Plant growth acceleration method and system based on electromagnetic field regulation and control

Abstract

The invention discloses a plant growth acceleration method and system based on electromagnetic field regulation, and the method comprises the steps: collecting plant growth environment parameters, plant physiological parameters and electromagnetic interference parameters in real time through a multi-dimensional sensor network, and carrying out the noise reduction and normalization processing, and constructing a dynamic database; dynamically identifying the plant growth stage based on a preset growth stage threshold and a machine learning model; calling a single-field basic parameter library according to a plant growth stage, and dynamically calculating a synergistic effect parameter and a compensation strategy of an electrostatic field and a magnetic field in combination with an electromagnetic interference parameter; a three-dimensional vector electrostatic field and an anti-interference magnetic field are output in a time-sharing superposition mode, and an effective operating distance is adjusted and maintained through a self-adaptive electrode; based on the plant growth condition, an optimization algorithm is adopted to carry out iterative optimization on the electromagnetic field parameters; the problems that in the prior art, a plant growth regulation and control technology is single in electromagnetic field regulation and control means and lacks a multi-field cooperative dynamic regulation and control mechanism are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of general botany, and in particular to the technical field of promoting plant growth by treating plants with electricity or magnetism, and specifically to a plant growth acceleration method and system based on electromagnetic field regulation. Background Art

[0002] At the intersection of agricultural science and bioelectromagnetism, plant growth regulation technology is undergoing a paradigm shift from traditional environmental factor control to physical field intervention. Traditional technologies primarily rely on photoperiod regulation, temperature and humidity management, and nutrient solution supply to achieve yield increases by simulating or optimizing the plant growth environment. However, these methods suffer from limitations such as low energy conversion efficiency, high environmental control costs, and delayed response. As bioelectromagnetic research deepens, scientists have discovered that electromagnetic fields with specific parameters can interact with plant cell membrane potential, enzyme activity, and photosynthetic systems: electrostatic fields promote ion channel opening by polarizing the cytoplasmic matrix, while magnetic fields influence the efficiency of the electron transport chain in chloroplasts through the Lorentz force.

[0003] Existing electromagnetic field plant regulation technologies have developed primarily along two technical paths: electrostatic field intervention, which uses parallel electrodes to apply a DC electric field, but suffers from limitations such as limited range and poor field uniformity. Magnetic field intervention, which utilizes arrays of permanent magnets to create a static magnetic field environment, struggles to achieve dynamic regulation. Existing electromagnetic field applications for plant growth regulation are mostly limited, employing only a single electrostatic or magnetic field, lacking a multi-field coordinated dynamic regulation mechanism. Plant growth is a complex physiological process, and a single electromagnetic field may only have a limited impact on a specific growth stage or physiological process, failing to fully realize its comprehensive growth-promoting effects. Existing systems often use fixed field strength parameters, failing to adapt to the diverse needs of plants at different growth stages. A further technical bottleneck lies in the inadequate understanding of the spatial coupling mechanisms of electromagnetic fields. Electrostatic fields are easily distorted by the humidity of the medium, while magnetic field distribution can be affected by ferromagnetic materials, resulting in gradient distortion.

[0004] Therefore, it is necessary to improve the plant growth acceleration method and system in the prior art to solve the above problems. Summary of the Invention

[0005] The present invention overcomes the shortcomings of the existing technology and provides a plant growth acceleration method and system based on electromagnetic field regulation, aiming to solve the problems of low energy conversion efficiency, high environmental control cost, delayed response, single electromagnetic field regulation means and lack of multi-field coordinated dynamic regulation mechanism in the existing plant growth regulation technology.

[0006] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a method for accelerating plant growth based on electromagnetic field regulation, comprising:

[0007] S1. Real-time collection of plant growth environment parameters, plant physiological parameters, and electromagnetic interference parameters through a multi-dimensional sensor network, and noise reduction and normalization processing to build a dynamic database;

[0008] S2, dynamically identifying plant growth stages based on preset growth stage thresholds and machine learning models;

[0009] S3. Call the single-field basic parameter library according to the plant growth stage and combine it with the electromagnetic interference parameters to dynamically calculate the synergistic parameters and compensation strategy of the electrostatic field and magnetic field;

[0010] S4, using time-sharing superposition mode to output three-dimensional vector electrostatic field and anti-interference magnetic field, and maintaining effective action distance through adaptive electrode adjustment;

[0011] S5. Based on the plant growth conditions, an optimization algorithm is used to iteratively optimize the electromagnetic field parameters.

[0012] In a preferred embodiment of the present invention, in step S1, the multidimensional sensor network includes an environmental parameter sensor, a plant physiological parameter sensor and an electromagnetic interference parameter sensor; the environmental parameter sensor is used to collect temperature and humidity, CO2 concentration, and light intensity; the plant physiological parameter sensor is used to collect cell membrane potential, plant height, and photosynthetic efficiency; the electromagnetic interference parameter sensor is used to collect geomagnetic field strength and direction, and air conductivity, and all sensors have real-time data transmission capabilities.

[0013] In a preferred embodiment of the present invention, in step S2, the preset growth stage threshold is specifically:

[0014] Germination stage: 0-7 days after sowing, plant height ≤ 5 cm, Fv / Fm value 0.3-0.6, leaf resistance 1.0–2.5 kΩ;

[0015] Growth period: 8-25 days after sowing, plant height 5-30 cm, Fv / Fm value 0.7-0.85, leaf resistance 0.8–1.5 kΩ;

[0016] Flowering period: 26-40 days after sowing, buds appear, the Fv / Fm value peaks at 0.6-0.7, and the leaf resistance is 1.2-2.0 kΩ;

[0017] Fruiting period: 41 days after sowing, the fruit diameter is ≥1 cm, the Fv / Fm value is stable at 0.5-0.6, and the leaf resistance is 2.0–3.5 kΩ;

[0018] The machine learning model uses a random forest algorithm with input parameters including plant height, Fv / Fm value, and cell membrane potential. It is trained with 1,000 sets of samples and the current growth stage is confirmed when the confidence level of a certain stage is ≥0.8.

[0019] In a preferred embodiment of the present invention, in step S3, the single field basic parameter library includes electrostatic field and magnetic field parameters in different stages;

[0020] Electrostatic field parameters: set voltage range, field strength and action time according to different growth stages;

[0021] Magnetic field parameters: set magnetic induction intensity, frequency and action mode according to different growth stages;

[0022] The compensation strategy includes reversely superimposing a compensation magnetic field according to the geomagnetic field vector and dynamically adjusting the electrostatic field voltage according to the air conductivity.

[0023] In a preferred embodiment of the present invention, the basic parameters are used as a reference and the compensation coefficient is generated in combination with the real-time interference parameters:

[0024] Geomagnetic field interference compensation: real-time measurement of geomagnetic field vector B earth , reverse superposition compensation magnetic field B comp =-B earth , the total superimposed magnetic field is B total =B 人工 +B comp ;

[0025] Electric field leakage compensation: Dynamically compensate the voltage according to the air conductivity σ. The total voltage is:

[0026] V 总 =V0×(1+0.2·max(0,RH-70%)), where V0 is the current artificial electric field strength. When the air conductivity RH is greater than the threshold (corresponding to humidity greater than 70%), electric field leakage causes the actual field strength to decrease, and the electrostatic field voltage needs to be compensated.

[0027] When the electrostatic field and magnetic field work together, the total biological effect E 总 Satisfying the nonlinear superposition relationship,

[0028] E 总 =k1·E+k2·B 2 +k3·E·B, where k1, k2, k3 are weight coefficients, E is the electrostatic field intensity, and B is the magnetic induction intensity.

[0029] In a preferred embodiment of the present invention, the time-sharing superposition mode in step S4 includes:

[0030] Photoperiod, 6:00-18:00: field strength combination = 1.2E+0.8B, using a combination of electrostatic field and magnetic field enhancement;

[0031] Dark period, 18:00-24:00: field strength combination = 0.5E+1.5B, using a combination of low static field and high magnetic field;

[0032] Dormant period, 24:00-6:00: turn off the electromagnetic field.

[0033] In a preferred embodiment of the present invention, the optimization algorithm in step S5 is a particle swarm optimization algorithm, which takes maximizing the growth rate as the objective function, iteratively optimizes the electrostatic field voltage and magnetic field frequency, and updates the optimization results to the single field basic parameter library.

[0034] The present invention provides a plant growth acceleration system based on electromagnetic field regulation, comprising modules:

[0035] A multi-dimensional sensor network module is used to collect plant growth environment parameters, plant physiological parameters, and electromagnetic interference parameters in real time, and to build a dynamic database through low-pass filtering, noise reduction, and normalization processing;

[0036] Intelligent control module, including: preset growth stage threshold unit, machine learning model unit, single field basic parameter library unit and collaborative parameter calculation and compensation strategy unit;

[0037] The preset growth stage threshold unit presets thresholds for different growth stages based on the physiological characteristics of plant growth and different responses to electromagnetic fields;

[0038] The machine learning model unit uses a random forest model with plant height, Fv / Fm, and cell membrane potential as input parameters. The trained classification model dynamically identifies the plant growth stage, outputs the confidence level of each growth stage, and confirms the current growth stage.

[0039] The single field basic parameter library unit stores the basic parameters of the electrostatic field and magnetic field at different growth stages;

[0040] The collaborative parameter calculation and compensation strategy unit combines the real-time collected electromagnetic interference parameters and, based on the preset compensation strategy, dynamically calculates the collaborative parameters and compensation coefficients of the electrostatic field and magnetic field to generate an accurate electromagnetic field control solution.

[0041] An electrostatic field generating module, used for outputting an electrostatic field;

[0042] A magnetic field generating module, used for outputting a magnetic field;

[0043] The time-sharing control module adopts a time-sharing superposition mode to dynamically match the electrostatic field and magnetic field in combination with the plant growth stage and the photoperiod;

[0044] The optimization module automatically calculates the growth rate and photosynthetic efficiency improvement rate at 24:00 every day, starts the PSO optimization engine to search for the optimal solution, iterates and optimizes through the speed update formula and position update formula, and synchronizes the optimization results to the single-field parameter library.

[0045] In a preferred embodiment of the present invention, the magnetic field generating module includes a three-axis Helmholtz coil group and a three-dimensional compensation coil, which offsets the interference of the earth's magnetic field through reverse current and uses a constant current power supply to achieve closed-loop control of the magnetic field strength.

[0046] In a preferred embodiment of the present invention, the electrostatic field generating module is realized by adaptive electrodes, and the distance between the electrodes is automatically adjusted by the electric guide rail to ensure that the distance between the top of the plant and the electrode plate is maintained within the range of 10-15 cm.

[0047] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0048] (1) The present invention discloses a plant growth acceleration method and system based on electromagnetic field regulation. The method collects plant growth environment parameters, plant physiological parameters and electromagnetic interference parameters in real time through a multi-dimensional sensor network, and performs noise reduction and normalization processing to build a dynamic database; dynamically identifies the plant growth stage based on a preset growth stage threshold and a machine learning model; calls a single field basic parameter library according to the plant growth stage, and dynamically calculates the synergistic parameters and compensation strategy of the electrostatic field and the magnetic field in combination with the electromagnetic interference parameters; uses a time-sharing superposition mode to output a three-dimensional vector electrostatic field and an anti-interference magnetic field, and maintains the effective action distance through adaptive electrode adjustment; and uses an optimization algorithm to iteratively optimize the electromagnetic field parameters based on the plant growth situation. The present invention accurately identifies the plant growth stage through the combination of a multi-dimensional sensor network and a machine learning model, dynamically adjusts the electromagnetic field parameters, realizes the synergistic effect of the electrostatic field and the magnetic field, improves the plant growth rate and photosynthetic efficiency, reduces the environmental control cost, and reduces the impact of electromagnetic interference.

[0049] (2) The present invention dynamically identifies the growth stage of plants based on preset growth stage thresholds and machine learning models. By presetting thresholds for different growth stages, the continuous growth process of plants is divided into discrete stages with clear physiological characteristics. At the same time, a random forest model is used to dynamically classify the plant height, Fv / Fm value, and cell membrane potential as input parameters, output the confidence level of each growth stage, and confirm the current growth stage. This process can accurately identify the growth stage of plants. Compared with the existing technology that uses fixed field strength parameters and cannot adapt to the needs of different growth stages, it realizes a differentiated electromagnetic field control strategy for each growth stage, ensures the accuracy and adaptability of the control strategy, further gives full play to the comprehensive promotion effect of the electromagnetic field on plant growth, and improves the effect and efficiency of plant growth control.

[0050] (3) The present invention calls a single-field basic parameter library according to the plant growth stage, and combines the electromagnetic interference parameters to dynamically calculate the synergistic parameters and compensation strategies of the electrostatic field and the magnetic field. In view of the differences in physiological needs of plants at different growth stages, a stage-by-stage electrostatic field and magnetic field basic parameter library is established to provide targeted electromagnetic field stimulation for each stage. At the same time, considering electromagnetic interference parameters, such as the strength and direction of the geomagnetic field and the air conductivity, a compensation coefficient is generated to compensate for the electrostatic field and the magnetic field. This enables electromagnetic field regulation to match the plant growth stage more accurately. Compared with the existing technology that lacks a multi-field synergistic dynamic regulation mechanism, it realizes the synergistic effect of the electrostatic field and the magnetic field, optimizes the electromagnetic field parameters, further improves the promoting effect of the electromagnetic field on plant growth, enhances the scientificity and effectiveness of plant growth regulation, reduces the regulation deviation caused by electromagnetic interference, and ensures the stability and reliability of plant growth regulation.

[0051] (4) The present invention adopts a time-sharing superposition mode to output a three-dimensional vector electrostatic field and an anti-interference magnetic field, and maintains an effective action distance through adaptive electrode adjustment. Different combinations of electrostatic field and magnetic field strength are set in the light cycle, dark cycle and dormant period, and the electromagnetic field is dynamically matched in combination with the growth stage and the light cycle. At the same time, the electrode array in the electrostatic field generating module can automatically adjust the spacing through the electric guide rail to ensure that the distance between the top of the plant and the electrode plate is maintained in an appropriate range. This process realizes the precise spatiotemporal control of the electromagnetic field output. Compared with the existing methods that are difficult to achieve dynamic regulation, it further improves the spatiotemporal accuracy and energy utilization efficiency of the electromagnetic field regulation, maximizes the plant growth acceleration effect, and at the same time, the adaptive electrode regulation mechanism ensures the effective action range of the electromagnetic field, improves the stability and adaptability of the electromagnetic field regulation, and enhances the effect and flexibility of plant growth regulation.

[0052] (5) Based on the plant growth situation, the present invention uses the particle swarm optimization (PSO) algorithm to iteratively optimize the electromagnetic field parameters. Key indicators such as growth rate and photosynthetic efficiency improvement rate are calculated daily. When the growth rate is lower than the expected value, the PSO optimization process is triggered. Taking the maximization of growth rate as the objective function, the parameters such as electrostatic field voltage and magnetic field frequency are iteratively optimized, and the optimized parameters are updated to the single field basic parameter library. This enables the electromagnetic field parameters to be adjusted in real time according to the actual growth situation of the plant. Compared with the existing technology that cannot adapt to the differentiated needs of plants at different growth stages, the self-optimization of the electromagnetic field parameters is realized, and the intelligent level and effect of plant growth regulation are further improved. The optimized parameters are used for subsequent regulation, forming a continuously improved closed-loop control, further improving the stability and effectiveness of plant growth regulation, and promoting the continuous improvement of plant growth performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive efforts.

[0054] Figure 1 is a flow chart of a preferred embodiment of the present invention;

[0055] Figure 2 This is a dynamic division diagram of plant growth stages according to a preferred embodiment of the present invention;

[0056] Figure 3 This is a diagram of the steps for dynamic calculation of electromagnetic field parameters according to a preferred embodiment of the present invention;

[0057] Figure 4 It is a time-sharing superposition mode diagram of a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0060] Application Overview:

[0061] The limitations of a single field effect are as follows: electrostatic fields primarily affect the distribution of surface charges on cell membranes, promoting the orderly arrangement of polar molecules, but long-term effects can lead to cytoplasmic acidification; magnetic fields affect stomatal opening and closing by regulating calmodulin activity, but constant magnetic fields can easily cause plants to produce magnetic saturation effects. Different electromagnetic schemes are required for different plant growth cycles to achieve complementary effects; the geomagnetic field has three-dimensional vector characteristics, and its intensity and direction vary at different geographical locations and altitudes. When an artificial magnetic field is applied indoors, the geomagnetic field interacts with the artificial magnetic field, causing the distribution of the artificial magnetic field to be distorted; the distribution and intensity of the electrostatic field are significantly affected by the relative humidity of the air. In high humidity environments, water molecules in the air will adsorb on the electrode surface, forming a water film conductive layer, causing electric field leakage, reducing the intensity and range of the electrostatic field.

[0062] Therefore, this application proposes a plant growth acceleration method and system based on electromagnetic field regulation. Through the synergistic effect of electrostatic field and magnetic field, combined with intelligent control technology, the electromagnetic field parameters are dynamically adjusted to match the plant growth stage; the magnetic field generating module uses a three-axis Helmholtz coil to generate a composite magnetic field with adjustable space vector, and cooperates with a three-dimensional magnetic field compensation device to eliminate geomagnetic field interference.

[0063] Exemplary methods:

[0064] like Figure 1 As shown, a method for accelerating plant growth based on electromagnetic field regulation includes:

[0065] S1. Real-time collection of plant growth environment parameters, plant physiological parameters, and electromagnetic interference parameters through a multi-dimensional sensor network, and noise reduction and normalization processing to build a dynamic database;

[0066] S2, dynamically identifying plant growth stages based on preset growth stage thresholds and machine learning models;

[0067] S3. Call the single-field basic parameter library according to the plant growth stage and combine it with the electromagnetic interference parameters to dynamically calculate the synergistic parameters and compensation strategy of the electrostatic field and magnetic field;

[0068] S4, using time-sharing superposition mode to output three-dimensional vector electrostatic field and anti-interference magnetic field, and maintaining effective action distance through adaptive electrode adjustment;

[0069] S5. Based on the plant growth conditions, an optimization algorithm is used to iteratively optimize the electromagnetic field parameters.

[0070] Plant growth is affected by many factors. By building a multi-dimensional sensor network, we can obtain comprehensive and real-time key parameters in the plant growth environment, providing accurate data support for subsequent growth stage identification and electromagnetic field regulation, thereby achieving refined management and optimized control of the plant growth process.

[0071] In step S1, the multi-dimensional sensor includes: an environmental parameter sensor, a plant physiological parameter sensor, and an electromagnetic interference parameter sensor;

[0072] Environmental parameter sensors, sampling frequency 1 time / minute, including:

[0073] Temperature and humidity sensor, SHT30 model, with an accuracy of ±0.5°C / ±2%RH, used to monitor the temperature and humidity of the plant's surrounding environment;

[0074] The CO2 concentration sensor uses the SCD41 model with a range of 0-5000ppm, which can detect the CO2 concentration in the plant growth environment in real time;

[0075] Light intensity sensor, with a range of 0-200,000 lux, is used to measure the light intensity received by plants.

[0076] Plant physiological parameter sensors, including:

[0077] Leaf resistance sensor, needle electrode contact sensor, uses needle electrodes to contact leaves, with a resolution of 0.05-0.1kΩ. It is attached to the back of the leaf, avoiding the main vein, to monitor changes in plant cell membrane potential and reflect cell activity;

[0078] A laser rangefinder, model VL53L1X, with an accuracy of ±1 mm, was used to measure plant height every 2 hours and record plant growth.

[0079] Chlorophyll fluorometer, using the MINI-PAM model, with a measurement frequency of 1 time / hour, to obtain the quantum efficiency of photosynthetic system II (Fv / Fm), which is used to evaluate the photosynthetic efficiency of plants;

[0080] Electromagnetic interference parameter sensors, including:

[0081] Three-dimensional fluxgate sensor, model HMC5883L, with an accuracy of ±0.1μT, monitors the strength and direction of the geomagnetic field in real time;

[0082] The air conductivity sensor uses a dual-electrode method with a range of 0-100μS / cm to monitor the risk of electric field leakage caused by humidity.

[0083] Through a multi-dimensional sensor network, we can comprehensively obtain the environmental status, physiological activity and external electromagnetic interference information of plant growth, provide data support for subsequent growth stage identification, dynamic calculation of electromagnetic field parameters and coordinated regulation, and ensure the accuracy and adaptability of the regulation strategy.

[0084] In step S1, the plant growth environment parameters include: temperature and humidity, CO2 concentration, and light intensity; these directly affect the plant's physiological processes such as photosynthesis, respiration, and water metabolism, provide the necessary external conditions for plant growth, and are key indicators for maintaining a suitable growth environment for plants. These parameters need to be monitored in real time to adjust the electromagnetic field control strategy;

[0085] Plant physiological parameters include: cell membrane potential, plant height, and photosynthetic efficiency; cell membrane potential reflects cell activity, plant height reflects plant growth rate, and photosynthetic efficiency is directly related to the plant's ability to synthesize organic matter. These parameters can effectively reflect the growth status and health of the plant and are a direct representation of the plant's growth status, used to identify growth stages and evaluate regulatory effects;

[0086] Electromagnetic interference parameters include: geomagnetic field strength and direction, air conductivity; artificial electromagnetic field control is susceptible to geomagnetic field interference and electric field leakage in high humidity environments. The acquisition parameters can correct the electromagnetic field output to ensure the stability and uniformity of the field strength in the target area.

[0087] In step S1, the collected multidimensional data is filtered through a low-pass filter with a cutoff frequency of 0.1 Hz to remove high-frequency noise. The cutoff frequency is set to f c =0.1Hz, the sampling frequency is f s , the sampling period is T = 1 / f s , convert the analog filter into a digital filter, and obtain the recursive formula: y(n) = y(n-1) + α[x(n)-x(n-1)], x(n), y(n) are the input signal and output signal of the nth sampling point, α is the filter coefficient, which is related to the cutoff frequency and sampling frequency; normalize the filtered data to the numerical range of 0-1, and the normalized data point is x is the original data point, x max ,x min The maximum and minimum values ​​of the data are used to make data of different dimensions comparable and unified; through low-pass filtering and normalization processing, high-frequency noise interference can be effectively removed, and data of different dimensions can be unified into the same numerical range, which is convenient for subsequent machine learning model analysis and dynamic calculation of electromagnetic field parameters; finally, it is stored in the database to form a dynamic data set.

[0088] The purpose of presetting growth stage thresholds is to divide the continuous growth process of plants into discrete stages with clear physiological characteristics, so as to formulate differentiated electromagnetic field control strategies based on the growth needs of each stage. Plant growth and development is a dynamic process from simple to complex in structure and function. For example, the budding stage is mainly characterized by cell division, while the growth stage is mainly characterized by cell elongation. There are significant differences in the responses to environmental factors and electromagnetic field parameters at different stages. For example, a low-field electrostatic field is required to promote germination during the budding stage, while an alternating magnetic field is required to enhance photosynthesis during the growth stage. By establishing thresholds, the stage boundaries can be clearly defined to ensure the accuracy and adaptability of the control strategy.

[0089] like Figure 2 As shown, in step S2, the growth stages of the plants are divided into:

[0090] Germination period: 0-7 days after sowing, plant height ≤ 5 cm, Fv / Fm value 0.3-0.6, leaf resistance 1.0–2.5 kΩ, characterized by seed germination and cotyledon expansion. Cell metabolism is active during the germination period. After the seeds absorb water and swell, the cell membrane permeability is high and the resistance value is low. The photosynthetic system has not yet been fully established, and the light energy conversion efficiency is low.

[0091] Growth period: 8-25 days after sowing, plant height is 5-30cm, Fv / Fm value is 0.7-0.85, leaf resistance is 0.8-1.5kΩ, and it is characterized by rapid elongation of stems and leaves and improvement of the photosynthetic system. Stems and leaves elongate rapidly, cell division is vigorous, membrane permeability further increases, resistance continues to decrease, the photosynthetic system gradually improves, and light energy conversion efficiency reaches its peak;

[0092] Flowering period: 26-40 days after sowing, flower buds appear, the Fv / Fm value peaks at 0.6-0.7, and the leaf resistance is 1.2-2.0 kΩ. It is characterized by reproductive organ differentiation and flower bud formation. Reproductive growth dominates, cell metabolism shifts to flower organ development, membrane stability is enhanced, resistance rises slightly, photosynthetic products are transferred to flower buds, and the light system is slightly inhibited.

[0093] Fruiting period: 41 days after sowing, the fruit diameter is ≥1cm, the Fv / Fm value is stable at 0.5-0.6, and the leaf resistance is 2.0-3.5kΩ. It is characterized by fruit enlargement and nutrient accumulation. During the fruit enlargement period, the cell membrane stability is enhanced, the resistance value further increases, the photosynthetic system declines, and the light energy conversion efficiency decreases significantly.

[0094] Through the clear stage thresholds, the electromagnetic field parameters can be adapted in a targeted manner.

[0095] In step S2, random forest is used as a machine learning model to process the data. Random forest is good at processing high-dimensional and nonlinear data, and is robust to noise and missing values, making it suitable for dynamic classification of plant growth stages.

[0096] The input parameters are plant height, Fv / Fm (photosynthetic system II quantum efficiency), and cell membrane potential among the plant physiological parameters collected in S1;

[0097] Plant height reflects the amount of morphological growth and is a direct morphological indicator for stage differentiation; Fv / Fm reflects the quantum efficiency of photosynthetic system II and is a core physiological indicator of photosynthetic efficiency; and cell membrane potential reflects the cell membrane potential and is an electrical representation of cell activity. These three indicators cover key characteristics of plant growth status from the morphological, physiological, and electrical dimensions, respectively, and can effectively distinguish physiological differences between stages.

[0098] The model is built through the following steps:

[0099] 1000 sets of plant growth cycle samples are used as training sets, each set of samples contains:

[0100] Input features: time series data of plant height (measured every 2 hours), Fv / Fm (measured every hour), and cell membrane potential (real-time monitoring value).

[0101] Growth stage labels: germination period, growth period, flowering period, fruiting period;

[0102] The classification model is constructed using the random forest algorithm. The algorithm randomly selects some samples and feature subsets to train multiple decision trees, and finally outputs the classification results through a multi-tree voting mechanism.

[0103] When using the model to determine the growth stage, the real-time collected plant height, Fv / Fm, and leaf resistance data are input, and the model outputs the confidence level of each growth stage. When the confidence level of a certain stage is ≥0.8, the current growth stage is confirmed.

[0104] The classification decision function of random forest is: Where N is the number of decision trees, h i (x) is the classification result of the i-th decision tree for the input feature x, I is the indicator function, if h i (x) = k, then it is 1; otherwise, it is 0; is the final identified growth stage, and k is the growth stage label.

[0105] Step S2 achieves dynamic and accurate identification of plant growth stages by integrating preset multi-dimensional thresholds with the random forest model.

[0106] like Figure 3 As shown, in step S3, a single-field basic parameter library for electrostatic and magnetic field effects is established. The physiological needs of plants at different growth stages vary significantly, and a single fixed parameter cannot meet the optimal regulation requirements at each stage. By establishing a stage-by-stage basic parameter library, targeted electromagnetic field stimulation can be provided, ensuring the scientific and effective regulation strategy.

[0107] Electrostatic field parameters:

[0108] Germination stage: voltage range 5-10kV, field strength 0.5-1kV / m, action time 8h / day, low field strength electrostatic field promotes seed water absorption and cell wall breaking, and enhances cell membrane permeability;

[0109] Growth period: voltage range 10-15kV, field strength 1-1.5kV / m, action time 12h / day. The field strength accelerates ion transmembrane transport and promotes stem and leaf elongation.

[0110] Flowering period: voltage range 8-12kV, field strength 0.8-1.2kV / m, action time 10h / day, inhibit photorespiration and guide the distribution of photosynthetic products to flower buds;

[0111] During the fruiting period, the voltage range is 3-5kV, the field strength is 0.3-0.5kV / m, and the action time is 6h / day to reduce energy consumption and avoid excessive division of fruit cells;

[0112] Magnetic field parameters:

[0113] Germination stage: magnetic induction intensity 1-3mT, frequency 0Hz, action mode is vertical uniform field, constant magnetic field enhances the polar growth of seed radicle;

[0114] Growth period: Magnetic induction intensity 3-5mT, frequency 8-10Hz, action mode is XY plane alternating field, alternating magnetic field promotes chloroplast thylakoid membrane electron transfer and increases photosynthetic rate;

[0115] Flowering period: Magnetic induction intensity 2-4mT, frequency 3-5Hz, action mode is Z-axis pulse field, low-frequency pulses regulate the conversion of phytochrome Pr / Pfr, and induce flower bud differentiation;

[0116] Fruiting period: Magnetic induction intensity is 1-2mT, frequency is 1-2Hz, and the action mode is a three-axis composite field. The composite magnetic field slows down cell aging and prolongs the nutrient accumulation period of the fruit.

[0117] Electromagnetic interference parameters include the strength and direction of the geomagnetic field and air conductivity. During dynamic calculation, the basic parameters are used as a benchmark and combined with real-time interference parameters to generate compensation coefficients:

[0118] Geomagnetic field interference compensation: real-time measurement of geomagnetic field vector B earth , reverse superposition compensation magnetic field B comp =-B earth , the total superimposed magnetic field is B total =B 人工 +B comp ;

[0119] Electric field leakage compensation: Dynamically compensate the voltage according to the air conductivity σ. The total voltage is:

[0120] V 总 =V0×(1+0.2·max(0,RH-70%)), where V0 is the current artificial electric field strength. When the air conductivity RH is greater than the threshold (corresponding to humidity greater than 70%), electric field leakage causes the actual field strength to decrease, and the electrostatic field voltage needs to be compensated.

[0121] When the electrostatic field and magnetic field work together, the total biological effect E 总 Satisfying the nonlinear superposition relationship,

[0122] E 总 =k1·E+k2·B 2 +k3·E·B, where k1, k2, k3 are weight coefficients, E is the electrostatic field intensity, and B is the magnetic induction intensity.

[0123] like Figure 4 As shown, the time-sharing control strategy adopts a time-sharing superposition mode, combining the growth stage with the photoperiod to dynamically match the electrostatic field and magnetic field:

[0124] Photoperiod (6:00-18:00): Field strength combination = 1.2E+0.8B, enhancing photosynthesis, electrostatic field promotes stomatal opening, and magnetic field accelerates electron transfer;

[0125] Dark cycle (18:00-24:00): Field strength combination = 0.5E+1.5B, constant magnetic field promotes cytokinin synthesis,

[0126] Dormant period (24:00-6:00): Turn off the electromagnetic field, simulate the natural environment, and avoid overstimulation.

[0127] In step S4, the adjustable DC voltage output and the electrode spacing are adaptively adjusted by the electrostatic generation module; the electrostatic generation module includes:

[0128] The electrostatic generator outputs a continuously adjustable high-voltage DC voltage of 5-20 kV, which is dynamically adjusted according to the compensation parameters in step S3;

[0129] Electrode array: Consists of 10 50cm x 50cm parallel aluminum plates, with spacing automatically adjusted by electric guide rails: Initial spacing is 30cm, increasing at a rate of 1cm / day as plant height increases, ensuring that the distance between the plant top and the electrode plates is always maintained at 10-15cm;

[0130] The insulating support frame adopts a polytetrafluoroethylene frame with a withstand voltage of 100kV and a humidity protection level of IP67 to prevent electric field leakage and ensure safety.

[0131] The high-voltage output end of the electrostatic generator is connected to the aluminum plate of the electrode array through a high-voltage shielded cable. Each aluminum plate is independently connected to the multi-channel high-voltage output module of the electrostatic generator, supporting independent voltage adjustment of each electrode plate; the aluminum plates of the electrode array are embedded in the guide rail groove of the insulating support frame through polytetrafluoroethylene insulating sliders to ensure that there is no metal contact between the electrode plates and the frame. The stepper motor of the electric guide rail drives the aluminum plate to move through the ball screw, and the spacing is automatically adjusted every day according to the plant height data; the central controller STM32H750 sends voltage instructions to the electrostatic generator through the CAN bus and controls the movement of the stepper motor of the electric guide rail; the real-time data of the electrode spacing is fed back to the controller by the laser rangefinder integrated in the edge of the electrode plate to form a closed-loop regulation.

[0132] In step S4, a uniform magnetic field that is resistant to geomagnetic field interference is generated by a magnetic field generating module; the magnetic field generating module includes:

[0133] Three-axis Helmholtz coil assembly, X / Y / Z axis independent control, single-axis coil radius 0.5m, number of turns 100 turns, maximum current 10A, used to generate three-dimensional vector magnetic field;

[0134] The three-dimensional compensation coil is coaxially and reversely wound with the Helmholtz coil, with independent control of the X / Y / Z axes. The single-axis coil has a radius of 0.5m and 100 turns. It monitors the geomagnetic field in real time and offsets the geomagnetic field interference through reverse current.

[0135] Constant current power supply, output current 0-10A adjustable, accuracy ±0.01A, provides stable current for the coil and quickly responds to magnetic field parameter adjustments;

[0136] Each axis coil is independently connected to the three-channel output of the constant current power supply. The compensation coil and the Helmholtz coil are coaxially connected in reverse series and share the same constant current power supply channel. The reverse current offsets the interference of the geomagnetic field. The central controller STM32H750 transmits magnetic field parameter instructions through the CAN bus and receives current feedback signals to achieve closed-loop control of the magnetic field strength. The sensor monitors the geomagnetic field vector in real time and transmits it to the controller. The controller calculates the compensation current and sends it to the constant current power supply of the compensation coil. The current value of the Helmholtz coil is measured by the CAN bus.

[0137] The Hall current sensor feeds back to the controller to ensure that the error between the actual magnetic field and the target value is less than 2%.

[0138] The Helmholtz coil and the compensation coil are coaxially nested, and the compensation coil and the Helmholtz coil are coaxially installed in the same plane with a spacing of 10 cm to ensure that the magnetic field superposition area coincides.

[0139] Step S4 accurately matches the plant growth stage and light cycle requirements through a time-sharing superposition mode, outputs a three-dimensional vector electrostatic field and an anti-interference magnetic field, and combines the adaptive electrode adjustment mechanism to optimize the field strength distribution in real time, significantly improving the temporal and spatial accuracy and energy utilization efficiency of electromagnetic field regulation, and maximizing the plant growth acceleration effect.

[0140] In step S5, the electromagnetic field parameters are dynamically adjusted using a particle swarm optimization (PSO) algorithm by real-time evaluation of plant growth effects to achieve parameter self-optimization;

[0141] The following two key indicators are calculated at 24:00 every day: growth rate and photosynthetic efficiency improvement rate;

[0142] The growth rate is the ratio of the plant height increment on the day to the plant height on the previous day, and the photosynthetic efficiency improvement rate is the difference between the Fv / Fm value on the day and the Fv / Fm value on the previous day;

[0143] If the growth rate G is lower than 80% of the expected value, the parameter self-optimization process is triggered;

[0144] Using the particle swarm optimization algorithm, PSO simulates the foraging behavior of bird flocks and uses information sharing of individuals in the group to achieve global optimal solution search, which is suitable for processing continuous parameter optimization problems.

[0145] The optimization parameter range is the electrostatic field voltage V and the magnetic field frequency f; the electrostatic field voltage V is ±10% of the voltage at the current plant growth stage, and the magnetic field frequency f is ±5Hz at the current plant growth stage;

[0146] Maximize the growth rate G as the objective function, MaximizeG(V,f);

[0147] Each particle in the particle swarm represents a set of electromagnetic field parameters x i =(V i ,f i ) Its state is determined by the velocity v i and position x i Description, updated during iteration by the following formula:

[0148] Speed ​​Update v i (t+1)=ω·v i (t)+c1·r1·(pbest-x i (t))+c2·r2·(gbest-x i (t)); where ω is the inertia weight, c1 and c2 are acceleration coefficients, r1 and r2 are random numbers in the range of [0,1], pbest is the historical optimal position of particle i, and gbest is the global optimal position;

[0149] Position update x i (t+1)=x i (t)+v i (t+1);

[0150] Particle position x i (t+1) is the optimized electromagnetic field parameter combination.

[0151] N particles are randomly generated. The initial position of each particle is randomly selected within the parameter range. For each particle i, its parameter x is i (t), input the system, apply electromagnetic field control, calculate the growth rate MaximizeG(V,f) as the fitness value the next day, compare the current fitness with the historical best of particle i, if G>pbest, then update, compare the pbest of all particles, and select the largest one as the global optimal gbest.

[0152] The optimized parameters are updated to the single-field basic parameter library for regulation in subsequent growth stages.

[0153] Example systems:

[0154] A plant growth acceleration system based on electromagnetic field regulation, comprising:

[0155] A multi-dimensional sensor network module is used to collect plant growth environment parameters, plant physiological parameters, and electromagnetic interference parameters in real time, and to build a dynamic database through low-pass filtering, noise reduction, and normalization processing;

[0156] Intelligent control module, including: preset growth stage threshold unit, machine learning model unit, single field basic parameter library unit and collaborative parameter calculation and compensation strategy unit;

[0157] The preset growth stage threshold unit presets thresholds for different growth stages based on the physiological characteristics of plant growth and different responses to electromagnetic fields;

[0158] The machine learning model unit uses a random forest model with plant height, Fv / Fm, and cell membrane potential as input parameters. The trained classification model dynamically identifies the plant growth stage, outputs the confidence level of each growth stage, and confirms the current growth stage.

[0159] The single field basic parameter library unit stores the basic parameters of the electrostatic field and magnetic field at different growth stages;

[0160] The collaborative parameter calculation and compensation strategy unit combines the real-time collected electromagnetic interference parameters and, based on the preset compensation strategy, dynamically calculates the collaborative parameters and compensation coefficients of the electrostatic field and magnetic field to generate an accurate electromagnetic field control solution.

[0161] An electrostatic field generating module, used for outputting an electrostatic field;

[0162] A magnetic field generating module, used for outputting a magnetic field;

[0163] The time-sharing control module adopts a time-sharing superposition mode to dynamically match the electrostatic field and magnetic field in combination with the plant growth stage and the photoperiod;

[0164] The optimization module automatically calculates the growth rate and photosynthetic efficiency improvement rate at 24:00 every day, starts the PSO optimization engine to search for the optimal solution, iterates and optimizes through the speed update formula and position update formula, and synchronizes the optimization results to the single-field parameter library.

[0165] The above description is based on the ideal embodiment of the present invention. Based on the above description, relevant personnel can make various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the content of the specification and must be determined according to the scope of the claims.

Claims

1. A method for accelerating plant growth based on electromagnetic field regulation, characterized in that: Including steps: S1. Real-time collection of plant growth environment parameters, plant physiological parameters, and electromagnetic interference parameters through a multi-dimensional sensor network, and noise reduction and normalization processing to build a dynamic database; S2, dynamically identifying plant growth stages based on preset growth stage thresholds and machine learning models; S3. Call the single-field basic parameter library according to the plant growth stage and combine it with the electromagnetic interference parameters to dynamically calculate the synergistic parameters and compensation strategy of the electrostatic field and magnetic field; S4, using time-sharing superposition mode to output three-dimensional vector electrostatic field and anti-interference magnetic field, and maintaining effective action distance through adaptive electrode adjustment; S5. Based on the plant growth conditions, an optimization algorithm is used to iteratively optimize the electromagnetic field parameters.

2. The method for accelerating plant growth based on electromagnetic field regulation according to claim 1, characterized in that: In step S1, the multidimensional sensor network includes an environmental parameter sensor, a plant physiological parameter sensor, and an electromagnetic interference parameter sensor; the environmental parameter sensor is used to collect temperature and humidity, CO2 concentration, and light intensity; the plant physiological parameter sensor is used to collect cell membrane potential, plant height, and photosynthetic efficiency; the electromagnetic interference parameter sensor is used to collect geomagnetic field strength and direction, and air conductivity, and all sensors have real-time data transmission capabilities.

3. The method for accelerating plant growth based on electromagnetic field regulation according to claim 1, characterized in that: In step S2, the preset growth stage threshold is specifically: Germination stage: 0-7 days after sowing, plant height ≤ 5 cm, Fv / Fm value 0.3-0.6, leaf resistance 1.0–2.5 kΩ; Growth period: 8-25 days after sowing, plant height 5-30 cm, Fv / Fm value 0.7-0.85, leaf resistance 0.8–1.5 kΩ; Flowering period: 26-40 days after sowing, buds appear, the Fv / Fm value peaks at 0.6-0.7, and the leaf resistance is 1.2-2.0 kΩ; Fruiting period: 41 days after sowing, the fruit diameter is ≥1 cm, the Fv / Fm value is stable at 0.5-0.6, and the leaf resistance is 2.0–3.5 kΩ; The machine learning model uses a random forest algorithm with input parameters including plant height, Fv / Fm value, and cell membrane potential. It is trained with 1,000 sets of samples and the current growth stage is confirmed when the confidence level of a certain stage is ≥0.

8.

4. The method for accelerating plant growth based on electromagnetic field regulation according to claim 1, characterized in that: In step S3, the single-field basic parameter library contains electrostatic field and magnetic field parameters in different stages; Electrostatic field parameters: set voltage range, field strength and action time according to different growth stages; Magnetic field parameters: set magnetic induction intensity, frequency and action mode according to different growth stages; The compensation strategy includes reversely superimposing a compensation magnetic field according to the geomagnetic field vector and dynamically adjusting the electrostatic field voltage according to the air conductivity.

5. The method for accelerating plant growth based on electromagnetic field regulation according to claim 4, characterized in that: Based on the basic parameters, the compensation coefficient is generated in combination with the real-time interference parameters: Geomagnetic field interference compensation: real-time measurement of geomagnetic field vector B earth , reverse superposition compensation magnetic field B comp =-B earth , the total superimposed magnetic field is B total =B 人工 +B comp ; Electric field leakage compensation: Dynamically compensate the voltage according to the air conductivity σ. The total voltage is: V 总 =V0×(1+0.2·max(0,RH-70%)), where V0 is the current artificial electric field strength. When the air conductivity RH is greater than the threshold (corresponding to humidity greater than 70%), electric field leakage causes the actual field strength to decrease, and the electrostatic field voltage needs to be compensated. When the electrostatic field and magnetic field work together, the total biological effect E 总 Satisfying the nonlinear superposition relationship, E 总 =k1·E+k2·B 2 +k3·E·B, where k1, k2, k3 are weight coefficients, E is the electrostatic field intensity, and B is the magnetic induction intensity.

6. The method for accelerating plant growth based on electromagnetic field regulation according to claim 1, characterized in that: The time-sharing superposition mode in step S4 includes: Photoperiod, 6:00-18:00: field strength combination = 1.2E+0.8B, using a combination of electrostatic field and magnetic field enhancement; Dark period, 18:00-24:00: field strength combination = 0.5E+1.5B, using a combination of low static field and high magnetic field; Dormant period, 24:00-6:00: turn off the electromagnetic field.

7. The method for accelerating plant growth based on electromagnetic field regulation according to claim 1, characterized in that: The optimization algorithm in step S5 is a particle swarm optimization algorithm, which takes maximizing the growth rate as the objective function, iteratively optimizes the electrostatic field voltage and the magnetic field frequency, and updates the optimization results to the single field basic parameter library.

8. A plant growth acceleration system based on electromagnetic field regulation, according to a plant growth acceleration method based on electromagnetic field regulation according to claims 1-7, characterized in that: Included modules: A multi-dimensional sensor network module is used to collect plant growth environment parameters, plant physiological parameters, and electromagnetic interference parameters in real time, and to build a dynamic database through low-pass filtering, noise reduction, and normalization processing; Intelligent control module, including: preset growth stage threshold unit, machine learning model unit, single field basic parameter library unit and collaborative parameter calculation and compensation strategy unit; The preset growth stage threshold unit presets thresholds for different growth stages based on the physiological characteristics of plant growth and different responses to electromagnetic fields; The machine learning model unit uses a random forest model with plant height, Fv / Fm, and cell membrane potential as input parameters. The trained classification model dynamically identifies the plant growth stage, outputs the confidence level of each growth stage, and confirms the current growth stage. The single field basic parameter library unit stores the basic parameters of the electrostatic field and magnetic field at different growth stages; The collaborative parameter calculation and compensation strategy unit combines the real-time collected electromagnetic interference parameters and, based on the preset compensation strategy, dynamically calculates the collaborative parameters and compensation coefficients of the electrostatic field and magnetic field to generate an accurate electromagnetic field control solution. An electrostatic field generating module, used for outputting an electrostatic field; A magnetic field generating module, used for outputting a magnetic field; The time-sharing control module adopts a time-sharing superposition mode to dynamically match the electrostatic field and magnetic field in combination with the plant growth stage and the photoperiod; The optimization module automatically calculates the growth rate and photosynthetic efficiency improvement rate at 24:00 every day, starts the PSO optimization engine to search for the optimal solution, iterates and optimizes through the speed update formula and position update formula, and synchronizes the optimization results to the single-field parameter library.

9. The plant growth acceleration system based on electromagnetic field regulation according to claim 8, characterized in that: The magnetic field generating module includes a three-axis Helmholtz coil group and a three-dimensional compensation coil, which offsets the interference of the earth's magnetic field through reverse current and uses a constant current power supply to achieve closed-loop control of the magnetic field strength.

10. The plant growth acceleration system based on electromagnetic field regulation according to claim 8, characterized in that: The electrostatic field generating module is realized by adaptive electrodes, and the electrode spacing is automatically adjusted by electric guide rails to ensure that the distance between the top of the plant and the electrode plate is maintained within the range of 10-15 cm.

Images