A synergistic light regulation decision method and system

Abstract

The application discloses a kind of synergic light regulation decision methods and systems, the present application relates to plant factory light environment intelligent regulation technology field, including: plant physiology monitoring unit, it is equipped with non-invasive microelectrode array and hyperspectral imager;Environment sensing unit is used to collect light intensity, spectrum, temperature, humidity and carbon dioxide concentration data.The synergic light regulation decision method and system, the fusion of multi-source heterogeneous data is realized by pulse timing coding mechanism, the problem that environmental parameters and plant physiological state are difficult to synergistically analyze in the prior art is solved;Based on the dynamic optimization architecture of double alliance Nash equilibrium, the autonomous synergic decision of spectral parameters can be completed in a short time, compared with the response speed of traditional preset light formula is improved;It can guarantee the effectiveness of decision simultaneously at virtual model and biological entity level, reduce light inhibition misjudgment rate, and simultaneously make plant light energy utilization rate steadily improve.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent regulation of plant factory light environment, in particular to a synergistic light regulation decision-making method and system. BACKGROUND

[0002] In the field of plant light regulation, the existing technology generally adopts preset light formula or simple feedback control based on a single environmental parameter. These methods can provide basic light management, but their core defect is that they cannot efficiently and accurately respond to the highly dynamic and mutually coupled complex changes in the plant growth process. Plant physiological states such as photosynthetic rate, morphological development, and metabolic activity fluctuate at all times and are simultaneously influenced by multiple environmental factors such as light intensity, spectrum, temperature, humidity, and carbon dioxide concentration. The preset static light formula lacks adaptability and cannot match the real needs of plants at a specific growth stage or when encountering environmental disturbances. The control logic that relies on single sensor data ignores the synergistic effects of multiple factors, which can lead to regulation conflicts or resource waste. More importantly, existing systems lack an intelligent decision-making core that can integrate multi-source heterogeneous data in real time, quickly assess plant status, and dynamically optimize the synergistic effects of multiple light source parameters. This results in system response lag, extensive regulation, and the inability to continuously optimize light resource utilization efficiency and plant growth goals in dynamic changes. SUMMARY

[0003] To achieve the above purpose, the present application is implemented by the following technical scheme: a synergistic light regulation decision-making system, comprising:

[0004] A plant physiology monitoring unit is provided with a non-invasive microelectrode array and a hyperspectral imager;

[0005] An environmental sensing unit is used to collect light intensity, spectrum, temperature, humidity, and carbon dioxide concentration data;

[0006] A synergistic decision-making processor is connected to the input end of the plant physiology monitoring unit and the environmental sensing unit;

[0007] A multi-band light source array is controlled by the output end of the synergistic decision-making processor;

[0008] The plant physiology monitoring unit captures leaf intercellular potential fluctuation frequency, vascular ion flow rate, and leaf fluorescence peak shift.

[0009] After the system is started, the plant physiology monitoring unit captures the leaf intercellular potential fluctuation frequency and vascular ion flow rate through a non-invasive microelectrode array, and synchronously extracts the leaf surface fluorescence peak shift amount from a hyperspectral imager. The environmental sensing unit collects light intensity, environmental spectral distribution, temperature, humidity, and carbon dioxide concentration data in parallel. All raw data are input into the cooperative decision processor, which performs intrinsic fusion by a built-in pulse timing encoder: converts the electrophysiological signals into pulse density features, maps the leaf surface fluorescence data into pulse waveform envelopes, and generates constraint pulse sequences from environmental parameters, forming a unified time-amplitude pulse stream. The pulse stream is input into the demand quantification module and the constraint perception module, respectively, the former analyzes the light demand intensity vector of each waveband, and the latter outputs the temperature-spectral coupling coefficient matrix.

[0010] Preferably, the cooperative decision processor comprises a pulse timing encoder connected to the plant physiology monitoring unit and the environmental sensing unit at the input end;

[0011] The pulse timing encoder converts the intercellular potential fluctuation frequency, ion flow rate, leaf surface fluorescence peak shift amount, and environmental data into a unified time-amplitude pulse sequence.

[0012] Preferably, the cooperative decision processor is also provided with a demand quantification module and a constraint perception module;

[0013] The demand quantification module analyzes the pulse sequence and outputs the light demand intensity vector of each waveband;

[0014] The constraint perception module generates a temperature-spectral coupling coefficient matrix.

[0015] Preferably, the cooperative decision processor comprises a cooperative decision engine, which takes the light demand intensity vector and the coupling coefficient matrix as input, and calculates the light source parameter combination including light quality ratio, intensity, and duty cycle through an asynchronous gradient tracking algorithm.

[0016] Preferably, the cooperative decision engine defines the light source parameter combination as a strategy space, constructs a payoff function with the plant electrophysiological signal smoothness and the environmental energy consumption weighted value, and solves the Pareto optimal solution through the Nash equilibrium principle.

[0017] Preferably, the cooperative light regulation decision system further comprises a virtual verification unit connected to the cooperative decision processor at the input end; the virtual verification unit is built-in with a metabolic flow topology model for deducing carbon and nitrogen assimilation pathways; when light inhibition risk or energy deficit is detected, a rollback instruction is sent to the cooperative decision processor.

[0018] Preferably, the biofeedback unit collects the leaf surface fluorescence kinetics curve after irradiation by the multi-band light source in real time; compares the curve with the deviation value of the pre-stored standard template; and triggers the cooperative decision processor to re-optimize when the deviation value exceeds the threshold value.

[0019] Preferably, the cooperative decision processor outputs the light source control instruction within a period shorter than the plant physiological response time window after receiving the complete input data.

[0020] The cooperative decision engine takes the light demand vector and the coupling matrix as input and performs dynamic optimization through the Nash equilibrium principle. The red light ratio, blue light intensity, green light spectrum width, and far-red light duty cycle are defined as a four-dimensional strategy space, wherein the red light and the far-red light automatically form a growth promotion alliance, and the blue light and the green light form an environmental response alliance.

[0021] The benefit function is constructed based on the plant physiological steady-state coefficient and the system energy consumption efficiency, and the energy consumption weight is automatically increased when the environmental temperature exceeds the critical value. During the optimization process, the game state between the alliances is monitored in real time: if the growth promotion alliance demand value continuously exceeds the constraint limit, a non-cooperative game mode is started; and when light saturation is detected, a Pareto boundary search is immediately activated. The optimization results are output to the virtual verification unit and the light source execution unit.

[0022] The virtual verification unit deduces the physiological response through the metabolic flow topology model, including: under high temperature conditions, the plastoquinone reduced state concentration of photosystem II is verified, and if it is continuously detected to be over standard, it is determined that there is a risk of photoinhibition; and under weak light environment, the carbon flux balance of the Calvin cycle is focused, and when the sucrose synthesis rate is found to be lagging, an energy deficit alarm is triggered. The biofeedback unit synchronously collects the actual leaf surface fluorescence kinetics curve, and compares it with the pre-stored healthy template for waveform similarity, including: under normal conditions, the shape characteristics are strictly matched, and in winter under weak light or high humidity environment, the deviation tolerance is automatically relaxed; and when a specific waveband distortion is detected, a device fault diagnosis protocol is started. The double verification results are fed back to the decision engine in real time, including: the parameter rollback is triggered when the metabolic flow deduction is abnormal, and the re-optimization is started when the fluorescence curve deviates beyond the limit.

[0023] After receiving the final instruction, the light source execution unit dynamically adjusts the light quality ratio, intensity, and duty cycle of the multi-band light source. Under high temperature conditions, the proportion of blue light output is automatically inhibited, and when the photosynthetic efficiency is insufficient, the intensity of red light is increased and the cycle is prolonged; under sudden natural light interference, the electrical physiological signal is preferentially maintained stable.

[0024] After each regulation, the plant physiological data is re-collected, and if the intercellular potential fluctuation does not converge or the fluorescence peak deviation is not improved, the whole process is restarted for optimization cycle. The system enhances the green light weight in the plum rain season under high humidity environment to improve the leaf transmittance, and injects ultraviolet pulse to induce resistance under pest stress, so as to ensure that the regulation strategy always has biological effectiveness and energy consumption economy.

[0025] A synergistic light regulation decision-making method, comprising the following steps:

[0026] S1: Obtain plant electrophysiological signals through a microelectrode array and leaf fluorescence data through a hyperspectral imager; simultaneously collect environmental parameters;

[0027] S2: Encode plant physiological data and environmental data into pulse sequences;

[0028] S3: Generate light demand intensity vectors and environmental coupling coefficient matrices according to the pulse sequences;

[0029] S4: Optimize light source parameter combinations through Nash equilibrium optimization;

[0030] S5: Execute light regulation after double confirmation of virtual verification and biological feedback.

[0031] Preferably, the virtual verification simulates carbon and nitrogen assimilation processes through a metabolic flow topology model; and the biological feedback evaluates the regulation effect through a leaf fluorescence kinetics curve deviation degree.

[0032] The present application provides a synergistic light regulation decision-making method and system, which has the following beneficial effects:

[0033] The synergistic light regulation decision-making method and system realize the fusion of multi-source heterogeneous data through a pulse timing coding mechanism, solve the problem that environmental parameters and plant physiological states are difficult to be synergistically analyzed in the prior art, and can complete autonomous synergistic decision-making of spectral parameters in a short time based on a dynamic optimization architecture of double alliance Nash equilibrium, thereby improving the response speed compared with traditional preset light formula, and reducing light inhibition misjudgment rate while stably improving plant light energy utilization rate through a double verification mechanism of metabolic flow deduction and fluorescence feedback.

[0034] The synergistic light regulation decision-making method and system enhance system robustness in complex agricultural scenes, avoid light damage through a blue light intelligent inhibition strategy under high-temperature working conditions, maintain photosynthetic efficiency through a red light compensation mechanism in weak light environments, realize seamless switching of light environments through dynamic response in the event of sudden environmental interference, and reduce the occurrence rate of crop physiological stress; and for extreme conditions such as high-humidity plum rain season and winter low-temperature weak light, innovative green light transmission enhancement and far-red light periodic regulation technology are used to increase the yield of leafy crops and shorten the color-changing period of fruit crops. BRIEF DESCRIPTION OF DRAWINGS

[0035] Fig. 1 It is a schematic diagram of the overall framework of the present application;

[0036] Fig. 2 It is a schematic diagram of the framework of the synergistic decision-making processor in the present application;

[0037] Fig. 3 This is the timing diagram of the control logic of the present invention. Detailed Implementation

[0038] 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.

[0039] Please see Figs. 1 to 3 This invention provides a technical solution: a collaborative light modulation decision system, comprising:

[0040] The plant physiological monitoring unit captures the frequency of intercellular potential fluctuations and vascular bundle ion flow rates in real time using a non-invasive microelectrode array, while extracting the leaf fluorescence peak shift using a hyperspectral imager; the environmental sensing unit simultaneously collects data on current light intensity, environmental spectral distribution, temperature, humidity, and carbon dioxide concentration.

[0041] The collaborative decision processor receives raw data from the plant physiological monitoring unit and the environmental sensing unit at its input terminals, and generates multi-band light source control commands after internal processing. These commands are then output to the multi-band light source array to drive it to adjust the light quality ratio, intensity, and duty cycle of the red, blue, green, and far-red LEDs.

[0042] When plants are under high-temperature stress, the collaborative decision processor automatically reduces the proportion of blue light output to avoid the risk of photoinhibition. When the leaf fluorescence peak shift indicates insufficient light energy utilization, it increases red light intensity and extends the photoperiod to enhance energy capture. In the event of sudden environmental disturbances, such as cloud cover causing abrupt changes in natural light, the system prioritizes maintaining the stability of electrophysiological signals to maintain plant homeostasis and dynamically compensates for artificial light source parameters.

[0043] The entire implementation process forms a closed-loop control of "data acquisition - decision-making and computation - light source execution", ensuring that multi-source data streams are connected to the hardware modules in real time.

[0044] The collaborative decision processor includes a pulse timing encoder, whose input is connected to the plant physiological monitoring unit and the environmental sensing unit. The pulse timing encoder converts the intercellular potential fluctuation frequency, ion current rate, leaf fluorescence peak offset, and environmental data into a unified time-amplitude pulse sequence.

[0045] It should be further explained that, in the specific implementation process, the pulse timing encoder built into the collaborative decision processor receives in real time data transmitted from the plant physiological monitoring unit, including leaf intercellular potential fluctuation frequency, vascular bundle ion flow rate, leaf fluorescence peak offset, and data on light intensity, spectral distribution, temperature, humidity, and carbon dioxide concentration collected by the environmental sensing unit. The encoder first samples the electrophysiological signals. When it detects a change in potential fluctuation frequency exceeding 10% within 0.5 seconds, it automatically increases the encoding priority of that data stream. Simultaneously, it maps the leaf fluorescence data captured by the hyperspectral imager into pulse waveforms, with the peak width negatively correlated with the fluorescence peak offset. Environmental parameters are then converted into constraint pulse envelopes. For example, when the temperature exceeds 30℃, a high-amplitude pulse cluster is generated; when the carbon dioxide concentration is below 400ppm, the pulse duration is extended. All heterogeneous data are unified into a time-amplitude pulse sequence through a biomimetic neural transmission mechanism, where the potential fluctuation frequency corresponds to the pulse density, the ion flow rate determines the pulse amplitude slope, and the change in environmental temperature controls the pulse envelope decay rate. In situations where light intensity drops by more than 50% due to overcast or rainy weather, the encoder automatically compresses the pulse generation cycle to 1 / 5 of the normal state to ensure that the decision response speed is not affected by sudden environmental changes.

[0046] The collaborative decision processor also includes a demand quantification module and a constraint sensing module. The demand quantification module analyzes the pulse sequence and outputs light demand intensity vectors for each band. The constraint sensing module generates a coupling coefficient matrix between temperature and spectrum. It should be further explained that, in the specific implementation process, after the pulse sequence is input into the demand quantification module, this module first identifies the pulse density distribution characteristics, including: when the intercellular potential fluctuation pulse density is higher than the historical average by 30%, the plant is determined to be under photosynthetic stress, and the output red light demand intensity vector value is increased to 1.5 times the baseline value; if the vascular bundle ion current pulse amplitude slope is lower than the threshold for 5 consecutive minutes, the nutrient compensation mechanism is activated, increasing the far-red light demand intensity by 20%. The synchronously operating constraint sensing module monitors the environmental pulse envelope characteristics. When it detects that the temperature pulse amplitude continuously exceeds the critical line and the carbon dioxide pulse duration is shortened to 60% of the normal value, it generates a high-temperature-low-carbon coupling coefficient matrix, forcibly limiting the blue light output upper limit to 40% of the maximum power. During the high humidity conditions of the rainy season, the module automatically enhances the weight of the green light demand vector to improve leaf transmittance. If the width of the fluorescence pulse peak on the leaf surface expands to more than twice the standard value, it is determined that the light energy capture efficiency is insufficient, triggering the full-spectrum intensity compensation mode. The output results of the two types of modules are compared in real time. When the light demand vector and the coupling matrix conflict in the blue light band, the limiting command of the constraint sensing module is given priority to ensure plant safety.

[0047] The collaborative decision processor includes a collaborative decision engine, which takes the light demand intensity vector and coupling coefficient matrix as inputs and calculates the light source parameter combination through an asynchronous gradient tracing algorithm. The light source parameter combination includes light quality ratio, intensity and duty cycle.

[0048] It should be further explained that, in the specific implementation process, after the collaborative decision engine receives the light demand intensity vectors of each band output by the demand quantification module and the environmental coupling coefficient matrix generated by the constraint perception module, it starts the asynchronous gradient tracking algorithm for dynamic optimization, including: first, taking the current light source parameter combination as the initial point, a four-dimensional strategy space is established in the light quality ratio dimension of red, blue, green, and far-red light. When the light demand vector indicates that the red light demand intensity exceeds the benchmark value of 150%, the red light ratio search step size is increased to 3 times the normal value to accelerate convergence; at the same time, the temperature-spectral constraint conditions in the environmental coupling coefficient matrix are monitored. If the blue light suppression coefficient in the matrix is ​​marked as active, the blue light ratio exploration range is forcibly limited to no more than 40% of the total spectrum during the iteration process.

[0049] The algorithm periodically calculates the trend of the benefit function, which is a linear superposition of the plant electrophysiological signal stability and environmental energy consumption. When the benefit improvement rate is less than 0.5% for three consecutive iterations, an early stop mechanism is triggered, and the current Pareto optimal solution is output as the light source parameter instruction. Under extreme conditions of high midday heat in summer combined with strong natural light, the engine automatically increases the environmental energy consumption weight to 0.5, prioritizing the reduction of the total power of artificial light sources to avoid energy waste. If the leaf fluorescence data simultaneously shows insufficient light energy utilization, a compensation mode is activated, including: redistributing the spectral proportion while maintaining the total power constraint, and increasing the red light duty cycle to 120% of the nighttime operation mode to compensate for the loss of photosynthetic efficiency.

[0050] The collaborative decision-making engine defines the combination of light source parameters as the strategy space, constructs a payoff function using the weighted values ​​of plant electrophysiological signal stability and environmental energy consumption, and solves for the Pareto optimal solution using the Nash equilibrium principle. It should be further explained that in the specific implementation process, the collaborative decision-making engine constructs a light source parameter optimization model based on the Nash equilibrium principle: the light quality ratio, intensity, and duty cycle of red, blue, green, and far-red light are defined as the strategy space of four participants, where the red light ratio and far-red light duty cycle form a growth promotion alliance, and the blue light intensity and green spectral breadth constitute an environmental response alliance.

[0051] The payoff function is composed of the plant physiological homeostasis coefficient and the system energy efficiency. When the environmental coupling coefficient matrix detects a temperature exceeding 32℃, the energy efficiency weight of the blue light alliance is automatically increased to 0.6 to suppress photothermal damage. During the optimization process, the game state between alliances is monitored in real time, including: if the demand vector value of the red light alliance is higher than the constraint matrix limit by 20% for 3 consecutive minutes, a non-cooperative game mode is initiated, allowing the red light ratio to exceed the constraint limit but simultaneously reducing its duty cycle weight; when the leaf fluorescence pulse shows signs of light saturation, the Pareto boundary search mechanism is forcibly activated to lock in a compromise solution that satisfies the minimum payoff of all alliances.

[0052] During the high humidity conditions of the plum rain season, the system automatically assigns additional compensation weights to the green light spectral width strategy, increasing its duty cycle to 150% of that in a dry environment, thereby alleviating photosynthetic resistance by enhancing leaf transmittance. If a stable solution is not achieved after five iterations of Nash equilibrium, a light source combination plan with similar environmental parameters from the historical best solution library is activated.

[0053] The collaborative light regulation decision-making system also includes: a virtual verification unit, whose input is connected to the collaborative decision processor; the virtual verification unit has a built-in metabolic flow topology model for simulating carbon and nitrogen assimilation pathways; when a photoinhibition risk or energy deficit is detected, it sends a rollback command to the collaborative decision processor. It should be further explained that, in the specific implementation process, after receiving the light source parameter combination output by the collaborative decision processor, the virtual verification unit starts the metabolic flow topology model for dynamic simulation, including: firstly, simulating the light energy capture process of the thylakoid membrane electron transport chain; when the red light duty cycle exceeds the historical average of 40% and the ambient temperature is higher than 28℃, automatically detecting the concentration of reduced ubiquinone in photosystem II; if this concentration exceeds the safety threshold for 30 seconds, a photoinhibition risk is determined and a level one warning is generated.

[0054] Simultaneously, the Calvin cycle carbon assimilation pathway is simulated, monitoring the balance between the ribulose-1,5-bisphosphate regeneration rate and sucrose synthesis flux. An energy deficit alarm is triggered when blue light intensity falls below 50% of the demand vector, leading to insufficient activity of the triose phosphate transporter. For high-temperature greenhouse conditions in summer, the model prioritizes photorespiration branch verification: if glycine decarboxylase flux reaches three times the baseline and serine storage is saturated, a rollback command is immediately sent to the decision processor, forcibly reducing red light intensity by 20%. In scenarios with continuous rain leading to insufficient natural light, the model additionally activates the crassamate metabolism verification channel. When malate decarboxylation rate lags behind the photoperiod phase, the far-red light irradiation time is automatically extended to 150% of the normal mode to maintain carbon skeleton turnover. All simulation results are periodically refreshed. When three consecutive simulation cycles show an upward trend in the energy deficit index, the current light source scheme is interrupted, and the model reverts to the previous stable version.

[0055] The biofeedback unit collects leaf fluorescence kinetic curves after multi-band light source irradiation in real time; compares the deviation values ​​of the curves with the pre-stored standard template; and triggers the collaborative decision processor to re-optimize when the deviation value exceeds a threshold. It should be further explained that, in the specific implementation process, the biofeedback unit captures the leaf fluorescence kinetic curves after multi-band light source irradiation in real time and dynamically compares them with the pre-stored health response template. This includes: when the fluorescence quenching rate of the curve in the 680nm band lags behind the template baseline value by 15%, it determines that the photochemical reaction efficiency is insufficient and generates a first-level optimization instruction; if the 730nm re-oxidation time of photosystem I is more than 20% earlier than the template, a light energy distribution imbalance alarm is triggered.

[0056] For greenhouses operating under low temperature and low light conditions in winter, the KL divergence deviation threshold is automatically relaxed to 1.8 times the normal value to avoid false alarms caused by insufficient natural light. When an abnormal double peak is detected in the 500-600nm band, the equipment fault diagnosis protocol is activated: if the same characteristic is shown in three consecutive samples, the system switches to a backup hyperspectral imager and reconstructs a healthy template. In the event of a sudden pest or disease attack, the unit automatically activates a stress response mode: when the chlorophyll fluorescence parameter Fv / Fm drops below 0.72 and is accompanied by an abnormally prolonged fluorescence lifetime in the blue-green band, the red light intensity is immediately increased by 30%, and ultraviolet pulses are injected to induce plant resistance. After each adjustment, resampling and verification are performed. If the KL divergence value decreases by less than 5% in two consecutive iterations, a full parameter reset command is sent to the collaborative decision processor, forcibly starting a new round of Nash equilibrium optimization cycle.

[0057] After receiving complete input data, the collaborative decision processor outputs light source control commands within a period shorter than the plant physiological response time window; the collaborative decision processor outputs light source control commands after receiving data. It should be further explained that in the specific implementation process, after receiving complete input data, the collaborative decision processor initiates response timing control: first, it completes pulse sequence generation and verification; when the electrophysiological signal sampling rate is detected to be below 1kHz, it automatically switches to the backup microelectrode array; then, it performs Nash equalization optimization calculations; if the ambient temperature exceeds 32℃, it activates the fast convergence mode, that is, it expands the iteration step size of the asynchronous gradient tracking algorithm to 2.5 times the normal value, while compressing the spectral ratio search space to a binary strategy domain dominated by red and blue light; finally, it performs virtual verification preloading, predicting the probability of light suppression risk under high-temperature conditions before starting the metabolic flow topology model; when the historical database shows that similar environmental parameters have triggered a level 3 alarm, it pre-injects a preset correction value of 20% blue light intensity attenuation. In the event of sensor data loss due to strong lightning interference, the system automatically activates a mechanism to fill in the preceding valid data: if three consecutive frames of temperature or light intensity data are lost, a replacement value is generated by linear extrapolation based on the trend of the most recent 10 seconds, and a verification flag is marked after the decision is made. In low-temperature, high-humidity scenarios on a winter morning, the response period is allowed to be extended to prioritize spectral accuracy, but redundant time is forcibly reserved for biofeedback channel initialization to ensure strict synchronization between leaf fluorescence sampling and regulation execution. A timestamp log is generated after each response. When five consecutive response delays exceed the preset response time, a hardware self-check is automatically triggered, and the system degrades to a safe operating mode.

[0058] A collaborative light modulation decision-making method includes the following steps:

[0059] S1: Acquire plant electrophysiological signals through a microelectrode array and leaf fluorescence data through a hyperspectral imager; simultaneously collect environmental parameters.

[0060] S2: Encode plant physiological data and environmental data into pulse sequences;

[0061] S3: Generate the light demand intensity vector and the environmental coupling coefficient matrix based on the pulse sequence;

[0062] S4: Calculate the combination of light source parameters through Nash equalization optimization;

[0063] S5: Light regulation is executed after dual confirmation by virtual verification and biofeedback.

[0064] It should be further explained that, in the specific implementation process, the collaborative light regulation decision method is implemented according to the following steps: the frequency of intercellular potential fluctuations and vascular bundle ion flow rate of leaves are captured in real time through a non-invasive microelectrode array, and the leaf fluorescence peak shift is obtained by using a hyperspectral imager, and time synchronization is achieved with five types of parameters: light intensity, environmental spectrum, temperature, humidity and carbon dioxide concentration.

[0065] The heterogeneous data is input into a pulse timing encoder for unified conversion, including: switching to a backup acquisition channel when the electrophysiological signal sampling rate is below 1kHz, generating a pulse waveform envelope for leaf fluorescence data according to wavelength-intensity distribution, and automatically increasing the amplitude weight of temperature pulses when the ambient temperature exceeds 28℃.

[0066] The converted pulse sequence is analyzed by the demand quantification module to obtain the red light dominance index and far-red light compensation coefficient. Combined with the spectrum-temperature coupling matrix generated by the constraint perception module, the Nash equilibrium optimization process is initiated. That is, if the red light dominance index is higher than the historical peak by 15% for two consecutive cycles, the search range of the red light strategy space is expanded to the normal value of 180%. When the blue light suppression flag in the coupling matrix is ​​activated, the upper limit of the blue light intensity exploration domain is forcibly limited to 30% of the total spectrum.

[0067] The optimized results are input into the virtual verification unit to perform metabolic flow simulation: under high temperature and high humidity conditions, photorespiration flux is verified first. When the glycine accumulation rate reaches 2.5 times the baseline value, the execution is interrupted and the system reverts to the safe spectral template. Simultaneously, the biofeedback unit compares the KL divergence value of the real-time leaf fluorescence curve with that of the healthy template. Under low light conditions in winter, the allowable deviation threshold is relaxed to 1.8 times, but a fault switching protocol is immediately initiated when an abnormal double peak is detected in the 500-600nm band. Finally, the control command drives the multi-band light source array to adjust the spectral parameters, and electrophysiological signals are re-acquired after execution to verify the effect. If the frequency of intercellular potential fluctuations does not converge to the safe range, the entire process is re-optimized.

[0068] Virtual validation simulates the carbon and nitrogen assimilation process using a metabolic flow topology model, while biofeedback assesses the regulatory effect through deviations from leaf fluorescence kinetic curves. Further explanation is needed regarding the implementation process of the synergistic light regulation decision-making method: The metabolic flow topology model dynamically extrapolates the thylakoid electron transport chain state based on the light source parameter combinations. When the ambient temperature exceeds 30°C and the red light duty cycle is higher than the historical average by 35%, the system automatically focuses on monitoring the reduced concentration of ubiquinone in system II. If this concentration exceeds the safety threshold for 15 consecutive seconds, it is immediately identified as a level-two light inhibition risk, and a spectral rollback command is generated, forcibly reducing the red light intensity to 80% of the baseline value. Simultaneously, Calvin cycle carbon flux balance validation is performed. Under conditions where the blue light intensity is lower than the demand vector by 40%, the activity level of the triose phosphate transporter is monitored. Specifically, when the sucrose synthesis rate lags behind starch accumulation by 25%, a level-three energy deficit alarm is triggered, and a far-red light compensation pulse is injected. The biofeedback channel collects the regulated leaf fluorescence kinetics curves in real time. Under low-light conditions in winter, the KL divergence deviation threshold is automatically widened to 1.8 times the standard value. However, if a bimodal distortion is detected in the 500-600nm band, a fault protocol is immediately activated: if the distortion feature is repeated in three consecutive samplings, a backup hyperspectral imager is switched on and the healthy template library is reloaded. In the event of sudden pest or disease stress, when the fluorescence parameter Fv / Fm continuously drops below 0.72 and is accompanied by an abnormal 20% increase in the fluorescence lifetime in the blue-green band, the stress response chain is activated, including increasing the red light intensity by 30% and inserting a 2-minute ultraviolet pulse cycle. After each validation, the effect is evaluated. If the electrophysiological signal stability index increases by less than 5% for two consecutive cycles, a full parameter reset request is sent to the decision-making level, triggering a new round of Nash equilibrium optimization cycle.

[0069] A collaborative light modulation decision-making method includes the following steps:

[0070] Step S1: Synchronously collect plant physiological data and environmental parameters: capture the frequency of intercellular potential fluctuations and vascular bundle ion current rates of leaves using a non-invasive microelectrode array, extract the leaf fluorescence peak shift using a hyperspectral imager, and acquire data on light intensity, environmental spectrum, temperature, humidity, and carbon dioxide concentration in parallel.

[0071] Step S2: Perform multi-source data pulse timing coding: convert electrophysiological signals into pulse density features, map leaf fluorescence data into pulse waveform envelopes, and generate constrained pulse sequences from environmental parameters to form a unified time-amplitude pulse stream.

[0072] Step S3: Analyze the pulse flow to generate decision parameters: The demand quantization module outputs the light demand intensity vector for each band, and the constraint perception module generates the temperature-spectral coupling coefficient matrix. When the temperature exceeds the critical value, the weight of the blue light suppression coefficient is automatically increased.

[0073] Step S4: Initiate Nash equilibrium collaborative optimization: Define red light ratio, blue light intensity, green spectrum width, and far-red light duty cycle as a four-dimensional strategy space, divide the growth promotion alliance and the environmental response alliance, and construct a weighted benefit function of plant physiological homeostasis and system energy consumption.

[0074] Step S5: Dynamically perform optimization calculations: Monitor the game state between alliances, activate the non-cooperative game mode when the growth promotion alliance demand value continues to exceed the limit, trigger Pareto boundary search when light saturation signs are detected, and output the light source parameter combination.

[0075] Step S6: Virtual verification of metabolic pathways: The state of the thylakoid electron transport chain is deduced through a metabolic flow topology model, the concentration of reduced ubiquinone in the focused light system II is monitored under high temperature conditions, and the carbon flux balance of the Calvin cycle is verified in a low light environment.

[0076] Step S7: Real-time verification of biofeedback: Collect the leaf fluorescence dynamics curve after light irradiation, compare the waveform similarity with the pre-stored healthy template, strictly match the features under normal working conditions, and automatically relax the deviation tolerance in winter when the light is weak.

[0077] Step S8: Perform dynamic light source control: Adjust the parameters of the multi-band light source according to the final instruction, suppress the blue light output ratio in high temperature scenarios, increase the red light intensity and extend the period when the photosynthetic efficiency is insufficient, and prioritize maintaining the stability of electrophysiological signals under sudden interference.

[0078] Step S9: Validation result closed-loop processing: When the metabolic flow projection is abnormal, the parameters are rolled back to the safety template; if the fluorescence curve deviates from the limit, the optimization cycle is restarted; if the equipment fault characteristics continue to appear, the backup acquisition device is switched.

[0079] Step S10: Effect evaluation and re-optimization: Re-collect intercellular potential fluctuation frequency and leaf fluorescence data. If the physiological indicators do not converge to the safe range or the energy consumption efficiency continues to deteriorate, trigger the full-process decision reset and inject the historical best plan.

[0080] By using a pulse timing coding mechanism to fuse multi-source heterogeneous data, the problem of difficulty in coordinating the analysis of environmental parameters and plant physiological states in existing technologies is solved. Based on the dynamic optimization architecture of dual-alliance Nash equilibrium, autonomous and coordinated decision-making of spectral parameters can be completed in a short time, which improves the response speed compared with traditional preset light formulas. Through the dual verification mechanism of metabolic flow inference and fluorescence feedback, the effectiveness of decision-making is ensured simultaneously at the virtual model and biological entity levels for the first time, reducing the false judgment rate of light suppression and steadily improving the plant light energy utilization rate.

[0081] The system enhances robustness in complex agricultural scenarios. Under high-temperature conditions, it avoids light damage through a blue light intelligent suppression strategy and maintains photosynthetic efficiency through a red light compensation mechanism in low-light environments. In the event of sudden environmental disturbances, it achieves seamless switching of light environment based on dynamic response, reducing the incidence of crop physiological stress. For extreme conditions such as high humidity during the plum rain season and low temperature and low light in winter, it innovates green light transmission enhancement and far-red light period regulation technology, which increases the yield of leafy vegetables and shortens the color-changing period of fruit crops.

[0082] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0083] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A collaborative light control decision system, characterized in that, include: The plant physiological monitoring unit is equipped with a non-invasive microelectrode array and a hyperspectral imager; An environmental sensing unit is used to collect data on light intensity, spectrum, temperature, humidity, and carbon dioxide concentration. The collaborative decision processor has its input terminals connected to the plant physiological monitoring unit and the environmental sensing unit. A multi-band light source array is controlled by the output of a collaborative decision processor; The plant physiological monitoring unit captures the frequency of intercellular potential fluctuations in leaves, the vascular bundle ion current rate, and the offset of leaf fluorescence peaks. The collaborative decision processor includes a pulse timing encoder, the input of which is connected to the plant physiological monitoring unit and the environmental sensing unit; the pulse timing encoder converts the intercellular potential fluctuation frequency, ion current rate, leaf fluorescence peak offset and environmental data into a unified time-amplitude pulse sequence. The collaborative decision processor also includes a demand quantization module and a constraint perception module. The demand quantization module parses the pulse sequence and outputs the light demand intensity vector for each band. The constraint perception module generates a coupling coefficient matrix between temperature and spectrum. The collaborative light regulation decision system further includes: a virtual verification unit, the input of which is connected to the collaborative decision processor; the virtual verification unit has a built-in metabolic flow topology model for deduce carbon and nitrogen assimilation pathways; when a light suppression risk or energy deficit is detected, a rollback command is sent to the collaborative decision processor. The collaborative light regulation decision system further includes a biofeedback unit, which collects the leaf fluorescence dynamics curves after multi-band light source irradiation in real time, compares the deviation values ​​of the curves with the pre-stored standard templates, and triggers the collaborative decision processor to re-optimize when the deviation value exceeds a threshold.

2. The collaborative optical modulation decision system according to claim 1, characterized in that: The collaborative decision processor includes a collaborative decision engine, which takes a light demand intensity vector and a coupling coefficient matrix as inputs. The collaborative decision engine calculates the light source parameter combination through an asynchronous gradient tracing algorithm. The light source parameter combination includes light quality ratio, intensity, and duty cycle.

3. The collaborative optical modulation decision system according to claim 2, characterized in that: The collaborative decision engine defines the combination of light source parameters as the strategy space, constructs a benefit function with the weighted value of plant electrophysiological signal stability and environmental energy consumption, and solves the Pareto optimal solution through the Nash equilibrium principle.

4. The collaborative optical modulation decision system according to claim 2, characterized in that: After receiving complete input data, the collaborative decision processor outputs light source control commands within a period shorter than the plant physiological response time window.

5. A collaborative light modulation decision-making method, characterized in that, Includes the following steps: S1: Acquire plant electrophysiological signals through a microelectrode array and leaf fluorescence data through a hyperspectral imager; simultaneously collect environmental parameters. S2: Encode plant physiological data and environmental data into pulse sequences; S3: Generate the light demand intensity vector and the environmental coupling coefficient matrix based on the pulse sequence; S4: Calculate the combination of light source parameters through Nash equalization optimization; S5: Light regulation is executed after dual confirmation by virtual verification and biofeedback; S6: The state of the thylakoid electron transport chain was deduced by metabolic flow topology model, the concentration of reduced ubiquinone in the focused light system II was monitored under high temperature conditions, and the carbon flux balance of the Calvin cycle was verified in a low light environment. S7: Collect the leaf fluorescence dynamics curve after light source illumination, compare the waveform similarity with the pre-stored healthy template, strictly match the characteristics under normal working conditions, and automatically relax the deviation tolerance in winter when the light is weak. S8: Adjust the parameters of the multi-band light source according to the final instruction, suppress the blue light output ratio in high-temperature scenarios, increase the red light intensity and extend the period when the photosynthetic efficiency is insufficient, and prioritize maintaining the stability of electrophysiological signals under sudden interference. S9: When metabolic flow projection is abnormal, parameters are rolled back to the safety template; if the fluorescence curve deviates from the limit, the optimization cycle is restarted; if equipment fault characteristics continue to appear, the backup acquisition device is switched. S10: Reacquire intercellular potential fluctuation frequency and leaf fluorescence data. If physiological indicators do not converge to a safe range or energy efficiency continues to deteriorate, trigger a full-process decision reset and inject the historical best contingency plan.

6. The collaborative optical modulation decision-making method according to claim 5, characterized in that: The virtual verification simulates the carbon and nitrogen assimilation process using a metabolic flow topology model; the biofeedback assesses the regulatory effect using the deviation of the leaf fluorescence kinetic curve.

Images