High-yield-demand-oriented multi-factor coupling ganoderma lucidum environment digital twinning regulation and control method

By establishing a digital twin of Ganoderma lucidum growth, real-time data on carbon dioxide concentration and light intensity are collected and analyzed to generate predicted values ​​and perform delay compensation and inhibition treatment, thus resolving the contradiction between environmental regulation and physiological response in Ganoderma lucidum cultivation and achieving a high-yield and stable growth environment.

CN120827071AActive Publication Date: 2025-10-24TIANSHUI NORMAL UNIV

Patent Information

Application Number
CN202511334556.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-18
Publication Date
2025-10-24
Estimated Expiration
2045-09-18

AI Technical Summary

Technical Problem

Existing environmental control systems in Ganoderma lucidum cultivation suffer from a contradiction between control commands and physiological responses, leading to periodic oscillations in equipment operation, resulting in overshooting of environmental parameters and physiological stress, which affects yield stability.

Method used

By establishing a digital twin of Ganoderma lucidum growth, real-time data on carbon dioxide concentration and light intensity are collected to generate predicted values. Based on the mycelial respiration entropy and reactive oxygen species accumulation curve, oxidative stress markers are activated, delayed compensation and inhibition treatments are performed, and synergistic regulatory instructions are generated.

Benefits of technology

It achieves precise alignment between environmental regulation and physiological response, reduces frequent equipment operation and parameter oscillation, and ensures biomass accumulation and stable synthesis of active ingredients under high-yield targets.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120827071A_ABST
    Figure CN120827071A_ABST
Patent Text Reader

Abstract

The invention discloses a multi-factor coupling ganoderma lucidum environment digital twinborn regulation and control method oriented to high-yield requirements, particularly relates to the technical field of intelligent cultivation of edible mushrooms, and is used for solving the problems of equipment action oscillation and recessive physiological stress caused by physiological response hysteresis of ganoderma lucidum in an existing environment regulation and control system. Carbon dioxide concentration and illumination intensity predicted values are generated in real time by constructing ganoderma lucidum growth digital twins, and an oxidative stress mark is activated by combining hypha respiratory entropy matching degree analysis and an active oxygen accumulation curve; when the matching degree exceeds a threshold value and oxidative stress exists, a metabolic overload signal is generated, and whether the carbon dioxide predicted value is in a physiological hysteresis interval or not is judged; delay compensation and metabolic overload suppression coefficient adjustment are performed on the carbon dioxide predicted value in the delay interval; and finally, inputting the compensated carbon dioxide value and the illumination prediction value into an environment factor coordination rule base, generating a ventilation opening degree and light supplementing power instruction to drive execution equipment, and ensuring the morphological development stability of the sporocarp and the synthesis efficiency of the active component.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent cultivation of edible fungi, more specifically, the present application relates to a multi-factor coupling ganoderma environmental digital twin regulation method for high yield demand. BACKGROUND

[0002] In the factory cultivation of ganoderma, the environmental regulation system generates control instructions by real-time monitoring of temperature, humidity, carbon dioxide concentration and light, etc. and combining with the preset growth model to drive the execution equipment (such as fan, humidifier); the existing technology generally adopts a closed-loop control strategy (such as PID algorithm) based on sensor feedback, and its design logic depends on the immediate mapping relationship between environmental parameters and device response, which has realized basic application in typical crop greenhouses, but in the cultivation of ganoderma and other medicinal fungi which are highly sensitive to multi-factor coupling, the regulation accuracy and yield stability still face significant challenges.

[0003] The existing environmental regulation system has defects in dealing with the growth characteristics of ganoderma: the real-time nature of the control instruction contradicts the hysteresis of the physiological response of ganoderma, because there is inherent delay in the physiological response of ganoderma to key environmental factors such as carbon dioxide (such as stomatal regulation mechanism), and the control system only adjusts the equipment frequently according to the immediate data of the sensor, resulting in a disconnection between short-term regulation targets (such as carbon dioxide concentration reaching the standard) and long-term biological effects (such as cap development), this contradiction causes periodic oscillation of equipment action, causing environmental parameter overshoot accumulation, and then forming hidden physiological stress, eventually showing abnormal morphology of fruiting body and uncontrollable yield fluctuations. SUMMARY

[0004] In order to overcome the above-mentioned defects of the prior art, the present application provides a multi-factor coupling ganoderma environmental digital twin regulation method for high yield demand to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical scheme: The multi-factor coupling ganoderma environmental digital twin regulation method for high yield demand comprises: S1, real-time acquisition of carbon dioxide concentration and light intensity in the ganoderma cultivation environment; S2, inputting the carbon dioxide concentration and light intensity into the ganoderma growth digital twin to generate real-time prediction values; S3, generating the matching degree of carbon dioxide concentration change rate and mycelium respiration entropy in the ganoderma growth digital twin, and simulating the intracellular active oxygen accumulation curve based on the carbon dioxide concentration change rate and light intensity, and activating the oxidative stress marker when the rising rate of the curve exceeds the growth rate of the matching degree; S4, generating a metabolic overload signal when the matching degree exceeds the set threshold and there is an oxidative stress marker, and simultaneously judging whether the real-time prediction value of carbon dioxide concentration is in the physiological response lag interval of Ganoderma lucidum; S5, performing delay compensation processing on the real-time prediction value of carbon dioxide concentration when it is in the physiological response lag interval of Ganoderma lucidum, and applying an inhibition coefficient if there is a metabolic overload signal, to generate a compensated carbon dioxide concentration value; S6, performing synergistic influence analysis on the compensated carbon dioxide concentration value and the real-time prediction value of light intensity, generating an environment regulation instruction and driving an execution device to execute.

[0006] Further, the carbon dioxide concentration and light intensity in the cultivation environment of Ganoderma lucidum are collected in real time, including: acquiring carbon dioxide concentration data at a first sampling frequency through a carbon dioxide concentration sensor; acquiring light intensity data at a second sampling frequency through a light intensity sensor; appending a time stamp to the carbon dioxide concentration data and the light intensity data; storing the time-stamped carbon dioxide concentration data and light intensity data to a distributed cache queue.

[0007] Further, the carbon dioxide concentration and light intensity are input into a Ganoderma lucidum growth digital twin to generate real-time prediction values, including: reading the time-stamped carbon dioxide concentration data and light intensity data from the distributed cache queue; inputting the time-stamped carbon dioxide concentration data into a carbon dioxide concentration prediction unit of the Ganoderma lucidum growth digital twin; inputting the time-stamped light intensity data into a light intensity prediction unit of the Ganoderma lucidum growth digital twin; calculating the carbon dioxide concentration change rate through the Ganoderma lucidum growth digital twin; generating the real-time prediction values of carbon dioxide concentration and light intensity through the Ganoderma lucidum growth digital twin.

[0008] Further, the Ganoderma lucidum growth digital twin is established by: collecting continuously recorded carbon dioxide concentration time series data and light intensity time series data in a historical cultivation period; identifying the repeatedly occurring diurnal concentration fluctuation features in the carbon dioxide concentration time series data; extracting the intensity mutation features caused by weather changes in the light intensity time series data; establishing the association rules of carbon dioxide concentration fluctuation features and light intensity mutation features; configuring the response mechanism of the carbon dioxide concentration prediction unit based on the association rules; Configuring a response mechanism of the light intensity prediction unit based on the association rule; Combining the carbon dioxide concentration prediction unit and the light intensity prediction unit forms the Ganoderma lucidum growth digital twin.

[0009] Further, in the Ganoderma lucidum growth digital twin, the matching degree of the carbon dioxide concentration change rate and the mycelium respiration entropy is generated, and the intracellular active oxygen accumulation curve is simulated based on the carbon dioxide concentration change rate and the light intensity, and when the rising rate of the curve exceeds the matching degree growth rate, the oxidative stress flag is activated, including: Obtaining the carbon dioxide concentration change rate; Determining the mycelium respiration entropy value according to the correspondence between the carbon dioxide concentration change rate and the preset mycelium oxygen consumption rate; Taking the deviation amount of the current mycelium respiration entropy value from the reference respiration entropy value as the matching degree; Synchronously monitoring the cooperative change trend of the carbon dioxide concentration change rate and the real-time prediction value of the light intensity; According to the cooperative change trend, the corresponding intracellular active oxygen accumulation level is queried in the active oxygen accumulation mapping table; Generating an accumulation curve reflecting the change of the intracellular active oxygen accumulation level over time; When the rising amplitude increment of the accumulation curve exceeds the matching degree growth amount, the oxidative stress flag is activated.

[0010] Further, determining the mycelium respiration entropy value according to the correspondence between the carbon dioxide concentration change rate and the preset mycelium oxygen consumption rate includes: Pre-storing a mycelium oxygen consumption rate reference value control table corresponding to different carbon dioxide concentration change rate intervals; Detecting the interval to which the current carbon dioxide concentration change rate belongs, and extracting the corresponding mycelium oxygen consumption rate reference value from the mycelium oxygen consumption rate reference value control table; Outputting the mycelium oxygen consumption rate reference value as the mycelium respiration entropy value.

[0011] Further, when the matching degree exceeds the set threshold and the oxidative stress flag exists, a metabolic overload signal is generated, and whether the real-time prediction value of the carbon dioxide concentration is in the Ganoderma lucidum physiological response lag interval is judged, including: Obtaining the matching degree and the oxidative stress flag; When the matching degree exceeds the preset matching degree threshold and the oxidative stress flag is in the activated state, a metabolic overload signal is generated; Synchronously reading the real-time prediction value of the carbon dioxide concentration; Querying the carbon dioxide concentration adaptive range corresponding to the current growth stage in the preset Ganoderma lucidum physiological response feature library; Judging whether the real-time prediction value of the carbon dioxide concentration is located in the lag boundary interval of the carbon dioxide concentration adaptive range; When the real-time predicted value of carbon dioxide concentration is within the hysteresis boundary interval, it is marked as being in the Ganoderma lucidum physiological response hysteresis interval.

[0012] Further, when in the Ganoderma lucidum physiological response hysteresis interval, a delay compensation process is performed on the real-time predicted value of carbon dioxide concentration, and if there is a metabolic overload signal, an inhibition coefficient is applied, to generate a compensated carbon dioxide concentration value, including: Confirming the marking state of the Ganoderma lucidum physiological response hysteresis interval; When the marking state is in the Ganoderma lucidum physiological response hysteresis interval, a time shift compensation process is performed on the real-time predicted value of carbon dioxide concentration; Detecting whether there is a metabolic overload signal; When there is a metabolic overload signal, reading the corresponding carbon dioxide concentration inhibition coefficient from the cultivation database; Applying the carbon dioxide concentration inhibition coefficient to the carbon dioxide concentration value after time shift compensation processing; Generating a compensated carbon dioxide concentration value after applying the carbon dioxide concentration inhibition coefficient.

[0013] Further, the compensated carbon dioxide concentration value and the real-time predicted value of light intensity are analyzed for synergistic influence, to generate an environment control instruction and drive an execution device to execute, including: Obtaining the compensated carbon dioxide concentration value and the real-time predicted value of light intensity; Querying the carbon dioxide regulation intensity level corresponding to the compensated carbon dioxide concentration value in the environment factor synergy rule library; Querying the light regulation intensity level corresponding to the real-time predicted value of light intensity in the environment factor synergy rule library; Determining the synergistic regulation mode according to the combination relationship of the carbon dioxide regulation intensity level and the light regulation intensity level; Generating an environment control instruction set including a ventilation device opening degree instruction and a light supplement device power instruction based on the synergistic regulation mode; Sending the environment control instruction set to the environment control execution device for execution.

[0014] Compared with the prior art, the present application has the following beneficial effects: 1. By establishing Ganoderma lucidum growth digital twin and physiological response hysteresis compensation, the contradiction between environmental regulation real-time and physiological response hysteresis is effectively solved. Specifically, in the digital twin, the matching degree of carbon dioxide concentration change rate and mycelium respiration entropy is dynamically generated, and based on the active oxygen accumulation curve, the oxidative stress marker is activated, combined with metabolic overload signal generation and hysteresis interval judgment, the physiological state of Ganoderma lucidum is realized in advance. By performing delay compensation and inhibition coefficient adjustment on the real-time predicted value of carbon dioxide concentration, the device control instruction and the actual metabolic response time window of Ganoderma lucidum are accurately aligned, which fundamentally avoids the frequent action of the device and parameter oscillation caused by physiological hysteresis. This predictive regulation mode based on physiological response characteristics significantly reduces the implicit stress risk of mycelium caused by environmental overshoot.

[0015] 2. By coupling analysis of the compensated carbon dioxide concentration value and the predicted value of light intensity through the environmental factor coordination rule base, the limitation of traditional single factor closed-loop control is broken through. The matching rule of carbon dioxide regulation intensity level and light regulation intensity level is used to generate coordinated regulation instructions, so that the ventilation and light supplement devices form dynamic cooperation. It fully adapts to the nonlinear interaction between multiple environmental factors in the growth process of Ganoderma lucidum, such as automatically triggering the inhibition mode when high carbon dioxide concentration and strong light exist at the same time, effectively preventing energy loss caused by intensified light respiration. This multi-factor coordinated regulation mode not only maintains the stability of environmental parameters, but also accurately matches the metabolic demand of different growth stages, creating a continuously optimized growth environment for fruit body morphological development, thereby ensuring effective accumulation of biomass and stable synthesis of active ingredients under high yield target. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The flowchart of the multi-factor coupled Ganoderma lucidum environmental digital twin regulation method of the present application for high yield demand; Figure 2 The flowchart of Ganoderma lucidum intracellular oxidative stress marker activation mechanism of the present application. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0018] Embodiment: Figure 1 The multi-factor coupled Ganoderma lucidum environmental digital twin regulation method of the present application for high yield demand is given, including: S1, real-time acquisition of carbon dioxide concentration and light intensity in Ganoderma lucidum cultivation environment; S2, input the carbon dioxide concentration and light intensity into the Ganoderma lucidum growth digital twin to generate real-time prediction values; S3, generate the matching degree of carbon dioxide concentration change rate and mycelium respiration entropy in the Ganoderma lucidum growth digital twin, and simulate the intracellular active oxygen accumulation curve based on the carbon dioxide concentration change rate and light intensity, and activate the oxidative stress marker when the rising rate of the curve exceeds the matching degree growth rate; S4, generate a metabolic overload signal when the matching degree exceeds the set threshold and the oxidative stress marker exists, and determine whether the real-time prediction value of the carbon dioxide concentration is in the Ganoderma lucidum physiological response lag interval; S5, when in the Ganoderma lucidum physiological response lag interval, perform delay compensation processing on the real-time prediction value of the carbon dioxide concentration, apply an inhibition coefficient if the metabolic overload signal exists, and generate a compensated carbon dioxide concentration value; S6, perform synergistic influence analysis on the compensated carbon dioxide concentration value and the real-time prediction value of the light intensity, generate an environment regulation instruction, and drive an execution device to execute.

[0019] S1, real-time acquisition of carbon dioxide concentration and light intensity in the cultivation environment of Ganoderma lucidum, implementation as follows: The carbon dioxide concentration data in the cultivation environment is obtained by a carbon dioxide concentration sensor at a preset first sampling frequency, which is set to be collected once every 30 seconds according to the Ganoderma lucidum mycelium respiration cycle, for example, collected once every 20 seconds in the active period and once every 60 seconds in the dormant period. The measurement range of the carbon dioxide concentration sensor covers the range of 0 to 5000 ppm, and the environmental temperature value is recorded synchronously for subsequent data compensation calculation, and the temperature compensation mechanism is automatically activated when the environmental temperature exceeds 30 degrees Celsius.

[0020] The light intensity data is obtained by a light intensity sensor at a second sampling frequency, which is set to be collected once every 10 seconds to adapt to the rapid change characteristics of natural light, for example, automatically increased to once every 5 seconds in rainy weather. The spectral response range of the light intensity sensor is limited between 400 nanometers and 700 nanometers, consistent with the optimal absorption wavelength band of Ganoderma lucidum photosensitive pigment, and an optical diffuser is configured to eliminate the measurement deviation caused by the light incidence angle.

[0021] The carbon dioxide concentration data and light intensity data obtained by each collection are attached with time stamp marks accurate to milliseconds, and the time stamp generation adopts a high-precision clock module to ensure that the time synchronization error of different sensor data is controlled within 50 milliseconds. When there is electromagnetic interference in the collection environment, automatically switch to the standby clock source and record the clock offset. During the time stamp marking process, if abnormal sensor data is detected (for example, negative carbon dioxide concentration or light intensity exceeding 200,000 lux), an abnormality mark is attached to the record.

[0022] The timestamped carbon dioxide concentration data and light intensity data are stored to the distributed cache queue. The storage process performs the following operations: first, verify the validity of the data, automatically discard the collection record when the carbon dioxide concentration data exceeds the range of 0 to 5000 ppm; trigger the sensor calibration program when the light intensity data is lower than 0 lux; valid data is written in time sequence to the cache partition node, each partition node stores data blocks within a continuous 60-minute time period and marks the start and end timestamps. When the cache queue data backlog exceeds the set threshold (e.g. 10000 records), start the data compression storage mechanism and activate the backup storage channel.

[0023] The data in the cache queue has a default retention period of 7 days, and is automatically archived to the long-term storage system after the retention period. Real-time monitoring of the queue state during data storage, when the data write rate continuously exceeds the system processing capacity (e.g. 5000 per second for 3 seconds), send a traffic alarm signal to the monitoring system and dynamically adjust the sampling frequency. After each data processing is completed, clear the processed data entries and rebuild the index sequence to ensure that the subsequent processing unit obtains a complete time continuous data set.

[0024] S2, input the carbon dioxide concentration and light intensity into the Ganoderma lucidum growth digital twin to generate real-time prediction values, and implement the following: Read the timestamped carbon dioxide concentration data and light intensity data in time sequence from the distributed cache queue, the reading operation is performed in a 60-minute time window, which is set to correspond to the Ganoderma lucidum photosynthesis cycle. When the timestamp interval exceeds the preset collection period, perform data completion operation: generate missing data points using linear interpolation algorithm, interpolation is based on the numerical trend of the two valid data points before and after. Update the queue index state after reading to ensure that the subsequent processing obtains a complete time sequence.

[0025] The timestamped carbon dioxide concentration data is input into the carbon dioxide concentration prediction unit for processing, which includes three stages. First, perform data smoothing, using a sliding average method with dynamically adjusted window width: the window width is automatically adjusted according to the data fluctuation degree, when the standard deviation of 10 consecutive data points is less than 5 ppm, use a 10-point window, otherwise reduce to a 5-point window. Then identify the fluctuation characteristics, determine the periodicity by locating consecutive peaks and valleys, and the peak determination needs to meet the conditions of being higher than the previous three data points and the next three data points. Finally, perform prediction calculation, match similar fluctuation patterns in the historical database, preferentially select historical data of the same growth stage, and use the waveform correlation coefficient method for similarity matching, with a correlation coefficient threshold of 0.85.

[0026] The timestamped light intensity data is input into the light intensity prediction unit, defining the criteria for a light intensity mutation event: a change of more than 3000 lux within 10 seconds or a cumulative change of more than 5000 lux within 60 seconds. After feature extraction, the predicted value is corrected in combination with the real-time weather type, which is obtained through a meteorological data interface and converted into a light correction coefficient, for example, a sunny day coefficient of 1.0 and a cloudy day coefficient of 0.6. Pseudo-mutations caused by device malfunctions are excluded during processing, with the condition being that no reverse mutation occurs within 30 minutes after the mutation.

[0027] The calculation of the rate of change of carbon dioxide concentration is realized using the difference method. The length of the calculation window is dynamically determined based on environmental stability: when the maximum fluctuation of the last three data points is less than 20 ppm, an average change rate is calculated using 10 data points; otherwise, 5 data points are used to capture rapid change trends. The change rate is in units of ppm per minute, and the calculation result is rounded to two decimal places. Abnormal data points are processed using the neighborhood mean replacement method, with a neighborhood range of two valid data points before and after the abnormal point.

[0028] The generation of real-time prediction values for carbon dioxide concentration combines pattern matching and trend extrapolation techniques. In the pattern matching stage, similar fluctuation patterns with a similarity of more than 85% are retrieved from the historical database. In the trend extrapolation stage, a time decay weight strategy is used: the weight of the last three months of historical data is 0.6, and the weight of each year is multiplied by a decay coefficient of 0.8. The final prediction value is the weighted average, and the weight sum is normalized to 1.0. The prediction result is range-verified to ensure it is within a reasonable range of 200 ppm to 2000 ppm.

[0029] The generation of real-time prediction values for light intensity establishes a weather reference curve mechanism. Three types of basic weather curves are preset: a sunny day reference curve with a maximum value of 120000 lux, a cloudy day reference curve with a maximum value of 50000 lux, and a rainy day reference curve with a maximum value of 20000 lux. During real-time prediction, the similarity between the current weather state and the reference curve is determined through fuzzy matching, and a secondary verification is performed after generating the prediction value: if the prediction value exceeds the historical maximum value of the current season, it is reset to 95% of the historical maximum value.

[0030] The construction of the Ganoderma lucidum growth digital twin begins with the execution of historical data collection specifications. Environmental data is 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 includes outlier rejection and normalization: outliers are defined as data points exceeding 3 times the standard deviation; the normalization range is set to the historical minimum to maximum value interval of each parameter.

[0031] The recognition of diurnal concentration fluctuation characteristics uses a periodic analysis method. After removing high-frequency noise by moving average method, the peak and valley distribution in 24-hour cycle is detected. The characteristic parameters include: the peak occurrence time deviation is not more than 30 minutes, the valley depth difference is less than 15%, and the waveform correlation coefficient is greater than 0.9. The stable fluctuation characteristics need to meet the above conditions for three consecutive days.

[0032] The quantification parameters of light intensity mutation characteristics include: mutation trigger slope (lux per second), mutation duration (second), and recovery stage length (minute). The feature vector storage uses a structured database, and each record contains the mutation occurrence time, environmental temperature and humidity, and associated response parameters.

[0033] The establishment of association rules is based on statistical correlation analysis. The change response of carbon dioxide concentration in a certain time window after light mutation is analyzed: the observation window of sudden rise type event is 30 minutes, and the observation window of slow decline type event is 120 minutes. The rule validity needs to meet: support greater than 50 samples, confidence more than 75%. The rule storage format is condition-result structure, for example, "light sudden rise event → carbon dioxide concentration drop 200±50ppm".

[0034] The response mechanism configuration of carbon dioxide concentration prediction unit includes parameter calibration. The rule weight is calculated according to the historical verification accuracy: the weight increases by 0.2 for every 10% increase in accuracy. The response trigger threshold is set to 80% through matching degree-accuracy balance analysis. The response execution uses a gradual influence strategy: the initial weight of rule prediction value is 0.3, and it is dynamically increased to the maximum weight of 0.8 according to real-time matching degree.

[0035] The reverse matching mechanism of light intensity prediction unit introduces time delay calibration. Through historical data analysis of the time lag relationship between carbon dioxide change and light response, the typical delay time is determined to be 20 to 40 minutes. A delay time-confidence mapping table is established: the confidence is 0.85 when the delay is 30 minutes, and the confidence is 0.75 when the delay is 40 minutes. Rules with a confidence lower than 0.6 need to be verified in conjunction with other indicators.

[0036] The coupling of the two prediction units realizes data interaction and weight coordination. The intermediate prediction results and confidence indicators are exchanged every 5 minutes. The dynamic weight adjustment algorithm is based on the environmental stability index, which is defined as the ratio of the variance of the last 1 hour data to the variance of the historical baseline. The main prediction unit weight calculation formula is: main prediction unit weight = 0.5 + 0.3 × (1 - environmental stability index), and the auxiliary unit weight is complementary to 1.

[0037] Figure 2A flowchart of the activation mechanism of the Ganoderma intracellular oxidative stress marker is given, S3, the matching degree of the carbon dioxide concentration change rate and the mycelium respiration entropy is generated in the Ganoderma growth digital twin, and the intracellular active oxygen accumulation curve is simulated based on the carbon dioxide concentration change rate and the light intensity. When the rising rate of the curve exceeds the growth rate of the matching degree, the oxidative stress marker is activated, and the following is implemented: The carbon dioxide concentration change rate data calculated by the Ganoderma growth digital twin in real time is obtained, which is in units of ppm per minute and updated every minute. The carbon dioxide concentration change rate has been obtained in step S2, and its value comes from the output result of the carbon dioxide concentration prediction unit.

[0038] The operation of determining the mycelium respiration entropy value according to the carbon dioxide concentration change rate is performed according to the following process: a mycelium oxygen consumption rate reference value control table is generated in advance, which is constructed through standard cultivation experiments. The construction process is: in a controlled environment with a temperature of 25±1 degrees Celsius and a humidity of 85%±5%, the mycelium oxygen consumption rate corresponding to each 20 ppm per minute increase in carbon dioxide concentration change rate is measured; 50 experiments are repeated for each rate interval, for example, 50 sets of oxygen consumption data are measured in the 0 to 20 ppm / minute interval; the arithmetic mean of the oxygen consumption rate in each interval is calculated as the reference value; the control table is stored in the form of a database table, containing two columns of "concentration change interval" and "reference oxygen consumption rate". When determining the mycelium respiration entropy value, the current carbon dioxide concentration change rate value is detected, the interval range it belongs to is matched (for example, the current value 25 ppm / minute matches the 20-40 ppm / minute interval), and the corresponding mycelium oxygen consumption rate reference value is extracted from the control table, which is directly output as the mycelium respiration entropy value. When the concentration change rate exceeds the range of the control table, the nearest neighbor interval reference value is used.

[0039] The deviation of the current mycelium respiration entropy value from the reference respiration entropy value is calculated as the matching degree. The reference respiration entropy value is dynamically set according to the growth stage of Ganoderma: the reference value in the mycelium growth period is set to 50 milliliters of oxygen per gram of dry weight per hour, the original base formation period is set to 65 milliliters, and the fruiting body development period is set to 80 milliliters. The matching degree is calculated using the relative deviation formula: matching degree = (current mycelium respiration entropy value - reference respiration entropy value) ÷ reference respiration entropy value x 100%, and the calculation result is in the form of integer percentage. When the absolute value of the matching degree exceeds 20%, an abnormality flag is triggered.

[0040] Synchronization monitoring of the cooperative change trend between the carbon dioxide concentration change rate and the real-time predicted value of light intensity, the monitoring process performs: taking 5 minutes as a fixed time window, recording a group of data pairs (carbon dioxide concentration change rate value, real-time predicted value of light intensity) every minute; calculating the covariance change amount of adjacent time window data pairs; when the signs of the covariance of the last three time windows remain the same, it is determined that there is a stable cooperative change trend; the trend type is divided into positive cooperation (both change in the same direction) and negative cooperation (both change in opposite directions), for example, when the carbon dioxide concentration rises, the light intensity increases, which is recorded as positive cooperation. If the covariance sign is unstable, the default neutral trend type is used.

[0041] According to the cooperative change trend, the intracellular reactive oxygen accumulation level is obtained by querying the active oxygen accumulation mapping table. The mapping table construction rule is: set the basic accumulation level = the absolute value of the carbon dioxide concentration change rate ÷ 10 (unit: accumulation unit), for example, 30 ppm / min corresponds to 3 units of basic accumulation; define the trend correction coefficient: positive cooperation coefficient 1.2, negative cooperation coefficient 0.8, neutral trend coefficient 1.0; the final accumulation level = the basic accumulation level × the trend correction coefficient. The accumulation unit is defined as 0.1 μmol / g of reactive oxygen species per minute under standard conditions. When querying, first determine the current cooperative trend type, and then calculate the accumulation level value combined with the real-time carbon dioxide concentration change rate.

[0042] The accumulation curve of the intracellular reactive oxygen accumulation level changing with time is generated, and the curve construction process is: recording the current accumulation level value every minute; using linear interpolation method to connect adjacent time point data to form a continuous curve; the horizontal axis of the curve is time (unit: minute), and the vertical axis is accumulation level (unit: accumulation unit); the time range of the curve covers the last 60 minutes, and a complete curve snapshot is saved every 5 minutes. The key parameters of the curve include: current value, average change rate in the last 10 minutes, recent peak value and occurrence time.

[0043] The condition for activating the oxidative stress marker performs the following operations: calculating the rising amplitude increment of the accumulation curve in the last 5 minutes (current accumulation level value-accumulation level value 5 minutes ago); synchronously calculating the growth of the matching degree in the same period (current matching degree percentage-matching degree percentage 5 minutes ago); when the rising amplitude increment value is greater than the matching degree growth, send an activation instruction to the control system; the activation state lasts for 30 minutes and then automatically resets. The judgment process sets a fault tolerance mechanism: it needs to meet the condition for two consecutive detection periods (i.e. two consecutive minute detections) to execute the activation, to avoid false triggering.

[0044] S4, when the matching degree exceeds the set threshold and there is an oxidative stress marker, a metabolic overload signal is generated, and it is judged whether the real-time predicted value of the carbon dioxide concentration is in the ganoderma physiological response lag interval, and the following is implemented: The matching degree data generated by the Ganoderma lucidum growth digital twin and the oxidative stress marker state data are obtained, wherein the matching degree data is expressed in percentage and updated every minute; the oxidative stress marker state is a Boolean variable with two states: activated and inactivated. These two data are transmitted to the processing unit in real time through shared memory area, and the transmission delay is controlled within 50 milliseconds.

[0045] When the matching degree value exceeds the preset matching degree threshold and the oxidative stress marker is in the activated state, the 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 to 15% in the mycelium growth period, 20% in the primordium formation period, and 25% in the fruiting body development period. The threshold setting is based on the analysis of historical cultivation data of each stage of metabolic abnormal events to determine the metabolic imbalance critical point and set a safety margin of 5%. For example, in the mycelium growth period, experimental data shows that metabolic disorder occurs when the matching degree reaches 20%, so the matching degree threshold is set to 15%. When the metabolic overload signal is generated, the trigger timestamp and the current matching degree value are recorded, and the signal is continuously output until the matching degree falls below the matching degree threshold and the oxidative stress marker resets to the inactivated state.

[0046] The carbon dioxide concentration real-time prediction value is read synchronously, which is derived from the output result of the carbon dioxide concentration prediction unit of the Ganoderma lucidum growth digital twin, with the unit of ppm and the update frequency of once per minute. When reading, data validity check is performed: if the carbon dioxide concentration real-time prediction value exceeds the range of 0 to 5000 ppm, the moving average of the previous three valid carbon dioxide concentration real-time prediction values is used instead, and the moving average calculation window is 3 data points.

[0047] Query the carbon dioxide concentration adaptive range corresponding to the current growth stage in the preset Ganoderma lucidum physiological response characteristic library. The Ganoderma lucidum physiological response characteristic library data structure includes the following fields: growth stage code field, mycelium growth period code is 1, primordium formation period code is 2, and fruiting body development period code is 3; carbon dioxide concentration adaptive range lower limit value field, unit: ppm; carbon dioxide concentration adaptive range upper limit value field, unit: ppm; lag boundary left boundary value field, unit: ppm; lag boundary right boundary value field, unit: ppm. The construction method of Ganoderma lucidum physiological response characteristic library is: under the standard cultivation conditions of temperature 25±1 degrees Celsius and humidity 85%±5%, measure the carbon dioxide concentration interval at which the physiological activity of Ganoderma lucidum in each growth stage remains above 90% as the carbon dioxide concentration adaptive range; through the carbon dioxide concentration step change experiment, determine the concentration boundary with a physiological response delay of more than 5 minutes as the lag boundary. For example, in the mycelium growth period, the carbon dioxide concentration adaptive range is recorded as 800 to 1200 ppm, and the lag boundary interval is recorded as 880 to 1120 ppm. When querying, the corresponding record is retrieved according to the real-time growth stage code.

[0048] Determine whether the real-time predicted value of the carbon dioxide concentration is located within the lag boundary interval of the carbon dioxide concentration adaptive range. The judgment logic is: if the condition "lag boundary left boundary value ≤ real-time predicted value of carbon dioxide concentration ≤ lag boundary right boundary value" is met, it is determined to be in the lag interval. The boundary value adopts the closed interval inclusion rule, for example, when the real-time predicted value of the carbon dioxide concentration is 880 ppm, it is considered to enter the lag zone. The judgment process sets a fault tolerance mechanism: when the real-time predicted value of the carbon dioxide concentration is located within the lag boundary interval for three consecutive detections, it is finally confirmed to enter the lag state.

[0049] The setting of the lag boundary interval calculation rule is based on the general law of Ganoderma lucidum physiological response characteristics: when the environmental parameters mutate, the mycelium growth period has weaker adaptability to carbon dioxide concentration fluctuations, and a wider buffer interval needs to be set. Specifically, a 1.1 times lower limit coefficient and a 0.9 times upper limit coefficient are used, so that the boundary range is expanded by about 10% compared to the actual adaptive range (for example, the 800-1200 ppm adaptive range corresponds to the 880-1080 ppm lag boundary). Due to the enhanced metabolic stability in other growth stages, the boundary range is narrowed to a 5% expansion range (800-1200 ppm corresponds to 840-1140 ppm). This proportion setting conforms to the general understanding of plant physiology that young organisms are more sensitive to environmental mutations. In actual application, the expansion ratio can be adjusted within the range of 5% to 15% according to the characteristics of the cultivated variety, for example, a variety sensitive to fluctuations can use a 12% expansion coefficient. The boundary value calculation always follows the unified formula "lag boundary left boundary value = adaptive range lower limit value × (1 + expansion coefficient), lag boundary right boundary value = adaptive range upper limit value × (1 - expansion coefficient)", and the expansion coefficient value is determined by cultivation experts according to the variety profile.

[0050] When the real-time prediction value of carbon dioxide concentration is within the hysteresis boundary interval, the current environmental state is marked as being in the Ganoderma lucidum physiological response hysteresis interval. The marked state is a global variable that is valid until the real-time prediction value of carbon dioxide concentration exceeds the hysteresis boundary interval and remains inconsistent with the hysteresis condition for five consecutive detections (i.e., 5 minutes). The following parameters are recorded synchronously when the state is marked: timestamp of entering the hysteresis interval, current real-time prediction value of carbon dioxide concentration, and growth phase code. The state exit condition is that the real-time prediction value of carbon dioxide concentration exceeds the hysteresis boundary interval range for five consecutive detections.

[0051] S5, when in the Ganoderma lucidum physiological response hysteresis interval, performing delay compensation processing on the real-time prediction value of carbon dioxide concentration, applying an inhibition coefficient if there is a metabolic overload signal, generating a compensated carbon dioxide concentration value, and implementing the following: Confirm the marked state of the Ganoderma lucidum physiological response hysteresis interval, which is a Boolean global variable generated and stored in the shared memory area by step S4. The state detection operation is performed every minute, and when the marked state is "in the Ganoderma lucidum physiological response hysteresis interval", the compensation processing flow of the real-time prediction value of carbon dioxide concentration is triggered. The validity of the marked state lasts until the exit condition defined in step S4 is met, i.e., when the real-time prediction value of carbon dioxide concentration exceeds the hysteresis boundary interval for five consecutive detections, the state is automatically released.

[0052] Perform time translation compensation processing on the real-time prediction value of carbon dioxide concentration. The specific operation flow is as follows: first, obtain the real-time prediction value of carbon dioxide concentration at the current time, which is in ppm; then query the hysteresis time parameter corresponding to the current growth phase in the preset feature library, which is in minutes; then shift the real-time prediction value of carbon dioxide concentration forward by the hysteresis time parameter. The hysteresis time parameter is determined by the following method: under standard cultivation conditions, perform a carbon dioxide concentration step change experiment, measure the physiological response delay time of Ganoderma lucidum mycelium at each growth stage, and take the median value of the delay time of 20 repeated experiments as the compensation amount. For example, in the mycelial growth phase, the median hysteresis time measured by the experiment is 8 minutes, so the current real-time prediction value of carbon dioxide concentration is replaced by the historical prediction value 8 minutes ago. When performing compensation, if the historical data at the target time is missing, use linear extrapolation to reconstruct the value based on the last three valid data points.

[0053] Synchronize the detection of the presence of metabolic overload signals, which is a Boolean variable. When accessing the real-time state bit of the signal register, if the state bit is "activated", it is determined that there is a metabolic overload signal. The association between the duration of the metabolic overload signal and the matching degree threshold and the oxidative stress flag has been defined in the previous steps.

[0054] When a metabolic overload signal is present, the corresponding CO2 concentration inhibition coefficient is retrieved from the cultivation database. This database uses a relational data structure and contains three key fields: a growth stage code (code 1 for mycelial growth, 2 for primordium formation, and 3 for fruiting body development); a metabolic overload level field (classified as mild, moderate, and severe); and a CO2 concentration inhibition coefficient field (ranging from 0.7 to 1.0). The CO2 concentration inhibition coefficient is determined by conducting controlled experiments in a controlled environment, measuring the CO2 tolerance decay rate of Ganoderma lucidum under varying levels of metabolic overload and converting the decay rate into an inhibition coefficient. For example, during the mycelial growth period, when the metabolic overload is moderate (a match exceeds a threshold of 5% to 10%), the experimentally measured tolerance decay rate is 15%, corresponding to a CO2 concentration inhibition coefficient of 0.85. Database access uses a "growth stage code + metabolic overload level" key combination query.

[0055] The CO2 concentration suppression coefficient is applied to the CO2 concentration value after time-shift compensation via a multiplication operation: Compensated CO2 concentration = Time-shift compensation value × CO2 concentration suppression coefficient. This calculation implements strict range validation: if the calculated result is less than 200 ppm, it is set to 200 ppm, corresponding to the minimum concentration requirement for Ganoderma lucidum survival; if the calculated result is greater than 5000 ppm, it is set to 5000 ppm, the upper limit of the sensor's range. The result is rounded to one decimal place, and the unit remains unchanged in ppm.

[0056] Generates a compensated CO2 concentration value after applying the CO2 suppression coefficient. This value is written to the environmental control bus as the final output. The following metadata is recorded simultaneously with the output: the original real-time CO2 concentration prediction value, the time shift compensation amount (in minutes), the CO2 suppression coefficient, and the timestamp of the application operation. The output frequency is synchronized with the input data, updating once every minute. When the Lingzhi physiological response hysteresis interval flag is exited, this process automatically terminates, and the system resumes directly outputting the real-time CO2 concentration prediction value.

[0057] S6. Perform a synergistic impact analysis on the compensated carbon dioxide concentration value and the real-time predicted light intensity value, generate an environmental control instruction, and drive the execution device to execute it. The implementation is as follows: Obtain the compensated CO2 concentration value generated in step S5 and the real-time light intensity prediction value generated in step S2. The compensated CO2 concentration value is in ppm, and the real-time light intensity prediction value is in lux. Both values ​​are updated synchronously every minute. The data transmission process uses a CRC-16 checksum mechanism. If the checksum fails, the median value of the last three valid data points is automatically retransmitted to ensure data integrity.

[0058] query the carbon dioxide concentration value corresponding to the carbon dioxide regulation intensity level in the environmental factor coordination rule base. The environmental factor coordination rule base is constructed by the following method: a three-year cultivation experiment is carried out under standard cultivation environment (temperature 25±1 degrees Celsius, humidity 85%±5%), the biomass growth rate curve of ganoderma lucidum in different carbon dioxide concentration intervals is recorded, and the concentration is divided into five regulation levels according to the curve inflection point: 0-400ppm is the lowest level, 400-800ppm is the low level, 800-1200ppm is the medium level, 1200-1600ppm is the high level, and 1600ppm or more is the very high level. For example, when the compensated carbon dioxide concentration value is 1000ppm, the "medium" level is obtained by querying. The rule base is stored in tables according to the growth stage of ganoderma lucidum, and the data table corresponding to the current growth stage is automatically matched during querying, and if the stage recognition fails, the mycelium growth period data table is used by default.

[0059] query the light intensity real-time prediction value corresponding to the light regulation intensity level in the environmental factor coordination rule base. The light intensity level is divided according to the following: the photosynthetic efficiency curve of each growth stage is determined by the light saturation point experiment, and the light intensity is divided into four levels: 0-20000 lux is weak light level, 20000-40000 lux is moderate level, 40000-60000 lux is strong light level, and 60000 lux or more is very strong light level. For example, when the light intensity real-time prediction value is 45000 lux, the "strong light" level is obtained by querying. The boundary value setting rule of the level is that the upper limit of the weak light level 20000 lux corresponds to the light compensation point of the mycelium growth period, and the upper limit of the strong light level 60000 lux corresponds to the light inhibition threshold of the fruiting body period.

[0060] The synergistic regulation mode is determined according to the combination relationship of the carbon dioxide regulation intensity level and the light regulation intensity level. The synergistic regulation mode is divided into six basic types, and the matching rules are as follows: when the carbon dioxide regulation intensity level is low and the light regulation intensity level is weak light, the A type maintenance mode is adopted; when the carbon dioxide regulation intensity level is medium and the light regulation intensity level is moderate, the B type optimization mode is adopted; when the carbon dioxide regulation intensity level is high and the light regulation intensity level is strong light, the C type inhibition mode is adopted; when the carbon dioxide regulation intensity level is very high, no matter what the light regulation intensity level is, the D type emergency ventilation mode is adopted; when the light regulation intensity level is very strong, no matter what the carbon dioxide regulation intensity level is, the E type shading mode is adopted; when the carbon dioxide regulation intensity level is low and the light regulation intensity level is strong light, the F type balance mode is adopted. For example, when the carbon dioxide regulation intensity level is high and the light regulation intensity level is strong light, the C type inhibition mode is determined. The mode matching matrix is verified by orthogonal experiment, and each combination is supported by not less than 200 groups of cultivation data, with a confidence degree of 95%.

[0061] Based on the synergistic regulation mode, an environment regulation instruction set containing a ventilation equipment opening degree instruction and a light supplement equipment power instruction is generated. The instruction generation rule is specifically: ventilation equipment opening degree instruction = basic opening degree value x mode coefficient, wherein the basic opening degree value is calculated according to the cultivation space volume, and the calculation formula is cultivation space volume (m3) x 3%, for example, the basic opening degree value of 10 m3 space is 30%; the mode coefficient is preset as: A type mode coefficient 1.0, B type mode coefficient 0.8, C type mode coefficient 1.2, D type mode coefficient 1.5, E type mode coefficient 0.5, and F type mode coefficient 0.9. Light supplement equipment power instruction = rated power x mode coefficient, and the rated power is 80% of the nominal maximum power of the light supplement equipment. Boundary check is performed when the instruction is generated: the ventilation equipment opening degree instruction is limited in the range of 0% to 100%, and the light supplement equipment power instruction does not exceed 90% of the rated power of the equipment.

[0062] The environmental regulation instruction set is sent to an environmental regulation execution device to perform an operation. The sending protocol adopts a Modbus-RTU standard, and a data frame structure comprises a device address code (1 byte), a function code (1 byte), an instruction data field (4 bytes, comprising an opening degree instruction value and a power instruction value), and a CRC check code (2 bytes). The execution device comprises two types of ventilation devices and light supplement devices: after the ventilation device receives the opening degree instruction, the opening degree is adjusted to the target value within 10 seconds at a gradual change rate of not more than 5% opening degree per second; after the light supplement device receives the power instruction, the output power is adjusted to the target value within 30 seconds at a gradual change rate of not more than 2% power per second. After the execution is completed, the device needs to return a state confirmation code within 20 seconds. If the timeout is not responded, a retransmission mechanism is started, and a maximum of three retries are performed; if the three retransmissions all fail, a device fault log is recorded and a backup control strategy is enabled.

[0063] The calculation involved in the embodiments is a de-dimensioned numerical calculation, and preset parameters and threshold values in the calculation are set by a person skilled in the art according to actual conditions.

[0064] It should be noted that the present application can be deployed in the device itself to realize embedded application, or can be run on a PC terminal or other terminal with a user interface, so as to meet various hardware environments and use requirements.

[0065] The above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. 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 through wireless or wired transmission. The wired transmission includes optical fiber, twisted pair, coaxial cable, etc. The wireless transmission includes infrared, microwave, etc. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), optical medium (for example, DVD), or semiconductor medium. The semiconductor medium can be a solid state disk.

[0066] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and module described above can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0067] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. In actual implementation, another division mode can be used. For example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0068] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, which can be located in one place or distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0069] In addition, the functional modules in each embodiment of the present application can be integrated in one processing module, or each module can exist physically, or two or more modules can be integrated in one module.

[0070] If the functions are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0071] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0072] Finally, the above merely provides the preferred embodiments of the present application, but is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A multi-factor coupling ganoderma environment digital twin regulation method for high yield demand, characterized in that, The method comprises the following steps: S1, real-time collection of carbon dioxide concentration and light intensity in the cultivation environment of Ganoderma lucidum; S2, inputting the carbon dioxide concentration and light intensity into the Ganoderma lucidum growth digital twin to generate real-time prediction values; S3, generating the matching degree of the carbon dioxide concentration change rate and the mycelium respiration entropy in the Ganoderma lucidum growth digital twin, and simulating the intracellular active oxygen accumulation curve based on the carbon dioxide concentration change rate and the light intensity, and activating the oxidative stress marker when the rising rate of the curve exceeds the growth rate of the matching degree; S4, generating a metabolic overload signal when the matching degree exceeds the set threshold and the oxidative stress marker exists, and simultaneously judging whether the real-time prediction value of the carbon dioxide concentration is in the Ganoderma lucidum physiological response lag interval; S5, performing delay compensation processing on the real-time prediction value of the carbon dioxide concentration when it is in the Ganoderma lucidum physiological response lag interval, applying an inhibition coefficient if the metabolic overload signal exists, and generating a compensated carbon dioxide concentration value; S6, performing synergistic influence analysis on the compensated carbon dioxide concentration value and the real-time prediction value of the light intensity, generating an environment regulation instruction, and driving an execution device to execute.

2. The high-yield demand-oriented multi-factor coupled lucidum environment digital twin regulation method according to claim 1, characterized in that, Real-time collection of carbon dioxide concentration and light intensity in the cultivation environment of Ganoderma lucidum comprises: acquiring carbon dioxide concentration data at a first sampling frequency through a carbon dioxide concentration sensor; acquiring light intensity data at a second sampling frequency through a light intensity sensor; appending timestamp labels to the carbon dioxide concentration data and the light intensity data; storing the timestamped carbon dioxide concentration data and light intensity data to a distributed cache queue.

3. The high-yield demand-oriented multi-factor coupled lucidum environment digital twin regulation method according to claim 2, characterized in that, Inputting the carbon dioxide concentration and light intensity into the Ganoderma lucidum growth digital twin to generate real-time prediction values comprises: reading the timestamped carbon dioxide concentration data and light intensity data from the distributed cache queue; inputting the timestamped carbon dioxide concentration data into the carbon dioxide concentration prediction unit of the Ganoderma lucidum growth digital twin; inputting the timestamped light intensity data into the light intensity prediction unit of the Ganoderma lucidum growth digital twin; calculating the carbon dioxide concentration change rate through the Ganoderma lucidum growth digital twin; generating the real-time prediction values of the carbon dioxide concentration and the light intensity through the Ganoderma lucidum growth digital twin.

4. The high-yield demand-oriented multi-factor coupled lucidum environment digital twin regulation method according to claim 3, characterized in that, The Ganoderma lucidum growth digital twin is established by the following methods: collecting continuously recorded carbon dioxide concentration time series data and light intensity time series data in a historical cultivation period; identifying the repeatedly occurring diurnal concentration fluctuation characteristics in the carbon dioxide concentration time series data; extracting the intensity mutation characteristics caused by weather changes in the light intensity time series data; establishing the association rules of the carbon dioxide concentration fluctuation characteristics and the light intensity mutation characteristics; configuring the response mechanism of the carbon dioxide concentration prediction unit based on the association rules; configuring the response mechanism of the light intensity prediction unit based on the association rules; combining the carbon dioxide concentration prediction unit and the light intensity prediction unit to form the Ganoderma lucidum growth digital twin.

5. The high-yield demand-oriented multi-factor coupled lucidum environment digital twin regulation method according to claim 3, characterized in that, Generating the matching degree of the carbon dioxide concentration change rate and the mycelium respiration entropy in the Ganoderma lucidum growth digital twin, and simulating the intracellular active oxygen accumulation curve based on the carbon dioxide concentration change rate and the light intensity, and activating the oxidative stress marker when the rising rate of the curve exceeds the growth rate of the matching degree, comprises: acquiring the carbon dioxide concentration change rate; Determine the mycelium respiration entropy value according to the correspondence between the carbon dioxide concentration change rate and the preset mycelium oxygen consumption rate; The deviation of the current mycelium respiration entropy value from the reference respiration entropy value is used as the matching degree; Synchronously monitor the cooperative change trend of the carbon dioxide concentration change rate and the real-time predicted value of the light intensity; According to the cooperative change trend, query the corresponding intracellular reactive oxygen accumulation level in the reactive oxygen accumulation mapping table; Generate an accumulation curve reflecting the change of intracellular reactive oxygen accumulation level over time; When the rising amplitude increment of the accumulation curve exceeds the matching degree growth, activate the oxidative stress flag.

6. The high-yield-oriented multi-factor coupled lucidum environment digital twin regulation method of claim 5, wherein, Determine the mycelium respiration entropy value according to the correspondence between the carbon dioxide concentration change rate and the preset mycelium oxygen consumption rate, including: Pre-store the mycelium oxygen consumption rate reference value control table corresponding to different carbon dioxide concentration change rate intervals; Detect the interval to which the current carbon dioxide concentration change rate belongs, and extract the corresponding mycelium oxygen consumption rate reference value from the mycelium oxygen consumption rate reference value control table; Output the mycelium oxygen consumption rate reference value as the mycelium respiration entropy value.

7. The high-yield-oriented multi-factor coupled lucidum environment digital twin regulation method of claim 5, wherein, When the matching degree exceeds the set threshold and there is an oxidative stress flag, generate a metabolic overload signal, and at the same time judge whether the real-time predicted value of the carbon dioxide concentration is in the Ganoderma lucidum physiological response lag interval, including: Obtain the matching degree and oxidative stress flag; When the matching degree exceeds the preset matching degree threshold and the oxidative stress flag is in the activated state, generate a metabolic overload signal; Synchronously read the real-time predicted value of the carbon dioxide concentration; Query the carbon dioxide concentration adaptation range corresponding to the current growth stage in the preset Ganoderma lucidum physiological response feature library; Determine whether the real-time predicted value of the carbon dioxide concentration is located in the lag boundary interval of the carbon dioxide concentration adaptation range; When the real-time predicted value of the carbon dioxide concentration is located in the lag boundary interval, mark it as being in the Ganoderma lucidum physiological response lag interval.

8. The high-yield-oriented multi-factor coupled lucidum environment digital twin regulation method of claim 7, wherein, When in the Ganoderma lucidum physiological response lag interval, perform delay compensation processing on the real-time predicted value of the carbon dioxide concentration, and if there is a metabolic overload signal, apply an inhibition coefficient to generate a compensated carbon dioxide concentration value, including: Confirm the marking state of the Ganoderma lucidum physiological response lag interval; When the marking state is in the Ganoderma lucidum physiological response lag interval, perform time shift compensation processing on the real-time predicted value of the carbon dioxide concentration; Detect whether there is a metabolic overload signal; When there is a metabolic overload signal, read the corresponding carbon dioxide concentration inhibition coefficient from the cultivation database; Apply the carbon dioxide concentration inhibition coefficient to the carbon dioxide concentration value after time shift compensation processing; Generate the compensated carbon dioxide concentration value after applying the carbon dioxide concentration inhibition coefficient.

9. The high-yield-oriented multi-factor coupled ganoderma environment digital twin regulation method of claim 8, wherein, Perform cooperative influence analysis on the compensated carbon dioxide concentration value and the real-time predicted value of the light intensity, generate environment regulation instructions and drive the execution equipment to execute, including: Obtain the compensated carbon dioxide concentration value and the real-time predicted value of the light intensity; Query the carbon dioxide regulation intensity level corresponding to the compensated carbon dioxide concentration value in the environment factor cooperative rule library; Query the light regulation intensity level corresponding to the real-time predicted value of the light intensity in the environment factor cooperative rule library; Determine the cooperative regulation mode according to the combination relationship between the carbon dioxide regulation intensity level and the light regulation intensity level; Generate an environment regulation instruction set containing the opening degree instruction of the ventilation equipment and the power instruction of the light supplement equipment based on the synergistic regulation mode; Send the environment regulation instruction set to the environment regulation execution equipment to execute the operation.

Citation Information

Patent Citations

  • A method for obtaining two-dimensional joint regulation target region based on regulation benefit priority

    CN109102420A

  • Greenhouse plant regulation and control method with optimal efficiency for carbon neutralization demand

    CN113625806A

  • Facility light and carbon dioxide environment cooperative regulation and control method

    CN115226516A

  • Stable metabonomics detection method based on metabolic state recognition

    CN115389555A

  • Lucid ganoderma cultivation environment multi-mode self-adaptive regulation and control method based on Internet of Things

    CN120178994A

Cited By

  • A Method and System for Correcting Construction Environment Monitoring Data Based on Multi-Sensor Fusion

    CN122487194A

  • Construction environment monitoring data correction method and system based on multi-sensor fusion

    CN122487194B