Cloud factory production device and control system for microbial fertilizer

Abstract

The invention discloses a cloud factory production device of a microbial fertilizer and a control system. The cloud factory production device comprises a fermentation module, a control module, a learning module, an analysis module, a drying module, a granulation module, an evaluation module, a data acquisition module and a data uploading module. Fermentation conditions are optimized through a genetic algorithm, and efficient proceeding of the fermentation process is ensured. And the fermentation environment is controlled by using fuzzy logic, so that the accurate control of environmental parameters in the fermentation process is realized, and the fermentation efficiency is improved. The reinforcement learning algorithm automatically optimizes the raw material ratio, and the growth rate and the product quality of microbial strains are improved. A user can access and upload the data of the fermentation process through the Internet through the cloud factory, remote management and monitoring are facilitated, the drying and granulation process is optimized through clustering analysis, and the uniformity and stability of products are ensured. The optimal drying condition is found through the simulated annealing algorithm, and the drying efficiency and quality of products are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of biofertilizers, and in particular to a cloud factory production device and a control system for microbial fertilizers. Background Art

[0002] As an important agricultural production material, microbial fertilizer plays an important role in improving soil fertility and crop growth environment. However, there are some technical difficulties in the production process of traditional microbial fertilizer, especially the inaccurate environmental control during the fermentation process, which leads to unstable product quality and high production cost.

[0003] After searching, the invention patent with Chinese patent number CN115261522A discloses a method and system for controlling the environment of microbial fermentation, which relates to the field of fermentation control technology. The method includes: obtaining target microorganisms; obtaining the parameter control range of multiple environmental indicators of the target microorganisms in fermentation culture, and obtaining multiple indicator parameter intervals; analyzing the correlation between multiple environmental indicators and the quality of microbial fermentation culture, and obtaining a correlation information set; according to the size of multiple correlation information in the correlation information set, weighting multiple environmental indicators, and obtaining weighting results; according to the weighting results, adjusting multiple indicator parameter intervals, and obtaining multiple adjusted indicator parameter intervals; according to the multiple adjusted indicator parameter intervals, controlling the fermentation culture environment of the target microorganism. Compared with the prior art, the invention patent with Chinese patent number CN115261522A can solve the technical problem of inaccurate microbial fermentation environment control in the prior art, and achieve the technical effect of improving the accuracy of environmental control and reducing control costs.

[0004] However, in the actual use of the above invention, the fermentation environment control method often adopts fixed or simple statistical analysis methods to control environmental indicators such as temperature, pH value, dissolved oxygen concentration, etc., lacking precise control of the differentiated degree of influence of different environmental indicators, resulting in unstable fermentation efficiency and product quality. In addition, the optimization of raw material ratio usually relies on empirical values, and it is difficult to achieve the best ratio, which affects the growth rate of microbial strains and product quality. In terms of drying and granulation processes, traditional control methods lack accuracy and pertinence, resulting in low drying efficiency and poor product uniformity. Finally, in terms of environmental impact assessment, the traditional production process lacks effective assessment methods to quantify the impact of the production process on the environment, resulting in high energy consumption and waste emissions in the production process.

[0005] Therefore, a cloud factory production device and control system of microbial fertilizer are proposed. Summary of the invention

[0006] The purpose of the present invention is to solve the problem that the fermentation environment control method in the prior art often adopts fixed or simple statistical analysis methods to control environmental indicators such as temperature, pH value, dissolved oxygen concentration, etc., lacks precise control of the differentiated degree of influence of different environmental indicators, resulting in unstable fermentation efficiency and product quality. In addition, the optimization of raw material ratio usually relies on empirical values, and it is difficult to achieve the best ratio, which affects the growth rate of microbial strains and product quality. In terms of drying and granulation processes, traditional control methods lack accuracy and pertinence, resulting in low drying efficiency and poor product uniformity. A cloud factory production device and control system for microbial fertilizer are proposed.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A cloud factory production device for microbial fertilizer, comprising:

[0009] A fermentation module, used for fermenting according to optimized fermentation conditions;

[0010] a control module for controlling environmental parameters during the fermentation process using fuzzy logic;

[0011] A learning module for optimizing raw material ratios using a reinforcement learning algorithm;

[0012] an analytical module for optimizing drying and granulation processes using cluster analysis;

[0013] A drying module, used to find the optimal drying conditions using a simulated annealing algorithm;

[0014] Granulation module, used to adjust key parameters of the granulation process using a Bayesian optimization algorithm;

[0015] An assessment module for guiding production process improvements using life cycle assessment algorithms;

[0016] Data acquisition module, used to collect key data in the production process in real time;

[0017] Data upload module, used to collect key data in the production process in real time and upload it to the cloud factory;

[0018] The data acquisition module collects key data of the production process in real time and transmits it to the fermentation module for fermentation according to the optimized fermentation conditions; the control module uses these data to control the environmental parameters in the fermentation process through fuzzy logic; the learning module uses the reinforcement learning algorithm to optimize the raw material ratio according to the collected data; the analysis module uses the collected data to perform cluster analysis to optimize the drying and granulation processes; the drying module uses the simulated annealing algorithm to find the optimal drying conditions; the granulation module uses the Bayesian optimization algorithm to adjust the key parameters of the granulation process; the evaluation module uses the life cycle assessment algorithm to quantify the impact of the production process on the environment through the collected production data and proposes improvement measures; the data upload module uploads the collected data to the cloud factory.

[0019] The above technical solution further includes:

[0020] Preferably, the fermentation module includes: a temperature control system, a pH adjustment system, and an oxygen supply system. The temperature control system is used to accurately control the temperature during the fermentation process; the pH adjustment system is used to accurately control the pH value during the fermentation process; and the oxygen supply system is used to accurately control the oxygen supply during the fermentation process.

[0021] Preferably, the control module includes: a fuzzy logic controller, a data acquisition unit, and a control algorithm unit. The fuzzy logic controller is used to monitor and adjust the environmental parameters during the fermentation process in real time; the data acquisition unit is used to collect key data during the fermentation process; and the control algorithm unit is used to automatically adjust the environmental conditions in the fermentation tank according to fuzzy logic rules.

[0022] Preferably, the learning module includes: a reinforcement learning unit, a data storage unit, and a model training unit. The reinforcement learning unit is used to automatically optimize the raw material ratio; the data storage unit is used to store training data; and the model training unit is used to train the reinforcement learning model.

[0023] Preferably, the analysis module includes: a data processing unit, a cluster analysis unit, and a parameter optimization unit, wherein the data processing unit is used to extract key features in the drying and granulation processes; the cluster analysis unit is used to perform cluster analysis according to product characteristics; and the parameter optimization unit is used to adjust parameter settings in the drying and granulation processes according to the clustering results.

[0024] Preferably, the drying module includes: a temperature control unit, a time control unit, and a simulated annealing algorithm unit. The temperature control unit is used to accurately control the temperature during the drying process; the time control unit is used to accurately control the time of the drying process; and the simulated annealing algorithm unit is used to find the optimal drying conditions.

[0025] Preferably, the granulation module includes: a pressure control unit, a Bayesian optimization algorithm unit, and a product detection unit. The pressure control unit is used to accurately control the pressure during the granulation process; the Bayesian optimization algorithm unit is used to automatically adjust the key parameters of the granulation process; and the product detection unit is used to detect the morphology and stability of the product after granulation.

[0026] Preferably, the assessment module includes: a data collection unit, an impact category definition unit, a quantitative analysis unit, and an improvement measures formulation unit, wherein the data collection unit is used to collect various data in the production process; the impact category definition unit is used to define the impact categories of the assessment; the quantitative analysis unit is used to calculate the quantitative results of each impact category; and the improvement measures formulation unit is used to determine the main environmental impact factors based on the quantitative results and propose improvement measures.

[0027] Preferably, the data acquisition module includes: a data acquisition unit, a data preprocessing unit, and a data storage unit. The data acquisition unit is used to collect key data of the entire production process in real time; the data preprocessing unit is used to clean and preprocess the collected data; and the data storage unit is used to store the preprocessed data.

[0028] A method for producing a cloud factory device for microbial fertilizer comprises the following steps:

[0029] S1: Optimization of fermentation conditions using genetic algorithms;

[0030] S2: Using fuzzy logic to control environmental parameters during fermentation;

[0031] S3: Use reinforcement learning algorithm to optimize raw material ratio;

[0032] S4: Optimization of drying and granulation processes using cluster analysis;

[0033] S5: Use simulated annealing algorithm to find the optimal drying conditions;

[0034] S6: Use Bayesian optimization algorithm to adjust key parameters of the granulation process;

[0035] S7: Use life cycle assessment algorithms to guide production process improvements.

[0036] The present invention has the following beneficial effects:

[0037] 1. In the present invention, the fermentation conditions are optimized by genetic algorithm to ensure the efficient progress of the fermentation process. The fermentation environment is controlled by fuzzy logic to achieve accurate control of environmental parameters in the fermentation process and improve the fermentation efficiency. The reinforcement learning algorithm automatically optimizes the raw material ratio and improves the growth rate of microbial strains and product quality. Cluster analysis optimizes the drying and granulation process to ensure the uniformity and stability of the product. The simulated annealing algorithm finds the optimal drying conditions and improves the drying efficiency and quality of the product. With the support of the cloud computing platform, users can access real-time data through Web applications or mobile applications anytime and anywhere to achieve remote monitoring and management. The Bayesian optimization algorithm adjusts the key parameters in the granulation process to improve the consistency and stability of the particles. By optimizing the fermentation conditions, raw material ratios, and drying and granulation processes, the production efficiency and product quality are significantly improved, and the production cost is reduced. Resource waste is reduced, the utilization rate of raw materials is improved, and the production cost is reduced.

[0038] 2. In the present invention, the impact of the production process on the environment is quantified by a life cycle assessment algorithm, and improvement measures are proposed accordingly to reduce the impact on the environment. By optimizing energy use and improving raw material utilization, energy consumption and waste emissions in the production process are reduced. The entire production process has a high degree of automation, which reduces the impact of human factors and improves the consistency and reliability of production. The data acquisition module collects key data in real time and provides necessary information support for other modules to ensure the efficiency and controllability of the entire production process. The production process improvement is guided by the life cycle assessment algorithm, which reduces the environmental impact of the production process and realizes environmentally friendly production. The sustainable production capacity of microbial fertilizer is improved, which is conducive to the sustainable development of agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a system architecture diagram of a cloud factory production device for microbial fertilizer proposed by the present invention;

[0040] Figure 2 The present invention is a flow chart of a control system of a cloud factory production device for microbial fertilizer. DETAILED DESCRIPTION

[0041] 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.

[0042] like Figure 1-Figure 2 As shown, a cloud factory production device of microbial fertilizer proposed by the present invention comprises:

[0043] A fermentation module, used for fermenting according to optimized fermentation conditions;

[0044] a control module for controlling environmental parameters during the fermentation process using fuzzy logic;

[0045] A learning module for optimizing raw material ratios using a reinforcement learning algorithm;

[0046] an analytical module for optimizing drying and granulation processes using cluster analysis;

[0047] A drying module, used to find the optimal drying conditions using a simulated annealing algorithm;

[0048] Granulation module, used to adjust key parameters of the granulation process using a Bayesian optimization algorithm;

[0049] An assessment module for guiding production process improvements using life cycle assessment algorithms;

[0050] Data acquisition module, used to collect key data in the production process in real time;

[0051] Data upload module, used to collect key data in the production process in real time and upload it to the cloud factory;

[0052] The data acquisition module collects key data of the production process in real time and passes it to the fermentation module for fermentation according to the optimized fermentation conditions; the control module uses these data to control the environmental parameters in the fermentation process through fuzzy logic, the learning module uses the reinforcement learning algorithm to optimize the raw material ratio according to the collected data, the analysis module uses the collected data to perform cluster analysis and optimize the drying and granulation processes, the drying module uses the simulated annealing algorithm to find the optimal drying conditions, the granulation module uses the Bayesian optimization algorithm to adjust the key parameters of the granulation process, and the evaluation module uses the life cycle assessment algorithm through the collected production data to quantify the impact of the production process on the environment and propose improvement measures. The data upload module uploads the collected data to the cloud factory.

[0053] In one embodiment, the fermentation module includes: a temperature control system, a pH adjustment system, and an oxygen supply system. The temperature control system is used to accurately control the temperature during the fermentation process; the pH adjustment system is used to accurately control the pH value during the fermentation process; and the oxygen supply system is used to accurately control the oxygen supply during the fermentation process.

[0054] In one embodiment, the control module includes: a fuzzy logic controller, a data acquisition unit, and a control algorithm unit. The fuzzy logic controller is used to monitor and adjust the environmental parameters during the fermentation process in real time; the data acquisition unit is used to collect key data during the fermentation process; and the control algorithm unit is used to automatically adjust the environmental conditions in the fermentation tank according to the fuzzy logic rules.

[0055] In one embodiment, the learning module includes: a reinforcement learning unit, a data storage unit, and a model training unit. The reinforcement learning unit is used to automatically optimize the raw material ratio; the data storage unit is used to store training data; and the model training unit is used to train the reinforcement learning model.

[0056] In one embodiment, the analysis module includes: a data processing unit, a cluster analysis unit, and a parameter optimization unit. The data processing unit is used to extract key features in the drying and granulation processes; the cluster analysis unit is used to perform cluster analysis based on product characteristics; and the parameter optimization unit is used to adjust parameter settings in the drying and granulation processes based on clustering results.

[0057] In one embodiment, the drying module includes: a temperature control unit, a time control unit, and a simulated annealing algorithm unit. The temperature control unit is used to accurately control the temperature during the drying process; the time control unit is used to accurately control the time of the drying process; and the simulated annealing algorithm unit is used to find the optimal drying conditions.

[0058] In one embodiment, the granulation module includes: a pressure control unit, a Bayesian optimization algorithm unit, and a product detection unit. The pressure control unit is used to accurately control the pressure during the granulation process; the Bayesian optimization algorithm unit is used to automatically adjust the key parameters of the granulation process; and the product detection unit is used to detect the morphology and stability of the product after granulation.

[0059] In one embodiment, the evaluation module includes: a data collection unit, an impact category definition unit, a quantitative analysis unit, and an improvement measure formulation unit. The data collection unit is used to collect various data in the production process; the impact category definition unit is used to define the impact category of the evaluation; the quantitative analysis unit is used to calculate the quantitative results of each impact category; the improvement measure formulation unit is used to determine the main environmental impact factors based on the quantitative results and propose improvement measures.

[0060] In one embodiment, the data acquisition module includes: a data acquisition unit, a data preprocessing unit, and a data storage unit. The data acquisition unit is used to collect key data of the entire production process in real time; the data preprocessing unit is used to clean and preprocess the collected data; and the data storage unit is used to store the preprocessed data.

[0061] A control system for a cloud factory production device of microbial fertilizer comprises the following steps:

[0062] S1: Optimization of fermentation conditions using genetic algorithms;

[0063] S2: Using fuzzy logic to control environmental parameters during fermentation;

[0064] S3: Use reinforcement learning algorithm to optimize raw material ratio;

[0065] S4: Optimization of drying and granulation processes using cluster analysis;

[0066] S5: Use simulated annealing algorithm to find the optimal drying conditions;

[0067] S6: Use Bayesian optimization algorithm to adjust key parameters of the granulation process;

[0068] S7: Use life cycle assessment algorithms to guide production process improvements.

[0069] In one embodiment, other components include a central processing unit for coordinating communication and data exchange between modules; a display unit for displaying key data and an operation interface; a storage unit for storing program code and production data; a wireless communication unit for realizing remote monitoring and data transmission functions; a safety protection unit for preventing accidents; and a backup power supply unit for ensuring that the system can still operate normally when the main power fails.

[0070] In one embodiment, the cloud computing platform:

[0071] Data processing and storage: The cloud server receives, processes and stores the data from the data loggers.

[0072] Data analysis and visualization: Develop data processing software or use existing data processing platforms to analyze data and generate real-time charts and historical data reports.

[0073] In one embodiment, a genetic algorithm optimizes fermentation conditions:

[0074] Background: Traditional fermentation condition adjustment relies on manual experience, and it is difficult to find the optimal combination.

[0075] Method: Genetic algorithm was used to automatically search for the optimal fermentation conditions, including temperature, pH value, oxygen supply, etc.

[0076] step:

[0077] Initialize population: Randomly generate a set of fermentation conditions as the initial population.

[0078] Fitness calculation: The fitness value is calculated based on the product quality and yield obtained under each set of fermentation conditions.

[0079] Selection operation: retain individuals with higher fitness to enter the next generation.

[0080] Crossover operation: Randomly select two individuals for crossover operation to generate new individuals.

[0081] Mutation operation: perform small-scale mutations on certain individuals to explore new solution spaces.

[0082] Termination condition: Stop the algorithm when the predetermined number of iterations is reached or the fitness value no longer increases significantly.

[0083] Results: After multiple rounds of iterations, an optimal set of fermentation conditions was found, which significantly improved the yield and quality of the fertilizer.

[0084] In one embodiment, fuzzy logic control responds to environmental changes:

[0085] Background: Changes in environmental parameters during fermentation can affect the quality of the final product.

[0086] Methods: A fuzzy logic controller was used to automatically adjust the environmental parameters in the fermenter.

[0087] step:

[0088] Define input variables: including temperature, pH value, oxygen content, etc.

[0089] Define output variables: including heating power, ventilation volume, acid / alkali addition amount, etc.

[0090] Formulate fuzzy rules: Formulate fuzzy rules based on expert experience and experimental data, such as "if the temperature is too high, reduce the heating power."

[0091] Construct a fuzzy logic system: Combine input variables, output variables, and fuzzy rules to form a fuzzy logic system.

[0092] Real-time adjustment: The environmental conditions in the fermentation tank are automatically adjusted through the fuzzy logic system according to the real-time monitored environmental parameters.

[0093] Result: The fermentation process became more stable and controllable, reducing product quality issues caused by environmental changes.

[0094] In one embodiment, the reinforcement learning algorithm optimizes the raw material ratio:

[0095] Background: The raw material ratio directly affects the growth rate of the strain and the quality of the final product.

[0096] Methods: A reinforcement learning algorithm was used to automatically optimize the raw material ratio.

[0097] step:

[0098] Define the state space: including the proportions of various raw materials.

[0099] Define the action space: change the proportion of a certain ingredient.

[0100] Define the reward function: Calculate the reward value based on the quality and output of the product.

[0101] Training model: By continuously trying different raw material ratios, learn which ratio can obtain the highest reward value.

[0102] Application model: Apply the trained model in actual production to automatically adjust the raw material ratio.

[0103] Results: The raw material ratio optimized by reinforcement learning algorithm significantly increased the growth rate of the strain and reduced the waste of raw materials.

[0104] In one embodiment, cluster analysis optimizes the drying and granulation process:

[0105] Background: The selection of parameters during drying and granulation directly affects the final morphology and quality of the product.

[0106] Methods: Cluster analysis algorithm was used to analyze the similarities and differences of different batches of products.

[0107] step:

[0108] Data collection: record parameters such as drying temperature, time, granulation pressure, etc. for different batches.

[0109] Feature extraction: Extract key features from the data, such as the hardness and solubility of the product.

[0110] Cluster analysis: Use clustering algorithms to group similar products into one category.

[0111] Parameter optimization: Adjust the parameter settings during drying and granulation processes based on the clustering results.

[0112] Results: The optimized drying and granulation processes through cluster analysis significantly improved the quality and consistency of the products.

[0113] In one embodiment, a simulated annealing algorithm finds the optimal drying conditions:

[0114] Background: The temperature and time of the drying process directly affect the quality of the product.

[0115] Method: The simulated annealing algorithm was used to find the optimal drying conditions.

[0116] step:

[0117] Define initial temperature: Set a higher initial temperature.

[0118] Define a cooling factor: gradually reduce the temperature as the number of iterations increases.

[0119] Define neighborhood structure: Define the neighborhood extent of the dry conditions.

[0120] Energy calculation: Calculate the quality score of the product based on the drying conditions.

[0121] Acceptance probability calculation: The acceptance probability is calculated based on the energy difference between the current state and the neighboring state.

[0122] Update state: decide whether to accept the neighborhood state as the next state according to the acceptance probability.

[0123] Termination condition: The algorithm stops when the predetermined number of iterations is reached or the temperature drops sufficiently low.

[0124] Results: The optimal drying conditions found by simulated annealing algorithm significantly improved the drying efficiency and quality of the product.

[0125] In one embodiment, Bayesian optimization adjusts key parameters of the granulation process:

[0126] Background: The selection of key parameters in the granulation process is crucial to the morphology and stability of the product.

[0127] Methods: A Bayesian optimization algorithm was used to automatically adjust key parameters in the granulation process.

[0128] step:

[0129] Define the objective function: Define the objective function based on the product's shape, hardness and other characteristics.

[0130] Construct prior distribution: Construct a prior distribution of parameters based on expert experience and historical data.

[0131] Select a sampling strategy: Determine the parameter values ​​that need to be tested in the next step.

[0132] Update posterior distribution: Update the posterior distribution of the parameters based on the new observations.

[0133] Iterative optimization: Optimize parameter configuration through multiple iterations.

[0134] Results: The granulation process adjusted by Bayesian optimization algorithm significantly improved the consistency and stability of the granules.

[0135] In one embodiment, the life cycle assessment algorithm guides production process improvements:

[0136] Background: Environmental impacts of production processes need to be effectively assessed and managed.

[0137] Methods: A life cycle assessment algorithm was used to quantify the environmental impact of the production process.

[0138] step:

[0139] Define Assessment Boundaries: Determine the scope and boundaries of the assessment.

[0140] Data collection: Collect various data during the production process, such as energy consumption, waste emissions, etc.

[0141] Impact category definition: Define the impact category to be assessed, such as greenhouse gas emissions, water resource consumption, etc.

[0142] Quantify impact: Calculate quantitative results for each impact category.

[0143] Interpretation of results: Interpret the quantitative results and identify the main environmental influencing factors.

[0144] Improvement measures: Propose improvement measures for major environmental impact factors.

[0145] Results: The main environmental impact factors in the production process were identified through the life cycle assessment algorithm, and measures were taken to improve them and reduce the impact on the environment.

[0146] How it works

[0147] Raw material preparation stage:

[0148] Raw material mixing: According to the initial formula, the basic raw materials are mixed.

[0149] Data collection: record the proportion, composition and other information of raw material mixing to provide reference for subsequent optimization.

[0150] Example data: The mixing ratio is nitrogen source: carbon source: inorganic salt = 1:3:0.5, and the total weight is 100kg.

[0151] Fermentation stage:

[0152] Genetic algorithm to optimize fermentation conditions: Use genetic algorithm to automatically search for optimal fermentation conditions, including temperature, pH value, oxygen supply, etc.

[0153] Example data: The optimal fermentation conditions are temperature 30°C, pH 7.0, and oxygen supply 1.5L / min.

[0154] Fuzzy logic control of fermentation environment: Use fuzzy logic controller to automatically adjust environmental parameters in the fermentation tank, such as temperature, pH value, oxygen content, etc.

[0155] Sample data: The real-time monitored temperature in the fermenter is 29.5°C, the pH value is 7.05, and the oxygen supply is 1.48L / min. The fuzzy logic controller automatically adjusts the environmental parameters in the fermenter to close to the optimal conditions.

[0156] Raw material ratio optimization stage:

[0157] Reinforcement learning algorithm optimizes raw material ratio: Use reinforcement learning algorithm to automatically optimize raw material ratio to improve the growth rate of strains and the quality of the final product.

[0158] Sample data: After optimization by reinforcement learning algorithm, the final raw material ratio is determined to be nitrogen source: carbon source: inorganic salt = 1:2.5:0.6, with a total weight of 100kg.

[0159] Drying stage:

[0160] Cluster analysis to optimize drying process: Cluster analysis algorithm is used to analyze the similarities and differences between different batches of products, and the parameter settings in the drying process are optimized accordingly.

[0161] Sample data: Through cluster analysis of the past 50 batches of products, it was found that the most stable drying conditions were a temperature of 50°C and a drying time of 12 hours.

[0162] Simulated annealing algorithm to find the optimal drying conditions: Use simulated annealing algorithm to find the optimal drying conditions to improve the drying efficiency and quality of the product.

[0163] Sample data: After optimization by simulated annealing algorithm, the optimal drying conditions were finally determined to be a temperature of 52°C and a time of 10 hours.

[0164] Granulation stage:

[0165] Bayesian Optimization Adjusts Key Parameters of the Granulation Process: Use Bayesian Optimization algorithms to automatically adjust key parameters in the granulation process to improve granule consistency and stability.

[0166] Sample data: After adjustment by the Bayesian optimization algorithm, the pressure is determined to be 100 kPa and the temperature is 45 °C.

[0167] Finished product evaluation stage:

[0168] Life cycle assessment algorithm guides production process improvement: Use life cycle assessment algorithm to quantify the impact of the production process on the environment, and propose improvement measures based on this to reduce the impact on the environment.

[0169] Sample data: Through the life cycle assessment algorithm, it is quantified that the production of 1 ton of microbial fertilizer will emit 200kg of CO2 equivalent and consume 150kWh of electricity. Suggestions are put forward to reduce environmental impact by improving raw material utilization and optimizing energy use.

[0170] Finished product packaging and storage:

[0171] Finished product testing: Quality testing of the final product to ensure it meets standards.

[0172] Example data: Test results show that the final product has a microbial activity of 95% and a moisture content of 8%.

[0173] Packaging and storage: Qualified products should be packaged and stored properly.

[0174] In one embodiment, data collection:

[0175] Sensors continuously monitor environmental parameters within the fermenter and send the data to a data logger.

[0176] The data logger processes the data and transmits it to the cloud server via the network.

[0177] Data processing and storage:

[0178] The cloud server receives, processes and stores data, and performs necessary data cleaning and format conversion.

[0179] The processed data is stored in the cloud for users to access.

[0180] User access:

[0181] Users can access real-time data through the web application or mobile application.

[0182] Users can query historical data as needed to understand the trends and changes in the fermentation process.

[0183] Users can set alarm thresholds, and when data exceeds the preset range, the system will automatically send an alarm notification.

[0184] Remote control function:

[0185] Parameter adjustment: allows users to remotely adjust the parameters of the fermentation environment, such as temperature, pH value, etc.

[0186] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A cloud factory production device for microbial fertilizer, characterized in that: include: A fermentation module, used for fermenting according to optimized fermentation conditions; a control module for controlling environmental parameters during the fermentation process using fuzzy logic; A learning module for optimizing raw material ratios using a reinforcement learning algorithm; an analytical module for optimizing drying and granulation processes using cluster analysis; A drying module, used to find the optimal drying conditions using a simulated annealing algorithm; Granulation module, used to adjust key parameters of the granulation process using a Bayesian optimization algorithm; An assessment module for guiding production process improvements using life cycle assessment algorithms; Data acquisition module, used to collect key data in the production process in real time; Data upload module, used to collect key data in the production process in real time and upload it to the cloud factory; The data acquisition module collects key data of the production process in real time and transmits it to the fermentation module for fermentation according to the optimized fermentation conditions; the control module uses these data to control the environmental parameters in the fermentation process through fuzzy logic; the learning module uses the reinforcement learning algorithm to optimize the raw material ratio according to the collected data; the analysis module uses the collected data to perform cluster analysis to optimize the drying and granulation processes; the drying module uses the simulated annealing algorithm to find the optimal drying conditions; the granulation module uses the Bayesian optimization algorithm to adjust the key parameters of the granulation process; the evaluation module uses the life cycle assessment algorithm to quantify the impact of the production process on the environment through the collected production data and proposes improvement measures; the data upload module uploads the collected data to the cloud factory.

2. The cloud factory production device of a microbial fertilizer according to claim 1 is characterized in that: The fermentation module includes: a temperature control system, a pH value adjustment system, and an oxygen supply system. The temperature control system is used to accurately control the temperature during the fermentation process; the pH value adjustment system is used to accurately control the pH value during the fermentation process; and the oxygen supply system is used to accurately control the oxygen supply during the fermentation process.

3. The cloud factory production device of a microbial fertilizer according to claim 1 is characterized in that: The control module includes: a fuzzy logic controller, a data acquisition unit, and a control algorithm unit. The fuzzy logic controller is used to monitor and adjust the environmental parameters in the fermentation process in real time; the data acquisition unit is used to collect key data in the fermentation process; and the control algorithm unit is used to automatically adjust the environmental conditions in the fermentation tank according to fuzzy logic rules.

4. The cloud factory production device of a microbial fertilizer according to claim 1 is characterized in that: The learning module includes: a reinforcement learning unit, a data storage unit, and a model training unit. The reinforcement learning unit is used to automatically optimize the raw material ratio; the data storage unit is used to store training data; and the model training unit is used to train the reinforcement learning model.

5. The cloud factory production device of a microbial fertilizer according to claim 1 is characterized in that: The analysis module includes: a data processing unit, a cluster analysis unit, and a parameter optimization unit. The data processing unit is used to extract key features in the drying and granulation processes; the cluster analysis unit is used to perform cluster analysis according to product characteristics; and the parameter optimization unit is used to adjust parameter settings in the drying and granulation processes according to clustering results.

6. The cloud factory production device of a microbial fertilizer according to claim 1 is characterized in that: The drying module includes: a temperature control unit, a time control unit, and a simulated annealing algorithm unit. The temperature control unit is used to accurately control the temperature during the drying process; the time control unit is used to accurately control the time of the drying process; and the simulated annealing algorithm unit is used to find the optimal drying conditions.

7. The cloud factory production device of a microbial fertilizer according to claim 1 is characterized in that: The granulation module includes: a pressure control unit, a Bayesian optimization algorithm unit, and a product detection unit. The pressure control unit is used to accurately control the pressure during the granulation process; the Bayesian optimization algorithm unit is used to automatically adjust the key parameters of the granulation process; and the product detection unit is used to detect the morphology and stability of the product after granulation.

8. The cloud factory production device of a microbial fertilizer according to claim 1 is characterized in that: The assessment module includes: a data collection unit, an impact category definition unit, a quantitative analysis unit, and an improvement measure formulation unit. The data collection unit is used to collect various data in the production process; the impact category definition unit is used to define the impact category of the assessment; the quantitative analysis unit is used to calculate the quantitative results of each impact category; the improvement measure formulation unit is used to determine the main environmental impact factors based on the quantitative results and propose improvement measures.

9. The cloud factory production device of a microbial fertilizer according to claim 1, characterized in that: include: The data acquisition module includes: a data acquisition unit, a data preprocessing unit, and a data storage unit. The data acquisition unit is used to collect key data in the entire production process in real time; the data preprocessing unit is used to clean and preprocess the collected data; and the data storage unit is used to store the preprocessed data.

10. A control system for a cloud factory production device of microbial fertilizer according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1: Optimization of fermentation conditions using genetic algorithms; S2: Using fuzzy logic to control environmental parameters during fermentation; S3: Use reinforcement learning algorithm to optimize raw material ratio; S4: Optimization of drying and granulation processes using cluster analysis; S5: Use simulated annealing algorithm to find the optimal drying conditions; S6: Use Bayesian optimization algorithm to adjust key parameters of the granulation process; S7: Use life cycle assessment algorithms to guide production process improvements.

Images