Intelligent agriculture monitoring management method based on Internet of Things

Abstract

The invention discloses an intelligent agriculture monitoring management method based on the Internet of Things. The method comprises a data acquisition step, a judgment I step, a monitoring I step, a regulation I step, a calculation I step, a calculation II step, a period calibration step, an analysis step, a root system monitoring step, a judgment II step, a regulation II step, a monitoring II step, a regulation III step, a monitoring III step and a feedback step. The crop growth condition is quantitatively judged through the calculation model, the ventilation condition and the light supplementing time are regulated and controlled, errors caused by dependence on artificial experience are reduced, the accuracy and reliability of crop growth condition evaluation are improved, the practicability and regional adaptability of the method are improved, and the crop growth regulation precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring and management, and in particular to a smart agriculture monitoring and management method based on the Internet of Things. Background Art

[0002] The growing environment of crops has a certain impact on production indicators such as growth, disease incidence, and harvest rate. Currently, Internet of Things (IoT) technology has been widely used in agriculture, construction, and water conservancy. Leveraging IoT technology, sensor networks are established in the growing environment of crops. Through these sensor networks, crop growth environment data is collected, enabling real-time perception of the agricultural environment and crop status, intelligent analysis, precise decision-making, and remote management.

[0003] Existing crop growth environment monitoring technology mainly involves setting up multiple sensors for detecting temperature, humidity, gas and other data near the farmland. The sensors then collect parameters such as temperature, humidity and gas concentration in the crop greenhouse in real time, thereby providing real-time crop growth environment data to judge the crop growth situation and predict environmental change trends.

[0004] At present, the Chinese patent with publication number CN119065311A proposes an intelligent information remote monitoring system for facility agriculture. It collects microclimate data through the microclimate monitoring module, and the comprehensive analysis module performs deviation analysis on the microclimate data and determines whether to trigger the evaluation mechanism. The soil microbial monitoring module collects microbial activity data, and the microbial evaluation module generates a quality evaluation value when the evaluation mechanism is triggered. The remote management module issues an abnormal warning based on the evaluation value.

[0005] Regarding the above technical solution, this method evaluates growth by monitoring indicators such as climate data and microbial data, and makes adjustments based on the evaluation values ​​after fusion analysis. This method has large system errors and is difficult to convert into effective management decisions, making it difficult to accurately control the growth of crops, thereby reducing the accuracy of crop growth regulation. Summary of the Invention

[0006] The purpose of the present invention is to provide a smart agricultural monitoring and management method based on the Internet of Things to solve the problems raised in the above background technology.

[0007] The present invention provides a smart agricultural monitoring and management method based on the Internet of Things, which uses the following technical solutions to achieve the invention objectives: A smart agriculture monitoring and management method based on the Internet of Things includes the following steps: Acquire data: Obtain real-time oxygen concentration, temperature, and light intensity in the greenhouse environment, and obtain preset lighting time for the current planting cycle and planted area S; Judgment I: If the crop is currently under light conditions, execute the monitoring step I; otherwise, execute the calculation step I; Monitoring I: When the crops are monitored to be under light conditions and the oxygen concentration change rate is less than the first benchmark change rate When , execute the regulation I step; Control I: Turn on the ventilation equipment and follow the standard ventilation rate Perform ventilation. After ventilation is completed, perform judgment step I; Calculation I: Calculate the rate of change of oxygen concentration, the average light intensity I and the average temperature T, and the oxygen production rate of crops The calculation model is: ,in is the maximum photosynthetic rate, is the half-saturation light intensity constant, α is the light energy utilization efficiency constant, and the value range of α is: , crop oxygen consumption rate The calculation model is: ,in is the reference temperature, For crops at base temperature The respiratory rate, is the temperature rise coefficient, The value range of is: ; Analysis: Calculate the net primary productivity (NPP) of crops. The NPP calculation model is: ,in is the length of a day; Judgment II: If NPP is less than the target net primary productivity NPB, it is judged that the crop accumulation is insufficient and the regulation II step is executed; Regulation II: Supplement the lighting time of the day. The supplementary lighting time is: .

[0008] By adopting the above technical solution, by using the oxygen concentration change rate as a judgment factor for the photosynthetic efficiency of crops, the first benchmark change rate Y1 can be used to accurately identify the photosynthetic inhibition state of crops. When the oxygen concentration change rate, that is, the oxygen generation rate, is detected to be abnormal, the ventilation compensation mechanism can be immediately triggered to reduce the probability of crops being in an inefficient photosynthetic state for a long time. In this way, the photosynthetic efficiency of crops can be compensated in cases of cloudy days or equipment failure. Compared with traditional methods that rely solely on threshold judgments such as carbon dioxide concentration or light intensity, this method can accurately regulate the growth of crops and the rate of biomass accumulation, reduce errors caused by reliance on manual experience, and thereby improve the accuracy of crop growth regulation. By calculating the oxygen production rate and oxygen consumption rate of crops, the net primary productivity (NPP) of crops can be further calculated. The oxygen consumption rate caused by crop respiration is calculated using a temperature-driven calculation model to determine the oxygen consumption trend and reduce the error caused by reliance on manual experience. The bioaccumulation of crops is dynamically quantified through the net primary productivity (NPP). Compared with the empirical threshold judgment in traditional methods, this method can accurately diagnose the growth lag of crops, thereby further adjusting the lighting time of crops, compensating for the growth gap of crops, and reducing ineffective lighting energy consumption, providing data support for subsequent lighting strategy adjustments, and thus improving the accuracy of crop growth regulation.

[0009] Optionally, a calculation II step is provided between the calculation I step and the analysis step; Calculation II: Calculate the total ventilation capacity of the ventilation equipment on that day. , get the average oxygen concentration outside and the average greenhouse oxygen concentration , calculate the ventilation rate of the equipment ; In the analysis step, according to The calculation model of net primary productivity (NPP) is revised. After the revision, the calculation model of NPP is updated as follows: .

[0010] By adopting the above technical solution, by quantifying the interference of ventilation on oxygen loss and calculating the net primary productivity NPP based on the oxygen loss, the potential systematic errors in the basic calculation method that relies solely on the oxygen production rate and oxygen consumption rate can be reduced. Compared with the traditional method that ignores the oxygen loss carried by the exhaust air, especially in a closed greenhouse with a high pressure difference, the systematic error can easily cause the NPP value to deviate significantly. Correcting the NPP through the equipment ventilation rate can reduce the oxygen content fluctuation caused by ventilation, improve the accuracy and reliability of the crop growth assessment, and enable the ventilation volume to be actively and accurately regulated, optimize equipment energy saving, improve the practicality and regional adaptability of the method, reduce the probability of control failure caused by a single parameter, improve the robustness of the model in complex scenarios, and thereby improve the accuracy of crop growth regulation.

[0011] Optionally, during the analysis step, the calculation model of the net primary productivity (NPP) is also revised. After the revision, the calculation model of the NPP is updated to: ,in is the first leaf area index, The value range is , is the second leaf area index, The value range is .

[0012] By adopting the above technical solution, by introducing the first leaf area index As a compensation coefficient for the photosynthetic efficiency of crops, the second leaf area index is introduced As a compensation coefficient for the respiratory consumption of crops, it can effectively solve the problem that the fixed parameters in the basic calculation model cannot be applied to different varieties of crops or different growth cycles of crops. For example, in the seedling stage of crops with small leaf area, the Weight, increased during the blooming period when the crop has larger leaf area The weights make the NPP calculation model accurately conform to the growth cycle of crops and match the characteristics of the growth stage. The leaf area index reflects the relationship between the light distribution of the crop canopy and the photosynthetic efficiency. When crops are planted at high density, The value of is close to 1, the system can improve The calculation weight of To increase the value of The calculation weight of the first leaf area index and the second leaf area index is used to reflect the increased respiratory consumption caused by overlapping leaves and shading, thereby reducing the quantitative error of the actual growth of crops. In addition, in extreme environments such as high temperature weather, some crops may reduce transpiration consumption by reducing leaf area. Traditional calculation methods are prone to misjudging the growth decline of crops, resulting in excessive light compensation. Dynamically correcting the calculation model of net primary productivity through the first leaf area index and the second leaf area index can reduce potential system errors, protect the self-regulation mechanism of crops, and improve the practicality and regional adaptability of the method, especially the applicability of the model in perennial crops or high-density planting scenarios, reduce the quantitative error of the actual growth of crops, and thus improve the accuracy of crop growth regulation.

[0013] Optionally, a periodic calibration step is provided between the calculation step I and the analysis step; Cycle calibration: According to the current planting cycle of the crop, the average value G of the crop leaf area is measured according to the specified measurement cycle. The preset value of the leaf area in the current planting cycle is ; In the analysis step, the first leaf area index The value of is determined. The specific value calculation model of is: .

[0014] By adopting the above technical solution, the actual leaf area of ​​crops is periodically measured and compared with the preset value of leaf area, so as to dynamically calibrate the first leaf area index and reduce the quantitative error of the actual growth of crops. For example, when crops encounter pests and diseases, The value of is lowered to match the decreased photosynthetic efficiency caused by leaf damage. Compared to the control method of excessive light supplementation based on the healthy crop model, this can reduce the probability of energy waste in the system. At the same time, if the actual leaf area continues to exceed the preset leaf area value without a corresponding increase in net primary productivity, the calculation model can provide early warning of potential crop growth problems, such as lack of leaves or mismatched light intensity, so that the model preset values ​​can be promptly optimized, further improving the practicality and reliability of the method, reducing potential system errors, and thus improving the accuracy of crop growth regulation.

[0015] Optionally, a periodic calibration step is provided between the calculation step I and the analysis step; Period calibration: Measure the dry matter weight W of the crop roots and stems according to the specified measurement period based on the current crop planting cycle. The preset value of the dry matter weight of the crop roots and stems in the current planting cycle is ; In the analysis step, the second leaf area index The value of is determined. The specific value calculation model of is: .

[0016] By adopting the above technical solution, the root and stem dry matter weight of crops is periodically measured and compared with the preset value of dry matter weight, so as to dynamically adjust the second leaf area index. Since there is a certain correlation between the respiratory efficiency of the root and stem of crops and the leaf area, the respiratory consumption of crops is compensated by the root and stem dry matter weight, thereby reducing the quantitative error of the actual growth of crops. For example, in high temperature seasons, some crops actively reduce dry matter accumulation to reduce respiratory consumption. The value of Compared with the traditional calculation model's unnecessary cooling intervention control method, this method can reduce the probability of energy waste caused by the system, and can use the calculation model to warn of potential crop growth problems, such as water-fertilizer imbalance, so that the model preset value can be optimized in time, further improving the practicality and reliability of the method, reducing potential system errors, and thus improving the accuracy of crop growth regulation.

[0017] Optionally, it also includes a monitoring II step and a regulation III step; The judgment II step is updated as follows: if NPP is less than the target net primary productivity NPB, the crop accumulation is judged to be insufficient and the regulation II step is executed; if NPP is greater than or equal to the target net primary productivity NPB, the crop accumulation is judged to be qualified and the monitoring II step is executed; Monitoring II: When it is detected that the crops are not under light conditions and the oxygen concentration change rate is greater than the second benchmark change rate When , perform regulation III step; Control III: Turn on ventilation equipment and follow standard ventilation volume Perform ventilation and after ventilation is complete, proceed to Monitoring II step.

[0018] By adopting the above technical solution, when it is monitored that the crops are not under light conditions and the oxygen concentration change rate is greater than the second reference change rate When the ventilation equipment is turned on, the ventilation volume should be adjusted according to the standard Perform ventilation. After ventilation is completed, repeatedly monitor whether the oxygen concentration change rate is greater than the second benchmark change rate. By dynamically capturing the changes in the respiratory efficiency of crops at night, it is helpful to accurately identify the changes in the accumulation of crops at night. When the oxygen concentration change rate is greater than the second benchmark change rate When the temperature is too low, it indicates that the anaerobic metabolites of crops in the greenhouse are accumulating vigorously. At this time, by triggering ventilation intervention, the accumulation rate of metabolites can be reduced, and the probability of damage caused by root respiratory stress can be reduced, such as persistent soil hypoxia caused by cloudy days, so that the yield of crops can be protected in time, which is conducive to the precise delivery of generated energy. Compared with the traditional method of relying on fixed-time ventilation control, this method can reduce the post-harvest loss rate, warn of potential growth problems of crops, improve the practicality and reliability of the method, and thus improve the accuracy of crop growth regulation.

[0019] Optionally, during the analysis step, the calculation model of the net primary productivity (NPP) is also revised. After the revision, the calculation model of the NPP is updated to: ,in is the soil microbial oxygen consumption rate, The calculation model is: , where k is the soil microbial respiration rate, and the value of k is calibrated according to the experiment.

[0020] By adopting the above technical solution, by calculating the oxygen consumption rate of soil microorganisms and correcting the calculation model, the temperature-dependent oxygen consumption of microorganisms can be quantified. The traditional calculation method of net primary productivity only considers plant respiration and ignores the situation where microorganisms consume a large amount of oxygen at suitable temperatures, especially in the initial stage of organic fertilizer application. The corrected calculation model can reduce the probability of misjudgment of crop growth conditions and the probability of failure of lighting supplementation decisions due to microbial oxygen consumption. The calculation model can be compatible with different types of planting soils, which is conducive to solving the model adaptation problem of cross-regional planting of the same variety of crops, so that the model can be optimized in a timely manner, further improving the practicality and reliability of the method, reducing potential system errors, and thus improving the accuracy of crop growth regulation.

[0021] Optionally, in the data acquisition step, the soil moisture θ in the greenhouse environment is also acquired; During the analysis step, the soil microbial oxygen consumption rate was also The calculation model is modified. The calculation model is updated to , where γ is the humidity coefficient, is the standard soil moisture.

[0022] By adopting the above technical solution, by monitoring soil moisture data and further correcting the oxygen consumption rate of soil microorganisms, compared with the calculation method of the linear model in the traditional method, the trend of the change of microbial oxygen consumption can be dynamically calibrated according to the soil moisture conditions. When the monitored θ deviates from the standard soil moisture, the oxygen consumption rate of the microorganisms can be calibrated dynamically according to the soil moisture conditions. When the oxygen consumption rate of microorganisms decreases, the method can accurately reflect the cliff-like drop in the oxygen consumption rate of microorganisms, thereby automatically reducing the value of the soil microbial oxygen consumption rate and the probability of false or delayed triggering of ventilation decisions. This makes the method applicable to precise water management scenarios such as tidal irrigation or hydroponics, enables the model to be optimized in a timely manner, and further improves the practicality and reliability of the method, thereby improving the accuracy of crop growth regulation.

[0023] Optionally, a root monitoring step is provided after the analysis step: the oxygen concentration of the crop root system is calculated as: , where Y is the oxygen concentration when the crops are not under light conditions on that day, and the minimum preset concentration is , the highest preset concentration is ,like , then it is judged that the root system has sufficient oxygen. If , it is judged that the root system is lacking oxygen.

[0024] By adopting the above technical solution, the oxygen concentration in the crop root system is dynamically quantified through the crop oxygen consumption rate, so that the underground metabolic activity of the crop can be linked with the above-ground gas monitoring, reducing the monitoring cost of the crop root system. It can respond to the oxygen conditions of the root system in a graded manner, reduce the probability of misjudgment, and reduce the probability of growth stagnation, thereby improving the practicality and reliability of the method and thereby improving the accuracy of crop growth regulation.

[0025] Optionally, a monitoring III step and a feedback step are also included; Monitoring III: Recording the number of times the crop accumulation is judged to be insufficient within a specified monitoring period. When the number of times the crop accumulation is judged to be insufficient exceeds a preset number, executing the feedback step; Feedback: Generates abnormal crop growth warnings and sends them to the management end.

[0026] By adopting the above technical solution, by counting the number of times NPP fails to meet the standard within a specified monitoring period, recording the progressive growth stagnation of crops, and setting a buffer threshold to reduce the probability of over-response, early warning of the accumulation of abnormal crop growth is issued, providing a quantitative basis for crop yield risk management, thereby warning of potential crop growth problems and improving the practicality and reliability of this method.

[0027] Compared with the prior art, the present invention has the following beneficial effects: 1. By using the rate of change of oxygen concentration as a factor in determining the photosynthetic efficiency of crops, the first benchmark change rate Y1 can be used to accurately identify the photosynthetic inhibition state of crops. When an abnormal oxygen concentration change rate, i.e., the oxygen production rate, is detected, the ventilation compensation mechanism can be immediately triggered to reduce the probability of crops being in an inefficient photosynthetic state for a long time. By calculating the crop oxygen production rate and the crop oxygen consumption rate, the net primary productivity of the crops can be further calculated. The oxygen consumption rate caused by crop respiration is calculated using a temperature-driven calculation model to determine the oxygen consumption trend and reduce the error caused by reliance on manual experience. By adjusting the ventilation conditions in real time under lighting conditions and the supplemental lighting time under non-lighting conditions, the oxygen consumption trend can be determined and the error caused by reliance on manual experience can be reduced. Compared with the empirical threshold judgment in traditional methods, this method can accurately diagnose the growth lag of crops, thereby further adjusting the lighting time of crops, reducing ineffective lighting energy consumption, providing data support for subsequent lighting strategy adjustments, and thus improving the accuracy of crop growth regulation.

[0028] 2. By quantifying the interference of ventilation on oxygen loss and calculating the net primary productivity (NPP) based on the oxygen loss, the potential systematic errors in the basic calculation method that relies solely on the oxygen production rate and oxygen consumption rate can be reduced. Compared with the traditional method that ignores the oxygen loss carried by the exhaust air, especially in a closed greenhouse with a high pressure difference, the systematic error can easily cause the NPP value to deviate significantly. Correcting the NPP by the equipment ventilation rate can reduce the oxygen content fluctuation caused by ventilation, improve the accuracy and reliability of the crop growth assessment, and enable the ventilation volume to be actively and accurately regulated, optimize equipment energy saving, improve the practicality and regional adaptability of the method, reduce the probability of control failure caused by a single parameter, improve the robustness of the model in complex scenarios, and thus improve the accuracy of crop growth regulation.

[0029] 3. By introducing the first leaf area index As a compensation coefficient for the photosynthetic efficiency of crops, the second leaf area index is introduced As a compensation coefficient for the respiratory consumption of crops, it can effectively solve the problem that the fixed parameters in the basic calculation model cannot be applied to different varieties of crops or different growth cycles of crops. For example, in the seedling stage of crops with small leaf area, the Weight, increased during the blooming period when the crop has larger leaf area The weights make the NPP calculation model accurately conform to the growth cycle of crops and match the characteristics of the growth stages.

[0030] 4. By periodically measuring the actual leaf area and root dry matter weight of crops, the first and second leaf area indices can be dynamically calibrated to reduce the quantitative error of the actual crop growth conditions. Compared with traditional calculation models, this method can reduce the probability of energy waste caused by the system, enable timely optimization of the model preset values, and use the calculation model to warn of potential crop growth problems, further improving the practicality and reliability of the method, reducing potential system errors, and thus improving the accuracy of crop growth regulation.

[0031] 5. When it is detected that the crops are not under light conditions and the oxygen concentration change rate is greater than the second benchmark change rate When the ventilation equipment is turned on, the ventilation volume should be adjusted according to the standard Perform ventilation. After ventilation is completed, repeatedly monitor whether the oxygen concentration change rate is greater than the second benchmark change rate. By dynamically capturing the changes in the respiratory efficiency of crops at night, it is helpful to accurately identify the changes in the accumulation of crops at night. When the oxygen concentration change rate is greater than the second benchmark change rate When the temperature is too low, it indicates that the anaerobic metabolites of crops in the greenhouse are accumulating vigorously. At this time, by triggering ventilation intervention, the accumulation rate of metabolites can be reduced, and the probability of damage caused by root respiratory stress can be reduced, such as persistent soil hypoxia caused by cloudy days, so that the yield of crops can be protected in time, which is conducive to the precise delivery of generated energy. Compared with the traditional method of relying on fixed-time ventilation control, this method can reduce the post-harvest loss rate, warn of potential growth problems of crops, improve the practicality and reliability of the method, and thus improve the accuracy of crop growth regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings described herein are used to provide a further understanding of this application and constitute a part of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation on this application. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without inventive effort. In the drawings: Figure 1 This is a flowchart of a smart agriculture monitoring and management method based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following is a combination of the embodiments of the present invention Figure 1The technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0034] This embodiment discloses a smart agriculture monitoring and management method based on the Internet of Things. Figure 1 , including the following steps: S1. Data acquisition step: Real-time acquisition of oxygen concentration, temperature and light intensity in the greenhouse environment, and the preset lighting time for the current planting cycle and the planting area S, to obtain the soil moisture θ in the greenhouse environment.

[0035] S2. Judgment step I: If the crops are currently under light conditions, execute monitoring step I S3; otherwise, execute calculation step I S5.

[0036] S2, monitoring step I: when it is monitored that the crops are under light conditions and the oxygen concentration change rate is less than the first reference change rate , execute control I step S4.

[0037] S4, Control step I: Turn on the ventilation equipment and ventilate at the standard rate Perform ventilation. After ventilation is completed, repeat the judgment step S2.

[0038] S5, calculation step I: calculate the oxygen concentration change rate, the average light intensity I and the average temperature T, and the oxygen production rate of crops The calculation model is: ,in is the maximum photosynthetic rate, is the half-saturation light intensity constant, α is the light energy utilization efficiency constant, and the value range of α is: The value of α is calibrated according to crop experiments, and the oxygen consumption rate of crops is The calculation model is: ,in is the reference temperature, For crops at base temperature The respiratory rate, is the temperature rise coefficient, The value of is: .

[0039] S6. Calculation step II: Count the opening records of the ventilation equipment and calculate the total ventilation volume of the ventilation equipment on that day: , get the average oxygen concentration outside and the average greenhouse oxygen concentration , calculate the ventilation rate of the equipment .

[0040] S7, cycle calibration step: according to the current planting cycle of the crop, the average value of the crop leaf area G and the crop root dry matter weight W are measured according to the specified measurement cycle. The preset value of the leaf area in the current planting cycle is The preset value of root dry matter weight in the current planting cycle is .

[0041] S8. Analysis steps: Calculate the net primary productivity of crops as NPP. The calculation model of NPP is: ,in For the length of a day, is the first leaf area index, The value range is , The specific value calculation model of is: , is the second leaf area index, The value range is , The specific value calculation model of is: , is the soil microbial oxygen consumption rate, The calculation model is: , where k is the soil microbial respiration rate, the value of k is calibrated according to the soil microbial experiment, γ is the humidity coefficient, is the standard soil moisture.

[0042] S9. Root system monitoring steps: Calculate the oxygen concentration of crop roots as: , where Y is the oxygen concentration when the crops are not under light conditions on that day, and the minimum preset concentration is , the highest preset concentration is ,like , then it is judged that the root system has sufficient oxygen. If , it is judged that the root system is lacking oxygen.

[0043] S10, judgment II step: If NPP is less than the target net primary productivity NPB, it is judged that the crop accumulation is insufficient, and the control II step S11 is executed. On the contrary, if NPP is greater than or equal to the target net primary productivity NPB, it is judged that the crop accumulation is qualified, and the monitoring II step S12 is executed.

[0044] S11, control step II: the lighting time of the day is supplemented according to the supplementary lighting time, and the supplementary lighting time is: , execute monitoring III step S14.

[0045] S12, Monitoring II step: When it is monitored that the crops are not under light conditions and the oxygen concentration change rate is greater than the second reference change rate , execute control III step S13.

[0046] S13, Control Step III: Turn on the ventilation equipment and ventilate at the standard rate Perform ventilation, and after ventilation is completed, perform monitoring II step S12.

[0047] S14, monitoring step III: recording the number of times the cumulative amount of crops is judged to be insufficient within the specified monitoring period, and executing feedback step S15 when the number of times the cumulative amount of crops is judged to be insufficient is greater than a preset number.

[0048] S15, feedback step: Generate an abnormal crop growth warning and send it to the management end.

[0049] The implementation principle of the smart agriculture monitoring and management method based on the Internet of Things in this embodiment is as follows: Multiple IoT sensors are installed in the crop greenhouse to obtain the oxygen concentration, temperature, light intensity and soil humidity θ in the crop greenhouse environment in real time. The IoT sensors also calculate the oxygen concentration change rate, the average light intensity I and the average temperature T of the day, and obtain the preset lighting time for the current crop planting cycle. and the planting area S.

[0050] Determine whether the crops are currently under light conditions. If the crops are currently under light conditions, monitor whether the rate of change of oxygen concentration in the greenhouse is less than the first benchmark rate of change. , if less than , then turn on the ventilation equipment and follow the standard ventilation volume Perform ventilation. After ventilation is completed, repeatedly monitor whether the rate of change of oxygen concentration is less than If the crops are not currently under light conditions, it means that the day's light time has ended. Calculate the oxygen production rate of the crops. , and then further calculate the net primary productivity NPP of crops.

[0051] By using the oxygen concentration change rate as a factor to judge the photosynthetic efficiency of crops, the first benchmark change rate Y1 can be used to accurately identify the photosynthetic inhibition state of crops. When the oxygen concentration change rate, that is, the oxygen generation rate, is detected to be abnormal, the ventilation compensation mechanism can be immediately triggered to reduce the probability of crops being in an inefficient photosynthetic state for a long time. In this way, the photosynthetic efficiency of crops can be compensated in cases of cloudy days or equipment failure. Compared with traditional methods that rely solely on threshold judgments such as carbon dioxide concentration or light intensity, this method can accurately regulate the growth of crops and the rate of biomass accumulation, reduce errors caused by reliance on manual experience, and thus improve the accuracy of crop growth regulation.

[0052] Oxygen production rate of crops The calculation model is: , crop oxygen consumption rate The calculation model is: By calculating the oxygen production rate and oxygen consumption rate of crops, the net primary productivity (NPP) of crops can be further calculated. The oxygen consumption rate caused by crop respiration is calculated using a temperature-driven calculation model to determine the oxygen consumption trend and reduce the error caused by reliance on manual experience. The bioaccumulation of crops is dynamically quantified through the net primary productivity (NPP). Compared with the empirical threshold judgment in traditional methods, this method can accurately diagnose the growth lag of crops, thereby further adjusting the lighting time of crops, compensating for the growth gap of crops, and reducing ineffective lighting energy consumption, providing data support for subsequent lighting strategy adjustments, and thus improving the accuracy of crop growth regulation.

[0053] Count the opening records of the ventilation equipment and calculate the total ventilation volume of the ventilation equipment on that day: , get the average oxygen concentration outside and the average greenhouse oxygen concentration , calculate the ventilation rate of the equipment By quantifying the interference of ventilation on oxygen loss and calculating the net primary productivity (NPP) based on the oxygen loss, the potential systematic errors in the basic calculation method that relies solely on the oxygen production rate and oxygen consumption rate can be reduced. Compared with the traditional method that ignores the oxygen loss carried by the exhaust air, the systematic error can easily cause the NPP value to deviate significantly, especially in a closed greenhouse with a high pressure difference. Correcting the NPP by the equipment ventilation rate can reduce the oxygen content fluctuation caused by ventilation, improve the accuracy and reliability of the crop growth assessment, and enable the ventilation volume to be actively and accurately regulated, optimize equipment energy saving, improve the practicality and regional adaptability of the method, reduce the probability of control failure caused by a single parameter, improve the robustness of the model in complex scenarios, and thus improve the accuracy of crop growth regulation.

[0054] According to the current planting cycle of the crop, the average leaf area G of the crop and the dry matter weight W of the crop root are measured according to the specified measurement cycle. The preset value of the leaf area in the current planting cycle is The preset value of root dry matter weight in the current planting cycle is , thereby calculating the first leaf area index and the second leaf area index.

[0055] The calculation model of the net primary productivity of crops is: , the calculation model of the first leaf area index is: , the calculation model of the second leaf area index is: , the calculation model of soil microbial oxygen consumption rate is: .

[0056] By introducing the first leaf area index As a compensation coefficient for the photosynthetic efficiency of crops, the second leaf area index is introduced As a compensation coefficient for the respiratory consumption of crops, it can effectively solve the problem that the fixed parameters in the basic calculation model cannot be applied to different varieties of crops or different growth cycles of crops. For example, in the seedling stage of crops with small leaf area, the Weight, increased during the blooming period when the crop has larger leaf area The weights make the NPP calculation model accurately conform to the growth cycle of crops and match the characteristics of the growth stage. The leaf area index reflects the relationship between the light distribution of the crop canopy and the photosynthetic efficiency. When crops are planted at high density, The value of is close to 1, the system can improve The calculation weight of To increase the value of The calculation weights are used to reflect the increased respiratory consumption caused by overlapping leaves and shading, thereby reducing the quantitative error of the actual growth of crops.

[0057] In addition, in extreme environments such as high temperature weather, some crops may reduce transpiration consumption by reducing leaf area. Traditional calculation methods are prone to misjudging the growth decline of crops, leading to excessive light compensation. Dynamically correcting the calculation model of net primary productivity through the first leaf area index and the second leaf area index can reduce potential system errors, protect the self-regulation mechanism of crops, and improve the practicality and regional adaptability of the method, especially the applicability of the model in perennial crops or high-density planting scenarios, reduce the quantitative error of the actual growth of crops, and thus improve the accuracy of crop growth regulation.

[0058] By periodically measuring the actual leaf area of ​​crops and comparing it with the preset leaf area value, the first leaf area index can be dynamically calibrated to reduce the quantitative error of the actual growth of crops. For example, when crops encounter pests and diseases, The value of is lowered to match the decreased photosynthetic efficiency caused by leaf damage. Compared to the control method of excessive light supplementation based on the healthy crop model, this can reduce the probability of energy waste in the system. At the same time, if the actual leaf area continues to exceed the preset leaf area value without a corresponding increase in net primary productivity, the calculation model can provide early warning of potential crop growth problems, such as lack of leaves or mismatched light intensity, so that the model preset values ​​can be promptly optimized, further improving the practicality and reliability of the method, reducing potential system errors, and thus improving the accuracy of crop growth regulation.

[0059] By periodically measuring the root and stem dry matter weight of crops and comparing it with the preset dry matter weight, the second leaf area index is dynamically adjusted. Since there is a certain correlation between the respiratory efficiency of the root and stem of crops and the leaf area, the respiratory consumption of crops is compensated by the root and stem dry matter weight, thereby reducing the quantitative error of the actual growth of crops. For example, in high temperature seasons, some crops actively reduce dry matter accumulation to reduce respiratory consumption. The value of Compared with the traditional calculation model's unnecessary cooling intervention control method, this method can reduce the probability of energy waste caused by the system, and can use the calculation model to warn of potential crop growth problems, such as water-fertilizer imbalance, so that the model preset value can be optimized in time, further improving the practicality and reliability of the method, reducing potential system errors, and thus improving the accuracy of crop growth regulation.

[0060] By calculating the oxygen consumption rate of soil microorganisms and correcting the calculation model, the temperature-dependent oxygen consumption of microorganisms can be quantified. The traditional calculation method of net primary productivity only considers plant respiration and ignores the situation where microorganisms consume a lot of oxygen at suitable temperatures, especially in the initial stage of organic fertilizer application. The corrected calculation model can reduce the probability of misjudgment of crop growth conditions and the probability of failure of lighting supplementation decisions due to microbial oxygen consumption. It makes the calculation model compatible with different types of planting soils, which is conducive to solving the model adaptation problem of cross-regional planting of the same variety of crops, so that the model can be optimized in a timely manner, further improving the practicality and reliability of the method, reducing potential system errors, and thus improving the accuracy of crop growth regulation.

[0061] By monitoring soil moisture data and further correcting the oxygen consumption rate of soil microorganisms, compared with the calculation method of the linear model in the traditional method, the trend of microbial oxygen consumption can be dynamically calibrated according to the soil moisture conditions. When the monitored θ deviates from the standard soil moisture, the oxygen consumption rate of the microorganisms can be calibrated dynamically according to the soil moisture conditions. When the oxygen consumption rate of microorganisms decreases, the method can accurately reflect the cliff-like drop in the oxygen consumption rate of microorganisms, thereby automatically reducing the value of the soil microbial oxygen consumption rate and the probability of false or delayed triggering of ventilation decisions. This makes the method applicable to precise water management scenarios such as tidal irrigation or hydroponics, enables the model to be optimized in a timely manner, and further improves the practicality and reliability of the method, thereby improving the accuracy of crop growth regulation.

[0062] Calculate the oxygen concentration of crop roots as: , let the minimum preset concentration be , the highest preset concentration is ,like , then it is judged that the root system has sufficient oxygen. If , then the root system is judged to be hypoxic. Dynamically quantifying the oxygen concentration in the crop root system through the crop oxygen consumption rate allows the correlation of underground metabolic activity with above-ground gas monitoring, reducing the cost of monitoring the crop root system. The system can respond to the root oxygen status in a graded manner, reducing the probability of misjudgment and the occurrence of growth stagnation. This improves the practicality and reliability of the method, thereby increasing the accuracy of crop growth regulation.

[0063] If the net primary productivity NPP is less than the target net primary productivity NPB, it is judged that the crop accumulation is insufficient and the lighting time of the day is supplemented. The supplementary lighting time is: , and records the number of times the crop accumulation is judged to be insufficient within the specified monitoring period. When the number of times the crop accumulation is judged to be insufficient is greater than the preset number, an abnormal crop growth warning is generated and sent to the management end.

[0064] By controlling ventilation in real time under lighting conditions and adjusting supplemental lighting duration under non-lighting conditions, oxygen consumption trends can be determined, reducing errors caused by reliance on manual experience. Compared to traditional methods using empirical thresholds, this method can accurately diagnose growth lags in crops, allowing for further adjustments to crop lighting schedules, reducing ineffective lighting energy consumption, and providing data support for subsequent adjustments to lighting strategies, thereby improving the accuracy of crop growth regulation. By counting the number of NPP failures within a specified monitoring period, recording the gradual growth stagnation of crops, and setting buffer thresholds to reduce the probability of over-response, this method provides early warnings of accumulated abnormal crop growth, providing a quantitative basis for crop yield risk management, and thus warning of potential crop growth problems, improving the practicality and reliability of the method.

[0065] When it is monitored that the crops are not under light conditions and the oxygen concentration change rate is greater than the second benchmark change rate When the ventilation equipment is turned on, the ventilation volume should be adjusted according to the standard Perform ventilation. After ventilation is completed, repeatedly monitor whether the oxygen concentration change rate is greater than the second benchmark change rate. By dynamically capturing the changes in the respiratory efficiency of crops at night, it is helpful to accurately identify the changes in the accumulation of crops at night. When the oxygen concentration change rate is greater than the second benchmark change rate When the temperature is too low, it indicates that the anaerobic metabolites of crops in the greenhouse are accumulating vigorously. At this time, by triggering ventilation intervention, the accumulation rate of metabolites can be reduced, and the probability of damage caused by root respiratory stress can be reduced, such as persistent soil hypoxia caused by cloudy days, so that the yield of crops can be protected in time, which is conducive to the precise delivery of generated energy. Compared with the traditional method of relying on fixed-time ventilation control, this method can reduce the post-harvest loss rate, warn of potential growth problems of crops, improve the practicality and reliability of the method, and thus improve the accuracy of crop growth regulation.

[0066] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A smart agriculture monitoring and management method based on the Internet of Things, characterized in that: The following steps are involved: Acquire data: Obtain real-time oxygen concentration, temperature, and light intensity in the greenhouse environment, and obtain preset lighting time for the current planting cycle and planted area S; Judgment I: If the crop is currently under light conditions, execute the monitoring step I; otherwise, execute the calculation step I; Monitoring I: When the crops are monitored to be under light conditions and the oxygen concentration change rate is less than the first benchmark change rate When , execute the regulation I step; Control I: Turn on the ventilation equipment and follow the standard ventilation rate Perform ventilation. After ventilation is completed, perform judgment step I; Calculation I: Calculate the rate of change of oxygen concentration, the average light intensity I and the average temperature T, and the oxygen production rate of crops The calculation model is: ,in is the maximum photosynthetic rate, is the half-saturation light intensity constant, α is the light energy utilization efficiency constant, and the value range of α is: , crop oxygen consumption rate The calculation model is: ,in is the reference temperature, For crops at base temperature The respiratory rate, is the temperature rise coefficient, The value range of is: ; Analysis: Calculate the net primary productivity (NPP) of crops. The NPP calculation model is: ,in is the length of a day; Judgment II: If NPP is less than the target net primary productivity NPB, it is judged that the crop accumulation is insufficient and the regulation II step is executed; Regulation II: Supplement the lighting time of the day. The supplementary lighting time is: .

2. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 1, wherein: There is also a calculation II step between the calculation I step and the analysis step; Calculation II: Calculate the total ventilation capacity of the ventilation equipment on that day. , get the average oxygen concentration outside and the average greenhouse oxygen concentration , calculate the ventilation rate of the equipment ; In the analysis step, according to The calculation model of net primary productivity (NPP) is revised. After the revision, the calculation model of NPP is updated as follows: .

3. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 1, wherein: During the analysis step, the calculation model of net primary productivity (NPP) was also revised. After the revision, the calculation model of NPP was updated to: ,in is the first leaf area index, The value range is , is the second leaf area index, The value range is .

4. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 3, wherein: A periodic calibration step is also provided between the calculation step I and the analysis step; Cycle calibration: According to the current planting cycle of the crop, the average value G of the crop leaf area is measured according to the specified measurement cycle. The preset value of the leaf area in the current planting cycle is ; In the analysis step, the first leaf area index The value of is determined. The specific value calculation model of is: .

5. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 3, wherein: A periodic calibration step is also provided between the calculation step I and the analysis step; Period calibration: Measure the dry matter weight W of the crop roots and stems according to the specified measurement period based on the current crop planting cycle. The preset value of the dry matter weight of the crop roots and stems in the current planting cycle is ; In the analysis step, the second leaf area index The value of is determined. The specific value calculation model of is: .

6. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 1, wherein: Also includes monitoring II step and regulation III step; The judgment II step is updated as follows: if NPP is less than the target net primary productivity NPB, the crop accumulation is judged to be insufficient and the regulation II step is executed; if NPP is greater than or equal to the target net primary productivity NPB, the crop accumulation is judged to be qualified and the monitoring II step is executed; Monitoring II: When it is detected that the crops are not under light conditions and the oxygen concentration change rate is greater than the second benchmark change rate When , perform regulation III step; Control III: Turn on ventilation equipment and follow standard ventilation volume Perform ventilation and after ventilation is complete, proceed to Monitoring II step.

7. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 1, characterized in that: During the analysis step, the calculation model of net primary productivity (NPP) was also revised. After the revision, the calculation model of NPP was updated to: ,in is the soil microbial oxygen consumption rate, The calculation model is: , where k is the soil microbial respiration rate, and the value of k is calibrated according to the experiment.

8. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 7, characterized in that: In the data acquisition step, the soil moisture θ in the greenhouse environment is also obtained; During the analysis step, the soil microbial oxygen consumption rate was also The calculation model is modified. The calculation model is updated to , where γ is the humidity coefficient, is the standard soil moisture.

9. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 7, characterized in that: After the analysis step, a root monitoring step is also set up: the oxygen concentration of the crop root system is calculated as: , where Y is the oxygen concentration when the crops are not under light conditions on that day, and the minimum preset concentration is , the highest preset concentration is ,like , then it is judged that the root system has sufficient oxygen. If , it is judged that the root system is lacking oxygen.

10. The method for monitoring and managing smart agriculture based on the Internet of Things according to claim 1, characterized in that: It also includes the Monitoring III step and the Feedback step; Monitoring III: Recording the number of times the crop accumulation is judged to be insufficient within a specified monitoring period. When the number of times the crop accumulation is judged to be insufficient exceeds a preset number, executing the feedback step; Feedback: Generates abnormal crop growth warnings and sends them to the management end.

Images