Plant negative ion generation method and system

Abstract

The invention provides a plant negative ion generation system and method, and the method comprises the steps: obtaining the basic information of a target potted plant, setting an initial high-voltage pulse parameter and an expected negative ion concentration target value, building an intelligent negative ion generation system based on the basic information of the plant, the initial high-voltage pulse parameter and the expected negative ion concentration target value, generating N groups of experimental high-voltage pulse parameters based on the initial high-voltage pulse parameters through a machine learning algorithm, performing high-voltage pulse stimulation on the target potted plant, obtaining the negative ion concentration, the actual voltage of the plant body and the environmental parameters in real time, constructing a multi-mode negative ion experimental data set, and combining with an expected negative ion concentration target value, the intelligent negative ion generation system is used for obtaining optimized high-voltage pulse parameters, safety verification and parameter adjustment are carried out on the optimized high-voltage pulse parameters, natural and artificial advantages are fused, plant source negative ions are safely, efficiently and continuously released in the indoor environment, and the indoor negative ion concentration is improved.

Description

Technical Field

[0001] This invention relates to the field of air purification technology, and more specifically, to a method and system for generating negative ions from plants. Background Technology

[0002] With the accelerating pace of urban life and extended time spent indoors, people are paying increasing attention to indoor air quality and a healthy environment. Due to their biological effects such as regulating the nervous system, promoting metabolism, and enhancing immunity, the concentration of negative air ions has become one of the important indicators for measuring air quality. Currently, increasing the concentration of indoor negative ions mainly relies on two technical approaches: natural release and artificial generation. However, existing methods still have significant limitations in terms of release efficiency and effectiveness, and cannot fully meet the urgent needs of a healthy living environment.

[0003] On the one hand, natural generation relies on the photosynthesis and tip discharge effect of plants, but its release efficiency is extremely low, making it difficult to achieve an effective concentration increase. For example, studies have shown that the concentration of negative ions released by a single potted plant under natural conditions is extremely low. Even under strong light conditions, the concentration is difficult to exceed the fresh air standard recommended by the World Health Organization. If you want to achieve the ideal concentration through natural release by plants, you need to place a large number of plants indoors. This not only takes up space, but also the effect is greatly reduced when there is insufficient light or at night. Its applicability and stability are both insufficient.

[0004] On the other hand, existing artificial negative ion generating devices, such as negative ion air purifiers or generators, although capable of producing high concentrations of negative ions, also have some significant drawbacks. Negative ions generated by purely electronic devices are mainly small ions with short lifespans and high mobility, which settle quickly in the air and have a limited range of action, lacking the ecological and sustainable characteristics of plant-derived negative ions.

[0005] In summary, existing technologies are inefficient and lack ecological benefits. Therefore, there is an urgent need in this field for a new method of generating negative ions that can integrate the advantages of nature and artificial methods, and can efficiently and continuously release plant-derived negative ions in indoor environments under safe conditions, so as to increase the concentration of negative ions indoors. Summary of the Invention

[0006] To address the aforementioned technical problems, the first aspect of this invention provides a method for generating negative ions from plants, comprising: Acquire the basic plant information of the target potted plant and set the initial high-voltage pulse parameters and the desired negative ion concentration target value based on the plant basic information. Construct an intelligent negative ion generating system based on the plant basic information, the initial high-voltage pulse parameters and the desired negative ion concentration target value. Based on the initial high-voltage pulse parameters, N sets of experimental high-voltage pulse parameters are generated through machine learning algorithms. Based on the experimental high-voltage pulse parameters, the target potted plant was stimulated with high-voltage pulses to obtain the negative ion concentration, actual plant voltage and environmental parameters in real time, and a multimodal negative ion experimental dataset was constructed. Based on the multimodal negative ion experimental dataset and the desired negative ion concentration target value, the intelligent negative ion generation system is used to obtain optimized high-voltage pulse parameters. The optimized high-voltage pulse parameters are subjected to safety verification and parameter adjustment. When the optimized high-voltage pulse parameters pass the safety verification, the target potted plant is stimulated with high-voltage pulse based on the optimized high-voltage pulse parameters.

[0007] According to a preferred embodiment, acquiring basic information about the target potted plant and setting initial high-voltage pulse parameters and a target value for the desired negative ion concentration based on the basic information about the target potted plant includes: Obtain the user's qualitative needs, and transform the user's qualitative needs into specific mathematical targets as the expected negative ion concentration target value; The basic plant information includes the type and size of the potted plant; A historical information database is constructed, which contains historical multimodal negative ion experimental datasets and has a built-in plant-parameter knowledge base, which stores the effective and safe pulse parameter ranges corresponding to different plant types. The initial high-voltage pulse parameters are set based on the historical information database and the basic information of the target potted plant, while the baseline environmental parameters are obtained. The initial high-voltage pulse parameters include the initial voltage, initial frequency, and initial duty cycle.

[0008] According to a preferred embodiment, the initial high-voltage pulse parameters are set based on the historical information database and the basic information of the target potted plant, while benchmark environmental parameters are acquired, including: Based on the basic information of the target potted plant, a matching query is performed on the historical information database, and a set of medium pulse parameters is selected from the plant-parameter knowledge base as the initial high-pressure pulse parameters.

[0009] The current environmental parameters are collected and recorded as baseline environmental parameters, including the initial negative ion concentration and the current illuminance, temperature, and humidity.

[0010] According to a preferred embodiment, based on initial high-voltage pulse parameters, N sets of experimental high-voltage pulse parameters are generated through a machine learning algorithm, including: The experimental high-voltage pulse parameters include the experimental voltage, experimental frequency, and experimental duty cycle.

[0011] According to a preferred embodiment, a high-voltage pulse stimulation is applied to the target potted plant based on the experimental high-voltage pulse parameters. The negative ion concentration, actual plant voltage, and environmental parameters are acquired in real time, and a multimodal negative ion experimental dataset is constructed, including: The environmental parameters include illuminance, temperature, and humidity; The multimodal negative ion experimental dataset is composed of the experimental high-voltage pulse parameters, the negative ion concentration, the actual voltage of the plant, and the environmental parameters.

[0012] According to a preferred embodiment, based on a multimodal negative ion experimental dataset and a desired target negative ion concentration, an intelligent negative ion generating system is used to obtain optimized high-voltage pulse parameters, including: The baseline environmental parameters, the multimodal negative ion experimental dataset, and the target value of the desired negative ion concentration are input into the intelligent negative ion generation system, and the Bayesian optimizer is used for analysis to obtain the optimized high-voltage pulse parameters.

[0013] According to a preferred embodiment, the optimized high-voltage pulse parameters undergo safety verification and parameter adjustment. When the optimized high-voltage pulse parameters pass the safety verification, high-voltage pulse stimulation is applied to the target potted plant based on the optimized high-voltage pulse parameters, including: Safety boundary conditions are set according to IEC standards to constrain the optimized high-voltage pulse parameters. These safety boundary conditions include a maximum voltage threshold and a maximum current threshold. When the optimized high-voltage pulse parameters meet the safety boundary conditions, high-voltage pulse stimulation is directly applied to the target potted plant based on the optimized high-voltage pulse parameters. If the optimized high-voltage pulse parameters do not meet the safety boundary conditions, the PSO algorithm is used to adjust the current optimized high-voltage pulse parameters and then the safety check is re-executed until the adjusted optimized high-voltage pulse parameters meet the safety boundary conditions. Based on the adjusted optimized high-voltage pulse parameters, high-voltage pulse stimulation is applied to the target potted plant.

[0014] When applying high-voltage pulse stimulation to the target potted plant, flow restriction and protective measures should be taken. The current limiting measure refers to adaptively limiting the current; The protective measures referred to here are adaptive voltage regulation. A second aspect of the present invention also provides a plant negative ion generating system, comprising: The information acquisition and initialization module is used to acquire the basic plant information of the target potted plant, set the initial high-voltage pulse parameters based on the basic plant information and historical information database, and receive user input to set the target value of the desired negative ion concentration. The pulse parameter decision module is used to generate N sets of experimental high-voltage pulse parameters based on the initial high-voltage pulse parameters and through a built-in machine learning algorithm. The high-pressure stimulation and data acquisition module includes a high-pressure pulse generation unit and a sensor unit. The high-pressure pulse generation unit is used to apply high-pressure pulse stimulation to the target potted plant based on the experimental high-pressure pulse parameters. The sensor unit is used to collect negative ion concentration, actual plant voltage and environmental parameters in real time, and to construct a multimodal negative ion experimental dataset. The parameter optimization module receives the multimodal negative ion experimental dataset and the desired negative ion concentration target value, and obtains optimized high-voltage pulse parameters through built-in optimization algorithms. The safety verification and execution module is used to perform safety verification and parameter adjustment on the optimized high-voltage pulse parameters. The safety verification and execution module includes a safety verification unit and a parameter adjustment unit. The safety verification unit is used to verify the safety of the parameters according to preset safety boundary conditions. The parameter adjustment unit is used to adjust the parameters that fail the verification. After the parameters pass the verification, the safety verification and execution module controls the high-voltage pulse generating unit to stimulate the target potted plant based on the final optimized high-voltage pulse parameters.

[0015] Based on the above, this application embodiment obtains the basic plant information of the target potted plant and sets initial high-voltage pulse parameters and desired negative ion concentration target values. Based on the plant information, initial high-voltage pulse parameters, and desired negative ion concentration target values, an intelligent negative ion generating system is constructed. A machine learning algorithm generates N sets of experimental high-voltage pulse parameters based on the initial high-voltage pulse parameters and applies high-voltage pulse stimulation to the target potted plant. The negative ion concentration, actual plant voltage, and environmental parameters are acquired in real time, and a multimodal negative ion experimental dataset is constructed. Combined with the desired negative ion concentration target value, the intelligent negative ion generating system obtains optimized high-voltage pulse parameters. The optimized high-voltage pulse parameters undergo safety verification and parameter adjustment, and are then executed. These steps, based on the natural generation of plant-derived negative ions, utilize machine learning algorithms to obtain suitable high-voltage pulse parameters to improve negative ion generation efficiency, enabling the potted plant to efficiently and continuously release plant-derived negative ions in the indoor environment under safe conditions, thereby increasing the indoor negative ion concentration. Attached Figure Description

[0016] Figure 1 A flowchart of the execution of a plant negative ion generation method of the present invention is presented.

[0017] Figure 2 A schematic diagram of a plant negative ion generating system of the present invention is shown. Detailed Implementation

[0018] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0019] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0020] like Figure 1 , Figure 2 As shown: The first aspect of this invention provides a method for generating negative ions in plants, comprising: Step S1: Obtain the basic plant information of the target potted plant and set the initial high-voltage pulse parameters and the target value of the desired negative ion concentration based on the plant information. Construct an intelligent negative ion generating system based on the plant information, the initial high-voltage pulse parameters and the target value of the desired negative ion concentration.

[0021] The basic plant information includes the type and size of the potted plant, and the initial high-voltage pulse parameters include the initial voltage, initial frequency, and initial duty cycle.

[0022] In this embodiment, step S1 includes: Step S11: Obtain the user's qualitative requirements, and convert the user's qualitative requirements into specific mathematical targets as the expected negative ion concentration target value.

[0023] Understandably, users' demand for negative ions is usually described in a vague qualitative way, such as purifying the air and improving breathing comfort. It is necessary to combine the usage scenario, space size and human comfort threshold to transform the vague qualitative description into a quantifiable mathematical target, that is, the desired negative ion concentration.

[0024] In some possible implementations, suppose a user makes a qualitative demand regarding pothos plants: in a 30㎡ living room, they want to generate negative ions through potted pothos to make breathing more comfortable for family members and reduce dust. First, analyze the scenario: a 30㎡ living room is a semi-enclosed space with low daily ventilation frequency, and negative ions are easily absorbed by furniture. Second, considering human comfort standards, a negative ion concentration of ≥1000 ions / cm³ is required for effective purification in a 30㎡ space. Therefore, this qualitative demand is converted into a mathematical target, with a desired negative ion concentration target value of ≥1000 ions / cm³. At the same time, it is clear that this target must be achieved without damaging the pothos, avoiding excessively increasing pulse parameters in pursuit of concentration.

[0025] Step S12: Construct a historical information database, which contains historical multimodal negative ion experimental datasets and includes a plant-parameter knowledge base that stores the effective and safe pulse parameter ranges corresponding to different plant types.

[0026] Among them, the historical multimodal is composed of the experimental high-voltage pulse parameters, negative ion concentration, actual plant voltage and environmental parameters during the historical operation process. The effective and safe pulse parameter range corresponding to the plant type is expressed as being able to make the plant negative ion concentration reach the common requirements, such as ≥800 ions / cm³ and ensure that the plant has no physiological damage, such as no yellowing of leaves and normal root vitality.

[0027] Step S13: Set the initial high-voltage pulse parameters based on the historical information database and the basic information of the target potted plant, and at the same time obtain the reference environmental parameters.

[0028] In this embodiment, step S13 includes: Step S131: Based on the basic information of the target potted plant, perform a matching query on the historical information database, and select a set of medium pulse parameters from the plant-parameter knowledge base as the initial high-pressure pulse parameters.

[0029] It should be noted that the matching query follows the principle of prioritizing accuracy. First, filter by plant type, such as locking in pothos and excluding spider plants and succulents, and then narrow down by size range, such as pot diameter ±2cm and plant height ±2cm, to ensure that the matching cases are consistent with the current scenario.

[0030] Furthermore, when selecting intermediate parameters, it is necessary to combine the median value of the knowledge base's safety range with the parameter distribution of the matching cases to avoid simply taking the mathematical median value, which would lead to a disconnect from the actual situation.

[0031] In some possible embodiments, it is assumed that in the historical information database, 50 cases of plant species = pothos are first screened, then narrowed down to 20 cases with pot diameter of 18-22cm and plant height of 28-32cm, and finally 15 cases with temperature of 23-27℃ and humidity of 48-52% are screened. The parameter distribution of these 15 cases is obtained, with voltage of 4.8-5.2kV, frequency of 49-51Hz and duty cycle of 29-31%. Combined with the median value of 5.25kV in the voltage range of 4-6.5kV in the knowledge base, the initial high voltage pulse parameters of pothos are determined as follows: voltage of 5kV, frequency of 50Hz and duty cycle of 30%.

[0032] Step S132: Collect and record the current environmental parameters as the baseline environmental parameters, which include the initial negative ion concentration and the current illuminance, temperature and humidity.

[0033] Understandably, the initial environmental negative ion concentration is used to determine whether the subsequent increase in concentration is caused by parameter stimulation rather than natural environmental changes. Illuminance affects plant photosynthesis, which in turn changes the surface charge distribution of leaves and indirectly affects the generation of negative ions. Excessively high or excessive temperatures will reduce plant physiological activity and affect the response to pulses. Humidity increases air conductivity and may change the electric field distribution.

[0034] Step S2: Based on the initial high-voltage pulse parameters, N sets of experimental high-voltage pulse parameters are generated through machine learning algorithms.

[0035] The experimental high-voltage pulse parameters include the experimental voltage, experimental frequency, and experimental duty cycle.

[0036] Specifically, based on historical databases and initial high-voltage pulse parameters, machine learning algorithms, such as gradient boosting trees or random forests, are used to learn the correlation between pulse parameters and negative ion concentration. For example, a 1kV increase in voltage leads to a 100-150 ions / cm³ increase in concentration. Subsequently, 5-10 sets of parameters are generated based on the learned correlation.

[0037] It should be noted that the 5-10 sets of parameters generated based on the learned correlation patterns must be within the safe range of the knowledge base and cover the three dimensions of voltage, frequency, and duty cycle, so as to comprehensively explore the influence of high voltage pulse parameters on concentration.

[0038] In some possible embodiments, assuming the initial high-voltage pulse parameters for the pothos are 5kV, 50Hz, and 30% duty cycle, analysis of historical data using the gradient boosting tree algorithm reveals that for every 0.5kV increase in voltage, the average concentration increases by 70 cells / cm³; for every 2Hz increase in frequency, the average concentration increases by 50 cells / cm³; and for every 2% increase in duty cycle, the average concentration increases by 30 cells / cm³. The safe range for pothos is 4-6.5kV, 45-55Hz, and 25-35%. Within this safe range, five sets of experimental high-voltage pulse parameters are generated: ① 5kV, 50Hz, 30% (control group); ② 5.5kV, 50Hz, 30% (only voltage increased compared to the control group); ③ 5kV, 52Hz, 30% (only frequency increased compared to the control group); ④ 5kV, 50Hz, 32% (only duty cycle increased compared to the control group); ⑤ 5.5kV, 52Hz, 32% (increased voltage, frequency, and duty cycle simultaneously compared to the control group).

[0039] Step S3: Based on the experimental high-voltage pulse parameters, apply high-voltage pulse stimulation to the target potted plant, obtain the negative ion concentration, actual plant voltage and environmental parameters in real time, and construct a multimodal negative ion experimental dataset.

[0040] The environmental parameters include light intensity, temperature, and humidity. The multimodal negative ion experimental dataset is composed of the experimental high-voltage pulse parameters, the negative ion concentration, the actual voltage of the plant, and the environmental parameters.

[0041] Specifically, fix the high-voltage pulse generator motor in the soil at the edge of the flowerpot, being careful to avoid the roots. Insert it to a depth of 5cm and fix its position to ensure that the electric field range is consistent each time.

[0042] Furthermore, the concentration of negative ions, the actual voltage of the plant body, and environmental parameters are recorded at fixed intervals. The recorded actual voltage of the plant body can be used to monitor the deviation between the high voltage pulse and the actual voltage of the plant body, while the environmental parameters can determine whether the data has reference value. For example, the fluctuation should be ≤±5%; otherwise, the data is invalid.

[0043] In some possible embodiments, it is assumed that five sets of experimental parameters are applied to the pothos plant. Copper electrodes are inserted 5cm deep into the soil around the edge of the pot, avoiding the roots, and the position is fixed. Each stimulation lasts for one hour. During this period, the living room environment is kept stable at 1500±50 lux of light, 25±0.5℃ of temperature, and 50±1% of humidity. The concentration of negative ions at a depth of 10cm around the pot is measured every 10 minutes using a negative ion detector, the actual voltage of the stem is measured using a voltage sensor, and environmental parameters are recorded using a thermometer and hygrometer. The final multimodal dataset contains five sets of multimodal negative ion experimental data, formatted as [voltage, frequency, duty cycle] → [mean concentration, plant voltage] → [light, temperature, humidity]. For example, the multimodal negative ion experimental data for group ⑤ is [5.5kV, 52Hz, 32%] → [980 ions / cm³, 5.3kV] → [1500 lux, 25℃, 50%RH], clearly showing the correlation between parameters and concentration.

[0044] Step S4: Based on the multimodal negative ion experimental dataset and the desired negative ion concentration target value, the optimized high-voltage pulse parameters are obtained using the intelligent negative ion generation system.

[0045] In this embodiment, step S4 includes: Step S41: Input the baseline environmental parameters, the multimodal negative ion experimental dataset, and the target value of the desired negative ion concentration into the intelligent negative ion generation system, and use a Bayesian optimizer to analyze and obtain the optimized high-voltage pulse parameters.

[0046] Specifically, based on the high-pressure pulse parameters and corresponding negative ion concentrations of similar plants in the historical database, a Gaussian process is used to describe the prior relationship model of high-pressure pulse parameters and negative ion concentrations. Then, the multimodal dataset obtained in the previous step is input into the prior relationship model to correct the probability distribution, so that the prior relationship model fits the actual response of the current plant. For example, if the concentration of the current pothos at 5.5kV is higher than the historical average, it indicates that its negative ion generation efficiency is higher, and the parameter coefficients need to be adjusted. Finally, the corrected prior relationship model is used to find the optimized high-pressure pulse parameters that are most likely to meet the target value of the desired negative ion concentration and also meet the effective and safe pulse parameter range corresponding to the plant type.

[0047] Step S5: Perform safety verification and parameter adjustment on the optimized high-voltage pulse parameters. When the optimized high-voltage pulse parameters pass the safety verification, apply high-voltage pulse stimulation to the target potted plant based on the optimized high-voltage pulse parameters.

[0048] In this embodiment, step S5 includes: Step S51: Set safety boundary conditions for constraining the optimized high-voltage pulse parameters according to IEC standards. The safety boundary conditions include a maximum voltage threshold and a maximum current threshold.

[0049] It should be noted that the safety boundary conditions for optimizing high-voltage pulse parameters must simultaneously meet IEC standards and plant-specific characteristics. IEC standards have requirements for the insulation strength and leakage current of low-voltage equipment, which need to be converted into high-voltage pulse parameter constraints. For example, the leakage current corresponds to the maximum current threshold that the plant can withstand. Plant characteristics need to be determined through gradient stimulation experiments. For specific plants of the same species, high-voltage pulses with different parameters are applied, and the maximum parameter value without damage is recorded, with a safety margin reserved. For example, if the pothos shows slight dehydration at 6.1kV in the experiment, the threshold is set to 6kV and the parameter is no longer increased.

[0050] Step S52: When the optimized high-voltage pulse parameters meet the safety boundary conditions, high-voltage pulse stimulation is directly applied to the target potted plant based on the optimized high-voltage pulse parameters.

[0051] Specifically, after optimizing the high-voltage pulse parameters to meet the aforementioned safety boundary conditions, the high-voltage pulse generator is first calibrated. The output parameters can be measured using an oscilloscope, and the calibration pass error is set to ≤ ±0.1kV. After calibrating the high-voltage pulse generator, high-voltage pulse stimulation is applied to the target potted plant, and the actual voltage and current are continuously recorded to ensure that they do not exceed the threshold. After stimulation, the plant's physiological indicators are evaluated in real time, including chlorophyll content and root conductivity, to confirm that there is no hidden damage. At the same time, the final concentration is recorded to confirm whether the desired negative ion concentration target value has been reached.

[0052] Step S53: If the optimized high-voltage pulse parameters do not meet the safety boundary conditions, the PSO algorithm is used to adjust the current optimized high-voltage pulse parameters and the safety check is re-executed until the adjusted optimized high-voltage pulse parameters meet the safety boundary conditions. Based on the adjusted optimized high-voltage pulse parameters, high-voltage pulse stimulation is applied to the target potted plant.

[0053] Specifically, initial particles are generated based on optimized high-voltage pulse parameters, such as a voltage of 6.2kV (example range 5.8-6.2kV). A fitness function is set based on safety boundary conditions and the desired negative ion concentration target value. The weight of the composite safety boundary conditions can be set to 60% to prioritize plant safety, and the weight of achieving the desired negative ion concentration target value can be set to 40%. In each iteration, the top 10% of high-fitness particles are retained to guide other particles to move closer. A maximum number of iterations is set, which can be up to 10 times to avoid infinite loops. After each iteration, the parameters need to be re-verified until they meet the conditions.

[0054] In this embodiment, when applying high-voltage pulse stimulation to the target potted plant, flow restriction and protective measures are taken.

[0055] The current limiting measure refers to adaptively limiting the current.

[0056] It should be noted that plants carry a high voltage, generally several thousand volts or more. Therefore, current limiting measures can be used to prevent danger caused by accidental contact. While current limiting will not cause harm to people, touching them may cause a tingling sensation.

[0057] The protective measures referred to here are adaptive voltage regulation.

[0058] It should be noted that in practical applications, either AC or DC power can be used. When high voltage is input to the plant, the plant will carry a high voltage. For safety, protective measures can be added, such as infrared, ultrasonic, and microwave protection. When someone approaches, the power should be cut off to stop the high voltage output, and the high voltage output should continue after the person leaves.

[0059] Furthermore, safe current can be referenced in GB / T 13870.1-2022 "Effects of Current on Humans and Livestock - Part 1: General Part", GB / T 13870.2-2016 "Effects of Current on Humans and Livestock - Part 2: Special Cases", GB / T 13870.4-2017 "Effects of Current on Humans and Livestock - Part 4: Lightning Effects", and GB / T 13870.5-2016 "Effects of Current on Humans and Livestock - Part 5: Contact Voltage Thresholds for Physiological Effects".

[0060] Among them, GB / T 13870.1-2022 "Effects of Current on Humans and Livestock - Part 1: General Part" aims to provide the basic principles of the effects of current on humans and livestock; GB / T 13870.2-2016 "Effects of Current on Humans and Livestock - Part 2: Special Cases" aims to describe the effects of sinusoidal alternating current with a frequency above 100Hz passing through the human body; GB / T 13870.4-2017 "Effects of Current on Humans and Livestock - Part 4: Lightning Effect" aims to describe the basic parameters and variability of the effects of lightning on humans and livestock; and GB / T 13870.5-2016 "Effects of Current on Humans and Livestock - Part 5: Contact Voltage Threshold for Physiological Effects" aims to analyze the current thresholds for human impedance and physiological effects in Part 1 and provide a combined threshold curve of contact voltage and duration.

[0061] A second aspect of the present invention provides a plant negative ion generating system, comprising: The information acquisition and initialization module is used to acquire the basic plant information of the target potted plant, set the initial high-voltage pulse parameters based on the basic plant information and historical information database, and receive user input to set the target value of the desired negative ion concentration. The pulse parameter decision module is used to generate N sets of experimental high-voltage pulse parameters based on the initial high-voltage pulse parameters and through a built-in machine learning algorithm. The high-pressure stimulation and data acquisition module includes a high-pressure pulse generation unit and a sensor unit. The high-pressure pulse generation unit is used to apply high-pressure pulse stimulation to the target potted plant based on the experimental high-pressure pulse parameters. The sensor unit is used to collect negative ion concentration, actual plant voltage and environmental parameters in real time, and to construct a multimodal negative ion experimental dataset. The parameter optimization module receives the multimodal negative ion experimental dataset and the desired negative ion concentration target value, and obtains optimized high-voltage pulse parameters through built-in optimization algorithms. The safety verification and execution module is used to perform safety verification and parameter adjustment on the optimized high-voltage pulse parameters. The safety verification and execution module includes a safety verification unit and a parameter adjustment unit. The safety verification unit is used to verify the safety of the parameters according to preset safety boundary conditions. The parameter adjustment unit is used to adjust the parameters that fail the verification. After the parameters pass the verification, the safety verification and execution module controls the high-voltage pulse generating unit to stimulate the target potted plant based on the final optimized high-voltage pulse parameters.

[0062] The specific usage and function of this invention are described below: This application embodiment acquires the basic plant information of the target potted plant and sets initial high-voltage pulse parameters and a target value for the desired negative ion concentration. Based on the plant information, initial high-voltage pulse parameters, and target value for the desired negative ion concentration, an intelligent negative ion generating system is constructed. A machine learning algorithm generates N sets of experimental high-voltage pulse parameters based on the initial high-voltage pulse parameters and applies high-voltage pulse stimulation to the target potted plant. The system acquires the negative ion concentration, actual plant voltage, and environmental parameters in real time and constructs a multimodal negative ion experimental dataset. Combined with the target value for the desired negative ion concentration, the intelligent negative ion generating system acquires optimized high-voltage pulse parameters. These optimized high-voltage pulse parameters undergo safety verification and parameter adjustment before execution. These steps, based on the natural generation of plant-derived negative ions, utilize machine learning algorithms to acquire suitable high-voltage pulse parameters to improve the efficiency of negative ion generation, enabling the potted plant to efficiently and continuously release plant-derived negative ions in an indoor environment under safe conditions, thereby increasing the indoor negative ion concentration.

[0063] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for generating negative ions from plants, characterized in that, The method includes: Acquire the basic plant information of the target potted plant and set the initial high-voltage pulse parameters and the desired negative ion concentration target value based on the plant basic information. Construct an intelligent negative ion generating system based on the plant basic information, the initial high-voltage pulse parameters and the desired negative ion concentration target value. Based on the initial high-voltage pulse parameters, N sets of experimental high-voltage pulse parameters are generated through machine learning algorithms. Based on the experimental high-voltage pulse parameters, the target potted plant was stimulated with high-voltage pulses to obtain the negative ion concentration, actual plant voltage and environmental parameters in real time, and a multimodal negative ion experimental dataset was constructed. Based on the multimodal negative ion experimental dataset and the desired negative ion concentration target value, the intelligent negative ion generation system is used to obtain optimized high-voltage pulse parameters. The optimized high-voltage pulse parameters are subjected to safety verification and parameter adjustment. When the optimized high-voltage pulse parameters pass the safety verification, the target potted plant is stimulated with high-voltage pulse based on the optimized high-voltage pulse parameters.

2. The method for generating negative ions from plants according to claim 1, characterized in that, Acquire basic information about the target potted plant and set initial high-voltage pulse parameters and target negative ion concentration based on the basic information of the target potted plant, including: Obtain the user's qualitative needs, and transform the user's qualitative needs into specific mathematical targets as the expected negative ion concentration target value; The basic plant information includes the type and size of the potted plant; A historical information database is constructed, which contains historical multimodal negative ion experimental datasets and has a built-in plant-parameter knowledge base, which stores the effective and safe pulse parameter ranges corresponding to different plant types. The initial high-voltage pulse parameters are set based on the historical information database and the basic information of the target potted plant, while the baseline environmental parameters are obtained. The initial high-voltage pulse parameters include the initial voltage, initial frequency, and initial duty cycle.

3. The method for generating negative ions from plants according to claim 2, characterized in that, The initial high-voltage pulse parameters are set based on the historical information database and the basic information of the target potted plant, while benchmark environmental parameters are acquired, including: Based on the basic information of the target potted plant, the historical information database is matched and queried, and a set of medium pulse parameters is selected from the plant-parameter knowledge base as the initial high-pressure pulse parameters. The current environmental parameters are collected and recorded as baseline environmental parameters, including the initial negative ion concentration and the current illuminance, temperature, and humidity.

4. The method for generating negative ions from plants according to claim 1, characterized in that, Based on the initial high-voltage pulse parameters, N sets of experimental high-voltage pulse parameters are generated through machine learning algorithms, including: The experimental high-voltage pulse parameters include the experimental voltage, experimental frequency, and experimental duty cycle.

5. A method for generating negative ions from plants according to claim 1, characterized in that, Based on the experimental high-voltage pulse parameters, high-voltage pulse stimulation was applied to the target potted plant to obtain the negative ion concentration, actual plant voltage, and environmental parameters in real time. A multimodal negative ion experimental dataset was then constructed, including: The environmental parameters include illuminance, temperature, and humidity; The multimodal negative ion experimental dataset is composed of the experimental high-voltage pulse parameters, the negative ion concentration, the actual voltage of the plant, and the environmental parameters.

6. A method for generating negative ions from plants according to claim 1, characterized in that, Based on a multimodal negative ion experimental dataset and the desired negative ion concentration target value, optimized high-voltage pulse parameters are obtained using an intelligent negative ion generation system, including: The baseline environmental parameters, the multimodal negative ion experimental dataset, and the target value of the desired negative ion concentration are input into the intelligent negative ion generation system, and the Bayesian optimizer is used for analysis to obtain the optimized high-voltage pulse parameters.

7. A method for generating negative ions from plants according to claim 1, characterized in that, The optimized high-voltage pulse parameters undergo safety verification and parameter adjustment. When the optimized high-voltage pulse parameters pass the safety verification, high-voltage pulse stimulation is applied to the target potted plant based on the optimized high-voltage pulse parameters, including: Safety boundary conditions are set according to IEC standards to constrain the optimized high-voltage pulse parameters. These safety boundary conditions include a maximum voltage threshold and a maximum current threshold. When the optimized high-voltage pulse parameters meet the safety boundary conditions, high-voltage pulse stimulation is directly applied to the target potted plant based on the optimized high-voltage pulse parameters. If the optimized high-voltage pulse parameters do not meet the safety boundary conditions, the PSO algorithm is used to adjust the current optimized high-voltage pulse parameters and then the safety check is re-executed until the adjusted optimized high-voltage pulse parameters meet the safety boundary conditions. Based on the adjusted optimized high-voltage pulse parameters, high-voltage pulse stimulation is applied to the target potted plant.

8. A method for generating negative ions from plants according to claim 1, characterized in that, The method further includes: When applying high-voltage pulse stimulation to the target potted plant, flow restriction and protective measures should be taken. The current limiting measure refers to adaptively limiting the current; The protective measures referred to here are adaptive voltage regulation.

9. A plant negative ion generation system, applying the method according to any one of claims 1 to 8, characterized in that, include: The information acquisition and initialization module is used to acquire the basic plant information of the target potted plant, set the initial high-voltage pulse parameters based on the basic plant information and historical information database, and receive user input to set the target value of the desired negative ion concentration. The pulse parameter decision module is used to generate N sets of experimental high-voltage pulse parameters based on the initial high-voltage pulse parameters and through a built-in machine learning algorithm. The high-pressure stimulation and data acquisition module includes a high-pressure pulse generation unit and a sensor unit. The high-pressure pulse generation unit is used to apply high-pressure pulse stimulation to the target potted plant based on the experimental high-pressure pulse parameters. The sensor unit is used to collect negative ion concentration, actual plant voltage and environmental parameters in real time, and to construct a multimodal negative ion experimental dataset. The parameter optimization module receives the multimodal negative ion experimental dataset and the desired negative ion concentration target value, and obtains optimized high-voltage pulse parameters through built-in optimization algorithms. The safety verification and execution module is used to perform safety verification and parameter adjustment on the optimized high-voltage pulse parameters. The safety verification and execution module includes a safety verification unit and a parameter adjustment unit. The safety verification unit is used to verify the safety of the parameters according to preset safety boundary conditions. The parameter adjustment unit is used to adjust the parameters that fail the verification. After the parameters pass the verification, the safety verification and execution module controls the high-voltage pulse generating unit to stimulate the target potted plant based on the final optimized high-voltage pulse parameters.

Images