Online monitoring system and method for baby chick feeding

Abstract

The invention relates to the field of baby chick feeding monitoring, in particular to an online monitoring system and method for baby chick feeding. The technical problems are that a baby chick feeding monitoring system in the prior art lacks intelligent decision-making ability based on data analysis, cannot generate a management scheme according to environmental changes and baby chick growth requirements, and lacks ability of dynamic adjustment according to real-time data; according to the technical scheme, the online monitoring system for baby chick feeding comprises a data analysis module, an intelligent decision module and an execution control module; according to the baby chick growth stage, the current environment condition and the analysis result of the intelligent algorithm, the feeding management scheme is intelligently recommended, the corresponding control instruction is generated, feeding management intelligence and automation are achieved, a large amount of data are processed and analyzed through deep learning and an intelligent prediction model, and the feeding management efficiency is improved. The trend and rule of environmental parameter change can be found, a scientific decision basis is provided for feeding management, and the scientificity and effectiveness of feeding management are improved.

Description

Technical Field

[0001] The present invention relates to the field of chicken raising monitoring, and in particular to an online monitoring system and method for chicken raising. Background Art

[0002] The chicken breeding monitoring system is an intelligent system that integrates modern communication technology, computer technology and network technology. It aims to provide accurate and efficient management methods for chicken breeding through real-time monitoring and data analysis. The chicken breeding monitoring system adopts a variety of sensor technologies and can monitor key environmental indicators such as temperature, humidity, carbon dioxide concentration, ammonia concentration, and the growth status of chicks in the chicken house in real time. However, most of the monitoring systems for chicken breeding under the existing technology can only provide real-time monitoring and recording of environmental parameters, but lack intelligent decision-making capabilities based on data analysis, and cannot automatically generate breeding management plans according to environmental changes and chick growth needs. Although some systems can control the equipment in the chicken house, the generation and execution of control instructions often rely on manual judgment or simple preset rules, and lack the ability to dynamically adjust according to real-time data. Summary of the invention

[0003] In order to overcome the problem that most monitoring systems for chicken breeding under existing technologies can only provide real-time monitoring and recording of environmental parameters, but lack intelligent decision-making capabilities based on data analysis, and cannot automatically generate feeding management plans according to environmental changes and chick growth needs. Although some systems can control the equipment in the chicken house, the generation and execution of control instructions often rely on manual judgment or simple preset rules, and lack the ability to dynamically adjust according to real-time data.

[0004] The technical solution of the present invention is: an online monitoring system for chicken breeding, comprising:

[0005] The data acquisition module is used to collect environmental parameters in the chicken house in real time using multiple sets of sensor devices and convert the collected analog signals into digital signals;

[0006] The data analysis module is used to conduct in-depth learning and analysis of the collected data, identify the changing trends and patterns of environmental parameters, and establish a prediction model to predict the future changing trends of the chicken house environment;

[0007] Intelligent decision-making module, which is used to intelligently recommend feeding and management plans based on the growth status of chicks and the analysis results of the data analysis module, and generate corresponding instructions;

[0008] The execution control module is used to receive control instructions and control the start and stop of the corresponding equipment in the chicken house and adjust the operating status of the equipment;

[0009] The monitoring interaction module is used to provide a user operation interface, display real-time video and key environmental parameters in the chicken house, monitor environmental parameters and equipment status in real time, and trigger alarms when abnormalities occur.

[0010] Preferably, the data acquisition module uses multiple groups of sensor devices to collect environmental parameters in the chicken house in real time, and converts the collected analog signals into digital signals. The data analysis module conducts deep learning and analysis on the collected data to identify the changing trends and laws of environmental parameters, and establishes a prediction model to predict future changing trends of the chicken house environment. The intelligent decision-making module intelligently recommends feeding management plans based on the growth status of the chicks and the analysis results of the data analysis module, and generates corresponding instructions. The execution control module receives control instructions and controls the start and stop of the corresponding equipment in the chicken house and adjusts the operating status of the equipment. The monitoring interaction module provides a user operation interface, displays real-time video and key environmental parameters in the chicken house, monitors environmental parameters and equipment status in real time, and triggers alarms in abnormal situations.

[0011] Preferably, the data acquisition module includes a sensor network unit and a data acquisition unit; the sensor network unit includes a temperature and humidity sensor, a harmful gas concentration sensor, a light intensity sensor, etc., which are used to collect environmental parameters in the chicken house in real time; the data acquisition unit is used to convert the analog signals collected by the sensor into digital signals, and perform preliminary processing and filtering to reduce noise and errors.

[0012] Preferably, the data acquisition module comprises the following steps when working:

[0013] S101: Start the data acquisition unit and load necessary configuration parameters, such as sampling frequency and data format;

[0014] S102: Check the connection status with the sensor network to ensure that all sensors are online and can stably transmit data; configure the communication interface between the data acquisition unit and the data processing and analysis module to ensure smooth data transmission;

[0015] S103: Each sensor in the sensor network starts to continuously collect environmental parameters in the chicken house;

[0016] S104: Each sensor collects data regularly according to a set sampling frequency, and converts the collected analog signals into digital signals;

[0017] S105: The sensor sends the converted digital signal to the data acquisition unit via a preset RS485 communication protocol;

[0018] S106: The data acquisition unit receives the data packet from the sensor network and performs a data integrity check to ensure that the data is not lost or damaged;

[0019] S107: Performing preliminary processing on the received data, including data filtering, denoising, etc., to reduce the impact of noise and errors on subsequent analysis;

[0020] S108: Packing the preliminarily processed data according to a specified format and preparing to send it to a data analysis module;

[0021] S109: The data acquisition unit sends the packaged data to the data analysis module through the communication interface;

[0022] S110: Waiting for a reception confirmation message from the data analysis module to ensure that the data has been successfully sent and received; if a confirmation message is received, continuing with the next data collection; if no confirmation message is received, resending or error processing is performed.

[0023] Preferably, the data analysis module includes an intelligent recognition unit, an intelligent prediction unit and a data storage unit; the intelligent recognition unit is used to integrate deep learning and machine learning algorithms, perform deep learning and analysis on the collected data, and identify the trends and patterns of changes in environmental parameters; the intelligent prediction unit is used to establish and maintain a prediction module based on historical data and current environmental data, which is used to predict future changes in the chicken house environment; the data storage unit is used to store original data, processed data, model parameters and historical prediction results.

[0024] Preferably, the data analysis module comprises the following steps when working:

[0025] S201: receiving real-time environmental parameter data collected by the data acquisition module through the sensor network, including temperature and humidity, concentration of harmful gases, light intensity, etc.;

[0026] S202: Use statistical methods and the Isolation Forest algorithm to identify and remove outliers and duplicate values ​​in the data;

[0027] S203: Use the minimum-maximum normalization method to scale the data to between 0 and 1, and convert data of different dimensions and scales to the same order of magnitude;

[0028] S204: storing the preprocessed data in a database;

[0029] S205: Select key features useful for chicken house environment prediction model;

[0030] S206: further process the selected features, calculate statistics such as mean, variance, and rate of change, and perform dimensionality reduction through principal component analysis (PCA) and linear discriminant analysis (LDA);

[0031] S207: Use convolutional neural network (CNN) to directly use the characteristics of time series to perform time series decomposition and seasonal trend decomposition from time series to extract trends, periodicity and other features;

[0032] S208: storing the extracted features in a database;

[0033] S209: Select recurrent neural network (RNN) and its variants such as LSTM, GRU, and autoregressive integrated moving average (ARIMA) according to the characteristics of the data and prediction requirements;

[0034] S210: using the historical data as a training set to train the selected model, and during the training process, adjusting the model parameters through a back propagation algorithm and a gradient descent method to minimize the prediction error;

[0035] S211: Use the validation set to evaluate the trained model to check the prediction accuracy and generalization ability of the model. If the model performance does not meet the requirements, return to step S209 to re-select the model and adjust the training;

[0036] S212: Deploy the trained model into the system to predict the changing trend of the chicken house environment in real time;

[0037] S213: Based on current environmental parameters and historical data, use the trained intelligent prediction model to predict the changing trend of the chicken house environment in the future;

[0038] S214: Output prediction results.

[0039] Preferably, the intelligent decision-making module includes a control strategy library, an intelligent recommendation unit and a control instruction generation unit; the control strategy library is used to store control strategies and threshold settings under different environmental conditions; the intelligent recommendation unit intelligently recommends feeding management plans based on the growth stage of the chicks, environmental conditions and the analysis results of the intelligent algorithm; the control instruction generation unit is used to generate corresponding control instructions based on the intelligent decision results.

[0040] Preferably, the intelligent decision-making module comprises the following steps when working:

[0041] S301: receiving current environmental parameter data, analysis report and prediction results of intelligent algorithms sent from the data analysis module;

[0042] S302: Verify and pre-process the received data to ensure the accuracy and completeness of the data;

[0043] S303: The intelligent recommendation system intelligently recommends the most suitable feeding and management plan for the current conditions according to the growth stage of the chicks, the current environmental conditions and the analysis results of the intelligent algorithm;

[0044] S304: The control strategy library matches the corresponding control strategy according to the received environmental parameter data, prediction results and recommended solutions;

[0045] S305: Prioritize the recommended solutions and matching strategies to ensure that the best solution can be selected when multiple strategies conflict;

[0046] S306: Compare the current environmental parameters with the preset thresholds, and determine whether the environmental parameters in the chicken house need to be adjusted in combination with the prediction results of the intelligent prediction model;

[0047] S307: If the current parameter exceeds or is about to exceed the preset threshold, and the forecast result shows that the environmental parameter will continue to be unfavorable in the future, it is decided to take adjustment measures; if the current parameter is within a reasonable range, and the forecast result shows that the environmental parameter will remain stable or improve in the future, no adjustment measures are taken;

[0048] S308: According to the decision result, the control instruction generation unit is responsible for generating a specific control instruction; the instruction specifies the device to be adjusted and the adjustment method thereof, and the instruction includes the execution time point and priority information;

[0049] S309: Send the generated control instruction to the execution control module and wait for execution feedback.

[0050] Preferably, the execution control module includes a device interface power supply and an execution unit; the device interface unit is used to connect with ventilators, feeders, water dispensers, heating equipment and other equipment; the execution unit is used to receive control instructions and control the start, stop or adjust the operating state of the corresponding equipment; the execution module includes the following steps when working:

[0051] S401: The execution control module receives a control instruction from the intelligent decision module through the internal communication interface;

[0052] S402: Verify the received control instruction to ensure the integrity and correctness of the instruction;

[0053] S403: parsing the verified control instruction to extract key information in the instruction, including the type of device to be controlled, the device number, the control action and the control parameter;

[0054] S404: According to the device type and device number in the control instruction, the execution control module connects to the corresponding device through the device interface unit, checks the device connection status, and ensures that the device is in a controllable state;

[0055] S405: According to the analyzed control action and control parameters, the execution control module sends a control signal to the device to execute the corresponding control action;

[0056] S406: During the execution of the control action, the execution control module continuously monitors the operation status of the device, including whether the device responds to the control signal and whether it operates as expected; if it is found that the device does not respond or operates abnormally, the error information is immediately recorded and an alarm mechanism is triggered;

[0057] S407: Feedback the control result to the intelligent decision-making module in real time;

[0058] S408: Record key information of the control instruction receiving, parsing, executing and feedback process in a log for subsequent query and audit;

[0059] S409: After completing the execution and feedback of the current control instruction, the execution control module enters a waiting state, ready to receive the next round of control instructions.

[0060] Preferably, the monitoring interaction module includes an interactive interface, a monitoring interface and an alarm unit; the interactive interface is used to provide a user operation interface, allowing the user to view real-time data, historical data, prediction results, receive alarm information, etc.; the monitoring interface is used to display real-time video and key environmental parameters in the chicken house, so that users can intuitively understand the breeding environment; the alarm unit is used to monitor environmental parameters and equipment status in real time, and once an abnormal situation is found, an alarm is immediately triggered to notify the user.

[0061] An online monitoring method for chicken breeding comprises the following steps:

[0062] S1: Initialize the monitoring system, load intelligent algorithms, intelligent prediction models, control strategy libraries, and set initial operating parameters and thresholds;

[0063] S2: The sensor network continuously collects environmental parameters in the chicken house, and the data acquisition unit sends the collected data to the data analysis module;

[0064] S3: Use intelligent algorithms to conduct deep learning and analysis on the received data to identify trends and patterns of environmental parameter changes;

[0065] S4: The intelligent prediction model predicts the changing trend of the chicken house environment in the future based on historical data and current environmental parameters;

[0066] S5: storing the processing results and analysis report in the data storage unit;

[0067] S6: Intelligently recommend feeding and management plans based on the growth stage of the chicks, environmental conditions and analysis results of the intelligent algorithm;

[0068] S7: The control strategy library determines whether the equipment operation status needs to be adjusted based on the comparison results of the current environmental parameters and the preset thresholds, as well as the prediction results of the intelligent prediction model;

[0069] S8: The control instruction generation unit generates corresponding control instructions according to the decision result;

[0070] S9: The execution control module receives the control instruction and controls the start, stop or adjusts the operation state of the corresponding device through the device interface unit;

[0071] S10: Real-time feedback of equipment operation status to the central control system;

[0072] S11: Users view real-time data through the human-computer interaction interface. The monitoring screen displays real-time video and key environmental parameters in the chicken house. Once an abnormal situation occurs, the alarm and notification system immediately triggers an alarm and notifies the user;

[0073] S12: The system continuously monitors the chicken house environmental parameters and equipment status, and repeats the above steps as needed.

[0074] Beneficial effects of the present invention:

[0075] 1. Compared with the existing monitoring systems for chicken feeding, most of them can only provide real-time monitoring and recording of environmental parameters, but lack intelligent decision-making capabilities based on data analysis, and cannot automatically generate feeding management plans according to environmental changes and chicken growth needs. Although some systems can control the equipment in the chicken house, the generation and execution of control instructions often rely on manual judgment or simple preset rules, and lack the ability to dynamically adjust according to real-time data. This system intelligently recommends feeding management plans and generates corresponding control instructions based on the growth stage of the chickens, the current environmental conditions and the analysis results of the intelligent algorithm, realizing the intelligence and automation of feeding management. Through deep learning and intelligent prediction models, a large amount of data is processed and analyzed, and the trends and laws of environmental parameter changes can be discovered, providing a scientific decision-making basis for feeding management, and improving the scientificity and effectiveness of feeding management.

[0076] 2. Receive the real-time environmental parameter data collected by the data acquisition module through the sensor network through the data analysis module, use statistical methods and isolation forest algorithm to identify and remove outliers and duplicate values ​​in the data; use the minimum-maximum normalization method to scale the data to between 0 and 1, and convert data of different dimensions and scales to the same order of magnitude; store the preprocessed data in the database; select key features that are useful for the chicken house environment prediction model; further process the selected features, calculate statistics such as mean, variance, and rate of change, and perform dimensionality reduction through principal component analysis PCA and linear discriminant analysis LDA; use convolutional neural network CNN to directly use the characteristics of the time series to perform time series decomposition and seasonal trend decomposition from the time series to extract trends, periodicity and other features; store the extracted features in the database; select recurrent neural network RNN ​​and its Variants such as LSTM, GRU, and autoregressive integrated moving average model ARIMA; use historical data as the training set to train the selected model. During the training process, adjust the model parameters through the back propagation algorithm and gradient descent method to minimize the prediction error; use the validation set to evaluate the trained model to check the prediction accuracy and generalization ability of the model. If the model performance does not meet the requirements, re-select the model and adjust the training; deploy the trained model to the system for real-time prediction of the changing trend of the chicken house environment; use the trained intelligent prediction model to predict the changing trend of the chicken house environment in the future based on the current environmental parameters and historical data; thus, through deep learning and intelligent prediction models, a large amount of data can be processed and analyzed, the trend and law of environmental parameter changes can be discovered, providing a scientific decision-making basis for feeding management, and improving the scientificity and effectiveness of feeding management;

[0077] 3. The intelligent decision-making module receives the current environmental parameter data, analysis report and prediction results of the intelligent algorithm sent by the data analysis module during operation; intelligently recommends the most suitable feeding and management plan for the current conditions according to the growth stage of the chicks, the current environmental conditions and the analysis results of the intelligent algorithm; the control strategy library matches the corresponding control strategy according to the received environmental parameter data, prediction results and recommended plans; prioritizes the recommended plans and matching strategies to ensure that the best plan can be selected when multiple strategies conflict; compares the current environmental parameters with the preset thresholds, and combines the prediction results of the intelligent prediction model to determine whether the environmental parameters in the chicken house need to be adjusted; if the current parameters exceed or are about to exceed the preset thresholds, the control strategy library will automatically adjust the environmental parameters of the chicken house; If the current parameters are within a reasonable range and the forecast results show that the environmental parameters will remain unfavorable for a period of time in the future, adjustment measures will be taken; if the current parameters are within a reasonable range and the forecast results show that the environmental parameters will remain stable or improve for a period of time in the future, no adjustment measures will be taken; according to the decision results, the control instruction generation unit is responsible for generating specific control instructions; the instructions specify the equipment to be adjusted and the adjustment method, and the instructions contain the execution time point and priority information; the generated control instructions are sent to the execution control module, and execution feedback is waited for; thus, according to the growth stage of the chicks, the current environmental conditions and the analysis results of the intelligent algorithm, the feeding management plan is intelligently recommended and the corresponding control instructions are generated, realizing the intelligent and automated feeding management. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 Shown is a schematic diagram of the workflow of the online monitoring system for chicken breeding of the present invention;

[0079] Figure 2 Shown is a schematic diagram of the steps of the online monitoring method for chicken breeding of the present invention. DETAILED DESCRIPTION

[0080] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0081] See also Figure 1-2 The present invention provides an embodiment: an online monitoring system for chicken breeding, comprising:

[0082] The data acquisition module is used to collect environmental parameters in the chicken house in real time using multiple sets of sensor devices and convert the collected analog signals into digital signals;

[0083] The data analysis module is used to conduct in-depth learning and analysis of the collected data, identify the changing trends and patterns of environmental parameters, and establish a prediction model to predict the future changing trends of the chicken house environment;

[0084] Intelligent decision-making module, which is used to intelligently recommend feeding and management plans based on the growth status of chicks and the analysis results of the data analysis module, and generate corresponding instructions;

[0085] The execution control module is used to receive control instructions and control the start and stop of the corresponding equipment in the chicken house and adjust the operating status of the equipment;

[0086] The monitoring interaction module is used to provide a user operation interface, display real-time video and key environmental parameters in the chicken house, monitor environmental parameters and equipment status in real time, and trigger alarms when abnormalities occur.

[0087] Preferably, the data acquisition module uses multiple groups of sensor devices to collect environmental parameters in the chicken house in real time, and converts the collected analog signals into digital signals. The data analysis module conducts deep learning and analysis on the collected data to identify the changing trends and laws of environmental parameters, and establishes a prediction model to predict future changing trends of the chicken house environment. The intelligent decision-making module intelligently recommends feeding management plans based on the growth status of the chicks and the analysis results of the data analysis module, and generates corresponding instructions. The execution control module receives control instructions and controls the start and stop of the corresponding equipment in the chicken house and adjusts the operating status of the equipment. The monitoring interaction module provides a user operation interface, displays real-time video and key environmental parameters in the chicken house, monitors environmental parameters and equipment status in real time, and triggers alarms in abnormal situations.

[0088] Preferably, the data acquisition module includes a sensor network unit and a data acquisition unit; the sensor network unit includes a temperature and humidity sensor, a harmful gas concentration sensor, a light intensity sensor, etc., which are used to collect environmental parameters in the chicken house in real time; the data acquisition unit is used to convert the analog signals collected by the sensor into digital signals, and perform preliminary processing and filtering to reduce noise and errors.

[0089] Preferably, the data acquisition module comprises the following steps when working:

[0090] S101: Start the data acquisition unit and load necessary configuration parameters, such as sampling frequency and data format;

[0091] S102: Check the connection status with the sensor network to ensure that all sensors are online and can stably transmit data; configure the communication interface between the data acquisition unit and the data processing and analysis module to ensure smooth data transmission;

[0092] S103: Each sensor in the sensor network starts to continuously collect environmental parameters in the chicken house;

[0093] S104: Each sensor collects data regularly according to a set sampling frequency, and converts the collected analog signals into digital signals;

[0094] S105: The sensor sends the converted digital signal to the data acquisition unit via a preset RS485 communication protocol;

[0095] S106: The data acquisition unit receives the data packet from the sensor network and performs a data integrity check to ensure that the data is not lost or damaged;

[0096] S107: Performing preliminary processing on the received data, including data filtering, denoising, etc., to reduce the impact of noise and errors on subsequent analysis;

[0097] S108: Packing the preliminarily processed data according to a specified format and preparing to send it to a data analysis module;

[0098] S109: The data acquisition unit sends the packaged data to the data analysis module through the communication interface;

[0099] S110: Waiting for a reception confirmation message from the data analysis module to ensure that the data has been successfully sent and received; if a confirmation message is received, continuing with the next data collection; if no confirmation message is received, resending or error processing is performed.

[0100] Preferably, the data analysis module includes an intelligent recognition unit, an intelligent prediction unit and a data storage unit; the intelligent recognition unit is used to integrate deep learning and machine learning algorithms, perform deep learning and analysis on the collected data, and identify the trends and patterns of changes in environmental parameters; the intelligent prediction unit is used to establish and maintain a prediction module based on historical data and current environmental data, which is used to predict future changes in the chicken house environment; the data storage unit is used to store original data, processed data, model parameters and historical prediction results.

[0101] Preferably, the data analysis module comprises the following steps when working:

[0102] S201: receiving real-time environmental parameter data collected by the data acquisition module through the sensor network, including temperature and humidity, concentration of harmful gases, light intensity, etc.;

[0103] S202: Use statistical methods and the Isolation Forest algorithm to identify and remove outliers and duplicate values ​​in the data;

[0104] S203: Use the minimum-maximum normalization method to scale the data to between 0 and 1, and convert data of different dimensions and scales to the same order of magnitude;

[0105] S204: storing the preprocessed data in a database;

[0106] S205: Select key features useful for chicken house environment prediction model;

[0107] S206: further process the selected features, calculate statistics such as mean, variance, and rate of change, and perform dimensionality reduction through principal component analysis (PCA) and linear discriminant analysis (LDA);

[0108] S207: Use convolutional neural network (CNN) to directly use the characteristics of time series to perform time series decomposition and seasonal trend decomposition from time series to extract trends, periodicity and other features;

[0109] S208: storing the extracted features in a database;

[0110] S209: Select recurrent neural network (RNN) and its variants such as LSTM, GRU, and autoregressive integrated moving average (ARIMA) according to the characteristics of the data and prediction requirements;

[0111] S210: using the historical data as a training set to train the selected model, and during the training process, adjusting the model parameters through a back propagation algorithm and a gradient descent method to minimize the prediction error;

[0112] S211: Use the validation set to evaluate the trained model to check the prediction accuracy and generalization ability of the model. If the model performance does not meet the requirements, return to step S209 to re-select the model and adjust the training;

[0113] S212: Deploy the trained model into the system to predict the changing trend of the chicken house environment in real time;

[0114] S213: Based on current environmental parameters and historical data, use the trained intelligent prediction model to predict the changing trend of the chicken house environment in the future;

[0115] S214: Output prediction results.

[0116] Preferably, the intelligent decision-making module includes a control strategy library, an intelligent recommendation unit and a control instruction generation unit; the control strategy library is used to store control strategies and threshold settings under different environmental conditions; the intelligent recommendation unit intelligently recommends feeding management plans based on the growth stage of the chicks, environmental conditions and the analysis results of the intelligent algorithm; the control instruction generation unit is used to generate corresponding control instructions based on the intelligent decision results.

[0117] Preferably, the intelligent decision-making module comprises the following steps when working:

[0118] S301: receiving current environmental parameter data, analysis report and prediction results of intelligent algorithms sent from the data analysis module;

[0119] S302: Verify and pre-process the received data to ensure the accuracy and completeness of the data;

[0120] S303: The intelligent recommendation system intelligently recommends the most suitable feeding and management plan for the current conditions according to the growth stage of the chicks, the current environmental conditions and the analysis results of the intelligent algorithm;

[0121] S304: The control strategy library matches the corresponding control strategy according to the received environmental parameter data, prediction results and recommended solutions;

[0122] S305: Prioritize the recommended solutions and matching strategies to ensure that the best solution can be selected when multiple strategies conflict;

[0123] S306: Compare the current environmental parameters with the preset thresholds, and determine whether the environmental parameters in the chicken house need to be adjusted in combination with the prediction results of the intelligent prediction model;

[0124] S307: If the current parameter exceeds or is about to exceed the preset threshold, and the forecast result shows that the environmental parameter will continue to be unfavorable in the future, it is decided to take adjustment measures; if the current parameter is within a reasonable range, and the forecast result shows that the environmental parameter will remain stable or improve in the future, no adjustment measures are taken;

[0125] S308: According to the decision result, the control instruction generation unit is responsible for generating a specific control instruction; the instruction specifies the device to be adjusted and the adjustment method thereof, and the instruction includes the execution time point and priority information;

[0126] S309: Send the generated control instruction to the execution control module and wait for execution feedback.

[0127] Preferably, the execution control module includes a device interface power supply and an execution unit; the device interface unit is used to connect with ventilators, feeders, water dispensers, heating equipment and other equipment; the execution unit is used to receive control instructions and control the start, stop or adjust the operating state of the corresponding equipment; the execution module includes the following steps when working:

[0128] S401: The execution control module receives a control instruction from the intelligent decision module through the internal communication interface;

[0129] S402: Verify the received control instruction to ensure the integrity and correctness of the instruction;

[0130] S403: parsing the verified control instruction to extract key information in the instruction, including the type of device to be controlled, the device number, the control action and the control parameter;

[0131] S404: According to the device type and device number in the control instruction, the execution control module connects to the corresponding device through the device interface unit, checks the device connection status, and ensures that the device is in a controllable state;

[0132] S405: According to the analyzed control action and control parameters, the execution control module sends a control signal to the device to execute the corresponding control action;

[0133] S406: During the execution of the control action, the execution control module continuously monitors the operation status of the device, including whether the device responds to the control signal and whether it operates as expected; if it is found that the device does not respond or operates abnormally, the error information is immediately recorded and an alarm mechanism is triggered;

[0134] S407: Feedback the control result to the intelligent decision-making module in real time;

[0135] S408: Record key information of the control instruction receiving, parsing, executing and feedback process in a log for subsequent query and audit;

[0136] S409: After completing the execution and feedback of the current control instruction, the execution control module enters a waiting state, ready to receive the next round of control instructions.

[0137] Preferably, the monitoring interaction module includes an interactive interface, a monitoring interface and an alarm unit; the interactive interface is used to provide a user operation interface, allowing the user to view real-time data, historical data, prediction results, receive alarm information, etc.; the monitoring interface is used to display real-time video and key environmental parameters in the chicken house, so that users can intuitively understand the breeding environment; the alarm unit is used to monitor environmental parameters and equipment status in real time, and once an abnormal situation is found, an alarm is immediately triggered to notify the user.

[0138] An online monitoring method for chicken breeding comprises the following steps:

[0139] S1: Initialize the monitoring system, load intelligent algorithms, intelligent prediction models, control strategy libraries, and set initial operating parameters and thresholds;

[0140] S2: The sensor network continuously collects environmental parameters in the chicken house, and the data acquisition unit sends the collected data to the data analysis module;

[0141] S3: Use intelligent algorithms to conduct deep learning and analysis on the received data to identify trends and patterns of environmental parameter changes;

[0142] S4: The intelligent prediction model predicts the changing trend of the chicken house environment in the future based on historical data and current environmental parameters;

[0143] S5: storing the processing results and analysis report in the data storage unit;

[0144] S6: Intelligently recommend feeding and management plans based on the growth stage of the chicks, environmental conditions and analysis results of the intelligent algorithm;

[0145] S7: The control strategy library determines whether the equipment operation status needs to be adjusted based on the comparison results of the current environmental parameters and the preset thresholds, as well as the prediction results of the intelligent prediction model;

[0146] S8: The control instruction generation unit generates corresponding control instructions according to the decision result;

[0147] S9: The execution control module receives the control instruction and controls the start, stop or adjusts the operation state of the corresponding device through the device interface unit;

[0148] S10: Real-time feedback of equipment operation status to the central control system;

[0149] S11: Users view real-time data through the human-computer interaction interface. The monitoring screen displays real-time video and key environmental parameters in the chicken house. Once an abnormal situation occurs, the alarm and notification system immediately triggers an alarm and notifies the user;

[0150] S12: The system continuously monitors the chicken house environmental parameters and equipment status, and repeats the above steps as needed.

[0151] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. An online monitoring system for chicken breeding, characterized in that: Included are: The data acquisition module is used to collect environmental parameters in the chicken house in real time using multiple sets of sensor devices and convert the collected analog signals into digital signals; The data analysis module is used to conduct in-depth learning and analysis of the collected data, identify the changing trends and laws of environmental parameters, and establish a prediction model to predict the future changing trends of the chicken house environment; Intelligent decision-making module, which is used to intelligently recommend feeding and management plans based on the growth status of chicks and the analysis results of the data analysis module, and generate corresponding instructions; The execution control module is used to receive control instructions and control the start and stop of the corresponding equipment in the chicken house and adjust the operating status of the equipment; The monitoring interaction module is used to provide a user operation interface, display real-time video and key environmental parameters in the chicken house, monitor environmental parameters and equipment status in real time, and trigger alarms when abnormalities occur.

2. The online monitoring system for chicken breeding according to claim 1, characterized in that: The data acquisition module includes a sensor network unit and a data acquisition unit; the sensor network unit includes temperature and humidity sensors, harmful gas concentration sensors, light intensity sensors, etc., which are used to collect environmental parameters in the chicken house in real time; the data acquisition unit is used to convert the analog signals collected by the sensor into digital signals, and perform preliminary processing and filtering to reduce noise and errors.

3. The online monitoring system for chicken breeding according to claim 2, characterized in that: When the data acquisition module is working, it includes the following steps: S101: Start the data acquisition unit and load necessary configuration parameters, such as sampling frequency and data format; S102: Check the connection status with the sensor network to ensure that all sensors are online and can stably transmit data; configure the communication interface between the data acquisition unit and the data processing and analysis module to ensure smooth data transmission; S103: Each sensor in the sensor network starts to continuously collect environmental parameters in the chicken house; S104: Each sensor collects data regularly according to a set sampling frequency, and converts the collected analog signals into digital signals; S105: The sensor sends the converted digital signal to the data acquisition unit through a preset RS485 communication protocol; S106: The data acquisition unit receives the data packet from the sensor network and performs a data integrity check to ensure that the data is not lost or damaged; S107: Performing preliminary processing on the received data, including data filtering, denoising, etc., to reduce the impact of noise and errors on subsequent analysis; S108: Packing the preliminarily processed data according to a specified format and preparing to send it to a data analysis module; S109: The data acquisition unit sends the packaged data to the data analysis module through the communication interface; S110: Waiting for a reception confirmation message from the data analysis module to ensure that the data has been successfully sent and received; if a confirmation message is received, continuing with the next data collection; if no confirmation message is received, resending or error processing is performed.

4. The online monitoring system for chicken breeding according to claim 3, characterized in that: The data analysis module includes an intelligent recognition unit, an intelligent prediction unit and a data storage unit; the intelligent recognition unit is used to integrate deep learning and machine learning algorithms, conduct deep learning and analysis on the collected data, and identify the trends and laws of changes in environmental parameters; the intelligent prediction unit is used to establish and maintain a prediction module based on historical data and current environmental data, which is used to predict future changes in the chicken house environment; the data storage unit is used to store raw data, processed data, model parameters and historical prediction results.

5. The online monitoring system for chicken breeding according to claim 4, characterized in that: When the data analysis module is working, it includes the following steps: S201: receiving real-time environmental parameter data collected by the data acquisition module through the sensor network, including temperature and humidity, concentration of harmful gases, light intensity, etc.; S202: Use statistical methods and the Isolation Forest algorithm to identify and remove outliers and duplicate values ​​in the data; S203: Use the minimum-maximum normalization method to scale the data to between 0 and 1, and convert data of different dimensions and scales to the same order of magnitude; S204: storing the preprocessed data in a database; S205: Select key features useful for chicken house environment prediction model; S206: further process the selected features, calculate statistics such as mean, variance, and rate of change, and perform dimensionality reduction through principal component analysis (PCA) and linear discriminant analysis (LDA); S207: Use convolutional neural network (CNN) to directly use the characteristics of time series to perform time series decomposition and seasonal trend decomposition from time series to extract trends, periodicity and other features; S208: storing the extracted features in a database; S209: Select recurrent neural network (RNN) and its variants such as LSTM, GRU, and autoregressive integrated moving average (ARIMA) according to the characteristics of the data and prediction requirements; S210: using the historical data as a training set to train the selected model, and during the training process, adjusting the model parameters through a back propagation algorithm and a gradient descent method to minimize the prediction error; S211: Use the validation set to evaluate the trained model to check the prediction accuracy and generalization ability of the model. If the model performance does not meet the requirements, return to step S209 to re-select the model and adjust the training; S212: Deploy the trained model into the system to predict the changing trend of the chicken house environment in real time; S213: Based on current environmental parameters and historical data, use the trained intelligent prediction model to predict the changing trend of the chicken house environment in the future; S214: Output prediction results.

6. The online monitoring system for chicken breeding according to claim 5, characterized in that: The intelligent decision-making module includes a control strategy library, an intelligent recommendation unit and a control instruction generation unit; the control strategy library is used to store control strategies and threshold settings under different environmental conditions; the intelligent recommendation unit intelligently recommends feeding management plans based on the growth stage of the chicks, environmental conditions and the analysis results of the intelligent algorithm; the control instruction generation unit is used to generate corresponding control instructions based on the intelligent decision results.

7. The online monitoring system for chicken breeding according to claim 6, characterized in that: When the intelligent decision-making module is working, it includes the following steps: S301: receiving current environmental parameter data, analysis report and prediction results of intelligent algorithms sent from the data analysis module; S302: Verify and pre-process the received data to ensure the accuracy and completeness of the data; S303: The intelligent recommendation system intelligently recommends the most suitable feeding and management plan for the current conditions according to the growth stage of the chicks, the current environmental conditions and the analysis results of the intelligent algorithm; S304: The control strategy library matches the corresponding control strategy according to the received environmental parameter data, prediction results and recommended solutions; S305: Prioritize the recommended solutions and matching strategies to ensure that the best solution can be selected when multiple strategies conflict; S306: Compare the current environmental parameters with the preset thresholds, and determine whether the environmental parameters in the chicken house need to be adjusted in combination with the prediction results of the intelligent prediction model; S307: If the current parameter exceeds or is about to exceed the preset threshold, and the forecast result shows that the environmental parameter will continue to be unfavorable in the future, it is decided to take adjustment measures; if the current parameter is within a reasonable range, and the forecast result shows that the environmental parameter will remain stable or improve in the future, no adjustment measures are taken; S308: According to the decision result, the control instruction generation unit is responsible for generating a specific control instruction; the instruction specifies the device to be adjusted and the adjustment method thereof, and the instruction includes the execution time point and priority information; S309: Send the generated control instruction to the execution control module and wait for execution feedback.

8. The online monitoring system for chicken breeding according to claim 7, characterized in that: The execution control module includes a device interface power supply and an execution unit; the device interface unit is used to connect with ventilators, feeders, water dispensers, heating equipment and other equipment; the execution unit is used to receive control instructions and control the start, stop or adjust the operating status of the corresponding equipment; the execution module includes the following steps when working: S401: The execution control module receives a control instruction from the intelligent decision module through the internal communication interface; S402: Verify the received control instruction to ensure the integrity and correctness of the instruction; S403: parsing the verified control instruction to extract key information in the instruction, including the type of device to be controlled, the device number, the control action and the control parameter; S404: According to the device type and device number in the control instruction, the execution control module connects to the corresponding device through the device interface unit, checks the device connection status, and ensures that the device is in a controllable state; S405: According to the analyzed control action and control parameters, the execution control module sends a control signal to the device to execute the corresponding control action; S406: During the execution of the control action, the execution control module continuously monitors the operation status of the device, including whether the device responds to the control signal and whether it operates as expected; if it is found that the device does not respond or operates abnormally, the error information is immediately recorded and an alarm mechanism is triggered; S407: Feedback the control result to the intelligent decision-making module in real time; S408: Record key information of the control instruction receiving, parsing, executing and feedback process in a log for subsequent query and audit; S409: After completing the execution and feedback of the current control instruction, the execution control module enters a waiting state, ready to receive the next round of control instructions.

9. An online monitoring system for chicken breeding according to claim 8, characterized in that: The monitoring interaction module includes an interactive interface, a monitoring interface and an alarm unit; the interactive interface is used to provide a user operation interface, allowing users to view real-time data, historical data, prediction results, receive alarm information, etc.; the monitoring interface is used to display real-time video and key environmental parameters in the chicken house, so that users can intuitively understand the breeding environment; the alarm unit is used to monitor environmental parameters and equipment status in real time, and immediately trigger an alarm and notify the user once an abnormal situation is found.

10. An online monitoring method for chicken breeding, characterized in that: The following steps are involved: S1: Initialize the monitoring system, load intelligent algorithms, intelligent prediction models, control strategy libraries, and set initial operating parameters and thresholds; S2: The sensor network continuously collects environmental parameters in the chicken house, and the data acquisition unit sends the collected data to the data analysis module; S3: Use intelligent algorithms to conduct deep learning and analysis on the received data to identify trends and patterns of environmental parameter changes; S4: The intelligent prediction model predicts the changing trend of the chicken house environment in the future based on historical data and current environmental parameters; S5: storing the processing results and analysis report in the data storage unit; S6: Intelligently recommend feeding and management plans based on the growth stage of the chicks, environmental conditions and analysis results of the intelligent algorithm; S7: The control strategy library determines whether the equipment operation status needs to be adjusted based on the comparison results of the current environmental parameters and the preset thresholds, as well as the prediction results of the intelligent prediction model; S8: The control instruction generation unit generates corresponding control instructions according to the decision result; S9: The execution control module receives the control instruction and controls the start, stop or adjusts the operation state of the corresponding device through the device interface unit; S10: Real-time feedback of equipment operation status to the central control system; S11: Users view real-time data through the human-computer interaction interface. The monitoring screen displays real-time video and key environmental parameters in the chicken house. Once an abnormal situation occurs, the alarm and notification system immediately triggers an alarm and notifies the user; S12: The system continuously monitors the chicken house environmental parameters and equipment status, and repeats the above steps as needed.

Images