Stropharia rugoso-annulata high-fruiting-rate cultivation system and method based on Juncao culture medium

Abstract

The invention relates to a Stropharia rugoso-annulata high-fruiting-rate cultivation system and method based on a Juncao culture medium, and belongs to the technical field of Stropharia rugoso-annulata planting. The Stropharia rugoso-annulata high-fruiting-rate cultivation system comprises an experimental design module, a data acquisition and preprocessing module, an evaluation index weight distribution module, a Stropharia rugoso-annulata cultivation parameter optimization module and a hyper-parameter optimization module; the experiment design module is used for receiving cultivation parameters input by a user and generating different experiment schemes; the data acquisition and preprocessing module is responsible for collecting evaluation index data and performing cleaning and normalization processing. The evaluation index weight distribution module calculates the weight of each index through a statistical method. The cultivation parameter optimization module is combined with a comprehensive evaluation formula, a convolutional neural network and a rhodeus ocellatus optimization algorithm to accurately find an optimal cultivation parameter combination. The hyper-parameter optimization module optimizes model hyper-parameters through a Bayesian optimization method, and the model performance is improved. The cultivation efficiency and the fruiting rate of the stropharia rugoso-annulata are remarkably improved, and powerful technical support is provided for large-scale cultivation of the stropharia rugoso-annulata.

Description

Technical Field

[0001] The present invention relates to the technical field of the cultivation of Stropharia rugoso-annulata, in particular to a high-yield cultivation system and method of Stropharia rugoso-annulata based on a Juncao culture medium substrate. Background Art

[0003] With the gradual development of the cultivation of Stropharia rugoso-annulata towards large-scale and industrialization, the demand for the preparation of strains and the optimization of culture media is increasing day by day. The traditional solid spawn production method has problems such as a long cycle, inconsistent mycelial age, weak mycelial vitality, and easy contamination by miscellaneous bacteria. Therefore, optimizing the culture medium formula and culture conditions has also become the focus of research. By screening different culture medium substrates and adjusting parameters such as the carbon-nitrogen ratio, the mycelial growth rate and biomass can be further improved. For example, it has been found that an appropriate carbon-nitrogen ratio of the culture material can provide more balanced nutrients for the growth of mycelia, thereby increasing the mycelial growth rate. At the same time, the particle size of the culture material also affects the mycelial growth rate, and an appropriate particle size can improve the air permeability of the culture medium and promote mycelial growth. The Juncao culture medium cultivation technology of Stropharia rugoso-annulata has made remarkable progress in recent years, but there are still many problems to be solved and room for optimization. The ratio of carbon source and nitrogen source in some culture media is unreasonable, resulting in slow mycelial growth or insufficient vitality. In the traditional culture medium formula, due to rich nutritional components and without strict sterilization treatment, it is easy to cause contamination by miscellaneous bacteria. Further optimizing the culture medium formula, improving resource utilization efficiency, reducing environmental pollution, and promoting the sustainable development of the Stropharia rugoso-annulata cultivation technology are urgent problems to be solved. Summary of the Invention

[0004] Based on this, in view of the problems that the ratio of carbon source and nitrogen source in the existing culture medium of Stropharia rugoso-annulata is unreasonable, resulting in slow mycelial growth or insufficient vitality, etc., it is necessary to provide a high-yield cultivation system and method of Stropharia rugoso-annulata based on a Juncao culture medium substrate.

[0005] The present invention is realized through the following technical solutions: A high-yield cultivation system of Stropharia rugoso-annulata based on a Juncao culture medium substrate, comprising:

[0006] An experimental design module, including a parameter input unit and a scheme generation unit; the parameter input unit receives the cultivation parameters of the Juncao culture medium of Stropharia rugoso-annulata input by the user; the scheme generation unit designs and implements cultivation experimental schemes of Stropharia rugoso-annulata in different ways according to the input parameters;

[0007] A data acquisition and preprocessing module, including a data acquisition unit, a data preprocessing unit and an encoding unit; the data acquisition unit is used to acquire the evaluation index data of Stropharia rugoso-annulata during the experiment and send it to the data preprocessing unit; the data preprocessing unit cleans and normalizes the input data and sends it to the encoding unit; the encoding unit encodes the preprocessed experimental data and makes it into a training set and a validation set, and sends it to the hyperparameter optimization module;

[0008] The evaluation index weight distribution module calculates the weights of the evaluation indexes for Stropharia rugosoannulata by statistically analyzing the weight distribution data of the evaluation indexes.

[0009] The Stropharia rugosoannulata cultivation parameter optimization module includes a comprehensive evaluation formula unit, a machine learning model unit, and a bitterling optimization unit. The comprehensive evaluation formula unit constructs a comprehensive evaluation formula for the cultivation method of Stropharia rugosoannulata based on the input evaluation index weight distribution results. The machine learning model unit constructs a machine learning model based on a convolutional neural network with the comprehensive evaluation formula as the objective function. The bitterling optimization unit applies the bitterling optimization algorithm to find the optimal combination of cultivation parameters.

[0010] The hyperparameter optimization module includes a model training unit and a Bayesian optimization unit. The model training unit trains the model based on the input training set by constructing a Gaussian process prior distribution. The Bayesian optimization unit uses the Bayesian optimization method to optimize the hyperparameters and evaluates the performance of the hyperparameter combinations through a validation set.

[0011] In one of the inventions, the Stropharia rugosoannulata cultivation experimental plan includes the treatment method of the Juncao culture medium substrate and the Juncao culture medium formula. The treatment method of the Juncao culture medium substrate includes raw material treatment, fermentation process treatment, and autoclaving treatment.

[0012] In one of the inventions, the Stropharia rugosoannulata evaluation index data includes the time for the sample to reach the preset mycelial concentration, the weight of the first flush of Stropharia rugosoannulata of the sample, and the polysaccharide content of the first flush of Stropharia rugosoannulata of the sample. The method for obtaining the index data is as follows: During the mycelial culture process of the experimental sample, samples are taken at preset time intervals by the five-point sampling method to observe the growth density and morphology of the mycelium, and the time for the mycelium to reach the preset growth concentration is recorded. After harvesting all the first flush of Stropharia rugosoannulata in the experimental sample area, they are collected, sorted, and weighed, and the total mass is recorded. The measurement method for the polysaccharide content of Stropharia rugosoannulata in the experimental sample is as follows:

[0013] All the first flush of Stropharia rugosoannulata fruiting bodies are collected from the experimental area. After washing the fresh first flush of Stropharia rugosoannulata, they are put into a dryer for dehydration. The dehydrated Stropharia rugosoannulata fruiting bodies are placed in a blender and ground into powder. Based on the water extraction and alcohol precipitation method, the Stropharia rugosoannulata powder is mixed with water in a preset ratio, heated, and then left to stand. Ethanol is added to the standing Stropharia rugosoannulata aqueous solution for mixing and filtering. The filtered Stropharia rugosoannulata extract is put into a reaction kettle for heating and concentration. After standing, the Stropharia rugosoannulata polysaccharide precipitate is collected. The protein in the polysaccharide precipitate is removed by the Sevag method to achieve dialysis purification of the Stropharia rugosoannulata polysaccharide precipitate. The phenol-sulfuric acid method is used to measure the concentration of Stropharia rugosoannulata polysaccharide in the purified polysaccharide precipitate. The polysaccharide content of the sample is calculated by combining the concentration of Stropharia rugosoannulata polysaccharide and the dry weight of the sample of the first flush of Stropharia rugosoannulata fruiting bodies.

[0014] In one of the inventions, data on the weight distribution of the evaluation indicators of Stropharia rugoso-annulata is collected in the form of a questionnaire. The content of the questionnaire on the weight distribution of the evaluation indicators of Stropharia rugoso-annulata includes: constructing a comparison matrix of the evaluation indicators of Stropharia rugoso-annulata, comparing any two evaluation indicators, and each element r of the comparison matrix of the evaluation indicators of Stropharia rugoso-annulata ij represents the degree of importance of the i-th indicator relative to the j-th indicator, and the degree of importance is evaluated through the Saaty scale

[0015] Normalize the questionnaire data and calculate the allocated weights of each evaluation indicator of Stropharia rugoso-annulata. The steps of normalization are as follows

[0016] Construct a comparison matrix T of the evaluation indicators of Stropharia rugoso-annulata; sum each column of the comparison matrix to obtain a row vector

[0017] Divide each element in the comparison matrix of the evaluation indicators of Stropharia rugoso-annulata by the sum of the corresponding column of this element to obtain the normalized comparison matrix T′

[0018] By summing all the elements in each row of the comparison matrix T′, an S-dimensional column vector of the weights ω of all the evaluation indicators of Stropharia rugoso-annulata is obtained

[0019] Calculate the consistency ratio C of the weight distribution result of the evaluation indicators of Stropharia rugoso-annulata based on the consistency test method R , and judge the rationality of its weight distribution. The calculation formula of the consistency ratio C R is as follows

[0020]

[0021] In the formula, C I represents the consistency index of the weight distribution result of the evaluation indicators of Stropharia rugoso-annulata, and R I represents the random consistency index corresponding to the number of evaluation indicators of Stropharia rugoso-annulata

[0022] The calculation formula of the consistency index C I is as follows

[0023]

[0024] In the formula, λ max represents the largest eigenvalue of the comparison matrix T of the evaluation indicators of Stropharia rugoso-annulata, and S represents the number of indicators

[0025] If C R is less than the preset value, it means that the consistency of the weight distribution result of the evaluation indicators of Stropharia rugoso-annulata is acceptable; otherwise, the weights of the evaluation indicators of Stropharia rugoso-annulata need to be re-evaluated

[0026] In one of the inventions, the calculation method of the comprehensive evaluation formula for the cultivation method of Stropharia rugoso-annulata is as follows

[0027]

[0028] Wherein, R k represents the comprehensive evaluation result of the cultivation method of Stropharia rugoso-annulata using the k-th experimental formula of mushroom grass culture medium; represents the j-th measurement result of the i-th evaluation index of Stropharia rugoso-annulata in the experiment of the k-th experimental formula of mushroom grass culture medium; ω i represents the calculation weight of the i-th evaluation index of Stropharia rugoso-annulata.

[0029] In one of the inventions, the steps of constructing an optimization model for Stropharia rugoso-annulata cultivation parameters based on machine learning are as follows:

[0030] Encode the Stropharia rugoso-annulata cultivation parameters as the input variables of the optimization model for Stropharia rugoso-annulata cultivation parameters;

[0031] Take the comprehensive evaluation formula of the Stropharia rugoso-annulata cultivation method as the objective function, and construct an optimization model for Stropharia rugoso-annulata cultivation parameters based on a convolutional neural network. The goal of the model is to predict the value of the objective function through the encoded Stropharia rugoso-annulata cultivation parameters input;

[0032] Randomly generate an initial population according to the range of Stropharia rugoso-annulata cultivation parameters, input the parameter combination of each individual into the machine learning model, and calculate the objective function value as the fitness value;

[0033] Gradually update the population through the bitterling algorithm until the loss function converges or reaches the maximum number of iterations; record the optimal parameter combination and its corresponding objective function value in each iteration, and finally determine the optimal cultivation parameter combination.

[0034] In one of the inventions, the data preprocessing unit preprocesses the experimental data including data cleaning and data standardization. Data cleaning includes identifying missing values in the samples and filling the missing values with the mean value; data standardization normalizes the data through the Z-score method to meet the input requirements of the Stropharia rugoso-annulata cultivation parameter encoding; randomly extract multiple preprocessed sample sets as the test set according to a preset ratio, and the remaining sample sets as the training set; adopt the K-fold cross-validation strategy, and take a part of the training set as the validation set in each training, and the rest as the training set for this training.

[0035] In one of the inventions, the Bayesian optimization method is used to optimize the hyperparameters of the optimization model for Stropharia rugoso-annulata cultivation parameters. The specific implementation steps of hyperparameter optimization are as follows:

[0036] Determine the value range of the convolutional neural network hyperparameters;

[0037] Construct a Gaussian process prior distribution of hyperparameters to guide the search process through the relationship smoothing between hyperparameters and objective function values;

[0038] Randomly select a set of hyperparameter combinations, train the model with the training set, and calculate the objective function value as the initial performance evaluation; update the posterior distribution according to the current hyperparameter combination and its performance evaluation results, and select a new hyperparameter combination through the posterior distribution for model training; evaluate the performance of the new hyperparameter combination on the validation set;

[0039] Select the hyperparameter combination with the optimal performance as the final hyperparameter optimization result.

[0040] In one of the inventions, the method for updating the hyperparameter combination of the convolutional neural network through the Gaussian process prior distribution is as follows:

[0041] P k+1 ={P k ∈N|EI(P k ) = maxEI(P k )}

[0042] In the formula, the calculation formula of EI is as follows:

[0043]

[0044] In the formula, P k+1 represents the new round of hyperparameter combination, EI represents the correction value of the hyperparameter combination, min(P k ) respectively represent the known maximum and minimum hyperparameter combination values, φ(), Φ() respectively represent the probability density function and cumulative distribution function of the standard normal distribution, and σ() represents the standard deviation of the hyperparameter combination.

[0045] In one of the inventions, the high-yield cultivation method of Stropharia rugosoannulata based on the Juncao culture medium includes the following steps:

[0046] S1: Determine the Stropharia rugosoannulata variety for research, and design several groups of Stropharia rugosoannulata cultivation experiments with different Juncao culture medium treatment methods;

[0047] S2: In each group of experiments, prepare the ingredients according to different Juncao culture medium formulas, and sow according to the preset sowing spacing of Stropharia rugosoannulata;

[0048] S3: Record the time when the experimental samples in each Stropharia rugosoannulata cultivation experiment reach the preset mycelium concentration, the total mass per square meter of the first flush of Stropharia rugosoannulata, and the polysaccharide content of Stropharia rugosoannulata; preprocess the condition parameters and measurement data of each Stropharia rugosoannulata cultivation experiment;

[0049] S4: Determine the evaluation indicators for Stropharia rugosoannulata, collect the weight distribution data of the evaluation indicators for Stropharia rugosoannulata to construct a comparison matrix of the evaluation indicators for Stropharia rugosoannulata, and establish a comprehensive evaluation formula for the cultivation method of Stropharia rugosoannulata;

[0050] S5: Use the comprehensive evaluation formula for the cultivation method of Stropharia rugosoannulata as the objective function, construct an optimization model for the cultivation parameters of Stropharia rugosoannulata based on machine learning. The input of the model is the encoding of the cultivation experiment parameters of Stropharia rugosoannulata, and the bitterling optimization algorithm is used to iteratively find the optimal parameter combination;

[0051] S6: Divide the preprocessed experimental data into a training set and a validation set, use the Bayesian optimization method to optimize the hyperparameters of the optimization model for the cultivation parameters of Stropharia rugosoannulata, train the model on the training set, and use the validation set to evaluate the performance of different hyperparameter combinations, and select the model with the optimal hyperparameter combination.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] In the present invention, a high-yield cultivation system and method for Stropharia rugosoannulata based on a Juncao culture medium is proposed. Through systematic experimental design, data collection and preprocessing, evaluation index weight allocation, cultivation parameter optimization, and hyperparameter optimization modules, the optimization of the cultivation parameters of Stropharia rugosoannulata and high-efficiency fruiting are realized. In the prior art, the traditional solid spawn production method has problems such as a long cycle, inconsistent mycelial age, and weak mycelial vitality. By optimizing the culture medium formula and treatment method and combining machine learning and optimization algorithms, the present invention can significantly improve the growth rate and vitality of the mycelium. For example, through the experimental design module, experiments are carried out according to different treatment methods (such as raw material treatment, fermentation process treatment, autoclaving treatment) and formulas of the Juncao culture medium, and the most suitable culture medium formula for the growth of Stropharia rugosoannulata is screened out, thereby shortening the mycelial growth cycle and improving the mycelial quality.

[0054] Through the comprehensive evaluation formula and machine learning model and combining with the optimization algorithm, the present invention can accurately find the optimal cultivation parameter combination. For example, by collecting the data of evaluation indicators such as the time when the mycelium reaches the preset concentration, the total mass and polysaccharide content of the first flush of Stropharia rugosoannulata in the experimental samples, a comprehensive evaluation formula is constructed, and then the cultivation parameters are optimized, thereby significantly improving the fruiting rate and yield of Stropharia rugosoannulata. This not only improves the economic benefits but also provides technical support for the large-scale production of Stropharia rugosoannulata.

[0055] In the prior art, the weight allocation of evaluation indicators often relies on empirical judgment and lacks scientific basis. The present invention collects the weight allocation data of evaluation indicators in the form of questionnaires and uses the consistency test method to judge the rationality of the weight allocation results. For example, by constructing a comparison matrix of the evaluation indicators of Stropharia rugosoannulata, using the Saaty scale table to evaluate the degree of importance, and through normalization processing and consistency ratio calculation, the scientificity and rationality of the weight allocation are ensured. This makes the evaluation process more objective and accurate, providing a reliable basis for the subsequent optimization of cultivation parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 FIG. is a schematic structural diagram of a high-yield cultivation system of Stropharia rugosoannulata based on a forage mushroom substrate for Example 1;

[0057] Figure 2 FIG. is a step diagram of constructing an optimization model for the cultivation parameters of Stropharia rugosoannulata based on machine learning in Example 1;

[0058] Figure 3 FIG. is a step diagram of a high-yield cultivation method of Stropharia rugosoannulata based on a forage mushroom substrate in Example 2. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0060] It should be noted that when a component is referred to as being "mounted on" another component, it can be directly on the other component or there can also be an intermediate component. When a component is considered to be "disposed on" another component, it can be directly disposed on the other component or there may be an intermediate component at the same time. When a component is considered to be "fixed to" another component, it can be directly fixed to the other component or there may be an intermediate component at the same time.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" used herein includes any and all combinations of one or more of the related listed items.

[0062] Example 1

[0063] Figure 1This is a schematic structural diagram of the high-yield cultivation system of Stropharia rugosoannulata based on the mushroom grass culture medium in Embodiment 1. Figure 2 This is a step diagram of constructing an optimization model for the cultivation parameters of Stropharia rugosoannulata based on machine learning in Embodiment 1. Please refer to Figure 1 - Figure 2 In this embodiment, a high-yield cultivation system of Stropharia rugosoannulata based on the mushroom grass culture medium is provided, including:

[0064] An experimental design module, including a parameter input unit and a scheme generation unit; the parameter input unit receives the cultivation parameters of the Stropharia rugosoannulata mushroom grass culture medium input by the user; the scheme generation unit designs and implements different Stropharia rugosoannulata cultivation experimental schemes according to the input parameters.

[0065] A data collection and preprocessing module, including a data collection unit, a data preprocessing unit, and an encoding unit; the data collection unit is used to collect the evaluation index data of Stropharia rugosoannulata during the experiment and send it to the data preprocessing unit; the data preprocessing unit cleans and normalizes the input data and sends it to the encoding unit; the encoding unit encodes the preprocessed experimental data to make a training set and a validation set and sends them to the hyperparameter optimization module.

[0066] An evaluation index weight distribution module, which calculates the weights of the evaluation indexes of Stropharia rugosoannulata by statistically analyzing the weight distribution data of the evaluation indexes.

[0067] An optimization module for the cultivation parameters of Stropharia rugosoannulata, including a comprehensive evaluation formula unit, a machine learning model unit, and a bitterling optimization unit; the comprehensive evaluation formula unit constructs a comprehensive evaluation formula for the cultivation method of Stropharia rugosoannulata according to the input evaluation index weight distribution result; the machine learning model unit constructs a machine learning model based on a convolutional neural network with the comprehensive evaluation formula as the objective function; the bitterling optimization unit applies the bitterling optimization algorithm to find the optimal combination of cultivation parameters.

[0068] A hyperparameter optimization module, including a model training unit and a Bayesian optimization unit; the model training unit trains the model according to the input training set by constructing a Gaussian process prior distribution; the Bayesian optimization unit uses the Bayesian optimization method to optimize the hyperparameters and evaluates the performance of the hyperparameter combination through the validation set.

[0069] The cultivation experiment plan for Stropharia rugoso-annulata includes the treatment method of the Juncao culture medium substrate and the formula of the Juncao culture medium; the Stropharia rugoso-annulata variety used in the research is Wine Red Stropharia No. 1, and the different treatment methods of the Juncao culture medium substrate in groups A, B, and C respectively represent raw material treatment, fermentation process treatment, and autoclaving treatment. In step S2, the composition components of the experimental Juncao culture medium formula are as follows: 45% of the main raw material, 33% of peach wood sawdust, 20% of wheat bran, 1% of gypsum, and 1% of vitamins; the main raw materials of different experimental Juncao culture medium formulas are different, and other composition components remain the same. The replaceable types of the main raw material include Pennisetum giganteum, Pennisetum purpureum, Pennisetum alopecuroides, or an equal ratio mixture of any two kinds of forage grasses; the sowing spacing of Stropharia rugoso-annulata in the experimental samples can be selected as 8 cm, 10 cm, 12 cm, or 14 cm.

[0070] In this embodiment, three different treatment methods of the Juncao culture medium substrate are designed, which can effectively compare the effects of different treatment methods on the growth of Stropharia rugoso-annulata, and can screen out the most suitable treatment method of the culture medium substrate for the growth of Stropharia rugoso-annulata, so as to improve the growth rate and vitality of the mycelium. In the experimental Juncao culture medium formula, the replaceable types of the main raw material include Pennisetum giganteum, Pennisetum purpureum, Pennisetum alopecuroides, or an equal ratio mixture of any two kinds of forage grasses. The flexibility of the formula enables the cultivation process to be adjusted according to the local resource situation, reducing the production cost and ensuring the quality of the culture medium at the same time.

[0071] The evaluation index data of Stropharia rugoso-annulata include the time for the sample to reach the preset mycelium concentration, the weight of the first flush of Stropharia rugoso-annulata in the sample, and the polysaccharide content of the first flush of Stropharia rugoso-annulata in the sample; during the mycelium culture process of the experimental sample, samples within the same square meter are sampled every 6 hours by the five-point sampling method and the growth density and morphology of the mycelium are observed through a microscope, and the time when the mycelium concentration reaches "++++" is recorded; the experimental sample area is divided according to the area of each square decimeter, and all the first flush of Stropharia rugoso-annulata within the area are harvested, sorted, and weighed, and the total mass is recorded; the measurement method of the polysaccharide content per square meter of the first flush of Stropharia rugoso-annulata in the experimental sample is as follows:

[0072] All the first flush of Stropharia rugoso-annulata fruiting bodies are collected from each square meter of the experimental area. After washing the fresh first flush of Stropharia rugoso-annulata, they are put into a dryer for dehydration. The dehydrated Stropharia rugoso-annulata fruiting bodies are placed in a blender and crushed into powder. Based on the water extraction and alcohol precipitation method, the Stropharia rugoso-annulata powder is mixed with water according to a preset ratio and heated to 100 °C and then left to stand; ethanol is added to the standing Stropharia rugoso-annulata aqueous solution for mixing and filtering. The filtered Stropharia rugoso-annulata extract is put into a reaction kettle for heating and concentration, and after standing, the Stropharia rugoso-annulata polysaccharide precipitate is collected; the protein in the polysaccharide precipitate is removed by the Sevag method to realize the dialysis purification of the Stropharia rugoso-annulata polysaccharide precipitate, and the phenol-sulfuric acid method is used to determine the Stropharia rugoso-annulata polysaccharide concentration in the purified polysaccharide precipitate; the polysaccharide content per square meter of the sample is calculated by combining the Stropharia rugoso-annulata polysaccharide concentration and the dry weight of the sample of the first flush of Stropharia rugoso-annulata fruiting bodies.

[0073] Collect the data of the weight distribution of the evaluation indicators of Stropharia rugosoannulata through questionnaires. The content of the questionnaire for the weight distribution of the evaluation indicators of Stropharia rugosoannulata includes: constructing a comparison matrix of the evaluation indicators of Stropharia rugosoannulata, comparing any two evaluation indicators, and each element r of the comparison matrix of the evaluation indicators of Stropharia rugosoannulata ij represents the degree of importance of the i-th indicator relative to the j-th indicator, and the degree of importance is evaluated through the Saaty scale

[0074] Normalize the questionnaire data and calculate the allocated weights of each evaluation indicator of Stropharia rugosoannulata. The steps of normalization are as follows

[0075] Construct a comparison matrix T of the evaluation indicators of Stropharia rugosoannulata; sum each column of the comparison matrix to obtain a row vector

[0076] Divide each element in the comparison matrix of the evaluation indicators of Stropharia rugosoannulata by the sum of the corresponding column of this element to obtain the normalized comparison matrix T′

[0077] By summing all the elements in each row of the comparison matrix T′, obtain an S-dimensional column vector of the weights ω of all the evaluation indicators of Stropharia rugosoannulata

[0078] Calculate the consistency ratio C of the weight distribution result of the evaluation indicators of Stropharia rugosoannulata based on the consistency test method R , and judge the rationality of its weight distribution. The calculation formula of the consistency ratio C R is as follows

[0079]

[0080] In the formula, C I represents the consistency index of the weight distribution result of the evaluation indicators of Stropharia rugosoannulata, and R I represents the random consistency index corresponding to the number of evaluation indicators of Stropharia rugosoannulata

[0081] The calculation formula of the consistency index C I is as follows

[0082]

[0083] In the formula, λ max represents the largest eigenvalue of the comparison matrix T of the evaluation indicators of Stropharia rugosoannulata, and S represents the number of indicators

[0084] If C R is less than the preset value, it means that the consistency of the weight distribution result of the evaluation indicators of Stropharia rugosoannulata is acceptable; otherwise, the weights of the evaluation indicators of Stropharia rugosoannulata need to be re-evaluated. In this embodiment, if C R the preset value is 0.1

[0085] In this embodiment, data on the weight distribution of evaluation indicators is collected in the form of a questionnaire, and a consistency test method is used to judge the rationality of the weight distribution results. By constructing a comparison matrix of evaluation indicators for Stropharia rugoso-annulata, the Saaty scale is used to evaluate the degree of importance, and through normalization and consistency ratio calculation, the scientificity and rationality of the weight distribution are ensured. This makes the evaluation process more objective and accurate, providing a reliable basis for the subsequent optimization of cultivation parameters.

[0086] The calculation method of the comprehensive evaluation formula for the cultivation method of Stropharia rugoso-annulata is as follows:

[0087]

[0088] In the formula, R k represents the comprehensive evaluation result of the cultivation method of Stropharia rugoso-annulata for the kth experimental Juncao culture medium formula; represents the jth measurement result of the ith evaluation indicator of Stropharia rugoso-annulata in the kth experimental Juncao culture medium formula test; ω i represents the calculated weight of the ith evaluation indicator of Stropharia rugoso-annulata.

[0089] The steps for constructing an optimization model for Stropharia rugoso-annulata cultivation parameters based on machine learning are as follows:

[0090] Encode the treatment method of Juncao culture medium, the Juncao culture medium formula, the sowing spacing of Stropharia rugoso-annulata, and the number of tests in the Stropharia rugoso-annulata cultivation experiment as input variables for the optimization model of Stropharia rugoso-annulata cultivation parameters;

[0091] Taking the comprehensive evaluation formula for the cultivation method of Stropharia rugoso-annulata as the objective function, construct an optimization model for Stropharia rugoso-annulata cultivation parameters based on a convolutional neural network. The goal of the model is to predict the value of the objective function through the encoded cultivation parameters of Stropharia rugoso-annulata input;

[0092] Randomly generate an initial population according to the range of Stropharia rugoso-annulata cultivation parameters, input the parameter combination of each individual into the machine learning model, and calculate the value of the objective function as the fitness value;

[0093] Through the movement, foraging, and reproduction operations of the bitterling algorithm, gradually update the population until the loss function converges or reaches the maximum number of iterations; record the optimal parameter combination and its corresponding objective function value in each iteration, and finally determine the optimal cultivation parameter combination.

[0094] In this embodiment, by introducing machine learning and optimization algorithms, the intelligentization and automation of the cultivation process of Stropharia rugoso-annulata are realized. In this embodiment, a cultivation parameter optimization model is constructed through a convolutional neural network and combined with the Rhodeus ocellatus optimization algorithm, which can automatically find the optimal combination of cultivation parameters. This not only improves the cultivation efficiency, but also reduces manual intervention and labor intensity, providing strong support for the large-scale and industrial development of Stropharia rugoso-annulata.

[0095] The data preprocessing unit preprocesses the experimental data, including data cleaning and data standardization. Data cleaning includes identifying missing values in the samples and filling the missing values with the mean value; data standardization normalizes the data through the Z-score standardization method to meet the input requirements of the coding of Stropharia rugoso-annulata cultivation parameters. After encoding the preprocessed experimental data, 80% is divided into the training set, and the remaining 20% is divided into the validation set. Data standardization processes the data through the Z-score standardization, and the calculation formula is as follows:

[0096]

[0097] In the formula, x represents the original data value, μ represents the mean value of the data set, and σ represents the standard deviation of the data set.

[0098] Randomly select several preprocessed sample sets as the test set, and the remaining sample sets as the training set; adopt the K-fold cross-validation strategy. Each time during training, take a part of the training set as the validation set, and the rest as the training set for this training.

[0099] The K-fold cross-validation strategy adopted in this embodiment can effectively improve the generalization ability of the model and reduce the risk of overfitting. By using a part of the training set as the validation set, it can ensure that each sample will be verified, which is particularly important for small-sample data. During the implementation process, attention should be paid to the computational cost of model training, the selection of the number of folds, and the balance of data distribution to obtain more reliable model evaluation results.

[0100] The Bayesian optimization method is used to optimize the hyperparameters of the Stropharia rugoso-annulata cultivation parameter optimization model. The specific implementation steps for hyperparameter optimization are as follows:

[0101] Determine the value ranges of the learning rate, the number of convolutional layers, the number of convolutional kernels, and the regularization parameter of the convolutional neural network;

[0102] Construct a Gaussian process prior distribution of the hyperparameters through the smoothing of the relationship between the hyperparameters and the objective function values to guide the search process;

[0103] Randomly select a set of hyperparameter combinations, train the model using the training set, and calculate the objective function value as the initial performance evaluation; update the posterior distribution based on the current hyperparameter combination and its performance evaluation result, and select a new hyperparameter combination through the posterior distribution for model training; evaluate the performance of the new hyperparameter combination on the validation set;

[0104] Select the hyperparameter combination with the optimal performance as the final hyperparameter optimization result.

[0105] The method for updating the hyperparameter combination of the convolutional neural network through the Gaussian process prior distribution is as follows:

[0106] P k+1 ={P k ∈N|EI(P k ) = maxEI(P k )

[0107] In the formula, the calculation formula of EI is as follows:

[0108]

[0109] In the formula, P k+1 represents the new round of hyperparameter combination, EI represents the correction value of the hyperparameter combination, min(P k ) respectively represent the known maximum and minimum hyperparameter combination values, φ(), Φ() respectively represent the probability density function and cumulative distribution function of the standard normal distribution, and σ() represents the standard deviation of the hyperparameter combination.

[0110] In this embodiment, through the Gaussian process optimization method, a Gaussian process prior distribution between hyperparameters and the objective function value is constructed, which can efficiently search for the optimal hyperparameter combination. Compared with traditional grid search and random search, the Gaussian process optimization method can find a better hyperparameter combination within fewer iterations, significantly improving the optimization efficiency. It has important application value in the Stropharia rugoso-annulata cultivation system and can significantly improve the cultivation efficiency and yield.

[0111] Example 2:

[0112] Figure 3 It is a step diagram of a high-yield cultivation method of Stropharia rugoso-annulata based on a mushroom grass substrate in Example 2. This embodiment provides a high-yield cultivation method of Stropharia rugoso-annulata based on a mushroom grass substrate, which can be applied to the high-yield cultivation system of Stropharia rugoso-annulata based on a mushroom grass substrate in Example 1. The method includes the following steps:

[0113] S1: Determine the Stropharia rugoso-annulata variety for research, and design several groups of Stropharia rugoso-annulata cultivation experiments with different mushroom grass substrate treatment methods;

[0114] S2: In each group of experiments, different Juncao culture medium formulas were used for preparation, and the Stropharia rugosa was sown according to the preset spacing;

[0115] S3: Record the time when the experimental sample reaches the preset mycelium concentration, the total mass per square meter of the first batch of Stropharia in each Stropharia cultivation experiment, and the polysaccharide content of Stropharia; pre-process the condition parameters and measurement data of each Stropharia cultivation experiment;

[0116] S4: Determine the evaluation index of Stropharia, collect the weight distribution data of the evaluation index of Stropharia, construct the comparison matrix of the evaluation index of Stropharia, and establish the comprehensive evaluation formula of the cultivation method of Stropharia;

[0117] S5: Taking the comprehensive evaluation formula of Stropharia cultivation methods as the objective function, a Stropharia cultivation parameter optimization model was constructed based on machine learning. The model input was the Stropharia cultivation experimental parameter encoding, and the minnow optimization algorithm was used to iteratively find the optimal parameter combination.

[0118] S6: The preprocessed experimental data were divided into a training set and a validation set. The Bayesian optimization method was used to optimize the hyperparameters of the parameter optimization model for the cultivation of Stropharia rugosa. The model was trained on the training set, and the validation set was used to evaluate the performance of different hyperparameter combinations, and the model with the optimal hyperparameter combination was selected.

[0119] The present embodiment realizes the efficient optimization of the cultivation process of Pleurotus eryngii through systematic experimental design and scientific data processing methods. First, by determining the Pleurotus eryngii varieties used for research and designing cultivation experiments of multiple groups of different mushroom grass culture substrate treatment methods, the influence of different treatment methods on mycelium growth and mushroom fruiting effect can be comprehensively evaluated. During the experiment, the key indicators such as the time when the mycelium concentration reaches the preset value, the yield and polysaccharide content of the first batch of Pleurotus eryngii were recorded in detail, and the experimental data were pre-processed to ensure the accuracy and reliability of the data. By constructing an evaluation index comparison matrix and a comprehensive evaluation formula, the weights of each evaluation index are scientifically allocated, providing a solid foundation for subsequent parameter optimization. The cultivation parameter optimization model based on machine learning combined with the minnow optimization algorithm can efficiently find the optimal cultivation parameter combination and significantly improve the cultivation efficiency and yield. In addition, the Bayesian optimization method is used to optimize the hyperparameters of the model, which further improves the performance and stability of the model. The application of this series of scientific methods not only improves the fruiting rate and yield of Pleurotus ostreatus, but also reduces production costs and the risk of bacterial contamination, providing strong technical support for the large-scale and industrialized cultivation of Pleurotus ostreatus, and has significant economic and ecological benefits.

[0120] The above embodiments merely illustrate several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A high-yield cultivation system for Stropharia rugosoannulata based on a mushroom grass culture medium, characterized in that, Including: An experimental design module, including a parameter input unit and a scheme generation unit; The parameter input unit receives the cultivation parameters of the Stropharia rugosoannulata straw medium input by the user; The scheme generation unit designs and implements the cultivation experiment schemes of Stropharia rugosoannulata in different ways according to the input parameters; A data acquisition and preprocessing module, including a data acquisition unit, a data preprocessing unit and a coding unit; the data acquisition unit is used to acquire the evaluation index data of Stropharia rugosoannulata during the experiment process and send it to the data preprocessing unit; the data preprocessing unit cleans and normalizes the input data and sends it to the coding unit; the coding unit encodes the preprocessed experimental data to make a training set and a validation set and sends them to the hyperparameter optimization module; An evaluation index weight allocation module, which calculates the weights of the Stropharia rugosoannulata evaluation indexes by statistically analyzing the weight allocation data of the evaluation indexes; A Stropharia rugosoannulata cultivation parameter optimization module, including a comprehensive evaluation formula unit, a machine learning model unit and a Rhodeus ocellatus optimization unit; The comprehensive evaluation formula unit constructs a comprehensive evaluation formula for the cultivation method of Stropharia rugosoannulata according to the input evaluation index weight allocation result; the machine learning model unit constructs a machine learning model based on a convolutional neural network with the comprehensive evaluation formula as the objective function; the Rhodeus ocellatus optimization unit applies the Rhodeus ocellatus optimization algorithm to find the optimal cultivation parameter combination; A hyperparameter optimization module, including a model training unit and a Bayesian optimization unit; the model training unit trains the model according to the input training set by constructing a Gaussian process prior distribution; the Bayesian optimization unit uses the Bayesian optimization method to optimize the hyperparameters and evaluates the performance of the hyperparameter combination through the validation set.

2. The high-yield cultivation system of Stropharia rugoso-annulata based on Juncao culture medium according to claim 1, characterized in that, The Stropharia rugosoannulata cultivation experiment scheme includes the treatment method of the straw medium and the formula of the straw medium; the treatment method of the straw medium includes raw material treatment, fermentation process treatment, and autoclaving treatment.

3. The high-yield cultivation system of Stropharia rugoso-annulata based on Juncao culture medium according to claim 1, characterized in that, The Stropharia rugosoannulata evaluation index data includes the time for the sample to reach the preset mycelial concentration, the weight of the first flush of Stropharia rugosoannulata of the sample, and the polysaccharide content of the first flush of Stropharia rugosoannulata of the sample; the acquisition method of the index data is as follows: during the mycelial culture process of the experimental sample, the sample is sampled at preset time intervals by the five-point sampling method to observe the growth density and morphology of the mycelium, and the time when the mycelium reaches the preset growth concentration is recorded; after harvesting all the first flush of Stropharia rugosoannulata in the experimental sample area, they are collected, sorted and weighed, and the total mass is recorded; the measurement method of the polysaccharide content of Stropharia rugosoannulata in the experimental sample is as follows: Collect all the first - crop fruiting bodies of Stropharia rugoso - annulata from the experimental area. Wash the fresh first - crop Stropharia rugoso - annulata and put them into a dryer for dehydration. Place the dehydrated Stropharia rugoso - annulata fruiting bodies in a blender and crush them into powder. Based on the water - extraction and alcohol - precipitation method, mix the Stropharia rugoso - annulata powder with water according to a preset ratio, heat it and then let it stand for treatment. Add ethanol to the standing Stropharia rugoso - annulata aqueous solution for mixing and filtration. Put the filtered Stropharia rugoso - annulata extract into a reaction kettle to heat and concentrate it. After standing, collect the Stropharia rugoso - annulata polysaccharide precipitate. Remove the protein in the polysaccharide precipitate by the Sevag method to realize the dialysis purification of the Stropharia rugoso - annulata polysaccharide precipitate, and use the phenol - sulfuric acid method to determine the concentration of Stropharia rugoso - annulata polysaccharide in the purified polysaccharide precipitate. Calculate the content of Stropharia rugoso - annulata polysaccharide in the sample by combining the concentration of Stropharia rugoso - annulata polysaccharide and the dry weight of the sample of the first - crop Stropharia rugoso - annulata fruiting bodies.

4. The high-yield cultivation system of Stropharia rugoso-annulata based on Juncao culture medium according to claim 1, wherein Collect the data of the weight distribution of the evaluation indexes of Stropharia rugoso-annulata through questionnaires. The content of the questionnaire on the weight distribution of the evaluation indexes of Stropharia rugoso-annulata includes: constructing a comparison matrix of the evaluation indexes of Stropharia rugoso-annulata, comparing any two evaluation indexes, and each element r ij represents the importance degree of the ith index relative to the jth index, and the importance degree is evaluated through the Saaty scale table; Perform normalization processing on the questionnaire data, and calculate the distribution weights of the evaluation indexes of Stropharia rugoso - annulata. The steps of the normalization processing are as follows: Construct a comparison matrix T of Stropharia rugoso - annulata evaluation indexes; sum each column of the comparison matrix to obtain a row vector; Divide each element in the Stropharia rugoso - annulata evaluation index comparison matrix by the sum of the corresponding column of this element to obtain a normalized comparison matrix T′; By summing all the elements of each row of the comparison matrix T′, obtain an S - dimensional column vector of the weights ω of all Stropharia rugoso - annulata evaluation indexes; Calculating the consistency ratio C of the weight distribution results of the evaluation indicators of Stropharia rugoso-annulata based on the consistency test method R , and judging the rationality of its weight distribution. The calculation formula of the consistency ratio C R is as follows: Where C I represents the consistency index of the weight distribution result of the evaluation indexes of *Stropharia rugoso-annulata*, and R I represents the random consistency index corresponding to the number of the evaluation indexes of *Stropharia rugoso-annulata*; The consistency index C I has the following calculation formula: where λ max represents the maximum eigenvalue of the comparison matrix T of the evaluation index of the Stropharia rugoso-annulata, and S represents the number of indexes; If C R is less than the preset value, it indicates that the consistency of the weight distribution result of the evaluation index of *Stropharia rugoso-annulata* can be accepted; otherwise, the weights of the evaluation indexes of *Stropharia rugoso-annulata* need to be re-evaluated.

5. The high-yield cultivation system of Stropharia rugosoannulata based on mushroom grass culture medium according to claim 1, characterized in that, The calculation method of the comprehensive evaluation formula of the Stropharia rugoso - annulata cultivation method is as follows: where, R k represents the comprehensive evaluation result of the cultivation method of Stropharia rugosoannulata using the k-th experimental formula of Juncao culture medium; represents the j-th measurement result of the i-th evaluation index of Stropharia rugosoannulata in the experiment of the k-th experimental formula of Juncao culture medium; ω i represents the calculation weight of the i-th evaluation index of Stropharia rugosoannulata.

6. The high-yield cultivation system of Stropharia rugoso-annulata based on Juncao culture medium according to claim 1, characterized in that The steps of constructing an optimization model for Stropharia rugoso - annulata cultivation parameters based on machine learning are as follows: Encode the Stropharia rugoso - annulata cultivation parameters as the input variables of the optimization model for Stropharia rugoso - annulata cultivation parameters; Take the comprehensive evaluation formula of the Stropharia rugoso - annulata cultivation method as the objective function, and construct an optimization model for Stropharia rugoso - annulata cultivation parameters based on a convolutional neural network. The goal of the model is to predict the value of the objective function through the encoded Stropharia rugoso - annulata cultivation parameters input; Randomly generate an initial population according to the range of Stropharia rugoso - annulata cultivation parameters, input the parameter combination of each individual into the machine learning model, and calculate the objective function value as the fitness value; Gradually update the population through the bitterling algorithm until the loss function converges or reaches the maximum number of iterations; record the optimal parameter combination and its corresponding objective function value in each iteration, and finally determine the optimal cultivation parameter combination.

7. The high-yield cultivation system of Stropharia rugoso-annulata based on Juncao culture medium according to claim 1, characterized in that, The data pre - processing unit pre - processes the experimental data including data cleaning and data standardization. Data cleaning includes identifying missing values in the samples and filling the missing values with the mean value; data standardization normalizes the data by the Z - score method to meet the input requirements of the Stropharia rugoso - annulata cultivation parameter encoding. Randomly select multiple pre - processed sample sets as the test set according to a preset ratio, and the remaining sample sets as the training set; adopt the K - fold cross - validation strategy, and take a part of the training set as the validation set each time during training, and the rest as the training set for this training.

8. The high-yield cultivation system of Stropharia rugosoannulata based on Juncao culture medium according to claim 1, wherein, Adopt the Bayesian optimization method to optimize the hyperparameters of the optimization model for Stropharia rugoso - annulata cultivation parameters. The specific implementation steps of hyperparameter optimization are as follows: Determine the value range of the hyperparameters of the convolutional neural network; Smoothing the relationship between hyperparameters and objective function values to construct a Gaussian process prior distribution of hyperparameters to guide the search process; Randomly select a set of hyperparameter combinations, train the model using the training set, and calculate the objective function value as the initial performance evaluation; update the posterior distribution based on the current hyperparameter combination and its performance evaluation results, and select a new hyperparameter combination through the posterior distribution for model training; evaluate the performance of the new hyperparameter combination on the validation set; Select the hyperparameter combination with the optimal performance as the final hyperparameter optimization result.

9. The high-yield cultivation system of Stropharia rugoso-annulata based on Juncao culture medium according to claim 8, characterized in that, The method for updating the hyperparameter combination of the convolutional neural network through the Gaussian process prior distribution is as follows: P k+1 = {P k ∈ N | EI(P k ) = maxEI(P k )} In the formula, the calculation formula of EI is as follows: where P k+1 represents a new round of hyperparameter combinations, EI represents the correction value of the hyperparameter combination, min(P k ) respectively represent the known maximum and minimum hyperparameter combination values, φ() and Φ() respectively represent the probability density function and cumulative distribution function of the standard normal distribution, and σ() represents the standard deviation of the hyperparameter combination.

10. A cultivation method for high yield of Stropharia rugoso-annulata based on a mushroom grass culture medium, which uses the cultivation system for high yield of Stropharia rugoso-annulata based on a mushroom grass culture medium as described in any one of claims 1-9, characterized in that It includes the following steps: S1: Determine the variety of Stropharia rugosoannulata for research, and design several groups of Stropharia rugosoannulata cultivation experiments with different treatment methods of Juncao culture media; S2: In each group of experiments, prepare the ingredients according to different Juncao culture medium formulas, and sow according to the preset sowing spacing of Stropharia rugosoannulata; S3: Record the time when the experimental samples in each Stropharia rugosoannulata cultivation experiment reach the preset mycelium concentration, the total mass per square meter of the first flush of Stropharia rugosoannulata, and the polysaccharide content of Stropharia rugosoannulata; preprocess the condition parameters and measurement data of each Stropharia rugosoannulata cultivation experiment; S4: Determine the evaluation indicators of Stropharia rugosoannulata, collect the weight distribution data of the evaluation indicators of Stropharia rugosoannulata to construct a comparison matrix of the evaluation indicators of Stropharia rugosoannulata, and establish a comprehensive evaluation formula for the cultivation method of Stropharia rugosoannulata; S5: Using the comprehensive evaluation formula for the cultivation method of Stropharia rugosoannulata as the objective function, construct an optimization model for Stropharia rugosoannulata cultivation parameters based on machine learning. The input of the model is the coding of Stropharia rugosoannulata cultivation experiment parameters, and the bitterling optimization algorithm is used to iteratively find the optimal parameter combination; S6: Divide the preprocessed experimental data into a training set and a validation set, use the Bayesian optimization method to optimize the hyperparameters of the Stropharia rugosoannulata cultivation parameter optimization model, train the model on the training set, and use the validation set to evaluate the performance of different hyperparameter combinations, and select the model with the optimal hyperparameter combination.

Images