A fermentation bed monitoring system for ecological breeding

Abstract

This invention discloses a monitoring system for fermented beds used in ecological aquaculture, belonging to the field of fermented bed monitoring technology. It includes a multi-dimensional data acquisition module, a data preprocessing and transmission module, a microbial activity analysis module, a litter status assessment module, an intelligent control execution module, an anomaly early warning module, and a cloud-based data management module. This invention establishes a solid data foundation through multi-dimensional data acquisition, ensures data quality through preprocessing and transmission, achieves in-depth and precise analysis of the litter status through microbial activity analysis and litter status assessment, completes targeted intervention through the intelligent control execution module, prevents aquaculture risks through the anomaly early warning module, and finally achieves data retention, traceability, and strategy optimization through the cloud-based data management module.

Description

Technical Field

[0001] This invention belongs to the field of fermentation bed monitoring technology, specifically referring to a fermentation bed monitoring system for ecological aquaculture. Background Technology

[0002] Fermented bed farming technology uses beneficial microorganisms to degrade livestock and poultry excrement, achieving on-site treatment of manure and wastewater, reducing environmental pollution, and improving animal welfare. It is an important development direction for green animal husbandry.

[0003] However, existing monitoring systems for fermentation beds used in ecological aquaculture still have certain shortcomings. Existing technologies rely on human experience or basic sensors, and the monitoring of environmental parameters of the fermentation bed is limited to the surface or a single point. They cannot cover key indicators such as multi-layer structure and complex microbial community activity. The assessment of microbial community activity mainly relies on manual observation or simple counting methods, which cannot accurately analyze the total number of viable bacteria, metabolic intensity, and dominant microbial community structure. The status of the bedding material is assessed through a single indicator without constructing an assessment model that integrates physical, chemical, and degradation capacity parameters. This results in unreasonable bedding material replacement cycles, low resource utilization, and the control relies on fixed thresholds or human experience. There is a lack of a dynamic adjustment mechanism based on microbial activity and bedding material status. Therefore, a monitoring system for fermentation beds used in ecological aquaculture is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a monitoring system for fermentation beds used in ecological aquaculture, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a monitoring system for fermentation beds used in ecological aquaculture, comprising a multi-dimensional data acquisition module, a data preprocessing and transmission module, a microbial activity analysis module, a bedding status assessment module, an intelligent control execution module, an anomaly early warning module, and a cloud data management module;

[0006] The multi-dimensional data acquisition module collects key basic data such as temperature, humidity, microbial activity, and bedding thickness of the fermentation bed in real time.

[0007] The data preprocessing and transmission module filters and standardizes the collected heterogeneous data;

[0008] The microbial activity analysis module analyzes the number of bacteria, metabolic intensity, and dominant bacterial community structure in the fermentation bed based on preprocessed data.

[0009] The bedding condition assessment module combines data to evaluate the physical compaction, chemical stability, and fecal degradation capacity of the bedding material.

[0010] The intelligent control and execution module performs temperature adjustment, turning, and inoculum replenishment operations based on the microbial activity analysis results and the bedding material status assessment results.

[0011] The anomaly warning module monitors the operating status of each module and analyzes and evaluates the results in real time, and issues a graded warning when a preset anomaly condition is triggered.

[0012] The cloud-based data management module stores and traces all data throughout the process, and optimizes system operating parameters based on historical data.

[0013] Preferably, the multi-dimensional data acquisition module includes a temperature sensor, a humidity sensor, a pH sensor, an ammonia concentration sensor, a microbial sensor, and a bedding thickness sensor; each sensor is arranged in the corresponding monitoring layer according to the layered structure of the fermentation bed and at a preset monitoring density; wherein, the microbial sensor has a built-in adaptive microbial activity detection component to collect the number of live bacteria and metabolic-related data of the compound bacteria in real time.

[0014] Preferably, the data preprocessing and transmission module includes a data filtering unit, a data standardization unit, a data verification unit, and a wireless transmission unit;

[0015] The data filtering unit removes environmental interference values ​​and abnormal fluctuation data from the collected data through preset anti-interference filtering adapted to the aquaculture environment.

[0016] The data standardization unit converts heterogeneous data output from different types of sensors into a data format standard, eliminating differences in data dimensions;

[0017] The data verification unit verifies the integrity of the collected data and marks invalid data based on preset data verification rules.

[0018] Preferably, the microbial activity analysis module includes a bacterial count unit, a metabolic intensity analysis unit, and a dominant bacterial group identification unit;

[0019] The microbial community counting unit, based on data collected by microbial sensors and combined with a preset microbial community counting model, calculates the total number of viable bacteria and the proportion of various microbial communities in a unit mass of bedding material, achieving the following: ,

[0020] In the formula, V represents the total number of viable bacteria per unit mass of bedding material, C represents the microbial community signal value collected by the microbial sensor, D represents the bedding material density, K represents the temperature sensitivity coefficient, and T represents the current fermentation bed temperature. Indicates the optimal temperature;

[0021] The metabolic intensity analysis unit monitors the rate of change of key substances such as organic carbon and total nitrogen in the bedding material, compares them with preset metabolic activity assessment standards, and calculates the degree of microbial metabolic activity, achieving the following: ,

[0022] In the formula, M represents the degree of microbial metabolic activity. This indicates the change in organic carbon. This represents the change in total nitrogen. This represents the organic carbon conversion efficiency coefficient. Indicates the total nitrogen conversion efficiency coefficient. Indicates the change over time. Indicates the total organic carbon content of the bedding material;

[0023] The dominant microbial community identification unit performs matching operations between the collected microbial community characteristic parameters and the standard parameters in the preset microbial community characteristic database, as follows: ,

[0024] In the formula, S represents the fitness of the bacterial community structure, and n represents the number of characteristic parameters of the bacterial community. This indicates the currently collected microbial community characteristic parameters. This represents the standard parameters in the preset microbial community feature database. This represents the feature parameter weights.

[0025] Preferably, the bedding material condition assessment module includes a physical condition assessment unit, a chemical condition assessment unit, and a degradation capacity assessment unit;

[0026] The physical condition assessment unit combines bedding thickness monitoring data and bulkiness test data, and compares them against preset bedding physical condition standards to determine the compaction degree and thickness compliance of the bedding. The physical condition assessment of the bedding is achieved as follows: ,

[0027] In the formula, P represents the physical state evaluation index of the bedding material, and H represents the measured thickness of the bedding material. This indicates the optimal bedding thickness, and D represents the measured density of the bedding material. Indicates the optimal density of the bedding material;

[0028] The chemical state assessment unit analyzes the chemical environmental compatibility of the bedding material based on monitoring data of pH value, total nitrogen content, and organic carbon content, and with reference to the preset chemical stability index system of the bedding material.

[0029] The degradation capacity assessment unit, by monitoring fecal degradation rate and ammonia nitrogen conversion efficiency parameters, and combining these with a preset fecal degradation efficiency benchmark, completes a quantitative assessment of the bedding waste treatment capacity, achieving the following: ,

[0030] In the formula, J represents the bedding degradation capacity assessment index. This indicates the measured rate of fecal degradation. Indicates the optimal rate of fecal degradation. This indicates the measured ammonia nitrogen conversion efficiency. This indicates the optimal ammonia nitrogen conversion efficiency.

[0031] Preferably, the intelligent control execution module consists of a temperature control unit, a humidity control unit, a turning execution unit, and a microbial replenishment unit. Each control unit uses the results of microbial activity analysis and the evaluation results of the bedding material status as the decision-making basis and executes a preset control strategy. The temperature control unit, through the coordinated linkage of heating and ventilation components, activates the corresponding components to complete temperature adjustment when the fermentation bed temperature exceeds the preset suitable range. The humidity control unit is equipped with humidification and dehumidification equipment, and performs adaptive control operations when the humidity deviates from the preset suitable range. The turning execution unit uses an adjustable turning mechanism to dynamically adjust the turning depth and frequency according to the compaction degree of the bedding material and the preset turning parameter standards. The microbial replenishment unit has a built-in quantitative feeding mechanism to accurately replenish the corresponding compound microbial agent when the number or activity of microorganisms is lower than the preset threshold.

[0032] Preferably, the anomaly warning module includes a graded warning unit, a multi-channel notification unit, and a fault location unit. The graded warning unit classifies abnormal data, abnormal microbial activity, abnormal bedding function, and abnormal equipment operation into three levels: minor warning, moderate warning, and severe warning, based on preset anomaly severity judgment standards. Different levels correspond to preset response priorities. The multi-channel notification unit matches preset notification strategies according to the warning level. The fault location unit accurately locates the abnormal module, specific equipment, and monitoring point based on the operating status data of each module, combined with preset fault troubleshooting logic and data interaction links.

[0033] Preferably, the cloud-based data management module includes a data storage unit, a data tracing unit, a trend analysis unit, and a parameter optimization unit. The data storage unit adopts a distributed storage architecture that supports massive amounts of time-series data, and the storage period meets the preset data retention period requirements. The data tracing unit associates basic information such as breeding batch, fermentation bed number, and breeding category, and quickly retrieves the corresponding historical monitoring data of the fermentation bed through preset search dimensions. The trend analysis unit analyzes the long-term accumulated data on microbial activity, bedding status, and control effects through a preset machine learning model, and explores the data change patterns and potential correlations between indicators. The parameter optimization unit combines historical operating data with a preset breeding effect evaluation index system to generate optimization suggestions for fermentation bed operating parameters.

[0034] Preferably, the data preprocessing and transmission module further includes an additional data encryption unit and an emergency backup unit; the data encryption unit encrypts the data during transmission by means of encryption that meets the preset data security level; the emergency backup unit backs up the preprocessed microbial activity data, bedding status data and other key data to the local storage device according to the preset backup frequency and storage strategy, and restores the key information based on the local backup data in the event of cloud transmission interruption or cloud system failure.

[0035] Preferably, the intelligent control execution module and the cloud data management module establish a two-way communication mechanism; after completing the control operation, the intelligent control execution module feeds back the actual execution parameters such as control duration, amount of supplemented inoculum, turning depth, and turning frequency to the cloud data management module in real time; the parameter optimization unit of the cloud data management module verifies the feedback data, determines the effectiveness of the control operation by comparing it with the preset feedback data evaluation standard, and dynamically adjusts the subsequent control strategy by combining historical optimization suggestions and real-time feedback data.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] 1. To address the problems of existing ecological aquaculture fermentation bed monitoring, such as reliance on manual operation, fragmented and incomplete data collection, difficulty in accurately controlling the microbial community and bedding status, lagging and crude control measures, untimely detection of abnormalities, and difficulty in long-term effective data utilization, this invention aims to improve the intelligence and precision of fermentation bed monitoring, enhance aquaculture management efficiency, extend the service life of fermentation beds, and reduce aquaculture risks and labor costs. This invention establishes a solid data foundation through multi-dimensional data collection, ensures data quality through preprocessing and transmission, achieves in-depth and precise analysis of the status based on microbial activity analysis and bedding status assessment, completes targeted intervention with an intelligent control execution module, prevents aquaculture risks with an anomaly early warning module, and achieves data retention, traceability, and strategy optimization through a cloud-based data management module, thus comprehensively breaking through the limitations of traditional monitoring models.

[0038] 2. This invention achieves dynamic analysis of the microbial community in the fermentation bed through the statistical analysis of the number of microorganisms, the analysis of metabolic intensity, and the identification of dominant microorganisms. By combining the microbial community signal value and environmental parameters, it calculates the total number of viable bacteria, the degree of metabolic activity, and the adaptability of the microbial community structure, monitors the trend of microbial activity decline in real time, provides early warning of the risk of microbial imbalance, and guides precise microbial replenishment operations, thereby extending the service life of the fermentation bed, improving the efficiency of manure degradation, and significantly improving the quality of the breeding environment.

[0039] 3. This invention achieves quantitative analysis of the comprehensive performance of bedding materials through physical state assessment, chemical state assessment, and degradation capacity assessment. Based on multidimensional data, an assessment model is constructed to accurately determine the compaction, chemical stability, and waste treatment capacity of the bedding materials. The degradation capacity assessment combines the degradation rate of feces and the ammonia nitrogen conversion efficiency to comprehensively reflect the functional status of the bedding materials and significantly improve the efficiency of bedding material use.

[0040] 4. This invention achieves precise operation of temperature regulation, humidity control, turning operations, and microbial replenishment based on the analysis results of microbial activity and bedding state. It regulates temperature through heating and ventilation linkage, dynamically controls humidity through humidification and dehumidification equipment, optimizes bedding structure through adjustable turning mechanism, and combines microbial activity threshold triggering microbial replenishment strategy to keep the fermentation bed environment in the optimal state at all times, avoiding performance degradation caused by excessively high temperature, excessively low humidity, or microbial imbalance. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the structure of a fermentation bed monitoring system for ecological aquaculture according to the present invention;

[0042] Figure 2 The present invention provides an operational flow chart for a fermentation bed monitoring system for ecological aquaculture. Figure 1 ;

[0043] Figure 3 The present invention provides an operational flow chart for a fermentation bed monitoring system for ecological aquaculture. Figure 2 ;

[0044] Figure 4 The present invention provides an operational flow chart for a fermentation bed monitoring system for ecological aquaculture. Figure 3 . Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example

[0046] Please see Figures 1-4 As shown, the present invention provides a technical solution including a multi-dimensional data acquisition module, a data preprocessing and transmission module, a microbial activity analysis module, a bedding material status assessment module, an intelligent control execution module, an anomaly early warning module, and a cloud data management module;

[0047] The multi-dimensional data acquisition module collects key basic data such as temperature, humidity, microbial activity, and bedding thickness of the fermentation bed in real time.

[0048] The data preprocessing and transmission module filters and standardizes the collected heterogeneous data;

[0049] The microbial activity analysis module analyzes the number of bacteria, metabolic intensity, and dominant bacterial community structure in the fermentation bed based on preprocessed data.

[0050] The bedding condition assessment module combines data to evaluate the physical compaction, chemical stability, and fecal degradation capacity of the bedding material.

[0051] The intelligent control and execution module performs targeted operations such as temperature adjustment, turning, and inoculum replenishment based on the microbial activity analysis results and the bedding condition assessment results.

[0052] The anomaly warning module monitors the operating status of each module and analyzes and evaluates the results in real time, and issues a graded warning when a preset anomaly condition is triggered.

[0053] The cloud-based data management module stores and traces all data throughout the process, and optimizes system operating parameters based on historical data.

[0054] In this embodiment, the multi-dimensional data acquisition module includes a temperature sensor, a humidity sensor, a pH sensor, an ammonia concentration sensor, a microbial sensor, and a bedding thickness sensor. Each sensor is arranged in the corresponding monitoring layer (surface, middle, and lower layers) according to the layered structure of the fermentation bed and a preset monitoring density. The microbial sensor has a built-in adaptive microbial activity detection component to collect real-time data on the number of viable bacteria and metabolic data of the compound bacteria. The bedding thickness sensor uses non-contact ranging to meet the accuracy requirements for dynamic monitoring of bedding thickness under the preset breeding scenario.

[0055] In this embodiment, the data preprocessing and transmission module includes a data filtering unit, a data standardization unit, a data verification unit, and a wireless transmission unit;

[0056] The data filtering unit removes environmental interference values ​​and abnormal fluctuation data from the collected data through preset anti-interference filtering adapted to the aquaculture environment.

[0057] The data standardization unit converts heterogeneous data output from different types of sensors into a data format standard, eliminating differences in data dimensions;

[0058] The data verification unit verifies the integrity of the collected data and marks invalid data based on preset data verification rules;

[0059] The wireless transmission unit is compatible with multiple wireless transmission protocols and can automatically switch to a transmission mode that meets the preset transmission stability requirements based on the signal coverage strength of the breeding area, so as to achieve real-time data transmission without loss.

[0060] In this embodiment, the microbial activity analysis module is equipped with a bacterial count unit, a metabolic intensity analysis unit, and a dominant bacterial group identification unit;

[0061] The microbial community counting unit, based on data collected by microbial sensors and combined with a preset microbial community counting model, calculates the total number of viable bacteria and the proportion of various microbial communities in a unit mass of bedding material, achieving the following: ,

[0062] In the formula, V represents the total number of viable bacteria per unit mass of bedding material, C represents the microbial community signal value collected by the microbial sensor, D represents the bedding material density, K represents the temperature sensitivity coefficient, and T represents the current fermentation bed temperature. Indicates the optimal temperature;

[0063] The metabolic intensity analysis unit monitors the rate of change of key substances such as organic carbon and total nitrogen in the bedding material, compares them with preset metabolic activity assessment standards, and calculates the degree of microbial metabolic activity, achieving the following: ,

[0064] In the formula, M represents the degree of microbial metabolic activity. This indicates the change in organic carbon. This represents the change in total nitrogen. This represents the organic carbon conversion efficiency coefficient. Indicates the total nitrogen conversion efficiency coefficient. Indicates the change over time. Indicates the total organic carbon content of the bedding material;

[0065] The dominant microbial community identification unit performs matching operations between the collected microbial community characteristic parameters and the standard parameters in the preset microbial community characteristic database, as follows: ,

[0066] In the formula, S represents the fitness of the bacterial community structure, and n represents the number of characteristic parameters of the bacterial community. This indicates the currently collected microbial community characteristic parameters. This represents the standard parameters in the preset microbial community feature database. The characteristic parameter weights are used to determine the types and trends of dominant microbial communities in the fermentation bed, and to complete the assessment of the adaptability of the microbial community structure.

[0067] In this embodiment, the bedding material condition assessment module includes a physical condition assessment unit, a chemical condition assessment unit, and a degradation capacity assessment unit;

[0068] The physical condition assessment unit combines bedding thickness monitoring data and bulkiness test data, and compares them against preset bedding physical condition standards to determine the compaction degree and thickness compliance of the bedding. The physical condition assessment of the bedding is achieved as follows: ,

[0069] In the formula, P represents the physical state evaluation index of the bedding material, and H represents the measured thickness of the bedding material. This indicates the optimal bedding thickness, and D represents the measured density of the bedding material. Indicates the optimal density of the bedding material;

[0070] The chemical state assessment unit analyzes the chemical environmental compatibility of the bedding material based on monitoring data such as pH value, total nitrogen content, and organic carbon content, and with reference to the preset chemical stability index system of the bedding material.

[0071] The degradation capacity assessment unit, by monitoring parameters such as fecal degradation rate and ammonia nitrogen conversion efficiency, and combining them with a preset fecal degradation efficiency benchmark, completes a quantitative assessment of the bedding waste treatment capacity, achieving the following: ,

[0072] In the formula, J represents the bedding degradation capacity assessment index. This indicates the measured rate of fecal degradation. Indicates the optimal rate of fecal degradation. This indicates the measured ammonia nitrogen conversion efficiency. This indicates the optimal ammonia nitrogen conversion efficiency.

[0073] In this embodiment, the intelligent control execution module consists of a temperature control unit, a humidity control unit, a turning execution unit, and a microbial replenishment unit. Each control unit uses the results of microbial activity analysis and the evaluation results of the bedding material status as the decision-making basis to execute a preset control strategy. The temperature control unit, through the coordinated linkage of heating and ventilation components, activates the corresponding components to complete temperature adjustment when the fermentation bed temperature exceeds the preset suitable range. The humidity control unit is equipped with humidification and dehumidification equipment, and performs adaptive control operations when the humidity deviates from the preset suitable range. The turning execution unit uses an adjustable turning mechanism to dynamically adjust the turning depth and frequency according to the compaction degree of the bedding material and the preset turning parameter standards. The microbial replenishment unit has a built-in quantitative feeding mechanism to accurately replenish the corresponding compound microbial agent when the number or activity of microorganisms is lower than the preset threshold.

[0074] In this embodiment, the anomaly early warning module includes a graded early warning unit, a multi-channel notification unit, and a fault location unit. The graded early warning unit classifies abnormal data, abnormal microbial activity, abnormal bedding function, and abnormal equipment operation into three levels: minor, moderate, and severe, based on a preset anomaly severity judgment standard. Different levels correspond to preset response priorities. The multi-channel notification unit matches a preset notification strategy according to the early warning level and simultaneously pushes early warning information through channels such as the aquaculture terminal APP, SMS, and on-site audible and visual alarm devices. The fault location unit accurately locates the abnormal module, specific equipment, and monitoring point based on the operating status data of each module, combined with preset fault investigation logic and data interaction links.

[0075] In this embodiment, the cloud-based data management module includes a data storage unit, a data traceability unit, a trend analysis unit, and a parameter optimization unit. The data storage unit adopts a distributed storage architecture that supports massive amounts of time-series data, with a storage period that meets the preset data retention period requirements and has efficient read / write capabilities for massive amounts of monitoring data. The data traceability unit associates basic information such as breeding batches, fermentation bed numbers, and breeding categories, and quickly retrieves historical monitoring data of the corresponding fermentation bed through preset search dimensions, achieving full-process data traceability. The trend analysis unit analyzes long-term accumulated data such as microbial activity, bedding status, and control effects through a preset machine learning model, uncovering data change patterns and potential correlations between indicators. The parameter optimization unit combines historical operating data with a preset breeding effect evaluation index system to generate optimization suggestions for fermentation bed operating parameters.

[0076] In this embodiment, the data preprocessing and transmission module further includes a data encryption unit and an emergency backup unit. The data encryption unit encrypts the data during transmission by using encryption that meets the preset data security level, preventing data leakage and tampering risks. The emergency backup unit backs up key data such as preprocessed microbial activity data and bedding status data to a local storage device according to a preset backup frequency and storage strategy. In the event of cloud transmission interruption or cloud system failure, the key information can be restored based on the local backup data.

[0077] In this embodiment, the intelligent control execution module and the cloud data management module establish a two-way communication mechanism. After completing the control operation, the intelligent control execution module feeds back the actual execution parameters such as control duration, amount of supplemented inoculum, turning depth, and turning frequency to the cloud data management module in real time. The parameter optimization unit of the cloud data management module verifies the feedback data, determines the effectiveness of the control operation by comparing it with the preset feedback data evaluation standard, and dynamically adjusts the subsequent control strategy by combining historical optimization suggestions and real-time feedback data.

[0078] Working Principle: Real-time monitoring of key operating parameters is achieved through sensors deployed in the surface, middle, and lower layers of the fermentation bed, monitoring temperature, humidity, pH, ammonia concentration, microbial activity, and bedding thickness. The sensors are layered at a preset density to ensure coverage of the fermentation bed's vertical profile and comprehensively capture environmental changes. The microbial sensors have built-in specific detection components for accurate identification of complex microbial communities, while the bedding thickness sensor uses non-contact ranging technology to dynamically reflect changes in bedding thickness. The collected heterogeneous data undergoes anti-interference filtering to remove environmental fluctuations and abnormal noise. Subsequently, a standardization unit converts the non-uniform format data output from different types of sensors into standardized dimensions, eliminating dimensional differences. Finally, a verification unit marks invalid data according to preset rules. The system retains complete data for analysis; the wireless transmission unit dynamically switches between LoRa, NB-IoT, or 5G protocols based on signal strength in the breeding area, and features encryption and emergency backup; the microbial activity analysis module analyzes the microbial community status based on pre-processed microbial signal data and environmental parameters; the microbial quantity statistics unit calculates the total number of viable bacteria and their classification percentage per unit mass of bedding material using a correlation model between sensor signal values ​​and factors such as density and temperature sensitivity; the metabolic intensity analysis unit monitors the consumption rate of organic carbon, total nitrogen, and other substances, and deduces the degree of microbial metabolic activity based on the conversion efficiency coefficient; the dominant microbial community identification unit compares the real-time collected microbial community characteristics with a preset database to identify the dominant microbial community types and dynamic changes, and determines the suitability of the microbial community structure. The bedding condition assessment module evaluates bedding performance based on physical, chemical, and degradation parameters. The physical condition assessment unit combines thickness and bulk density data to determine the compaction level and thickness compliance. The chemical condition assessment unit analyzes the chemical stability of the bedding using pH, C, and N ratios. The degradation capacity assessment unit monitors the decomposition rate of feces and ammonia nitrogen conversion efficiency to quantify the bedding waste treatment capacity. Based on microbial activity and bedding condition analysis results, precise control operations are implemented. The temperature control unit uses a linkage between heating and ventilation equipment to quickly adjust the temperature when it deviates from the optimal range. The humidity control unit is equipped with humidification and dehumidification equipment to maintain bedding humidity within the optimal range. The turning unit dynamically adjusts the turning depth and frequency based on the compaction level to restore bedding permeability. The system features a gas-resistant microbial culture system; an automatic microbial supplementation unit that replenishes compound microbial agents at a preset ratio when microbial activity is insufficient; real-time monitoring of system operation status and analysis results; and a tiered early warning mechanism triggered when preset abnormal conditions are met; minor warnings are pushed to the app; moderate warnings trigger SMS and on-site audible and visual alarms; and severe warnings combine buzzers and remote alarms to ensure priority handling of emergencies; a fault location unit accurately identifies the source of abnormalities through data link tracing; a cloud-based data management module handles the storage, traceability, and analysis of data throughout the entire process; a distributed storage unit supports efficient reading and writing of massive amounts of time-series data to meet long-term data retention needs; and a data traceability unit associates metadata such as breeding batches and fermentation bed numbers to achieve rapid retrieval of historical records and full-process traceability.The trend analysis unit utilizes machine learning models to uncover patterns in indicators such as microbial activity and bedding status, predicting potential risks. The parameter optimization unit combines historical operational data with aquaculture performance evaluation systems to dynamically adjust control strategies, driving the system from experience-driven to data-driven optimization. An encryption unit is added to the data preprocessing and transmission stages, employing AES-256 to protect sensitive data from tampering or leakage. The emergency backup unit periodically archives critical data to local devices; in the event of cloud transmission interruption or system failure, critical information is restored based on the backup data. This dual protection mechanism strengthens data security and establishes a real-time communication link between the intelligent control execution module and the cloud data management module. After control operations are completed, the actual execution parameters are immediately fed back to the cloud. The cloud parameter optimization unit verifies the feedback data and dynamically adjusts subsequent control plans based on historical strategies and real-time status.

[0079] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their likenesses.

[0080] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A monitoring system for a fermentation bed used in ecological aquaculture, characterized in that: It includes a multi-dimensional data acquisition module, a data preprocessing and transmission module, a microbial activity analysis module, a bedding material status assessment module, an intelligent control and execution module, an anomaly early warning module, and a cloud data management module; The multi-dimensional data acquisition module collects key basic data such as temperature, humidity, microbial activity, and bedding thickness of the fermentation bed in real time. The data preprocessing and transmission module filters and standardizes the collected heterogeneous data; The microbial activity analysis module analyzes the number of bacteria, metabolic intensity, and dominant bacterial community structure in the fermentation bed based on preprocessed data. The bedding condition assessment module combines data to evaluate the physical compaction, chemical stability, and fecal degradation capacity of the bedding material. The intelligent control and execution module performs temperature adjustment, turning, and inoculum replenishment operations based on the microbial activity analysis results and the bedding material status assessment results. The anomaly warning module monitors the operating status of each module and analyzes and evaluates the results in real time, and issues a graded warning when a preset anomaly condition is triggered. The cloud-based data management module stores and traces all data throughout the process, and optimizes system operating parameters based on historical data.

2. The monitoring system for a fermentation bed used in ecological aquaculture according to claim 1, characterized in that: The multi-dimensional data acquisition module includes a temperature sensor, a humidity sensor, a pH sensor, an ammonia concentration sensor, a microbial sensor, and a bedding thickness sensor. Each sensor is arranged in the corresponding monitoring layer according to the layered structure of the fermentation bed and a preset monitoring density. Among them, the microbial sensor has a built-in adaptive microbial activity detection component to collect the number of live bacteria and metabolic data of the compound bacteria in real time.

3. The monitoring system for a fermentation bed used in ecological aquaculture according to claim 1, characterized in that: The data preprocessing and transmission module includes a data filtering unit, a data standardization unit, a data verification unit, and a wireless transmission unit; The data filtering unit removes environmental interference values ​​and abnormal fluctuation data from the collected data through preset anti-interference filtering adapted to the aquaculture environment. The data standardization unit converts heterogeneous data output from different types of sensors into a data format standard, eliminating differences in data dimensions; The data verification unit verifies the integrity of the collected data and marks invalid data based on preset data verification rules.

4. The monitoring system for a fermentation bed used in ecological aquaculture according to claim 1, characterized in that: The microbial activity analysis module is equipped with a bacterial count unit, a metabolic intensity analysis unit, and a dominant bacterial group identification unit. The microbial community counting unit, based on data collected by microbial sensors and combined with a preset microbial community counting model, calculates the total number of viable bacteria per unit mass of bedding material, achieving the following: , In the formula, V represents the total number of viable bacteria per unit mass of bedding material, C represents the microbial community signal value collected by the microbial sensor, D represents the bedding material density, K represents the temperature sensitivity coefficient, and T represents the current fermentation bed temperature. Indicates the optimal temperature; The metabolic intensity analysis unit monitors the rate of change of key substances such as organic carbon and total nitrogen in the bedding material, compares them with preset metabolic activity assessment standards, and calculates the degree of microbial metabolic activity, achieving the following: , In the formula, M represents the degree of microbial metabolic activity. This indicates the change in organic carbon. This represents the change in total nitrogen. This represents the organic carbon conversion efficiency coefficient. Indicates the total nitrogen conversion efficiency coefficient. Indicates the change over time. Indicates the total organic carbon content of the bedding material; The dominant microbial community identification unit performs matching operations between the collected microbial community characteristic parameters and the standard parameters in the preset microbial community characteristic database, as follows: , In the formula, S represents the fitness of the bacterial community structure, and n represents the number of bacterial community characteristic parameters. This indicates the currently collected microbial community characteristic parameters. This represents the standard parameters in the preset microbial community feature database. This represents the feature parameter weights.

5. The monitoring system for a fermentation bed used in ecological aquaculture according to claim 1, characterized in that: The bedding material condition assessment module includes a physical condition assessment unit, a chemical condition assessment unit, and a degradation capacity assessment unit. The physical condition assessment unit combines bedding thickness monitoring data and bulkiness test data, and compares them against preset bedding physical condition standards to determine the compaction degree and thickness compliance of the bedding. The physical condition assessment of the bedding is achieved as follows: , In the formula, P represents the physical state evaluation index of the bedding material, and H represents the measured thickness of the bedding material. This indicates the optimal bedding thickness, and D represents the measured density of the bedding material. Indicates the optimal density of the bedding material; The chemical state assessment unit analyzes the chemical environmental compatibility of the bedding material based on monitoring data of pH value, total nitrogen content, and organic carbon content, and with reference to the preset chemical stability index system of the bedding material. The degradation capacity assessment unit, by monitoring fecal degradation rate and ammonia nitrogen conversion efficiency parameters, and combining these with a preset fecal degradation efficiency benchmark, completes a quantitative assessment of the bedding waste treatment capacity, achieving the following: , In the formula, J represents the bedding degradation capacity assessment index. This indicates the measured rate of fecal degradation. Indicates the optimal rate of fecal degradation. This indicates the measured ammonia nitrogen conversion efficiency. This indicates the optimal ammonia nitrogen conversion efficiency.

6. The monitoring system for a fermentation bed used in ecological aquaculture according to claim 1, characterized in that: The intelligent control and execution module consists of a temperature control unit, a humidity control unit, a turning execution unit, and a microbial replenishment unit. Each control unit uses the results of microbial activity analysis and the evaluation results of the bedding material status as the basis for decision-making and executes a preset control strategy. The temperature control unit, through the coordinated linkage of heating and ventilation components, activates the corresponding components to complete temperature adjustment when the fermentation bed temperature exceeds the preset suitable range. The humidity control unit is equipped with humidification and dehumidification equipment, and performs adaptive control operations when the humidity deviates from the preset suitable range. The turning execution unit uses an adjustable turning mechanism to dynamically adjust the turning depth and frequency according to the compaction degree of the bedding material and the preset turning parameter standards. The microbial replenishment unit has a built-in quantitative feeding mechanism to accurately replenish the corresponding compound microbial agent when the number or activity of microorganisms is lower than the preset threshold.

7. The monitoring system for a fermentation bed used in ecological aquaculture according to claim 1, characterized in that: The anomaly warning module includes a graded warning unit, a multi-channel notification unit, and a fault location unit. The graded warning unit classifies data anomalies, microbial activity anomalies, bedding material function anomalies, and equipment operation anomalies into three levels: minor warning, moderate warning, and severe warning, according to a preset anomaly degree judgment standard. Different levels correspond to preset response priorities. The multi-channel notification unit matches preset notification strategies according to the warning level; the fault location unit accurately locates the abnormal module, specific equipment and monitoring point based on the operating status data of each module, combined with preset fault investigation logic and data interaction links.

8. The monitoring system for a fermentation bed used in ecological aquaculture according to claim 1, characterized in that: The cloud-based data management module includes a data storage unit, a data tracing unit, a trend analysis unit, and a parameter optimization unit. The data storage unit adopts a distributed storage architecture that supports massive amounts of time-series data, and the storage period meets the preset data retention period requirements. The data tracing unit associates basic information such as breeding batch, fermentation bed number, and breeding category, and can quickly retrieve the corresponding historical monitoring data of the fermentation bed through preset search dimensions. The trend analysis unit uses a preset machine learning model to analyze long-term accumulated data on microbial activity, bedding status, and control effects, and to uncover data change patterns and potential correlations between indicators. The parameter optimization unit combines historical operating data with a preset breeding effect evaluation index system to generate optimization suggestions for fermentation bed operating parameters.

9. A monitoring system for an ecological aquaculture fermentation bed according to claim 3, characterized in that: The data preprocessing and transmission module also includes an additional data encryption unit and an emergency backup unit. The data encryption unit encrypts the data during transmission by using encryption that meets the preset data security level. The emergency backup unit backs up the preprocessed microbial activity data, bedding status data and other key data to the local storage device according to the preset backup frequency and storage strategy. In the event of cloud transmission interruption or cloud system failure, the key information can be restored based on the local backup data.

10. A monitoring system for an ecological aquaculture fermentation bed according to claim 6, characterized in that: The intelligent control execution module and the cloud data management module establish a two-way communication mechanism; after completing the control operation, the intelligent control execution module feeds back the actual execution parameters such as control duration, amount of supplemented inoculum, turning depth, and turning frequency to the cloud data management module in real time. The parameter optimization unit of the cloud data management module verifies the feedback data, judges the effectiveness of the control operation by comparing it with the preset feedback data evaluation standards, and dynamically adjusts the subsequent control strategy by combining historical optimization suggestions and real-time feedback data.

Images