Multi-factor coupling ganoderma environmental digital twin regulation method for high yield demand

Abstract

The application discloses a multi-factor coupling ganoderma environmental digital twin regulation method for high-yield demand, and particularly relates to the intelligent cultivation technology field of edible fungi, and is used for solving the problems of device action oscillation and hidden physiological stress caused by the physiological response hysteresis of the existing environmental regulation system; by constructing a ganoderma growth digital twin, real-time generation of carbon dioxide concentration and light intensity prediction values is realized, combined with mycelium respiration entropy matching degree analysis and active oxygen accumulation curve activated oxidation stress markers; when the matching degree exceeds the threshold value and oxidation stress exists, a metabolic overload signal is generated, and it is judged whether the carbon dioxide prediction value is in the physiological lag interval; delay compensation and metabolic overload inhibition coefficient adjustment are performed on the carbon dioxide prediction value in the lag interval; finally, the compensated carbon dioxide value and the light prediction value are input into the environmental factor cooperative rule library to generate a ventilation opening degree and light supplement power instruction to drive the execution equipment, thereby ensuring the stability of the fruit body morphological development and the synthesis efficiency of active ingredients.

Description

Technical Field

[0001] This invention relates to the field of intelligent cultivation technology for edible fungi, and more specifically, to a multi-factor coupled digital twin regulation method for the environment of Ganoderma lucidum aimed at high yield. Background Technology

[0002] In factory-scale Ganoderma lucidum cultivation, environmental control systems monitor multiple parameters such as temperature, humidity, carbon dioxide concentration, and light in real time, and generate control commands to drive equipment (such as fans and humidifiers) based on preset growth models. Existing technologies generally adopt closed-loop control strategies based on sensor feedback (such as PID algorithms). Their design logic relies on the instantaneous mapping relationship between environmental parameters and equipment responses. Basic applications have been achieved in typical agricultural greenhouses. However, in the cultivation of medicinal fungi such as Ganoderma lucidum that are highly sensitive to the coupling of multiple factors, the accuracy of control and the stability of yield still face significant challenges.

[0003] Existing environmental control systems have shortcomings in addressing the growth characteristics of Ganoderma lucidum: there is a contradiction between the real-time nature of control commands and the lag in the physiological response of Ganoderma lucidum. Due to the inherent delay in the physiological response of Ganoderma lucidum to key environmental factors such as carbon dioxide (e.g., stomatal regulation mechanism), and the fact that the control system frequently adjusts the equipment based solely on real-time sensor data, short-term control targets (e.g., achieving the carbon dioxide concentration target) become disconnected from long-term biological effects (e.g., cap development). This contradiction causes periodic oscillations in equipment operation, resulting in the accumulation of environmental parameter overshoot, which in turn leads to latent physiological stress, ultimately manifesting as abnormal fruiting body morphology and uncontrollable yield fluctuations. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-factor coupled digital twin regulation method for the environment of Ganoderma lucidum to meet the demand for high yield, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A multi-factor coupled digital twin regulation method for the environment of Ganoderma lucidum aimed at high yield includes:

[0007] S1. Real-time collection of carbon dioxide concentration and light intensity in the Ganoderma lucidum cultivation environment;

[0008] S2. Input carbon dioxide concentration and light intensity into the digital twin of Ganoderma lucidum growth to generate real-time prediction values;

[0009] S3. In the digital twin of Ganoderma lucidum growth, the matching degree between the rate of change of carbon dioxide concentration and the mycelial respiratory entropy is generated, and the accumulation curve of intracellular reactive oxygen species is simulated based on the rate of change of carbon dioxide concentration and light intensity. When the rate of increase of the curve exceeds the rate of increase of the matching degree, the oxidative stress marker is activated.

[0010] S4. When the matching degree exceeds the set threshold and there is an oxidative stress sign, a metabolic overload signal is generated. At the same time, it is determined whether the real-time predicted value of carbon dioxide concentration is in the lag range of Ganoderma lucidum physiological response.

[0011] S5. When the Ganoderma lucidum physiological response lag range is in, the real-time predicted value of carbon dioxide concentration is subjected to delay compensation processing. If there is a metabolic overload signal, an inhibition coefficient is applied to generate a compensated carbon dioxide concentration value.

[0012] S6. Perform a synergistic impact analysis between the compensated carbon dioxide concentration value and the real-time predicted light intensity value, generate environmental control instructions, and drive the execution equipment to execute them.

[0013] Furthermore, the carbon dioxide concentration and light intensity in the Ganoderma lucidum cultivation environment were collected in real time, including:

[0014] Carbon dioxide concentration data is acquired using a carbon dioxide concentration sensor at a first sampling frequency;

[0015] Light intensity data is acquired using a light intensity sensor at a second sampling frequency;

[0016] Add timestamps to carbon dioxide concentration data and light intensity data;

[0017] Timestamped carbon dioxide concentration data and light intensity data are stored in a distributed cache queue.

[0018] Furthermore, carbon dioxide concentration and light intensity are input into the digital twin of Ganoderma lucidum growth to generate real-time predicted values, including:

[0019] Read timestamped carbon dioxide concentration data and light intensity data from a distributed cache queue;

[0020] Input the timestamped carbon dioxide concentration data into the carbon dioxide concentration prediction unit of the Ganoderma lucidum growth digital twin;

[0021] Input the timestamped light intensity data into the light intensity prediction unit of the Ganoderma lucidum growth digital twin;

[0022] Calculate the rate of change in carbon dioxide concentration using a digital twin of Ganoderma lucidum growth;

[0023] Real-time predicted values ​​of carbon dioxide concentration and light intensity are generated using a digital twin of Ganoderma lucidum growth.

[0024] Furthermore, the digital twin of Ganoderma lucidum growth is established through the following methods:

[0025] Collect time-series data on carbon dioxide concentration and light intensity continuously recorded throughout the historical cultivation cycle;

[0026] Identify recurring diurnal concentration fluctuations in carbon dioxide concentration time-series data;

[0027] Extract the characteristics of abrupt changes in light intensity caused by weather changes from time-series data;

[0028] Establish a correlation rule between the characteristics of carbon dioxide concentration fluctuations and the characteristics of sudden changes in light intensity;

[0029] The response mechanism of the carbon dioxide concentration prediction unit is configured based on association rules;

[0030] The response mechanism of the illumination intensity prediction unit is configured based on association rules;

[0031] A digital twin of Ganoderma lucidum growth is formed by combining a carbon dioxide concentration prediction unit and a light intensity prediction unit.

[0032] Furthermore, a matching degree between the rate of change in carbon dioxide concentration and mycelial respiratory entropy was generated in a digital twin of Ganoderma lucidum growth. Based on the rate of change in carbon dioxide concentration and light intensity, an intracellular reactive oxygen species (ROS) accumulation curve was simulated. When the rate of increase of the curve exceeded the rate of increase of the matching degree, oxidative stress markers were activated, including:

[0033] Obtain the rate of change of carbon dioxide concentration;

[0034] The mycelial respiration entropy value is determined based on the correspondence between the rate of change of carbon dioxide concentration and the preset mycelial oxygen consumption rate.

[0035] The deviation between the current mycelial respiratory entropy value and the baseline respiratory entropy value is used as the degree of matching.

[0036] Simultaneously monitor the coordinated changing trend of carbon dioxide concentration change rate and real-time predicted light intensity;

[0037] Based on the synergistic change trend, query the corresponding intracellular reactive oxygen species accumulation level in the reactive oxygen species accumulation mapping table;

[0038] Generate a cumulative curve reflecting the change in intracellular reactive oxygen species accumulation levels over time;

[0039] When the increase in the cumulative curve exceeds the increase in the matching degree, the oxidative stress flag is activated.

[0040] Furthermore, the mycelial respiration entropy value is determined based on the correspondence between the rate of change in carbon dioxide concentration and the preset mycelial oxygen consumption rate, including:

[0041] Pre-stored reference table of mycelial oxygen consumption rate for different carbon dioxide concentration change rate ranges;

[0042] Detect the range to which the current rate of change of carbon dioxide concentration belongs, and extract the corresponding baseline value of mycelial oxygen consumption rate from the reference table of mycelial oxygen consumption rate baseline values;

[0043] The baseline value of mycelial oxygen consumption rate is output as the mycelial respiration entropy value.

[0044] Furthermore, when the matching degree exceeds a set threshold and an oxidative stress marker is present, a metabolic overload signal is generated. Simultaneously, it is determined whether the real-time predicted carbon dioxide concentration falls within the lag range of Ganoderma lucidum's physiological response, including:

[0045] Obtain matching degree and oxidative stress markers;

[0046] When the matching degree exceeds the preset matching degree threshold and the oxidative stress flag is in an activated state, a metabolic overload signal is generated;

[0047] Simultaneously read real-time predicted values ​​of carbon dioxide concentration;

[0048] Query the carbon dioxide concentration adaptation range corresponding to the current growth stage in the preset Ganoderma lucidum physiological response feature database;

[0049] Determine whether the real-time predicted value of carbon dioxide concentration is within the hysteresis boundary range of the carbon dioxide concentration adaptation range;

[0050] When the real-time predicted value of carbon dioxide concentration is within the hysteresis boundary range, it is marked as being in the hysteresis range of Ganoderma lucidum physiological response.

[0051] Furthermore, when the physiological response of Ganoderma lucidum is in a lag zone, a delay compensation process is performed on the real-time predicted value of carbon dioxide concentration. If a metabolic overload signal exists, an inhibition coefficient is applied to generate a compensated carbon dioxide concentration value, including:

[0052] Confirm the marking status of the lag region in the physiological response of Ganoderma lucidum;

[0053] When the marked state is in the lag range of Ganoderma lucidum physiological response, the real-time predicted value of carbon dioxide concentration is subjected to time shift compensation.

[0054] Detect the presence of metabolic overload signals;

[0055] When a metabolic overload signal is present, the corresponding carbon dioxide concentration inhibition coefficient is read from the cultivation database;

[0056] Apply the carbon dioxide concentration suppression coefficient to the carbon dioxide concentration value after time-shift compensation.

[0057] Generate the compensated carbon dioxide concentration value after applying the carbon dioxide concentration suppression coefficient.

[0058] Furthermore, a synergistic impact analysis is performed between the compensated carbon dioxide concentration value and the real-time predicted light intensity value to generate environmental control commands and drive the execution equipment, including:

[0059] Obtain the compensated carbon dioxide concentration value and the real-time predicted value of light intensity;

[0060] Search the environmental factor collaborative rule base for the carbon dioxide regulation intensity level corresponding to the compensated carbon dioxide concentration value;

[0061] Query the light intensity control level corresponding to the real-time predicted light intensity value in the environmental factor collaborative rule base;

[0062] The coordinated control mode is determined based on the combination relationship between the carbon dioxide control intensity level and the light control intensity level.

[0063] An environmental control instruction set, including ventilation equipment opening instructions and supplementary lighting equipment power instructions, is generated based on the coordinated control mode.

[0064] The environmental control instruction set is sent to the environmental control execution equipment for operation.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] 1. By establishing a digital twin of Ganoderma lucidum growth and physiological response lag compensation, the contradiction between the real-time nature of environmental regulation and the lag in physiological response is effectively resolved. Specifically, the matching degree between the rate of change of carbon dioxide concentration and mycelial respiration entropy is dynamically generated in the digital twin, and oxidative stress markers are activated based on the reactive oxygen species accumulation curve. Combined with the generation of metabolic overload signals and the judgment of lag intervals, advanced perception of the physiological state of Ganoderma lucidum is achieved. By performing delay compensation and inhibition coefficient adjustment on the real-time predicted value of carbon dioxide concentration, the equipment control commands are precisely aligned with the actual metabolic response window of Ganoderma lucidum, fundamentally avoiding frequent equipment actions and parameter oscillations caused by physiological lag. This predictive regulation mode based on physiological response characteristics significantly reduces the risk of latent stress to mycelium caused by environmental overshoot.

[0067] 2. By coupling the compensated carbon dioxide concentration value with the predicted light intensity value through an environmental factor synergistic rule base, the limitations of traditional single-factor closed-loop control are overcome. Synergistic control instructions are generated by using matching rules between carbon dioxide regulation intensity levels and light regulation intensity levels, enabling ventilation and supplemental lighting equipment to work in dynamic coordination. This fully adapts to the nonlinear interactions between multiple environmental factors during Ganoderma lucidum growth. For example, when high carbon dioxide concentration and strong light coexist, an inhibition mode is automatically triggered, effectively preventing energy loss caused by increased photorespiration. This multi-factor synergistic control mode maintains stable environmental parameters while precisely matching the metabolic needs of different growth stages, creating a continuously optimized growth environment for fruiting body morphology development, thereby ensuring the effective accumulation of biomass and the stable synthesis of active ingredients under high-yield targets. Attached Figure Description

[0068] Figure 1This is a flowchart of the multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment oriented towards high-yield requirements of the present invention;

[0069] Figure 2 This is a flowchart illustrating the activation mechanism of intracellular oxidative stress markers in Ganoderma lucidum according to the present invention. Detailed Implementation

[0070] 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.

[0071] Example: Figure 1 This invention presents a multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment, aimed at high-yield production, comprising:

[0072] S1. Real-time collection of carbon dioxide concentration and light intensity in the Ganoderma lucidum cultivation environment;

[0073] S2. Input carbon dioxide concentration and light intensity into the digital twin of Ganoderma lucidum growth to generate real-time prediction values;

[0074] S3. In the digital twin of Ganoderma lucidum growth, the matching degree between the rate of change of carbon dioxide concentration and the mycelial respiratory entropy is generated, and the accumulation curve of intracellular reactive oxygen species is simulated based on the rate of change of carbon dioxide concentration and light intensity. When the rate of increase of the curve exceeds the rate of increase of the matching degree, the oxidative stress marker is activated.

[0075] S4. When the matching degree exceeds the set threshold and there is an oxidative stress sign, a metabolic overload signal is generated. At the same time, it is determined whether the real-time predicted value of carbon dioxide concentration is in the lag range of Ganoderma lucidum physiological response.

[0076] S5. When the Ganoderma lucidum physiological response lag range is in, the real-time predicted value of carbon dioxide concentration is subjected to delay compensation processing. If there is a metabolic overload signal, an inhibition coefficient is applied to generate a compensated carbon dioxide concentration value.

[0077] S6. Perform a synergistic impact analysis between the compensated carbon dioxide concentration value and the real-time predicted light intensity value, generate environmental control instructions, and drive the execution equipment to execute them.

[0078] S1. Real-time collection of carbon dioxide concentration and light intensity in the Ganoderma lucidum cultivation environment, implemented as follows:

[0079] Carbon dioxide concentration data in the cultivation environment is acquired using a carbon dioxide concentration sensor at a preset first sampling frequency. This first sampling frequency is set to once every 30 seconds based on the respiration cycle of Ganoderma lucidum mycelium; for example, once every 20 seconds during the active mycelial period and once every 60 seconds during the dormant period. The carbon dioxide concentration sensor's measurement range covers 0 to 5000 ppm. The ambient temperature value is recorded simultaneously with each acquisition for subsequent data compensation calculations. When the ambient temperature exceeds 30 degrees Celsius, the temperature compensation mechanism is automatically activated.

[0080] Light intensity data is acquired using a light intensity sensor at a second sampling frequency, set to once every 10 seconds to adapt to the rapid changes in natural light, automatically increasing to once every 5 seconds during cloudy or rainy weather. The spectral response range of the light intensity sensor is limited to between 400 nm and 700 nm, consistent with the optimal absorption band of the Ganoderma lucidum photosensitive pigment, and an optical diffuser is incorporated to eliminate measurement deviations caused by the angle of light incidence.

[0081] Each acquired carbon dioxide concentration and light intensity data point is timestamped to millisecond precision. A high-precision clock module is used to generate the timestamps, ensuring that the time synchronization error between different sensor data points is controlled within 50 milliseconds. When electromagnetic interference is present in the acquisition environment, the system automatically switches to a backup clock source and records the clock offset. During timestamp marking, if any abnormal sensor data is detected (e.g., negative carbon dioxide concentration or light intensity exceeding 200,000 lux), an anomaly marker is added to that record.

[0082] Timestamped carbon dioxide concentration data and light intensity data are stored in a distributed cache queue. The storage process performs the following operations: First, the data validity is verified; if the carbon dioxide concentration data exceeds the range of 0 to 5000 ppm, the collection record is automatically discarded; if the light intensity data is below 0 lux, a sensor calibration procedure is triggered; valid data is written to the cache partition nodes in chronological order, with each partition node storing data blocks for a continuous 60-minute time period and marking the start and end timestamps. When the data backlog in the cache queue exceeds a set threshold (e.g., 10,000 records), a data compression storage mechanism is initiated, and a backup storage channel is activated.

[0083] Data in the cache queue is retained for a default period of 7 days, after which it is automatically archived to the long-term storage system. The queue status is monitored in real time during data storage. When the data write rate consistently exceeds the system's processing capacity (e.g., exceeding 5000 entries per second for 3 consecutive seconds), a traffic alarm signal is sent to the monitoring system, and the sampling frequency is dynamically adjusted. After each data processing step, processed data entries are cleared and the index sequence is rebuilt to ensure that subsequent processing units obtain the complete, continuous time dataset.

[0084] S2. Input carbon dioxide concentration and light intensity into the digital twin of Ganoderma lucidum growth to generate real-time predicted values, and implement the following:

[0085] The system reads timestamped carbon dioxide concentration and light intensity data from a distributed cache queue in chronological order, with each read operation performed within a 60-minute time window, corresponding to the photosynthetic cycle of Ganoderma lucidum. When a timestamp interval exceeds a preset collection period, data completion is performed: a linear interpolation algorithm is used to generate missing data points, based on the numerical trend of two consecutive valid data points. After reading, the queue index status is updated to ensure that subsequent processing obtains the complete time series.

[0086] Timestamped carbon dioxide concentration data is input into the carbon dioxide concentration prediction unit for processing, which consists of three stages. First, data smoothing is performed using a moving average method with dynamically adjusted window width: the window width automatically adjusts according to the degree of data fluctuation; a 10-point window is used when the standard deviation of 10 consecutive data points is below 5 ppm, otherwise it is reduced to a 5-point window. Next, fluctuation characteristics are identified by locating consecutive peaks and troughs to determine periodic patterns; a peak must simultaneously meet the condition of being higher than the three preceding and three following data points. Finally, prediction calculations are performed, matching similar fluctuation patterns in the historical database, prioritizing historical data from the same growth stage. Similarity matching uses the waveform correlation coefficient method, with a correlation coefficient threshold set at 0.85.

[0087] Timestamped light intensity data is input into the light intensity prediction unit for processing. The criteria for identifying abrupt changes in light intensity are defined as: a change exceeding 3000 lux within 10 seconds or a cumulative change exceeding 5000 lux within 60 seconds. After feature extraction, the predicted value is corrected by incorporating real-time weather type. The weather type is obtained through a meteorological data interface and converted into a light intensity correction coefficient, for example, a coefficient of 1.0 for sunny days and 0.6 for cloudy days. False abrupt changes caused by equipment malfunctions are excluded during processing; the criterion for judgment is that no reverse abrupt change occurs within 30 minutes after the initial change.

[0088] The rate of change of carbon dioxide concentration was calculated using the finite difference method. The calculation window length was dynamically determined based on environmental stability: when the maximum fluctuation of the three most recent data points was less than 20 ppm, 10 data points were used to calculate the average rate of change; otherwise, 5 data points were used to capture rapid trends. The rate of change was expressed in ppm per minute, and the results were rounded to two decimal places. Outlier data points were handled using the neighborhood mean substitution method, with the neighborhood consisting of two valid data points before and after the outlier.

[0089] The generation of real-time carbon dioxide concentration predictions incorporates pattern matching and trend extrapolation techniques. In the pattern matching stage, fluctuation patterns with a similarity exceeding 85% are retrieved from the historical database. The trend extrapolation stage employs a time-decay weighting strategy: the most recent three months of historical data have a weight of 0.6, and each year earlier has a weight multiplied by a decay coefficient of 0.8. The final prediction value is a weighted average, with the total weights normalized to 1.0. The prediction results undergo range validation to ensure they fall within a reasonable range of 200 ppm to 2000 ppm.

[0090] A mechanism for generating real-time light intensity forecasts establishes a weather baseline curve. Three types of baseline weather curves are preset: a maximum value of 120,000 lux for sunny days, 50,000 lux for cloudy days, and 20,000 lux for rainy days. During real-time forecasting, fuzzy matching is used to determine the similarity between the current weather condition and the baseline curve. After generating the forecast value, a secondary verification is performed: if the forecast value exceeds the historical maximum value for the current season, it is reset to 95% of the historical maximum value.

[0091] The construction of the digital twin of Ganoderma lucidum growth began with the execution of historical data collection standards. Environmental data were collected for three consecutive cultivation cycles, with a fixed sampling interval of 1 minute and a data missing rate requirement of less than 5%. Data preprocessing included outlier removal and normalization: outliers were defined as data points exceeding 3 standard deviations; the normalization range was set to the interval between the historical minimum and maximum values ​​of each parameter.

[0092] The diurnal concentration fluctuation characteristics were identified using a periodic analysis method. After eliminating high-frequency noise using the moving average method, the peak and trough distribution within a 24-hour period was detected. Characteristic parameters included: peak occurrence time deviation not exceeding 30 minutes, trough depth difference less than 15%, and waveform correlation coefficient greater than 0.9. Stable fluctuation characteristics required meeting the above conditions for three consecutive days.

[0093] The quantification parameters for the abrupt change characteristics of light intensity include: the abrupt change trigger slope (lux per second), the abrupt change duration (seconds), and the recovery phase duration (minutes). The feature vector is stored in a structured database, with each record containing the time of the abrupt change, ambient temperature and humidity, and associated response parameters.

[0094] Association rules were established based on statistical correlation analysis. The analysis focused on the response of carbon dioxide concentration changes within specific time windows following sudden changes in light intensity: a 30-minute observation window for sudden increases and a 120-minute observation window for gradual decreases. Rule validity required the following: support greater than 50 samples and confidence level exceeding 75%. Rules were stored in a condition-result structure, for example, "Sudden increase in light intensity → carbon dioxide concentration decreases by 200±50ppm".

[0095] The response mechanism configuration of the carbon dioxide concentration prediction unit includes parameter calibration. Rule weights are calculated based on historical validation accuracy: the weight increases by 0.2 for every 10% increase in accuracy. The response trigger threshold is set to 80% through a matching-accuracy balance analysis. Response execution employs a progressive impact strategy: the initial weight of the rule prediction value is 0.3, dynamically increasing to a maximum weight of 0.8 based on real-time matching accuracy.

[0096] The reverse matching mechanism of the light intensity prediction unit introduces time delay calibration. By analyzing historical data to determine the time lag relationship between carbon dioxide changes and light response, a typical delay time of 20 to 40 minutes is identified. A delay-confidence mapping table is established: a 30-minute delay has a confidence level of 0.85, and a 40-minute delay has a confidence level of 0.75. Rules with a confidence level below 0.6 require verification using other indicators.

[0097] The coupling of the two prediction units enables data interaction and weight coordination. Intermediate prediction results and confidence indices are exchanged every 5 minutes. The dynamic weight adjustment algorithm is calculated based on the environmental stability index, which is defined as the ratio of the variance of the most recent hour's data to the historical baseline variance. The formula for calculating the weight of the main prediction unit is: Main prediction unit weight = 0.5 + 0.3 × (1 - environmental stability index), and the weights of the auxiliary units are complementary to 1.

[0098] Figure 2 The flowchart of the activation mechanism of the intracellular oxidative stress marker in Ganoderma lucidum according to the present invention is given. S3: In the digital twin of Ganoderma lucidum growth, the matching degree between the rate of change of carbon dioxide concentration and the mycelial respiratory entropy is generated, and the accumulation curve of intracellular reactive oxygen species is simulated based on the rate of change of carbon dioxide concentration and light intensity. When the rate of increase of the curve exceeds the rate of increase of the matching degree, the oxidative stress marker is activated. The implementation is as follows:

[0099] The rate of change of carbon dioxide concentration, calculated in real time by the digital twin of Ganoderma lucidum growth, is obtained. This data is in ppm per minute and is updated every minute. The rate of change of carbon dioxide concentration has already been obtained in step S2, and its value comes from the output of the carbon dioxide concentration prediction unit.

[0100] The procedure for determining mycelial respiration entropy based on the rate of change of carbon dioxide concentration is as follows: A baseline reference table for mycelial oxygen consumption rate is pre-generated, constructed through standard cultivation experiments. The construction process involves: in a controlled environment of 25±1 degrees Celsius and 85%±5% humidity, measuring the mycelial oxygen consumption rate corresponding to every 20 ppm / min increase in the rate of change of carbon dioxide concentration; repeating the experiment 50 times for each rate interval (e.g., 50 sets of oxygen consumption data for the 0-20 ppm / min interval); calculating the arithmetic mean of the oxygen consumption rates for each interval as the baseline value; storing the reference table in a database table format, containing two columns: "Concentration Change Interval" and "Baseline Oxygen Consumption Rate". When determining the mycelial respiration entropy value, the current rate of change of carbon dioxide concentration is detected, and its corresponding interval range is matched (e.g., the current value of 25 ppm / min matches the 20-40 ppm / min interval). The corresponding baseline value for mycelial oxygen consumption rate is extracted from the reference table and directly output as the mycelial respiration entropy value. When the rate of change of concentration exceeds the range of the reference table, the nearest neighbor interval baseline value is used.

[0101] The deviation between the current mycelial respiratory entropy value and the baseline respiratory entropy value is calculated as the matching degree. The baseline respiratory entropy value is dynamically set according to the growth stage of Ganoderma lucidum: 50 ml oxygen per gram dry weight per hour during the mycelial growth stage, 65 ml during the primordia formation stage, and 80 ml during the fruiting body development stage. The matching degree is calculated using the relative deviation formula: Matching degree = (Current mycelial respiratory entropy value - Baseline respiratory entropy value) ÷ Baseline respiratory entropy value × 100%, and the result is rounded to an integer percentage. An anomaly is triggered when the absolute value of the matching degree exceeds 20%.

[0102] The system synchronously monitors the coordinated trend of carbon dioxide concentration change rate and real-time predicted light intensity. The monitoring process involves recording a data pair (carbon dioxide concentration change rate and real-time predicted light intensity) every minute within a fixed 5-minute time window; calculating the covariance change of data pairs from adjacent time windows; and determining a stable coordinated trend when the covariance signs remain consistent across three consecutive time windows. Trend types are categorized as positive coordination (both changing in the same direction) and negative coordination (both changing in opposite directions). For example, an increase in carbon dioxide concentration followed by an increase in light intensity is considered positive coordination. If the covariance sign is unstable, a default neutral trend type is used.

[0103] Intracellular reactive oxygen species (ROS) accumulation levels are obtained by querying the ROS accumulation mapping table based on the synergistic trend. The mapping table is constructed as follows: Baseline accumulation level = absolute value of carbon dioxide concentration change rate ÷ 10 (unit: accumulation unit), for example, 30 ppm / min corresponds to 3 units of base accumulation; trend correction coefficients are defined: positive synergistic coefficient 1.2, negative synergistic coefficient 0.8, neutral trend coefficient 1.0; final accumulation level = base accumulation level × trend correction coefficient. An accumulation unit is defined as 0.1 μmol / g of ROS generated per minute under standard conditions. During the query, the current synergistic trend type is first determined, and then the accumulation level value is calculated based on the real-time carbon dioxide concentration change rate.

[0104] A cumulative curve showing the change of intracellular reactive oxygen species (ROS) levels over time was generated. The curve construction process was as follows: the current cumulative level value was recorded every minute; adjacent time points were connected using linear interpolation to form a continuous curve; the horizontal axis of the curve represents time (in minutes), and the vertical axis represents the cumulative level (in cumulative units); the curve time range covered the most recent 60 minutes, and a complete curve snapshot was saved every 5 minutes. Key parameters of the curve included: current value, average rate of change over the most recent 10 minutes, most recent peak value, and its occurrence time.

[0105] The conditions for activating the oxidative stress flag are determined by performing the following operations: calculating the incremental increase of the cumulative curve over the last 5 minutes (current cumulative level value - cumulative level value 5 minutes ago); simultaneously calculating the increase in the matching degree over the same period (current matching degree percentage - matching degree percentage 5 minutes ago); when the incremental increase value is greater than the matching degree increase, an activation command is sent to the control system; the activated state is automatically reset after 30 minutes. A fault-tolerant mechanism is set in the determination process: activation is only executed if the conditions are met for two consecutive detection cycles (i.e., two consecutive minute-per-hour detections) to avoid false triggering.

[0106] S4. When the matching degree exceeds the set threshold and an oxidative stress sign is present, a metabolic overload signal is generated. At the same time, it is determined whether the real-time predicted value of carbon dioxide concentration is within the lag range of Ganoderma lucidum physiological response. The implementation is as follows:

[0107] The matching degree data and oxidative stress flag status data generated from the digital twin of Ganoderma lucidum growth are acquired. The matching degree data is expressed as a percentage and is updated every minute; the oxidative stress flag status is a Boolean variable with two states: active and inactive. These two data sets are transmitted to this processing unit in real time via a shared memory area, with the transmission latency controlled within 50 milliseconds.

[0108] When the matching degree value exceeds the preset matching degree threshold and the oxidative stress flag is activated, a metabolic overload signal generation operation is performed. The preset matching degree threshold is dynamically configured according to different growth stages of Ganoderma lucidum: the matching degree threshold is set at 15% during the mycelial growth stage, 20% during the primordium formation stage, and 25% during the fruiting body development stage. The threshold setting is based on: determining the critical point of metabolic imbalance and setting a 5% safety margin by analyzing metabolic abnormal events at each stage in historical cultivation data. For example, during the mycelial growth stage, experimental data shows that metabolic disorder occurs when the matching degree reaches 20%, so the matching degree threshold is set at 15%. When generating the metabolic overload signal, the trigger timestamp and the current matching degree value are recorded simultaneously. This signal is continuously output until the matching degree falls below the matching degree threshold and the oxidative stress flag is reset to an inactive state.

[0109] The system synchronously reads real-time predicted carbon dioxide concentration values. This data originates from the carbon dioxide concentration prediction unit of the Ganoderma lucidum growth digital twin, with the unit being ppm and an update frequency of once per minute. During reading, a data validity check is performed: if the real-time predicted carbon dioxide concentration exceeds the range of 0 to 5000 ppm, the moving average of the three previous valid real-time predicted carbon dioxide concentration values ​​is used instead. The moving average calculation window consists of three data points.

[0110] This function queries the carbon dioxide concentration adaptation range corresponding to the current growth stage in a pre-defined Ganoderma lucidum physiological response feature database. The database contains the following fields: a growth stage code field (mycelial growth stage is coded as 1, primordium formation stage as 2, and fruiting body development stage as 3); a lower limit field for the carbon dioxide concentration adaptation range (in ppm); an upper limit field for the carbon dioxide concentration adaptation range (in ppm); a left boundary field for the hysteresis boundary; and a right boundary field for the hysteresis boundary (in ppm). The database is constructed as follows: under standard cultivation conditions of 25±1°C and 85%±5% humidity, the carbon dioxide concentration range in which Ganoderma lucidum maintains above 90% physiological activity at each growth stage is measured as the carbon dioxide concentration adaptation range; through a carbon dioxide concentration step change experiment, the concentration boundary where the physiological response delay exceeds 5 minutes is determined as the hysteresis boundary. For example, during the mycelial growth stage, the carbon dioxide concentration adaptation range is recorded as 800 to 1200 ppm, and the hysteresis boundary range is recorded as 880 to 1120 ppm. The query retrieves the corresponding record based on the real-time growth stage code.

[0111] The system determines whether the real-time predicted carbon dioxide concentration falls within the hysteresis boundary range of the carbon dioxide concentration tolerance zone. The logic is as follows: if the condition "left boundary value ≤ real-time predicted carbon dioxide concentration ≤ right boundary value" is met, then the value is considered to be within the hysteresis zone. The boundary values ​​use a closed-interval inclusion rule; for example, a real-time predicted carbon dioxide concentration of 880 ppm is considered to be within the hysteresis zone. A fault-tolerant mechanism is implemented in the determination process: only when the real-time predicted carbon dioxide concentration is detected three consecutive times within the hysteresis boundary range is the state of hysteresis finally confirmed.

[0112] The calculation rules for the hysteresis boundary interval are based on the general principles of Ganoderma lucidum's physiological response characteristics: when environmental parameters change abruptly, the mycelial growth stage is less adaptable to fluctuations in carbon dioxide concentration, requiring a wider buffer zone. Specifically, a lower limit coefficient of 1.1 and an upper limit coefficient of 0.9 are used, making the boundary range approximately 10% larger than the actual adaptive range (e.g., an adaptive range of 800-1200 ppm corresponds to a hysteresis boundary of 880-1080 ppm). For other growth stages, due to increased metabolic stability, the boundary range narrows to a 5% expansion (800-1200 ppm corresponds to 840-1140 ppm). This ratio setting aligns with the general understanding in plant physiology—the young stages of an organism are more sensitive to environmental changes. In practical applications, the expansion ratio can be adjusted within the range of 5% to 15% according to the characteristics of the cultivar; for example, a 12% expansion coefficient can be used for varieties sensitive to fluctuations. Boundary value calculation always follows the unified formula: "Hysteresis boundary left boundary value = adaptation range lower limit value × (1 + expansion coefficient), hysteresis boundary right boundary value = adaptation range upper limit value × (1 - expansion coefficient)". The expansion coefficient value is determined by cultivation experts based on the variety file.

[0113] When the real-time predicted carbon dioxide concentration falls within the hysteresis boundary range, the current environmental state is marked as being within the hysteresis range of Ganoderma lucidum's physiological response. This marked state is a global variable and remains valid until the real-time predicted carbon dioxide concentration exceeds the hysteresis boundary range and five consecutive measurements (i.e., 5 minutes) do not meet the hysteresis condition. The following parameters are recorded simultaneously during marking: the timestamp of entering the hysteresis zone, the current real-time predicted carbon dioxide concentration, and the code for the corresponding growth stage. The state exit condition is: five consecutive measurements of the real-time predicted carbon dioxide concentration exceeding the hysteresis boundary range.

[0114] S5. When the Ganoderma lucidum physiological response lag range is in effect, perform delay compensation processing on the real-time predicted value of carbon dioxide concentration. If a metabolic overload signal exists, apply an inhibition coefficient to generate a compensated carbon dioxide concentration value, as follows:

[0115] The labeling state of the hysteresis interval of Ganoderma lucidum physiological response is confirmed. This state is a Boolean global variable, generated by step S4 and stored in the shared memory area. The state detection operation is performed every minute. When the labeling state is "within the hysteresis interval of Ganoderma lucidum physiological response", the compensation processing flow of the real-time predicted value of carbon dioxide concentration is triggered. The validity of the labeling state continues until the exit condition defined in step S4 is met, that is, the state is automatically released when the real-time predicted value of carbon dioxide concentration exceeds the hysteresis boundary interval for five consecutive measurements.

[0116] The real-time predicted carbon dioxide concentration is compensated by time shifting. The specific operation process is as follows: First, obtain the current real-time predicted carbon dioxide concentration in ppm; then, query the lag time parameter corresponding to the current growth stage in the preset feature library (in minutes); then, shift the real-time predicted carbon dioxide concentration forward according to the lag time parameter. The lag time parameter is determined as follows: A step change experiment of carbon dioxide concentration is conducted under standard cultivation conditions, and the physiological response delay time of Ganoderma lucidum mycelium at each growth stage is measured. The median delay time of 20 repeated experiments is used as the compensation amount. For example, if the median lag time measured in the experiment during the mycelial growth period is 8 minutes, then the current real-time predicted carbon dioxide concentration is replaced with the historical predicted value from 8 minutes ago. During compensation, if historical data for the target time is missing, a linear extrapolation method is used to reconstruct the value based on the three most recent valid data points.

[0117] The presence and status of metabolic overload signals are detected synchronously; these signals are Boolean variables. During detection, the real-time status bit of the signal register is accessed, and the presence of a metabolic overload signal is determined when the status bit is "active." The correlation between the duration of the metabolic overload signal and the matching threshold and oxidative stress flag has been clearly defined in previous steps.

[0118] When a metabolic overload signal is present, the corresponding carbon dioxide concentration inhibition coefficient is retrieved from the cultivation database. The cultivation database uses a relational data structure and contains three key fields: a growth stage coding field (mycelial growth stage coded as 1, primordia formation stage coded as 2, and fruiting body development stage coded as 3); a metabolic overload level field (divided into mild, moderate, and severe levels); and a carbon dioxide concentration inhibition coefficient field (with a value range of 0.7 to 1.0). The carbon dioxide concentration inhibition coefficient is set as follows: a control experiment is conducted in a controlled environment to measure the carbon dioxide tolerance decay rate of Ganoderma lucidum under different metabolic overload levels, and the decay rate is converted into an inhibition coefficient. For example, during the mycelial growth stage, when there is moderate metabolic overload (matching degree exceeding the threshold of 5%–10%), the experimentally measured tolerance decay rate is 15%, corresponding to a carbon dioxide concentration inhibition coefficient of 0.85. Database access uses a query mode combining the "growth stage coding + metabolic overload level" key.

[0119] The carbon dioxide concentration suppression coefficient is applied to the time-shift compensated carbon dioxide concentration value using a multiplicative operation: compensated carbon dioxide concentration value = time-shift compensation value × carbon dioxide concentration suppression coefficient. Strict numerical range verification is performed during the calculation process: when the calculated result is below 200 ppm, it is forcibly set to 200 ppm, corresponding to the minimum concentration required for Ganoderma lucidum survival; when the calculated result is above 5000 ppm, it is forcibly set to 5000 ppm, which is the upper limit of the sensor's range. The calculation result retains one decimal place of accuracy, and the unit ppm remains unchanged.

[0120] The system generates a compensated carbon dioxide concentration value after applying a carbon dioxide concentration suppression coefficient, and writes this value as the final output to the environmental control bus. During output, the following metadata is recorded synchronously: the original real-time predicted carbon dioxide concentration, the time shift compensation amount (unit: minutes), the carbon dioxide concentration suppression coefficient, and the timestamp of the application operation. The output frequency is synchronized with the input data, updating once per minute. When the Ganoderma lucidum physiological response hysteresis interval marker state is exited, this process automatically terminates, and the system resumes directly outputting the real-time predicted carbon dioxide concentration value.

[0121] S6. Perform a synergistic impact analysis between the compensated carbon dioxide concentration value and the real-time predicted light intensity value, generate environmental control instructions, and drive the execution equipment to execute them, as follows:

[0122] The compensated carbon dioxide concentration value generated in step S5 and the real-time predicted light intensity value generated in step S2 are obtained. The unit of the compensated carbon dioxide concentration value is ppm, and the unit of the real-time predicted light intensity value is lux. Both data are updated synchronously every minute. The data transmission process adopts a CRC-16 check mechanism. When the check fails, the median value of the three most recent valid data is automatically retransmitted to ensure data integrity.

[0123] The system queries the environmental factor collaborative rule base to find the carbon dioxide regulation intensity level corresponding to the compensated carbon dioxide concentration value. The environmental factor collaborative rule base is constructed as follows: A three-year cultivation experiment was conducted under standard cultivation conditions (temperature 25±1 degrees Celsius, humidity 85%±5%), recording the biomass growth rate curves of Ganoderma lucidum within different carbon dioxide concentration ranges. Based on the inflection points of the curves, the concentrations were divided into five regulation levels: 0 to 400 ppm is extremely low, 400 to 800 ppm is low, 800 to 1200 ppm is medium, 1200 to 1600 ppm is high, and above 1600 ppm is extremely high. For example, when the compensated carbon dioxide concentration is 1000 ppm, the query returns a "medium" level. The rule base is stored in separate tables according to the Ganoderma lucidum growth stages. During a query, the system automatically matches the data table corresponding to the current growth stage; if stage identification fails, the mycelial growth stage data table is used by default.

[0124] The light intensity level corresponding to the real-time predicted light intensity is queried in the environmental factor collaborative rule base. The light intensity level is divided into four levels based on the photosynthetic efficiency curves at each growth stage determined by light saturation point experiments: 0 to 20,000 lux is considered weak light, 20,000 to 40,000 lux is moderate light, 40,000 to 60,000 lux is strong light, and above 60,000 lux is extremely strong light. For example, when the real-time predicted light intensity is 45,000 lux, the query returns the "strong light" level. The level boundary value setting rules are: the upper limit of 20,000 lux for the weak light level corresponds to the light compensation point during the mycelial growth stage, and the upper limit of 60,000 lux for the strong light level corresponds to the light inhibition threshold during the fruiting body stage.

[0125] The coordinated control mode is determined based on the combination relationship between the carbon dioxide control intensity level and the light control intensity level. There are six basic types of coordinated control modes, with the following matching rules: When the carbon dioxide control intensity level is low and the light control intensity level is weak light, type A (maintenance mode) is used; when the carbon dioxide control intensity level is medium and the light control intensity level is moderate, type B (optimization mode) is used; when the carbon dioxide control intensity level is high and the light control intensity level is strong light, type C (suppression mode) is used; when the carbon dioxide control intensity level is extremely high, regardless of the light control intensity level, type D (emergency ventilation mode) is used; when the light control intensity level is extremely strong, regardless of the carbon dioxide control intensity level, type E (shading mode) is used; and when the carbon dioxide control intensity level is low and the light control intensity level is strong light, type F (balance mode) is used. For example, when the carbon dioxide control intensity level is high and the light control intensity level is strong light, type C (suppression mode) is selected. The pattern matching matrix was verified through orthogonal experiments, with each combination supported by no fewer than 200 sets of cultivation data, achieving a confidence level of 95%.

[0126] An environmental control command set, including ventilation equipment opening instructions and supplemental lighting equipment power instructions, is generated based on a coordinated control mode. The specific rules for instruction generation are as follows: Ventilation equipment opening instruction = Basic opening value × Mode coefficient, where the basic opening value is calculated based on the cultivation space volume using the formula: Cultivation space volume (cubic meters) × 3%, for example, a 10 cubic meter space has a basic opening value of 30%; The preset mode coefficients are: Type A mode coefficient 1.0, Type B mode coefficient 0.8, Type C mode coefficient 1.2, Type D mode coefficient 1.5, Type E mode coefficient 0.5, and Type F mode coefficient 0.9. Supplemental lighting equipment power instruction = Rated power × Mode coefficient, where the rated power is 80% of the supplemental lighting equipment's nominal maximum power. Boundary checks are performed during instruction generation: Ventilation equipment opening instructions are limited to the range of 0% to 100%, and supplemental lighting equipment power instructions do not exceed 90% of the equipment's rated power.

[0127] The environmental control command set is sent to the environmental control execution equipment for operation. The transmission protocol adopts the Modbus-RTU standard, and the data frame structure includes: device address code (1 byte), function code (1 byte), command data field (4 bytes, including opening command value and power command value), and CRC check code (2 bytes). The execution equipment includes two types: ventilation equipment and supplementary lighting equipment. After receiving the opening command, the ventilation equipment adjusts the opening to the target value within 10 seconds at a gradual rate of no more than 5% per second; after receiving the power command, the supplementary lighting equipment adjusts the output power to the target value within 30 seconds at a gradual rate of no more than 2% per second. After execution, the equipment must return a status confirmation code within 20 seconds. If there is no response within the timeout period, a retransmission mechanism is initiated, with a maximum of three retries; if all three retries fail, a device fault log is recorded and a backup control strategy is activated.

[0128] All calculations involved in the embodiments are dimensionless numerical calculations, and the preset parameters and thresholds in the calculations are set by those skilled in the art according to the actual situation.

[0129] It should be noted that this invention can be deployed on the device itself to realize embedded applications, or it can run on a PC or other terminal with a user interface, thereby meeting various hardware environments and usage requirements.

[0130] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wireless or wired transmission; wired transmission methods include optical fiber, twisted pair, coaxial cable, etc.; wireless transmission includes infrared, microwave, etc. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0131] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0133] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0135] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] 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.

[0137] 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 multi-factor coupled digital twin regulation method for the environment of Ganoderma lucidum oriented towards high-yield requirements, characterized in that, include: S1. Real-time collection of carbon dioxide concentration and light intensity in the Ganoderma lucidum cultivation environment; S2. Input carbon dioxide concentration and light intensity into the digital twin of Ganoderma lucidum growth to generate real-time prediction values; S3. In the digital twin of Ganoderma lucidum growth, the matching degree between the rate of change of carbon dioxide concentration and the mycelial respiratory entropy is generated, and the accumulation curve of intracellular reactive oxygen species is simulated based on the rate of change of carbon dioxide concentration and light intensity. When the rate of increase of the curve exceeds the growth rate of the matching degree, the oxidative stress marker is activated. S4. When the matching degree exceeds the set threshold and there is an oxidative stress sign, a metabolic overload signal is generated. At the same time, it is determined whether the real-time predicted value of carbon dioxide concentration is in the lag range of Ganoderma lucidum physiological response. S5. When the Ganoderma lucidum physiological response lag range is in effect, a delay compensation process is performed on the real-time predicted value of carbon dioxide concentration. If a metabolic overload signal exists, an inhibition coefficient is applied to generate a compensated carbon dioxide concentration value, including: Confirm the marking status of the lag region in the physiological response of Ganoderma lucidum; When the marked state is in the lag range of Ganoderma lucidum physiological response, the real-time predicted value of carbon dioxide concentration is subjected to time shift compensation. Detect the presence of metabolic overload signals; When a metabolic overload signal is present, the corresponding carbon dioxide concentration inhibition coefficient is read from the cultivation database; Apply the carbon dioxide concentration suppression coefficient to the carbon dioxide concentration value after time-shift compensation. Generate the compensated carbon dioxide concentration value after applying the carbon dioxide concentration suppression coefficient; S6. Perform a synergistic impact analysis between the compensated carbon dioxide concentration value and the real-time predicted light intensity value, generate environmental control instructions, and drive the execution equipment to perform them, including: Obtain the compensated carbon dioxide concentration value and the real-time predicted value of light intensity; Search the environmental factor collaborative rule base for the carbon dioxide regulation intensity level corresponding to the compensated carbon dioxide concentration value; Query the light intensity control level corresponding to the real-time predicted light intensity value in the environmental factor collaborative rule base; The coordinated control mode is determined based on the combination relationship between the carbon dioxide control intensity level and the light control intensity level. An environmental control instruction set, including ventilation equipment opening instructions and supplementary lighting equipment power instructions, is generated based on the coordinated control mode. The environmental control instruction set is sent to the environmental control execution equipment for execution.

2. The multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment oriented towards high-yield requirements as described in claim 1, characterized in that, Real-time monitoring of carbon dioxide concentration and light intensity in the Ganoderma lucidum cultivation environment, including: Carbon dioxide concentration data is acquired using a carbon dioxide concentration sensor at a first sampling frequency; Light intensity data is acquired using a light intensity sensor at a second sampling frequency; Add timestamps to carbon dioxide concentration data and light intensity data; Timestamped carbon dioxide concentration data and light intensity data are stored in a distributed cache queue.

3. The multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment oriented towards high-yield requirements as described in claim 2, is characterized in that... Inputting carbon dioxide concentration and light intensity into the digital twin of Ganoderma lucidum growth generates real-time predicted values, including: Read timestamped carbon dioxide concentration data and light intensity data from a distributed cache queue; Input the timestamped carbon dioxide concentration data into the carbon dioxide concentration prediction unit of the Ganoderma lucidum growth digital twin; Input the timestamped light intensity data into the light intensity prediction unit of the Ganoderma lucidum growth digital twin; Calculate the rate of change in carbon dioxide concentration using a digital twin of Ganoderma lucidum growth; Real-time predicted values ​​of carbon dioxide concentration and light intensity are generated using a digital twin of Ganoderma lucidum growth.

4. The multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment oriented towards high-yield requirements as described in claim 3, is characterized in that... The digital twin of Ganoderma lucidum growth is established through the following methods: Collect time-series data on carbon dioxide concentration and light intensity continuously recorded throughout the historical cultivation cycle; Identify recurring diurnal concentration fluctuations in carbon dioxide concentration time-series data; Extract the characteristics of abrupt changes in light intensity caused by weather variations from time-series data; Establish a correlation rule between the characteristics of carbon dioxide concentration fluctuations and the characteristics of sudden changes in light intensity; The response mechanism of the carbon dioxide concentration prediction unit is configured based on association rules; The response mechanism of the illumination intensity prediction unit is configured based on association rules; A digital twin of Ganoderma lucidum growth is formed by combining a carbon dioxide concentration prediction unit and a light intensity prediction unit.

5. The multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment oriented towards high-yield requirements as described in claim 3, characterized in that, In a digital twin of Ganoderma lucidum growth, a matching degree between the rate of change in carbon dioxide concentration and mycelial respiratory entropy was generated. Based on the rate of change in carbon dioxide concentration and light intensity, an intracellular reactive oxygen species (ROS) accumulation curve was simulated. When the rate of increase of the curve exceeded the rate of increase of the matching degree, oxidative stress markers were activated, including: Obtain the rate of change of carbon dioxide concentration; The mycelial respiration entropy value is determined based on the correspondence between the rate of change of carbon dioxide concentration and the preset mycelial oxygen consumption rate. The deviation between the current mycelial respiratory entropy value and the baseline respiratory entropy value is used as the degree of matching. Simultaneously monitor the coordinated changing trend of carbon dioxide concentration change rate and real-time predicted light intensity; Based on the synergistic change trend, query the corresponding intracellular reactive oxygen species accumulation level in the reactive oxygen species accumulation mapping table; Generate a cumulative curve reflecting the change in intracellular reactive oxygen species accumulation levels over time; When the increase in the cumulative curve exceeds the increase in the matching degree, the oxidative stress flag is activated.

6. The multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment oriented towards high-yield requirements as described in claim 5, is characterized in that... The mycelial respiration entropy value is determined based on the correlation between the rate of change of carbon dioxide concentration and the preset mycelial oxygen consumption rate, including: Pre-stored reference table of mycelial oxygen consumption rate for different carbon dioxide concentration change rate ranges; Detect the range to which the current rate of change of carbon dioxide concentration belongs, and extract the corresponding baseline value of mycelial oxygen consumption rate from the reference table of mycelial oxygen consumption rate baseline values; The baseline value of mycelial oxygen consumption rate is output as the mycelial respiration entropy value.

7. The multi-factor coupled digital twin regulation method for the Ganoderma lucidum environment oriented towards high-yield requirements as described in claim 5, characterized in that, When the matching degree exceeds a set threshold and an oxidative stress marker is present, a metabolic overload signal is generated. Simultaneously, it is determined whether the real-time predicted carbon dioxide concentration falls within the hysteresis range of Ganoderma lucidum's physiological response, including: Obtain matching degree and oxidative stress markers; When the matching degree exceeds the preset matching degree threshold and the oxidative stress flag is in an activated state, a metabolic overload signal is generated; Simultaneously read real-time predicted values ​​of carbon dioxide concentration; Query the carbon dioxide concentration adaptation range corresponding to the current growth stage in the preset Ganoderma lucidum physiological response feature database; Determine whether the real-time predicted value of carbon dioxide concentration is within the hysteresis boundary range of the carbon dioxide concentration adaptation range; When the real-time predicted value of carbon dioxide concentration is within the hysteresis boundary range, it is marked as being in the hysteresis range of Ganoderma lucidum physiological response.

Images