Intelligent control method and system for plant growth lamp based on biological rhythm

Abstract

The invention relates to the technical field of intelligent agricultural lighting, and discloses a plant growth lamp intelligent control method and system based on biological rhythm. The method comprises the following steps: collecting physiological data of leaves and roots and environmental temperature and humidity, and removing anomalies to obtain multi-organ and environmental original data; extracting a leaf and root rhythm curve through rhythm analysis to obtain time difference characteristics; calculating a rhythm peak offset to obtain an accurate phase difference, and generating a preliminary illumination scheme in combination with a plant growth stage if the phase difference exceeds a threshold value; and fusing an environment data optimization scheme, comparing with a preset circadian rhythm to correct parameters, and finally driving the growth lamp to output a control instruction. Dynamic adaptation of illumination and biological rhythm is achieved, and the light energy utilization rate and the plant growth quality stability are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent agricultural lighting, and in particular to an intelligent control method and system for plant growth lights based on biological rhythms. Background Technology

[0002] Currently, in the fields of modern agriculture and protected horticulture, new lighting technologies, by simulating natural light patterns to regulate plant growth, have become a core means of improving crop yield and quality. They play a crucial role in plant factories, greenhouses, and other settings, dynamically adjusting light parameters according to plant needs to adapt to their growth cycles. With the development of precision agriculture, the requirements for the synergy between light and plant physiological rhythms, environmental adaptability, and the precision of regulation are increasingly stringent.

[0003] In one existing technology, plant growth lights are mostly controlled by a fixed light period and light intensity mode. They are periodically output by preset light time and intensity parameters, and only simple parameter switching is performed according to the plant growth stage. They lack targeted adaptation to the differences in the biological rhythms of plant organs such as leaves and roots.

[0004] However, fixed-parameter models cannot capture the dynamic changes in the rhythms of multiple plant organs in real time, making it difficult to precisely regulate light based on the time difference between leaf photosynthesis and root nutrient absorption. When environmental temperature and humidity fluctuate or plants enter different growth stages, a mismatch between light supply and physiological needs can easily occur, leading to low light energy utilization efficiency. Therefore, existing technologies suffer from insufficient adaptability between light regulation and plant biological rhythms. Summary of the Invention

[0005] This invention provides a method and system for intelligent control of plant growth lights based on biological rhythms, in order to solve the problem of insufficient adaptability of light regulation to plant biological rhythms in the prior art.

[0006] In a first aspect, the present invention provides an intelligent control method for plant growth lights based on biological rhythms, comprising: Data on leaf photosynthesis, root nutrient absorption, and environmental temperature and humidity were collected and outliers were removed to obtain raw data on multiple organs and the environment. Rhythm analysis was performed on the raw data of the multiple organs and environment to extract leaf rhythm curves and root rhythm curves, and rhythm time difference characteristics were obtained. The time offset between the peak rhythms of the leaves and roots is calculated based on the rhythm time difference characteristics, and the precise phase difference is obtained by quantification. If the precise phase difference exceeds the preset phase difference threshold, a preliminary light control scheme is generated based on the light requirements of the plant growth stage. By integrating the environmental temperature and humidity data with the circadian rhythm time difference characteristics, the preliminary light control scheme is optimized to obtain the adjusted control scheme. The adjusted control scheme is compared with the preset diurnal rhythm to verify and update the illumination parameters, thereby obtaining the corrected illumination parameter set. The growth lamp controller is driven to execute outputs based on the modified light parameter set, generating the final control command.

[0007] In one optional implementation, the step of collecting leaf photosynthesis data, root nutrient absorption data, and environmental temperature and humidity data through a sensor array to obtain raw data on multiple organs and the environment includes: Data on leaf photosynthesis, root nutrient absorption, and environmental temperature and humidity are collected using a sensor array to form multi-source raw monitoring data. Outlier removal and unified timestamp format are performed on the multi-source raw monitoring data to obtain standardized raw data; The standardized raw data are integrated to generate raw data for multiple organs and the environment.

[0008] In one optional implementation, the step of performing rhythm analysis on the raw data of the multiple organs and the environment, extracting leaf rhythm curves and root rhythm curves, and obtaining rhythm time difference characteristics includes: The physiological parameter time series of leaves and roots were separated from the original data of the multiple organs and environment to obtain organ-specific data; Periodic analysis is performed on the organ data to extract the peak time and period length of the rhythm of leaves and roots, generating leaf rhythm curves and root rhythm curves. For the leaf rhythm curve and the root rhythm curve, calculate the peak time difference to obtain the initial time difference characteristics; The initial time difference characteristics are corrected by combining environmental temperature and humidity data to determine the final rhythmic time difference characteristics.

[0009] In one optional implementation, the step of calculating the time offset between the peak of leaf and root rhythm based on the rhythm time difference characteristics and quantifying it to obtain a precise phase difference includes: Calculate the initial time offset based on the peak time points of the leaf and root rhythms in the rhythm time difference characteristics; If the initial time offset exceeds the preset offset threshold, the historical rhythm data is combined with smoothing to obtain the corrected offset. The correction offset is segmented and quantized to obtain the phase difference value for each time period; By integrating the phase difference values ​​from each time period, a precise phase difference is generated.

[0010] In one optional implementation, if the precise phase difference exceeds a preset phase difference threshold, a preliminary light control scheme is generated based on the light requirements of the plant's growth stage, including: Obtain the reference parameters of light intensity and photoperiod corresponding to the current growth stage of the plant; The precise phase difference is compared with a preset phase threshold. When the preset phase threshold is exceeded, it is determined that the plant's multiple organs are in a state of rhythm asynchrony. The light intensity is adjusted according to the rhythm asynchrony state, and a preliminary parameter adjustment sequence is generated by combining the light period reference parameter; By integrating the aforementioned preliminary parameter adjustment sequence, a preliminary illumination control scheme is formed.

[0011] In one optional implementation, the step of fusing the environmental temperature and humidity data with the circadian rhythm time difference characteristics to optimize the initial illumination control scheme and obtain the adjusted control scheme includes: The fluctuation values ​​of ambient temperature and humidity within a unit time are extracted from the original data of the multiple organs and environment to obtain the temperature and humidity fluctuation sequence. The temperature and humidity fluctuation sequence is compared with the rhythm time difference characteristics, and the correlation coefficient between the two is calculated to determine the degree of correlation. If the correlation degree exceeds a preset correlation threshold, the correction coefficients for the light intensity and light period reference parameters are calculated based on the correlation degree. Substitute the correction coefficient into the initial illumination control scheme, adjust the light intensity gradient and photoperiod parameters for each time period, and generate the adjusted control scheme.

[0012] In one optional implementation, the step of comparing the adjusted control scheme with a preset circadian rhythm, verifying and updating the illumination parameters to obtain a corrected illumination parameter set includes: The light parameters of the adjusted control scheme are compared with the standard parameters of the preset diurnal rhythm, and the deviation value is calculated. If the deviation value exceeds the preset deviation threshold, update the light intensity gradient and light period parameters; The updated light intensity gradient and light period parameter are subjected to time series smoothing to obtain a candidate illumination parameter set; Verify the feasibility of the candidate illumination parameter set and determine the corrected illumination parameter set.

[0013] In one optional implementation, the step of driving the growth lamp controller to execute outputs based on the modified illumination parameter set to generate final control commands includes: The corrected light intensity, light period and spectral ratio data are obtained from the set of corrected illumination parameters and converted into electrical signal parameters that can be recognized by the grow lamp controller to obtain the initial control signal. The matching degree between the initial control signal and the rated parameters of the growth lamp hardware is compared. If the matching degree is higher than the preset matching degree threshold, the signal is determined to be compliant, and a compliance status is obtained. Based on the compliance status and the initial control signal, the execution time period of each parameter is allocated according to the time axis, and a dynamic control sequence containing the light intensity change gradient and the start and end time of the light period is generated. Based on the dynamic control sequence and the real-time operation feedback data of the growth lamp, the parameter execution deviation rate is calculated. By comparing the deviation rate with the preset allowable range, an adjusted illumination control command is generated to obtain the final control output.

[0014] Secondly, the present invention provides an intelligent control system for plant growth lights based on biological rhythms, comprising: Data acquisition module: Collects data on leaf photosynthesis, root nutrient absorption, and environmental temperature and humidity, and removes outliers to obtain raw data on multiple organs and the environment; Rhythm extraction module: Performs rhythm analysis on the raw data of the multiple organs and environment, extracts leaf rhythm curves and root rhythm curves, and obtains rhythm time difference characteristics; Phase calculation module: Calculates the time offset between the peak of leaf and root rhythm based on the rhythm time difference characteristics, and quantifies it to obtain the accurate phase difference; Solution generation module: If the precise phase difference exceeds the preset phase difference threshold, a preliminary light control solution is generated based on the light requirements of the plant growth stage; Solution optimization module: By integrating the environmental temperature and humidity data with the circadian rhythm time difference characteristics, the initial light control scheme is optimized to obtain the adjusted control scheme; Parameter correction module: compares the adjusted control scheme with the preset diurnal rhythm, verifies and updates the illumination parameters, and obtains the corrected illumination parameter set; Control output module: Drives the growth lamp controller to execute output based on the modified light parameter set, generating the final control command.

[0015] Thirdly, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the intelligent control method for plant growth lights based on biological rhythms as described above.

[0016] Fourthly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the intelligent control method for plant growth lights based on biological rhythms described above.

[0017] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention collects physiological data of plant leaves and roots in real time, accurately extracts rhythmic time difference characteristics, breaks through the limitations of traditional fixed light parameters, and realizes dynamic adaptation of light regulation and plant biological rhythm. (2) This invention combines environmental temperature and humidity data to optimize the lighting scheme, and improves the accuracy of lighting control in complex environments by setting up a circadian rhythm model to verify parameters, thereby solving the problem of low light energy utilization efficiency caused by environmental fluctuations. (3) This invention significantly improves the targeting of plant growth lights to different growth stages and physiological needs of different organs through a closed-loop mechanism of “data acquisition-rhythm analysis-scheme generation-optimized output” combined with hardware compatibility verification, thereby promoting efficient plant growth. Attached Figure Description

[0018] Figure 1 This is a schematic flowchart of an intelligent control method for plant growth lights based on biological rhythms provided in the first embodiment of the present invention; Figure 2 This is a schematic diagram of the intelligent control system structure of a plant growth lamp based on biological rhythms, provided in the second embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Reference Figure 1 The first embodiment of the present invention provides a method for intelligent control of plant growth lights based on biological rhythms, including the following steps: S1 collects data on leaf photosynthesis, root nutrient absorption, and environmental temperature and humidity, and removes outliers to obtain raw data on multiple organs and the environment. S2, perform rhythm analysis on the original data of the multiple organs and environment, extract leaf rhythm curves and root rhythm curves, and obtain rhythm time difference characteristics; S3, calculate the time offset between the peak of leaf and root rhythm based on the rhythm time difference characteristics, and quantify the precise phase difference; S4. If the precise phase difference exceeds the preset phase difference threshold, a preliminary light control scheme is generated based on the light requirements of the plant growth stage. S5, integrate the environmental temperature and humidity data with the circadian rhythm time difference characteristics, optimize the preliminary light control scheme, and obtain the adjusted control scheme; S6. Compare the adjusted control scheme with the preset circadian rhythm, verify and update the illumination parameters, and obtain the corrected illumination parameter set. S7, drive the growth lamp controller to execute output according to the modified light parameter set, and generate the final control command.

[0021] In step S1, leaf photosynthesis data, root nutrient absorption data, and environmental temperature and humidity data are collected, and outlier removal is performed to obtain raw data for multiple organs and the environment, including: S11 collects data on leaf photosynthesis, root nutrient absorption, and environmental temperature and humidity through a sensor array to form multi-source raw monitoring data; S12, outlier removal is performed on the multi-source raw monitoring data, and the timestamp format is unified to obtain standardized raw data; S13, integrate the standardized raw data to generate multi-organ and environmental raw data.

[0022] In step S11, data on leaf photosynthesis, root nutrient absorption, and environmental temperature and humidity are collected through a sensor array to form multi-source raw monitoring data.

[0023] It should be noted that the sensor array includes leaf photosynthesis sensors, root monitoring sensors, and temperature and humidity sensors, which respectively collect the net photosynthetic rate and transpiration rate of the leaves, the ion absorption rate of the roots, and the ambient temperature (in °C) and relative humidity (in %). The data sampling interval is 1 minute, generating multi-source raw monitoring data containing multiple types of parameters.

[0024] For example, in a greenhouse strawberry growing scenario, the leaf photosynthesis sensor records the net photosynthetic rate (unit μmol CO2 / m²·s) every minute, the root sensor synchronously collects the potassium ion absorption rate (unit mmol / h), and the temperature and humidity sensor records environmental data. The three are combined to form multi-source raw monitoring data.

[0025] In step S12, outlier values ​​are removed from the multi-source raw monitoring data, and the timestamp format is standardized to obtain standardized raw data.

[0026] It should be noted that the outlier removal adopts the box plot method, and data exceeding 1.5 times the interquartile range are judged as outliers and removed; the timestamps are uniformly converted to the "year-month-day hour:minute:second" format to ensure the time consistency of data from different sensors, and the processed data retains the original physical quantity units.

[0027] For example, in the multi-source data of strawberry cultivation, the net photosynthetic rate at a certain moment was -10 μmol CO2 / m²·s (far below the normal range of 2-8 μmol CO2 / m²·s), which was identified as an outlier and removed. At the same time, all data timestamps were unified to "2024-07-01 10:00:00" to obtain standardized raw data.

[0028] In step S13, the standardized raw data is integrated to generate multi-organ and environmental raw data.

[0029] It should be noted that the integration of the standardized raw data to generate multi-organ and environmental raw data involves integrating leaf data, root data, and environmental temperature and humidity data at the same time, using timestamps as unique identifiers, and storing them together to form a structured data table containing four columns: time, leaf parameters, root parameters, and environmental parameters. This is the multi-organ and environmental raw data.

[0030] For example, based on the timestamp "2024-07-01 10:00:00", the net photosynthetic rate of strawberries at that time (5 μmol CO2 / m²·s), potassium ion absorption rate (0.8 mmol / h), temperature (28℃), and humidity (70%) are correlated and integrated to form a complete record in the original data of multiple organs and environment.

[0031] In step S2, rhythm analysis is performed on the raw data of the multiple organs and the environment to extract leaf rhythm curves and root rhythm curves, obtaining rhythm time difference characteristics, including: S21, Separate the time series of physiological parameters of leaves and roots from the original data of multiple organs and environment to obtain organ-specific data; S22, Perform periodic analysis on the organ data, extract the peak time and period length of the rhythm of leaves and roots, and generate leaf rhythm curves and root rhythm curves; S23, calculate the peak time difference for the leaf rhythm curve and the root rhythm curve to obtain the initial time difference characteristics; S24, combine the environmental temperature and humidity data to correct the initial time difference characteristics, and determine the final rhythm time difference characteristics.

[0032] In step S21, the time series of physiological parameters of leaves and roots are separated from the original data of multiple organs and environment to obtain organ-specific data.

[0033] It should be noted that the separation is based on data tags. From the structured raw data of multiple organs and environment, leaf-related physiological parameters, such as the time series of photosynthetic rate and stomatal conductance, and root-related physiological parameters, such as the time series of nutrient absorption rate and soil nutrient concentration, are screened out to form leaf data sequences and root data sequences, i.e., organ-specific data.

[0034] For example, from the raw data of multiple organs and environment of tomatoes, a 72-hour photosynthetic rate time series is extracted as a leaf data series, and the nutrient absorption rate time series during the same period is extracted as a root data series, thus obtaining organ-specific data.

[0035] In step S22, the organ data is periodically analyzed to extract the peak time and period length of the rhythm of leaves and roots, and to generate leaf rhythm curves and root rhythm curves.

[0036] It should be noted that the periodic analysis uses a cosine fitting algorithm to detect the rhythmic cycle of the time series of organ data, determine the rhythmic cycle length of the physiological activities of leaves and roots (e.g., 24 hours), and locate the rhythmic peak time within each cycle. For example, the leaves reach the photosynthetic peak at 12:00. Then, continuous leaf rhythm curves and root rhythm curves are generated through curve fitting.

[0037] For example, cosine fitting was performed on the leaf data sequence of cucumber to obtain its rhythm period of 24 hours, with the peak time at 11:00. The fitting generated a leaf rhythm curve reflecting the change of photosynthetic rate over time. Similarly, the root data sequence was processed to generate a root rhythm curve.

[0038] In step S23, the peak time difference is calculated for the leaf rhythm curve and the root rhythm curve to obtain the initial time difference characteristics.

[0039] It should be noted that the peak time difference is the time interval between the peak time point of the leaf rhythm curve and the peak time point of the root rhythm curve, in hours. This interval constitutes the initial time difference feature, which is used to reflect the degree of asynchrony between the peaks of the two rhythms.

[0040] For example, the peak time of the leaf rhythm curve is 10:00, and the peak time of the root rhythm curve is 14:00. The calculated peak time difference is 4 hours, that is, the initial time difference characteristic is 4 hours.

[0041] In step S24, the initial time difference characteristics are corrected by combining the environmental temperature and humidity data to determine the final rhythm time difference characteristics.

[0042] It should be noted that the correction is achieved by analyzing the correlation between environmental temperature and humidity fluctuations and the initial time difference characteristics. If temperature and humidity fluctuations have a significant impact on the circadian rhythm time difference, for example, if a 10% increase in humidity leads to a 0.5-hour increase in time difference, then the initial time difference characteristics are corrected according to the influence coefficient to obtain a more accurate final circadian rhythm time difference characteristics.

[0043] For example, the initial time difference characteristic is 4 hours. Analysis of environmental temperature and humidity data shows that the current temperature and humidity conditions make the actual time difference 0.3 hours smaller than the initial value. After correction, the final rhythm time difference characteristic is 3.7 hours.

[0044] In step S3, the time offset between the peak of leaf and root rhythms is calculated based on the rhythm time difference characteristics, and the precise phase difference is quantified, including: S31, Calculate the initial time offset based on the rhythm peak time points of the leaves and roots in the rhythm time difference characteristics; S32, if the initial time offset exceeds the preset offset threshold, the historical rhythm data is combined for smoothing to obtain the corrected offset. S33, the correction offset is segmented and quantized to obtain the phase difference value for each time period; S34, integrate the phase difference values ​​of each time period to generate an accurate phase difference.

[0045] In step S31, the initial time offset is calculated based on the peak time points of the leaf and root rhythms in the rhythm time difference characteristics.

[0046] It should be noted that the rhythm time difference feature includes the respective rhythm peak time points of the leaves and roots. For example, the peak time for leaves is 9:00 and the peak time for roots is 13:00. By calculating the difference between the two time points (in hours), the initial time offset reflecting the degree of initial asynchrony between the two is obtained.

[0047] For example, the peak time of leaf rhythm is extracted from the rhythm time difference features as 8:30 and the peak time of root rhythm is 12:00, and the initial time offset is calculated to be 3.5 hours.

[0048] In step S32, if the initial time offset exceeds a preset offset threshold, the data is combined with historical rhythm data for smoothing to obtain the corrected offset.

[0049] It should be noted that the preset offset threshold is set according to the plant species. For example, it is set to 3 hours for most crops. If the initial time offset exceeds this threshold, the historical rhythm data of the past 7 days is called up, and the moving average method is used to smooth the initial offset to reduce the impact of short-term fluctuations and obtain the corrected offset.

[0050] For example, the initial time offset is 4 hours (exceeding the threshold of 3 hours), and after combining the average offset of the past 7 days of 3.2 hours, the corrected offset is 3.6 hours after the moving average processing.

[0051] In step S33, the correction offset is segmented and quantized to obtain the phase difference value for each time period.

[0052] It should be noted that the segmented quantization decomposes the correction offset into different time periods according to time intervals (e.g., every 6 hours is a segment), calculates the phase difference between the leaf and root rhythms in each time period (in degrees, 360 degrees corresponds to a 24-hour cycle), and forms the phase difference value for each time period.

[0053] For example, the correction offset is 3.6 hours, calculated in 6-hour segments, resulting in a phase difference of 54 degrees for the 0-6 hour period. For other periods, the corresponding phase difference value is generated based on the actual offset trend.

[0054] In step S34, the phase difference values ​​of each time period are integrated to generate an accurate phase difference.

[0055] It should be noted that the integration is achieved through time series splicing, which combines the phase difference values ​​of each time period in chronological order to form a continuous phase difference sequence covering the entire cycle, i.e., precise phase difference, which can intuitively reflect the degree of rhythm synchronization between leaves and roots at different time periods.

[0056] For example, the phase difference values ​​for each time period (0-6 hours 54 degrees, 6-12 hours 48 degrees, 12-18 hours 50 degrees, 18-24 hours 52 degrees) are integrated to generate a precise phase difference sequence covering the entire day.

[0057] In step S4, if the precise phase difference exceeds a preset phase difference threshold, a preliminary light control scheme is generated based on the light requirements of the plant's growth stage, including: S41, obtain the light intensity and photoperiod baseline parameters corresponding to the current growth stage of the plant; S42, compare the precise phase difference with a preset phase threshold, and when it exceeds the preset phase threshold, determine that the plant's multiple organs are in a state of rhythm asynchrony; S43, adjust the light intensity according to the rhythm asynchrony state, and generate a preliminary parameter adjustment sequence in combination with the light period reference parameter; S44, Integrate the preliminary parameter adjustment sequence to form a preliminary illumination control scheme.

[0058] In step S41, the light intensity and photoperiod reference parameters corresponding to the current growth stage of the plant are obtained.

[0059] It should be noted that the light intensity and photoperiod baseline parameters are preset based on plant species and growth stage. For example, the light intensity is 200 μmol / m²·s and the photoperiod is 12 hours of light / 12 hours of darkness during the seedling stage. These parameters can be retrieved from historical plant growth parameter databases and used as initial reference standards for light regulation.

[0060] For example, for peppers in the flowering stage, the baseline light intensity is obtained from the database as 350 μmol / m²·s, and the photoperiod is 14 hours of light / 10 hours of darkness.

[0061] In step S42, the precise phase difference is compared with a preset phase threshold. When the preset phase threshold is exceeded, the plant's multi-organ rhythms are determined to be out of sync.

[0062] It should be noted that the preset phase threshold is set according to the physiological characteristics of plants. It is calculated based on the 24-hour diurnal rhythm corresponding to a 360° phase cycle. A 1-hour time difference corresponds to a 15° phase difference. The preset phase difference threshold for most vegetables is 30° (corresponding to a 2-hour time difference). For example, if the precise phase difference exceeds this threshold, it is determined that the leaf and root rhythms are out of sync and need to be corrected through light regulation.

[0063] For example, if the precise phase difference is 45° (corresponding to a time difference of 3 hours), which exceeds the preset threshold of 30° (corresponding to a time difference of 2 hours), it is determined that the chili pepper is in a state of multi-organ rhythm asynchrony.

[0064] In step S43, the light intensity is adjusted according to the rhythm asynchrony state, and a preliminary parameter adjustment sequence is generated by combining the light period reference parameter.

[0065] It should be noted that the light intensity adjustment is determined based on the degree of asynchrony. For example, the light intensity is increased by 10% every hour exceeding the threshold. While keeping the optical cycle reference parameter framework unchanged, a preliminary parameter adjustment sequence containing the light intensity values ​​of each time period is generated in segments according to time.

[0066] For example, the degree of dyssynchrony in chili pepper rhythm is 1 hour (3 hours - 2 hours). The light intensity is increased by 10% from the baseline value of 350 μmol / m²·s to 385 μmol / m²·s. Combined with a 14-hour light cycle, a preliminary parameter adjustment sequence with a light intensity of 385 μmol / m²·s per hour is generated from 0 to 14 hours.

[0067] In step S44, the preliminary parameter adjustment sequence is integrated to form a preliminary illumination control scheme.

[0068] It should be noted that the integration sorts out the preliminary parameter adjustment sequence along the time axis, clarifies the start time, end time of illumination, and light intensity parameters for each time period, and forms a structured preliminary illumination control scheme, providing a basic framework for subsequent optimization.

[0069] For example, the initial parameter adjustment sequence for chili peppers is integrated into an initial light control scheme of "6:00-20:00 daily, light intensity 385 μmol / m²·s; 20:00-6:00 the next day, light intensity 0 μmol / m²·s".

[0070] In step S5, the environmental temperature and humidity data are fused with the circadian rhythm time difference characteristics to optimize the initial illumination control scheme, resulting in an adjusted control scheme, including: S51, extract the fluctuation values ​​of ambient temperature and humidity per unit time from the original data of the multiple organs and environment to obtain the temperature and humidity fluctuation sequence. S52, compare the temperature and humidity fluctuation sequence with the rhythm time difference characteristics, calculate the correlation coefficient between the two, and determine the degree of correlation; S53, if the correlation degree exceeds a preset correlation threshold, calculate the correction coefficients for the light intensity and light period reference parameters based on the correlation degree; S54, Substitute the correction coefficient into the preliminary illumination control scheme, adjust the light intensity gradient and light period parameters for each time period, and generate the adjusted control scheme.

[0071] In step S51, the fluctuation values ​​of ambient temperature and humidity within a unit time are extracted from the original data of the multiple organs and environment to obtain the temperature and humidity fluctuation sequence.

[0072] It should be noted that the unit time can be set according to the plant's sensitivity to environmental changes. For example, every 30 minutes can be a unit. By calculating the difference between the maximum and minimum values ​​of temperature and humidity in each unit time, the fluctuation value of that period can be obtained. These fluctuation values ​​are then arranged in chronological order to form a temperature and humidity fluctuation sequence, thereby reflecting the dynamic changes in environmental temperature and humidity.

[0073] For example, temperature and humidity data are extracted from the raw data of multiple organs and environment of tomatoes in 30-minute intervals. The temperature fluctuation value is calculated to be 2℃ and the humidity fluctuation value is 5% from 8:00 to 8:30, and the temperature fluctuation value is 1.5℃ and the humidity fluctuation value is 3% from 8:30 to 9:00. The data are combined in chronological order to obtain the temperature and humidity fluctuation sequence.

[0074] In step S52, the temperature and humidity fluctuation sequence is compared with the rhythm time difference characteristics, the correlation coefficient between the two is calculated, and the degree of correlation is determined.

[0075] It should be noted that the comparison is achieved through time series correlation analysis, using the Pearson correlation coefficient calculation method to quantify the linear correlation between temperature and humidity fluctuations and circadian rhythm characteristics. The correlation coefficient ranges from -1 to 1. The closer the absolute value is to 1, the stronger the correlation between the two. Positive values ​​indicate a positive correlation because circadian rhythm increases when temperature and humidity fluctuations increase, while negative values ​​indicate a negative correlation because circadian rhythm decreases when temperature and humidity fluctuations increase.

[0076] For example, the temperature and humidity fluctuation sequence of cucumber was compared with the rhythm time difference characteristics, and the correlation coefficient was calculated to be 0.7, indicating that there is a strong positive correlation between the two, that is, the greater the temperature and humidity fluctuation, the more obvious the rhythm time difference between the leaves and roots.

[0077] In step S53, if the correlation degree exceeds a preset correlation threshold, the correction coefficients for the light intensity and light period reference parameters are calculated based on the correlation degree.

[0078] It should be noted that the preset correlation threshold is set based on plant growth characteristics (e.g., 0.6 for most crops). If the absolute value of the correlation coefficient exceeds this threshold, it indicates that temperature and humidity fluctuations have a significant impact on circadian rhythm lag. In this case, a correction coefficient needs to be calculated based on the strength of the correlation. The correction coefficient is positively correlated with the degree of correlation; that is, the stronger the correlation, the larger the correction coefficient, in order to more accurately offset the interference of environmental factors on circadian rhythm synchronization. In specific calculations, the relationship between the degree of correlation and the correction coefficient can be fitted using linear regression. For example, when the correlation coefficient is 0.6, the light intensity correction coefficient is set to 1.05 and the photoperiod correction coefficient is set to 1.02. For every 0.1 increase in the correlation coefficient, the light intensity correction coefficient increases by 0.03 and the photoperiod correction coefficient increases by 0.01.

[0079] For example, the correlation coefficient between the temperature and humidity fluctuation sequence of eggplant and the rhythm time difference characteristics is 0.75, which exceeds the preset correlation threshold of 0.6. Based on the set fitting relationship, the light intensity correction coefficient is calculated to be 1.1 and the light period correction coefficient is 1.05.

[0080] In step S54, the correction coefficient is substituted into the preliminary illumination control scheme to adjust the light intensity gradient and light period parameters at each time period, thereby generating the adjusted control scheme.

[0081] It should be noted that the substitution process involves multiplying the light intensity values ​​for each time period in the initial light control scheme by a light intensity correction factor, and multiplying the photoperiod duration by a photoperiod correction factor. Simultaneously, the light intensity gradient is adjusted specifically according to the peak periods of temperature and humidity fluctuations. For example, during periods of significant temperature and humidity fluctuations, the amplitude of the light intensity gradient change is appropriately increased to enhance the plant's adaptability to environmental changes. After adjustment, it is necessary to ensure that the light intensity and photoperiod parameters remain within the suitable range for plant growth, ultimately forming an adjusted control scheme that balances environmental adaptability and rhythmic synchronization.

[0082] For example, the light intensity values ​​(e.g., a baseline light intensity of 300 μmol / m²·s) at each time period in the initial light control scheme for strawberries are multiplied by a light intensity correction factor of 1.1 to obtain an adjusted light intensity of 330 μmol / m²·s; the photoperiod duration (e.g., 12 hours of light) is multiplied by a photoperiod correction factor of 1.05 to obtain an adjusted photoperiod of 12.6 hours of light; and during the period of 10:00-12:00 when temperature and humidity fluctuate greatly, the light intensity gradient is adjusted from an increase of 20 μmol / m²·s per hour to an increase of 25 μmol / m²·s per hour to generate the adjusted control scheme.

[0083] In step S6, the adjusted control scheme is compared with the preset diurnal rhythm to verify and update the illumination parameters, resulting in a corrected illumination parameter set, including: S61, compare the light parameters of the adjusted control scheme with the standard parameters of the preset circadian rhythm, and calculate the deviation value; S62, if the deviation value exceeds the preset deviation threshold, update the light intensity gradient and light period parameters; S63, perform time-series smoothing on the updated light intensity gradient and light period parameter to obtain a candidate illumination parameter set; S64, verify the feasibility of the candidate illumination parameter set and determine the corrected illumination parameter set.

[0084] In step S61, the illumination parameters of the adjusted control scheme are compared with the standard parameters of the preset circadian rhythm, and the deviation value is calculated.

[0085] It should be noted that the preset circadian rhythm standard parameters are set based on the natural diurnal light and shadow patterns of plant growth. This includes standard light intensities at different times of day; for example, during the day, light intensity gradually increases from 300 μmol / m²·s to 500 μmol / m²·s and then decreases back to 300 μmol / m²·s from 8:00 to 18:00, while the nighttime light intensity is 0, and a standard photoperiod (e.g., 12 hours of light, 12 hours of darkness). For comparison, the difference between the adjusted light parameters and the standard parameters is calculated at the same time points. The light intensity deviation is expressed in μmol / m²·s, and the photoperiod deviation is expressed in hours. This deviation value is used to measure the degree to which the adjusted scheme matches the natural circadian rhythm.

[0086] For example, the light intensity of 450 μmol / m²·s at 12:00 in the adjusted control scheme is compared with the standard light intensity of 400 μmol / m²·s for that time period in the preset circadian rhythm, and the light intensity deviation value is calculated to be 50 μmol / m²·s; the light cycle of the adjusted light period is 13 hours, and compared with the standard light cycle of 12 hours, the light cycle deviation value is 1 hour.

[0087] In step S62, if the deviation value exceeds the preset deviation threshold, the light intensity gradient and light period parameters are updated.

[0088] It should be noted that the preset deviation thresholds are set based on the plant's sensitivity to light rhythms. For example, the light intensity deviation threshold is 80 μmol / m²·s, and the photoperiod deviation threshold is 1.5 hours. If the deviation value exceeds the threshold, it indicates that the adjusted scheme deviates too much from the natural rhythm, and the parameters need to be updated according to the deviation ratio: when adjusting the light intensity gradient, the standard light intensity is used as the basis, plus the value obtained by multiplying the deviation value by the correction ratio; the photoperiod parameter is then brought closer to the standard photoperiod, such as shortening or extending the light duration until the deviation value is below the threshold.

[0089] For example, if the light intensity deviation of a plant is 90 μmol / m²·s after adjustment (exceeding the threshold of 80) and the photoperiod deviation is 2 hours (exceeding the threshold of 1.5), then the light intensity of the corresponding time period in the light intensity gradient will be reduced by 10 μmol / m²·s and the photoperiod will be shortened by 0.5 hours to 12.5 hours, so that the deviation value falls back to within the threshold.

[0090] In step S63, the updated light intensity gradient and the light period parameter are subjected to time series smoothing to obtain a candidate illumination parameter set.

[0091] It should be noted that the smoothing process uses the moving average method, which calculates the average value using the illumination parameters of three adjacent time points as a window to eliminate abrupt changes in the parameters over time. For example, if the light intensity suddenly increases from 300 μmol / m²·s to 500 μmol / m²·s in one hour, the light intensity gradient changes more gently and the light cycle transitions more naturally. After processing, a candidate illumination parameter set containing continuous illumination parameters for each time period is formed.

[0092] For example, the light intensities of the three nodes 9:00 (350), 10:00 (500), and 11:00 (450) in the updated light intensity gradient are processed by moving average, and the smoothed light intensity of 10:00 is (350+500+450) / 3≈433μmol / m²·s. After integration, a candidate illumination parameter set is formed.

[0093] In step S64, the feasibility of the candidate illumination parameter set is verified, and the corrected illumination parameter set is determined.

[0094] It should be noted that the feasibility verification includes two aspects: first, whether the parameters are within the suitable range for plant growth, such as light intensity not exceeding the plant's light saturation point and photoperiod meeting its growth stage requirements; second, whether the parameters match the hardware performance of the grow light, such as light intensity adjustment range within the grow light's maximum output capacity. If the candidate parameter set passes the verification, it is directly used as the corrected lighting parameter set; if it fails, it needs to be fine-tuned again to meet the conditions.

[0095] For example, if the light intensity in the candidate light parameter set is 600 μmol / m²·s at a certain time, which exceeds the plant light saturation point of 550 μmol / m²·s, the verification fails. After reducing it to 550 μmol / m²·s, the verification passes again, and it is finally determined to be the corrected light parameter set.

[0096] In step S7, the growth lamp controller is driven to execute outputs based on the modified illumination parameter set, generating final control commands, including: S71, Obtain the corrected light intensity, light period and spectral ratio data from the corrected light parameter set, and convert them into electrical signal parameters that the growth lamp controller can recognize, to obtain the initial control signal; S72, compare the matching degree between the initial control signal and the rated parameters of the growth lamp hardware. If the matching degree is higher than the preset matching degree threshold, the signal is determined to be compliant, and a compliance status is obtained. S73, based on the compliance status and the initial control signal, allocate the execution time period of each parameter according to the time axis, and generate a dynamic control sequence that includes the light intensity change gradient and the start and end time of the light cycle; S74. Based on the dynamic control sequence and the real-time operation feedback data of the growth lamp, calculate the parameter execution deviation rate, and generate an adjusted illumination control command by comparing the deviation rate with the preset allowable range to obtain the final control output.

[0097] In step S71, the corrected light intensity, light period and spectral ratio data are obtained from the corrected illumination parameter set and converted into electrical signal parameters that can be recognized by the growth lamp controller to obtain the initial control signal.

[0098] It should be noted that the light intensity (in μmol / m²·s), photoperiod (in hours), and spectral ratio (e.g., red / blue light ratio) in the modified light parameter set are parameters representing the physiological needs of plants. However, grow light controllers typically achieve control through electrical signals such as current and voltage. Data conversion requires establishing a mapping relationship between physiological parameters and electrical signals. For example, a light intensity of 200 μmol / m²·s corresponds to a current of 0.5 A, and a red light ratio of 60% corresponds to a specific voltage combination. The light parameters are then converted into electrical signal parameters that the controller can recognize, such as current values, voltage values, and pulse widths, forming the initial control signal.

[0099] For example, light intensity of 300 μmol / m²·s, light period of 14 hours, and red light / blue light ratio of 7:3 are obtained from the modified illumination parameter set. These parameters are then converted into electrical signal parameters with current of 0.7A, voltage of 12V, and red light channel duty cycle of 70% through data conversion to obtain the initial control signal.

[0100] In step S72, the matching degree between the initial control signal and the rated parameters of the growth lamp hardware is compared. If the matching degree is higher than the preset matching degree threshold, the signal is determined to be compliant, and a compliance status is obtained.

[0101] It should be noted that the rated parameters of the grow lamp hardware include the maximum allowable current, voltage range, and spectral adjustment limits. For example, the maximum current is 1A, the voltage is 10-15V, and the red light ratio is 50%-90%. The matching degree is obtained by calculating the degree of fit between each electrical signal parameter in the initial control signal and the rated parameters. For example, a current of 0.7A within the 0-1A range scores 100 points, and a voltage of 12V within the 10-15V range scores 100 points. The overall matching degree is calculated according to weights. The preset matching degree threshold is usually set to 80 points. If the score exceeds this threshold, it indicates that the signal is within the hardware's carrying capacity and is judged to be compliant; otherwise, parameter adjustments are required.

[0102] For example, the initial control signal has a current of 0.7A (rated 0-1A), a voltage of 12V (rated 10-15V), and a red light ratio of 70% (rated 50%-90%). The calculated matching score is 100 points, which is higher than the threshold of 80 points, and is judged to be in a compliant state.

[0103] In step S73, based on the compliance status and the initial control signal, the execution time period of each parameter is allocated according to the time axis to generate a dynamic control sequence that includes the light intensity change gradient and the start and end time of the light period.

[0104] It should be noted that the time axis allocation needs to be combined with the photoperiod parameters to determine the start (e.g., 6:00) and end (e.g., 20:00) times of illumination, and the photoperiod should be divided into multiple time periods according to the light intensity change gradient (e.g., an increase of 50 μmol / m²·s per hour), with corresponding electrical signal parameters assigned to each time period. The dynamic control sequence is presented in a time-parameter form to ensure that the growth lamp gradually adjusts its output according to the preset rhythm.

[0105] For example, based on the compliance status and initial control signal, a dynamic control sequence is generated within a 14-hour light cycle (6:00-20:00) by increasing the light intensity from 200 μmol / m²·s to 300 μmol / m²·s (corresponding to an increase in current from 0.5A to 0.7A) from 6:00 to 8:00, maintaining 300 μmol / m²·s from 8:00 to 18:00, and decreasing to 200 μmol / m²·s from 18:00 to 20:00.

[0106] In step S74, the parameter execution deviation rate is calculated based on the dynamic control sequence and the real-time operation feedback data of the growth lamp. By comparing the deviation rate with the preset allowable range, an adjusted illumination control command is generated to obtain the final control output.

[0107] It should be noted that the real-time operation feedback data includes the actual output light intensity, spectrum, and temperature of the grow lamp (collected through onboard sensors). The parameter execution deviation rate is obtained by subtracting the dynamic control sequence setting value from the actual output value of the grow lamp, and then dividing the difference by the dynamic control sequence setting value. For example, if the light intensity is set to 300 μmol / m²·s and the actual output is 285 μmol / m²·s, the deviation rate is -5%. The preset allowable range is usually ±10%. If the deviation rate is within the range, the dynamic control sequence can be directly used as the control command; if it exceeds the range (e.g., deviation rate -15%), the electrical signal parameters are adjusted in reverse according to the deviation value. For example, the current is increased to 0.75A to increase the light intensity, generating the adjusted control command, which is the final control output.

[0108] For example, in the dynamic control sequence, at 10:00 the light intensity is set to 300 μmol / m²·s, the actual light intensity is fed back to 270 μmol / m²·s, the deviation rate is -10%, which is within the allowable range (±10%), then the control command remains unchanged during this period; at 12:00 the feedback deviation rate is -12%, which is outside the range, the current is adjusted from 0.7A to 0.78A, the adjusted control command is generated, and the final control output is obtained after integration.

[0109] In summary, this invention discloses an intelligent control method for plant grow lights based on biological rhythms. The method includes collecting leaf photosynthesis data, root nutrient absorption data, and environmental temperature and humidity data, and removing outliers to obtain raw data on multiple organs and the environment. Rhythm analysis is performed on this raw data to extract leaf and root rhythm curves to obtain rhythm time difference characteristics. The time offset between the peaks of leaf and root rhythms is calculated based on the rhythm time difference characteristics, and the precise phase difference is quantified. If the precise phase difference exceeds a preset threshold, a preliminary light regulation scheme is generated based on the light requirements of the plant's growth stage. The preliminary scheme is optimized by integrating environmental temperature and humidity data with the rhythm time difference characteristics to obtain an adjusted regulation scheme. The adjusted scheme is compared with a preset diurnal rhythm to verify and update the light parameters, resulting in a corrected light parameter set. The grow light controller is driven to execute outputs based on the corrected parameter set, generating the final control command. This invention achieves precise matching of light supply and plant physiological needs by dynamically regulating the grow light based on the differences in biological rhythms of multiple plant organs and environmental factors, thereby improving light energy utilization efficiency and plant growth quality.

[0110] Reference Figure 2 The second embodiment of the present invention provides an intelligent control system for plant growth lights based on biological rhythms, comprising: The data acquisition module is used to collect data on leaf photosynthesis, root nutrient absorption, and environmental temperature and humidity, and to remove outliers to obtain raw data on multiple organs and the environment. The rhythm extraction module is used to perform rhythm analysis on raw data from multiple organs and the environment, extract leaf rhythm curves and root rhythm curves, and obtain rhythm time difference characteristics. The phase calculation module is used to calculate the time offset between the peak of leaf and root rhythm based on the rhythm time difference characteristics, and quantify it to obtain the accurate phase difference. The scheme generation module is used to generate a preliminary light control scheme if the precise phase difference exceeds a preset phase difference threshold, combined with the light requirements of the plant growth stage. The scheme optimization module is used to integrate environmental temperature and humidity data with circadian rhythm time difference characteristics to optimize the initial light control scheme and obtain the adjusted control scheme. The parameter correction module is used to compare the adjusted control scheme with the preset diurnal rhythm, verify and update the illumination parameters, and obtain the corrected illumination parameter set. The control output module is used to drive the grow lamp controller to execute outputs based on the corrected light parameter set, and generate the final control command.

[0111] It should be noted that the intelligent control system for plant growth lights based on biological rhythms provided in this embodiment of the invention is used to execute all the process steps of the intelligent control method for plant growth lights based on biological rhythms in the above embodiment. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0112] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a biorhythm-based intelligent control program for plant growth lights. When the processor executes the computer program, it implements the steps described in the various biorhythm-based intelligent control method embodiments of plant growth lights, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module in the above-described device embodiments, such as the data acquisition module.

[0113] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0114] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0115] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.

[0116] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD card), flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0117] If the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0118] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0119] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for intelligent control of a plant growth light based on biological rhythms, characterized in that, The method comprises the following steps: Collecting leaf photosynthesis data, root nutrient absorption data, and environmental temperature and humidity data, and removing outliers to obtain multi-organ and environmental raw data; Performing rhythm analysis on the multi-organ and environmental raw data to extract leaf rhythm curves and root rhythm curves, and obtaining rhythm time difference characteristics; According to the rhythm time difference characteristics, the time offset of the leaf and root rhythm peaks is calculated, and the accurate phase difference is quantified; If the accurate phase difference exceeds the preset phase difference threshold, a preliminary light regulation scheme is generated in combination with the light demand of the plant growth stage; Fusing the environmental temperature and humidity data and the rhythm time difference characteristics, the preliminary light regulation scheme is optimized to obtain an adjusted regulation scheme; Comparing the adjusted regulation scheme with the preset circadian rhythm, verifying and updating the light parameters to obtain a corrected light parameter set; According to the corrected light parameter set, the growth lamp controller is driven to execute output, and the final control instruction is generated.

2. The method of claim 1, wherein, The method comprises the following steps: Collecting leaf photosynthesis data, root nutrient absorption data, and environmental temperature and humidity data, and removing outliers to obtain multi-organ and environmental raw data, comprising: Collecting leaf photosynthesis data, root nutrient absorption data, and environmental temperature and humidity data through a sensor array to form multi-source raw monitoring data; Removing outliers from the multi-source raw monitoring data and unifying the timestamp format to obtain standardized raw data; 3. The method of claim 1, wherein, Integrating the standardized raw data to generate multi-organ and environmental raw data. The method comprises the following steps: Separating the physiological parameter time series of leaves and roots from the multi-organ and environmental raw data to obtain organ-specific data; Performing periodic analysis on the organ-specific data to extract the rhythm peak time and cycle length of leaves and roots, and generating leaf rhythm curves and root rhythm curves; According to the leaf rhythm curves and the root rhythm curves, the peak time difference is calculated to obtain initial time difference characteristics; 4. The method of claim 1, wherein, Combining the environmental temperature and humidity data to correct the initial time difference characteristics and determine the final rhythm time difference characteristics. The method comprises the following steps: According to the rhythm time difference characteristics, the time offset of the leaf and root rhythm peaks is calculated, and the accurate phase difference is quantified; According to the rhythm time difference characteristics, the time offset of the leaf and root rhythm peaks is calculated, and the accurate phase difference is quantified; If the initial time offset exceeds the preset offset threshold, historical rhythm data is combined for smoothing to obtain a corrected offset; 5. The method of claim 1, wherein, Segmenting and quantifying the corrected offset to obtain phase difference values for each period; Integrating the phase difference values for each period to generate an accurate phase difference. The method comprises the following steps: Obtaining the light intensity and photoperiod reference parameters corresponding to the current growth stage of the plant; Comparing the accurate phase difference with the preset phase threshold, and determining that the plant is in a multi-organ rhythm desynchronization state when the accurate phase difference exceeds the preset phase threshold; Adjust the light intensity according to the different rhythm out-of-sync state, combine the photoperiod reference parameter, and generate a preliminary parameter adjustment sequence; Integrate the preliminary parameter adjustment sequence to form a preliminary light regulation scheme.

6. The method of claim 1, wherein, The fusion of the environmental temperature and humidity data and the rhythm time difference characteristics optimizes the preliminary light regulation scheme to obtain an adjusted regulation scheme, including: From the multi-organ and environmental original data, the fluctuation value of environmental temperature and humidity in unit time is extracted to obtain a temperature and humidity fluctuation sequence; Compare the temperature and humidity fluctuation sequence with the rhythm time difference characteristics, calculate the correlation coefficient of the two, and determine the degree of correlation; If the degree of correlation exceeds the preset correlation threshold, calculate the correction coefficient of the light intensity and the photoperiod reference parameter according to the degree of correlation; Substitute the correction coefficient into the preliminary light regulation scheme to adjust the light intensity gradient and the photoperiod parameter of each period to generate an adjusted regulation scheme.

7. The method of claim 1, wherein, The adjusted regulation scheme is compared with the preset circadian rhythm to verify and update the light parameters to obtain a corrected light parameter set, including: Compare the light parameters of the adjusted regulation scheme with the standard parameters of the preset circadian rhythm to calculate the deviation value; If the deviation value exceeds the preset deviation threshold, update the light intensity gradient and the photoperiod parameter; Perform time series smoothing processing on the updated light intensity gradient and the photoperiod parameter to obtain a candidate light parameter set; Verify the feasibility of the candidate light parameter set to determine the corrected light parameter set.

8. The method of claim 1, wherein, According to the corrected light parameter set, drive the growth lamp controller to execute output to generate the final control instruction, including: From the corrected light parameter set, obtain the corrected light intensity, photoperiod, and spectral proportion data, and convert them into electrical signal parameters recognizable by the growth lamp controller to obtain an initial control signal; Compare the matching degree of the initial control signal and the rated parameters of the growth lamp hardware. If the matching degree is higher than the preset matching degree threshold, it is determined that the signal is compliant to obtain a compliance state; Based on the compliance state and the initial control signal, allocate the execution period of each parameter according to the time axis to generate a dynamic control sequence containing the light intensity change gradient and the photoperiod start and end time; According to the dynamic control sequence and the real-time running feedback data of the growth lamp, calculate the parameter execution deviation rate, compare the deviation rate with the preset allowed range, generate an adjusted light control instruction, and obtain the final control output.

9. An intelligent control system for a biorhythm-based plant growth light, characterized in that, It includes: Data acquisition module: collect leaf photosynthesis data, root nutrient absorption data, and environmental temperature and humidity data, and perform outlier rejection to obtain multi-organ and environmental original data; Rhythm extraction module: perform rhythm analysis on the multi-organ and environmental original data to extract leaf rhythm curve and root rhythm curve to obtain rhythm time difference characteristics; Phase calculation module: calculate the time offset of leaf and root rhythm peaks according to the rhythm time difference characteristics to quantitatively obtain the accurate phase difference; Scheme generation module: if the accurate phase difference exceeds the preset phase difference threshold, combine the light demand of the plant growth stage to generate a preliminary light regulation scheme; The scheme optimization module: fuses the environment temperature and humidity data and the rhythm time difference characteristics, optimizes the preliminary light regulation scheme, and obtains an adjusted regulation scheme; The parameter correction module: compares the adjusted regulation scheme with a preset circadian rhythm, verifies and updates light parameters, and obtains a corrected light parameter set; The control output module: drives a growth lamp controller to perform output according to the corrected light parameter set, and generates a final control instruction.

10. An electronic device, comprising: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the biological rhythm-based plant growth lamp intelligent control method according to any one of claims 1 to 8 when executing the computer program.

Images