the continuous and efficient operation of agricultural and forestry spraying.

[0131] Accurate environmental assessments prevent ineffective or repetitive operations due to unsuitable environments, reducing waste of resources such as pesticides and electricity. Simultaneously, they effectively mitigate equipment damage risks caused by environmental factors, lower maintenance costs, and optimize operational costs from multiple perspectives.

[0132] The process of obtaining and judging the anomalies of wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters and light intensity assessment parameters is as follows: Calculate the ratio of wind speed information to standard wind speed, that is, obtain wind speed assessment parameter D1. When wind speed assessment D1 exceeds the preset range, it indicates that there is an anomaly.

[0133] The ratio of the ambient temperature information to the standard temperature is calculated, which is the temperature assessment parameter D2. When the temperature assessment parameter D2 exceeds the preset range, it indicates that there is an anomaly.

[0134] The ratio of ambient humidity to standard humidity is calculated, which is the humidity assessment parameter D3. When the humidity assessment parameter D3 exceeds the preset range, it indicates that there is an abnormality.

[0135] The ratio of the light intensity information to the standard light intensity is calculated, which is the light evaluation parameter D4. When the light evaluation parameter D4 exceeds the preset range, it indicates that there is an anomaly.

[0136] The process for obtaining comprehensive evaluation parameters and determining anomalies is as follows:

[0137] Assign correction value β1 to D1, correction value β2 to D2, correction value β3 to D3, and correction value β4 to D4;

[0138] β1+β2+β3+β4=1, β1>β2>β3>β4;

[0139] The comprehensive evaluation parameter Dd can be obtained by using the formula D1*β1+D2*β2+D2*β3+D4*β4=Dd. When the comprehensive evaluation parameter Dd is less than the preset value, it indicates that there is an anomaly.

[0140] By converting environmental factors such as wind speed, temperature, humidity, and light intensity into specific ratio parameters, and comparing them with preset standard ranges, it is possible to intuitively and accurately determine whether a single environmental factor is abnormal. For example, when the wind speed assessment parameter exceeds the range, the potential threat of strong winds to drone flight and pesticide dispersion can be immediately identified, avoiding errors in subjective judgment and providing a reliable basis for risk warning.

[0141] The comprehensive assessment parameters combine individual parameters and are weighted by correction values ​​to fully consider the different weights of environmental factors affecting operations. Even if an individual parameter does not reach the abnormal threshold, the superposition of multiple factors may create risks. In this case, the comprehensive assessment can capture potential threats, such as the combination of high temperature, low humidity, and strong winds, which may accelerate the evaporation of the pesticide solution. Based on this, the system generates control information to achieve more comprehensive and intelligent decision-making.

[0142] Based on real-time evaluation of quantitative parameters, the system can dynamically adjust its operational strategies according to environmental changes. For example, when temperature evaluation parameters are abnormal, the system automatically adjusts the spraying height and speed; when comprehensive evaluation parameters are abnormal, the system pauses or re-plans the operation, ensuring that the drone remains in a safe and efficient operating state in complex environments and reducing the negative impact of the environment on operational results.

[0143] Standardized parameter calculation and anomaly judgment rules make the environmental assessment process standardized and replicable, reducing operation interruptions, equipment wear and tear and pesticide waste caused by environmental factors, effectively controlling operating costs, ensuring that agricultural and forestry spraying tasks proceed as planned, and improving overall operational reliability and economic benefits.

[0144] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0145] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0146] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A control platform for a large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system, characterized in that, include: The agricultural and forestry data collection module is used to collect agricultural and forestry information. The drone data acquisition module is used to collect drone information. The environmental data acquisition module is used to collect environmental information. The control platform processes agricultural and forestry information to generate first control information, processes drone information to generate second control information, and processes environmental information to generate third control information. After the first control information, the second control information and the third control information are generated, the control platform sends the first control information, the second control information and the third control information to the corresponding receiving terminals. The specific process of the agricultural and forestry data collection module collecting agricultural and forestry information is as follows: Agricultural and forestry information collection drones were set up. These drones are small drones with infrared image collection capabilities. They collect images of agricultural and forestry before the large drones begin spraying, i.e., images before spraying. The drones take off before the large drones begin spraying, and real-time images of the agriculture and forestry are collected after the drones take off, i.e., images of the spraying process. The collected agricultural and forestry information includes images before spraying and images during the spraying process; The specific process of processing agricultural and forestry information to generate the first control information is as follows: Images prior to spraying were extracted from agricultural and forestry information. These images were infrared images collected by an agricultural and forestry information collection drone. The infrared model of the human body is imported into the infrared images collected by the drone to analyze whether a human body exists. When a human body is detected in the infrared image captured by the drone, the location of the human body is extracted and analyzed to determine if the human body is on the preset spraying path. If the human body is on the preset spraying path, the first control information is generated, and the agricultural and forestry information collection drone is controlled to play a prompt message to remind personnel in the agricultural and forestry area to leave the spraying area. The system extracts images of the spraying process and identifies preset target objects in the images. When a preset target object is abnormal, the system generates the first control information and sends control information to the spraying drone to control the spraying drone to slow down the spraying speed or change the spraying route. The preset target object identification process and anomaly determination process are as follows: The abnormal flying object models were imported into the spraying process images. The abnormal flying object models included insect models and bird models. When an abnormal flying object model is identified in the video of the spraying process, its flight altitude is monitored and it is marked as H; When the number of abnormal flying objects exceeding the warning altitude exceeds the preset value, it indicates that the preset target object is abnormal; Simultaneously, the number of abnormal flying objects within a unit range is collected. When the number of abnormal flying objects exceeds the warning number, it indicates that the preset target object is abnormal. At the same time, it also performs behavior anomaly judgment on preset target objects. When the preset target object has behavior anomalies, the first control information is generated. The process for determining abnormal behavior of a pre-defined target object is as follows: Monitor abnormal flying objects; when the number of abnormal flying objects within the range exceeds a preset value, the abnormal flying objects are identified as an abnormal group. Abnormal populations include bird groups and insect groups; Extract the center position a1 of the abnormal group, then extract the position a2 of the spraying drone, and then connect a1 and a2 to obtain the evaluation line. When the position of a2 does not change, but the evaluation line gradually shrinks, it is determined that the preset target object has abnormal behavior and the first control information is generated. When the abnormal group is a flock of birds, monitor a1 in real time. When a1 flies toward the area that has already been sprayed, it is determined that the preset target object has abnormal behavior and the first control information is generated. When the abnormal group is an insect group, a1 is monitored in real time. When the position of a1 moves towards the edge of the spraying area, it is determined that the preset target object has abnormal behavior and the first control information is generated.

2. The control platform for a large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system according to claim 1, characterized in that: The specific process of processing the drone information to generate the second control information is as follows: Extract drone information, including real-time remaining liquid in the tank, spraying flow rate, drone battery information, and drone location information; The real-time remaining amount of medicine in the medicine tank and the spraying flow rate are processed to obtain the first parameter; The second parameter is obtained by processing the drone battery information; The drone's location information is processed to obtain the third parameter; When any one of the first, second, or third parameters is abnormal, the second control information is generated.

3. The control platform for a large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system according to claim 1, characterized in that: The specific process of processing environmental information to generate third-party control information is as follows: Environmental information is extracted, including wind speed, ambient temperature, ambient humidity, and light intensity. The wind speed information is processed to obtain wind speed assessment parameters. If the wind speed assessment parameters are abnormal, third control information is generated. The ambient temperature information is processed to obtain temperature assessment parameters. If the temperature assessment parameters are abnormal, third-party control information is generated. The environmental humidity information is processed to obtain humidity assessment parameters. If the humidity assessment parameters are abnormal, third-party control information is generated. The light intensity information is processed to obtain light assessment parameters. If the light assessment parameters are abnormal, third control information is generated. When the wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters, and light intensity assessment parameters are all normal, the wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters, and light intensity assessment parameters are processed to obtain comprehensive assessment parameters. When the comprehensive assessment parameters are abnormal, third control information is generated.

4. The control platform for a large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system according to claim 3, characterized in that: The process of obtaining and judging the anomalies of wind speed assessment parameters, temperature assessment parameters, humidity assessment parameters and light intensity assessment parameters is as follows: Calculate the ratio of wind speed information to standard wind speed, that is, obtain wind speed assessment parameter D1. When wind speed assessment D1 exceeds the preset range, it indicates that there is an anomaly. The ratio of the ambient temperature information to the standard temperature is calculated, which is the temperature assessment parameter D2. When the temperature assessment parameter D2 exceeds the preset range, it indicates that there is an anomaly. The ratio of ambient humidity to standard humidity is calculated, which is the humidity assessment parameter D3. When the humidity assessment parameter D3 exceeds the preset range, it indicates that there is an abnormality. The ratio of the light intensity information to the standard light intensity is calculated, which is the light evaluation parameter D4. When the light evaluation parameter D4 exceeds the preset range, it indicates that there is an anomaly.

5. The control platform for a large-scale unmanned aerial vehicle (UAV) agricultural and forestry spraying system according to claim 4, characterized in that: The process for obtaining comprehensive evaluation parameters and determining anomalies is as follows: Assign correction value β1 to D1, correction value β2 to D2, correction value β3 to D3, and correction value β4 to D4; The comprehensive evaluation parameter Dd can be obtained by using the formula D1*β1+D2*β2+D2*β3+D4*β4=Dd. When the comprehensive evaluation parameter Dd is less than the preset value, it indicates that there is an anomaly.

Images