Environmental parameter adaptive optimization algorithm and system for edible mushroom breeding

Abstract

The invention provides an environment parameter adaptive optimization method for edible mushroom breeding. The method comprises the following steps: S1, constructing an edible mushroom growth cycle standard database; s2, collecting multi-dimensional environmental parameters of the edible mushrooms; s3, constructing a growth cycle prediction model, inputting multi-dimensional environmental parameters, and predicting the growth cycle of the edible fungi; the growth cycle prediction model is used for constructing a daily growth variable function by taking matrix overall weight and matrix pressure in multi-dimensional environmental parameters as core parameters, accumulating daily growth variables to obtain a comprehensive growth index, and finally predicting the current growth stage of the edible mushrooms according to threshold intervals of different growth stages corresponding to the comprehensive growth index; s4, inputting a predicted edible mushroom growth cycle to the standard database in the step 1 to obtain standard environment parameters and self-adaptive regulation and control environment parameters; and according to the predicted growth cycle, obtaining the standard environmental parameters of the edible mushrooms in the corresponding stages from the standard database, and correspondingly regulating and controlling the real-time environmental parameters of the edible mushrooms.

Description

Technical Field

[0001] This invention relates to the field of agricultural Internet of Things (IoT) technology, and in particular to an adaptive optimization algorithm and system for environmental parameters in edible fungi breeding. Background Technology

[0002] Edible fungi are rich in nutrients such as protein and polysaccharides, possessing both edible and medicinal value. They have broad application prospects in the food industry and biomedicine, and market demand continues to rise. As an important component of modern agriculture, the cultivation of edible fungi using spawn is gradually shifting from traditional manual experience to data-driven intelligent regulation in response to the complex challenges of climate change and market demands. By introducing advanced environmental monitoring and control technologies, the growth conditions of edible fungi can be optimized, improving yield and quality, thereby meeting the growing consumer demand and the goals of sustainable development.

[0003] Currently, the regulation of environmental parameters in edible fungi breeding mainly relies on traditional experience-based management or simple automated control methods. Traditional experience-based management depends on the subjective judgment of operators, adjusting environmental parameters based on the visual observation of the growth status of edible fungi. This has problems such as regulatory lag, large individual differences, and low parameter accuracy, making it difficult to meet the needs of large-scale and standardized breeding. While simple automated control methods can achieve automatic collection and regulation of some environmental parameters, they cannot adaptively adjust environmental parameters according to the different stages of edible fungi growth.

[0004] Therefore, an adaptive optimization method and system for environmental parameters for edible fungi breeding is proposed, but it is impossible to adaptively adjust environmental parameters according to the different stages of edible fungi to achieve adaptive optimization of environmental parameters. Summary of the Invention

[0005] In view of this, the present invention proposes an adaptive optimization method and system for environmental parameters for edible fungi breeding, which solves the problem that the existing technology cannot adaptively adjust environmental parameters according to the different stages of edible fungi growth, so as to achieve adaptive optimization of environmental parameters for edible fungi growth.

[0006] This invention proposes an adaptive optimization method for environmental parameters in edible fungi breeding, comprising the following steps: S1: Construct a standard database of edible fungi growth cycles; S2: Collect multi-dimensional environmental parameters of edible fungi; S3: Construct a growth cycle prediction model, input multi-dimensional environmental parameters, and predict the growth cycle of edible fungi; The growth cycle prediction model uses the total weight of the substrate and substrate pressure from the multi-dimensional environmental parameters to construct a daily growth variable function, and accumulates the daily growth variables to obtain a comprehensive growth index. Finally, based on the threshold range of the comprehensive growth index corresponding to different growth stages, it predicts the current growth stage of the edible fungi. S4: Input the predicted growth cycle of edible fungi into the standard database described in step 1 to obtain standard environmental parameters, and adaptively adjust the environmental parameters. Based on the predicted growth cycle, standard environmental parameters for edible fungi at the corresponding stage are obtained from a standard database, and the real-time environmental parameters for edible fungi are adjusted accordingly.

[0007] Based on the above technical solution, preferably, in step S2, the environmental parameters of the edible fungi include: ambient temperature, ambient humidity, carbon dioxide concentration, light intensity, substrate temperature, substrate moisture content, substrate conductivity, substrate pressure, and total substrate weight.

[0008] Based on the above technical solution, preferably, in step S3, the daily growth variable function is modified by combining carbon dioxide concentration, matrix moisture content and matrix conductivity.

[0009] Based on the above technical solution, preferably, the growth cycle prediction model is divided into at least four growth stages, and the comprehensive growth index is defined and the growth process stage of the edible fungus is predicted by the threshold intervals corresponding to each stage.

[0010] Based on the above technical solution, preferably, the auxiliary correction of carbon dioxide concentration adopts segmented parameters, and the most suitable carbon dioxide concentration range is set according to the different growth stages of edible fungi.

[0011] Based on the above technical solution, preferably, the matrix conductivity and the matrix water content are modified by a peak function to correct the comprehensive growth index.

[0012] Based on the above technical solution, preferably, in step S1, the standard database for edible fungi growth cycle includes environmental parameters, substrate parameters, growth phenotype parameters, and cycle time parameters.

[0013] Based on the above technical solution, preferably, in step S1, the standard database for the growth cycle of edible fungi collects full-cycle data of at least three kinds of edible fungi under different breeding batches, covering different seasons and different cultivation equipment.

[0014] Based on the above technical solution, preferably, the time series modeling of the growth cycle prediction model is implemented using an LSTM time series model.

[0015] On the other hand, the present invention also provides an adaptive optimization system for environmental parameters in edible fungi breeding, using the aforementioned adaptive optimization method for environmental parameters in edible fungi breeding, including: A multi-dimensional environmental parameter acquisition module is used to collect multi-dimensional environmental parameters of edible fungi. The data processing and analysis module is used to construct a standard database and a growth cycle prediction model for edible fungi, and to predict the growth cycle of edible fungi based on multi-dimensional environmental parameters, and then output environmental parameters according to the growth cycle of edible fungi. The communication control module is used to adaptively adjust environmental parameters based on the output environmental parameters.

[0016] The present invention provides an adaptive optimization algorithm and system for environmental parameters in edible fungi breeding, which has the following advantages compared with the prior art: (1) A multi-dimensional environmental parameter acquisition mode is adopted, and the overall weight of edible fungi and substrate and substrate pressure are used as the main parameters. This provides accurate and highly correlated data support for the construction of daily growth variable functions and the calculation of comprehensive growth index. This makes up for the shortcomings of existing technologies in terms of single parameter acquisition dimension and lack of core growth-related parameters. According to the prediction model of edible fungi, combined with the stage-adaptive environmental parameters of the standard database, it can automatically adapt to the needs of different growth stages of edible fungi, and improve the accuracy and automation level of environmental parameter regulation. (2) The matrix conductivity and the matrix moisture content are corrected by peak function to obtain the comprehensive growth index. The growth activity is highest when the moisture content and conductivity are at the optimal values. Deviating from the optimal values ​​will inhibit growth, thus accurately fitting the single-peak pattern of edible fungi. (3) Different environmental parameters are used to modify the comprehensive growth index with different functions, so that the growth prediction model can more delicately reflect the dynamic changes of environmental requirements of edible fungi at different growth stages, thereby making more accurate stage predictions and growth regulation. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the steps of an adaptive optimization method for environmental parameters in edible fungi breeding according to the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] In the description of the embodiments of the present invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of the present invention based on the specific circumstances.

[0021] In the description of the embodiments of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of the present invention.

[0022] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0023] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0024] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. Additionally, examples of various specific processes and materials are provided in this invention; however, those skilled in the art will recognize the applicability of other processes and / or the use of other materials.

[0025] The technical solution was explained. Traditional experience-based management relies on the subjective judgment of operators, adjusting environmental parameters based on visual observation of edible fungi growth. This approach suffers from problems such as regulatory lag, significant individual variability, and low parameter accuracy, making it difficult to meet the needs of large-scale, standardized breeding. While simple automated control methods can automatically collect and regulate some environmental parameters, they cannot adaptively adjust these parameters according to the different stages of edible fungi growth. Therefore, as... Figure 1 As shown, this invention provides an adaptive optimization method for environmental parameters in edible fungi breeding, comprising the following steps: S1: Construct a standard database of edible fungi growth cycles; S2: Collect multi-dimensional environmental parameters of edible fungi; S3: Construct a growth cycle prediction model, input multi-dimensional environmental parameters, and predict the growth cycle of edible fungi; The growth cycle prediction model constructs a daily growth variable function with the total weight of the substrate and substrate pressure among the multi-dimensional environmental parameters as the core parameters, and accumulates the daily growth variables to obtain a comprehensive growth index. Finally, based on the threshold range of the comprehensive growth index corresponding to different growth stages, the current growth stage of edible fungi is predicted. The total weight of the substrate is the sum of the weight of the edible fungi and the substrate. S4: Input the predicted growth cycle of edible fungi into the standard database described in step 1 to obtain standard environmental parameters, and adaptively adjust the environmental parameters. Among them, the standard environmental parameters of edible fungi at the corresponding stage are obtained from the standard database based on the predicted growth cycle, and the real-time environmental parameters of edible fungi are adjusted accordingly.

[0026] Employing a multi-dimensional environmental parameter acquisition model, and using the overall weight of edible fungi and substrate, as well as substrate pressure, as the main parameters, this method provides accurate and highly correlated data support for the construction of daily growth variable functions and the calculation of comprehensive growth indices. This overcomes the shortcomings of existing technologies, which suffer from single-dimensional parameter acquisition and lack of core growth-related parameters. Based on the prediction model of edible fungi and combined with the stage-adaptive environmental parameters of the standard database, it can automatically adapt to the needs of different growth stages of edible fungi, thereby improving the accuracy and automation level of environmental parameter control.

[0027] In step S2, the environmental parameters of the edible fungi include: ambient temperature, ambient humidity, carbon dioxide concentration, light intensity, substrate temperature, substrate moisture content, substrate conductivity, substrate pressure, and total substrate weight.

[0028] Specifically, in step S2, a distributed sensing and centralized calibration acquisition mode is adopted. Multiple types of sensors are deployed at preset intervals in the edible fungus breeding and cultivation space. At the same time, micro-sensor components are embedded at different depths of the substrate to collect substrate temperature, substrate moisture content, substrate conductivity, and substrate pressure in real time. The total weight of the substrate here refers to the total weight of the substrate and the edible fungus, which is obtained by weighing with an electronic scale. In addition, sensors are arranged in the greenhouse of edible fungus. The sensors are used to acquire ambient temperature, ambient humidity, carbon dioxide concentration, and light intensity. The collected data are transmitted to the data processing terminal through wireless communication technology.

[0029] In step S3, the daily growth variable function is modified by combining carbon dioxide concentration, substrate moisture content and substrate conductivity, and a comprehensive growth index is calculated. Based on the range of the comprehensive growth index, the various growth stages of edible fungi are predicted.

[0030] The specific daily growth variable function is as follows: , formula 1; in The daily growth increment is represented by t, which is time (days). The total weight change (kg) of the substrate and utilitarian bacteria on that day. This represents the daily pressure change (kPa). The initial bacterial strain and substrate weight (kg); Initial matrix pressure (kPa); This is the weighting coefficient; This is the pressure weighting coefficient; , which are auxiliary correction factors for CO2 concentration, matrix moisture content and matrix conductivity; C is CO2 concentration; M is matrix moisture content; E is matrix conductivity.

[0031] Specifically, the cumulative formula for the composite growth index is: , formula 2; According to Formula 2, the comprehensive growth index accumulates from zero and gradually reflects the growth process. The growth cycle prediction model is divided into at least four growth stages, and the comprehensive growth index is defined and the growth process stage of edible fungi is predicted by the threshold range corresponding to each stage.

[0032] During the mycelial growth stage, <S1, mycelial expansion stage, weight increases slowly, pressure initially rises; During the primordium formation stage, S1≤ <S2, primordia appear, weight increases rapidly, and pressure rises significantly; During the mushroom bud formation stage, S2≤ <S3, mushroom buds form, and weight increases rapidly; During the elongation period of the fruiting body, S3≤ <S4, the fruiting body elongates rapidly and reaches its peak weight; Fruiting body maturity period, S4≥ Growth slows down, time to prepare for harvest.

[0033] The thresholds for each stage are S1=1, S2=2.5, S3=5, and S4=8. Example calculation: If... =10kg, =10kPa, assuming data from day 5. =0.2kg, =0.5kPa, =2000mg / m 3 , =65%, =2.0 mS / cm, =0.7, =0.3, It is 0.7.

[0034] Therefore, according to the cumulative formula of the comprehensive growth index, i.e., Formula 1, =0.7x0.2÷10+ 0.3x0.5÷10 x0.7 =0.029 x0.7=0.02 Assuming the GI is 0.5 for the first 4 days, then <S1, therefore the stage is still the mycelial growth stage.

[0035] The auxiliary correction of the carbon dioxide concentration uses segmented parameters, and the most suitable carbon dioxide concentration range is set according to the different growth stages of edible fungi.

[0036] A CO2 concentration correction function is used, where high CO2 inhibits primordium formation but promotes mycelial growth. A piecewise function is employed, which can trigger differentiated correction magnitudes at different stages. ; in, The optimal CO2 concentration (unit: mg / m³) for the current stage is as follows: mycelial stage: 3500–4000 mg / m³; primordia stage: 3000–3500 mg / m³; bud stage: 2500–3000 mg / m³; fruiting body elongation stage: 2000–2500 mg / m³; fruiting body maturity stage: 1000–2000 mg / m³; kc is the inhibition coefficient, kc=10. -6 .

[0037] The matrix conductivity and the matrix moisture content are modified using a peak function to correct the comprehensive growth index. The growth response of edible fungi to most environmental parameters follows a single-peak curve of low growth promotion and high growth inhibition. The growth activity is highest when the moisture content and conductivity are at the optimal values, and deviations from the optimal values ​​will inhibit growth, thus accurately fitting the single-peak pattern of edible fungi.

[0038] Moisture content correction function, inhibiting growth when deviating from the optimal range for edible fungi: ; in, The optimal moisture content for the current stage (unit: %); km is the sensitivity coefficient, km=0.05.

[0039] The conductivity correction function reflects the nutritional status of the substrate. A moderate conductivity parameter is most conducive to the growth of edible fungi, while deviations will inhibit growth. ; The optimal conductivity is expressed in mS / cm, typically 1.5–2.5 mS / cm; ke is the suppression coefficient, ke = 0.5.

[0040] In the auxiliary correction factors, any environmental factor that deviates from the optimal range for edible fungi will directly reduce the comprehensive growth index of the day, thereby more accurately simulating the inhibitory effect of environmental stress on the growth of edible fungi and providing a clear target for precise regulation.

[0041] Different environmental parameters are used to modify the comprehensive growth index using different functions, enabling the growth prediction model to more accurately reflect the dynamic changes in the environmental requirements of edible fungi at different growth stages, thereby making more precise stage predictions and growth regulation.

[0042] To improve the accuracy of the prediction model, the weighting coefficients will be further optimized. Specifically, the daily growth increment (GI) will be considered as the dependent variable, and the normalized rate of change of weight (GROUP) will be used as the weighting coefficient. ) and pressure change rate ( () is considered as an independent variable and regression analysis is performed.

[0043] After performing Z-score standardization preprocessing on the data for each stage, a multiple linear regression model was fitted separately, and the fitted regression equation was: ; Obtain the coefficients of the original regression weight term for this stage. Coefficient of the original regression stress term ; After standardization, the coefficients of the independent variables in the regression equation can approximately reflect their importance, thus providing... and The settings are provided for reference.

[0044] Next, the coefficients of the original regression weight term and the coefficients of the original regression stress term are standardized using Z-scores. The specific formula is as follows: , ; The standard deviation of the corresponding index is used to obtain the dimensionless standardized coefficient. , This can directly reflect the importance of parameters, and then based on the standardized coefficients... , Calculate the various stages of edible fungi using the formula below. and value: , ; Verification of each stage of edible fungi and The value will be the value of each stage. and Substitute the value into the LSTM prediction model, test the accuracy of the judgment, and fine-tune it based on the actual performance of the value. In the specific fine-tuning process, if the judgment error is large at a certain stage, the error at that stage will be fine-tuned in steps of ±0.02. and The value is maintained until the model's performance at that stage meets the target.

[0045] This method of splitting data according to growth stages and performing regression analysis in stages ensures that the weighting coefficients better reflect the growth patterns of edible fungi at different stages, thereby improving the model's accuracy. The core driving parameters differ across different growth stages of edible fungi; for example, weight changes dominate during mycelial growth, while pressure changes dominate during primordium formation. Stage-based regression allows for... and The weighting coefficients are precisely matched to the actual impact weights of each stage to avoid a one-size-fits-all bias and to ensure that the weights are highly consistent with the growth patterns of each stage.

[0046] In step S1, the standard database for the growth cycle of edible fungi includes environmental parameters, substrate parameters, growth phenotype parameters, and cycle time parameters.

[0047] Raw data is collected through a combination of automated sensor networks and manual recording. All data is accompanied by metadata tags, including strain name, strain generation, cultivation batch, collection timestamp, and sensor number, ensuring data traceability. Simultaneously, automated data cleaning rules are established to normalize parameters of different dimensions and align all data along a timeline to form a well-structured time-series dataset. For example, based on the analysis of standardized cultivation data, the database sets a standard range of 20-25℃ for the ambient temperature during the "mycelial growth period" and a standard range of 60.5%-62.5% for the substrate moisture content. It also records optimal growth phenotypes, such as the fastest mycelial germination under conditions of 24℃ and 65% humidity.

[0048] In step S1, the edible fungi growth cycle standard database collects full-cycle data for at least three edible fungi under different breeding batches, covering different seasons and different cultivation equipment. Oyster mushrooms, shiitake mushrooms, and enoki mushrooms are selected to cover different growth characteristics and cycles; laboratory-grade intelligent incubators, factory-style three-dimensional cultivation racks, and outdoor solar greenhouses are selected to simulate mainstream cultivation modes; seasonal simulation uses spring, summer, autumn, and winter in temperate regions as the cycle, adapting to the temperature requirements of different fungi and adjusting equipment control strategies; batch design: at least nine combinations are set according to fungi, equipment, and season, with three batches replicated in each group, and a blank control batch is set simultaneously; data acquisition: the overall weight of edible fungi and substrate, substrate pressure, and auxiliary parameters such as CO2 concentration and moisture content are collected throughout the entire cycle, with the collection frequency adjusted according to the growth stage; data processing: outliers are removed, blank controls are corrected, parameters are standardized, and threshold data for each stage are extracted; database construction: a structured database is built using MySQL, containing five core tables, supporting multidimensional queries and dynamic updates, providing data support for model optimization.

[0049] The core temporal modeling part of the growth cycle prediction model is implemented using an LSTM (Long Short-Term Memory) model. Specifically, the core temporal modeling part of this growth cycle prediction model is implemented using an LSTM (Long Short-Term Memory) network. Based on the standardized database constructed above, and considering the temporal dependence and stage correlation characteristics of edible fungi growth parameters, the LSTM model captures the dynamic changes of parameters over time, accurately outputting the temporal nodes and cycle prediction results for each growth stage. This solves the problem that traditional models are difficult to fit nonlinear temporal data and easily lose long-range dependency information. The core adaptability design of the LSTM temporal modeling revolves around the growth characteristics of edible fungi: the parameters of each stage of edible fungi growth (such as substrate pressure increment, overall weight growth rate, and CO2 concentration) have significant temporal correlations. For example, pressure changes during mycelial growth directly affect the time node of primordia formation. The gating mechanism of LSTM can effectively retain key temporal features, filter noise data caused by environmental fluctuations, and avoid gradient vanishing or exploding problems, adapting to various growth cycle temporal prediction needs. The model input layer uses a standardized time-series parameter sequence, including core parameters (overall matrix weight increment, matrix pressure increment) and auxiliary correction parameters (CO2 concentration correction coefficient, matrix water content correction coefficient, electrical conductivity correction coefficient). Time-series samples are constructed according to the daily collection frequency, and each sample contains the parameter sequence of the previous N days. The output layer is the daily growth increment and the corresponding growth stage label.

[0050] The model training and optimization process relies on a standardized database: the database is divided into training and testing sets in an 8:2 ratio. The training set is used for model parameter iteration, and the testing set is used to verify generalization ability. Data augmentation is performed by expanding the sample size through methods such as time shifting and noise addition. Finally, LSTM time-series modeling is used to achieve a closed-loop process from real-time parameter input to dynamic output of growth stages and accurate cycle prediction, adapting to the actual application needs of different cultivation scenarios. On the other hand, the present invention also discloses an adaptive optimization system for environmental parameters in edible fungi breeding, which uses the aforementioned adaptive optimization method for environmental parameters in edible fungi breeding, including: A multi-dimensional environmental parameter acquisition module is used to collect multi-dimensional environmental parameters of edible fungi. The data processing and analysis module is used to construct a standard database and a growth cycle prediction model for edible fungi, and to predict the growth cycle of edible fungi based on multi-dimensional environmental parameters, and then output environmental parameters according to the growth cycle of edible fungi. The communication control module is used to adaptively adjust environmental parameters based on the output environmental parameters.

[0051] Specifically, the core sensor arrangement includes a high-precision electronic scale (model: JA5003N, measuring range 0-50kg, accuracy ±0.1g) deployed at the bottom of each cultivation container, which can weigh the edible fungi and the substrate together daily; a thin-film pressure sensor (model: FSR402, measuring range 0-1MPa, accuracy ±0.001MPa) is embedded in the middle layer of each substrate to synchronously collect substrate pressure, and the sensor lead is led out along the side wall of the container to avoid interfering with mycelial growth.

[0052] To assist in parameter correction, environmental sensor groups (including CO2, temperature, and humidity sensors) were deployed at a density of 5㎡ / unit in each cultivation area. The CO2 sensor was an infrared sensor (model: MH-Z19C, range 0-10000ppm, accuracy ±50ppm), and the temperature and humidity sensors were integrated temperature and humidity sensors (model: DHT22, temperature range -10-50℃, accuracy ±0.1℃, humidity range 0-100%RH, accuracy ±1%RH). The sensors were installed 30cm above the cultivation surface to maintain a non-contact distance from the edible fungi. A substrate moisture sensor (model: TDR-300, frequency domain reflectance type, measurement range 0-100%, accuracy ±0.1%) and a conductivity sensor (model: EC-300, probe type, range 0-20mS / cm, accuracy ±0.01mS / cm) were also used. For each batch of experiments, the sensors were inserted into three different areas of the substrate (surface, middle, and lower layers), and the average of the three measurements was taken as the final data.

[0053] Each cultivation area is equipped with one industrial-grade data acquisition unit (model: STM32F407, supporting 8 analog inputs and 16 digital inputs), which supports multi-channel parallel acquisition. The acquisition frequency is dynamically issued by the data processing and analysis module and is adjusted by default according to the growth stage.

[0054] The preprocessing algorithm is integrated into the built-in firmware of the data acquisition unit. It uses a 3-point moving average method to filter sensor noise and remove instantaneous fluctuation data. All parameter data are uniformly converted into JSON format and bound with batch number, acquisition time (accurate to the second), device number, and sensor number to ensure data traceability. The data is then transmitted to the data processing and analysis module through a communication link.

[0055] The data processing and analysis module is deployed on the control center server, adopting an integrated hardware and software configuration. The database unit is based on MySQL 8.0 to build a four-dimensional label database, storing more than 108 batches of valid data, and supporting hierarchical permission management and automatic backup. The model training and prediction unit is based on Python and TensorFlow to build an LSTM model. The parameter optimization unit uses the NSGA-III multi-objective algorithm, combined with the optimal parameter range in the database, to generate environmental parameter optimization schemes that are adapted to different devices and growth stages, and clearly define the control objectives and priorities.

[0056] The communication control module adopts a dual-mode communication and closed-loop control design to ensure real-time and accurate transmission and execution of commands. The communication submodule uses an RS485 bus for short-range communication and is equipped with 5G / Wi-Fi dual-mode redundant long-range communication, featuring fault self-diagnosis and automatic switching functions.

[0057] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An adaptive optimization method for environmental parameters in edible fungi breeding, characterized in that, Includes the following steps: S1: Construct a standard database of edible fungi growth cycles; S2: Collect multi-dimensional environmental parameters of edible fungi; S3: Construct a growth cycle prediction model, input multi-dimensional environmental parameters, and predict the growth cycle of edible fungi; The growth cycle prediction model uses the total weight of the substrate and substrate pressure from the multi-dimensional environmental parameters to construct a daily growth variable function, and accumulates the daily growth variables to obtain a comprehensive growth index. Finally, based on the threshold range of the comprehensive growth index corresponding to different growth stages, it predicts the current growth stage of the edible fungi. S4: Input the predicted growth cycle of edible fungi into the standard database described in step 1 to obtain standard environmental parameters, and adaptively adjust the environmental parameters. Based on the predicted growth cycle, standard environmental parameters for edible fungi at the corresponding stage are obtained from a standard database, and the real-time environmental parameters for edible fungi are adjusted accordingly.

2. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 1, characterized in that, In step S2, the environmental parameters of the edible fungi include: ambient temperature, ambient humidity, carbon dioxide concentration, light intensity, substrate temperature, substrate moisture content, substrate conductivity, substrate pressure, and total substrate weight.

3. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 1, characterized in that, In step S3, the daily growth variable function is further corrected by incorporating carbon dioxide concentration, matrix moisture content, and matrix conductivity.

4. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 3, characterized in that, The growth cycle prediction model is divided into at least four growth stages, and the comprehensive growth index is defined and the growth process stage of edible fungi is predicted by the threshold intervals corresponding to each stage.

5. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 3, characterized in that, The auxiliary correction of the carbon dioxide concentration uses segmented parameters, and the most suitable carbon dioxide concentration range is set according to the different growth stages of edible fungi.

6. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 3, characterized in that, The matrix conductivity and the matrix water content are used to correct the comprehensive growth index using a peak function.

7. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 1, characterized in that, In step S1, the standard database for the growth cycle of edible fungi includes environmental parameters, substrate parameters, growth phenotype parameters, and cycle time parameters.

8. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 7, characterized in that, In step S1, the standard database for the growth cycle of edible fungi collects full-cycle data for at least three types of edible fungi under different breeding batches, covering different seasons and different cultivation equipment.

9. The adaptive optimization method for environmental parameters in edible fungi breeding as described in claim 3, characterized in that, The time series modeling of the growth cycle prediction model is implemented using an LSTM time series model.

10. An adaptive optimization system for environmental parameters in edible fungi breeding, characterized in that, The adaptive optimization method for environmental parameters in edible fungi breeding as described in any one of claims 1-9 includes: A multi-dimensional environmental parameter acquisition module is used to collect multi-dimensional environmental parameters of edible fungi. The data processing and analysis module is used to construct a standard database and a growth cycle prediction model for edible fungi, and to predict the growth cycle of edible fungi based on multi-dimensional environmental parameters, and then output environmental parameters according to the growth cycle of edible fungi. The communication control module is used to adaptively adjust environmental parameters based on the output environmental parameters.

Images