Organic fertilizer production parameter optimization control method for compound microbial agent

Abstract

The invention relates to the technical field of production parameter control, and particularly discloses an organic fertilizer production parameter optimization control method for a compound microbial agent, which comprises the following steps of: calculating a temperature fluctuation index and a pH stability index according to temperature data and a pH value in a fermentation stage so as to quantitatively evaluate the stability of a fermentation environment; evaluating the external interference degree by using the normalized comprehensive influence factor, intelligently analyzing the microbial ecological disorder condition through clustering analysis and a decision tree algorithm in combination with microbial concentration data, and calculating a microbial ecological disorder fluctuation coefficient; based on an evaluation result, dynamically calculating an adjustment factor, accurately adjusting the temperature and the pH value in the fermentation condition, and ensuring that the microbial flora is in an optimal active state; finally, whether the fermentation parameters reach the standard or not is determined by re-evaluating the adjusted flora state, so that the quality and the production efficiency of the organic fertilizer are ensured.

Description

Technical Field

[0001] The invention relates to the technical field of production parameter control, and in particular to an organic fertilizer production parameter optimization control method for a composite microbial agent. Background Art

[0002] With the global emphasis on environmental protection and sustainable development, organic fertilizers, as green alternatives to traditional chemical fertilizers, are gradually becoming an important part of modern agricultural production. Organic fertilizers can not only improve soil structure and soil fertility, but also reduce the pollution caused by chemical fertilizers to the environment and promote the effective recycling of agricultural waste. In the production process of organic fertilizers, microbial fermentation plays a core role. Through the action of composite microbial agents, the decomposition of organic matter can be accelerated, and agricultural waste can be converted into nutrient-rich organic fertilizers. However, the fermentation process is affected by many factors, such as temperature and pH value. Changes in these factors will directly or indirectly affect the activity and metabolic efficiency of microorganisms, and thus affect the quality and yield of organic fertilizers.

[0003] The prior art has the following deficiencies:

[0004] Most of the current fermentation control systems rely on empirical manual adjustments and lack the ability of real-time monitoring and intelligent regulation, which makes it difficult to maintain ideal fermentation conditions, thus affecting the fermentation efficiency and consistency of product quality. Secondly, the understanding and management of the dynamic changes of microbial communities during fermentation is still insufficient, especially the lack of effective quantitative indicators to evaluate the stability and health status of microbial ecosystems, which makes it difficult to take effective intervention measures in time when encountering flora disorders.

[0005] In addition, the existing technology rarely involves the comprehensive evaluation of the temperature fluctuation index and pH stability index during the fermentation process, which cannot fully reflect the impact of external interference on the fermentation process, limiting the optimization and refined management of the production process. Therefore, developing a technical solution that can accurately monitor and intelligently adjust the fermentation conditions to ensure the stability and efficiency of the fermentation process is an urgent problem to be solved in the current field of organic fertilizer production. Summary of the invention

[0006] The object of the present invention is to provide a method for optimizing and controlling the production parameters of organic fertilizer using a composite microbial agent to solve the above-mentioned problems.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A method for optimizing and controlling parameters of organic fertilizer production using a composite microbial agent comprises the following steps:

[0009] S1: Real-time monitoring of the fermentation stage in organic fertilizer production, real-time collection of temperature data and pH data in the fermentation stage of organic fertilizer, and generation of corresponding temperature fluctuation index and pH stability index;

[0010] S2: Normalize the temperature fluctuation index and pH stability index during the organic fertilizer fermentation process, calculate the comprehensive influencing factor, and evaluate the degree of interference in the organic fertilizer fermentation process based on the comprehensive influencing factor;

[0011] S3: Process the comprehensive influencing factors and the concentration of microorganisms to analyze the microbial ecological disorder. According to the microbial ecological disorder, calculate the microbial ecological disorder fluctuation coefficient, and evaluate whether the state of the bacterial community is stable according to the microbial ecological disorder fluctuation coefficient;

[0012] S4: According to the evaluation results, the unstable bacterial community state is extracted, and the temperature data and pH data during the organic fertilizer fermentation state are adjusted by calculating the adjustment factor;

[0013] S5: According to the adjusted temperature data and pH data, the state of the bacterial community in the organic fertilizer fermentation process is extracted, and the microbial ecological disorder fluctuation coefficient is recalculated. If the state of the bacterial community is stable after adjustment, the adjusted temperature data and pH data meet the standards.

[0014] As a further solution of the present invention: the real-time monitoring of the fermentation stage in the production of organic fertilizer, the real-time collection of temperature data and pH data of the fermentation stage of organic fertilizer, and the generation of corresponding temperature fluctuation index and pH stability index specifically include:

[0015] The process of obtaining the temperature fluctuation index is as follows:

[0016] Temperature sensors are deployed in the fermentation tank to collect temperature data in real time during the fermentation stage;

[0017] Acquire the temperature data of the fermentation stage according to the time series;

[0018] Calculate the average value of temperature data separately and standard deviation σ T ;

[0019] The average value of the temperature data and standard deviation σ T The ratio calculation is performed to obtain the jump ratio of the temperature data. The jump ratio of the temperature data and the standard deviation of the temperature data are processed to calculate the temperature fluctuation index. The calculation expression is:

[0020]

[0021] Where, T srepresents the temperature fluctuation index, e represents the logarithm of the natural number base, a1 and a2 are the preset proportional coefficients, σ T represents the temperature standard deviation, Indicates the average value of temperature data;

[0022] The process of obtaining the pH stability index is as follows:

[0023] The fermentation tank is divided into several fermentation tanks, and a pH sensor is deployed in each fermentation tank to collect pH data in real time during the fermentation process;

[0024] Obtain pH measurements in different fermentation tanks in time series, divide the fermentation area into grids, and record pH measurements at each grid point;

[0025] The spatial gradient of pH is obtained by calculating the difference between adjacent grid points. The calculation expression is:

[0026]

[0027] In the formula, Gradient ij represents the spatial gradient of the i-th and j-th grid points, i represents the number of grid points in the spatial position, j represents the number of grid points in the time dimension, pH i,j (t) represents the pH measurement value of the i-th and j-th grid points at time t, t represents the time series acquisition point, Δx represents the grid space step in the x direction, and Δy represents the grid space step in the y direction;

[0028] Calculate the mean value G and standard deviation σ of the pH distribution gradient G ;

[0029] The pH distribution gradient deviation index is calculated by calculating the gradient deviation of each grid point. The calculation expression is:

[0030]

[0031] Where D i Represents the pH distribution gradient deviation index of the i-th grid point, Gradient i represents the pH gradient at the ith grid point, G represents the average pH gradient of all grid points, σ G represents the standard deviation of pH gradient at all grid points;

[0032] The pH stability index is calculated according to the pH distribution gradient deviation index. The calculation expression is:

[0033]

[0034] Where n is the total number of grid points and PSI is the pH stability index.

[0035] As a further solution of the present invention: the temperature fluctuation index and pH stability index in the organic fertilizer fermentation process are normalized, the comprehensive influence factor is calculated, and the interference degree of the organic fertilizer fermentation process is evaluated according to the comprehensive influence factor, which specifically includes:

[0036] The temperature fluctuation index and pH stability index in the organic fertilizer fermentation process are obtained, the temperature fluctuation index and pH stability index are normalized, the comprehensive influencing factor of the organic fertilizer fermentation stage is calculated through the normalized temperature fluctuation index and pH stability index, and the comprehensive influencing factor is compared with the corresponding preset threshold value to determine whether the organic fertilizer fermentation process is disturbed.

[0037] As a further solution of the present invention: the method of judging whether the organic fertilizer fermentation process is disturbed specifically includes:

[0038] Determine whether the comprehensive influencing factor is greater than or equal to a preset threshold value. If so, the fluctuation of temperature and pH in the corresponding fermentation stage has a high degree of interference with the organic fertilizer fermentation process, and the corresponding fermentation process is disturbed;

[0039] If not, the fluctuation of temperature and pH in the corresponding fermentation stage has a low degree of interference with the organic fertilizer fermentation process, and the corresponding fermentation process is not disturbed.

[0040] As a further solution of the present invention: the comprehensive influencing factors and the concentration of microorganisms are processed, the microbial ecological disorder is analyzed, and the abnormal coefficient of microbial concentration is calculated, which specifically includes:

[0041] According to the time series, the microbial concentration data at each time point is collected in real time;

[0042] Standardize the microbial concentration data;

[0043] The microbial concentration data were processed using cluster analysis algorithms;

[0044] Initialize the cluster center and randomly select k points as the initial cluster center;

[0045] The distance between each microbial concentration data point and the center of each cluster was calculated and assigned to the nearest cluster;

[0046] Calculate the mean of each cluster;

[0047] Wherein, the distance between each microorganism concentration data point and each cluster center is calculated by the Euclidean distance calculation formula;

[0048] According to the distance between each microbial concentration data point and each cluster center and the standard deviation of all microbial concentration data points to the cluster center, the microbial concentration anomaly coefficient is calculated. The calculation expression is:

[0049]

[0050] In the formula, MCAI represents the microbial concentration anomaly coefficient, m represents the mth microbial concentration data, c represents the total number of microbial concentration data, d m represents the distance from the mth microbial concentration data to the cluster center, σ cluster Represents the standard deviation of all microbial concentration data points to the cluster center.

[0051] As a further solution of the present invention: the microbial ecological disorder fluctuation coefficient is calculated according to the microbial ecological disorder situation, and whether the state of the flora is stable is evaluated according to the microbial ecological disorder fluctuation coefficient, specifically including:

[0052] The abnormal coefficient of microbial concentration and the comprehensive influencing factors are analyzed by the decision tree algorithm; the abnormal coefficient of microbial concentration and the comprehensive influencing factors in the fermentation stage are used as training data, and the decision tree is trained using the training set data.

[0053] Preprocess the training data and select the decision tree algorithm to build the model;

[0054] Obtain the abnormal coefficient and comprehensive influencing factor of microbial concentration in the fermentation stage as input features;

[0055] The microbial ecological disorder fluctuation coefficient is used as the output of the algorithm;

[0056] Construct decision trees through feature selection, information gain or Gini coefficient methods;

[0057] Use the test set data to verify the model performance, calculate indicators such as accuracy, recall, and F1 score, and further evaluate the stability and generalization ability of the model through cross-validation;

[0058] It is determined whether the microbial ecological disorder fluctuation coefficient is greater than or equal to a preset threshold value. If so, the state of the corresponding bacterial community is unstable; if not, the state of the corresponding bacterial community is stable.

[0059] As a further solution of the present invention: the temperature data and pH data in the organic fertilizer fermentation process are adjusted by calculating the adjustment factor, specifically including:

[0060] Obtain the microbial ecological disorder fluctuation coefficient, temperature fluctuation index and pH stability index during the organic fertilizer fermentation process;

[0061] The microbial ecological disorder fluctuation coefficient, temperature fluctuation index and pH stability index are comprehensively processed, and combined with the preset proportional factor, the adjustment factor is calculated through a comprehensive calculation formula, and the adjustment factor is multiplied with the corresponding temperature data and pH data in the fermentation process to obtain the control threshold of the temperature data and pH data, and the temperature data and pH data of the fermentation process are adjusted to be less than the control threshold.

[0062] As a further solution of the present invention: the comprehensive calculation formula is:

[0063]

[0064] In the formula, AC E Indicates the adjustment factor. h1, h2, and h3 are preset proportional factors, and h1, h2, and h3 are all greater than 0. T s PSI represents the temperature fluctuation index, PSI represents the pH stability index, and DEW represents the microbial ecological disorder fluctuation coefficient.

[0065] Beneficial effects of the present invention:

[0066] (1) By implementing the real-time monitoring and analysis system of the present invention, the core parameters including temperature and pH value in the organic fertilizer fermentation process can be dynamically monitored with high precision. The present invention can not only capture subtle environmental changes through advanced quantitative evaluation indicators such as temperature fluctuation index, pH stability index and microbial ecological disorder fluctuation coefficient, but also provide a scientific basis for comprehensively evaluating fermentation conditions. Using these quantitative indicators, combined with the calculation of comprehensive influencing factors, the interference factors that may appear in the fermentation process can be accurately located and quantified, and then a targeted optimization strategy can be formulated. When unstable factors are detected, the system will automatically calculate the adjustment factor to achieve fine-tuning of the fermentation conditions (such as temperature and pH value) to ensure that the microbial flora is always in the most suitable growth and metabolic environment, thereby maximizing its activity and efficiency. This method not only significantly reduces the impact of external environmental changes on the fermentation process and maintains an ideal fermentation state, but also greatly improves the stability, consistency and efficiency of the entire fermentation process, ultimately ensuring the high quality and performance consistency of organic fertilizer products. In addition, through the refined control of the fermentation process, the present invention also helps to reduce unnecessary resource consumption and reduce production costs, while promoting the effective transformation and recycling of agricultural waste, and promoting green agriculture and sustainable development.

[0067] (2) By introducing quantitative indicators such as comprehensive influencing factors and microbial concentration anomaly coefficients, the present invention realizes the refined monitoring and optimization of the microbial ecosystem during the organic fertilizer fermentation process. Specifically, the calculation of the comprehensive influencing factor combines the temperature fluctuation index and the pH stability index, which can comprehensively evaluate the impact of external factors on the fermentation environment; and the microbial concentration anomaly coefficient accurately identifies the disordered state of the flora and its potential risks through an in-depth analysis of the structure and dynamic changes of the microbial community. This two-pronged evaluation method not only improves the accuracy of the prediction of the stability of the fermentation process, but also provides a scientific basis for timely adjustment of the fermentation conditions. The key to this beneficial effect is that it enables producers to detect adverse changes that may affect the fermentation efficiency and product quality at an early stage, and take rapid measures to correct them. Through continuous monitoring and intelligent regulation, it is ensured that the microbial flora maintains the optimal activity state throughout the fermentation cycle, thereby significantly improving the quality and consistency of organic fertilizers. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The present invention will be further described below in conjunction with the accompanying drawings.

[0069] Figure 1 It is a flowchart of the specific steps of a method for optimizing and controlling the production parameters of organic fertilizers using a composite microbial agent of the present invention;

[0070] Figure 2 It is a flowchart of the specific steps of comprehensive influencing factors in the present invention. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] See also Figure 1 As shown, the present invention is a method for optimizing and controlling parameters of organic fertilizer production using a composite microbial agent, comprising the following steps:

[0073] S1: Real-time monitoring of the fermentation stage in organic fertilizer production, real-time collection of temperature data and pH data in the fermentation stage of organic fertilizer, and generation of corresponding temperature fluctuation index and pH stability index;

[0074] S2: Normalize the temperature fluctuation index and pH stability index during the organic fertilizer fermentation process, calculate the comprehensive influencing factor, and evaluate the degree of interference in the organic fertilizer fermentation process based on the comprehensive influencing factor;

[0075] S3: Process the comprehensive influencing factors and the concentration of microorganisms to analyze the microbial ecological disorder. According to the microbial ecological disorder, calculate the microbial ecological disorder fluctuation coefficient, and evaluate whether the state of the bacterial community is stable according to the microbial ecological disorder fluctuation coefficient;

[0076] S4: According to the evaluation results, the unstable bacterial community state is extracted, and the temperature data and pH data during the organic fertilizer fermentation state are adjusted by calculating the adjustment factor;

[0077] S5: According to the adjusted temperature data and pH data, the state of the bacterial community in the organic fertilizer fermentation process is extracted, and the microbial ecological disorder fluctuation coefficient is recalculated. If the state of the bacterial community is stable after adjustment, the adjusted temperature data and pH data meet the standards.

[0078] In S1, the fermentation stage in the production of organic fertilizer is monitored in real time, the temperature data and pH data of the fermentation stage of organic fertilizer are collected in real time, and the corresponding temperature fluctuation index and pH stability index are generated, including:

[0079] The process of obtaining the temperature fluctuation index is as follows:

[0080] Temperature sensors are deployed in the fermentation tank to collect temperature data in real time during the fermentation stage;

[0081] Acquire the temperature data of the fermentation stage according to the time series;

[0082] Calculate the mean value T and standard deviation σ of the temperature data respectively T ;

[0083] It should be noted that the average temperature can reflect the temperature trend of the fermentation environment, and the standard deviation can reflect the fluctuation range of the temperature data.

[0084] The average value of the temperature data and standard deviation σ T The ratio calculation is performed to obtain the jump ratio of the temperature data. The jump ratio of the temperature data and the standard deviation of the temperature data are processed to calculate the temperature fluctuation index. The calculation expression is:

[0085]

[0086] Where, T s represents the temperature fluctuation index, e represents the logarithm of the natural number base, a1 and a2 are the preset proportional coefficients, σ T represents the temperature standard deviation, Indicates the average value of temperature data;

[0087] The process of obtaining the pH stability index is as follows:

[0088] The fermentation tank is divided into several fermentation tanks, and a pH sensor is deployed in each fermentation tank to collect pH data in real time during the fermentation process;

[0089] Obtain pH measurements in different fermentation tanks in time series, divide the fermentation area into grids, and record pH measurements at each grid point;

[0090] The spatial gradient of pH is obtained by calculating the difference between adjacent grid points. The calculation expression is:

[0091]

[0092] In the formula, Gradient ij represents the spatial gradient of the i-th and j-th grid points, i represents the number of grid points in the spatial position, j represents the number of grid points in the time dimension, pH i,j (t) represents the pH measurement value of the i-th and j-th grid points at time t, t represents the time series acquisition point, Δx represents the grid space step in the x direction, and Δy represents the grid space step in the y direction;

[0093] Calculate the mean value G and standard deviation σ of the pH distribution gradient G ;

[0094] The pH distribution gradient deviation index is calculated by calculating the gradient deviation of each grid point. The calculation expression is:

[0095]

[0096] Where D i Represents the pH distribution gradient deviation index of the i-th grid point, Gradient i represents the pH gradient at the ith grid point, G represents the average pH gradient of all grid points, σ G represents the standard deviation of pH gradient at all grid points;

[0097] The pH stability index is calculated according to the pH distribution gradient deviation index. The calculation expression is:

[0098]

[0099] Where n represents the total number of grid points, PSI represents the pH stability index;

[0100] It should be noted that the pH stability index is used to evaluate the pH stability of the entire fermentation area. The larger the value of the pH stability index, the greater the pH fluctuation in the fermentation area and the more unstable the fermentation process. The smaller the value of the pH stability index, the smaller the pH fluctuation and the more stable the fermentation process.

[0101] See also Figure 2 As shown, in S2, the temperature fluctuation index and pH stability index in the organic fertilizer fermentation process are normalized, and the comprehensive influencing factor is calculated. The degree of interference in the organic fertilizer fermentation process is evaluated according to the comprehensive influencing factor, which specifically includes:

[0102] Obtaining the temperature fluctuation index and pH stability index during the organic fertilizer fermentation process, normalizing the temperature fluctuation index and pH stability index, calculating the comprehensive influencing factor of the organic fertilizer fermentation stage through the normalized temperature fluctuation index and pH stability index, and comparing the comprehensive influencing factor with the corresponding preset threshold value to determine whether the organic fertilizer fermentation process is disturbed;

[0103] Among them, the calculation expression of the comprehensive impact factor is:

[0104]

[0105] In the formula, Z S represents the comprehensive influencing factor, b1 and b2 are preset proportional factors, and both b1 and b2 are greater than 0, e is the logarithm of the natural number base, PSI represents the pH stability index, T s Indicates the temperature fluctuation index;

[0106] The comprehensive impact factor Z S comparing with a preset threshold;

[0107] If the comprehensive impact factor Z S If it is greater than or equal to the preset threshold, it means that the fluctuation of temperature and pH in the corresponding fermentation stage has a high degree of interference with the organic fertilizer fermentation process, and the corresponding fermentation process is disturbed;

[0108] If the comprehensive impact factor Z S If the value is less than the preset threshold, it means that the fluctuation of temperature and pH in the corresponding fermentation stage has a low degree of interference to the organic fertilizer fermentation process, and the corresponding fermentation process is not disturbed;

[0109] It should be noted that the comprehensive influencing factor reflects the fluctuation of temperature data and pH data in the organic fertilizer fermentation process, and the degree of influence on the fermentation process. The larger the value of the comprehensive influencing factor, the higher the degree of influence on the corresponding fermentation process.

[0110] In S3, the comprehensive influencing factors and the concentration of microorganisms are processed to analyze the microbial ecological disorder. According to the microbial ecological disorder, the microbial ecological disorder fluctuation coefficient is calculated, and the stability of the bacterial community is evaluated according to the microbial ecological disorder fluctuation coefficient, which includes:

[0111] Collect samples from different depths and areas of the fermentation tank to ensure representativeness. Set up timed sampling (e.g., sampling every 1 hour) according to the dynamic characteristics of the fermentation stage.

[0112] Use a sterile sampler to collect samples, use sterile containers to store samples, and keep them low to prevent further growth or death of microorganisms;

[0113] Quantitative detection of concentrations of specific microorganisms through gene amplification techniques;

[0114] According to the time series, the microbial concentration data at each time point is collected in real time;

[0115] Standardize the microbial concentration data;

[0116] The microbial concentration data were processed using cluster analysis algorithms;

[0117] Initialize the cluster center and randomly select k points as the initial cluster center;

[0118] The distance between each microbial concentration data point and the center of each cluster was calculated and assigned to the nearest cluster;

[0119] Calculate the mean of each cluster;

[0120] Wherein, the distance between each microorganism concentration data point and each cluster center is calculated by the Euclidean distance calculation formula;

[0121] According to the distance between each microbial concentration data point and each cluster center and the standard deviation of all microbial concentration data points to the cluster center, the microbial concentration anomaly coefficient is calculated. The calculation expression is:

[0122]

[0123] In the formula, MCAI represents the microbial concentration anomaly coefficient, m represents the mth microbial concentration data, c represents the total number of microbial concentration data, d m represents the distance from the mth microbial concentration data to the cluster center, σ cluster represents the standard deviation of all microbial concentration data points to the cluster center;

[0124] The abnormal coefficient of microbial concentration and the comprehensive influencing factors are analyzed by the decision tree algorithm; the abnormal coefficient of microbial concentration and the comprehensive influencing factors in the fermentation stage are used as training data, and the decision tree is trained using the training set data.

[0125] Preprocess the training data and select the decision tree algorithm to build the model;

[0126] Obtain the abnormal coefficient and comprehensive influencing factor of microbial concentration in the fermentation stage as input features;

[0127] The microbial ecological disorder fluctuation coefficient is used as the output of the algorithm;

[0128] Construct decision trees through feature selection, information gain or Gini coefficient methods;

[0129] Use the test set data to verify the model performance, calculate indicators such as accuracy, recall, and F1 score, and further evaluate the stability and generalization ability of the model through cross-validation;

[0130] Compare the microbial ecological disorder fluctuation coefficient with a preset threshold;

[0131] If the microbial ecological disorder fluctuation coefficient is greater than or equal to the preset threshold, it means that the state of the corresponding bacterial community is unstable;

[0132] If the microbial ecological disorder fluctuation coefficient is less than the preset threshold, it means that the state of the corresponding bacterial community is stable.

[0133] In S4, according to the evaluation results, the unstable bacterial community state is extracted, and the temperature data and pH data in the organic fertilizer fermentation state are adjusted by calculating the adjustment factor, specifically including:

[0134] Obtain the microbial ecological disorder fluctuation coefficient, temperature fluctuation index and pH stability index during the organic fertilizer fermentation process;

[0135] The microbial ecological disorder fluctuation coefficient, temperature fluctuation index and pH stability index are comprehensively processed, and combined with the preset proportional factor, the adjustment factor is calculated through a comprehensive calculation formula, and the adjustment factor is multiplied with the corresponding temperature data and pH data in the fermentation process to obtain the control threshold of the temperature data and pH data, and the temperature data and pH data of the fermentation process are adjusted to be less than the control threshold;

[0136] Among them, the calculation expression of the comprehensive calculation formula is:

[0137]

[0138] In the formula, AC E Indicates the adjustment factor. h1, h2, and h3 are preset proportional factors, and h1, h2, and h3 are all greater than 0. T s represents the temperature fluctuation index, PSI represents the pH stability index, and DEW represents the microbial ecological disorder fluctuation coefficient;

[0139] In S5, the state of the flora in the organic fertilizer fermentation process is extracted according to the adjusted temperature data and pH data, and the microbial ecological disorder fluctuation coefficient is recalculated. If the state of the flora is stable after adjustment, the adjusted temperature data and pH data meet the standards, including:

[0140] Use the adjusted temperature and pH data to re-evaluate the status of the bacterial flora during the fermentation process;

[0141] By observing the relative concentration, activity, and dynamic changes of microorganisms, we can extract the stability index of the bacterial community;

[0142] These stability indicators are closely related to changes in temperature and pH. Therefore, by extracting the corresponding bacterial community status data, it can be reflected whether the temperature and pH adjustments have achieved the expected effects. In particular, in the adjusted data, the bacterial community should show a more stable state.

[0143] If the adjusted bacterial flora status shows small fluctuations and remains within a relatively stable range, it means that the bacterial flora is stable and the temperature and pH data during the fermentation process meet the standards;

[0144] Specifically, the calculated microbial ecological disorder fluctuation coefficient should be close to an ideal stable value, indicating that the adjusted temperature and pH conditions have effectively reduced the disorder of the bacterial flora, thereby ensuring the stability and efficiency of the fermentation process.

[0145] The working principle of the present invention is to evaluate the stability of the fermentation environment by monitoring the temperature and pH value in the fermentation process in real time, and calculating the corresponding fluctuation index and stability index. Furthermore, by normalizing these indexes and combining them with the microbial concentration data, the comprehensive influencing factors are used to quantify the degree of interference in the fermentation process, and cluster analysis and decision tree algorithms are used to evaluate the microbial ecological disorder, so as to dynamically adjust the fermentation conditions to maintain the stability and activity of the flora. When an unstable state is detected, the method calculates the adjustment factor to optimize the temperature and pH value to ensure that the flora can reach an ideal stable state under the adjusted conditions, thereby ensuring the efficiency of the organic fertilizer fermentation process and the product quality. This scheme improves the effectiveness of microbial agents by accurately controlling fermentation parameters, and promotes the standardization and intelligence of organic fertilizer production.

[0146] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0147] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0148] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0149] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0150] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for optimizing and controlling parameters of organic fertilizer production using a composite microbial agent, characterized in that: The following steps are involved: S1: Real-time monitoring of the fermentation stage in organic fertilizer production, real-time collection of temperature data and pH data in the fermentation stage of organic fertilizer, and generation of corresponding temperature fluctuation index and pH stability index; S2: Normalize the temperature fluctuation index and pH stability index during the organic fertilizer fermentation process, calculate the comprehensive influencing factor, and evaluate the degree of interference in the organic fertilizer fermentation process based on the comprehensive influencing factor; S3: Process the comprehensive influencing factors and the concentration of microorganisms to analyze the microbial ecological disorder. According to the microbial ecological disorder, calculate the microbial ecological disorder fluctuation coefficient, and evaluate whether the state of the bacterial community is stable according to the microbial ecological disorder fluctuation coefficient; S4: According to the evaluation results, the unstable bacterial community state is extracted, and the temperature data and pH data during the organic fertilizer fermentation state are adjusted by calculating the adjustment factor; S5: According to the adjusted temperature data and pH data, the state of the bacterial community in the organic fertilizer fermentation process is extracted, and the microbial ecological disorder fluctuation coefficient is recalculated. If the state of the bacterial community is stable after adjustment, the adjusted temperature data and pH data meet the standards.

2. The method for optimizing the production parameters of organic fertilizer using a composite microbial agent according to claim 1, characterized in that: The real-time monitoring of the fermentation stage in the organic fertilizer production, the real-time collection of temperature data and pH data of the organic fertilizer fermentation stage, and the generation of the corresponding temperature fluctuation index and pH stability index specifically include: The process of obtaining the temperature fluctuation index is as follows: Temperature sensors are deployed in the fermentation tank to collect temperature data in real time during the fermentation stage; Acquire the temperature data of the fermentation stage according to the time series; Calculate the average value of temperature data separately and standard deviation σ T ; The average value of the temperature data and standard deviation σ T The ratio calculation is performed to obtain the jump ratio of the temperature data. The jump ratio of the temperature data and the standard deviation of the temperature data are processed to calculate the temperature fluctuation index. The calculation expression is: Where, T s represents the temperature fluctuation index, e represents the logarithm of the natural number base, a1 and a2 are the preset proportional coefficients, σ T represents the temperature standard deviation, Indicates the average value of temperature data; The process of obtaining the pH stability index is as follows: The fermentation tank is divided into several fermentation tanks, and a pH sensor is deployed in each fermentation tank to collect pH data in real time during the fermentation process; Obtain pH measurements in different fermentation tanks in time series, divide the fermentation area into grids, and record pH measurements at each grid point; The spatial gradient of pH is obtained by calculating the difference between adjacent grid points. The calculation expression is: In the formula, Gradient ij represents the spatial gradient of the i-th and j-th grid points, i represents the number of grid points in the spatial position, j represents the number of grid points in the time dimension, pH i,j (t) represents the pH measurement value of the i-th and j-th grid points at time t, t represents the time series acquisition point, Δx represents the grid space step in the x direction, and Δy represents the grid space step in the y direction; Calculate the mean value G and standard deviation σ of the pH distribution gradient G ; The pH distribution gradient deviation index is calculated by calculating the gradient deviation of each grid point. The calculation expression is: Where D i Represents the pH distribution gradient deviation index of the i-th grid point, Gradient i represents the pH gradient at the ith grid point, G represents the average pH gradient of all grid points, σ G represents the standard deviation of pH gradient at all grid points; The pH stability index is calculated according to the pH distribution gradient deviation index. The calculation expression is: Where n is the total number of grid points and PSI is the pH stability index.

3. The method for optimizing the production parameters of organic fertilizer using a composite microbial agent according to claim 1, characterized in that: The temperature fluctuation index and pH stability index in the organic fertilizer fermentation process are normalized, a comprehensive influencing factor is calculated, and the degree of interference in the organic fertilizer fermentation process is evaluated according to the comprehensive influencing factor, specifically including: The temperature fluctuation index and pH stability index in the organic fertilizer fermentation process are obtained, the temperature fluctuation index and pH stability index are normalized, the comprehensive influencing factor of the organic fertilizer fermentation stage is calculated through the normalized temperature fluctuation index and pH stability index, and the comprehensive influencing factor is compared with the corresponding preset threshold value to determine whether the organic fertilizer fermentation process is disturbed.

4. The method for optimizing the production parameters of organic fertilizer using a composite microbial agent according to claim 3, characterized in that: The step of judging whether the organic fertilizer fermentation process is disturbed specifically includes: Determine whether the comprehensive influencing factor is greater than or equal to a preset threshold value. If so, the fluctuation of temperature and pH in the corresponding fermentation stage has a high degree of interference with the organic fertilizer fermentation process, and the corresponding fermentation process is disturbed; If not, the fluctuation of temperature and pH in the corresponding fermentation stage has a low degree of interference with the organic fertilizer fermentation process, and the corresponding fermentation process is not disturbed.

5. The method for optimizing the production parameters of organic fertilizer using a composite microbial agent according to claim 1, characterized in that: The comprehensive influencing factors and the concentration of microorganisms are processed to analyze the disorder of microbial ecology and calculate the abnormal coefficient of microbial concentration, which specifically includes: According to the time series, the microbial concentration data at each time point is collected in real time; Standardize the microbial concentration data; The microbial concentration data were processed using cluster analysis algorithms; Initialize the cluster center and randomly select k points as the initial cluster center; The distance between each microbial concentration data point and the center of each cluster was calculated and assigned to the nearest cluster; Calculate the mean of each cluster; Wherein, the distance between each microorganism concentration data point and each cluster center is calculated by the Euclidean distance calculation formula; According to the distance between each microbial concentration data point and each cluster center and the standard deviation of all microbial concentration data points to the cluster center, the microbial concentration anomaly coefficient is calculated. The calculation expression is: In the formula, MCAI represents the microbial concentration anomaly coefficient, m represents the mth microbial concentration data, c represents the total number of microbial concentration data, d m represents the distance from the mth microbial concentration data to the cluster center, σ cluster Represents the standard deviation of all microbial concentration data points to the cluster center.

6. The method for optimizing the production parameters of organic fertilizer using a composite microbial agent according to claim 1, characterized in that: The method of calculating the microbial ecological disorder fluctuation coefficient according to the microbial ecological disorder situation and evaluating whether the state of the flora is stable according to the microbial ecological disorder fluctuation coefficient specifically includes: The abnormal coefficient of microbial concentration and the comprehensive influencing factors are analyzed by the decision tree algorithm; the abnormal coefficient of microbial concentration and the comprehensive influencing factors in the fermentation stage are used as training data, and the decision tree is trained using the training set data. Preprocess the training data and select the decision tree algorithm to build the model; Obtain the abnormal coefficient and comprehensive influencing factor of microbial concentration in the fermentation stage as input features; The microbial ecological disorder fluctuation coefficient is used as the output of the algorithm; It is determined whether the microbial ecological disorder fluctuation coefficient is greater than or equal to a preset threshold value. If so, the state of the corresponding bacterial community is unstable; if not, the state of the corresponding bacterial community is stable.

7. The method for optimizing the production parameters of organic fertilizer using a composite microbial agent according to claim 1, characterized in that: The temperature data and pH data in the organic fertilizer fermentation process are adjusted by calculating the adjustment factor, specifically including: Obtain the microbial ecological disorder fluctuation coefficient, temperature fluctuation index and pH stability index during the organic fertilizer fermentation process; The microbial ecological disorder fluctuation coefficient, temperature fluctuation index and pH stability index are comprehensively processed, and combined with the preset proportional factor, the adjustment factor is calculated through a comprehensive calculation formula, and the adjustment factor is multiplied with the corresponding temperature data and pH data in the fermentation process to obtain the control threshold of the temperature data and pH data, and the temperature data and pH data of the fermentation process are adjusted to be less than the control threshold.

8. The method for optimizing the production parameters of organic fertilizer using a composite microbial agent according to claim 7, characterized in that: The comprehensive calculation formula is: In the formula, AC E Indicates the adjustment factor. h1, h2, and h3 are preset proportional factors, and h1, h2, and g3 are all greater than 0. T s PSI represents the temperature fluctuation index, PSI represents the pH stability index, and DEW represents the microbial ecological disorder fluctuation coefficient.

Images