Method and system for controlling corn yield by spraying a chemical control agent with uniformity

Abstract

The application discloses a method and system for controlling corn yield by spraying chemical control agent uniformity, and relates to the technical field of corn chemical control.The application introduces a uniformity monitoring and real-time feedback mechanism, dynamically adjusts spraying parameters according to crown density, ensures uniform coverage of the chemical control agent in the corn crown, effectively avoids local pesticide damage or poor effect caused by uneven spraying, and guarantees the chemical control effect from the source; through integration of growth data and spraying uniformity for yield prediction, scientific judgment can be made on the final yield trend in the middle growth period, which provides valuable early decision basis for corn management, helps risk avoidance and resource allocation; the optimized feedback mechanism reversely uses the yield prediction result to optimize the spraying strategy, not only realizes precise regulation and control in the current production cycle, but also accumulates a data basis for scientific planting in the next cycle, and finally achieves comprehensive benefits of controlling corn yield.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of corn regulation and control, in particular to a method and system for controlling corn yield by spraying a regulation and control agent uniformly. BACKGROUND

[0002] Corn regulation and control technology is a key agronomic measure for regulating plant growth and improving yield. The effect evaluation of traditional spraying operations is often lagging, which cannot provide timely and effective decision support for the current production, and it is difficult to form a closed-loop management. This not only causes waste of agricultural chemicals, but also cannot guarantee the full play of the yield-increasing potential of regulation and control technology, restricting the refinement and benefit improvement of corn planting.

[0003] The prior art, such as the planting method for improving corn yield disclosed in the patent application for invention with publication number CN113229074A, includes seed selection, selection of high-yield, high-quality, disease-resistant and highly adaptable varieties according to local ecological environment conditions, selection of coated seeds with large, full, non-molded, non-damaged and uniform seeds; soil treatment, soil fertilization of the selected planting site soil, and soil disinfection after fertilization; preparation before sowing, leveling and applying base fertilizer to the treated soil in S2; sowing, timely sowing according to local climate and corn varieties; field management, reasonable watering and fertilization on the basis of uniform, uniform and strong seedlings, reasonable fertilization and watering at the large trumpet stage, and appropriate application of seedling fertilizer and grain fertilizer, to promote the healthy growth of corn by reasonable control of fertilizer and water.

[0004] For the above-mentioned scheme, the inventors of the present application found that the above-mentioned technology at least has the following technical problems:

[0005] 1. There is currently a lack of a comprehensive "uniformity coefficient", which does not integrate the actual spraying amount, crown structure density and preset weight parameters, and only measures the deposition amount of liquid medicine in a unit area; there is a lack of introduction of crown density weight, which cannot identify the "hidden" uneven problems of excessive amount in sparse places and insufficient amount in dense places, cannot make the state judgment closer to the real demand, cannot avoid misjudgment, and cannot provide data support for fine adjustment.

[0006] 2. Currently, there is a lack of a closed-loop real-time control mechanism based on uniformity deviation values. This mechanism cannot automatically diagnose the root causes of unevenness, nor can it accurately control the execution mechanism. Without real-time fine-tuning, it cannot continuously maintain the spraying uniformity within the optimal threshold range, thus failing to ensure that the chemical control agent exerts a consistent and reliable effect across the entire field and cannot avoid regional differences in the effect. Furthermore, the quality of spraying operations is not included as one of the core input variables in the yield prediction model. This model does not break the limitations of traditional yield prediction that relies solely on static data such as climate, soil, and variety. It also fails to incorporate human-controllable management factors into the model, making the prediction results less comprehensive and accurate. It is also unable to predict the potential trend of the final yield based on the current spraying quality during the mid-growth stage. Summary of the Invention

[0007] To address the aforementioned technical shortcomings, the purpose of this application is to provide a method and system for controlling corn yield by ensuring uniformity of chemical control agent application.

[0008] To solve the above-mentioned technical problems, this application adopts the following technical solution: In the first aspect, this application provides a method for controlling the yield of corn by controlling the uniformity of chemical control agent spraying. The method includes the following steps: Step 1, spraying parameter preset: Based on the corn basic data, preset the chemical control agent type, target spraying amount, uniformity threshold and canopy density weight parameters, and then generate an initial spraying instruction;

[0009] Step 2, Uniformity Monitoring: Based on the uniformity threshold, canopy density weighting parameter, pre-acquired chemical control agent application amount and canopy density data, the uniformity coefficient is calculated, and then the spraying uniformity status is determined.

[0010] Step 3: Spraying Adjustment: When the spraying uniformity is abnormal, analyze the uniformity deviation value to adjust the operating parameters of the spraying device.

[0011] Step 4: Yield Forecasting: Based on the pre-acquired maize growth data and uniformity coefficient, analyze and generate yield forecasting coefficients, and then predict the maize yield trend.

[0012] Step 5: Optimize Feedback: Based on the yield prediction coefficient, optimize the spraying strategy, generate updated spraying instructions, and transmit them to the spraying device.

[0013] Preferably, the initial spraying instruction includes spraying rate, coverage area, and canopy correction flag.

[0014] Preferably, generating the initial spraying command includes:

[0015] Based on the target spraying amount and uniformity threshold, the spraying rate is calculated to obtain the spraying rate; based on the canopy density weight parameter, the coverage area is determined to obtain the coverage area; based on the canopy density weight parameter and uniformity threshold, a canopy correction flag is generated to obtain the canopy correction flag; the spraying rate, coverage area, and canopy correction flag are recorded as the initial spraying command; and then the spraying device is initialized based on the initial spraying command.

[0016] Preferably, the step of calculating the corrected uniformity coefficient based on the uniformity threshold, canopy density weighting parameter, pre-acquired chemical control agent application rate, and canopy density data includes:

[0017] The formula for calculating the uniformity coefficient derive the uniformity coefficient ,in This is represented by the number corresponding to the sampling point. , This represents the total number of sampling points. Represented as the first The amount of chemical control agent sprayed at each sampling point This represents the average amount of chemical control agent applied. Represented as the first Canopy density data from each sampling point This is expressed as the average value of the canopy density data. It is represented as the canopy density weighting parameter.

[0018] Preferably, determining the spray uniformity includes:

[0019] The uniformity coefficient is compared with the uniformity coefficient threshold. When the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, the spraying uniformity is determined to be uniform, and step four is performed. When the uniformity coefficient is less than the uniformity coefficient threshold, the spraying uniformity is determined to be abnormal, and step three is performed.

[0020] Preferably, when the spray uniformity is abnormal, analyzing the uniformity deviation value to adjust the operating parameters of the spraying device includes:

[0021] When the spray uniformity is abnormal, the deviation value is calculated based on the uniformity coefficient and the uniformity coefficient threshold to obtain the uniformity deviation value; based on the uniformity deviation value, the adjustment amount of the working parameters is calculated to obtain the adjustment amount of the spraying rate and the adjustment amount of the coverage area; based on the adjustment amount of the spraying rate and the adjustment amount of the coverage area, the working parameters of the spraying device are adjusted.

[0022] Preferably, the corn growth data includes leaf area index and plant height data.

[0023] Preferably, the step of analyzing and generating yield prediction coefficients based on pre-acquired maize growth data and uniformity coefficients, and then predicting maize yield trends, includes:

[0024] The leaf area index and plant height data in the maize growth data are normalized to obtain normalized growth data; based on the normalized growth data and the corrected evenness coefficient, a weighted fusion calculation is performed to obtain the yield prediction coefficient; based on the yield prediction coefficient, a trend classification operation is performed to obtain the maize yield trend.

[0025] Preferably, the weighted fusion calculation to obtain the yield prediction coefficient, and the trend classification operation based on the yield prediction coefficient to obtain the corn yield trend, includes:

[0026] A1. Calculation formula based on weighted fusion derive the production prediction coefficient , Expressed as normalized leaf area index, Expressed as normalized plant height, This is expressed as the uniformity coefficient. , and These are respectively represented as the weighting factors corresponding to the normalized leaf area index, the weighting factors corresponding to the normalized plant height, and the weighting factors corresponding to the evenness coefficient.

[0027] A2. Threshold comparison formula for trend classification operation To determine the corn yield trend ,in This represents the upper limit of the production prediction coefficient threshold. This represents the lower limit of the threshold for the production prediction coefficient.

[0028] In a second aspect, this application provides a system for controlling maize yield by the uniformity of chemical control agent spraying, comprising: a spraying parameter preset module, which presets chemical control agent type, target spraying amount, uniformity threshold and canopy density weight parameters based on maize basic data, and then generates an initial spraying instruction;

[0029] The uniformity monitoring module calculates the uniformity coefficient based on the uniformity threshold, canopy density weight parameter, pre-acquired chemical control agent spraying amount and canopy density data, and then judges the spraying uniformity status.

[0030] The spraying adjustment module analyzes and calculates the uniformity deviation value when the spraying uniformity is abnormal, so as to adjust the working parameters of the spraying device.

[0031] The yield prediction module analyzes and generates yield prediction coefficients based on pre-acquired corn growth data and uniformity coefficients, thereby predicting corn yield trends.

[0032] The optimization feedback module optimizes the spraying strategy based on the yield prediction coefficient, generates updated spraying instructions, and transmits them to the spraying device.

[0033] The beneficial effects of this application are as follows:

[0034] 1. This application provides a method and system for controlling maize yield by adjusting the uniformity of chemical control agent spraying. By introducing a uniformity monitoring and real-time feedback mechanism, the spraying parameters are dynamically adjusted according to the canopy density to ensure uniform coverage of the chemical control agent in the maize canopy. This effectively avoids local phytotoxicity or poor efficacy caused by uneven spraying, thus guaranteeing the effectiveness of chemical control from the source. By integrating growth data and spray uniformity for yield prediction, a scientific judgment on the final yield trend can be made in the mid-growth stage, providing valuable early decision-making basis for maize management and assisting in risk avoidance and resource allocation. The optimized feedback mechanism uses the yield prediction results to optimize the spraying strategy, achieving precise control not only within the current production cycle but also accumulating a data foundation for scientific planting in the next cycle, ultimately achieving comprehensive benefits in controlling maize yield.

[0035] 2. This application constructs a multi-factor fusion intelligent initial decision-making model, which changes the traditional extensive setting method based on experience or single crop growth stage, making the initial spraying instructions more scientific and forward-looking, laying the foundation for precise control and improving resource utilization efficiency; it defines a comprehensive "uniformity coefficient", which integrates the actual spraying amount, canopy structure density and preset weight parameters, rather than just measuring the amount of pesticide deposited per unit area; by introducing canopy density weight, it can identify "hidden" unevenness problems such as excessive spraying in sparse areas and insufficient spraying in dense areas, making the state judgment closer to the actual needs, avoiding misjudgment, and providing data support for fine-tuning.

[0036] 3. This application establishes a closed-loop real-time control mechanism based on uniformity deviation values. The system can automatically diagnose the root causes of unevenness (such as travel speed, pressure, nozzle switching, etc.) and precisely control the actuator. Through real-time fine-tuning, it can continuously maintain the spraying uniformity within the optimal threshold range, ensuring that the chemical control agent exerts a consistent and reliable effect throughout the entire field, avoiding regional differences in effect. By using the spraying operation quality (uniformity coefficient) as one of the core input variables of the yield prediction model, a quantitative correlation between agricultural operation quality and final yield is established. This breaks the limitations of traditional yield prediction that relies solely on static data such as climate, soil, and variety. By incorporating human-controllable management factors into the model, the prediction results become more comprehensive and accurate. The potential trend of final yield can be predicted based on the current spraying quality during the mid-growth stage, providing managers with valuable early warning and intervention opportunities.

[0037] 4. This application constructs a "strategy self-evolution" system that spans the production cycle. By using the output prediction of the current operation, it reverse-optimizes the input strategy for the next operation; it not only completes the task of a single operation, but also learns from historical data, continuously iterating and optimizing its own decision-making logic, making the spraying strategy increasingly accurate and efficient. It connects the various links of "pre-setting - execution - monitoring - prediction" into a self-improving life cycle, greatly enhancing the technical level and sustainability of the entire corn management system. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating the steps involved in implementing the method described in this application.

[0040] Figure 2 This is a schematic diagram of the system structure connection of this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] Please see Figure 1 As shown, this application provides a method for controlling corn yield by adjusting the uniformity of chemical control agent spraying in a first aspect, comprising:

[0043] Step 1: Preset spraying parameters: Based on the basic data of corn, preset the chemical control agent type, target spraying amount, uniformity threshold and canopy density weight parameters, and then generate the initial spraying instruction;

[0044] In one specific instance, the initial spraying instructions include spraying rate, coverage area, and canopy correction flag.

[0045] In one specific instance, generating the initial spraying command includes:

[0046] Based on the target spraying amount and uniformity threshold, the spraying rate is calculated to obtain the spraying rate; based on the canopy density weight parameter, the coverage area is determined to obtain the coverage area; based on the canopy density weight parameter and uniformity threshold, a canopy correction flag is generated to obtain the canopy correction flag; the spraying rate, coverage area, and canopy correction flag are recorded as the initial spraying command; and then the spraying device is initialized based on the initial spraying command.

[0047] It should be noted that the preset chemical control agent type refers to selecting an appropriate type of chemical regulator, such as a herbicide or growth regulator, based on the corn's growth stage and pest and disease risk to ensure targeted and effective spraying. The target spraying amount is the amount of chemical agent required per unit area, usually expressed in liters per hectare, used to ensure the economic and environmental friendliness of the spraying. The uniformity threshold is the upper limit of the allowable uniformity deviation during spraying, used to control spraying quality and avoid localized over- or under-application. The canopy density weighting parameter is a weighted value reflecting the density of the corn canopy structure, used to adjust spraying parameters to adapt to canopy characteristics and improve spraying accuracy.

[0048] It should be noted that the spraying rate calculation refers to the calculation based on the target spraying amount using a formula. Calculate the spraying rate ,in This represents the target spraying amount. Indicated as coverage area, This indicates the spraying time. It is expressed as a calibration coefficient; further, the spraying rate is the volume of chemical agent sprayed per unit time, used to control the output flow of the spraying device to ensure spraying uniformity and efficiency.

[0049] It should be noted that determining the coverage area refers to calculating it based on the canopy density weighting parameter using a formula. Determine the coverage area ,in Represented as a canopy density weighting parameter, This refers to the base coverage area; further, the coverage range is the corn canopy area covered by the spraying device in a single operation, used to optimize spraying distribution and reduce resource waste.

[0050] It should be noted that when generating the canopy correction flag, the process determines whether spraying parameters need to be adjusted to address canopy inhomogeneity. This determination is based on a comparison between the canopy density weight parameter and the uniformity threshold. Specifically, when the canopy density weight parameter is greater than or equal to the uniformity threshold, a binary flag of 1 is generated, indicating that canopy adaptive adjustment is enabled; otherwise, a flag of 0 is generated, indicating that canopy adaptive adjustment is not enabled. Further, the comparison process calculates the difference between the canopy density weight parameter and the uniformity threshold, and is implemented based on preset rules (e.g., adjustment is enabled if the difference exceeds zero). This ensures that spraying parameters are automatically adjusted when the canopy structure is complex or inhomogeneous, thereby improving spraying uniformity.

[0051] It should be noted that generating the initial spraying command refers to combining the spraying rate, coverage area, and canopy correction flags into a control command to guide the initial setup of the spraying device. Furthermore, the initial spraying command is a dataset containing key spraying parameters used to initialize the operating status of the spraying device, thereby improving spraying accuracy and automation.

[0052] It should be noted that initializing the spraying device refers to setting the operating parameters of the spraying device according to the initial spraying command, such as setting the nozzle pressure value, to ensure the spraying rate and coverage. Furthermore, the nozzle pressure value is a key operating parameter of the spraying device, which directly affects the spraying atomization effect and distribution uniformity. For example, setting the nozzle pressure value to 0.3MPa can ensure basic spraying performance.

[0053] Step 2, Uniformity Monitoring: Based on the uniformity threshold, canopy density weighting parameter, pre-acquired chemical control agent application amount and canopy density data, the uniformity coefficient is calculated, and then the spraying uniformity status is determined.

[0054] In a specific example, the calculation of the corrected uniformity coefficient based on the uniformity threshold, canopy density weighting parameter, pre-acquired chemical control agent application rate, and canopy density data includes:

[0055] The formula for calculating the uniformity coefficient derive the uniformity coefficient ,in This is represented by the number corresponding to the sampling point. , This represents the total number of sampling points. Represented as the first The amount of chemical control agent sprayed at each sampling point This represents the average amount of chemical control agent applied. Represented as the first Canopy density data from each sampling point This is expressed as the average value of the canopy density data. It is represented as the canopy density weighting parameter.

[0056] It should be noted that the amount of chemical control agent sprayed reflects the local distribution of the spraying, and its unit is usually liters per hectare, obtained through sampling devices; the average amount of chemical control agent sprayed represents the overall spraying level, used to standardize the local spraying amount and avoid evaluation bias caused by differences in absolute amount; the canopy density data is obtained through image analysis technology, reflecting the density of the corn canopy, which affects the penetration and distribution efficiency of chemical control agents in the canopy; the average amount of canopy density data represents the overall canopy density level, used to balance the impact of local canopy variations on uniformity calculations.

[0057] In a specific example, determining the spray uniformity status includes:

[0058] The uniformity coefficient is compared with the uniformity coefficient threshold. When the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, the spraying uniformity is determined to be uniform, and step four is performed. When the uniformity coefficient is less than the uniformity coefficient threshold, the spraying uniformity is determined to be abnormal, and step three is performed.

[0059] It should be noted that the uniformity coefficient threshold is a preset uniformity standard used to determine whether the spraying meets the standard, and its value is set based on the target yield requirement.

[0060] This application constructs a multi-factor fusion intelligent initial decision-making model, which changes the traditional extensive setting method based on experience or single crop growth stage, making the initial spraying instructions more scientific and forward-looking, laying the foundation for precise control and improving resource utilization efficiency. It defines a comprehensive "uniformity coefficient", which integrates the actual spraying amount, canopy structure density and preset weight parameters, rather than just measuring the amount of pesticide deposited per unit area. By introducing canopy density weight, it can identify "hidden" unevenness problems such as excessive spraying in sparse areas and insufficient spraying in dense areas, making the state judgment closer to the actual needs, avoiding misjudgment, and providing data support for fine-tuning.

[0061] Step 3: Spraying Adjustment: When the spraying uniformity is abnormal, analyze the uniformity deviation value to adjust the operating parameters of the spraying device.

[0062] In a specific example, when the spray uniformity is abnormal, analyzing the uniformity deviation value to adjust the operating parameters of the spraying device includes:

[0063] When the spray uniformity is abnormal, the deviation value is calculated based on the uniformity coefficient and the uniformity coefficient threshold to obtain the uniformity deviation value; based on the uniformity deviation value, the adjustment amount of the working parameters is calculated to obtain the adjustment amount of the spraying rate and the adjustment amount of the coverage area; based on the adjustment amount of the spraying rate and the adjustment amount of the coverage area, the working parameters of the spraying device are adjusted.

[0064] It should be noted that the deviation value is calculated by comparing the difference between the uniformity coefficient and the uniformity coefficient threshold using a mathematical expression. First, the uniformity coefficient is subtracted from the uniformity coefficient threshold, and the difference obtained is the uniformity deviation. Furthermore, the uniformity deviation quantifies the degree of insufficient spray uniformity. When the uniformity deviation value is positive, it indicates that the actual uniformity is lower than the standard, and compensation needs to be made by adjusting the working parameters.

[0065] It should be noted that the calculation of the working parameter adjustment amounts includes: The working parameter adjustment amounts are calculated based on the uniformity deviation value, and the adjustment range of the spraying rate and coverage area is determined through proportional control calculations; the uniformity deviation value is multiplied by the spraying rate gain coefficient to obtain the spraying rate adjustment amount; the uniformity deviation value is multiplied by the coverage area gain coefficient to obtain the coverage area adjustment amount. These adjustment amounts are used to guide the modification of the working parameters of the spraying device to compensate for insufficient uniformity; furthermore, the spraying rate gain coefficient and the coverage area gain coefficient are preset adjustment sensitivity parameters, optimized based on historical spraying data, used to map the uniformity deviation value to the actual change in working parameters.

[0066] It should be noted that the operating parameters of the spraying device are adjusted as follows: The adjustment of the operating parameters is based on the adjustment amount of the spraying rate and the adjustment amount of the coverage area. The current spraying rate and coverage area settings of the spraying device are modified. The specific adjustment process is as follows: the spraying rate value is updated to the original spraying rate plus the spraying rate adjustment amount, and the coverage area value is updated to the original coverage area plus the coverage area adjustment amount. Furthermore, adjusting the operating parameters of the spraying device can improve the uniformity of the distribution of the chemical control agent in the corn canopy by increasing the spraying rate or expanding the coverage area. For example, when the uniformity deviation value is large, the spraying rate is increased to enhance the atomization effect, or the coverage area is expanded to reduce the missed areas, thereby correcting the problem of uneven spraying.

[0067] Step 4: Yield Forecasting: Based on the pre-acquired maize growth data and uniformity coefficient, analyze and generate yield forecasting coefficients, and then predict the maize yield trend.

[0068] In one specific example, the maize growth data includes leaf area index and plant height data.

[0069] It should be noted that pre-acquiring maize growth data refers to collecting leaf area index (LAI) and plant height data of maize through field sensors. This data is used to characterize the maize canopy structure and growth status, providing a basic input for subsequent yield prediction. The LAI is the ratio of the total area of ​​maize leaves per unit surface area to the surface area, reflecting the density of the canopy and photosynthetic potential. A higher LAI indicates a denser canopy and higher light energy utilization. Plant height data is the vertical height of the maize plant from the ground to its highest point, used to indicate the growth stage and biomass accumulation.

[0070] In a specific example, the step of analyzing and generating yield prediction coefficients based on pre-acquired maize growth data and uniformity coefficients, and then predicting maize yield trends, includes:

[0071] The leaf area index and plant height data in the maize growth data are normalized to obtain normalized growth data; based on the normalized growth data and the corrected evenness coefficient, a weighted fusion calculation is performed to obtain the yield prediction coefficient; based on the yield prediction coefficient, a trend classification operation is performed to obtain the maize yield trend.

[0072] It should be noted that normalization transforms the leaf area index (LAI) and plant height data linearly to the [0,1] interval to eliminate the influence of dimensional differences and numerical ranges, facilitating subsequent analysis on a uniform scale. First, the LAI and plant height values ​​are extracted from the original growth data. Then, the normalized value of each feature is calculated by subtracting the minimum value of the feature from the original value and dividing by the difference between the maximum and minimum values. Finally, normalized growth data within the [0,1] range is obtained.

[0073] In a specific example, the weighted fusion calculation to obtain the yield prediction coefficient; and the trend classification operation based on the yield prediction coefficient to obtain the corn yield trend, including:

[0074] A1. Calculation formula based on weighted fusion derive the production prediction coefficient , Expressed as normalized leaf area index, Expressed as normalized plant height, This is expressed as the uniformity coefficient. , and These are respectively represented as the weighting factors corresponding to the normalized leaf area index, the weighting factors corresponding to the normalized plant height, and the weighting factors corresponding to the evenness coefficient.

[0075] It should be noted that, , , , We obtained the weight factors corresponding to the normalized leaf area index, the normalized plant height, and the evenness coefficient through factor analysis. First, we condensed the information of the normalized leaf area index, the normalized plant height, and the evenness coefficient, and then obtained the variance explained after rotation. We obtained the weights by dividing the cumulative variance explained.

[0076] It should be noted that factor analysis is a well-known technique. It is a multivariate statistical analysis method that starts by studying the internal dependencies of variables and reduces some variables with complex relationships to a few comprehensive factors. Information condensation is expressed as the calculation of the median. The variance explained rate is the amount of information extracted by the factors. Variance explained rate = eigenvalues ​​ / total number of analysis terms. The rotated variance explained rate is expressed as the variance explained by the factors after maximum variance rotation.

[0077] Furthermore, the essence of weighted fusion calculation is to perform parallel multiplication and addition operations through embedded arithmetic units, complete the fusion of multiple data sources within a single clock cycle, and generate a comprehensive yield index. The yield prediction coefficient is a scalar value output by weighted fusion calculation, used to quantify the potential level of maize yield. The higher the value, the greater the yield potential. It integrates the influence of canopy growth status and spray uniformity on yield, and its role is to provide standardized input for trend prediction.

[0078] A2. Threshold comparison formula for trend classification operation To determine the corn yield trend ,in This represents the upper limit of the production prediction coefficient threshold. This represents the lower limit of the threshold for the production prediction coefficient.

[0079] It should be noted that the corn yield trend is the classification result output by the trend classification operation, which is used to indicate the direction of future yield changes. Its physical meaning is the yield dynamics predicted based on the current growth and spraying data, and its function is to provide a decision-making basis for optimizing spraying strategies.

[0080] This application establishes a closed-loop real-time control mechanism based on uniformity deviation values. The system can automatically diagnose the root causes of unevenness (such as travel speed, pressure, nozzle switching, etc.) and precisely control the actuator. Through real-time fine-tuning, it can continuously maintain the spraying uniformity within the optimal threshold range, ensuring that the chemical control agent exerts a consistent and reliable effect throughout the entire field, avoiding regional differences in effect. By using the spraying operation quality (uniformity coefficient) as one of the core input variables of the yield prediction model, a quantitative correlation between agricultural operation quality and final yield is established. This breaks through the limitations of traditional yield prediction that relies solely on static data such as climate, soil, and variety, and incorporates human-controllable management factors into the model, making the prediction results more comprehensive and accurate. The potential trend of final yield can be predicted based on the current spraying quality during the mid-growth stage, providing managers with valuable early warning and intervention opportunities.

[0081] Step 5: Optimize Feedback: Based on the yield prediction coefficient, optimize the spraying strategy, generate updated spraying instructions, and transmit them to the spraying device.

[0082] It should be noted that, based on the yield prediction coefficient, optimizing the spraying strategy, generating an updated spraying instruction, and transmitting it to the spraying device includes: calculating the optimization deviation based on the yield prediction coefficient and a preset yield prediction coefficient threshold to obtain an optimization deviation value; calculating the spraying parameter adjustment amount based on the optimization deviation value to obtain the spraying rate adjustment amount and the coverage adjustment amount; adjusting the spraying rate and coverage in the initial spraying instruction based on the spraying rate adjustment amount and the coverage adjustment amount to obtain an updated spraying instruction; and transmitting the updated spraying instruction to the spraying device.

[0083] It should be noted that the optimization deviation calculation is performed by comparing the difference between the yield prediction coefficient and the yield prediction coefficient threshold. The specific calculation process is as follows: the optimization deviation value equals the yield prediction coefficient threshold minus the yield prediction coefficient, where the yield prediction coefficient threshold is a preset standardized yield potential reference value used to define whether the yield prediction meets the standard; further, a positive optimization deviation value indicates that the actual yield prediction is lower than the standard, and compensation needs to be made by adjusting the spraying strategy; a negative optimization deviation value indicates that the yield prediction meets or exceeds the standard, and no adjustment is needed; furthermore, the optimization deviation value is a scalar value output by the optimization deviation calculation, used to indicate the deviation range between the yield prediction and the standard, representing the insufficient yield potential, and its function is to provide quantitative input for adjusting spraying parameters, ensuring that the optimization of the spraying strategy is highly targeted.

[0084] It should be noted that the calculation of spraying parameter adjustment amounts is based on the optimization deviation value. The adjustment range of spraying rate and coverage area is determined through proportional control calculation. The specific calculation formula is as follows: the spraying rate adjustment amount equals the optimization deviation value multiplied by the spraying rate optimization gain coefficient, and the coverage area adjustment amount equals the optimization deviation value multiplied by the coverage area optimization gain coefficient. Among them, the spraying rate optimization gain coefficient and the coverage area optimization gain coefficient are preset adjustment sensitivity parameters, which are optimized based on historical spraying data and are used to map the optimization deviation value to the actual change in spraying parameters. Furthermore, the spraying rate adjustment amount is a scalar value output from the spraying parameter adjustment amount calculation, representing the increase or decrease in the spraying rate, which is the adjustment range of the sprayed volume per unit time. Its function is to compensate for insufficient yield potential by changing the spraying rate. The coverage area adjustment amount is another scalar value output from the spraying parameter adjustment amount calculation, representing the expansion or contraction of the coverage area, which is the adjustment range of the sprayed area. Its function is to optimize the distribution of chemical control agents by adjusting the coverage area, thereby improving spraying uniformity and efficiency.

[0085] It should be noted that the adjustments to the spraying rate and coverage area in the initial spraying command are based on the spraying rate adjustment and coverage area adjustment amounts. The parameter values ​​of the initial spraying command are modified through arithmetic addition. Specifically, the updated spraying rate equals the initial spraying rate plus the spraying rate adjustment amount, and the updated coverage area equals the initial coverage area plus the coverage area adjustment amount. The initial spraying rate and initial coverage area originate from the initial spraying command generated in step one. Furthermore, the adjustment process achieves dynamic optimization of the spraying command through data update operations, ensuring that the spraying parameters are adapted in real-time to yield prediction deviations. Updating the spraying rate and updating the coverage area are used to generate more accurate spraying control signals to improve the distribution effect of the chemical regulator in the maize canopy.

[0086] It should be noted that the updated spraying command is a dataset of control commands that adjusts the operation output. It includes updated spraying rate and coverage parameters and is a concrete representation of the optimized spraying strategy. Its purpose is to provide real-time control guidance for the spraying device and improve spraying accuracy and yield responsiveness.

[0087] It should be noted that transmitting the updated spraying command to the spraying device is done via a wireless communication protocol, sending the updated spraying command to the control unit of the spraying device to achieve remote updating and execution of the command. Furthermore, the transmission process relies on data encapsulation and transmission operations to ensure the integrity and real-time nature of the command. The result of the transmission operation is that the updated spraying command is received and parsed by the spraying device, which is the implementation of the optimization strategy. Its function is to directly affect the chemical control agent spraying process by adjusting the operating parameters of the spraying device, ultimately improving corn yield and resource utilization efficiency.

[0088] This application constructs a "strategy self-evolution" system that spans the production cycle. By using the output prediction of the current operation, it reverse-optimizes the input strategy for the next operation; it not only completes the task of a single operation, but also learns from historical data, continuously iterating and optimizing its own decision-making logic, making the spraying strategy increasingly accurate and efficient. It links the various links of "pre-setting - execution - monitoring - prediction" into a self-improving life cycle, greatly enhancing the technical level and sustainability of the entire corn management system.

[0089] Please see Figure 2 As shown, in a second aspect, this application provides a system for a method of controlling corn yield by spraying a chemical control agent to ensure uniformity.

[0090] The system 100 of the method for controlling corn yield by uniformity of chemical control agent spraying according to the present invention can be installed in an electronic device. Depending on the functions implemented, the system 100 may include a spraying parameter preset module 101, a uniformity monitoring module 102, a spraying adjustment module 103, a yield prediction module 104, and an optimization feedback module. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0091] In this embodiment, the functions of each module / unit are as follows: The spraying parameter preset module presets the chemical control agent type, target spraying amount, uniformity threshold and canopy density weight parameters based on the corn basic data, and then generates the initial spraying instruction;

[0092] The uniformity monitoring module calculates the uniformity coefficient based on the uniformity threshold, canopy density weight parameter, pre-acquired chemical control agent spraying amount and canopy density data, and then judges the spraying uniformity status.

[0093] The spraying adjustment module analyzes and calculates the uniformity deviation value when the spraying uniformity is abnormal, so as to adjust the working parameters of the spraying device.

[0094] The yield prediction module analyzes and generates yield prediction coefficients based on pre-acquired corn growth data and uniformity coefficients, thereby predicting corn yield trends.

[0095] The optimization feedback module optimizes the spraying strategy based on the yield prediction coefficient, generates updated spraying instructions, and transmits them to the spraying device.

[0096] This application provides a method and system for controlling maize yield by adjusting the uniformity of chemical control agent spraying. By introducing a uniformity monitoring and real-time feedback mechanism, the spraying parameters are dynamically adjusted according to the canopy density to ensure uniform coverage of the chemical control agent in the maize canopy. This effectively avoids localized phytotoxicity or poor efficacy caused by uneven spraying, thus guaranteeing the effectiveness of chemical control from the source. By integrating growth data and spray uniformity for yield prediction, a scientific judgment on the final yield trend can be made in the mid-growth stage, providing valuable early decision-making basis for maize management and assisting in risk avoidance and resource allocation. The optimized feedback mechanism uses the yield prediction results to optimize the spraying strategy, achieving precise control not only within the current production cycle but also accumulating a data foundation for scientific planting in the next cycle, ultimately achieving comprehensive benefits in controlling maize yield.

[0097] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0098] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0100] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0101] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for controlling corn yield by adjusting the uniformity of chemical control agent application, characterized in that, include: Step 1: Preset spraying parameters: Based on the basic data of corn, preset the chemical control agent type, target spraying amount, uniformity threshold and canopy density weight parameters, and then generate the initial spraying instruction; Step 2, Uniformity Monitoring: Based on the uniformity threshold, canopy density weighting parameter, pre-acquired chemical control agent application amount and canopy density data, the uniformity coefficient is calculated, and then the spraying uniformity status is determined. The corrected uniformity coefficient is calculated based on the uniformity threshold, canopy density weighting parameter, pre-acquired chemical control agent application rate, and canopy density data, including: The formula for calculating the uniformity coefficient derive the uniformity coefficient ,in This is represented by the number corresponding to the sampling point. , This represents the total number of sampling points. Represented as the first The amount of chemical control agent sprayed at each sampling point This represents the average amount of chemical control agent applied. Represented as the first Canopy density data from each sampling point This is expressed as the average value of the canopy density data. Represented as a canopy density weighting parameter; Step 3: Spraying Adjustment: When the spraying uniformity is abnormal, analyze the uniformity deviation value to adjust the operating parameters of the spraying device. Step 4: Yield Forecasting: Based on the pre-acquired maize growth data and uniformity coefficient, analyze and generate yield forecasting coefficients, and then predict the maize yield trend. Step 5: Optimize Feedback: Based on the yield prediction coefficient, optimize the spraying strategy, generate updated spraying instructions, and transmit them to the spraying device.

2. The method for controlling corn yield by spraying a chemical control agent according to claim 1, characterized in that, The initial spraying instructions include spraying rate, coverage area, and canopy correction flag.

3. The method for controlling corn yield by uniformity of chemical control agent spraying according to claim 1, characterized in that, The generation of the initial spraying command includes: Based on the target spraying amount and uniformity threshold, the spraying rate is calculated to obtain the spraying rate; based on the canopy density weight parameter, the coverage area is determined to obtain the coverage area; based on the canopy density weight parameter and uniformity threshold, a canopy correction flag is generated to obtain the canopy correction flag; the spraying rate, coverage area, and canopy correction flag are recorded as the initial spraying command; and then the spraying device is initialized based on the initial spraying command.

4. The method for controlling corn yield by uniformity of chemical control agent spraying according to claim 1, characterized in that, The determination of spray uniformity includes: The uniformity coefficient is compared with the uniformity coefficient threshold. When the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, the spraying uniformity is determined to be uniform, and step four is performed. When the uniformity coefficient is less than the uniformity coefficient threshold, the spraying uniformity is determined to be abnormal, and step three is performed.

5. The method for controlling corn yield by uniformity of chemical control agent spraying according to claim 1, characterized in that, When the spray uniformity is abnormal, the uniformity deviation value is analyzed to adjust the operating parameters of the spraying device, including: When the spray uniformity is abnormal, the deviation value is calculated based on the uniformity coefficient and the uniformity coefficient threshold to obtain the uniformity deviation value; based on the uniformity deviation value, the adjustment amount of the working parameters is calculated to obtain the adjustment amount of the spraying rate and the adjustment amount of the coverage area; based on the adjustment amount of the spraying rate and the adjustment amount of the coverage area, the working parameters of the spraying device are adjusted.

6. The method for controlling corn yield by spraying a chemical control agent according to claim 1, characterized in that, The corn growth data includes leaf area index and plant height data.

7. The method for controlling corn yield by uniformity of chemical control agent spraying according to claim 1, characterized in that, The process of analyzing and generating yield prediction coefficients based on pre-acquired maize growth data and uniformity coefficients, and then predicting maize yield trends, includes: The leaf area index and plant height data in the maize growth data are normalized to obtain normalized growth data; based on the normalized growth data and the corrected evenness coefficient, a weighted fusion calculation is performed to obtain the yield prediction coefficient; based on the yield prediction coefficient, a trend classification operation is performed to obtain the maize yield trend.

8. A method for controlling corn yield by uniformity of chemical control agent application according to claim 7, characterized in that, The weighted fusion calculation is performed to obtain the production prediction coefficient; Based on the yield prediction coefficient, a trend classification operation is performed to obtain the corn yield trend, including: A1. Calculation formula based on weighted fusion derive the production prediction coefficient , Expressed as normalized leaf area index, Expressed as normalized plant height, This is expressed as the uniformity coefficient. , and These are respectively represented as the weighting factors corresponding to the normalized leaf area index, the weighting factors corresponding to the normalized plant height, and the weighting factors corresponding to the evenness coefficient. A2. Threshold comparison formula for trend classification operation To determine the corn yield trend ,in This represents the upper limit of the production prediction coefficient threshold. This represents the lower limit of the threshold for the production prediction coefficient.

9. A system for implementing the method of controlling corn yield by spraying a chemical control agent according to any one of claims 1-8, characterized in that, include: The spraying parameter preset module presets the chemical control agent type, target spraying amount, uniformity threshold and canopy density weight parameters based on the basic data of corn, and then generates the initial spraying instruction; The uniformity monitoring module calculates the uniformity coefficient based on the uniformity threshold, canopy density weight parameter, pre-acquired chemical control agent spraying amount and canopy density data, and then judges the spraying uniformity status. The spraying adjustment module analyzes and calculates the uniformity deviation value when the spraying uniformity is abnormal, so as to adjust the working parameters of the spraying device. The yield prediction module analyzes and generates yield prediction coefficients based on pre-acquired corn growth data and uniformity coefficients, thereby predicting corn yield trends. The optimization feedback module optimizes the spraying strategy based on the yield prediction coefficient, generates updated spraying instructions, and transmits them to the spraying device.

Images