Method and system for self-adaptive regulation of CO2 concentration in mushroom growth stage

Abstract

The application relates to a mushroom growth stage CO2 concentration self-adaptive regulation method and system, and the mushroom growth stage CO2 concentration self-adaptive regulation method comprises the following steps: constructing a CO2 tolerance threshold database of mushrooms; acquiring real-time growth data of the mushrooms, identifying a current growth stage of the mushrooms based on the real-time growth data; acquiring a CO2 tolerance threshold of the current growth stage of the mushrooms from the CO2 tolerance threshold database; and based on the acquired CO2 tolerance threshold of the current growth stage of the mushrooms, self-adaptively regulating the CO2 concentration in the mushroom growth environment. The application can realize self-adaptive regulation of the CO2 concentration in the mushroom growth environment according to the growth stage of the mushrooms, can realize automatic and collaborative optimization of nutrient accumulation in the mushroom mycelium stage and high-quality growth in the fruiting body stage, can significantly reduce energy consumption and labor cost, and can improve the stability and economic benefits of mushroom production.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence design, in particular to a method and system for self-adaptive regulation of CO2 concentration in mushroom growth stages. BACKGROUND

[0002] Mushrooms (such as edible mushrooms) have significant differences in CO2 concentration requirements at different growth stages. Mycelium stage requires a higher concentration of CO2 (usually tolerable range of 0.1%-0.3%) to promote nutrient accumulation, while the fruiting body stage is very sensitive to CO2 concentration (needs to be controlled at 0.03%-0.1%), and too high a concentration will cause the fruiting body to be deformed or growth to stop. Currently, traditional CO2 concentration regulation methods mainly rely on human experience, and there are two main problems in relying on human experience to regulate CO2 concentration: in the mycelium stage, excessive ventilation will result in too low CO2 concentration, affecting the nutrient accumulation of mycelium; in the fruiting body stage, continuous high ventilation can reduce CO2 concentration, but will cause large fluctuations in temperature and humidity, not only affecting the growth quality of mushrooms, but also causing energy waste. These problems have become a key bottleneck restricting the efficiency and economic benefit of mushroom large-scale production. SUMMARY

[0003] Therefore, it is necessary to provide a method and system for self-adaptive regulation of CO2 concentration in mushroom growth stages to solve the problems in the related art.

[0004] To achieve the above purpose, in a first aspect, the present application provides a method for self-adaptive regulation of CO2 concentration in mushroom growth stages, which includes a mycelium stage and a fruiting body stage. The method comprises:

[0005] constructing a CO2 tolerance threshold database of mushrooms, including: obtaining historical growth data of mushrooms, the historical growth data including mycelium dry weight in the mycelium stage and fruiting body morphological indicators in the fruiting body stage under different CO2 concentrations; based on the historical growth data, using an improved Gaussian process regression algorithm to obtain expected values and confidence intervals of growth efficiency of mushrooms corresponding to different CO2 concentrations; based on the expected values and the confidence intervals, using NSGA-II optimization to obtain CO2 tolerance thresholds of the mycelium stage and the fruiting body stage, thereby obtaining the CO2 tolerance threshold database of mushrooms;

[0006] obtaining real-time growth data of mushrooms, and identifying the current growth stage of mushrooms based on the real-time growth data;

[0007] obtaining the CO2 tolerance threshold of the current growth stage of mushrooms from the CO2 tolerance threshold database;

[0008] Based on the CO2 tolerance threshold of the mushroom at its current growth stage, the CO2 concentration in the mushroom growth environment is adaptively regulated.

[0009] In some embodiments, acquiring real-time growth data of the mushrooms and identifying the current growth stage of the mushrooms based on the real-time growth data includes:

[0010] The mycelial density index and primordium number of mushrooms were obtained as real-time growth data for mushrooms.

[0011] A time window for the mycelial stage is set. Within the time window, if the mycelial density index is greater than a preset threshold and the number of primordia is greater than or equal to a preset number, the mushroom is determined to have entered the fruiting body stage; otherwise, the mushroom is determined to be in the mycelial stage. If, at the end of the time window for the mycelial stage, the mycelial density index is still less than or equal to a preset threshold and / or the number of primordia is still less than a preset number, the mushroom is still determined to have entered the fruiting body stage.

[0012] In some embodiments, if the mycelial density index is still less than or equal to a preset threshold and / or the number of primordia is still less than a preset number when the mycelial stage time window ends, and the mushroom is still determined to have entered the fruiting body stage, the method further includes: activating an abnormal alarm.

[0013] In some embodiments, the kernel function used to obtain the expected values ​​and confidence intervals of mushroom growth efficiency corresponding to different CO2 concentrations is as follows:

[0014]

[0015] in, For kernel function, α As a stage weighting factor, x This is the first CO2 concentration sample. This is the second CO2 concentration sample. Let Euclidean distance be the distance between samples. l For length scale, Standard deviation of concentration fluctuation; mycelial stage, stage weighting factor α =0.7, sub-entity stage, stage weight factor α =0.3.

[0016] In some embodiments, based on the expected growth efficiency and the confidence interval, NSGA-II optimization is used to obtain the CO2 tolerance thresholds for the mycelial and fruiting body stages, including:

[0017] Construct a dual-objective optimization function based on Pareto optimal front theory:

[0018]

[0019] in, This represents the expected growth efficiency corresponding to the maximum CO2 concentration. The confidence interval for minimum growth efficiency;

[0020] Set the following constraints:

[0021]

[0022] in, μ This represents the expected growth efficiency. μ max To obtain the maximum growth efficiency within the current growth stage using an improved Gaussian process regression algorithm, σ represents the confidence interval, and ∧ represents the logical AND operator;

[0023] Based on the aforementioned constraints, the NSGA-II algorithm is used to solve the optimal solution of the biobjective optimization function to obtain the CO2 tolerance thresholds for the mycelial stage and the fruiting body stage.

[0024] In some embodiments, the CO2 concentration in the mushroom growth environment is adaptively controlled based on the obtained CO2 tolerance threshold of the current growth stage of the mushroom, including:

[0025] Obtain the real-time CO2 concentration in the mushroom growth environment;

[0026] The CO2 concentration deviation is obtained based on the real-time CO2 concentration in the mushroom growth environment and the CO2 tolerance threshold of the mushroom at the current growth stage.

[0027] The ventilation duration is obtained based on the CO2 concentration deviation.

[0028] Ventilation is performed on the mushroom growth environment based on the ventilation duration to adaptively regulate the CO2 concentration in the mushroom growth environment.

[0029] In some embodiments, the formula for obtaining the CO2 concentration deviation based on the real-time CO2 concentration in the mushroom growth environment and the CO2 tolerance threshold of the mushroom at the current growth stage includes:

[0030]

[0031] in, For CO2 concentration deviation, C t This refers to the real-time CO2 concentration in the mushroom growth environment. This represents the CO2 tolerance threshold for the mushrooms at their current growth stage. β The time decay coefficient, t This represents the duration of the deviation.

[0032] In some embodiments, when the mushroom is in the mycelial stage of growth, the ventilation duration is determined based on the CO2 concentration deviation, including the following formula: T on :

[0033]

[0034] in, K p This is the proportionality coefficient. K i The integral coefficient is... K d These are the differential coefficients. E To normalize the error, , For CO2 concentration deviation, δ The allowable fluctuation threshold.

[0035] In some embodiments, when the mushroom is in the fruiting body stage, the ventilation duration is determined based on the CO2 concentration deviation, including:

[0036] A ventilation pulse generator is designed based on an improved Hodgkin-Huxley neuron model. The expression for the ventilation pulse generator is as follows:

[0037]

[0038] in, The rate of change of membrane potential. τ It is a time constant. V rest This is the resting potential. V This refers to the neuronal membrane potential. R m For membrane resistance, I ext External stimulation current; neuronal membrane potential V Corresponding to the level of CO2 accumulation in the mushroom growth environment, ;

[0039] Determine whether the neuron membrane potential has reached a threshold potential. If so, trigger ventilation and calculate the ventilation duration based on the following formula. T on :

[0040]

[0041] in, V This refers to the neuronal membrane potential. T on,min Minimum ventilation duration, T on,maxFor maximum ventilation duration, V max This represents the maximum neuronal membrane potential. V min This represents the minimum neuronal membrane potential.

[0042] Secondly, this application also provides an adaptive CO2 concentration control system for the mushroom growth stage, the adaptive CO2 concentration control system for the mushroom growth stage includes:

[0043] A CO2 tolerance threshold database construction module is used to construct a CO2 tolerance threshold database for mushrooms. This includes: acquiring historical growth data of mushrooms, including mycelial dry weight at the mycelial stage and fruiting body morphology indicators at the fruiting body stage under different CO2 concentrations; based on the historical growth data, using an improved Gaussian process regression algorithm to obtain the expected growth efficiency and confidence intervals of mushrooms corresponding to different CO2 concentrations; and based on the expected growth efficiency and the confidence intervals, using NSGA-II optimization to obtain the CO2 tolerance thresholds for the mycelial and fruiting body stages, thereby obtaining the CO2 tolerance threshold database for mushrooms.

[0044] The growth stage identification module is used to acquire real-time growth data of mushrooms and identify the current growth stage of mushrooms based on the real-time growth data.

[0045] The control module is used to obtain the CO2 tolerance threshold of the mushroom at the current growth stage from the CO2 tolerance threshold database; and to adaptively control the CO2 concentration in the mushroom growth environment based on the obtained CO2 tolerance threshold of the mushroom at the current growth stage.

[0046] The aforementioned adaptive CO2 concentration control method and system for mushroom growth stages involves constructing a CO2 tolerance threshold database for mushrooms and identifying the current growth stage of the mushrooms based on real-time growth data. It then retrieves the CO2 tolerance threshold for the current growth stage from the database and adaptively controls the CO2 concentration in the mushroom growth environment based on this threshold. This allows for the adaptive control of CO2 concentration in the mushroom growth environment according to the mushroom's growth stage, enabling automatic and coordinated optimization of nutrient accumulation in the mycelium stage and high-quality growth in the fruiting body stage. This significantly reduces energy consumption and labor costs, improving the stability and economic benefits of mushroom production. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of a method for adaptive control of CO2 concentration during the growth stage of fungi provided in one embodiment of this application;

[0049] Figure 2 The following is a structural block diagram of an adaptive CO2 concentration control system for the mushroom growth stage, provided in another embodiment of this application. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] In one embodiment, see Figure 1 This application provides a method for adaptively regulating CO2 concentration during the growth stages of mushrooms, which include the mycelial stage and the fruiting body stage. The method for adaptively regulating CO2 concentration during the growth stages of mushrooms may include the following steps: S10~S40.

[0052] S10: Construct a CO2 tolerance threshold database for mushrooms, including: acquiring historical growth data of mushrooms, the historical growth data including mycelial dry weight at the mycelial stage and fruiting body morphology indicators at the fruiting body stage under different CO2 concentrations; based on the historical growth data, using an improved Gaussian process regression algorithm to obtain the expected value and confidence interval of mushroom growth efficiency corresponding to different CO2 concentrations; based on the expected value of growth efficiency and the confidence interval, using NSGA-II optimization to obtain the CO2 tolerance thresholds at the mycelial stage and the fruiting body stage, thereby obtaining the CO2 tolerance threshold database for mushrooms.

[0053] S20: Obtain real-time growth data of the mushrooms, and identify the current growth stage of the mushrooms based on the real-time growth data.

[0054] S30: Obtain the CO2 tolerance threshold of the mushroom at the current growth stage from the CO2 tolerance threshold database.

[0055] S40: Based on the obtained CO2 tolerance threshold of the current growth stage of the mushroom, adaptively regulate the CO2 concentration in the mushroom growth environment.

[0056] In the adaptive CO2 concentration control method for mushroom growth stages in this embodiment, a CO2 tolerance threshold database for mushrooms is constructed, and the current growth stage of the mushrooms is identified based on real-time growth data. The CO2 tolerance threshold for the current growth stage of the mushrooms is obtained from the CO2 tolerance threshold database. Based on the obtained CO2 tolerance threshold for the current growth stage of the mushrooms, the CO2 concentration in the mushroom growth environment is adaptively controlled. This method can achieve adaptive control of the CO2 concentration in the mushroom growth environment according to the growth stage of the mushrooms, and can realize automatic coordinated optimization of nutrient accumulation in the mycelium stage and high-quality growth in the fruiting body stage. It can significantly reduce energy consumption and labor costs, and improve the stability and economic benefits of mushroom production.

[0057] As an example, in step S10, historical growth data of the mushroom is acquired. This historical growth data includes the mycelial dry weight at the mycelial stage and the fruiting body morphology indicators at the fruiting body stage under different CO2 concentrations. This may include the following: designing an orthogonal experimental matrix to control the combination of CO2 concentration gradient (e.g., 0.01%~0.3%, i.e., the volume percentage of CO2 in the mushroom's growth environment is 0.01%~0.3%, with a step size of 0.01%) and the duration of the mushroom's growth stages. A high-precision CO2 sensor (±10ppm) is used to record environmental data (i.e., the CO2 concentration in the mushroom's growth environment) every 5 minutes, and mycelial dry weight (mycelial stage) and fruiting body morphology indicators (fruiting body stage) are collected simultaneously. In one example, the storage format of the historical growth data can be:

[0058]

[0059] The sub-entity morphology score is the sub-entity morphology index.

[0060] As an example, multiple CO2 concentration gradients can be set up, and each group can be repeated multiple times (e.g., 3 times) to collect the mycelial dry weight (mycelial stage) and fruiting body morphology indicators (fruiting body stage) corresponding to each CO2 concentration gradient.

[0061] As an example, in step S10, the improved Gaussian process regression algorithm is used to obtain the expected value and confidence interval of the growth efficiency of mushrooms corresponding to different CO2 concentrations. That is, the improved Gaussian process regression (GPR) model can be used to analyze and obtain the expected value and confidence interval of the growth efficiency of mushrooms corresponding to different CO2 concentrations.

[0062] As an example, the improvement of the improved Gaussian process regression model compared to the conventional Gaussian process regression model lies in the addition of a stage weight factor to the standard Gaussian process regression kernel function. This allows for the adaptive matching of an improved Gaussian process regression model to different growth stages of mushrooms.

[0063] As an example, the kernel function of the improved Gaussian process regression model can be:

[0064]

[0065] in, For kernel function, α As a stage weighting factor, x This is the first CO2 concentration sample. This is the second CO2 concentration sample. Let Euclidean distance be the distance between samples. l For length scale, Standard deviation of concentration fluctuation; mycelial stage, stage weighting factor α =0.7, sub-entity stage, stage weight factor α =0.3.

[0066] The improved Gaussian process regression model described above can perform regression analysis on the input CO2 concentration data, ultimately outputting two key indicators: the expected value of mushroom growth efficiency and the confidence interval. The expected growth efficiency is the optimal predicted value for the mushroom's growth state at a given CO2 concentration (e.g., mycelial dry weight at the mycelial stage, fruiting body morphology indicators at the fruiting body stage), reflecting the mushroom's growth potential at that CO2 concentration. The confidence interval corresponds to the fluctuation range of growth efficiency at that CO2 concentration, reflecting the stability risk of the growth state. The smaller the confidence interval, the more stable the mushroom growth at that concentration; the larger the confidence interval, the higher the possibility of environmental interference affecting the growth state.

[0067] The improved Gaussian process regression model in this application adds a stage weight factor to the kernel function. α The kernel function weights can be dynamically adjusted through stage weighting factors to avoid fitting biases of the single model to the CO2-tolerant mycelial stage and the low-CO2-sensitive fruiting body stage, thereby improving prediction accuracy. In addition, the kernel function of the improved Gaussian process regression model includes the standard deviation of concentration fluctuations, which can incorporate environmental noise in the actual mushroom growth environment (such as small fluctuations in CO2 concentration) into the improved Gaussian process regression model, making the output growth efficiency expectation value and confidence interval closer to the real growth environment.

[0068] As an example, stage weighting factor α The size can be dynamically adjusted according to the growth stage of the mushroom, such as the mycelium stage, with a stage weighting factor. α A value of 0.7 can be used; for the sub-entity stage, the stage weight factor. α A value of 0.3 can be used; stage weighting factors for mycelial stage and fruiting body stage.α The value can be an empirical value, that is, an empirical value set based on actual experience.

[0069] As an example, in step S10, based on the expected growth efficiency and the confidence interval, the CO2 tolerance thresholds for the mycelial stage and the fruiting body stage are obtained using NSGA-II optimization, which may include:

[0070] Construct a dual-objective optimization function based on Pareto optimal front theory:

[0071]

[0072] in, This represents the expected growth efficiency corresponding to the maximum CO2 concentration. The confidence interval for minimum growth efficiency;

[0073] Set the following constraints:

[0074]

[0075] in, μ This represents the expected growth efficiency. μ max To obtain the maximum growth efficiency within the current growth stage using an improved Gaussian process regression algorithm, σ represents the confidence interval, and ∧ represents the logical AND operator;

[0076] Based on the aforementioned constraints, the NSGA-II algorithm is used to solve the optimal solution of the biobjective optimization function to obtain the CO2 tolerance thresholds for the mycelial stage and the fruiting body stage.

[0077] As an example, the specific method for solving the biobjective optimization function using the NSGA-II algorithm is known to those skilled in the art and will not be elaborated here. The obtained optimal solution can include the optimal solution for the mycelial stage and the optimal solution for the fruiting body stage. The optimal solution for the mycelial stage can be used as the CO2 tolerance threshold for the mycelial stage, and the optimal solution for the fruiting body stage can be used as the CO2 tolerance threshold for the fruiting body stage.

[0078] As an example, the CO2 tolerance thresholds for both the mycelial stage and the fruiting body stage can be concentration ranges with upper and lower limits. Taking a CO2 tolerance threshold of 0.18% ± 0.03% for the mycelial stage and 0.07% ± 0.01% for the fruiting body stage as an example, the data in the mushroom CO2 tolerance threshold database can be stored in the following format:

[0079]

[0080] The data stored in the above format provides a clear understanding of the CO2 tolerance thresholds for mushrooms at the mycelial and fruiting body stages.

[0081] As an example, step S20, acquiring real-time growth data of the mushrooms and identifying the current growth stage of the mushrooms based on the real-time growth data, may include the following steps:

[0082] S201: Obtain the mycelial density index and primordium number of mushrooms as real-time growth data of mushrooms.

[0083] S202: Set a time window for the mycelial stage; within the time window of the mycelial stage, if the mycelial density index is greater than a preset threshold and the number of primordia is greater than or equal to a preset number, then the mushroom is determined to have entered the fruiting body stage; otherwise, the mushroom is determined to be in the mycelial stage; if the time window of the mycelial stage ends and the mycelial density index is still less than or equal to a preset threshold and / or the number of primordia is still less than a preset number, then the mushroom is still determined to have entered the fruiting body stage.

[0084] As an example, in step S20, multimodal sensor fusion technology can be used to achieve accurate identification of the growth status by having a mycelium density sensor and a fruiting body primordium detection sensor installed in the mushroom growth environment work together.

[0085] As an example, a mycelial density sensor can employ the near-infrared spectral reflectance measurement principle (wavelength range 800nm~2500nm) to determine its growth density by measuring the absorption characteristics of mycelium to light of a specific wavelength. The mycelial density sensor can collect data at a preset frequency (e.g., once every 6 hours), and the measurement formula can be as follows:

[0086]

[0087] in, D It is the mycelial density index (dimensionless, ranging from 0 to 1 or 0 to 100). wavelength λ i Reflectivity at that location is the weighting coefficient for wavelength, and n is the total number of wavelength points involved in the calculation.

[0088] As an example, the mycelial density index can be used... D To determine whether the mycelium has entered the mature stage, for example, when the mycelium density index... If the mycelium concentration exceeds 0.7 for three consecutive days, it can be determined that the mycelium has entered the mature stage. Only after the mycelium enters the mature stage can it enter the fruiting body stage.

[0089] As an example, the primordium detection sensor can employ machine vision technology, equipped with a ring-shaped LED light source (color temperature can be 5000K) and a 5-megapixel CMOS camera, and detect primordium features through image processing algorithms. The image processing algorithm first converts the image to the HSV color space and extracts the saturation channel; then it applies morphological opening operations to remove noise, and finally identifies the number of primordia through contour detection.

[0090] As an example, if the mycelial density index is greater than a preset threshold and the number of primordia is greater than or equal to a preset number, then the mushroom can be determined to have entered the fruiting body stage. For example, if more than 5 primordia are detected in a unit area (e.g., 10cm×10cm), then the mushroom can be determined to have entered the fruiting body stage.

[0091] As an example, in step S20, by setting a time window for the mycelial stage, a dual verification mechanism for time threshold judgment can be achieved: within the time window of the mycelial stage (e.g., 7-14 days), if the mycelial density index is greater than a preset threshold and the number of primordia is greater than or equal to a preset number (i.e., the morphological characteristics of the mushroom meet the conversion conditions), then the mushroom is determined to have entered the fruiting body stage (i.e., the stage switching is immediately triggered); if at the end of the time window of the mycelial stage, the mycelial density index is still less than or equal to a preset threshold and / or the number of primordia is still less than a preset number (i.e., the morphological standard is not met), then the mushroom is still determined to have entered the fruiting body stage (i.e., it is forced to enter the next growth stage).

[0092] As an example, if the mycelial density index is still less than or equal to a preset threshold and / or the number of primordia is still less than a preset number when the mycelial stage time window ends, and the mushroom is still determined to have entered the fruiting body stage, the method further includes: activating an abnormal alarm.

[0093] As an example, in step S30, after determining the current growth stage of the mushroom, the CO2 tolerance threshold of the current growth stage of the mushroom can be obtained from the CO2 tolerance threshold database.

[0094] As an example, step S40, based on the obtained CO2 tolerance threshold of the current growth stage of the mushroom, adaptively regulating the CO2 concentration in the mushroom growth environment may include the following steps:

[0095] S401: Obtain the real-time CO2 concentration in the mushroom growth environment.

[0096] S402: The CO2 concentration deviation is obtained based on the real-time CO2 concentration in the mushroom growth environment and the CO2 tolerance threshold of the mushroom at the current growth stage.

[0097] S403: The ventilation duration is obtained based on the CO2 concentration deviation;

[0098] S404: Ventilate the mushroom growth environment based on the ventilation duration to adaptively regulate the CO2 concentration in the mushroom growth environment.

[0099] As an example, in step S401, a CO2 sensor can be used to collect the real-time CO2 concentration in the mushroom growth environment.

[0100] As an example, in step S402, the formula for obtaining the CO2 concentration deviation based on the real-time CO2 concentration in the mushroom growth environment and the CO2 tolerance threshold of the mushroom at its current growth stage can be:

[0101]

[0102] in, For CO2 concentration deviation, C t This refers to the real-time CO2 concentration in the mushroom growth environment. This represents the CO2 tolerance threshold for the mushrooms at their current growth stage. β The time decay coefficient, t This represents the duration of the deviation.

[0103] As an example, time decay coefficient β It is used to suppress transient fluctuations and its value can be set to 0.05 by default.

[0104] As an example, when CO2 concentration deviation Regulation is triggered when the allowable fluctuation threshold is exceeded; that is, regulation is only triggered when the CO2 concentration deviation exceeds the threshold. Steps S403 and S404 are only executed if the allowable fluctuation threshold is exceeded (e.g., 0.03%, or 0.03% in the mycelial stage and 0.01% in the fruiting body stage); if the CO2 concentration deviation... If the value is less than or equal to the allowable fluctuation threshold, no regulation will be implemented.

[0105] As an example, in step S403, when the mushroom is in the mycelial stage of growth, obtaining the ventilation duration based on the CO2 concentration deviation may include: obtaining the ventilation duration based on the following formula. T on :

[0106]

[0107] in, K p This is the proportionality coefficient. K i The integral coefficient is... K d These are the differential coefficients. E To normalize the error, , For CO2 concentration deviation, δ The allowable fluctuation threshold.

[0108] As an example, the scaling factor K p Integral coefficient K i and differential coefficients K d Adjustments can be made dynamically based on the operational phase. For example, the following adjustment strategies can be used:

[0109] It should be noted that the initial stage, stable stage, and recovery stage can be divided according to the specific circumstances, and no specific limitation is made here.

[0110] As an example, in step S403, when the mushroom is in the fruiting body stage, obtaining the ventilation duration based on the CO2 concentration deviation may include the following steps:

[0111] A ventilation pulse generator is designed based on an improved Hodgkin-Huxley neuron model. The expression for the ventilation pulse generator is as follows:

[0112]

[0113] in, The rate of change of membrane potential. τ It is a time constant. V rest This is the resting potential. V This refers to the neuronal membrane potential. R m For membrane resistance, I ext External stimulation current; neuronal membrane potential V Corresponding to the level of CO2 accumulation in the mushroom growth environment, ;

[0114] Determine whether the neuron membrane potential has reached a threshold potential. If so, trigger ventilation and calculate the ventilation duration based on the following formula. T on :

[0115]

[0116] in, V This refers to the neuronal membrane potential. T on,min Minimum ventilation duration, T on,max For maximum ventilation duration, Vmax This represents the maximum neuronal membrane potential. V min This represents the minimum neuronal membrane potential.

[0117] It should be noted that the minimum ventilation duration T on,min Maximum ventilation duration T on,max Maximum neuronal membrane potential V max and minimum neuronal membrane potential V min All of these can be set values, specifically set values ​​obtained through pre-testing of actual conditions.

[0118] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0119] In another embodiment, please refer to Figure 2This application also provides an adaptive CO2 concentration control system for mushroom growth stages. The system may include: a CO2 tolerance threshold database construction module 10, a growth stage identification module 20, and a control module 30. The CO2 tolerance threshold database construction module 10 is used to construct a CO2 tolerance threshold database for mushrooms, including: acquiring historical growth data of the mushrooms, which includes mycelial dry weight at the mycelial stage and fruiting body morphology indicators at the fruiting body stage under different CO2 concentrations; and, based on the historical growth data, using an improved Gaussian process regression algorithm to obtain the effect of different CO2 concentrations on the growth stage. The expected value and confidence interval of the mushroom growth efficiency are obtained; based on the expected value and confidence interval, the CO2 tolerance thresholds of the mycelial stage and fruiting body stage are obtained by NSGA-II optimization, thereby obtaining a CO2 tolerance threshold database for mushrooms; the growth stage identification module 20 is used to acquire real-time growth data of mushrooms and identify the current growth stage of mushrooms based on the real-time growth data; the regulation module 30 is used to acquire the CO2 tolerance threshold of the current growth stage of mushrooms from the CO2 tolerance threshold database; based on the acquired CO2 tolerance threshold of the current growth stage of mushrooms, the CO2 concentration in the mushroom growth environment is adaptively regulated.

[0120] As an example, the adaptive CO2 concentration control system for the mushroom growth stage described in this embodiment can be used to perform, for example... Figure 1 The method for adaptive control of CO2 concentration during the growth stage of fungi in the corresponding embodiments.

[0121] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features of the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for adaptively regulating CO2 concentration during the growth stage of fungi, characterized in that, The growth stages of mushrooms include the mycelial stage and the fruiting body stage; the adaptive regulation method for CO2 concentration during the mushroom growth stages includes: Constructing a CO2 tolerance threshold database for mushrooms includes: acquiring historical growth data of mushrooms, including mycelial dry weight at the mycelial stage and fruiting body morphology indicators at the fruiting body stage under different CO2 concentrations; based on the historical growth data, using an improved Gaussian process regression algorithm to obtain the expected value and confidence interval of mushroom growth efficiency corresponding to different CO2 concentrations; and based on the expected value of growth efficiency and the confidence interval, using NSGA-II optimization to obtain the CO2 tolerance thresholds at the mycelial stage and the fruiting body stage, thereby obtaining the CO2 tolerance threshold database for mushrooms. Acquire real-time growth data of mushrooms, and identify the current growth stage of mushrooms based on the real-time growth data; Obtain the CO2 tolerance threshold of the mushroom at the current growth stage from the CO2 tolerance threshold database; Based on the CO2 tolerance threshold of the mushroom at its current growth stage, the CO2 concentration in the mushroom growth environment is adaptively regulated.

2. The adaptive CO2 concentration control method for the mushroom growth stage according to claim 1, characterized in that, Acquiring real-time growth data of mushrooms and identifying the current growth stage of the mushrooms based on the real-time growth data includes: The mycelial density index and primordium number of mushrooms were obtained as real-time growth data for mushrooms. A time window for the mycelial stage is set. Within the time window, if the mycelial density index is greater than a preset threshold and the number of primordia is greater than or equal to a preset number, the mushroom is determined to have entered the fruiting body stage; otherwise, the mushroom is determined to be in the mycelial stage. If, at the end of the time window for the mycelial stage, the mycelial density index is still less than or equal to a preset threshold and / or the number of primordia is still less than a preset number, the mushroom is still determined to have entered the fruiting body stage.

3. The adaptive CO2 concentration control method for the mushroom growth stage according to claim 2, characterized in that, If, at the end of the mycelial stage time window, the mycelial density index is still less than or equal to a preset threshold and / or the number of primordia is still less than a preset number, and the mushroom is still determined to have entered the fruiting body stage, the following steps are also included: activating an abnormal alarm.

4. The method for adaptive control of CO2 concentration during the growth stage of fungi according to claim 1, characterized in that, The kernel function used in the improved Gaussian process regression algorithm to obtain the expected value and confidence interval of mushroom growth efficiency for different CO2 concentrations is as follows: in, For kernel function, α As a stage weighting factor, x This is the first CO2 concentration sample. This is the second CO2 concentration sample. Let Euclidean distance be the distance between samples. l For length scale, Standard deviation of concentration fluctuation; mycelial stage, stage weighting factor α =0.7, sub-entity stage, stage weight factor α =0.

3.

5. The method for adaptive control of CO2 concentration during the growth stage of fungi according to claim 1, characterized in that, Based on the expected growth efficiency and the confidence interval, the CO2 tolerance thresholds for the mycelial and fruiting body stages were obtained using NSGA-II optimization, including: Construct a dual-objective optimization function based on Pareto optimal front theory: in, This represents the expected growth efficiency corresponding to the maximum CO2 concentration. The confidence interval for minimum growth efficiency; Set the following constraints: in, μ This represents the expected growth efficiency. μ max To obtain the maximum growth efficiency within the current growth stage using an improved Gaussian process regression algorithm, σ represents the confidence interval, and ∧ represents the logical AND operator; Based on the aforementioned constraints, the NSGA-II algorithm is used to solve the optimal solution of the biobjective optimization function to obtain the CO2 tolerance thresholds for the mycelial stage and the fruiting body stage.

6. The method for adaptive control of CO2 concentration during the growth stage of fungi according to any one of claims 1 to 5, characterized in that, Based on the obtained CO2 tolerance threshold of the current growth stage of the mushrooms, the CO2 concentration in the mushroom growth environment is adaptively regulated, including: Obtain the real-time CO2 concentration in the mushroom growth environment; The CO2 concentration deviation is obtained based on the real-time CO2 concentration in the mushroom growth environment and the CO2 tolerance threshold of the mushroom at the current growth stage. The ventilation duration is obtained based on the CO2 concentration deviation. Ventilation is performed on the mushroom growth environment based on the ventilation duration to adaptively regulate the CO2 concentration in the mushroom growth environment.

7. The adaptive CO2 concentration control method for the mushroom growth stage according to claim 6, characterized in that, The formula for calculating the CO2 concentration deviation based on the real-time CO2 concentration in the mushroom growth environment and the CO2 tolerance threshold of the mushroom at its current growth stage includes: in, For CO2 concentration deviation, C t This refers to the real-time CO2 concentration in the mushroom growth environment. This represents the CO2 tolerance threshold for the mushrooms at their current growth stage. β The time decay coefficient, t This represents the duration of the deviation.

8. The method for adaptive regulation of CO2 concentration during the growth stage of fungi according to claim 7, characterized in that, When the mushroom is in the mycelial stage of growth, the ventilation duration based on the CO2 concentration deviation includes: The ventilation duration is calculated using the following formula. T on : in, K p This is the proportionality coefficient. K i The integral coefficient is... K d These are the differential coefficients. E To normalize the error, , For CO2 concentration deviation, δ The allowable fluctuation threshold.

9. The method for adaptive regulation of CO2 concentration during the growth stage of fungi according to claim 7, characterized in that, When the mushrooms are in the fruiting body stage, the ventilation duration, based on the CO2 concentration deviation, includes: A ventilation pulse generator is designed based on an improved Hodgkin-Huxley neuron model. The expression for the ventilation pulse generator is as follows: in, The rate of change of membrane potential. τ It is a time constant. V rest This is the resting potential. V This refers to the neuronal membrane potential. R m For membrane resistance, I ext External stimulation current; neuronal membrane potential V Corresponding to the level of CO2 accumulation in the mushroom growth environment, ; Determine whether the neuron membrane potential has reached a threshold potential. If so, trigger ventilation and calculate the ventilation duration based on the following formula. T on : in, V This refers to the neuronal membrane potential. T on,min Minimum ventilation duration, T on,max For maximum ventilation duration, V max This represents the maximum neuronal membrane potential. V min This represents the minimum neuronal membrane potential.

10. A system for adaptively regulating CO2 concentration during the growth stage of fungi, characterized in that, include: A CO2 tolerance threshold database construction module is used to construct a CO2 tolerance threshold database for mushrooms. This includes: acquiring historical growth data of mushrooms, including mycelial dry weight at the mycelial stage and fruiting body morphology indicators at the fruiting body stage under different CO2 concentrations; based on the historical growth data, using an improved Gaussian process regression algorithm to obtain the expected growth efficiency and confidence intervals of mushrooms corresponding to different CO2 concentrations; and based on the expected growth efficiency and the confidence intervals, using NSGA-II optimization to obtain the CO2 tolerance thresholds for the mycelial and fruiting body stages, thereby obtaining the CO2 tolerance threshold database for mushrooms. The growth stage identification module is used to acquire real-time growth data of mushrooms and identify the current growth stage of mushrooms based on the real-time growth data. The control module is used to obtain the CO2 tolerance threshold of the mushroom at the current growth stage from the CO2 tolerance threshold database; and to adaptively control the CO2 concentration in the mushroom growth environment based on the obtained CO2 tolerance threshold of the mushroom at the current growth stage.

Images