Chicken farm environment data closed-loop regulation and control and abnormity early warning method and system

Abstract

The invention discloses a chicken farm environment data closed-loop regulation and control and abnormity early warning method and system, and belongs to the technical field of chicken farm monitoring, and the system comprises an environment data collection module, a data transmission and storage module, a data analysis and decision module, and a regulation and early warning execution module. The environment data acquisition module comprises a multi-dimensional sensing sub-module, a data preprocessing sub-module and an acquisition time sequence control sub-module, and the environment data acquisition module realizes real-time and comprehensive acquisition of key environment parameters in the chicken farm and provides data support for analysis, regulation and control. According to the chicken farm environment data closed-loop regulation and control and abnormity early warning system, the system firstly collects and preprocesses henhouse environment data and transmits the henhouse environment data to the cloud synchronous epidemic prevention center in a dual mode, the cloud analyzes the henhouse environment data to generate an early warning and regulation instruction, the early warning and regulation instruction is fed back in real time to form a closed loop after execution, and precise environment regulation and control, abnormal early warning and enhanced epidemic prevention cooperation are achieved. The breeding automation level is improved, and cost reduction and quality improvement are facilitated.

Description

Technical Field

[0001] This invention relates to the field of chicken farm monitoring technology, specifically to a method and system for closed-loop control and abnormal early warning of chicken farm environmental data. Background Technology

[0002] Chicken farms provide a stable and suitable growth environment for chickens. During the chicken farming process, the farm environment (temperature, humidity, ammonia, etc.) directly affects the health, survival rate, and egg production rate of the flock. Therefore, environmental data monitoring is necessary. Simultaneously, during monitoring, rapid early warning and handling are required for any abnormalities. This necessitates a closed-loop control and anomaly early warning method and system for chicken farm environmental data to maintain the normal operation of the farm. For example, Chinese invention patent application number 201711258231.2, filed on December 4, 2017, describes an Internet of Things (IoT)-based chicken farm environmental management system. During operation, the IoT... The technology enables real-time monitoring of environmental indices in chicken farms, and simultaneously allows for remote automatic control of facilities and equipment such as ventilation, heating, water mist, lighting, and atomized disinfection, thereby reducing labor costs, achieving precise regulation, and effectively mitigating production risks. Another example is a Chinese invention patent application with application number 201810692416.2 and application date of June 29, 2018, which describes an IoT-based environmental monitoring system for mountain and forest chicken farms. This system transmits data to a sending module via a communication module. The sending module displays current environmental information based on pre-set keyboard parameters and forwards the environmental information data to a remote server via a configured remote communication module.

[0003] During the operation of chicken farms, environmental factors, equipment failures leading to sanitary deterioration, and insufficient coordination in disease prevention can cause pathogens to breed and spread, which can then lead to epidemics. In the process of abnormal detection, if a reasonable epidemic prevention and control module is not set up, it will be impossible to link and synchronize epidemic prevention-related data with the epidemic prevention center and receive control requirements. Moreover, the risk of disease transmission is difficult to predict, and the handling of abnormalities is delayed, which can threaten the health of chicken flocks and the safety of breeding, affect the compliance of breeding, and cause economic losses. Summary of the Invention

[0004] The purpose of this invention is to provide a closed-loop control and anomaly early warning method and system for chicken farm environmental data, in order to solve the problems mentioned in the background art, such as the inability to link and synchronize epidemic prevention and control data with the epidemic prevention center and receive control requirements without a reasonable epidemic prevention and control module, the difficulty in predicting the risk of disease transmission, the lag in handling anomalies, the threat to the health of chicken flocks and the safety of breeding, the impact on breeding compliance, and the economic losses.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a closed-loop control and anomaly early warning system for chicken farm environmental data, comprising an environmental data acquisition module, a data transmission and storage module, a data analysis and decision-making module, and an execution control and early warning module; the environmental data acquisition module includes a multi-dimensional sensing submodule, a data preprocessing submodule, and a data acquisition timing control submodule, enabling real-time and comprehensive acquisition of key environmental parameters within the chicken farm, providing data support for analysis and control; the data transmission and storage module includes a multi-channel transmission submodule, a local caching submodule, and a cloud storage and management submodule, ensuring stable and secure transmission of the acquired data. The system includes storage to ensure data continuity and traceability. The data analysis and decision-making module comprises a real-time data analysis submodule, an anomaly diagnosis submodule, a control decision generation submodule, and a threshold dynamic optimization submodule. This module analyzes collected environmental data in real time to determine if the environmental state is normal and generates control decisions and early warning information for abnormal situations. The execution control and early warning module includes a control execution submodule, a multi-dimensional early warning submodule, and an equipment status monitoring submodule. This module executes the control instructions generated by the data analysis and decision-making module to precisely control the chicken farm environment. Simultaneously, it promptly pushes abnormal information to relevant personnel to ensure rapid handling of abnormal situations.

[0006] Preferably, the multi-dimensional sensing submodule is equipped with temperature sensors, humidity sensors, ammonia sensors, carbon dioxide sensors, and dust sensors, covering the chicken house feeding area, drinking area, roosting area, and sewage discharge area to ensure the comprehensiveness and representativeness of the collected data; the sensors support high-precision acquisition, with temperature error ≤ ±0.5℃ and humidity error ≤ ±3%RH; When the data preprocessing submodule is working, it performs noise reduction, filtering, and format standardization on the raw data collected by the sensor, removes abnormal interference data, and converts the data into a unified format that the system can recognize, thereby improving data quality. When the data acquisition timing control submodule is working, it flexibly sets the data acquisition frequency according to the needs of the chicken farm during the brooding, rearing, and laying periods. Under normal conditions, it collects data once every 5 minutes, and under high temperature and high humidity conditions, it collects data once every 1 minute, balancing data real-time performance and system energy consumption.

[0007] Preferably, the multi-channel transmission submodule adopts a wireless + wired dual transmission mode. The sensors inside the chicken house transmit data to the local gateway wirelessly via LoRa or Wi-Fi. The gateway then uploads the data to the cloud platform via Ethernet or 4G / 5G networks. At the same time, a network interface for the epidemic prevention center is added to realize two-way data interaction between the cloud platform and the livestock epidemic prevention center system. This supports the real-time synchronization of abnormal data of the chicken farm environment, equipment failure data, and stocking density data to the epidemic prevention center, and also receives epidemic prevention early warning information and control requirements issued by the epidemic prevention center. It also supports the function of resuming interrupted transmission to avoid data loss due to network interruption.

[0008] Preferably, when the local caching submodule is working, a caching unit is deployed on the local gateway. When the cloud network is abnormal, the collected data is automatically cached locally. The cache capacity supports data storage of ≥72 hours. After the network is restored, it is automatically synchronized to the cloud to ensure data continuity. When the cloud storage and management submodule is working, it builds a distributed database based on the cloud server to store the collected real-time data, historical data, equipment operation data and control records; it uses data encryption technology to protect the stored data, and supports data retrieval and export by time, region and parameter type, which facilitates subsequent data analysis and traceability; it also divides the epidemic prevention data storage partition separately to ensure the security and traceability of epidemic prevention related data.

[0009] Preferably, when the real-time data analysis submodule is working, it compares and analyzes the real-time collected data based on preset chicken farm environmental parameter thresholds, calculates parameter deviation values, and determines whether the environment is within the normal range; at the same time, it uses a trend analysis algorithm to predict the changing trend of environmental parameters and identify potential abnormal risks in advance. When the anomaly diagnosis submodule is working, it detects abnormal environmental parameters and uses multi-parameter correlation analysis to locate the cause of the anomaly, providing a precise basis for regulation. The control decision generation submodule automatically generates targeted control strategies based on the abnormal diagnosis results, and supports manual intervention mode, allowing managers to modify and execute control instructions according to the actual situation; When the threshold dynamic optimization submodule is working, it dynamically optimizes the environmental parameter thresholds at different breeding stages based on historical environmental data and breeding benefit data, thereby improving breeding benefits.

[0010] Preferably, the control execution submodule is connected to the ventilation equipment, humidification equipment, cooling equipment, heating equipment, and sewage discharge equipment of the chicken farm through relays and frequency converters. After receiving the control decision command, it automatically controls the start-up, shutdown, operating power, and running time of the relevant equipment to achieve closed-loop control of environmental parameters. When the multi-dimensional early warning submodule is working, it will issue early warning information through local audible and visual alarms, remote message push, and platform pop-up alarm when it detects abnormal environmental parameters or equipment failure. The early warning information includes the type of abnormality, the area of ​​abnormality, the value of abnormal parameters, and suggested handling measures. It supports graded early warning according to the severity of the abnormality, with different levels corresponding to different push frequencies and processing time limits. The equipment status monitoring submodule monitors and controls the operating status of the equipment in real time. When the equipment malfunctions, it automatically issues an equipment malfunction warning and records the malfunction time and malfunction type, which facilitates timely maintenance by management personnel.

[0011] A method for closed-loop control and anomaly early warning of chicken farm environmental data includes the following steps: S1. Multi-dimensional environmental data collection and synchronous transmission enables accurate collection, preprocessing, and multi-channel transmission and backup of core environmental parameters in chicken farms, while simultaneously synchronizing epidemic prevention-related data to provide a complete and reliable data foundation for subsequent analysis. S2. Real-time data analysis and anomaly decision generation: Through data analysis, anomalies are identified and tiered early warning information and targeted control decisions are generated simultaneously, providing accurate basis for environmental control and anomaly handling. S3, Control Execution and Status Closed-Loop Feedback: Executes control commands and provides real-time feedback on the effects, forming a closed-loop control system. At the same time, it records data to support subsequent optimization and ensures a stable and controllable environment.

[0012] Preferably, S1 consists of two steps: S11. Parameter Acquisition and Preprocessing: Start the environmental data acquisition module, and collect temperature, humidity and ammonia parameters in key areas of the chicken house through the multi-dimensional sensor submodule. The data preprocessing submodule completes noise reduction and standardization, and removes interference data. S12. Data transmission and backup: The pre-processed data is transmitted to the cloud platform via both wireless and wired modes. At the same time, epidemic prevention-related data is synchronized through the network interface of the epidemic prevention center, and the local cache submodule backs up the data to ensure data integrity.

[0013] Preferably, S2 consists of two steps: S21. Data analysis and anomaly location: The real-time data analysis submodule reads real-time data, compares it with preset thresholds and combines trend analysis to judge the environmental status. If there are anomalies or potential risks, the cause of the anomaly is located through multi-parameter correlation analysis. S22. Early Warning and Decision Generation: Generate graded early warning information based on the level of abnormality, push it to management personnel and the epidemic prevention center, and simultaneously generate targeted control decision instructions, supporting manual intervention and adjustment.

[0014] Preferably, S3 consists of two steps: S31. Precise Control and Execution: The control and early warning module receives control commands and automatically controls the start-up, shutdown, and operating parameters of ventilation and humidification equipment to achieve precise environmental control. S32. Closed-loop feedback and optimization: During the control process, feedback data is continuously collected to determine whether the parameters have returned to normal. If they have not returned, the strategy is adjusted and re-executed to form a closed loop. The system records data to support dynamic optimization of thresholds and data traceability.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: Employing a novel structural design, the system first collects and preprocesses chicken house environmental data, then transmits it to the cloud-based epidemic prevention center via dual-mode transmission. After cloud analysis, it generates early warning and control commands, which are then executed and fed back in real time, forming a closed loop. This achieves precise environmental control and early warning of anomalies, strengthens epidemic prevention collaboration, improves the level of automation in poultry farming, and helps reduce costs and improve quality. The specific details are as follows: (1) The closed-loop control and abnormal early warning system for the chicken farm's environmental data is equipped with an environmental data acquisition module, which serves as the core of the system's data source. Through multi-dimensional high-precision sensors, it achieves full coverage acquisition of environmental parameters in the chicken house. After preprocessing, it removes interference data to improve quality. Combined with the dynamic adjustment of the acquisition frequency during the breeding stage, it provides comprehensive, accurate, and reliable data support for subsequent transmission, analysis, and control, which is the basic premise for precise control.

[0016] (2) The closed-loop control and abnormal early warning system for the chicken farm's environmental data is equipped with a data transmission and storage module, which undertakes the key responsibilities of data flow and security assurance. It adopts a wireless + wired dual transmission mode with local caching to ensure stable data transmission and continuous data without loss. Cloud-based distributed encrypted storage enables data security traceability, and the epidemic prevention network interface opens up a two-way collaborative channel, providing a stable data hub support for data analysis and epidemic prevention linkage.

[0017] (3) The closed-loop control and early warning system for environmental data of the chicken farm is equipped with a data analysis and decision-making module, which serves as the core hub of the system. It achieves accurate judgment of environmental status through real-time comparison of thresholds and trend prediction. When an anomaly occurs, the root cause is located through correlation analysis, and targeted control strategies are automatically generated and manual intervention is supported. The threshold is dynamically optimized in combination with historical data, providing a scientific and accurate decision-making basis for control execution and early warning.

[0018] Furthermore, an execution control and early warning module is set up to realize the implementation of decisions and risk prevention and control. The precise execution of control instructions ensures closed-loop management of environmental parameters; multi-dimensional hierarchical early warning ensures timely response to anomalies; real-time monitoring of equipment status ensures stable operation, effectively reduces aquaculture risks, improves the efficiency of anomaly handling, and helps to standardize and improve aquaculture management.

[0019] (4) The closed-loop control and abnormal early warning method for chicken farm environmental data relies on the system to realize closed-loop control of chicken farm environmental data. Through precise data collection and transmission, intelligent analysis and decision-making, and efficient execution feedback, the environmental parameters of the chicken house are stabilized, and early warning and rapid handling of abnormalities are achieved. At the same time, it strengthens collaboration with the epidemic prevention center, improves the level of automation and intelligence in breeding management, ensures the health of the flock and the safety of breeding, and helps to reduce costs, improve quality and increase efficiency. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the system workflow structure of the present invention; Figure 2 This is a schematic diagram of the workflow structure of the method of the present invention. Detailed Implementation

[0021] 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.

[0022] Please see Figures 1-2 The present invention provides the following technical solution: a closed-loop control and anomaly early warning system for chicken farm environmental data.

[0023] It includes an environmental data acquisition module, a data transmission and storage module, a data analysis and decision-making module, and an execution, control, and early warning module. The environmental data acquisition module includes a multi-dimensional sensing submodule, a data preprocessing submodule, and an acquisition timing control submodule. The environmental data acquisition module enables real-time and comprehensive acquisition of key environmental parameters within the chicken farm, providing data support for analysis and regulation. The multi-dimensional sensing submodule is equipped with temperature sensors, humidity sensors, ammonia sensors, carbon dioxide sensors, and dust sensors, covering the chicken house's feeding area, drinking area, roosting area, and sewage discharge area to ensure the comprehensiveness and representativeness of the collected data. The sensors support high-precision acquisition with a temperature error of ≤±0.5℃ and a humidity error of ≤±3%RH. When the above-mentioned multi-dimensional sensing submodules are working, they are responsible for the real-time acquisition and raw signal output of multiple parameters of the chicken house environment. The work revolves around accurate perception, signal preprocessing and collaborative time-series acquisition. In key areas such as the chicken house feeding area, drinking area, resting area and sewage discharge area, special sensors such as temperature, humidity, ammonia, carbon dioxide and dust are accurately deployed to fully cover the chicken house environment monitoring needs. For different environmental parameters, signal conversion is accomplished through dedicated sensing mechanisms: temperature sensors monitor ambient temperature in real time and convert temperature signals into electrical signals by utilizing the characteristic that the resistance of a thermistor changes with temperature; humidity sensors convert ambient humidity into detectable electrical signals by utilizing the change in resistance or capacitance of moisture-sensitive materials after absorbing moisture; ammonia and carbon dioxide sensors achieve accurate sensing of gas concentration by triggering fluctuations in electrical signal intensity through chemical reactions between gas molecules and sensitive materials; and dust sensors rely on the principle of light scattering to capture the degree of light scattering by dust particles and convert it into quantified electrical signals. Meanwhile, the raw electrical signals output by each sensor are initially optimized. The built-in conditioning circuit amplifies weak signals and filters out interference noise. The calibration chip then corrects errors to ensure acquisition accuracy. In addition, the acquisition timing control submodule receives instructions and adjusts the acquisition frequency according to the needs of different breeding stages to achieve synchronous acquisition of multiple regions and parameters, providing high-quality raw data for subsequent data preprocessing.

[0024] When the data preprocessing submodule is working, it performs noise reduction, filtering, and format standardization on the raw data collected by the sensors, removes abnormal and interfering data, and converts the data into a unified format that the system can recognize, thereby improving data quality. When the above data preprocessing submodule is working, it optimizes the raw environmental data transmitted by the multi-dimensional sensing submodule to provide high-quality data support for subsequent cloud analysis and decision-making. The specific workflow is as follows: First, it receives raw electrical signal data of multiple parameters such as temperature, humidity, and ammonia, starts the data verification program, and removes abnormal and missing values ​​caused by sensor failure and signal interference to ensure data integrity. The data is then standardized to convert parameter data of different units and magnitudes into a unified standard range, eliminating the impact of dimensional differences on subsequent analysis. Simultaneously, a smoothing filter algorithm is used to further filter out residual high-frequency noise, improving data stability. After basic processing, the data is format-converted, transforming analog signals into digital signals recognizable by the cloud system, and then categorized and packaged according to preset rules. Finally, a data quality assessment mechanism is established to verify the accuracy of the processed data, ensuring that the data error meets the system requirements. The qualified data is then transmitted to the data transmission and storage module, while processing logs are retained for traceability. This ensures the reliability and availability of the data throughout the process, laying the foundation for accurate analysis and decision-making in the future.

[0025] When the data acquisition timing control submodule is working, it flexibly sets the data acquisition frequency according to the needs of the chicken farm during the brooding, rearing, and laying periods. Under normal conditions, it collects data once every 5 minutes, and under high temperature and high humidity conditions, it collects data once every 1 minute, balancing data real-time performance and system energy consumption.

[0026] The aforementioned data acquisition timing control submodule enables the orderly and accurate acquisition of chicken house environmental data. The workflow revolves around instruction reception, parameter configuration, timing scheduling, and status feedback. First, it receives the system's preset breeding stage parameters (brooding period, egg-laying period, etc.) and the acquisition instructions sent from the cloud, and analyzes the acquisition requirements and accuracy requirements of parameters such as temperature and humidity corresponding to different stages. Subsequently, based on the analysis results, the acquisition strategy was configured, setting a basic acquisition frequency of 5 minutes / time for normal scenarios, and triggering a high-frequency acquisition mode of 1 minute / time for special environments such as high temperature and high humidity. At the same time, the synchronous acquisition sequence of each sensor was defined to avoid data interference. After the configuration was completed, timing control commands were sent to the multi-dimensional sensing submodule to schedule the sensors in each area to acquire data synchronously according to the set frequency and timing. During the data acquisition process, the system monitors the sensor's operating status and data transmission in real time. If any abnormalities such as acquisition delay or signal interruption occur, a retry mechanism is immediately triggered and feedback is sent to the system fault warning unit. Simultaneously, the system periodically receives acquisition status feedback from the sensor submodules, dynamically fine-tuning the acquisition timing and frequency to ensure the real-time and continuous nature of data acquisition, providing stable data acquisition support for subsequent data preprocessing and analysis decisions.

[0027] The data transmission and storage module includes a multi-channel transmission submodule, a local cache submodule, and a cloud storage and management submodule. The data transmission and storage module enables stable transmission and secure storage of collected data, ensuring data continuity and traceability. The multi-channel transmission submodule adopts a dual transmission mode of wireless + wired. Sensors inside the chicken house transmit data wirelessly to the local gateway via LoRa and Wi-Fi. The gateway then uploads the data to the cloud platform via Ethernet or 4G / 5G networks. At the same time, a network interface for the epidemic prevention center is added to realize two-way data interaction between the cloud platform and the livestock epidemic prevention center system. It supports the real-time synchronization of abnormal data of chicken farm environment, equipment failure data, and stocking density data to the epidemic prevention center, and also receives epidemic prevention early warning information and control requirements issued by the epidemic prevention center. It supports the function of resuming interrupted transmission to avoid data loss due to network interruption.

[0028] When the above-mentioned multi-channel transmission submodule is working, it first receives the standardized digital data and classification and packaging information output by the data preprocessing submodule, and simultaneously reads the system's preset transmission priority rules to clarify the transmission priority of key parameters such as temperature and ammonia concentration. Then, the channel detection program is started to detect the link status, bandwidth and stability of the wireless + wired dual transmission channels in real time. Based on the detection results, the optimal transmission channel is dynamically selected. In normal scenarios, the wireless channel is given priority to ensure transmission flexibility. In scenarios with strong wireless signal interference and large data volume, the wired channel is automatically switched to ensure transmission stability. At the same time, the channel backup mechanism is enabled to avoid data loss. During the transmission phase, data is pushed in priority order, and key parameter data is encrypted and packaged for transmission to prevent data leakage. At the same time, control instructions, parameter configurations and other information are received from the cloud, parsed and forwarded to the corresponding sub-modules. During the transmission process, the data transmission status is monitored in real time, and indicators such as transmission progress and delay are recorded. If an abnormality such as transmission interruption or data packet loss occurs, the retransmission mechanism is immediately triggered, the backup channel is switched to retransmit, and the abnormal information is fed back to the system early warning unit. After the transmission is completed, a transmission log is generated, recording information such as channel selection, transmission duration, and data integrity for traceability. This ensures the real-time performance, stability, and security of data transmission throughout the process, building an efficient communication bridge between the data acquisition end and the cloud.

[0029] When the local caching submodule is working, it deploys a caching unit on the local gateway. When the cloud network is abnormal, it automatically caches the collected data locally. The cache capacity supports data storage of ≥72 hours. After the network is restored, it is automatically synchronized to the cloud to ensure data continuity. The aforementioned local caching submodule is equipped with a cloud storage module. During operation, it first receives preprocessed data pushed by the multi-channel transmission submodule, and simultaneously monitors the cloud transmission link status in real time to determine whether the data can be uploaded to the cloud storage module normally. When the transmission link is detected to be unobstructed, the data is synchronously uploaded to the cloud, and key parameters (such as abnormal values ​​of temperature and ammonia concentration) are extracted according to preset rules for local lightweight caching as a backup. If abnormal situations such as transmission interruption or cloud failure are detected, the full caching mode is immediately activated, and all data to be transmitted is stored in the local storage unit in timestamp order. A partitioned storage strategy is used to distinguish between real-time data and historical data to avoid cache chaos. A data priority mechanism is established during the caching process. Critical data such as environmental parameters exceeding standards and equipment failure warnings are marked with high priority to ensure their cache integrity. Routine monitoring data is stored with normal priority to optimize cache resource allocation. At the same time, the status of the transmission link recovery is monitored in real time. Once the link is restored, the data synchronization mechanism is immediately triggered to upload the cached data to the cloud in batches according to priority. After the upload is completed, the data integrity is verified to ensure no packet loss. In addition, the entire process records cache logs, with detailed annotations of cache time, data type, synchronization status, and other information, which facilitates subsequent data traceability and troubleshooting. Through real-time monitoring, dynamic caching, and breakpoint resumption management, the continuity and security of data transmission are ensured, providing data backup support for stable system operation. When the cloud storage and management submodule is working, it builds a distributed database based on the cloud server to store the collected real-time data, historical data, equipment operation data and control records; it uses data encryption technology to protect the stored data, and supports data retrieval and export by time, region and parameter type, which facilitates subsequent data analysis and traceability; it also sets up a separate partition for epidemic prevention data storage to ensure the security and traceability of epidemic prevention-related data.

[0030] When the cloud storage and management submodule is working, it first receives encrypted data uploaded by the multi-channel transmission submodule, starts the data verification mechanism, checks the data integrity and format standardization, removes abnormal data generated during transmission, and synchronizes the data verification results with the local cache submodule to ensure data consistency. After verification, the data is categorized according to preset rules—real-time monitoring data such as temperature and humidity, equipment operation data, and abnormal early warning data are divided into different storage partitions, linked with timestamps and chicken coop area information, and structured data archives are generated. The storage phase employs a distributed storage architecture, performs multiple backups and encryption on critical data, compresses historical data to optimize storage resources, sets data retention periods, and automatically cleans up expired and redundant data. In daily management, it responds to data query requests from various modules of the system, quickly retrieves target data according to permissions, and supports multi-dimensional searches by time, region, parameter type, etc. At the same time, it monitors the operating status of the storage system in real time, investigates storage faults and security risks, and receives instruction generation requirements from the data analysis and decision-making module. It then formats and distributes instructions such as control strategies and parameter configurations to the multi-channel transmission submodule, and records the instruction distribution log synchronously. Throughout the process, it ensures data storage security and efficient access through mechanisms such as data encryption, partition management, and backup redundancy, providing core support for analysis and decision-making and data traceability.

[0031] The data analysis and decision-making module includes a real-time data analysis submodule, an anomaly diagnosis submodule, a control decision generation submodule, and a threshold dynamic optimization submodule. The data analysis and decision-making module performs real-time analysis on the collected environmental data, determines whether the environmental state is normal, and generates control decisions and early warning information for abnormal situations. When the real-time data analysis submodule is working, it compares and analyzes the real-time collected data based on the preset threshold values ​​of chicken farm environmental parameters, calculates the parameter deviation value, and determines whether the environment is within the normal range; at the same time, it uses a trend analysis algorithm to predict the changing trend of environmental parameters and identify potential abnormal risks in advance. When the above real-time data analysis submodule is working, it first retrieves the pre-processed real-time environmental data from the cloud storage module according to the preset cycle, and simultaneously loads the system's preset environmental threshold standards for different breeding stages and historical abnormal data archives. Subsequently, a multi-dimensional analysis engine is activated to accurately compare real-time data with threshold standards, combine trend prediction algorithms to judge the changing trends of environmental parameters, and identify abnormal fluctuation patterns by correlating historical data. If parameters such as temperature or ammonia concentration are detected to exceed the standard or show abnormal trends, an early warning mechanism is immediately triggered. The abnormal causes (such as equipment failure or insufficient ventilation) are located through correlation analysis, and targeted control strategies (such as adjusting ventilation frequency or starting cooling equipment) are automatically generated. If the data is within the normal range, an environmental status assessment report is generated. Finally, the control strategy, early warning information, and assessment report are simultaneously output to the cloud storage and management submodule, which then distributes them to the execution end. At the same time, analysis logs are retained to provide a basis for dynamic threshold optimization and subsequent data traceability, ensuring the timeliness and accuracy of environmental control throughout the process.

[0032] When the anomaly diagnosis submodule is working, it detects abnormal environmental parameters and uses multi-parameter correlation analysis to locate the cause of the anomaly, providing a precise basis for regulation. The aforementioned abnormal diagnosis submodule is responsible for the accurate identification of abnormalities in the chicken house environment, the location of the causes, and the generation of treatment suggestions. The workflow revolves around data access, abnormality detection, root cause analysis, and result output. First, it accesses the environmental parameter data and preliminary abnormality warning information transmitted by the real-time data analysis submodule in real time, and simultaneously retrieves historical environmental data and equipment operation records stored in the cloud as the basis for analysis. Then, a multi-level anomaly detection mechanism is activated. First, real-time parameters are compared with preset thresholds to filter out data that exceeds the standard. Then, a trend analysis algorithm is used to identify hidden problems such as parameter mutations and continuous anomalies, and to eliminate false anomalies such as sensor errors. If an anomaly is confirmed, the anomaly type is matched through correlation analysis (such as excessive temperature and humidity, abnormal gas concentration, etc.). Combined with historical data and chicken house area information, the root cause of the anomaly is located, such as ventilation equipment failure, sensor malfunction, or excessive stocking density. Finally, a standardized anomaly diagnosis report is generated, which clarifies the anomaly level, scope of impact, root cause, and targeted treatment recommendations. This report is simultaneously pushed to the real-time data analysis submodule and the cloud storage and management submodule to support the generation of subsequent control instructions. At the same time, the diagnosis process log is recorded to ensure the traceability and accuracy of anomaly handling.

[0033] The control decision generation submodule automatically generates targeted control strategies based on the anomaly diagnosis results, and supports manual intervention mode, allowing managers to modify and execute control instructions according to the actual situation; The aforementioned control decision generation submodule is responsible for converting abnormal diagnosis results into executable control instructions. The workflow revolves around demand access, scheme matching, instruction generation, and output. First, it receives the diagnosis report pushed by the abnormal diagnosis submodule in real time, clarifies the abnormality type, level, root cause, and scope of impact, and simultaneously retrieves historical control schemes and environmental standard parameters for different breeding stages stored in the cloud as the basis for decision-making. The solution matching engine is then activated to match corresponding control strategies based on the root cause of the anomaly (such as ventilation equipment failure or excessive temperature and humidity). For complex anomalies, the strategy details are optimized and adjusted by combining the environmental trend prediction results from the real-time data analysis submodule to ensure the relevance and feasibility of the solution. Simultaneously, command priorities are set according to the anomaly level, with emergency anomalies (such as excessive ammonia concentration) receiving priority in generating control commands to ensure timely response. The generated control commands include specific execution parameters (such as equipment runtime and adjustment range). After being processed in a standardized format, they are synchronously pushed to the cloud storage and management submodule and the execution terminal. At the same time, the command generation log is recorded, including information such as decision basis and scheme details. The real-time data analysis submodule is linked throughout the process to obtain closed-loop feedback data. If the environmental parameters do not return to normal, the decision scheme is immediately re-optimized to ensure the control effect and support the closed-loop operation of the system.

[0034] When the threshold dynamic optimization submodule is working, it uses machine learning algorithms to dynamically optimize the environmental parameter thresholds at different stages of breeding based on historical environmental data and breeding benefit data, thereby improving breeding benefits.

[0035] When the above threshold dynamic optimization submodule is working, it first periodically retrieves historical environmental data, breeding benefit data (survival rate, egg production rate) and closed-loop feedback control effect data from the cloud storage module, and simultaneously receives the latest environmental parameter trend report transmitted by the real-time data analysis submodule. Subsequently, the correlation between environmental parameters and breeding efficiency at different breeding stages (brooding period and laying period) was analyzed using algorithmic models. The rationality of the current thresholds was evaluated using closed-loop feedback data, identifying problems such as untimely regulation and resource waste caused by thresholds that are too high or too low. For different parameter characteristics, a gradient optimization algorithm was used to adjust the threshold range, ensuring that the optimized thresholds both meet the growth needs of the flock and adapt to fluctuations in the actual breeding environment. After optimization, the new threshold is validated and tested. The control effect during the test period is compared with historical data to confirm the validity of the threshold. Finally, the optimized threshold standard is updated to the cloud storage module and simultaneously pushed to the real-time data analysis submodule and the anomaly diagnosis submodule as the basis for subsequent data comparison and anomaly judgment. At the same time, the threshold optimization log is recorded, including information such as the basis for optimization and the adjustment range, to ensure the traceability of the optimization process and continuously improve the accuracy of system control.

[0036] The execution control and early warning module includes a control execution submodule, a multi-dimensional early warning submodule, and an equipment status monitoring submodule. The execution control and early warning module executes the control instructions generated by the data analysis and decision-making module to accurately control the chicken farm environment; at the same time, it promptly pushes abnormal information to relevant personnel to ensure rapid handling of abnormal situations.

[0037] The control and execution submodule is connected to the ventilation equipment, humidification equipment, cooling equipment, heating equipment and sewage discharge equipment of the chicken farm through relays and frequency converters. After receiving the control and decision instructions, it automatically controls the start-up, shutdown, operating power and running time of the relevant equipment to realize closed-loop control of environmental parameters. When the above-mentioned control execution submodule is working, it first receives standardized control instructions issued by the cloud storage and management submodule, and parses the execution object (ventilation equipment, temperature control equipment, etc.), operation parameters (running time, adjustment range) and priority information in the instructions; Subsequently, the corresponding execution devices are started according to the command priority, and the control actions are executed strictly according to the parsed parameters. At the same time, the device operating status is monitored in real time (such as whether the start-up is successful and whether the operation is stable), and environmental parameters during the execution process are collected as feedback data. If the device malfunctions, the execution is immediately suspended and the fault information is reported to the cloud, awaiting subsequent handling instructions; if the device is operating normally, changes in environmental parameters are continuously tracked. After the control action is completed, the equipment operation records and real-time feedback data are organized, packaged, and uploaded to the cloud storage and management submodule, and simultaneously pushed to the real-time data analysis submodule for effect evaluation. If the feedback data shows that the environmental parameters have not returned to normal, in conjunction with the system's closed-loop mechanism, new optimization control instructions are received and re-executed, ensuring the accuracy and timeliness of the control actions throughout the process and supporting the closed-loop operation of the system.

[0038] When the multi-dimensional early warning submodule is working, it will issue early warning information through local audible and visual alarms, remote message push, and platform pop-up alarm when it detects abnormal environmental parameters or equipment failure. The early warning information includes the type of abnormality, the area of ​​abnormality, the value of abnormal parameters, and suggested handling measures. It supports graded early warning based on the severity of the abnormality, with different levels corresponding to different push frequencies and processing time limits. The aforementioned multi-dimensional early warning submodule first accesses the anomaly diagnosis results from the anomaly diagnosis submodule and the parameter trend data from the real-time data analysis submodule in real time, and simultaneously retrieves the early warning level classification standards and push rules stored in the cloud. Subsequently, the warning level is determined based on the type of anomaly, its scope of impact, and the degree of urgency. For example, excessive ammonia concentration is set as a Level 1 emergency warning, while slight fluctuations in temperature and humidity are set as a Level 3 general warning. Standardized warning information is generated based on the warning level, clearly specifying the abnormal parameters, the area where the anomaly occurred, the risk warning, and the initial response direction, while also linking the corresponding summary of control and regulation decision instructions. The system initiates multi-channel push notifications according to preset rules, simultaneously pushing early warning information to the cloud storage and management submodule and the control execution submodule, while also providing feedback to relevant aquaculture management personnel. After the notification is pushed, the system tracks the status of the early warning handling in real time, receives feedback data from the control execution submodule, and continues to follow up on the early warning if the anomaly is not eliminated; if the anomaly is resolved, the early warning is terminated, and the entire early warning process log is recorded and archived to the cloud to provide support for subsequent early warning optimization and data traceability.

[0039] The equipment status monitoring submodule monitors and controls the operating status of the equipment in real time. When the equipment malfunctions, it automatically issues an equipment malfunction warning and records the malfunction time and malfunction type, which facilitates timely maintenance by management personnel.

[0040] When the above-mentioned equipment status monitoring submodule is working, it first collects the operating data of the equipment associated with the control and execution submodule in real time, including startup status, operating parameters, energy consumption data and fault codes, and synchronously accesses the equipment operation records fed back by the control and execution submodule. Subsequently, a status verification mechanism is initiated, comparing real-time operating data with standard operating parameters of the device stored in the cloud to identify issues such as device start-up / shutdown failures, deviations in operating parameters, and abnormal energy consumption, while eliminating parameter fluctuations caused by normal operation. If a device abnormality is detected, device fault information is immediately generated, specifying the fault type, location, and scope of impact, and is simultaneously pushed to the cloud storage and management submodule and the multi-dimensional early warning submodule. Simultaneously, the system continuously tracks the equipment status, receives fault handling feedback from the control execution submodule, and records the equipment's return to normal status if the fault is resolved; if the fault remains unresolved, it continuously reports and updates the status, records the entire equipment operation log and fault handling process, archives it to the cloud, provides equipment data support for anomaly diagnosis and control decision optimization, and ensures the integrity and stability of the system control link.

[0041] A method for closed-loop control and anomaly early warning of chicken farm environmental data includes the following steps: S1. Multi-dimensional environmental data collection and synchronous transmission enables accurate collection, preprocessing, and multi-channel transmission and backup of core environmental parameters in chicken farms, while simultaneously synchronizing epidemic prevention-related data to provide a complete and reliable data foundation for subsequent analysis. S2. Real-time data analysis and anomaly decision generation: Through data analysis, anomalies are identified and tiered early warning information and targeted control decisions are generated simultaneously, providing accurate basis for environmental control and anomaly handling. S3, Control Execution and Status Closed-Loop Feedback: Executes control commands and provides real-time feedback on the effects, forming a closed-loop control system. At the same time, it records data to support subsequent optimization and ensures a stable and controllable environment.

[0042] S1 consists of two steps: S11. Parameter Acquisition and Preprocessing: Start the environmental data acquisition module, and collect temperature, humidity and ammonia parameters in key areas of the chicken house through the multi-dimensional sensor submodule. The data preprocessing submodule completes noise reduction and standardization, and removes interference data. S12. Data transmission and backup: The pre-processed data is transmitted to the cloud platform via both wireless and wired modes. At the same time, epidemic prevention-related data is synchronized through the network interface of the epidemic prevention center, and the local cache submodule backs up the data to ensure data integrity.

[0043] S2 consists of two steps: S21. Data analysis and anomaly location: The real-time data analysis submodule reads real-time data, compares it with preset thresholds and combines trend analysis to judge the environmental status. If there are anomalies or potential risks, the cause of the anomaly is located through multi-parameter correlation analysis. S22. Early Warning and Decision Generation: Generate graded early warning information based on the level of abnormality, push it to management personnel and the epidemic prevention center, and simultaneously generate targeted control decision instructions, supporting manual intervention and adjustment.

[0044] S3 consists of two steps: S31. Precise Control and Execution: The control and early warning module receives control commands and automatically controls the start-up, shutdown, and operating parameters of ventilation and humidification equipment to achieve precise environmental control. S32. Closed-loop feedback and optimization: During the control process, feedback data is continuously collected to determine whether the parameters have returned to normal. If they have not returned, the strategy is adjusted and re-executed to form a closed loop. The system records data to support dynamic optimization of thresholds and data traceability.

[0045] When the above-mentioned closed-loop control and anomaly early warning method for chicken farm environmental data is in operation, the raw data such as temperature, humidity, gas concentration, and dust in various areas of the chicken house are first collected through the multi-dimensional sensing submodule. After noise reduction, calibration, and standardization are completed by the data preprocessing submodule, the data is uploaded to the cloud by the multi-channel transmission submodule. The local caching submodule ensures that the data is not lost in the event of transmission failure. The cloud storage and management submodule classifies and stores the data, the real-time data analysis submodule compares the real-time data with preset thresholds, and the anomaly diagnosis submodule locates the root cause of the anomaly based on this.

[0046] Subsequently, the regulation decision generation submodule matches the optimal regulation scheme and generates instructions, the threshold dynamic optimization submodule continuously iterates the threshold standard by combining historical data and breeding benefits, the regulation execution submodule receives instructions to drive equipment operation, the equipment status monitoring submodule monitors the equipment operating condition in real time, and the multi-dimensional early warning submodule pushes early warning information according to the abnormality level. At the same time, the system continuously collects environmental data after regulation and feeds it back to the analysis end to form a closed loop, ensuring that the chicken house environment is stable and adapts to the breeding needs.

[0047] The above is the entire working process of the device, and all contents not described in detail in this specification are existing technologies known to those skilled in the art.

[0048] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A closed-loop control and anomaly early warning system for chicken farm environmental data, comprising an environmental data acquisition module, a data transmission and storage module, a data analysis and decision-making module, and an execution control and early warning module, characterized in that: The environmental data acquisition module includes a multi-dimensional sensing submodule, a data preprocessing submodule, and an acquisition timing control submodule. The environmental data acquisition module realizes real-time and comprehensive acquisition of key environmental parameters inside the chicken farm, providing data support for analysis and regulation. The data transmission and storage module includes a multi-channel transmission submodule, a local cache submodule, and a cloud storage and management submodule. The data transmission and storage module enables stable transmission and secure storage of collected data, ensuring data continuity and traceability. The data analysis and decision-making module includes a real-time data analysis submodule, an anomaly diagnosis submodule, a control decision generation submodule, and a threshold dynamic optimization submodule. The data analysis and decision-making module performs real-time analysis on the collected environmental data, determines whether the environmental state is normal, and generates control decisions and early warning information for abnormal situations. The execution control and early warning module includes a control execution submodule, a multi-dimensional early warning submodule, and an equipment status monitoring submodule. The execution control and early warning module executes the control instructions generated by the data analysis and decision-making module to accurately control the chicken farm environment; at the same time, it promptly pushes abnormal information to relevant personnel to ensure rapid handling of abnormal situations.

2. The closed-loop control and anomaly early warning system for chicken farm environmental data according to claim 1, characterized in that: The multi-dimensional sensing submodule is equipped with temperature sensors, humidity sensors, ammonia sensors, carbon dioxide sensors, and dust sensors, covering the chicken house's feeding area, drinking area, roosting area, and sewage discharge area to ensure the comprehensiveness and representativeness of the collected data. The sensors support high-precision acquisition with a temperature error of ≤±0.5℃ and a humidity error of ≤±3%RH. When the data preprocessing submodule is working, it performs noise reduction, filtering, and format standardization on the raw data collected by the sensor, removes abnormal interference data, and converts the data into a unified format that the system can recognize, thereby improving data quality. When the data acquisition timing control submodule is working, it flexibly sets the data acquisition frequency according to the needs of the chicken farm during the brooding, rearing, and laying periods. Under normal conditions, it collects data once every 5 minutes, and under high temperature and high humidity conditions, it collects data once every 1 minute, balancing data real-time performance and system energy consumption.

3. The closed-loop control and anomaly early warning system for chicken farm environmental data according to claim 2, characterized in that: The multi-channel transmission submodule adopts a dual transmission mode of wireless + wired. Sensors inside the chicken house transmit data to the local gateway wirelessly via LoRa and Wi-Fi. The gateway then uploads the data to the cloud platform via Ethernet or 4G / 5G networks. Simultaneously, a network interface for the disease prevention center is added to enable bidirectional data interaction between the cloud platform and the livestock disease prevention center system. This supports real-time synchronization of abnormal chicken farm environmental data, equipment malfunction data, and stocking density data to the disease prevention center, as well as receiving disease prevention warnings and control requirements issued by the center. It also supports breakpoint resume functionality to prevent data loss due to network interruptions.

4. The closed-loop control and anomaly early warning system for chicken farm environmental data according to claim 3, characterized in that: When the local caching submodule is working, a caching unit is deployed on the local gateway. When the cloud network is abnormal, the collected data is automatically cached locally. The cache capacity supports data storage of ≥72 hours. After the network is restored, it is automatically synchronized to the cloud to ensure data continuity. When the cloud storage and management submodule is working, it builds a distributed database based on the cloud server to store the collected real-time data, historical data, equipment operation data and control records; it uses data encryption technology to protect the stored data, and supports data retrieval and export by time, region and parameter type, which facilitates subsequent data analysis and traceability; A separate partition is designated for storing epidemic prevention data to ensure the security and traceability of such data.

5. The closed-loop control and anomaly early warning system for chicken farm environmental data according to claim 4, characterized in that: When the real-time data analysis submodule is working, it compares and analyzes the real-time collected data based on preset chicken farm environmental parameter thresholds, calculates parameter deviation values, and determines whether the environment is within the normal range; at the same time, it uses a trend analysis algorithm to predict the changing trend of environmental parameters and identify potential abnormal risks in advance. When the anomaly diagnosis submodule is working, it detects abnormal environmental parameters and uses multi-parameter correlation analysis to locate the cause of the anomaly, providing a precise basis for regulation. The control decision generation submodule automatically generates targeted control strategies based on the abnormal diagnosis results, and supports manual intervention mode, allowing managers to modify and execute control instructions according to the actual situation; When the threshold dynamic optimization submodule is working, it dynamically optimizes the environmental parameter thresholds at different breeding stages based on historical environmental data and breeding benefit data, thereby improving breeding benefits.

6. The closed-loop control and anomaly early warning system for chicken farm environmental data according to claim 5, characterized in that: The control execution submodule is connected to the ventilation equipment, humidification equipment, cooling equipment, heating equipment and sewage discharge equipment of the chicken farm through relays and frequency converters. After receiving the control decision command, it automatically controls the start-up, shutdown, operating power and running time of the relevant equipment to realize closed-loop control of environmental parameters. When the multi-dimensional early warning submodule is working, it will issue early warning information through local audible and visual alarms, remote message push, and platform pop-up alarms when it detects abnormal environmental parameters or equipment failures. The early warning information includes the type of abnormality, the area of ​​abnormality, the value of abnormal parameters, and suggested handling measures. It supports tiered alerts based on the severity of anomalies, with different levels corresponding to different push frequencies and processing time limits; The equipment status monitoring submodule monitors and controls the operating status of the equipment in real time. When the equipment malfunctions, it automatically issues an equipment malfunction warning and records the malfunction time and malfunction type, which facilitates timely maintenance by management personnel.

7. A method for closed-loop control and anomaly early warning of chicken farm environmental data, applied to the chicken farm environmental data closed-loop control and anomaly early warning system as described in claim 6, characterized in that, Includes the following steps: S1. Multi-dimensional environmental data collection and synchronous transmission enables accurate collection, preprocessing, and multi-channel transmission and backup of core environmental parameters in chicken farms, while simultaneously synchronizing epidemic prevention-related data to provide a complete and reliable data foundation for subsequent analysis. S2. Real-time data analysis and anomaly decision generation: Through data analysis, anomalies are identified and tiered early warning information and targeted control decisions are generated simultaneously, providing accurate basis for environmental control and anomaly handling. S3, Control Execution and Status Closed-Loop Feedback: Executes control commands and provides real-time feedback on the effects, forming a closed-loop control system. At the same time, it records data to support subsequent optimization and ensures a stable and controllable environment.

8. The method for closed-loop control and anomaly early warning of chicken farm environmental data according to claim 7, characterized in that: S1 consists of two steps: S11. Parameter Acquisition and Preprocessing: Start the environmental data acquisition module, and collect temperature, humidity and ammonia parameters in key areas of the chicken house through the multi-dimensional sensor submodule. The data preprocessing submodule completes noise reduction and standardization, and removes interference data. S12. Data transmission and backup: The pre-processed data is transmitted to the cloud platform via both wireless and wired modes. At the same time, epidemic prevention-related data is synchronized through the network interface of the epidemic prevention center, and the local cache submodule backs up the data to ensure data integrity.

9. The method for closed-loop control and anomaly early warning of chicken farm environmental data according to claim 8, characterized in that: S2 consists of two steps: S21. Data analysis and anomaly location: The real-time data analysis submodule reads real-time data, compares it with preset thresholds and combines trend analysis to judge the environmental status. If there are anomalies or potential risks, the cause of the anomaly is located through multi-parameter correlation analysis. S22. Early Warning and Decision Generation: Generate graded early warning information based on the level of abnormality, push it to management personnel and the epidemic prevention center, and simultaneously generate targeted control decision instructions, supporting manual intervention and adjustment.

10. The method for closed-loop control and anomaly early warning of chicken farm environmental data according to claim 9, characterized in that: S3 consists of two steps: S31. Precise Control and Execution: The control and early warning module receives control commands and automatically controls the start-up, shutdown, and operating parameters of ventilation and humidification equipment to achieve precise environmental control. S32. Closed-loop feedback and optimization: During the control process, feedback data is continuously collected to determine whether the parameters have returned to normal. If they have not returned, the strategy is adjusted and re-executed to form a closed loop. The system records data to support dynamic optimization of thresholds and data traceability.

Images