Intelligent peanut monitoring growth method

Abstract

The present application relates to the technical field of agricultural monitoring, and more particularly to a peanut intelligent monitoring growth method, comprising: step 1: underground organ cooperative monitoring; step 2: soil mechanical behavior analysis: when the compressive stress change characteristics meet the fruit needle bending event judgment condition, the soil penetrability index is generated combined with the calibration test data; step 3: cross-medium growth decision: according to the time sequence relationship between the volume change rate of the reconstructed pod and the canopy spectral senescence index, the nutrient transport imbalance early warning is generated; the surface area to volume ratio change characteristics of the three-dimensional morphology of the pod are extracted, when the change trend meets the maturity inflection point judgment condition, the internal vascular bundle browning state of the pod is verified and the harvesting instruction is output. The strain sensing device can monitor the compressive stress change in the fruit needle penetration process in real time, which can effectively analyze the physical properties of the soil and provide real-time soil mechanical data support for the growth of the pod.

Description

Technical Field

[0001] This invention relates to the field of agricultural monitoring technology, and in particular to a method for intelligent monitoring of peanut growth. Background Technology

[0002] Peanuts are a typical above-ground flowering and underground fruiting crop, with their pods developing entirely underground. Current monitoring technologies have the following limitations:

[0003] Monitoring of underground pod development is lacking.

[0004] Current technology relies on manual digging and sampling, which destructively obtains pod morphology data every 7-10 days. This leads to:

[0005] Individual plant data cannot reflect the dynamics of population development;

[0006] The critical morphological transition period (if the needle punctures the pod and then it swells) cannot be captured in real time;

[0007] Destructive operations alter the root microenvironment, resulting in data distortion rates exceeding 30%.

[0008] Lack of multi-source parameter collaborative analysis: Although soil temperature and humidity sensors and canopy spectrometers have been deployed, however:

[0009] Soil compaction data were not correlated with peg mechanical behavior;

[0010] The canopy senescence index was not associated with changes in the fullness of underground pods;

[0011] Parameters are stored independently, and there is a lack of a cross-media growth equilibrium model.

[0012] The lack of quantitative standards for maturity: Field management relies mainly on experience (such as fruit shell texture and plant leaf color), leading to:

[0013] Premature harvesting leads to an increase in the percentage of unripe fruit (>15%).

[0014] Delayed harvesting increases the risk of sprouting in the field;

[0015] Existing electronic devices can only detect moisture content at a single point and cannot quantify the physiological maturation relationship between vascular bundle browning and grain dry weight.

[0016] Therefore, there is an urgent need for a method to intelligently monitor peanut growth and solve the above problems. Summary of the Invention

[0017] To achieve the above objectives, the present invention provides a method for intelligent monitoring of peanut growth, comprising the following steps:

[0018] Step 1: Collaborative monitoring of underground organs:

[0019] By simultaneously transmitting electromagnetic waves with different penetration depths using a dual-band radar array deployed on peanut planting ridges, the soil attenuation effect of high-frequency echoes is compensated based on low-frequency echo signals.

[0020] The spatial coordinates of the fruit needle tip are identified based on the abrupt change point of the compensated high-frequency echo amplitude. When the distance between adjacent fruit needles collected over several consecutive days is less than the critical threshold for pod enlargement, 3D reconstruction of the pod is triggered.

[0021] Step 2: Analysis of soil mechanical behavior:

[0022] Strain sensing devices are deployed based on the coordinates of the fruit needle tip to monitor the changes in radial compressive stress during the fruit needle penetration process in real time.

[0023] When the compressive stress change characteristics meet the criteria for determining the fruit needle bending event, the soil permeability index is generated by combining the calibration test data.

[0024] Step 3: Cross-media growth decision:

[0025] Based on the temporal relationship between the reconstructed pod volume change rate and the canopy spectral aging index, an early warning of nutrient transport imbalance is generated.

[0026] The surface area-to-volume ratio of the three-dimensional morphology of the pods is extracted. When the trend of change meets the criteria for determining the maturity inflection point, the browning state of the vascular bundles inside the pods is verified and a harvesting command is output.

[0027] Preferably, the specific process of triggering the three-dimensional reconstruction of the pod includes:

[0028] The method for determining the critical threshold for pod enlargement is as follows: during the peanut flowering period, the distance between healthy pods is continuously measured, the minimum distance value when the pods begin to enlarge is statistically analyzed, and this value is multiplied by a safety factor as the threshold benchmark.

[0029] The three-dimensional reconstruction is performed as follows: taking the point with the maximum value of the high-frequency echo amplitude gradient as the pod growth center, the reconstruction area is expanded according to the gradient decay direction.

[0030] The reconstruction accuracy control method is as follows: the point cloud density is dynamically adjusted according to the spatial variation coefficient of the soil dielectric constant; the larger the variation coefficient, the higher the point cloud density.

[0031] Preferably, the deployment and monitoring of the strain sensing device includes:

[0032] The sensing device adopts a concentric ring structure. The diameter of the inner ring is set according to the calibrated value of the fruit needle diameter during the flowering period, and the diameter of the outer ring is set according to the maximum enlarged diameter of the pod in historical data.

[0033] The method for establishing the judgment condition of the fruit needle bending event is as follows: In the calibration test, simulated fruit needles are inserted into soils of different textures, and the waveform of the compressive stress change rate when the fruit needle undergoes permanent deformation is recorded. The characteristic range of duration and slope extreme values ​​in the waveform is extracted as the judgment condition.

[0034] Preferably, the generation of the soil permeability index includes:

[0035] Statistical analysis of the number of fruit needle bending events per unit area and the total number of fruit needles;

[0036] Soil compaction compensation factor was obtained through calibration test: the penetration resistance curves of soils with different textures were measured under controlled moisture content conditions, and the ratio of the slope of the linear segment of the curve to the slope of the reference soil was used as the compensation factor.

[0037] The index is calculated as: 1 minus the product of the bending event occurrence rate and the compensation factor.

[0038] Preferably, the triggering logic for the nutrient transport imbalance early warning is as follows:

[0039] The rate of change of pod volume was calculated by the difference in convex hull volume between the reconstructed pod point clouds on two consecutive days.

[0040] Method for obtaining the canopy spectral senescence index: Collect the reflectance of the canopy in the chlorophyll-sensitive band and the leaf structure-sensitive band daily, calculate the difference in the diurnal variation of the reflectance in the two bands, and then divide it by the corresponding difference benchmark of healthy plants in the flowering period.

[0041] An early warning is triggered when the volume change rate exceeds the typical value during the vigorous growth period and the spectral aging index is below the critical value.

[0042] Preferably, the specific method for determining the maturity inflection point is as follows:

[0043] Calculate the surface area-to-volume ratio of the reconstructed pod point cloud daily and record the change in the ratio over three consecutive days;

[0044] When the absolute value of the change is less than the stability threshold and the trend of change changes from positive to negative, it is determined to be an inflection point.

[0045] The stability threshold is set according to the pod variety: the fluctuation range of the surface area to volume ratio of healthy pods is continuously measured during the milk stage, and the percentage value of the maximum fluctuation amplitude is taken.

[0046] Preferably, the verification of the browning state of the vascular bundles includes:

[0047] Within 48 hours after the inflection point is determined, a miniature imaging probe is inserted at a randomly selected monitoring point;

[0048] After the probe reaches the pod area along the fruit needle trajectory, it switches to the browning feature recognition mode:

[0049] 1) Irradiate the inside of the pod shell with a light source of a specific wavelength;

[0050] 2) Collect the intensity of characteristic bands related to browning in the reflectance spectrum;

[0051] Maturity is confirmed when the intensity ratio of characteristic bands exceeds the variety-related threshold.

[0052] Preferably, the dynamic adjustment method for the concentric ring structure is as follows:

[0053] Method for setting the inner ring diameter during the flowering period: Measure the diameter of the base of the fruit needle on the main stem of 10 healthy plants and take the arithmetic mean as the calibration value;

[0054] Outer ring diameter expansion mechanism: When the maximum diameter of the reconstructed pod point cloud reaches the set ratio of the current outer ring diameter, the outer ring diameter is automatically updated to the current maximum diameter multiplied by the expansion coefficient.

[0055] Preferably, the detailed process of the browning feature recognition pattern is as follows:

[0056] Feature band selection method: In the laboratory, spectral scanning of pod shells at different maturity levels was performed to determine the band interval with the greatest difference in reflectance between browned and non-browned areas;

[0057] Intensity ratio calculation: The ratio of the intensity of the characteristic band to the intensity of the reference band is used as the browning index;

[0058] Calibration of variety-related thresholds: Samples are taken during the peak harvest period, and the minimum browning index value in the samples whose dry grain weight reaches the biological maturity standard is set as the threshold.

[0059] Preferably, the method for optimizing the harvesting command is as follows:

[0060] Obtain meteorological data within 72 hours after the maturity inflection point;

[0061] When the probability of rainfall exceeds the preset risk value, the harvesting time will be brought forward to a specific time before the rainfall.

[0062] The determination of the specific duration: based on historical data, the shortest time required for soil moisture content to recover to a safe range for mechanical harvesting under different rainfall intensities.

[0063] The beneficial effects of this invention are:

[0064] 1. This invention achieves non-destructive monitoring of underground pods using a dual-band radar array, enabling real-time acquisition of three-dimensional morphological data of the pods and avoiding data distortion caused by manual sampling. It utilizes radar signals to compensate for soil attenuation effects and automatically triggers three-dimensional reconstruction of the pods based on changes in the spacing between the pod needles, effectively capturing key morphological transformation periods. If the needles penetrate to the point of pod enlargement, it can comprehensively reflect the dynamic development of the population.

[0065] 2. This invention establishes a mechanical relationship between soil and plants by combining strain sensing devices to monitor the radial compressive stress changes when fruit thorns penetrate the soil, and by calculating the soil permeability index based on soil mechanics data. This overcomes the limitations of traditional methods that lack multi-source parameter synergistic analysis. Furthermore, the correlation analysis between the canopy spectral senescence index and pod volume change rate further advances cross-media growth decision-making, enabling more accurate prediction of pod fullness changes and comprehensively improving the accuracy and reliability of the monitoring system.

[0066] 3. This invention accurately determines the physiological maturity of peanuts by calculating the change in the surface area-to-volume ratio of the pods, combined with a stability threshold and a method for determining the maturity inflection point. When the change in the surface area-to-volume ratio is less than the stability threshold for three consecutive days, and the trend changes from positive to negative, the system automatically identifies it as a maturity inflection point, thus avoiding the risk of increased shriveled pods or field sprouting due to harvesting too early or too late. Furthermore, the method for verifying the browning state of the vascular bundles, combined with spectral reflectance data in a specific band, can accurately determine the physiological maturity of peanuts, further ensuring the scientific validity and accuracy of the harvest timing.

[0067] 4. This invention optimizes harvesting instructions by collecting meteorological data and combining rainfall probability with soil moisture recovery. When the rainfall probability exceeds a set risk value, the system can adjust the harvesting time in advance to ensure harvesting at the optimal time, thereby avoiding the risk of excessive soil moisture affecting harvesting and improving the safety and effectiveness of harvesting operations. Attached Figure Description

[0068] To more clearly illustrate the technical solutions in this invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0069] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0070] Figure 2 This is a flowchart illustrating the steps of the browning feature recognition pattern process in the method of the present invention.

[0071] Figure 3 This is a flowchart illustrating the steps of the optimized harvesting command method of the present invention. Detailed Implementation

[0072] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0073] Please see Figures 1-3 This invention provides a method for intelligent monitoring of peanut growth. In step 1, a dual-band radar array is deployed on the peanut planting ridge to simultaneously emit low-frequency and high-frequency electromagnetic waves, which can penetrate soil layers at different depths and accurately capture the morphological changes of underground pods. The low-frequency echo signal is used to compensate for soil attenuation effects, ensuring the clarity and accuracy of the high-frequency echo signal. Furthermore, by identifying abrupt changes in the amplitude of the compensated high-frequency echo signal, the spatial coordinates of the pod tip are accurately determined. When the distance between adjacent pods is measured to be less than the critical threshold for pod enlargement for several consecutive days, three-dimensional reconstruction of the pod is triggered. This step enables non-destructive real-time monitoring of the pod development process, overcoming the errors and data distortion problems caused by traditional manual sampling, and ensuring the accuracy and reliability of the monitoring data.

[0074] In step 2, strain sensors are deployed based on the coordinates of the prickle tip to monitor the radial compressive stress changes during the prickle's penetration of the soil in real time. When the compressive stress change characteristics during prickle penetration meet the criteria for a prickle bending event, the soil permeability index is calculated based on calibration test data. By monitoring and analyzing soil mechanical behavior, soil permeability information can be obtained, providing soil environmental data support for subsequent prickle growth and pod development. This technology can track changes in soil condition in real time, accurately identify changes in soil hardness and moisture, and provide precise soil mechanical parameter support for prickle growth.

[0075] In step 3, by monitoring the rate of change in the reconstructed pod volume and comparing it with the temporal relationship of the canopy spectral senescence index, early warning signals of nutrient transport imbalance can be generated in a timely manner. The three-dimensional morphological data of the pods is used to extract the change characteristics of the surface area to volume ratio. If the trend of this change meets the criteria for determining the maturity inflection point, it further verifies whether the vascular bundles inside the pod have begun to brown. Through scientific data analysis and model prediction, accurate prediction of the entire peanut growth process can be achieved, optimizing the harvesting timing. The judgment of the vascular bundle browning state provides a basis for timely output of harvesting instructions, avoiding increased shriveled pod rate or the risk of sprouting in the field due to improper harvesting timing.

[0076] In this embodiment of the invention, real-time non-destructive monitoring of underground pods is achieved through dual-band radar and high-frequency echo signal compensation technology, solving the problems of data distortion and periodic monitoring in traditional methods. Real-time monitoring of compressive stress changes during pod penetration using strain sensors effectively analyzes soil physical properties, providing real-time soil mechanics data support for pod growth. Combining the temporal changes in pod volume change rate and canopy spectral aging index provides a scientific early warning mechanism for nutrient transport imbalance, improving the accuracy of decision-making during peanut growth. By judging three-dimensional morphological changes and vascular bundle browning status, the increased rate of unfilled pods or the risk of sprouting due to premature or late harvesting is effectively avoided, ensuring the accuracy of peanut physiological maturity and harvest timing.

[0077] In summary, the method of this invention solves several technical problems in peanut growth monitoring, significantly improves the accuracy of monitoring and the reliability of data, and can provide strong support for intelligent management of peanut planting.

[0078] In one possible implementation, during the peanut flowering period, the spacing of healthy pegs is continuously monitored, and data on peg spacing during growth is collected. Specifically, the minimum spacing value is measured when the pegs begin to swell. This minimum spacing value typically represents a growth marker in the early stages of peg development. This minimum spacing value is then multiplied by a safety factor to obtain a threshold value. This threshold value can be used to determine whether the pegs have reached the swelling stage, providing a trigger condition for subsequent 3D reconstruction.

[0079] The core of 3D reconstruction lies in accurately acquiring peg growth information through high-frequency echo signals. When the amplitude of the signal returned by the high-frequency electromagnetic waves emitted by the radar array reaches its maximum gradient, that point is identified as the growth center of the pod. Based on this center, the reconstruction area is gradually expanded according to the attenuation direction of the signal gradient. This method ensures that the 3D morphology of the pod is comprehensively and accurately constructed, reflecting the morphological changes of the pegs and their spatial distribution of growth.

[0080] To ensure high accuracy in 3D reconstruction, the point cloud density is dynamically adjusted based on the spatial variability coefficient of the soil's dielectric constant. The soil's dielectric constant is an important physical parameter reflecting the distribution of moisture in the soil and its influence on electromagnetic waves. A larger spatial variability coefficient of the soil's dielectric constant indicates more significant variations within the soil, resulting in greater differences in the penetration and reflection characteristics of electromagnetic waves. Therefore, it is necessary to increase the point cloud density accordingly to ensure sufficient detailed data in areas with significant soil variations, thereby guaranteeing the accuracy of the 3D reconstruction.

[0081] By statistically analyzing the minimum spacing of healthy fruit pods and setting a threshold using a safety factor, it is possible to accurately determine whether the pods have entered the swelling stage, thereby precisely triggering the 3D reconstruction of the pods. Using the maximum gradient point of the high-frequency echo signal as the pod growth center and expanding the reconstruction area according to the signal attenuation direction, morphological changes in the pods can be captured comprehensively and accurately, providing high-precision 3D data. The point cloud density is dynamically adjusted based on the spatial variation coefficient of the soil dielectric constant to ensure that more detailed information is obtained in areas with significant soil variations, thereby improving the accuracy and reliability of the reconstruction.

[0082] Through the above technical steps, this method can achieve high-precision intelligent monitoring of the peanut growth process, effectively provide scientific growth data, optimize agricultural management decisions, and improve the level of intelligence in peanut production.

[0083] In one possible implementation, the strain sensing device employs a concentric ring structure, where the diameters of the inner and outer rings are set based on different calibration data. The diameter of the inner ring is set according to the diameter of the peanut pod during the flowering stage, because changes in the pod diameter directly affect the stress distribution during soil penetration, ensuring that the inner ring sensor can accurately monitor the initial penetration state of the pod. The diameter of the outer ring is set based on the maximum pod enlargement diameter from historical data, ensuring that the outer ring can monitor soil changes over a wider range during pod growth, especially the stress fluctuations that the pod may experience during penetration. This design allows for comprehensive collection of pod growth data at different stages, thereby accurately obtaining the interaction force between the pod and the soil.

[0084] In the calibration experiment, to establish the criteria for determining a needle bending event, simulated needles were inserted into soils of different textures. The waveform of the compressive stress change rate when the needle underwent permanent deformation was observed and recorded. This experimental method allows us to understand the stress variation characteristics of the needle during penetration under different soil conditions. In particular, when the needle experiences significant soil resistance, the compressive stress fluctuates drastically, leading to bending or permanent deformation. By analyzing the waveform, the duration, slope extremes, and other characteristic ranges can be extracted and used as criteria for determining whether a needle bending event has occurred. This determination method, combining experimental data and stress waveform characteristics, can accurately identify the bending state of the needle, providing important evidence for subsequent soil mechanics analysis and growth monitoring.

[0085] The embodiments of the present invention provide strong support for intelligent growth monitoring of peanuts through precise strain monitoring and peg bending determination technology. This not only improves the monitoring accuracy of the growth process, but also provides more data support and decision-making basis for agricultural production.

[0086] In one possible implementation, firstly, a unit area needs to be defined within the study region, and the growth of all pegs within this area should be monitored, particularly whether bending events occurred during peg growth. Peg bending events are an important indicator, reflecting soil compaction and the resistance to peg growth within the soil. A higher ratio of the number of peg bending events per unit area to the total number of pegs indicates poor soil permeability and greater resistance encountered by the pegs during penetration. This ratio can be used to preliminarily determine soil permeability.

[0087] To more accurately calculate soil permeability, a soil compaction compensation factor needs to be obtained through calibration tests. The calibration test procedure includes: measuring the penetration resistance of soils with different textures under controlled moisture content conditions; selecting the linear segment of the curve by measuring the penetration resistance curve for each soil type, and obtaining the slope of that segment; then, using the ratio of this slope to the slope of the reference soil as the compensation factor. This compensation factor reflects the degree of soil compaction and provides necessary corrections for subsequent soil permeability assessments.

[0088] Ultimately, the soil permeability index is calculated as: 1 minus the product of the bending event rate and the compensation factor. Specifically, a higher bending event rate indicates greater soil resistance and poorer soil permeability; the compensation factor is adjusted based on soil compaction, making the index more accurately reflect the actual permeability of the soil. This formula yields a quantitative soil permeability index, which can guide adjustments to soil management and crop planting strategies in agricultural production.

[0089] This method enables precise soil monitoring and optimized management in farmland, improving the efficiency and sustainability of agricultural production.

[0090] In one possible implementation, the pod volume change rate is first calculated by the difference in convex hull volume between the pod point cloud over two days. Specifically, on each monitoring day, three-dimensional point cloud data of the pods is acquired using point cloud reconstruction technology. Based on the data from two adjacent days, the volume difference is obtained by calculating the change in the convex hull volume of the point cloud. The convex hull volume is determined by enclosing the point cloud data within a minimal convex polyhedron, thus accurately representing the shape and volume of the pods. By calculating the change in pod volume over two days, the pod volume change rate is obtained. This rate reflects the pod's growth rate and health status. If the rate is greater than a certain set typical value, it indicates that the pods have not shown any abnormalities during growth; conversely, a lower rate may indicate problems during growth, such as nutrient transport imbalances.

[0091] The canopy spectral senescence index is calculated by monitoring canopy reflectance. Daily, reflectance data of the canopy is collected in two specific wavelength bands: one sensitive to chlorophyll and the other sensitive to leaf structure. The reflectance in these two bands reflects the plant's growth status. First, the change in reflectance in these two bands is calculated over two days, then compared to the baseline difference of healthy plants during the flowering period, yielding the ratio of diurnal changes. The canopy spectral senescence index, by reflecting these reflectance changes, can effectively determine the degree of plant senescence. Generally, changes in chlorophyll content are closely related to the plant's nutritional status and growth rate. When the spectral senescence index is too low, it may indicate malnutrition or other abnormal growth phenomena in the plant.

[0092] Based on the two indicators mentioned above, a warning of nutrient transport imbalance is triggered when the pod volume change rate exceeds the typical value during vigorous growth and the canopy spectral senescence index is below a set critical value. Specifically, if the pods exhibit excessively rapid volume growth during the expected growth stage, and the canopy senescence index is too low, it may indicate that the plant is experiencing nutrient transport problems during growth, such as limited root absorption or leaf photosynthesis, resulting in ineffective nutrient supply to growing parts. This condition can lead to uneven plant growth and even affect the final yield.

[0093] This early warning mechanism enables the timely detection of potential problems during critical peanut growth periods, effectively guiding agricultural management and improving the precision and efficiency of peanut planting.

[0094] In one possible implementation, three-dimensional data of the pods are acquired daily using point cloud reconstruction technology. The point cloud data reflects the shape and structure of the pods, allowing for the calculation of their surface area and volume. The surface area to volume ratio, which reflects the pod's ripening process, is the ratio of its surface area to its volume. During ripening, the pod's volume increases, but the surface area changes relatively little; therefore, the surface area to volume ratio gradually decreases. Continuously monitoring changes in this ratio provides a basis for determining the ripening time.

[0095] To more accurately pinpoint the inflection point of pod ripening, it is necessary to record the change in the surface area to volume ratio over three consecutive days. The surface area to volume ratio is calculated each day and compared with the data from the previous two days to obtain the change in the ratio. The trend of this change reflects whether the pods have entered the ripening stage. If the trend of the ratio changes steadily or slows down over three consecutive days, and the magnitude of the change gradually decreases, it may mean that the pods are beginning to ripen.

[0096] The criteria for determining the maturity inflection point are that the absolute value of the change in the ratio is less than the stability threshold, and the trend of change changes from positive to negative. When the change in the ratio is less than the set stability threshold, and the trend reverses from increasing to decreasing, it indicates that the growth rate of the pods has slowed down, and the maturation process has begun. This change marks the pods entering the maturity stage, which can accurately predict the peanut harvesting time.

[0097] The stability threshold is set according to the characteristics of different peanut varieties. Specifically, during the milk stage, the fluctuation range of the surface area-to-volume ratio of healthy pods is continuously measured. By statistically analyzing multiple measurements, the maximum fluctuation range of the pod surface area-to-volume ratio is determined, and this percentage is used as the stability threshold. In this way, the threshold can be dynamically adjusted according to the growth characteristics of different varieties, thereby improving the accuracy of maturity determination.

[0098] The above methods can be used to accurately identify the maturity stage of peanuts during their growth, thereby improving the precision of farmland management and the efficiency of agricultural production.

[0099] In one possible implementation, within 48 hours of determining that the peanuts have reached maturity, a monitoring point is randomly selected as the verification location. By randomly selecting points around the pods, coverage of pods in different locations can be ensured, avoiding bias in local samples. A miniature imaging probe is inserted into the selected monitoring point. This probe is small and precise, and it does not interfere with the natural state of the pods, facilitating continuous monitoring without causing damage during growth.

[0100] After the monitoring point is inserted, the miniature imaging probe advances along the peanut needle trajectory until it reaches the pod area. The needle trajectory refers to the growth path from the plant stem to the pod. By following this trajectory, the probe can penetrate deep into the core area of ​​the pod, ensuring accurate detection of changes inside the pod, especially for early warning of vascular bundle browning.

[0101] Once the probe reaches the pod area, it enters the browning feature recognition mode. In this mode, the probe's operation is adjusted to focus on recognizing browning features, using spectral analysis technology to detect biochemical changes inside the pod shell. Vascular bundle browning is an important marker of maturation, usually accompanied by physiological changes within the plant, such as the cessation of nutrient flow and the occurrence of oxidation reactions. Therefore, the detection of this feature can effectively verify the maturity status.

[0102] The probe emits a light source of a specific wavelength to illuminate the inside of the pod shell. Because the pod shell is sealed, the spectral response of the inside can better reflect the physiological state of the pod. Under the illumination of the specific wavelength light source, the browning components inside the pod absorb and reflect light of that specific wavelength. Therefore, by analyzing the data in the reflectance spectrum, key information about the degree of browning can be obtained.

[0103] The probe receives the light signal reflected from the inside of the pod shell and analyzes the intensity of characteristic bands in the spectrum. Browning typically causes pigment changes in plant tissues, resulting in specific intensity variations in the spectrum, especially within the wavelength range associated with browning. By monitoring the intensity of these bands, details of plant physiological changes can be accurately captured.

[0104] When the proportion of characteristic bands associated with browning in the detected reflectance spectrum exceeds a threshold set for the specific peanut variety, the pods can be considered mature. This threshold is determined based on the physiological characteristics of different peanut varieties, using large-scale experimental data to identify the reflectance spectral characteristics of each variety at maturity.

[0105] By using miniature imaging probes and spectral analysis technology, physiological changes inside the pods can be detected with high precision and without damage, especially the browning of vascular bundles, a sign of maturity. This allows for accurate assessment of peanut maturity, avoiding errors caused by manual visual inspection. The use of miniature imaging probes ensures that the monitoring process does not interfere with the natural growth of the crop, guaranteeing continuous data acquisition and enabling long-term monitoring without damaging the crop.

[0106] By setting specific reflectance spectral thresholds for each peanut variety, the method can flexibly adapt to the growth characteristics of different varieties, improving the accuracy and universality of the assessment. This method can provide farmers with scientific and timely information on peanut maturity, helping them to harvest at the optimal time and avoid the negative impacts of harvesting too early or too late on yield and quality, thereby improving the efficiency and quality of agricultural production.

[0107] In one possible implementation, at the beginning of the flowering period, the diameter of the base of the fruit pegs on the main stem of 10 healthy plants is first measured. This measurement process involves using precise tools to measure the base of the fruit pegs on the main stem of each plant individually, obtaining the diameter data for the base of the fruit pegs for each plant. Next, the arithmetic mean of the base diameters of the fruit pegs from these 10 plants is calculated, and this average is used as the calibration value for the inner ring during the flowering period. This calibration value serves as the benchmark for the inner ring diameter of the concentric ring structure throughout the monitoring process, ensuring that the setting of the inner ring during the flowering period conforms to the actual growth conditions of most healthy plants, thereby avoiding measurement errors caused by abnormal growth in individual plants.

[0108] As peanuts grow, the size of the pods gradually increases. At this point, the outer ring diameter expansion mechanism plays a crucial role. When the maximum diameter obtained by reconstructing the pod point cloud reaches a set proportion of the current outer ring diameter, the system automatically updates the outer ring diameter to the product of the current maximum pod diameter and the expansion coefficient. The expansion coefficient is set based on factors such as plant growth patterns, variety characteristics, and climatic conditions, ensuring that the expansion of the outer ring diameter adapts to the growth patterns and changes of the peanut pods. Through this dynamic adjustment mechanism, the size of the outer ring can be updated in real time, ensuring that the monitoring range always covers the maximum range of the peanut pods during growth.

[0109] Through the above method, the present invention can achieve precise monitoring of the peanut growth process, enabling the plant's growth characteristics to be captured comprehensively and accurately, thereby providing a more scientific basis for agricultural production decisions.

[0110] In one possible implementation, in a laboratory setting, the spectral data of the reflected light from peanut pods at different maturity levels are analyzed by performing spectral scanning. Peanut pods at different maturity levels exhibit different physiological changes, especially in the browned areas, where the characteristic bands of the reflectance spectrum differ significantly from those in the non-brown areas. In the experiment, multiple batches of samples, covering pods at different stages from immature to fully mature, were selected and systematically spectrally scanned. Based on the scanning results, the band intervals with the greatest difference in reflectance between the browned and non-brown areas were determined. These band intervals are closely related to the degree of browning and can effectively reflect the browning changes of peanut pods during growth.

[0111] After identifying the characteristic band, the intensity of the characteristic band is compared to the intensity of a reference band. The reference band is typically a spectral range that does not exhibit browning characteristics; this band is used for comparison with the characteristic band. By calculating the intensity ratio of the characteristic band to the reference band, a browning index is obtained. This ratio quantifies the degree of browning in the pods. As the pods mature, the reflectance of the characteristic band gradually increases, while the intensity of the reference band changes relatively little; therefore, their ratio reflects the progress of pod browning.

[0112] During the peak peanut harvest season, samples from different peanut varieties are collected, with a focus on analyzing samples whose kernel dry weight meets the biological maturity standard. At this stage, the pods in the samples are close to biological maturity, thus providing accurate data for calibrating browning indices. The lowest browning index value among these samples is selected as the threshold. This threshold represents the minimum standard for peanut maturity; any browning index below this value indicates that the pods are not yet fully mature. When the browning index of the pods exceeds this threshold, it indicates that the peanuts have entered the mature stage and are suitable for harvesting.

[0113] The browning feature recognition mode of this invention can achieve high-precision monitoring of peanut maturity, has significant agricultural application value, and can provide a more scientific management method for modern agriculture.

[0114] In one possible implementation, after the peanut plants enter the maturity stage and pass the maturity inflection point, the system will collect and analyze meteorological data in real time for the next 72 hours. The meteorological data includes information such as temperature, humidity, rainfall probability, and wind speed. Rainfall probability, in particular, will become an important reference factor for optimizing the harvest time. This process typically relies on real-time data from meteorological stations or climate forecast information provided by remote sensing technology. In this way, harvesting instructions can be dynamically adjusted to ensure timely harvesting even under unfavorable weather conditions, avoiding the impact of severe weather on the harvested crop.

[0115] Based on collected meteorological data, when the probability of rainfall exceeds a preset risk threshold, it indicates impending heavy or continuous precipitation, which may affect the peanut harvesting time. To prevent negative impacts from rainfall on soil moisture and peanut quality, the harvesting time needs to be adjusted promptly. The specific amount of time needed to advance the harvesting time is determined based on the expected rainfall time, typically by a certain amount of time before the rainfall arrives. This adjustment helps avoid difficulties in mechanical harvesting due to excessively moist soil or damp peanut pods, reducing harvest risk.

[0116] To ensure the quality and safety of peanut harvesting, the specific timing for early harvesting needs to be adjusted based on changes in soil moisture content under different rainfall intensities. Based on historical meteorological data and statistical analysis of soil moisture content, the system can accurately calculate the shortest time required for soil moisture content to recover to a safe range for mechanical harvesting under different rainfall intensities. This data primarily comes from long-term monitoring of historical meteorological and soil moisture changes, combined with the experience of agricultural experts, forming a formula that accurately reflects the relationship between soil moisture and rainfall intensity. When a rainfall warning occurs, the system calculates the early harvesting time based on the actual rainfall intensity and automatically optimizes the harvesting plan to ensure that harvesting is completed at the most appropriate time.

[0117] The optimized harvesting command method, through precise analysis of meteorological data, scientific assessment of soil moisture, and reasonable adjustment of harvesting time, can ensure efficient and safe peanut harvesting in complex climatic environments, providing effective decision support for modern agricultural management.

[0118] The following examples will illustrate this in detail:

[0119] This embodiment takes peanuts grown in an agricultural production base as an example to describe in detail how to optimize the harvesting time by using meteorological data, soil data and historical experience to ensure that peanuts can be harvested at the best time and avoid the adverse effects of rainfall on the harvesting process.

[0120] Located in a temperate monsoon climate zone with relatively even annual rainfall, the base is prone to sudden rainfall during the peanut ripening period, which can affect harvesting. Therefore, this invention uses real-time meteorological monitoring and data analysis to adjust the harvesting time in advance, ensuring efficient harvesting and peanut quality.

[0121] Within 72 hours of peanuts entering the ripening stage, the following data were acquired in real time:

[0122] Meteorological data:

[0123] Rainfall probability: Rainfall probability data provided by the meteorological station, predicting rainfall conditions for the next 72 hours.

[0124] Temperature and humidity: Real-time temperature and humidity data are obtained through weather stations or online platforms to analyze the potential impact on soil moisture.

[0125] Soil data:

[0126] Soil moisture: The soil moisture content is monitored in real time using a soil moisture sensor.

[0127] Soil temperature: Monitor soil temperature to assess the rate of soil moisture evaporation.

[0128] In this embodiment, a preset risk value of 70% for the probability of rainfall is set. That is, when the probability of rainfall in the next 72 hours exceeds 70%, the system will automatically adjust the harvesting time.

[0129] When the probability of rainfall exceeds 70%, the harvest time will be brought forward: To ensure that the soil moisture is not too high before harvest, the advance harvest time needs to be calculated using the following formula:

[0130] ;

[0131] in, This represents the shortest time required for soil moisture content to recover to a safe range for mechanical harvesting. Historical data analysis reveals the relationship between the time required for soil moisture to recover to a safe harvesting range and rainfall intensity. Based on past meteorological data, the following formula is derived:

[0132] ;

[0133] For example, if the predicted rainfall intensity is 50 mm / hour, the time required for soil moisture recovery is:

[0134] ;

[0135] This means that if the rainfall intensity is 50 mm / hour, the harvest time should be 5 days earlier.

[0136] To achieve more precise harvesting timing adjustments, this embodiment introduces a soil moisture recovery model based on rainfall intensity. By analyzing the impact of different rainfall intensities on soil moisture, the time required for the soil to recover to a safe harvesting range under different rainfall intensities is determined. The specific model is as follows:

[0137] ;

[0138] in: The time it takes for the soil to recover to a safe harvesting range (unit: hours). This is the rainfall intensity coefficient. Original soil moisture content (unit: %). Standard recovery time (in hours) based on historical data statistics.

[0139] For example, if the rainfall intensity is 40 mm / hour and the initial soil moisture content is 18%, calculations based on historical data and models yield the following results:

[0140] ;

[0141] The harvesting time optimization method of this invention has significant advantages over traditional harvesting methods. Traditional methods usually do not consider the impact of rainfall on harvesting, and often excessive soil moisture causes mechanical equipment to malfunction or delays harvesting time, thereby reducing the quality and yield of peanuts.

[0142] Comparative experiment:

[0143] Experiment 1 (Traditional Harvesting Method):

[0144] Harvesting time: Harvest peanuts 72 hours after they are fully mature.

[0145] Results: Due to excessive soil moisture caused by rainfall, mechanical harvesting was difficult, some peanuts were damaged, peanut quality declined, and overall yield decreased by about 15%.

[0146] Experiment 2 (Harvesting Method of This Invention):

[0147] Harvesting time: Through the optimization of the method of the present invention, the harvesting time can be advanced by 4 days.

[0148] Results: Harvesting proceeded smoothly, soil moisture remained within a safe range, peanut quality was maintained well, and yield increased by 18%.

[0149] Preset risk value for rainfall probability: 70%.

[0150] Model of the time required for soil moisture to recover to a safe range for mechanical harvesting:

[0151] Soil recovery time Rainfall intensity and soil moisture A joint decision.

[0152] Rainfall intensity: Provided by meteorological data, in millimeters per hour.

[0153] Harvest advance time: Based on rainfall intensity and historical data, the time required for the soil to recover to a safe harvesting range is calculated, thereby determining the harvest time.

[0154] This embodiment combines meteorological and soil data, employing a soil moisture recovery model to optimize harvesting timing, thus avoiding soil over-wetting caused by rainfall and improving harvesting efficiency. Compared to traditional harvesting methods, this invention not only improves harvesting efficiency but also significantly enhances peanut quality and yield. By adjusting the harvesting time in advance, it ensures that peanuts are harvested under optimal conditions, fully demonstrating the innovation and practical application value of this invention.

[0155] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0156] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for intelligent monitoring of peanut growth, characterized in that, Includes the following steps: Step 1: Collaborative monitoring of underground organs: By simultaneously transmitting electromagnetic waves with different penetration depths using a dual-band radar array deployed on peanut planting ridges, the soil attenuation effect of high-frequency echoes is compensated based on low-frequency echo signals. The spatial coordinates of the fruit needle tip are identified based on the abrupt change point of the compensated high-frequency echo amplitude. When the distance between adjacent fruit needles collected over several consecutive days is less than the critical threshold for pod enlargement, 3D reconstruction of the pod is triggered. Step 2: Analysis of soil mechanical behavior: Strain sensing devices are deployed based on the coordinates of the fruit needle tip to monitor the changes in radial compressive stress during the fruit needle penetration process in real time. When the compressive stress change characteristics meet the criteria for determining the fruit needle bending event, the soil permeability index is generated by combining the calibration test data. Step 3: Cross-media growth decision: Based on the temporal relationship between the reconstructed pod volume change rate and the canopy spectral aging index, an early warning of nutrient transport imbalance is generated. Extract the surface area-to-volume ratio variation characteristics of the three-dimensional morphology of the pods. When the trend of change meets the criteria for determining the maturity inflection point, verify the browning state of the vascular bundles inside the pods and output the harvesting command. The specific process for triggering the 3D reconstruction of the pod includes: The method for determining the critical threshold for pod enlargement is as follows: during the peanut flowering period, the distance between healthy pods is continuously measured, the minimum distance value when the pods begin to enlarge is statistically analyzed, and this value is multiplied by a safety factor as the threshold benchmark. The three-dimensional reconstruction is performed as follows: taking the point with the maximum value of the high-frequency echo amplitude gradient as the pod growth center, the reconstruction area is expanded according to the gradient decay direction. The reconstruction accuracy control method is as follows: the point cloud density is dynamically adjusted according to the spatial variation coefficient of the soil dielectric constant; the larger the variation coefficient, the higher the point cloud density. The deployment and monitoring of the strain sensing device include: The sensing device adopts a concentric ring structure. The diameter of the inner ring is set according to the calibrated value of the fruit needle diameter during the flowering period, and the diameter of the outer ring is set according to the maximum enlarged diameter of the pod in historical data. The method for establishing the judgment condition of the fruit needle bending event is as follows: In the calibration test, simulated fruit needles are inserted into soils of different textures, the waveform of the compressive stress change rate when the fruit needle undergoes permanent deformation is recorded, and the characteristic range of duration and slope extreme values ​​in the waveform is extracted as the judgment condition. The generation of the soil permeability index includes: Statistical analysis of the number of fruit needle bending events per unit area and the total number of fruit needles; Soil compaction compensation factor was obtained through calibration test: the penetration resistance curves of soils with different textures were measured under controlled moisture content conditions, and the ratio of the slope of the linear segment of the curve to the slope of the reference soil was used as the compensation factor. The index is calculated as: 1 minus the product of the bending event occurrence rate and the compensation factor; The triggering logic for the nutrient transport imbalance warning: The rate of change of pod volume was calculated by the difference in convex hull volume between the reconstructed pod point clouds on two consecutive days. Method for obtaining the canopy spectral senescence index: Collect the reflectance of the canopy in the chlorophyll-sensitive band and the leaf structure-sensitive band daily, calculate the difference in the diurnal variation of the reflectance in the two bands, and then divide it by the corresponding difference benchmark of healthy plants in the flowering period. An early warning is triggered when the volume change rate is greater than the typical value during the vigorous growth period and the spectral aging index is lower than the critical value. The specific method for determining the maturity inflection point is as follows: Calculate the surface area-to-volume ratio of the reconstructed pod point cloud daily and record the change in the ratio over three consecutive days; When the absolute value of the change is less than the stability threshold and the trend of change changes from positive to negative, it is determined to be an inflection point. The stability threshold is set according to the pod variety: the surface area to volume ratio of healthy pods is continuously measured during the milk stage, and the percentage value of the maximum fluctuation is taken. The verification of the browning state of the vascular bundles includes: Within 48 hours after the inflection point is determined, a miniature imaging probe is inserted at a randomly selected monitoring point; After the probe reaches the pod area along the fruit needle trajectory, it switches to the browning feature recognition mode: 1) Irradiate the inside of the pod shell with a light source of a specific wavelength; 2) Collect the intensity of characteristic bands related to browning in the reflectance spectrum; Maturity is confirmed when the intensity ratio of characteristic bands exceeds the variety-related threshold.

2. The method for intelligent monitoring of peanut growth according to claim 1, characterized in that, The dynamic adjustment method of the concentric ring structure: Method for setting the inner ring diameter during the flowering period: Measure the diameter of the base of the fruit needle on the main stem of 10 healthy plants and take the arithmetic mean as the calibration value; Outer ring diameter expansion mechanism: When the maximum diameter of the reconstructed pod point cloud reaches the set ratio of the current outer ring diameter, the outer ring diameter is automatically updated to the current maximum diameter multiplied by the expansion coefficient.

3. The method for intelligent monitoring of peanut growth according to claim 1, characterized in that, The process of identifying browning feature patterns: Feature band selection method: In the laboratory, spectral scanning of pod shells at different maturity levels was performed to determine the band interval with the greatest difference in reflectance between browned and non-browned areas; Intensity ratio calculation: The ratio of the intensity of the characteristic band to the intensity of the reference band is used as the browning index; Calibration of variety-related thresholds: Samples are taken during the peak harvest period, and the minimum browning index value in the samples whose dry grain weight reaches the biological maturity standard is set as the threshold.

4. The method for intelligent monitoring of peanut growth according to claim 1, characterized in that, The optimization method for the harvesting command: Obtain meteorological data within 72 hours after the maturity inflection point; When the probability of rainfall exceeds the preset risk value, the harvesting time will be brought forward to a specific time before the rainfall. The determination of the specific duration: based on historical data, the shortest time required for soil moisture content to recover to a safe range for mechanical harvesting under different rainfall intensities.

Images