An Internet of Things-based intelligent control system for crop diseases and pests

Abstract

The application discloses a kind of crop disease and insect pest intelligent prevention and control systems based on Internet of Things, it is related to agricultural technology field, by the mutual cooperation of three algorithm units, constitute a kind of core architecture of crop disease and insect pest intelligent prevention and control systems based on Internet of Things, comprehensively consider multiple factors such as insect population density Di, environmental temperature Ta, fog drop deposition density Pd and chlorophyll content variation ΔEc, calculate to obtain disease and insect pest comprehensive risk value Dir and disease and insect pest comprehensive risk value Et, so that crop disease and insect pest intelligent prevention and control system can accurately judge the severity of disease and insect pest, and real-time calculation and adjustment pesticide dosage Q, to carry out accurate pesticide application, this kind of pesticide application mode can effectively prevent and control the disease and insect pest of crop while reducing the waste of pesticide, reduce the pollution of pesticide to environment, help to promote agriculture to green, sustainable direction development, improve the ecological benefit and economic benefit of agricultural production.

Description

Technical Field

[0001] This invention relates to the field of agricultural technology, specifically to an intelligent pest and disease control system for crops based on the Internet of Things. Background Technology

[0002] Current crop pest and disease control methods involve spraying pesticides after observing that crops are affected by pests or diseases. However, this conventional method makes it difficult to adjust the amount of pesticide applied based on the extent of the damage. Excessive pesticide application can pollute the soil, water, and air, while wasting pesticides. Conversely, insufficient pesticide application can be ineffective.

[0003] Therefore, there is an urgent need for an intelligent pest and disease control system for crops based on the Internet of Things to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent pest and disease control system for crops based on the Internet of Things, thereby solving the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent crop pest and disease control system based on the Internet of Things, comprising:

[0006] The data collection module is used to collect information on crop growth environment and pesticide application data. The crop growth environment information specifically includes: ambient temperature Ta, soil electrical conductivity Sc, number of pests and diseases Nk, monitored area Ak, and change in chlorophyll content ΔEc.

[0007] Application data specifically includes: droplet deposition density Pd and drone flight altitude Vd;

[0008] The data preprocessing module is used to decode and preprocess the data information to obtain the parameters that will be used in the calculation in the computation module.

[0009] The computational processing module includes:

[0010] The comprehensive risk value algorithm unit is used to calculate the insect population density Di based on the number of pests Nk and the monitored area Ak. It also combines the two crop growth environment factors, namely ambient temperature Ta and soil electrical conductivity Sc, to calculate the comprehensive risk value of pests and diseases Diir after adjusting for the growth environment.

[0011] The pesticide application rate algorithm unit is used to take the integrated pest and disease risk value Dir as the input parameter and calculate the three different pesticide application rates Q when the integrated pest and disease risk value Dir is different through a piecewise function.

[0012] The system optimization value algorithm unit is used to input the application rate Qn for the nth application and the integrated pest and disease risk value Dir into the system optimization value algorithm unit, and combine it with two crop growth environmental factors, chlorophyll ΔEc and soil electrical conductivity Sc, to calculate the system optimization value Et. The system parameter optimization value Et is then compared with the previous system parameter optimization value Et. last Then, the parameters in the comprehensive risk value algorithm unit are adjusted.

[0013] Optionally, the collection of crop growth environment information and pesticide application data specifically includes:

[0014] The ambient temperature Ta is obtained by monitoring with a temperature sensor;

[0015] Soil electrical conductivity Sc was obtained by monitoring using EC sensors;

[0016] The number of pests and diseases, Nk, and the monitored area, Ak, were obtained using an insect monitoring instrument.

[0017] The droplet deposition density Pd and the drone's flight altitude Vd are obtained from the control center of the spraying drone.

[0018] The concentration of pathogenic spores, Cs, was obtained in real time through a spore trapping device.

[0019] The change in chlorophyll content ΔEc of crops was obtained by measuring with a chlorophyll meter.

[0020] The droplet deposition density Pd and the drone's flight altitude Vd are obtained from the control center of the spraying drone.

[0021] Optionally, the parameter adjustment specifically includes:

[0022] When Et > Etlast, and |Et - Et last When |>0.2, it means that the optimized value of system parameter Et has been significantly reduced, the intelligent prevention and control effect of crops is good, and the adjustment coefficient α in the algorithm unit for reducing the comprehensive risk value of pests and diseases is 0.8 times that of the previous calculation, so as to reduce the comprehensive risk value of pests and diseases Dir obtained in the next calculation.

[0023] When Et < Etlast, and |Et - Et last When |>0.2, it means that the optimized value of the system parameter Et has increased significantly, the intelligent prevention and control effect of crops is poor, and the value of the adjustment coefficient α in the integrated pest and disease risk value algorithm unit is increased to 1.2 times that in the previous calculation, so as to increase the integrated pest and disease risk value Dir obtained in the next calculation.

[0024] Optionally, the calculation logic of the integrated pest management risk value algorithm unit is as follows:

[0025] S11. The number of pests Nk obtained by monitoring the pests once is divided by the monitored area Ak to obtain the number of pests per unit area during the monitoring. The number of pests per unit area obtained by multiple monitoring is added together and then divided by the current number of monitoring n to obtain the averaged pest density Di, which serves as the basis for calculating the comprehensive pest risk value Dir.

[0026] S12 uses the growth characteristics of the exponential function to reflect the contribution of ambient temperature Ta to the calculated comprehensive risk value of pests and diseases Dir, so as to reflect the promoting effect of extreme temperature on the occurrence of pests and diseases.

[0027] S13 uses a modified Sigmoid function to scale the influence of soil conductivity Sc on the integrated pest and disease risk value Dir to a range of 0 to 1. When the soil conductivity Sc exceeds the conductivity threshold of 20, the calculated integrated pest and disease risk value Dir is increased to reflect the inhibitory effect on crop disease resistance.

[0028] Optionally, the influence value of the integrated pest and disease risk value Dir can be scaled by a variant of the Sigmoid function. This retains the positive influence of soil conductivity Sc on the integrated pest and disease risk value Dir after it exceeds the conductivity threshold of 20, while also avoiding the excessive influence of soil conductivity Sc on the integrated pest and disease risk value Dir when it reaches an extreme value.

[0029] Optionally, the calculation logic of the dosage algorithm unit is as follows:

[0030] The minimum application rate Qmin is set to a fixed value of 0.2, the baseline application rate Qbase is set to a fixed value of 0.5, and the maximum application rate Qmax is set to a fixed value of 2.0. A piecewise function is used to calculate different application rates for different values ​​of the integrated pest management risk (IMR) Dir, specifically including:

[0031] S22. When the integrated pest and disease risk value Dir is between 0.6 and 1.2, it means that the crops in this area are in a low-risk area for pests and diseases. The minimum application rate Qmin is taken as the basis for calculating the application rate Q. The application rate Q is directly calculated by using the integrated pest and disease risk value Dir as a variable in a linear function. When the pest and disease risk is low, the application rate Q increases linearly with the integrated pest and disease risk value Dir, ensuring that minimum control measures are still taken when the risk is low to avoid pest accumulation.

[0032] S23. When the comprehensive pest and disease risk value Dir is between 1.2 and 2.0, it means that the crops in this area are in the medium-risk area of ​​pests and diseases. The baseline application rate Qbase is taken as the basis for calculating the application rate Q. The spraying efficiency of the drone is obtained by dividing the droplet deposition density Pd by the drone flight altitude Vd. The numerical influence of the drone spraying efficiency on the application rate Q is reflected by the logarithmic function. While retaining the positive gain of the drone spraying efficiency on the application rate Q, the excessive influence of the drone spraying efficiency on the application rate Q when it reaches the extreme value is compressed by the logarithmic function.

[0033] S24. When the comprehensive risk value of pests and diseases, Dir, is greater than 2.0, it means that the crops in this area are in a high-risk area for pests and diseases. The maximum application rate, Qmax, is taken as the basis for calculating the application rate, Q. The product of the insect population density, di, and the pathogen spore concentration, Cs, is used as the input of the tanh function to obtain an output value between -1 and 1. This output value is then multiplied by the maximum application rate, Qmax, to obtain an application rate, Q, that is affected by the severity of pests and diseases but does not increase indefinitely. Due to the characteristics of the tanh function, the growth of the output value slows down when the input value is large, so as to limit the increase rate of the application rate, Q, and avoid the risks caused by overuse of pesticides.

[0034] Optionally, the calculation logic of the system optimization value algorithm unit is as follows:

[0035] S31, subtract the baseline application rate Qbase from the nth application rate Qn to obtain the rate of change of application rate, and then multiply it by the soil electrical conductivity Sc. This reflects the change in soil conditions caused by the system after adjusting the application rate Q. As the application rate Q increases, the soil electrical conductivity Sc will also increase, and the calculated system optimization value Et will also increase.

[0036] S32, the difference between the ideal value of the integrated pest management system Dir (0.9) and the actual value of the integrated pest management system Dir reflects the parameter status in the intelligent pest and disease control system. The larger the difference in this part, the more ideal the integrated pest management system Dir is, the better the parameters in the intelligent pest and disease control system are, and the lower the calculated system optimization value Et.

[0037] S33, the change in chlorophyll content ΔEc is magnified by 100 and used as the minuend to calculate the system optimization value Et. As the change in chlorophyll content ΔEc increases, it means that the crop has been effectively controlled for pests and diseases after the pesticide application, and the intelligent pest and disease control system for crops is operating effectively, thus reducing the calculated system optimization value Et.

[0038] Optionally, the decoding preprocessing includes data cleaning and data standardization.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0040] I. This invention, through the cooperation of three algorithm units, constitutes the core architecture of an IoT-based intelligent crop pest and disease control system. It comprehensively considers multiple factors such as insect population density Di, ambient temperature Ta, droplet deposition density Pd, and pathogen spore concentration Cs to calculate the comprehensive pest and disease risk values ​​Dir and Et. This enables the intelligent crop pest and disease control system to accurately determine the occurrence trend and severity of pests and diseases, and to calculate and adjust the pesticide application rate Q in real time. Based on the application rate Q, precise pesticide application to crops can be achieved. This method effectively controls crop pests and diseases while reducing pesticide waste and mitigating the risk of pesticide pollution to soil, water, and air. It helps promote green and sustainable agricultural development, improving the ecological and economic benefits of agricultural production.

[0041] II. This invention compares the optimized system parameter value Et with the previous optimized system parameter value Et in the IoT database. last Furthermore, the value of the adjustment coefficient α in the integrated risk value algorithm unit for pests and diseases is dynamically adjusted, enabling the three algorithm units to continuously provide feedback and make adjustments. This enhances the adaptive capability of the IoT-based intelligent pest and disease control system and is worthy of promotion and use. Attached Figure Description

[0042] Figure 1 A flowchart of an IoT-based intelligent pest and disease control system for crops;

[0043] Figure 2 This is a schematic diagram of the overall structure of an IoT-based intelligent pest and disease control system for crops. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Example 1, please refer to Figures 1 to 2 This invention provides an intelligent pest and disease control system for crops based on the Internet of Things, comprising:

[0046] The data collection module is used to collect information on crop growth environment and pesticide application data, specifically including:

[0047] The ambient temperature Ta is obtained by monitoring with a temperature sensor;

[0048] Soil electrical conductivity (Sc) was obtained by monitoring using EC sensors.

[0049] The number of pests and diseases, Nk, and the monitored area, Ak, were obtained using an insect monitoring instrument.

[0050] The droplet deposition density Pd and the drone's flight altitude Vd are obtained from the control center of the spraying drone.

[0051] The concentration of pathogenic spores, Cs, was obtained in real time through a spore trapping device.

[0052] The change in chlorophyll content ΔEc of crops was obtained by measuring with a chlorophyll meter.

[0053] The droplet deposition density Pd and the drone's flight altitude Vd are obtained from the control center of the spraying drone.

[0054] The data preprocessing module is used to decode and preprocess the data information to obtain the parameters that will be used in the calculation in the computation module.

[0055] Calculation processing module

[0056] The comprehensive risk value algorithm unit is used to calculate the insect population density Di based on the number of pests Nk and the monitored area Ak. It also combines the two crop growth environment factors, namely ambient temperature Ta and soil electrical conductivity Sc, to calculate the comprehensive risk value of pests and diseases Diir after adjusting for the growth environment.

[0057] The pesticide application rate algorithm unit is used to take the integrated pest and disease risk value Dir as the input parameter and calculate the three different pesticide application rates Q when the integrated pest and disease risk value Dir is different through a piecewise function.

[0058] The system optimization value algorithm unit is used to input the application rate Qn for the nth application and the integrated pest and disease risk value Dir into the system optimization value algorithm unit, and combine it with two crop growth environmental factors, chlorophyll ΔEc and soil electrical conductivity Sc, to calculate the system optimization value Et. The system parameter optimization value Et is then compared with the previous system parameter optimization value Et. last Then, the parameters in the comprehensive risk value algorithm unit are adjusted, specifically including:

[0059] When Et > Et last And |Et-Et last When |>0.2, it means that the optimized value of system parameter Et has been significantly reduced, the intelligent prevention and control effect of crops is good, and the adjustment coefficient α in the algorithm unit for reducing the comprehensive risk value of pests and diseases is 0.8 times that of the previous calculation, so as to reduce the comprehensive risk value of pests and diseases Dir obtained in the next calculation.

[0060] When Et < Et last And |Et-Et last When |>0.2, it means that the optimized value of the system parameter Et has increased significantly, the intelligent prevention and control effect of crops is poor, and the value of the adjustment coefficient α in the integrated pest and disease risk value algorithm unit is increased to 1.2 times that in the previous calculation, so as to increase the integrated pest and disease risk value Dir obtained in the next calculation.

[0061] In this embodiment:

[0062] This invention utilizes the synergy of three algorithm units to form the core architecture of an IoT-based intelligent crop pest and disease control system. By comprehensively considering multiple factors such as insect population density Di, ambient temperature Ta, drone flight altitude Vd, droplet deposition density Pd, and pathogen spore concentration Cs, it calculates the comprehensive pest and disease risk values ​​Dir and Et. This allows the intelligent crop pest and disease control system to accurately determine the occurrence trend and severity of pests and diseases based on the actual conditions in different risk areas, and to calculate and adjust the pesticide application rate Q in real time. This precise application method not only improves the effectiveness of pesticides... The system improves utilization efficiency, reduces pesticide waste and overuse, lowers the risk of pesticide pollution to soil, water, and air, reduces the negative impact of pesticides on crops and ecosystems, and improves the efficiency of pest and disease control. Furthermore, by optimizing the drone's flight altitude (Vd) and droplet deposition density (Pd), it can further reduce pesticide drift and volatilization during spraying, thereby further reducing environmental pollution. In summary, the intelligent pest and disease control system can dynamically adjust the application strategy to ensure effective control in the early stages of pests and diseases, avoid the spread of disease and excessive pesticide use, and improve the control effect of the intelligent pest and disease control system.

[0063] Please see Figures 1 to 2 The integrated risk value algorithm unit for pests and diseases is as follows:

[0064]

[0065] in:

[0066] Dir represents the overall risk value for pests and diseases:

[0067] Di represents the insect population density, which is the number of pests per square meter, and the unit is heads / ㎡;

[0068] Ta represents the ambient temperature, which is obtained in real time through a temperature sensor;

[0069] Sc represents soil electrical conductivity, which is acquired in real time via an EC sensor;

[0070] α represents an adjustment coefficient, ranging from 0.4 to 1.5, with a base value of 0.8. It can self-adjust in the calculation of the integrated pest management (IPM) algorithm unit.

[0071] In the formula calculation:

[0072] This section represents the contribution of insect population density Di to the calculated integrated pest management risk value Dir. Insect population density Di represents the number of pests per unit square meter and is the dominant influencing factor in the calculation of the integrated pest management risk value Dir, determining the fundamental quantity of the integrated pest management risk value. The constant 5 in the denominator represents the economic threshold of insect population density Di, indicating that when the number of pests per unit square meter exceeds 5, economic losses will occur to crops if no control measures are taken. When the insect population density Di is below 5... The power function of the insect population density Di has a low growth rate and contributes little to the calculated integrated pest and disease risk value Dir. When the insect population density Di is higher than 5... The high growth rate of the power function of insect population density Di in this part contributes significantly to the calculated integrated pest risk value Dir, thus reflecting the serious impact of insect population density Di on the calculation of integrated pest risk value Dir when it exceeds the economic threshold of 5.

[0073] This section uses an exponential function to reflect the contribution of ambient temperature Ta to the calculated integrated pest and disease risk value Dir. When the ambient temperature Ta equals the optimum temperature of 25℃, The calculated value of 1 for this part represents that the ambient temperature Ta is at the temperature most suitable for crop growth. For every 5°C deviation between the ambient temperature Ta and the optimal growth temperature of 25°C, ... The calculated values ​​in this part will increase exponentially, thereby increasing the calculated comprehensive risk value of pests and diseases, Dir, which is used to reflect the significant promoting effect of extreme temperatures on the occurrence of pests and diseases.

[0074] A higher soil conductivity (Sc) indicates a higher salt concentration and a more severe degree of soil salinization. Increased soil salinization reduces the disease and pest resistance of crops grown in the soil. This section represents the inhibitory effect of soil conductivity (Sc) exceeding the conductivity threshold of 20 on crop disease resistance. When the soil conductivity (Sc) is less than 25... The calculated value for this part is close to 0, indicating that when the soil conductivity Sc is low, the inhibitory effect on crop disease resistance is small, and the calculated comprehensive risk value of pests and diseases Dir is small. When the soil conductivity Sc is greater than 25, ... The calculated value for this part is close to 1, which means that when the soil conductivity Sc is high, it has a greater inhibitory effect on the disease resistance of crops, and the calculated comprehensive risk value of pests and diseases Dir is relatively large.

[0075] The formula for calculating the insect population density Di is as follows:

[0076]

[0077] in:

[0078] Di represents insect population density;

[0079] Nk represents the number of pests and diseases, which is the number of pests and diseases obtained from a single monitoring by the pest monitoring instrument.

[0080] Ak represents the monitoring area, which is the monitoring area of ​​the insect pest monitoring instrument and is obtained from the specifications of the insect pest monitoring instrument.

[0081] n represents the number of previous monitoring sessions;

[0082] In the formula calculation, the number of pests and diseases obtained by the pest monitoring instrument in one monitoring is divided by the monitoring area of ​​the pest monitoring instrument to obtain the number of pests and diseases per unit area in one monitoring. The number of pests and diseases per unit area obtained by multiple monitoring is added together and divided by the current number of monitoring n, which can obtain the averaged insect population density Di.

[0083] In this embodiment:

[0084] The integrated pest and disease risk value algorithm unit comprehensively considers multiple influencing factors such as insect population density Di, ambient temperature Ta, and soil electrical conductivity Sc to calculate the integrated pest and disease risk value Dir. By monitoring these three key indicators—insect population density Di, ambient temperature Ta, and soil electrical conductivity Sc—in real time, the intelligent crop pest and disease control system can more accurately predict the occurrence trend and risk level of pests and diseases, providing farmers with a scientific and reliable basis for prevention and control decisions. Farmers can rationally formulate prevention and control plans based on the magnitude and trend of the risk value, select appropriate prevention and control methods and agents, and avoid blind use of pesticides and over-control, thus saving prevention and control costs and protecting the ecological environment. Furthermore, the IoT-based intelligent prevention and control system can monitor and record farmland environmental data in real time. Combined with the analysis results of multiple integrated pest and disease risk values ​​Dir, the system can automatically adjust the operating parameters of prevention and control equipment, such as the spray volume and spray frequency of sprayers, to ensure the maximization of prevention and control effects. At the same time, the system can also dynamically adjust prevention and control strategies according to changes in the risk value, improving the targeting and timeliness of prevention and control.

[0085] In summary, assessing pest and disease risks by comprehensively considering environmental factors such as ambient temperature (Ta) and soil electrical conductivity (Sc) can help promote agriculture towards a more intelligent and precise direction. This can not only improve crop yield and quality, but also reduce the use of pesticides and fertilizers, reduce agricultural pollution to the environment, and promote sustainable agricultural development.

[0086] Please see Figures 1 to 2 The dosage algorithm unit is as follows:

[0087]

[0088] in:

[0089] Q represents the dosage of pesticide, expressed in liters per acre;

[0090] Qmin represents the minimum application rate, expressed in liters per acre, and is set to a fixed value of 0.2.

[0091] Qbase represents the baseline application rate, expressed in liters per acre, and is set to a fixed value of 0.5.

[0092] Qmax represents the maximum application rate, expressed in liters per acre, and is set to a fixed value of 2.0.

[0093] Dir represents the integrated risk value of pests and diseases, which is calculated by the integrated risk value algorithm unit for pests and diseases;

[0094] Pd represents the droplet deposition density, measured in drops / cm³. 2 The spraying drones are monitored and adjusted in real time through the control center.

[0095] Vd represents the drone's flight altitude, which is monitored and adjusted in real time by the drone's control center.

[0096] Di represents insect population density;

[0097] Cs represents the concentration of pathogenic spores, which is obtained in real time through a spore trapping device;

[0098] k represents the adjustment coefficient, which ranges from 0.2 to 0.5 and can self-adjust in the calculation of the dosage algorithm unit. Specifically:

[0099] In crop areas, when the pests and diseases are mainly those with a fast reproduction rate (such as aphids), the value of k should be higher (0.35-0.5) to increase the calculated amount of pesticide Q and quickly suppress the growth of the insect population.

[0100] When the pests and diseases are mainly fast-reproducing pests (such as stem borers), the value of k should be low (0.2-0.35) to reduce the calculated amount of pesticide Q and avoid pesticide waste.

[0101] μ represents the droplet efficiency coefficient, with a default value of 3. It can be self-adjusted in the calculation of the dosage algorithm unit. Specifically:

[0102] The droplet efficiency coefficient μ represents the balance between the droplet deposition density Pd per unit area and the UAV flight altitude Vd. The default value is 3. When the default value is 3, the droplet coverage uniformity (CV value) is ≤20%, which meets the requirements of precise application. The droplet efficiency coefficient μ is affected by environmental factors. When the wind speed is >3m / s, η needs to be increased by 10-20% to compensate for the droplet drift caused by the wind speed.

[0103] δ represents the insect-fungus synergy coefficient, with a default value of 800. It can be self-adjusted in the calculation of the application rate algorithm unit. Specifically:

[0104] The insect-fungus synergy coefficient δ represents the strength of the synergistic effect between insect population density Di and pathogen spore concentration Cs. According to agricultural research, the synergistic damage of pests (such as rice planthoppers) and pathogens (such as rice blast) increases non-linearly. When the insect-fungus synergy coefficient δ is set to a default value of 800, this relationship can be fitted. The insect-fungus synergy coefficient δ can be adjusted according to the sensitivity of crops to pests and diseases and the ambient temperature. For crops with high sensitivity to pests and diseases (such as rice), the insect-fungus synergy coefficient δ will be reduced by 10% to 20%. For crops with low sensitivity to pests and diseases (such as corn), the insect-fungus synergy coefficient δ will be increased by 20% to 40%. In high temperature and high humidity environments, insect and pathogen activity is enhanced, and the insect-fungus synergy coefficient δ will be reduced by 10% to 20%.

[0105] In the formula calculation:

[0106] When the integrated pest and disease risk value Dir is between 0.6 and 1.2, it means that the crops in this area are in a low-risk area for pests and diseases. The required amount of pesticide Q is calculated by the first part of the piecewise function in the pesticide application algorithm unit, Q = k × (Dir - 0.6). This means that when the pest and disease risk is low, the amount of pesticide Q increases linearly with the integrated pest and disease risk value Dir, ensuring that minimal control measures are taken even when the risk is low, thus avoiding pest accumulation.

[0107] When the integrated pest and disease risk value Dir is between 1.2 and 2.0, it indicates that crops in that area are in a medium-risk area for pests and diseases. This is determined by the second part of the piecewise function in the pesticide application rate algorithm unit. The required spraying amount Q is calculated, and the ratio obtained by dividing the droplet deposition density Pd by the drone's flight altitude Vd reflects the drone's spraying efficiency. A higher ratio indicates that the drone can spray more droplets at the same flight altitude Vd. Furthermore, the logarithmic function reflects the non-linear relationship between droplet deposition density Pd and flight altitude, enabling... When this ratio is large, compression has an excessive impact on the calculated application rate Q, while retaining... This ratio increases as a positive gain on the calculation results;

[0108] When the integrated pest and disease risk value Dir is greater than 2.0, it indicates that the crops in that area are in a high-risk area for pests and diseases. This is determined by the third part of the piecewise function in the pesticide application rate algorithm unit. The required pesticide application rate Q is calculated by taking the product of the insect population density di and the pathogen spore concentration Cs as the input to the tanh function, resulting in an output value between -1 and 1. This output value is then multiplied by the maximum application rate Qmax to obtain an application rate Q that is affected by the severity of the pests and diseases but will not increase indefinitely. Since the output value of the tanh function increases more slowly when the input value is large, it can limit the rate of increase of the application rate Q. This means that even if the severity of the pests and diseases is very high, the application rate Q will not increase indefinitely, thus avoiding the risks of overuse of pesticides.

[0109] In this embodiment:

[0110] The pesticide application algorithm unit comprehensively considers multiple factors such as the comprehensive risk value of pests and diseases (Dir), the drone flight altitude (Vd), the droplet deposition density (Pd), the insect population density (Di), and the pathogen spore concentration (Cs). This enables the intelligent pest and disease control system to calculate the optimal pesticide application rate (Q) based on the actual conditions in different risk areas. This precision application method not only improves pesticide utilization but also reduces pesticide waste and overuse, lowers the risk of pesticide pollution to soil, water, and air, and reduces the negative impact of pesticides on crops and ecosystems, thus improving the efficiency of pest and disease control. Furthermore, by optimizing the drone flight altitude (Vd) and droplet deposition density (Pd), pesticide drift and volatilization during spraying can be further reduced, thereby further reducing environmental pollution.

[0111] Precision application not only improves control efficiency but also significantly reduces pesticide costs. Because intelligent crop pest and disease control systems can manage pests and diseases intelligently based on their actual conditions, unnecessary pesticide inputs and labor costs can be reduced. Furthermore, optimizing drone flight paths and spraying strategies can further improve operational efficiency, thereby lowering overall control costs. These measures help improve the economic benefits of agricultural production and promote sustainable agricultural development. IoT-based intelligent crop pest and disease control systems, by integrating sensors, drones, and data analysis technologies, achieve real-time monitoring and precise control of pests and diseases. This intelligent management approach not only improves control efficiency and quality but also promotes agricultural modernization, providing strong scientific data support for sustainable agricultural development.

[0112] Please see Figures 1 to 2 The system optimization value algorithm unit is as follows:

[0113] Et=(Qn-Qbase)×Sc-(0.9-Dir)-100×△Ec

[0114] in:

[0115] Et represents the system's optimal value;

[0116] Qn represents the dosage for the nth application;

[0117] Qbase represents the baseline application rate, expressed in liters per acre, and is set to a fixed value of 0.5.

[0118] Sc represents soil electrical conductivity;

[0119] Dir represents the overall risk value for pests and diseases;

[0120] △Ec represents the change in chlorophyll content, which is obtained by subtracting the chlorophyll content measured after the (n-1)th application of pesticide from the chlorophyll content measured after the nth application of pesticide. The chlorophyll content is obtained by measuring chlorophyll meter. The normal range of chlorophyll content in crops is usually between 0.0005 and 0.0025.

[0121] In the calculation within the formula;

[0122] Currently, most pesticides on the market contain a certain amount of soluble salt ions or other electrolyte components. When these components are sprayed onto the soil surface or seep into the soil, they increase the ion concentration in the soil, thereby increasing the soil electrical conductivity Sc. The part (Qn-0.5)×Sc is obtained by subtracting the baseline application amount Qbase from the nth application amount Qn, and then multiplying the rate of change of application amount by the soil electrical conductivity Sc. This reflects the change in soil conditions caused by the system after adjusting the application amount Q. When the nth application amount Qn is greater than the baseline application amount Qbase, the calculated value of (Qn-0.5)×Sc will increase, indicating that as the application amount Q increases, the soil electrical conductivity Sc will also increase, and the calculated system optimization value Et will also increase.

[0123] The ideal value of the integrated pest and disease risk value Dir is 0.9. The part 0.9-Dir is the difference between the ideal value of the integrated pest and disease risk value Dir and the integrated pest and disease risk value Dir. The larger this part is, the more ideal the integrated pest and disease risk value Dir is. It means that the parameters in the intelligent pest and disease control system are good and do not need to be optimized, thus reducing the calculated system optimization value Et.

[0124] The 100×△Ec part is the system optimization value Et obtained by magnifying the change in chlorophyll content △Ec by 100 and using it as the minuend. As the change in chlorophyll content △Ec increases, it means that the crop has achieved effective pest and disease control after the pesticide application, and that the intelligent pest and disease control system is operating effectively. No parameter optimization is needed, thus reducing the calculated system optimization value Et.

[0125] In this embodiment:

[0126] The optimal system parameter value Et was calculated by comprehensively considering the integrated pest and disease risk value Dir, the change in chlorophyll content ΔEc, the change rate of pesticide application rate, and the soil electrical conductivity Sc. The optimal system parameter value Et was then compared with the previous optimal system parameter value Et. last :

[0127] When Et > Et last And |Et-Et last When |>0.2, it means that the optimized value of the system parameter Et has been significantly reduced compared to the previous calculation, indicating that the intelligent control effect of crops is good. The adjustment coefficient α in the algorithm unit for reducing the integrated pest and disease risk value is 0.8 times that of the previous calculation, so as to reduce the integrated pest and disease risk value Dir obtained in the next calculation. As the integrated pest and disease risk value Dir decreases, the amount of pesticide Q applied in the next application will also be reduced, thus reducing the application intensity and avoiding waste of pesticide solution.

[0128] When Et < Et last And |Et-Et last When | > 0.2, it means that the optimized value of the system parameter Et has increased significantly compared with the previous calculation, and the intelligent prevention and control effect of crops is poor. Increasing the value of the adjustment coefficient α in the comprehensive risk value algorithm unit of pests and diseases to 1.2 times that of the previous calculation will increase the comprehensive risk value of pests and diseases Dir obtained in the next calculation. At the same time, the amount of pesticide Q will be increased in the next calculation to increase the pesticide application intensity.

[0129] In summary, by monitoring the comprehensive risk value of pests and diseases (Et) in real time, the system can accurately determine the occurrence trend and severity of pests and diseases, and adjust the pesticide application rate (Q) in real time. This allows the intelligent pest and disease control system to dynamically adjust the pesticide application strategy, ensuring effective control in the early stages of pests and diseases, avoiding the spread of disease and excessive pesticide use. This precise control not only improves the control effect but also reduces pesticide residues and environmental pollution. Soil electrical conductivity (Sc) is an important indicator for measuring soil salinity and moisture status. By incorporating it into the calculation of system parameter optimization values, the system can monitor soil environmental conditions in real time, providing suitable soil conditions for crops. When soil electrical conductivity is abnormal, the system can adjust irrigation and fertilization strategies in a timely manner to improve soil structure and increase soil fertility, thereby promoting crop root development and nutrient absorption. Therefore, the IoT-based intelligent pest and disease control system effectively reduces the negative environmental impact of agricultural production through precise control, optimized pesticide use, and improved soil health. This helps promote the green and sustainable development of agriculture and improve the ecological and economic benefits of agricultural production.

[0130] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent crop disease and pest prevention system based on the Internet of Things, characterized in that, The application relates to a crop growth environment information collection and pesticide application data collection method. The data collection module is used for collecting crop growth environment information and pesticide application data, and the crop growth environment information specifically comprises environmental temperature Ta, soil conductivity Sc, pest quantity Nk, monitoring area Ak and chlorophyll content variation Delta Ec. The pesticide application data specifically comprises mist drop deposition density Pd and unmanned aerial vehicle flight height Vd. The data preprocessing module is used for decoding and preprocessing data information to obtain parameters for calculation in the calculation processing module. The calculation processing module comprises: The integrated risk value algorithm unit is used for calculating pest density Di as a calculation basis of the integrated risk value algorithm unit through the pest quantity Nk and the monitoring area Ak, and calculating an adjusted pest hazard integrated risk value Dir through the environmental temperature Ta and the soil conductivity Sc. The pesticide application amount algorithm unit is used for taking the pest hazard integrated risk value Dir as an input parameter and calculating three groups of different pesticide application amounts Q corresponding to different integrated risk values Dir through a segmented function. The system optimization value algorithm unit is used to input the n-th application amount Qn and the disease and pest comprehensive risk value Dir into the system optimization value algorithm unit, combine the two crop growth environment factors of chlorophyll △Ec and soil conductivity Sc, calculate the system optimization value Et, and compare the system parameter optimization value Et with the system parameter optimization value Et of the previous time last After that, the parameter adjustment in the comprehensive risk value algorithm unit is performed.

2. The crop disease and pest intelligent prevention and control system based on the Internet of Things according to claim 1, characterized in that: The crop growth environment information collection and pesticide application data collection specifically comprise: The environmental temperature Ta is monitored and obtained through a temperature sensor. The soil conductivity Sc is monitored and obtained through an EC sensor. The pest quantity Nk and the monitoring area Ak are obtained through a pest monitoring instrument. The mist drop deposition density Pd and the unmanned aerial vehicle flight height Vd are obtained through a control center of a spraying unmanned aerial vehicle. The spore concentration Cs is obtained through real-time monitoring of a spore trap. The chlorophyll content variation Delta Ec of crops is obtained through measurement of a chlorophyll meter. The mist drop deposition density Pd and the unmanned aerial vehicle flight height Vd are obtained through a control center of a spraying unmanned aerial vehicle.

3. The intelligent crop disease and pest control system based on the Internet of Things according to claim 1, characterized in that: The parameter adjustment specifically comprises: When Et>Et last , and |Et-Et last |>0.2, it represents that the system parameter optimization value Et has a significant decrease, the intelligent control effect of crops is good, and the value of the adjustment coefficient α in the disease and pest comprehensive risk value algorithm unit is 0.8 times of the value in the last calculation, so as to reduce the disease and pest comprehensive risk value Dir obtained in the next calculation. When Et < Et last , and |Et-Et last |>0.2, it represents that the system parameter optimization value Et has a significant increase, the intelligent control effect of the crop is poor, and the value of the adjustment coefficient α in the disease and pest comprehensive risk value algorithm unit is 1.2 times of the last calculation, so as to increase the disease and pest comprehensive risk value Dir obtained by the next calculation.

4. The crop disease and pest intelligent prevention and control system based on the Internet of Things according to claim 3, characterized in that: The calculation logic of the pest hazard integrated risk value algorithm unit is as follows: S11: the pest quantity Nk obtained through one-time monitoring of a pest monitoring instrument is divided by the monitoring area Ak to obtain the pest quantity in unit area at one-time monitoring, and the pest quantities in unit area obtained through multiple times of monitoring are added and then divided by the current monitoring times n to obtain the pest density Di after average processing, which is used as the calculation basis of the pest hazard integrated risk value Dir. S12: the exponential function growth characteristic is used to reflect the contribution degree of the environmental temperature Ta to the calculation result, the pest hazard integrated risk value Dir, so as to reflect the promoting effect of extreme temperature on pest occurrence. S13: the influence value of the soil conductivity Sc on the pest hazard integrated risk value Dir is scaled to the value interval of 0 to 1 through a variable form of the Sigmoid function, and the pest hazard integrated risk value Dir is increased after the soil conductivity Sc exceeds the conductivity threshold value 20, so as to reflect the inhibiting effect of crop disease resistance.

5. The crop disease and pest intelligent prevention and control system based on the Internet of Things according to claim 4, characterized in that: The influence value of the disease and pest comprehensive risk value Dir is scaled by a variant of the Sigmoid function, which retains the positive influence of the soil conductivity Sc on the disease and pest comprehensive risk value Dir when the soil conductivity Sc exceeds the conductivity threshold 20, and avoids excessive influence of the soil conductivity Sc on the disease and pest comprehensive risk value Dir when the soil conductivity Sc takes an extreme value.

6. The crop disease and pest intelligent prevention and treatment system based on the Internet of Things according to claim 4, characterized in that: The calculation logic of the pesticide application amount algorithm unit is as follows: The minimum pesticide application amount Qmin is set as a fixed value 0.2, the reference pesticide application amount Qbase is set as a fixed value 0.5, the maximum pesticide application amount Qmax is set as a fixed value 2.0, and different pesticide application amounts are calculated at different values of the disease and pest comprehensive risk value Dir by using a piecewise function, which specifically includes: S22, when the disease and pest comprehensive risk value Dir is between 0.6 and 1.2, it represents that the crops in the region are in a low-risk area of diseases and pests, and the minimum pesticide application amount Qmin is taken as the calculation basis of the pesticide application amount Q, and the disease and pest comprehensive risk value Dir is directly calculated as a linear function, when the disease and pest risk is low, the pesticide application amount Q increases linearly with the disease and pest comprehensive risk value Dir, to ensure that the minimum control measures are taken when the risk is low, and to avoid the accumulation of pests; S23, when the disease and pest comprehensive risk value Dir is between 1.2 and 2.0, it represents that the crops in the region are in a medium-risk area of diseases and pests, and the reference pesticide application amount Qbase is taken as the calculation basis of the pesticide application amount Q, the drone spraying efficiency is obtained by dividing the fog drop deposition density Pd by the drone flight height Vd, and the logarithmic function is used to reflect the influence of the drone spraying efficiency on the value of the pesticide application amount Q, which retains the positive gain of the drone spraying efficiency on the pesticide application amount Q, and compresses the excessive influence of the drone spraying efficiency on the pesticide application amount Q when the drone spraying efficiency takes an extreme value; S24, when the disease and pest comprehensive risk value Dir is greater than 2.0, it represents that the crops in the region are in a high-risk area of diseases and pests, and the maximum pesticide application amount Qmax is taken as the calculation basis of the pesticide application amount Q, the product of the pest density di and the pathogen spore concentration Cs is taken as the input of the tanh function to obtain an output value between -1 and 1, and the output value is multiplied by the maximum pesticide application amount Qmax to obtain a pesticide application amount Q that is affected by the severity of diseases and pests and will not increase indefinitely. Due to the characteristics of the tanh function, the output value grows slowly when the input value is large, to limit the increase speed of the pesticide application amount Q and avoid the risk of overuse of pesticides.

7. The crop disease and pest intelligent prevention and treatment system based on the Internet of Things according to claim 6, characterized in that: The calculation logic of the system optimization value algorithm unit is as follows: S31, subtract the reference pesticide application amount Qbase from the nth pesticide application amount Qn to obtain the change rate of the pesticide application amount, and then multiply it by the soil conductivity Sc to reflect the changes in soil conditions after adjusting the pesticide application amount Q. With the increase of the pesticide application amount Q, the soil conductivity Sc also increases, and the system optimization value Et calculated also increases. S32, the difference between the ideal value 0.9 of the disease and pest comprehensive risk value Dir and the real value of the disease and pest comprehensive risk value Dir reflects the parameter state in the crop disease and pest intelligent prevention and control system, the greater the difference, the better the parameter in the crop disease and pest intelligent prevention and control system, and the lower the system optimization value Et calculated; S33, the chlorophyll content change amount△Ec is magnified by 100 and used as the system optimization value Et calculated by subtraction correction, and with the increase of the chlorophyll content change amount△Ec, it is represented that the crop has been effectively prevented and controlled after pesticide application, and the crop disease and pest intelligent prevention and control system is effectively running, thereby reducing the system optimization value Et calculated. 8.The intelligent crop disease and pest prevention system based on the Internet of Things according to claim 1, characterized in that, The decoding preprocessing includes data cleaning and data standardization.

Images