A multi-energy coupling-based net-zero energy consumption organic vertical farm system and method

Abstract

The application provides a kind of net zero energy consumption organic stereo farm system and method based on multi-energy coupling, which realizes the synergistic optimization of carbon cycle, energy cycle and nutrient solution cycle through digital twin modeling, spectral sensing prediction, crop-algae coupling scheduling, crop residue energy recovery and multi-loop closed-loop control.The method comprises: collecting environmental, crop and energy consumption multi-modal data and standardizing modeling;Construct a carbon dioxide priority scheduling model to link crop respiration and algal photosynthesis, achieve carbon-oxygen cycle balance;Anaerobic fermentation of crop residues produces biogas and is converted into electrical energy, and the fermentation liquid is returned to the nutrient solution unit, achieving energy and nutrient reuse;Based on multi-modal sensing of spectrum and gas exchange, combined with LSTM prediction and Kalman filter correction, dynamically output light and fertilizer control instructions;Through the hybrid matrix and genetic algorithm optimization colony resource allocation, maintain metabolic stability.

Description

Technical Field

[0001] This invention relates to the field of net-zero energy agriculture technology, and in particular to a net-zero energy organic three-dimensional farm system and method based on multi-energy coupling. Background Technology

[0002] As modern agriculture develops towards high density, vertical integration, and facility-based systems, the energy consumption and carbon emissions of farm systems are becoming increasingly prominent. While traditional greenhouses and vertical farms can maintain the light, water, fertilizer, and atmospheric conditions for crops through automated equipment, their operational models often exhibit the following shortcomings: First, existing technologies mostly rely on regulating a single environmental variable, such as maintaining crop growth through constant light intensity or fixed water pump flow. However, the carbon cycle, energy cycle, and nutrient solution cycle are inherently intertwined, and regulating only one link can easily lead to system instability or decreased energy efficiency. Secondly, most farm systems focus only on the immediate control of crop growth conditions, lacking real-time constraints on the balance between carbon emissions and carbon sequestration. For example, excessive carbon dioxide input may not be effectively utilized, resulting in waste and emission pressure.

[0003] Therefore, we propose a net-zero energy organic three-dimensional farm system and method based on multi-energy coupling. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by providing a net-zero energy organic three-dimensional farm system and method based on multi-energy coupling, thereby solving the technical problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling includes the following steps: S1. Establish a digital twin model to initialize and model the environmental parameters, crop growth parameters, and energy budget parameters of the organic three-dimensional farm, forming a multimodal sensing and carbon-energy cycle operation baseline; S2. Collect carbon dioxide data released by crop respiration and direct the carbon dioxide to the algae cultivation unit. During the photosynthesis of algae, oxygen is generated and reinjected into the crop growth chamber. The digital twin model dynamically prioritizes the carbon dioxide-oxygen flow distribution to match the metabolic needs of different crop growth stages. S3. Anaerobic fermentation of crop residues is carried out to obtain biogas, which is then input into the energy subsystem as supplementary energy. At the same time, the fermentation residue is returned to the nutrient solution circulation unit, and the biogas is converted into electricity through the energy storage unit to avoid the impact of instantaneous energy fluctuations on system stability. S4. Collect data on the light demand, water demand and gas exchange of crop communities based on spectral imaging sensors, root zone conductivity sensors and gas sensors, and perform cross-temporal calculations on the multimodal sensing data in combination with time-series prediction algorithms to form a prediction model of the complementary energy-water-light characteristics of crop communities. S5. Based on the energy-water-light complementary feature prediction model, use artificial intelligence algorithms to dynamically generate a hybrid matrix, and bind the hybrid matrix with the diurnal metabolic rhythm of crops to automatically adjust the planting ratio, light distribution and water and fertilizer scheduling of different crop communities, so that the crop community can maintain the stability of the metabolic rhythm while minimizing the overall energy consumption of the system. S6. During the cycle from step S2 to step S5, the carbon dioxide flow, oxygen flow, energy compensation flow and multimodal sensing prediction results are continuously coupled and optimized to ensure that carbon emissions and energy consumption in the agricultural production process are balanced in real time, thereby maintaining the net-zero energy consumption dynamic steady-state operation of the organic three-dimensional farm system.

[0006] S1 specifically involves: collecting environmental parameters, including temperature, humidity, light intensity, carbon dioxide concentration, and nutrient solution pH; collecting crop growth parameters, including plant height, leaf area index, root biomass, and chlorophyll content; collecting energy budget parameters, including carbon dioxide supply, oxygen emissions, lighting energy consumption, and nutrient solution pump energy consumption; standardizing the environmental parameters, crop growth parameters, and energy budget parameters; and establishing an operating baseline based on the standardized parameters, including a carbon balance coefficient and an energy efficiency coefficient.

[0007] S2 specifically involves: collecting carbon dioxide concentration data released by crop respiration; transmitting the carbon dioxide concentration data to the algae cultivation unit and inputting it at a preset flow rate; establishing a carbon sink model during algal photosynthesis and calculating the net photosynthetic rate based on the carbon dioxide concentration; setting weighting factors based on crop growth stages and using a weighted priority scheduling algorithm to dynamically schedule carbon dioxide allocation; and matching the scheduling results with the metabolic needs of different crops to ensure that carbon dioxide utilization efficiency is not lower than a preset threshold.

[0008] S3 specifically involves: collecting crop residues and controlling their moisture content within a preset range; fermenting the residues in an anaerobic digester, maintaining temperature, pH, and residence time to meet set conditions to obtain biogas; transporting the biogas to the energy subsystem, converting it into electrical energy, and returning the fermentation liquid to the nutrient solution unit for recycling; staggering the distribution of electrical energy in the energy storage unit to avoid energy fluctuations exceeding a preset threshold; and avoiding the adverse effects of instantaneous energy fluctuations on system stability through distribution.

[0009] S4 specifically involves: collecting the spectral reflectance of crop leaves within a preset wavelength range using a spectral sensor; collecting the transpiration rate and gas exchange rate of the crop community using an environmental sensing unit, which includes a capacitive humidity sensor, an infrared gas analyzer, and an oxygen electrode gas sensor; inputting the collected data into a prediction model to predict the light and water requirements within a preset time range in the future, and performing real-time corrections using a filtering algorithm; and outputting light and water vapor control commands to dynamically adapt to the environmental factors of the crop community.

[0010] S5 specifically involves: constructing a crop community mixing matrix based on energy, water, and light prediction results; iteratively optimizing the mixing matrix using an optimization algorithm to minimize energy consumption; generating a light and water / fertilizer allocation scheme based on the optimization results and limiting the control error to a preset range; outputting the allocation scheme to a light and water / fertilizer control device; evaluating the community metabolic rhythm through spectral analysis and triggering re-optimization when the stability is lower than a preset threshold.

[0011] S6 specifically involves: collecting real-time data on carbon dioxide flow, oxygen flow, energy flow, and nutrient solution flow; using control algorithms to dynamically regulate each flow rate to keep system deviation within a preset range; constraining the difference between carbon and energy budgets to not exceed a set threshold within a preset time period; establishing a coupled control relationship between carbon cycle, energy cycle, and material cycle, and setting balance judgment conditions; evaluating system operation based on the net zero energy efficiency factor, and triggering parameter re-optimization and resource reallocation when the efficiency is lower than the threshold.

[0012] A net-zero energy organic three-dimensional farm system based on multi-energy coupling includes: The digital twin modeling module is used to collect and model environmental parameters, crop growth parameters, and energy budget parameters of organic vertical farms, forming a multimodal sensing and carbon-energy cycle operation baseline. The carbon dioxide-oxygen cycle module is used to collect carbon dioxide released by crop respiration and transport it to the algae cultivation unit. During the photosynthesis of algae, oxygen is generated and reinjected into the crop growth chamber. At the same time, the carbon dioxide-oxygen flow distribution is dynamically prioritized based on a digital twin model to match the metabolic needs of different crop growth stages. The residue anaerobic fermentation and energy recovery module is used to anaerobic ferment crop residues to obtain biogas and input it into the energy subsystem as supplementary energy. At the same time, the fermentation residue is returned to the nutrient solution circulation unit, and the power is staggered through the energy storage unit to avoid the impact of instantaneous energy fluctuations on the system stability. The multimodal sensing and prediction module, including a spectral imaging sensor, a root zone conductivity sensor, and a gas sensor, is used to collect data on the light demand, water demand, and gas exchange of crop communities, and to form an energy-water-light complementary feature prediction model by combining it with a time-series prediction algorithm. The intelligent control module is used to generate a hybrid matrix based on the prediction model using artificial intelligence algorithms, and bind the hybrid matrix with the crop diurnal metabolic rhythm to automatically adjust the planting ratio, light distribution and water and fertilizer scheduling of different crop communities, thereby minimizing the overall energy consumption of the system while maintaining the stability of the metabolic rhythm. The closed-loop optimization module is used to couple and optimize the carbon dioxide flow, oxygen flow, energy compensation flow and multimodal sensing and prediction results to ensure that carbon emissions and energy consumption in the agricultural production process are balanced in real time, thereby maintaining the net-zero energy consumption dynamic steady-state operation of the organic three-dimensional farm system.

[0013] The beneficial effects of this invention are as follows: This invention achieves a triple cycle of carbon, energy, and nutrients by constructing a dynamic coupling mechanism involving multiple loops such as crop respiration, algal photosynthesis, residue fermentation, and energy recovery. The system can still operate in self-balancing mode under day-night cycles and seasonal fluctuations, continuously maintaining a dynamic balance between energy input and output, thus realizing a truly net-zero energy organic agriculture system.

[0014] This invention introduces a comprehensive analysis mechanism that simultaneously incorporates carbon fixation, respiration, and energy consumption indicators into the carbon cycle pathway, enabling the system to quantify carbon utilization efficiency and energy conversion efficiency in real time. This mechanism effectively avoids the waste or emissions caused by excessive carbon dioxide input in traditional systems, achieving simultaneous improvement in carbon utilization and energy efficiency. The system establishes a bidirectional carbon-oxygen regulation channel between algae and crops, automatically adjusting the photosynthetic intensity and carbon dioxide absorption rate of algae according to the crop growth stage and respiration intensity. Through this synergistic mechanism, algae provide oxygen and carbon fixation compensation when crop photosynthesis is insufficient, achieving adaptive balance and stable operation of cross-species metabolic processes. Crop residues can produce renewable energy sources such as methane through anaerobic fermentation, which is fed back to the lighting and temperature control systems through energy storage and energy recovery units, achieving a closed-loop energy system. Simultaneously, the fermentation broth is treated and returned to the nutrient solution system, forming a co-circulation chain of energy and nutrients, significantly reducing dependence on external energy and fertilizers.

[0015] This invention introduces a multimodal sensing network integrating spectral imaging, gas exchange, and root zone conductivity. Combined with time-series prediction algorithms and filtering correction mechanisms, it can pre-emptively manage light, water, and gas supply before changes in the crop environment occur. This intelligent prediction strategy significantly improves the foresight and stability of regulation, reducing energy waste and the impact of environmental fluctuations.

[0016] The crop community mixing matrix and intelligent optimization mechanism proposed in this invention can automatically calculate and allocate resource ratios based on the dynamic needs of different crops for light, water, and carbon, achieving optimal energy consumption and metabolic stability under multi-plant co-habitation conditions. This mechanism effectively improves the composite utilization rate and overall biomass output of the vertical planting system. Through real-time weighted feedback control of the carbon, energy, and nutrient cycling loops, the system can quickly recover to a steady state when external fluctuations or sudden increases in energy consumption occur. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the net-zero energy organic three-dimensional farm system framework based on multi-energy coupling according to the present invention; Figure 2 This is a schematic diagram of a net-zero energy organic three-dimensional farm operation method based on multi-energy coupling according to the present invention; Figure 3 This is a framework diagram for the coordinated operation of photovoltaic agriculture integration, microalgae resource utilization, and net-zero carbon emissions. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1: As Figure 2 As shown, this embodiment provides a method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling, including the following steps: S1. Establish a digital twin model to initialize and model the environmental parameters, crop growth parameters, and energy budget parameters of the organic three-dimensional farm, forming a multimodal sensing and carbon-energy cycle operation baseline; S2. Collect carbon dioxide data released by crop respiration and direct the carbon dioxide to the algae cultivation unit. During the photosynthesis of algae, oxygen is generated and reinjected into the crop growth chamber. The digital twin model dynamically prioritizes the carbon dioxide-oxygen flow distribution to match the metabolic needs of different crop growth stages. S3. Anaerobic fermentation of crop residues is carried out to obtain biogas, which is then input into the energy subsystem as supplementary energy. At the same time, the fermentation residue is returned to the nutrient solution circulation unit, and the biogas is converted into electricity through the energy storage unit to avoid the impact of instantaneous energy fluctuations on system stability. S4. Collect data on the light demand, water demand and gas exchange of crop communities based on spectral imaging sensors, root zone conductivity sensors and gas sensors, and perform cross-temporal calculations on the multimodal sensing data in combination with time-series prediction algorithms to form a prediction model of the complementary energy-water-light characteristics of crop communities. S5. Based on the energy-water-light complementary feature prediction model, use artificial intelligence algorithms to dynamically generate a hybrid matrix, and bind the hybrid matrix with the diurnal metabolic rhythm of crops to automatically adjust the planting ratio, light distribution and water and fertilizer scheduling of different crop communities, so that the crop community can maintain the stability of the metabolic rhythm while minimizing the overall energy consumption of the system. S6. During the cycle from step S2 to step S5, the carbon dioxide flow, oxygen flow, energy compensation flow and multimodal sensing prediction results are continuously coupled and optimized to ensure that carbon emissions and energy consumption in the agricultural production process are balanced in real time, thereby maintaining the net-zero energy consumption dynamic steady-state operation of the organic three-dimensional farm system.

[0020] S1 specifically includes the following sub-steps: S110, Environmental Parameter Acquisition: Utilizing temperature and humidity sensors, PAR quantum sensors, and infrared sensors. The analyzer and pH electrode collect key parameters of the farm environment, including but not limited to: temperature: 15-35℃; relative humidity: 40-90%; light intensity: 100-1000 μmol·m⁻². -2 ·s -1 ; Concentration: 300-1200ppm; Nutrient solution pH: 5.5-7.5; Sampling cycle: 1-5min; All data are uploaded to the digital twin database in real time.

[0021] S120. Crop growth parameter collection: Plant height (10-120cm) and leaf area index (LAI) (0.5-6.0) are obtained through an image recognition system; chlorophyll content (20-60SPAD) is measured through a SPAD meter; root zone dry matter (1-20g / plant) is measured using the drying method, with a sampling frequency of once a day to form a dynamic record of community growth status.

[0022] S130. Energy Budget Parameter Acquisition: Infrared gas flow meters, electrochemical sensors, and online power meters are used to collect data including, but not limited to: Input rate: 0-10 L / min; Discharge rate: 0-8L / min; Lighting energy consumption: 0-2kW; Water pump energy consumption: 0-500W; Sampling cycle: 1min.

[0023] S140. Data Standardization: Z-score standardization method is used.

[0024] in, Represents the original data; This represents the mean of this type of data; This indicates the standard deviation of this type of data. After standardization, data from different environmental conditions are comparable.

[0025] S150, Establishing the Operating Baseline: Based on the results of S110-S140, establish the carbon balance ratio and energy efficiency ratio: Carbon balance sheet factor:

[0026] in, Indicates the amount of photosynthetic fixation by crops; Indicates the amount of respiration released by the crop; The formula above represents the amount of external input and measures carbon utilization efficiency: this coefficient is used to quantify external input. How much of it is effectively fixed (after subtracting respiratory losses)? Approaching 1 indicates input It is basically fixed; when Low → indicates Insufficient fixed efficiency leads to waste; System operation evaluation: It can serve as a core monitoring indicator for carbon cycling in a vertical farming system, used to determine whether an ideal carbon balance has been achieved; Optimization basis: If the value is too low, it indicates... If the input is excessive or the crop's photosynthetic efficiency is insufficient, adjustments should be made. The amount of electricity delivered or the light intensity; if the value is consistently ≥0.9, it indicates that the system has a high carbon utilization rate.

[0027] Energy efficiency coefficient:

[0028] in, This represents the crop dry matter output per unit period (g). This represents the total energy input of the system (kWh).

[0029] In a preferred embodiment, for example at a temperature of 25°C and a light intensity of 500 μmol·m⁻¹, -2 ·s -1 , At a concentration of 600 ppm, the following was measured. =0.92, =3.8 g / kWh; at a temperature of 28℃ and a light intensity of 800 μmol·m -2 ·s -1 , At a concentration of 900 ppm, the following was measured. =0.95, =4.2g / kWh.

[0030] The results show that the baseline model can operate stably under different environments, ensuring the repeatability and universality of carbon-energy balance.

[0031] Furthermore, the digital twin model also collects photovoltaic agricultural synergy parameters, including photovoltaic panel tilt angle, photovoltaic panel array shading area, real-time photovoltaic power generation, photovoltaic module backsheet temperature, crop canopy photosynthetically active radiation, crop canopy temperature, and LED supplemental lighting power. The system incorporates photovoltaic agriculture coordination parameters into the operational baseline and establishes a synergistic constraint relationship between crop light requirements and photovoltaic power generation revenue. When the photosynthetically active radiation of the crop canopy is below the target range for the corresponding crop growth stage, the digital twin model prioritizes reducing the shading ratio of the photovoltaic panels or increasing the LED supplemental lighting power. When the photosynthetically active radiation of the crop canopy meets the target range and the state of charge of the energy storage unit is below a set threshold, the digital twin model prioritizes increasing the power generation output of the photovoltaic panels, enabling the photovoltaic panels to participate in system energy compensation without affecting crop photosynthesis. Thus, the photovoltaic agriculture unit is no longer merely an external energy supply device, but a coupled node that participates in crop light regulation, shading control, and energy recovery.

[0032] S2 specifically includes the following sub-steps: S210. Acquisition of carbon dioxide time-series data: Using an infrared gas sensor, data on respiration release from crop communities is collected at a time resolution of 1 minute. concentration Concentration at the inlet of the algae culture unit Record gas volume flow rate (0.1-1.0 L / min). System volume A range of 50-500 L was used for subsequent kinetic calculations, with light intensity recorded simultaneously. (200-1000 μmol·m -2 ·s -1 ) and temperature T （ 20-30℃).

[0033] S220, Establishment Mass conservation kinetics: The algal culture unit is approximated by a completely mixed reactor (CSTR), and its The change in concentration over time is given by the following formula:

[0034] in This represents the carbon dioxide concentration of the system at time t (unit: mol / m³). This indicates the concentration of carbon dioxide in the externally input gas (mol / m³). The inlet flow rate (m³ / s) represents the gas input rate to the system; V is the effective volume of the reactor (m³), a constant. This represents the rate of carbon dioxide consumption per unit volume due to crop photosynthesis or algal fixation (mol / (m³·s)). This term is related to the current carbon dioxide concentration C(t) and light intensity I(t).

[0035] This equation describes the internal workings of the system. The dynamic equilibrium process of concentration change over time, where: the first term This is a gas input compensation term, indicating that when the input concentration is higher than the system concentration, The system is continuously replenished from the outside; the second term, U(C(t),I(t)), is the consumption term due to photosynthesis, representing the loss caused by the photosynthetic reaction. Absorption rate; the above equation reflects The "input-consumption-accumulation" balance mechanism within the system is the core mathematical model for the dynamic regulation of the carbon cycle in multi-energy coupled systems. In detail, this dynamic equation can be calculated in real time. Concentration change rate And it is used as a feedback signal input in the controller for: real-time adjustment of the intake air flow q(t), to prevent The concentration is too high or too low; it determines the carbon fixation efficiency under current illumination conditions; and it provides a basis for decision-making regarding energy distribution and light intensity control. This equation combines the sensor input signal ( Concentration sensors and light sensors can be used to solve the problem in real time, thereby achieving closed-loop control.

[0036] To accurately describe the dynamic relationship between carbon dioxide fixation rate and gas concentration and light intensity, the photosynthetic rate function is established as follows:

[0037] Where U(C,I) represents the carbon dioxide fixation rate per unit volume, i.e., the photosynthetic rate; is the photosynthetic efficiency coefficient, representing the overall efficiency of a biological system in converting light energy into chemical energy; C is the current carbon dioxide concentration in the system; K is the carbon dioxide half-saturation constant, representing the carbon dioxide concentration corresponding to when the photosynthetic rate reaches half of its maximum value; This represents the maximum photosynthetic rate under light intensity I. is the theoretical maximum photosynthetic rate, which is the limit that can be achieved under extremely strong light; k is the light response coefficient, which reflects the sensitivity of light intensity to the growth of the photosynthetic rate; I is the light intensity, which represents the photosynthetically active radiation intensity. The above parameters are preferably determined experimentally in S240.

[0038] This function consists of two parts: the first term Used to characterize the saturation effect of carbon dioxide concentration on photosynthesis, that is, when the carbon dioxide concentration is low. This becomes a limiting factor; when the concentration increases to a level much higher than the half-saturation constant K, the rate of photosynthesis tends to saturate and no longer increases linearly with concentration. (The latter term...) Used to characterize the response of light intensity to the rate of photosynthesis, reflecting that as light intensity increases, the photosynthetic rate gradually rises but eventually tends to a stable value. (Exponential term) The nonlinear characteristics of the light response are characterized, enabling the model to accurately reflect the actual photosynthetic saturation effect.

[0039] S230, Construction Priority scheduling target: in units The time interval is defined by maximizing the net photosynthetic gain brought about by the increment. Allocation priority:

[0040] in This represents the partial derivative of the photosynthetic rate U(C,I) with respect to the carbon dioxide concentration C(t) in the system at time t, i.e., the sensitivity of the photosynthetic rate to small changes in carbon dioxide concentration. (Symbol) This represents the partial derivative operation, which means calculating the effect of changes in carbon dioxide concentration on the photosynthetic rate under the condition that the light intensity I(t) remains constant. The light energy utilization efficiency coefficient; t represents the maximum photosynthetic rate under the current light intensity; K is the half-saturation constant; C(t) is the carbon dioxide concentration detected by the system in real time.

[0041] This partial derivative expression reflects the sensitivity of the photosynthetic rate to changes in carbon dioxide concentration: when A large value indicates that changes in carbon dioxide concentration in the system significantly affect the rate of photosynthesis; when When the value approaches zero, it indicates that the system is in a state of equilibrium. Saturation state, at which point further increase Concentration has a limited effect on increasing the rate of photosynthesis. From a physiological perspective, Corresponding to the activity of intracellular carbon fixative enzymes in plants or algae cells and their external effects The ability to respond to concentration is an important indicator for measuring carbon utilization efficiency.

[0042] In a preferred embodiment, when multiple receptors exist (e.g., three pathways from algal units A and B to the crop growth chamber), then... Distribute from largest to smallest, while applying stage weights. (Vegetative growth period) =0.7, reproductive growth period =0.3 (parameter can be adjusted according to actual needs): To achieve quantitative evaluation of the carbon use response of crop populations at different growth stages, the weighted response scoring function is defined as follows:

[0043] in This represents the carbon response score of the j-th crop population or growth unit at time t; This is a weighting coefficient for this growth stage, used to characterize the weight of carbon demand at different growth stages; The photosynthetic response coefficient (i.e., the partial derivative of photosynthetic rate with respect to carbon dioxide concentration) of the corresponding crop population reflects the sensitivity of photosynthetic rate to changes in carbon dioxide concentration. The purpose of the above scoring model is to standardize and quantify the carbon response of different crop populations in a multi-crop symbiotic system; when A higher value indicates that the crop population is in a state of high carbon demand or high photosynthetic activity, and the system should prioritize its allocation. Resources; when A lower value indicates that the group is more sensitive to... It is not sensitive to changes in concentration, and gas supply can be temporarily suspended to reduce energy consumption; Weighting coefficients The weighting is set according to the crop growth stage. For example, a lower weight (e.g., 0.5) can be used for seedlings, indicating lower carbon demand; a higher weight (e.g., 1.2) can be used for vigorous growth, indicating strong carbon fixation activity; and a moderate weight (e.g., 0.8) can be used to maintain metabolic balance. By introducing weighting coefficients, adaptive carbon allocation can be achieved for different crop populations throughout their life cycle. Descending order allocation And satisfy the flow constraint of 0.05 ≤ per channel. ≤1.0L / min, total flow rate = The parameters can be adjusted according to actual needs.

[0044] S240, Parameter Calibration and Uncertainty Sampling: To avoid a "black box," Perform experimental calibration: ={300,600,900}μmol·m -2 ·s -1 , The net photosynthetic rate was measured at 3×3 condition points ({300, 600, 900} ppm) and obtained using least-squares fitting. Considering environmental fluctuations, for Latin hypercube sampling (LHS) is performed with measurement noise, with a sampling size N = 2000–5000 and a confidence interval of 95%. This is used to evaluate the robustness of the scheduling strategy under parameter uncertainty, and the utilization distribution is output. .

[0045] S250, Performance and Safety Threshold Determination: Based on Utilization efficiency

[0046] As the main indicator, requirements ≥0.85 (both P50 and P90 are satisfied); Simultaneously, a safety boundary is set: when any path >1.0L / min or When the flow rate is >1200ppm, the system enters protection mode (automatically reduces the flow rate of this channel to 0.3L / min and linearly recovers within 5 minutes).

[0047] The function of the above formula: dynamic evaluation Utilization efficiency: The numerator represents the cumulative assimilation of nutrients by the crop within the time interval T. The quantity; the denominator represents the actual input to the system within the same period. Net flux. The ratio of the two is... The utilization efficiency; considering the dynamic process: this formula is not a static ratio, but an integral form, which can reflect the efficiency of utilization; The actual situation of utilization rate fluctuations over time and under environmental conditions; optimization basis: if efficiency is low, it indicates... Excessive carbon input or insufficient light requires adjustment of the carbon source input or lighting configuration; if the efficiency is close to 1, it indicates... It is basically fully utilized.

[0048] In a preferred embodiment, for example during the vegetative growth period, an LHS assessment with N=3000 provides... The median was 0.88 and the 10th percentile was 0.86, meeting the threshold; the median of the reproductive growth period was 0.86. Actual measurements showed that the utilization rate was 0.76-0.82 before scheduling and stabilized at 0.86-0.90 after scheduling, with a fluctuation of ±2% within a 10-minute sliding window.

[0049] S3 specifically includes the following sub-steps: S310. Crop Residue Collection and Pretreatment: After collecting crop residue from the planting unit, it is first mechanically crushed to control the particle size between 5-20mm, which facilitates the attachment and decomposition of anaerobic fermentation microorganisms. The crushed residue is then uniformly mixed using a stirring device, and the moisture content is adjusted to 60-70% by adding clean water or reflux liquid for precise adjustment. The stirring cycle is set to 10 minutes every 4 hours to prevent sedimentation and enhance the mass transfer efficiency of anaerobic fermentation.

[0050] S320 Anaerobic Fermentation Conditions: In a closed anaerobic fermenter, maintain a temperature of 35-38℃ and a pH of 6.8-7.2, with the hydraulic retention time (HRT) controlled at 20-25 days. The fermenter is equipped with a temperature probe, pH electrode, and agitator. Temperature fluctuations should not exceed ±0.5℃, and pH deviations should not exceed ±0.1℃. Experimental verification shows that methane content is most stable at 35-36℃ and pH 6.9-7.0; when the temperature exceeds 40℃ or the pH exceeds 7.5, the methane content decreases to below 50%, verifying the rationality and necessity of the parameter range.

[0051] S330. Biogas Collection and Energy Conversion: Collected biogas must have a methane content ≥55% before it can be input into the energy subsystem for power generation. The generator set uses a micro gas internal combustion engine or a solid oxide fuel cell (SOFC), with a conversion efficiency maintained at 30-40%. Test method: The methane content of the biogas is determined using a gas chromatograph, and the electrical output is recorded using a power meter. The efficiency calculation formula is:

[0052] in, Indicates the output electrical energy (kWh). This indicates the calorific value of methane combustion (kWh).

[0053] The above formula serves the following purposes: Measuring methane utilization efficiency: This formula assesses how much of the input methane energy is successfully converted into usable energy output during anaerobic fermentation or methane combustion; Energy system performance indicator: This is one of the commonly used performance indicators in energy engineering, used to determine the efficiency of fermentation devices or energy recovery systems; Optimization basis: If... A low reading indicates heat loss or insufficient energy conversion in the system, requiring optimization of reaction conditions or equipment structure.

[0054] S340. Fermentation Broth Reflux and Nutrient Control: After solid-liquid separation, the fermentation broth is refluxed to the nutrient solution circulation unit, requiring nitrogen concentration to be controlled between 50-150 mg / L. When the detected nitrogen concentration exceeds 180 mg / L, the system automatically dilutes the broth with clean water or low-salt water to restore the concentration to the target range, preventing root zone salt damage. Nitrogen detection uses an online ion-selective electrode (ISE) with an accuracy of ±5%.

[0055] S350, Energy Storage and Peak Shaving: The energy storage unit is equipped with lithium battery packs (energy density 100-200Wh / kg) and supercapacitors (power density 5-10kW / kg) for peak shaving and transient regulation. Operating Strategy: In a preferred embodiment, when the load fluctuation is ≤±5%, the power is directly supplied by the grid and the power generation unit; when the load suddenly increases by >20%, the supercapacitor prioritizes releasing energy, with a response time ≤50ms; when the load suddenly decreases by >20%, the lithium battery enters charging mode, absorbing and storing excess energy. Load changes are monitored in real time by a power meter and current transformer, and the working state of the battery and capacitor is scheduled in the controller using a PID algorithm to ensure steady-state system operation.

[0056] S4 specifically includes the following sub-steps: S410. Spectral Imaging Acquisition and Preprocessing: The reflectance of crop leaves in the 400-800nm ​​wavelength range is acquired using a spectral imaging sensor, with a sampling frequency of 1-5 minutes / sample. The raw spectral vectors are then stored in a digital twin database. To avoid interference from lighting conditions and sensor noise, preprocessing is performed after acquisition. Noise reduction: A Savitzky-Golay smoothing filter (window width 5-9 points, second-order polynomial) is used to remove high-frequency noise; Normalization: The spectral data were normalized by standard normal transformation (SNV) to standardize the mean and variance. In a preferred embodiment, principal component extraction is performed: the first 5-10 principal components are extracted using PCA, with a cumulative variance explanation rate of ≥95%, reducing redundant information.

[0057] Furthermore, the system acquires crop canopy images in the 400nm to 1000nm wavelength range using a hyperspectral imaging sensor, and extracts spectral features of leaf lesions, chlorophyll attenuation features, abnormal canopy water content features, and pest bite edge features from these images. The system inputs these features into a convolutional neural network model and outputs an early pest and disease risk level. When the early pest and disease risk level reaches a set threshold, the system prioritizes generating non-chemical control instructions. These instructions include adjusting ventilation humidity, activating physical trapping devices, releasing natural enemy insects, applying permitted microbial agents, or isolating affected crop areas. The system does not use chemical pesticide spraying as the default control instruction. The system simultaneously records the source of organic fertilizer return, the destination of algal biomass utilization, fermentation broth treatment parameters, air-to-water production parameters, non-chemical pest and disease control measures, and water and fertilizer scheduling records, forming an organic production process traceability record. This organic production process traceability record is used to demonstrate the system's non-chemical operation path in the processes of water source, fertilizer source, pest and disease control, and resource recovery.

[0058] S420, Moisture and Gas Acquisition: Through multiple types of environmental sensing units deployed in the crop canopy and ventilation flow field, the moisture evaporation and gas exchange processes of the crop community are monitored simultaneously. The environmental sensing unit includes a capacitive humidity sensor for real-time detection of changes in relative humidity and temperature-humidity gradients, and for calculating the transpiration rate of the crop community (unit: mmol·m³). -2 ·s -1 Infrared gas analyzer (IRGA) and oxygen electrode gas sensor are used to measure the carbon dioxide uptake rate and oxygen release rate of crop communities (unit: mmol·m³). -2 ·s -1 Temperature compensation and wind speed sensing modules are used to correct diffusion errors under different airflow conditions. Each sensor's sampling frequency is set to 1–5 Hz, and a timestamp synchronization mechanism is used to maintain sampling consistency with the spectral acquisition module, forming a multimodal synchronous sampling mechanism. The acquired moisture and gas signals are filtered and interpolated, and then fused with spectral reflectance data in a unified time domain to form a multimodal input dataset containing multiple parameters of light, air, and water. This dataset serves as the input basis for the energy-carbon model, used to calculate key physiological parameters such as the carbon fixation rate, light energy utilization efficiency, and transpiration rate of the crop community, and to provide real-time feedback support for subsequent energy-carbon coupling regulation algorithms.

[0059] Furthermore, the system also collects operational data from an air-to-water generator, which obtains supplementary water from ambient air condensation. This operational data includes inlet air temperature, inlet air humidity, condenser temperature, water production per unit time, energy consumption per unit of water production, water conductivity, and water pH. The system timestamps the air-to-water generator's operational data with root zone conductivity data, transpiration rate data, and nutrient solution remaining data to generate a water supply status record. This record is used to determine the priority among air-to-water production, nutrient solution return water volume, and external supplementary water volume. When the inlet air humidity is higher than a set humidity threshold and the energy consumption per unit of water production is lower than a set energy consumption threshold, the system prioritizes starting the air-to-water generator and inputs the produced water into the nutrient solution circulation unit. When the air-to-water production is insufficient to meet the crop's transpiration needs, the system then uses nutrient solution return water or external supplementary water, thus making the air-to-water module a priority source of water for water and fertilizer management.

[0060] S430, Prediction Model Construction: Input the data from S410 and S420 into the LSTM neural network model to predict the light and water requirements for the next 1-24 hours.

[0061] Training dataset: No fewer than 1,000 sets of spectral-transpiration coupled data, covering multiple seasons, day and night, and different environmental conditions; Network structure: input layer, 2-3 hidden layers (64-128 neurons per layer), output layer (predicting light / water requirements); hyperparameter settings: learning rate 0.001-0.01, batch size 32-64, number of training epochs ≥500; loss function is mean squared error (MSE). In the preferred embodiment, the training environment is as follows: NVIDIA RTX 3090 GPU with 24GB of video memory is used, and the training time is about 3-5 hours; the deep learning framework is TensorFlow 2.x; the update cycle is: retraining / fine-tuning once a day to ensure the dynamic adaptability of the model.

[0062] S440, Prediction Correction: The LSTM output is corrected in real-time using a Kalman filter, with a prediction error threshold set to ≤10% and a correction cycle of 5 minutes / time. When the difference between the predicted value and the real-time sensor value exceeds the threshold, the Kalman gain is dynamically adjusted to ensure convergence of the prediction results. For example, in a summer environment, the predicted light demand is 650 μmol·m³. -2 ·s -1 After correction, the error was reduced to 8%.

[0063] S450, Output Control Command: Converts the corrected prediction results into specific control commands and applies them in real time to the lighting and water vapor control devices: Lighting adjustment range: LED array output 0-1000 μmol·m -2 ·s -1 Water pump flow range: 0.1-1.0L / min; Gas flow range: 0.05-0.5L / min; Command issuance cycle: updated every 10s; Control accuracy: error controlled within ±5%.

[0064] S5 specifically includes the following sub-steps: S510. Construction of the Mixed Matrix: Constructing a crop community mixed matrix based on a three-dimensional prediction model of energy, water, and light. Its definition is:

[0065] in, Indicates the size of the crop community. Indicates resource types (water, sunlight, etc.) ), Indicates the first The first community to the first Demand coefficient for this type of resource.

[0066] Preferred embodiment, example: taking wheat (C1), lettuce (C2), tomato (C3), and cucumber (C4) as examples, a 4×3 matrix is ​​obtained:

[0067] The first row indicates the wheat's sensitivity to light / water / The demand coefficient is calculated accordingly.

[0068] Furthermore, the system establishes a plant formulation database, which stores physiological parameters, environmental requirements, and resource constraints of various plants at different growth stages.

[0069] Physiological parameters include plant height range, leaf area index range, root volume range, diurnal metabolic rhythm parameters, and growth cycle; environmental requirements parameters include light requirement curve, water requirement curve, carbon dioxide requirement curve, oxygen requirement curve, and suitable temperature and humidity range; resource constraints parameters include nitrogen requirement, phosphorus requirement, potassium requirement, suitable root zone electrical conductivity range, space occupancy parameters, and light shading sensitivity.

[0070] The system uses a plant formulation database to select candidate plant combinations from the set of plants to be planted that meet the current constraints of light, water, carbon source, nutrient solution, spatial height, and root zone volume. A hybrid matrix is ​​then constructed based on these candidate plant combinations. The rows of the hybrid matrix represent candidate plants or plant communities, and the columns represent resource or state dimensions such as light, water, carbon dioxide, oxygen, nitrogen, phosphorus, potassium, spatial height, root zone volume, and metabolic rhythm phase. The original four crop matrices are used as preferred examples, and the expansion of the plant species and plant combinations in the plant formulation database is not limited.

[0071] S520, Genetic Algorithm Optimization: A genetic algorithm (GA) is used to dynamically optimize the matrix, aiming to minimize energy consumption and maintain community stability. Fitness Function:

[0072] Where F is the overall performance function (dimensionless), which represents the overall operating effect of the system and is used to guide the optimization direction of the control strategy; , These represent weighting coefficients, indicating the relative importance of energy efficiency and stability in the overall evaluation; This represents the system's energy efficiency improvement rate, which is the ratio of the difference in energy input before and after optimization. Indicates system stability metrics;

[0073] in The baseline energy consumption represents the total energy consumption of the system under unoptimized or conventional operating modes (kWh). This indicates the optimized energy consumption; this indicator is automatically calculated by the monitoring module based on historical energy consumption baseline curves and real-time power data.

[0074]

[0075] in It is the power of the main frequency band (W), that is, the power in the main operating frequency band of the system; It is the total power spectral energy (W); this index is obtained by frequency domain analysis of the system power signal P(t). The closer the value is to 1, the more concentrated the energy is in the main frequency region, resulting in small system fluctuations and stable operation. When the value is low, it indicates that the energy is dispersed across multiple frequency bands, and the system is experiencing periodic oscillations or energy leakage.

[0076] The above formula serves the following purposes: Multi-objective fusion: It integrates the two objectives of "minimizing energy consumption" and "stabilizing metabolic rhythm" into a unified evaluation index, avoiding situations where optimizing only energy consumption leads to physiological disorders; Genetic algorithm selection criteria: During the iteration process, the algorithm compares... The size of the value determines the quality of individuals, thus gradually evolving to the optimal state; the weights can be flexibly adjusted: if energy conservation is the priority, then... > If stability is the priority, then... > Parameter settings: Population size 50-200; Number of iterations 100-500; Crossover probability 0.6-0.9; Mutation probability 0.01-0.05; Termination condition: Fitness change rate ≤ 0.1% for 20 consecutive generations; Output: Optimal matrix. This is used to guide subsequent resource allocation.

[0077] S530, Light and Water / Fertilizer Scheduling: Based on the optimization results, generate light and water / fertilizer scheduling ratios to ensure scheduling errors are ≤±5%. For example, after optimization, the allocation ratio is: wheat 35%, lettuce 25%, tomato 20%, cucumber 20%.

[0078] S540, Control Command Output: Converts the optimized scheduling ratio into execution commands and sends them to the LED light array and water-fertilizer mixing device. The command issuance cycle is 30 seconds per cycle. Light intensity adjustment range: 0-1000 μmol·m -2 ·s -1 Pump flow rate range: 0.1-1.0L / min; nutrient solution mixing ratio is dynamically adjusted according to the needs of the crop community.

[0079] S550, Evaluation of Metabolic Rhythm Stability: Fourier spectral analysis was used to decompose the time-series signal of crop community metabolic rhythms.

[0080] Where X(k) is the k-th frequency component (in W·s or complex form of energy units) of the complex spectrum of the frequency domain signal, representing the amplitude and phase of the signal at that frequency; x(t) is the original time domain signal, usually the power, flow, or energy data obtained from sampling; N is the total number of sampling points, i.e., the number of discrete time points sampled by the system in one period; k is the frequency index (0≤k≤N-1); t is the time sampling point index; j is the imaginary unit, used to represent phase information; It is a complex exponential basis function used to project a time-domain signal onto different frequency components.

[0081] Define the energy percentage of the dominant rhythm:

[0082] in This represents the set of frequency indices for the main frequency band, typically corresponding to the system's main energy concentration region (e.g., the 0-0.1Hz range); the above formula is used for stability determination: if When ≥90%, it indicates that most of the energy of the metabolic signal is concentrated in the main frequency band, and the system's metabolic rhythm is stable; if <90% indicates dispersed metabolic energy and rhythm disorder, requiring triggering readjustment; Noise and anomaly identification: Abnormally dispersed signal energy distribution may indicate environmental fluctuations or crop metabolic abnormalities, serving as an early warning indicator; Optimization feedback basis: The value can be used as one of the fitness functions of genetic algorithms or other optimization methods to dynamically adjust the allocation of light / water and fertilizer.

[0083] Preferred embodiment, example: Scenario 1: Rhythm stable, total energy: 100 units; main frequency band energy: 92 units;

[0084] A score greater than 90% indicates a stable metabolic rhythm.

[0085] Scenario 2: Rhythm Disorder: Total Energy: 100 units; Main Frequency Band Energy: 78 units;

[0086] If the percentage is less than 90%, it indicates that the metabolic energy distribution is scattered, and the system needs to re-optimize resource allocation.

[0087] S6 specifically includes the following sub-steps: S610, Multi-loop Data Acquisition: Acquires the following real-time data from the three-dimensional farm system: Flow rate: 0.1-5 L / min; Flow rate: 0.1-5L / min; Energy flow: lighting energy consumption, pump energy consumption, unit kWh; Nutrient solution flow rate: 1-50L / h; Sampling cycle: 1-10s / time; Acquisition equipment includes infrared gas analyzer, power meter and flow sensor.

[0088] S620, Dynamic Control: Employs a multivariable PID controller for... , The energy flow and nutrient solution flow are adjusted in real time. Parameter range: P=0.5-2.0, I=0.1-1.0, D=0.01-0.1; Tuning method: Initially, the Ziegler-Nichols method is used, and adaptive fine-tuning is performed based on steady-state error and dynamic response during operation; Control objective: The deviation of each system variable does not exceed ±2%; Dynamic performance indicators: Rise time ≤5s, Settlement time ≤15s, Overshoot ≤10%, Steady-state error ≤2%.

[0089] S630, Carbon balance constraints: Within a 24-hour integral period: the difference between carbon emissions and carbon sequestration ≤ 5%; the difference between energy input and crop sequestration ≤ 10%.

[0090] The formula is as follows:

[0091] in It is the carbon concentration change rate, which indicates what proportion of the input carbon dioxide is fixed or absorbed; It is the rate of change of energy consumption, which represents the ratio of loss between input energy and effective energy conversion; It is the concentration of carbon dioxide in the input gas, determined by... Flow sensor measured in actual operation; It is the fixed carbon dioxide concentration, that is, the portion that is absorbed and converted into organic matter through photosynthesis; The system input energy (kWh) includes energy for lighting, electric drive, and gas transport. It is the portion of energy (kWh) that is effectively utilized after energy conversion, such as the portion used to maintain photosynthesis or heat cycle.

[0092] The above formula quantifies carbon energy balance: these two indicators are used to measure whether the system has truly achieved a dynamic balance between the carbon cycle and the energy cycle, when... ≤5% → good carbon balance; when ≤10% → Reasonable energy balance; Monitoring and early warning: If or Exceeding the threshold indicates Or the energy utilization efficiency is insufficient and adjustments are needed. Delivery, lighting, or nutrient solution distribution; the foundation for achieving net-zero energy consumption: through control and This ensures the closed-loop utilization of carbon and energy, laying the foundation for a subsequent net-zero energy efficiency factor (NAE). The calculation provides the prerequisites.

[0093] Preferred embodiment, example: Scenario 1: Carbon energy balance is normal. =100mol, =96mol, If it is less than 5%, the carbon balance meets the standard; =200kWh =185kWh Less than 10%, energy balance meets the standard.

[0094] Scenario 2: Energy imbalance =120mol, =112 mol, Exceeding 5% indicates insufficient carbon utilization. =180kWh =150kWh If the percentage exceeds 10%, it indicates serious energy waste and the need for re-optimization of energy scheduling.

[0095] S640, Three-Loop Coupled Control: The controller coordinates the carbon cycle, energy cycle, and nutrient solution cycle to establish a weighted comprehensive deviation rate formula.

[0096] Where F is the comprehensive optimization objective function (dimensionless), used to quantify the overall performance of the system; , , These represent the weighting coefficients for carbon balance, energy efficiency, and nutrient balance, respectively, and satisfy the following conditions: ; It is the carbon cycle deviation, which represents the difference between the system's actual carbon budget and the target carbon balance; It is the energy deviation degree, which indicates the degree of deviation between the actual energy consumption of the system and the expected energy efficiency; It is the nutrient deviation, which indicates the deviation between the concentration changes of nutrient elements (such as nitrogen, phosphorus, and potassium) and the set steady-state value.

[0097] The above formula unifies the evaluation index: it summarizes the deviations in carbon, energy, and nutrient solution into a comprehensive index. To avoid the problem of overall imbalance caused by a single parameter meeting the standard; dynamic balance judgment: when When ≤5%, the system is considered to be in a coupled equilibrium state; if If the percentage is greater than 5%, it indicates an imbalance in a certain loop, requiring re-regulation. The weights can be flexibly adjusted: the weights can be adjusted according to actual needs; for example, in scenarios prioritizing energy conservation, the weight can be increased. Under strict carbon reduction scenarios, it can improve .

[0098] Preferred embodiment, example: Scenario 1: Normal operation, =3% =4% =2%, weight: =0.3、 =0.4、 =0.3, calculate =0.031 (3.1%), Result: =3.1% < 5%, the system determines it to be balanced.

[0099] Scenario 2: Abnormally high energy consumption =4% =12% =3%, with equal weight: =0.3、 =0.4、 =0.3, calculate: =0.071 (7.1%), Result: =7.1%>5%, indicating that the energy loop deviation is too large and the system needs to re-optimize energy allocation.

[0100] S650, Net Zero Energy Evaluation: Definition of Net Zero Energy Efficiency Factor ( ):

[0101] in, This represents the energy fixed by crop photosynthesis (kWh). This represents the energy (kWh) generated from residue fermentation and waste heat recovery. Expressed as external input energy (kWh), the determination criteria are: ≥0.95 → Achieve dynamic equilibrium; ≥1 → Energy self-sufficiency or surplus; <1→ Not up to standard.

[0102] Preferred embodiment, multi-scenario experimental verification: Summer with sufficient sunlight: =100kWh =70kWh =35kWh =1.05≥1, the system has a 5% energy surplus; low light intensity in winter: =120kWh =60kWh =55kWh =0.96≥0.95, the system remains balanced but has no surplus; abnormally high load scenario: =150kWh =80kWh =60kWh =0.93<0.95, the system triggers PID parameter re-optimization and resource scheduling adjustment. It should be emphasized that the parameters in this embodiment can be adjusted according to actual needs.

[0103] Example 2: Figure 1 As shown, this embodiment provides a net-zero energy organic three-dimensional farm system based on multi-energy coupling, including: The digital twin modeling module is used to collect and model environmental parameters, crop growth parameters, and energy budget parameters of organic vertical farms, forming a multimodal sensing and carbon-energy cycle operation baseline. The carbon dioxide-oxygen cycle module is used to collect carbon dioxide released by crop respiration and transport it to the algae cultivation unit. During the photosynthesis of algae, oxygen is generated and reinjected into the crop growth chamber. At the same time, the carbon dioxide-oxygen flow distribution is dynamically prioritized based on a digital twin model to match the metabolic needs of different crop growth stages. The residue anaerobic fermentation and energy recovery module is used to anaerobic ferment crop residues to obtain biogas and input it into the energy subsystem as supplementary energy. At the same time, the fermentation residue is returned to the nutrient solution circulation unit, and the power is staggered through the energy storage unit to avoid the impact of instantaneous energy fluctuations on the system stability. The multimodal sensing and prediction module, including a spectral imaging sensor, a root zone conductivity sensor, and a gas sensor, is used to collect data on the light demand, water demand, and gas exchange of crop communities, and to form an energy-water-light complementary feature prediction model by combining it with a time-series prediction algorithm. The intelligent control module is used to generate a hybrid matrix based on the prediction model using artificial intelligence algorithms, and bind the hybrid matrix with the crop diurnal metabolic rhythm to automatically adjust the planting ratio, light distribution and water and fertilizer scheduling of different crop communities, thereby minimizing the overall energy consumption of the system while maintaining the stability of the metabolic rhythm. The closed-loop optimization module is used to couple and optimize the carbon dioxide flow, oxygen flow, energy compensation flow and multimodal sensing and prediction results to ensure that carbon emissions and energy consumption in the agricultural production process are balanced in real time, thereby maintaining the net-zero energy consumption dynamic steady-state operation of the organic three-dimensional farm system.

[0104] Furthermore, the system also establishes a collaborative operation mechanism that integrates photovoltaic agriculture, air-to-water equipment, microalgae resource utilization, and net-zero carbon emissions.

[0105] Photovoltaic agriculture integration refers to using photovoltaic panel arrays as a coupling unit for crop shading regulation, light compensation, and power supply. The system synchronously collects photovoltaic panel tilt angle, shading area, real-time power generation, module temperature, effective photosynthetic radiation of crop canopy, and supplemental light power, and adjusts photovoltaic output and shading ratio according to crop light requirements and energy storage status.

[0106] Air-to-water generator (AWG) refers to a device that obtains supplementary water by condensing water vapor in the ambient air. The system collects data such as inlet air temperature, inlet air humidity, condenser temperature, water production per unit time, energy consumption per unit of water production, water conductivity, and water pH, and prioritizes inputting the produced water into the nutrient solution circulation unit.

[0107] Microalgae resource utilization refers to transporting carbon dioxide released by crop respiration to microalgae culture units, using microalgae photosynthesis to generate oxygen and reinjecting it into the crop growth chamber, while the harvested microalgae biomass is separated into solid and liquid components and used as an organic nutrient supplement, anaerobic fermentation substrate, or stabilized carbon fixation recording object.

[0108] The system calculates negative carbon evaluation index and net zero energy consumption evaluation index respectively. The negative carbon evaluation index is used to characterize the difference between the sum of crop carbon fixation, microalgae carbon fixation and stabilized carbon storage and the carbon emissions converted from system operation. The net zero energy consumption evaluation index is used to characterize the matching relationship between the sum of photovoltaic power generation, residual fermentation recovery energy and energy storage and allocation energy and external input energy. When the negative carbon evaluation index is greater than zero and the net zero energy consumption evaluation index is not lower than the set threshold, the organic three-dimensional farm is determined to have entered the state of coordinated operation of negative carbon and net zero energy consumption.

[0109] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0110] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0111] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0112] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling, characterized in that, Includes the following steps: S1. Establish a digital twin model to initialize and model the environmental parameters, crop growth parameters, and energy budget parameters of the organic three-dimensional farm, forming a multimodal sensing and carbon-energy cycle operation baseline; S2. Carbon dioxide is directed to the algae cultivation unit, where it generates oxygen during algae photosynthesis and is then reinjected into the crop growth chamber. The digital twin model dynamically prioritizes the allocation of carbon dioxide and oxygen flow to match the metabolic needs of different crop growth stages. S3. Anaerobic fermentation of crop residues to obtain biogas and input it into the energy subsystem as supplementary energy. At the same time, the fermentation residue is returned to the nutrient solution circulation unit, and the biogas is converted into electricity through the energy storage unit for peak-shifting. S4. Collect data on the light demand, water demand and gas exchange of crop communities based on spectral imaging sensors, root zone conductivity sensors and gas sensors, and perform cross-temporal calculations on the multimodal sensing data in combination with time-series prediction algorithms to form a prediction model of complementary energy, water and light characteristics of crop communities. S5. Utilize artificial intelligence algorithms to dynamically generate a hybrid matrix, and bind the hybrid matrix to the diurnal metabolic rhythm of crops to automatically adjust the planting ratio, light distribution, and water and fertilizer scheduling of different crop communities, so as to minimize the overall energy consumption of the crop community in the system while maintaining the stability of the metabolic rhythm.

2. The method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling according to claim 1, characterized in that, It also includes S6, which continuously couples and optimizes the carbon dioxide flow, oxygen flow, energy compensation flow and multimodal sensing prediction results to ensure that carbon emissions and energy consumption in the agricultural production process are balanced in real time, thereby maintaining the net-zero energy consumption dynamic steady-state operation of the organic three-dimensional farm system.

3. The method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling according to claim 1, characterized in that, S1 specifically refers to: Collect environmental parameters, including temperature, humidity, light intensity, carbon dioxide concentration, and pH of nutrient solution; Collect crop growth parameters, including plant height, leaf area index, root biomass, and chlorophyll content; Collect energy balance parameters, including carbon dioxide supply, oxygen emissions, lighting energy consumption, and nutrient solution pump energy consumption; The environmental parameters, crop growth parameters, and energy budget parameters are standardized. An operating baseline is established based on standardized parameters, which includes the carbon balance coefficient and the energy efficiency coefficient.

4. The method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling according to claim 1, characterized in that, S2 specifically refers to: Collect data on the concentration of carbon dioxide released by crop respiration; The carbon dioxide concentration data is transmitted to the algae cultivation unit and input at a preset flow rate; A carbon sink model was established during algal photosynthesis, and the net photosynthetic rate was calculated based on the carbon dioxide concentration. Based on crop growth stages, a weighted priority scheduling algorithm is used to dynamically schedule carbon dioxide allocation. The scheduling results are matched with the metabolic needs of different crops to ensure that carbon dioxide utilization efficiency is not lower than a preset threshold.

5. The method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling according to claim 1, characterized in that, S3 specifically refers to: Collect crop residues and control their moisture content within a preset range; The residue is fermented in an anaerobic digester, and the temperature, pH and residence time are maintained at the set conditions to obtain biogas. The biogas is transported to the energy subsystem, converted into electrical energy, and the fermentation liquid is returned to the nutrient solution unit to achieve recycling; In the energy storage unit, electrical energy is staggered to avoid energy fluctuations exceeding a preset threshold; By adjusting the energy allocation, we can avoid the adverse effects of instantaneous energy fluctuations on system stability.

6. The method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling according to claim 1, characterized in that, S4 specifically refers to: The spectral reflectance of crop leaves within a preset wavelength range is collected using a spectral sensor. The transpiration rate and gas exchange rate of the crop community are collected by an environmental sensing unit, which includes: a capacitive humidity sensor, an infrared gas analyzer, and an oxygen electrode gas sensor. The collected data is input into the prediction model to predict the light and water requirements within a preset time range in the future, and is then corrected in real time using a filtering algorithm. It outputs commands for light and water vapor regulation to dynamically adapt to environmental factors in crop communities.

7. The method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling according to claim 1, characterized in that, S5 specifically refers to: A crop community mixing matrix was constructed based on the predicted results of energy, water, and light. The hybrid matrix is ​​iteratively optimized using an optimization algorithm to minimize energy consumption; Based on the optimization results, a light and water / fertilizer allocation scheme is generated, and the control error is limited to a preset range. The allocation scheme is output to the light and water control device; Community metabolic rhythms are evaluated through spectral analysis, and re-optimization is triggered when the stability falls below a preset threshold.

8. The method for operating a net-zero energy organic three-dimensional farm based on multi-energy coupling according to claim 2, characterized in that, S6 specifically refers to: Collect real-time data on carbon dioxide flow, oxygen flow, energy flow, and nutrient solution flow; A control algorithm is used to dynamically regulate each flow rate, keeping the system deviation within a preset range; Within a preset time period, the difference between carbon balance and energy balance shall not exceed a set threshold. Establish the coupled control relationship between the carbon cycle, energy cycle, and material cycle, and set equilibrium determination conditions; The system operation is evaluated based on the net zero energy efficiency factor, and parameter re-optimization and resource reallocation are triggered when the efficiency is lower than the threshold.

9. A net-zero energy organic three-dimensional farm system based on multi-energy coupling, employing the net-zero energy organic three-dimensional farm operation method based on multi-energy coupling as described in any one of claims 1-8, characterized in that, include: The digital twin modeling module is used to collect and model environmental parameters, crop growth parameters, and energy budget parameters of organic vertical farms, forming a multimodal sensing and carbon cycle operation baseline. The carbon dioxide and oxygen circulation module is used to collect carbon dioxide released by crop respiration and transport it to the algae cultivation unit, where oxygen is generated during algae photosynthesis and then reinjected into the crop growth chamber. The residue anaerobic fermentation and energy recovery module is used to anaerobic fermentation of crop residues to obtain biogas, which is then input into the energy subsystem as supplementary energy. The fermentation residue is returned to the nutrient solution circulation unit, and the power is staggered and allocated through the energy storage unit. The multimodal sensing and prediction module, including a spectral imaging sensor, a root zone conductivity sensor, and a gas sensor, is used to collect data on the light demand, water demand, and gas exchange of crop communities, and to form a prediction model of complementary energy, water, and light characteristics by combining it with a time-series prediction algorithm. The intelligent control module is used to generate a hybrid matrix based on the prediction model using artificial intelligence algorithms, and bind the hybrid matrix with the crop diurnal metabolic rhythm to automatically adjust the planting ratio, light distribution and water and fertilizer scheduling of different crop communities, so as to maintain the stability of the metabolic rhythm while minimizing the overall energy consumption of the system. The closed-loop optimization module is used to couple and optimize the carbon dioxide flow, oxygen flow, energy compensation flow and multimodal sensing and prediction results to ensure that carbon emissions and energy consumption in the agricultural production process are balanced in real time, thereby maintaining the net-zero energy consumption dynamic steady-state operation of the organic three-dimensional farm system.

Images