Meat goat shed environment automatic control method and system

Abstract

The invention relates to the technical field of environment automatic control, in particular to a meat goat shed environment automatic control method and system. The method comprises the following steps: acquiring temperature and carbon dioxide / ammonia gas time sequence fluctuation data; extracting temperature and carbon dioxide / ammonia gas fluctuation data, and performing diffusion increment fitting to obtain carbon dioxide / ammonia gas diffusion accumulation data; then, estimating the respiratory stress probability caused by ammonia intake so as to map an ammonia safety content interval, and carrying out ventilation parameter balance processing on diffusion accumulation data so as to carry out oxygen content compensation; and finally, based on the ventilation parameters and the balance data, making a sheep house environment automatic control strategy, and sending the sheep house environment automatic control strategy to the terminal for execution, thereby realizing automatic regulation and control of the meat goat house environment. According to the invention, the automatic environment control technology is optimized, so that the automatic environment control technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic environmental control, and in particular to an automatic environmental control method and system for a meat goat house. Background Art

[0002] In high-altitude areas, due to the thin air, cold climate and low oxygen content, the growth environment and physiological needs of meat goats are very different from those in low-altitude areas. The high-altitude environment has a significant impact on the feeding, reproduction and health of meat goats, especially environmental factors such as temperature, humidity and gas concentration (such as carbon dioxide and ammonia), which directly affect the growth rate, immunity and respiratory health of meat goats. Excessive carbon dioxide and ammonia concentrations, especially ammonia intake, cause respiratory stress in meat goats, affecting their appetite, weight gain and immune function, and even causing diseases. A traditional method for automatic control of the environment of meat goat sheds has the problem of inaccurate analysis of the probability of ammonia intake stress in meat goats, resulting in large errors in the control of the environment of meat goat sheds. Summary of the invention

[0003] Based on this, it is necessary to provide a method and system for automatic control of the environment of a meat goat house to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for automatically controlling the environment of a meat goat house is provided, the method comprising the following steps: Step S1: collecting all-weather data in the high-altitude environment of the goats through sensors to obtain all-weather environmental data in the high-altitude goat house; extracting the all-weather time series fluctuations of temperature and carbon dioxide / ammonia in the high-altitude goat house to obtain the time series fluctuation data of temperature in the goat house and the time series fluctuation data of carbon dioxide / ammonia in the goat house; Step S2: performing carbon dioxide / ammonia diffusion increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; estimating the probability of ammonia ingestion respiratory stress on the carbon dioxide / ammonia diffusion accumulation data to obtain the probability of ammonia ingestion respiratory stress; Step S3: mapping the ammonia safety content interval according to the probability of respiratory stress caused by ammonia intake to obtain the ammonia safety content interval; performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data based on the ammonia safety content interval to obtain ventilation parameter balance design data; performing oxygen content compensation processing in the sheep house based on the ventilation parameter balance design data to obtain oxygen content compensation data; Step S4: Formulate an automatic control strategy for the sheep house environment based on the ventilation parameter balance design data and the oxygen content compensation data, obtain the automatic control strategy for the sheep house environment, and send the automatic control strategy for the sheep house environment to the terminal to execute the automatic control method for the meat goat house environment.

[0005] Preferably, step S1 comprises the following steps: Step S11: collecting all-weather data of the high-altitude environment of the goats in the goat shed through sensors to obtain all-weather environmental data of the high-altitude goat shed; Step S12: Filling missing values ​​in the all-weather environmental data of the high-altitude sheep house to obtain environmental filling data of the high-altitude sheep house; Step S13: extract the temperature, humidity and carbon dioxide / ammonia all-weather time series fluctuations of the high-altitude sheep house environment filling data, and obtain the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data in the sheep house respectively.

[0006] Preferably, step S2 comprises the following steps: Step S21: performing a low oxygen environment concentration fluctuation analysis on the all-weather environmental data in the high-altitude sheep house to obtain low oxygen environment concentration fluctuation data; Step S22: evaluating the respiratory rate demand acceleration of meat goats based on the hypoxic environment concentration fluctuation data to obtain respiratory rate demand acceleration data; Step S23: performing carbon dioxide / ammonia diffusion accumulation increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; Step S24: Estimating the probability of respiratory stress caused by ammonia intake based on the carbon dioxide / ammonia diffusion accumulation data according to the respiratory rate demand acceleration data to obtain the probability of respiratory stress caused by ammonia intake.

[0007] Preferably, step S23 includes the following steps: Step S231: analyzing the carbon dioxide content rising period on the carbon dioxide / ammonia time series fluctuation data, and then analyzing the greenhouse effect enhancement period based on the temperature time series fluctuation data to obtain the greenhouse effect enhancement period; Step S232: identifying the thermal pressure enhancement gradient during the greenhouse effect enhancement period to obtain thermal pressure enhancement gradient data; Step S233: performing thermal convection accumulation vertical azimuth analysis on the carbon dioxide / ammonia time series fluctuation data based on the thermal pressure enhancement gradient data to obtain carbon dioxide / ammonia accumulation vertical azimuth data; Step S234: Perform carbon dioxide / ammonia diffusion accumulation increment fitting based on the heat pressure enhancement gradient data and the carbon dioxide / ammonia accumulation vertical orientation data to obtain carbon dioxide / ammonia diffusion accumulation data.

[0008] Preferably, step S24 comprises the following steps: Step S241: numerically integrating the ammonia accumulation pressure of the carbon dioxide / ammonia diffusion accumulation data to obtain ammonia accumulation pressure data; Step S242: performing agglomeration distribution robust regression analysis on the carbon dioxide / ammonia diffusion accumulation data according to the ammonia accumulation pressure data to obtain ammonia accumulation distribution pressure regression data; Step S243: performing a pressure logarithmic transformation on the ammonia gas accumulation distribution pressure regression data to obtain ammonia gas accumulation pressure logarithmic transformation data; Step S244: obtaining the body characteristic data of the goats; performing the logarithmic conversion data of the ammonia accumulation pressure on the gas inhalation amount of the goats with different body characteristics per unit time according to the respiratory rate demand acceleration data and the body characteristic data of the goats, and obtaining the gas inhalation amount calculation data per unit time; Step S245: performing ammonia respiratory dissolution rate simulation estimation on the gas inhalation amount calculation data based on the body characteristic data of the goat to generate ammonia respiratory dissolution rate estimation data; Step S246: Estimating the probability of respiratory stress caused by ammonia ingestion based on the ammonia respiratory dissolution rate estimation data to obtain the probability of respiratory stress caused by ammonia ingestion.

[0009] Preferably, step S245 includes the following steps: According to the physical characteristics of meat goats, the gas inhalation calculation data were used to evaluate the cumulative exposure of ammonia breathing between different physical characteristics, and the cumulative exposure data of ammonia were obtained; The ammonia absorption rate is calculated based on the ammonia cumulative exposure data and the respiratory rate demand acceleration data to obtain the ammonia absorption rate; Ammonia solubility parameter correction calculation is performed based on ammonia cumulative exposure data and ammonia absorption rate to obtain ammonia respiratory solubility correction data; The ammonia respiratory dissolution rate is simulated and estimated based on the ammonia respiratory dissolution correction data to generate the ammonia respiratory dissolution rate estimation data.

[0010] Preferably, step S3 comprises the following steps: Step S31: normalizing the probability of respiratory stress caused by ammonia ingestion to obtain normalized data of the probability of respiratory stress; Step S32: mapping the respiratory rate demand acceleration data to the ammonia safety content intervals between different respiratory frequencies according to the respiratory stress probability normalization data, to obtain the ammonia safety content interval; Step S33: matching the humidity content in the sheep house based on the safe content range of ammonia to obtain humidity content matching data; Step S34: performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data according to the humidity content matching data to obtain ventilation parameter balance design data; Step S35: Based on the humidity content matching data and the ventilation parameter balance design data, oxygen content compensation processing is performed in the sheep house to obtain oxygen content compensation data.

[0011] Preferably, step S34 includes the following steps: Step S341: performing ventilation humidity loss compensation matching according to the humidity content matching data to obtain ventilation humidity loss compensation data; Step S342: performing accumulation density difference analysis on the carbon dioxide / ammonia diffusion accumulation data to obtain carbon dioxide / ammonia accumulation density difference data; Step S343: performing ventilation wind pressure matching of the sheep house based on the carbon dioxide / ammonia accumulation density difference data to obtain ventilation wind pressure matching data of the sheep house; Step S344: Design ventilation structure parameters based on the carbon dioxide / ammonia accumulation density difference data and the sheep house ventilation wind pressure matching data to obtain ventilation structure parameters; Step S345: Perform ventilation parameter balance processing according to the ventilation humidity loss compensation data and the ventilation structure parameters to obtain ventilation parameter balance design data.

[0012] Preferably, step S344 includes the following steps: Acquire sheep house structural design data; extract ventilation paths from the sheep house structural design data to obtain sheep house ventilation path data; Based on the carbon dioxide / ammonia accumulation density difference data, the carbon dioxide / ammonia accumulation pressure difference on the sheep house ventilation path data is analyzed to obtain the carbon dioxide / ammonia accumulation pressure difference between ventilation paths; According to the sheep house ventilation wind pressure matching data, the wind speed and flow rate are matched with the carbon dioxide / ammonia accumulation pressure difference to obtain the wind speed and flow rate matching data; Performing repeated behavior learning on the accumulated pressure difference of carbon dioxide / ammonia to obtain accumulated pressure behavior learning data; Based on the sheep house ventilation wind pressure matching data and wind speed flow matching data, the accumulated pressure behavior learning data is intelligently matched with the ventilation rate to obtain the ventilation rate intelligent matching data; The ventilation structure parameters are designed according to the wind speed and flow matching data, the sheep house ventilation pressure matching data and the air change rate intelligent matching data to obtain the ventilation structure parameters.

[0013] Preferably, the present invention also provides an automatic control system for the environment of a meat goat house, which is used to execute the automatic control method for the environment of a meat goat house as described above, and the automatic control system for the environment of a meat goat house comprises: The environmental data acquisition module is used to collect all-weather data in the high-altitude environment of the meat goats through sensors to obtain all-weather environmental data in the high-altitude goat house; extract the temperature, humidity and carbon dioxide / ammonia all-weather time series fluctuations of the all-weather environmental data in the high-altitude goat house, and obtain the temperature time series fluctuation data and carbon dioxide / ammonia time series fluctuation data in the goat house respectively; A stress probability estimation module is used to perform carbon dioxide / ammonia diffusion increment fitting based on the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; perform ammonia intake respiratory stress probability estimation on the carbon dioxide / ammonia diffusion accumulation data to obtain the ammonia intake respiratory stress probability; The safety content interval mapping module is used to map the ammonia safety content interval according to the probability of respiratory stress caused by ammonia intake to obtain the ammonia safety content interval; based on the ammonia safety content interval, the ventilation parameter balance processing is performed on the carbon dioxide / ammonia diffusion accumulation data to obtain the ventilation parameter balance design data; based on the ventilation parameter balance design data, the oxygen content compensation processing is performed in the sheep house to obtain the oxygen content compensation data; The automatic control strategy formulation module is used to formulate an automatic control strategy for the sheep house environment based on ventilation parameter balance design data and oxygen content compensation data, obtain the automatic control strategy for the sheep house environment, and send the automatic control strategy for the sheep house environment to the terminal to execute the automatic control method for the meat goat house environment.

[0014] The beneficial effect of the present invention is that the environmental data (such as temperature and carbon dioxide / ammonia concentration) in the high-altitude sheep house can be monitored by sensors around the clock, and the real-time environmental fluctuation information inside the sheep house can be fully obtained. These data provide a basis for subsequent analysis and control. The extraction of temperature time series fluctuations and carbon dioxide / ammonia time series fluctuations helps to reveal the changing trend of the sheep house environment, and provides a scientific basis for accurately regulating environmental parameters, thereby avoiding adverse effects caused by environmental fluctuations and ensuring the health of the sheep. Through the fitting analysis of carbon dioxide / ammonia diffusion increments, the accumulation of gases in the sheep house can be effectively predicted, and the potential accumulation trend of harmful gases can be identified. Estimating the probability of respiratory stress of meat goats due to ammonia intake based on these data helps to evaluate the safety of the current sheep house environment. Timely identification of changes in ammonia concentration and evaluation of its threat to the health of the sheep flock can take intervention measures in advance to avoid health risks caused by excessive accumulation of ammonia and improve the growth efficiency and survival rate of the sheep flock. By mapping the probability of respiratory stress due to ammonia intake to the safe content range of ammonia, the ammonia concentration in the sheep house can be accurately controlled to ensure that it is within a safe range that is harmless to the health of meat goats. In addition, ventilation parameter balance design based on carbon dioxide / ammonia diffusion accumulation data is helpful to optimize the ventilation system and improve air circulation efficiency. By optimizing the ventilation design, the concentration of harmful gases can be reduced and the oxygen content can be increased, providing a more suitable growth environment for meat goats, thereby promoting their healthy development. Based on the ventilation parameter balance design data and oxygen content compensation data, an efficient automatic control strategy can be formulated to adjust the environmental parameters such as temperature, humidity, and gas concentration in the sheep house in real time. This automatic control strategy can be automatically adjusted according to the changes in the sheep house environment, reduce the need for manual intervention, and improve the intelligent level of sheep house management. By sending these strategies to the terminal for execution, real-time control and optimization of the sheep house environment can be achieved. Therefore, the present invention is an optimization process made to a traditional automatic control method for the environment of a meat goat house, which solves the problem that a traditional automatic control method for the environment of a meat goat house has an inaccurate analysis of the probability of ammonia intake stress of meat goats, thereby causing a large error in the control of the environment of the meat goat house, improves the accuracy of the analysis of the probability of ammonia intake stress of meat goats, and reduces the error of the control of the environment of the meat goat house. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the steps of an automatic control method for a meat goat house environment; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. DETAILED DESCRIPTION

[0016] See also Figures 1 to 3 , a method for automatically controlling the environment of a meat goat house, the method comprising the following steps: Step S1: collecting all-weather data in the high-altitude environment of the goats through sensors to obtain all-weather environmental data in the high-altitude goat house; extracting the all-weather time series fluctuations of temperature and carbon dioxide / ammonia in the high-altitude goat house to obtain the time series fluctuation data of temperature in the goat house and the time series fluctuation data of carbon dioxide / ammonia in the goat house; Step S2: performing carbon dioxide / ammonia diffusion increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; estimating the probability of ammonia ingestion respiratory stress on the carbon dioxide / ammonia diffusion accumulation data to obtain the probability of ammonia ingestion respiratory stress; Step S3: mapping the ammonia safety content interval according to the probability of respiratory stress caused by ammonia intake to obtain the ammonia safety content interval; performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data based on the ammonia safety content interval to obtain ventilation parameter balance design data; performing oxygen content compensation processing in the sheep house based on the ventilation parameter balance design data to obtain oxygen content compensation data; Step S4: Formulate an automatic control strategy for the sheep house environment based on the ventilation parameter balance design data and the oxygen content compensation data, obtain the automatic control strategy for the sheep house environment, and send the automatic control strategy for the sheep house environment to the terminal to execute the automatic control method for the meat goat house environment.

[0017] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of an automatic control method for a meat goat house environment of the present invention. In this example, the automatic control method for a meat goat house environment comprises the following steps: Step S1: collecting all-weather data in the high-altitude environment of the goats through sensors to obtain all-weather environmental data in the high-altitude goat house; extracting the all-weather time series fluctuations of temperature and carbon dioxide / ammonia in the high-altitude goat house to obtain the time series fluctuation data of temperature in the goat house and the time series fluctuation data of carbon dioxide / ammonia in the goat house; In an embodiment of the present invention, all-weather environmental information is collected by a data acquisition system deployed in a goat house in a high-altitude area. The system consists of an integrated temperature and humidity sensor, an infrared carbon dioxide sensor, an electrochemical ammonia sensor, an air pressure sensor, and a wind speed and direction sensor. The data acquisition frequency is set to collect once every 30 seconds, and the collection period is not less than 30 consecutive days to ensure the continuity and periodicity of the data. The deployed temperature and humidity sensors have a measurement accuracy of ±0.1°C and ±1.5%RH; the carbon dioxide sensor has a measurement range of 400ppm to 5000ppm and an accuracy of ±(50ppm + 3%); the ammonia sensor has a measurement range of 0~1000ppm and an accuracy of ±5ppm. During the collection process, the sensors are arranged at different spatial levels of the goat house, including 0.5 meters above the ground, 1.2 meters above the sheep body, and 2 meters at the top, and 4 groups of sensor nodes are arranged respectively to obtain the distribution data of environmental parameters in the vertical space. The collected raw data is transmitted to the central controller via the RS485 bus and stored in the local database. The original data was then preprocessed, including timestamp correction, outlier removal, and missing value interpolation. The interpolation method used linear interpolation to fill in the missing data in a short period of time (less than 5 minutes). After the preprocessing was completed, the temperature data and carbon dioxide and ammonia concentration data were extracted according to the time series order. Fluctuation extraction was performed using a sliding window method with a window width of 30 minutes and a sliding step of 5 minutes. The extracted indicators included maximum, minimum, mean, standard deviation, and change rate to form temperature time series fluctuation data and carbon dioxide / ammonia time series fluctuation data.

[0018] Step S2: performing carbon dioxide / ammonia diffusion increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; estimating the probability of ammonia ingestion respiratory stress on the carbon dioxide / ammonia diffusion accumulation data to obtain the probability of ammonia ingestion respiratory stress; In an embodiment of the present invention, in step S2, based on the extracted temperature time series fluctuation data and carbon dioxide / ammonia time series fluctuation data, a joint diffusion accumulation analysis is first performed on the concentration changes of carbon dioxide and ammonia. This process uses a time series difference analysis method to calculate the change in gas concentration in each sliding window, and performs an incremental fitting operation in combination with the temperature change rate of the corresponding time period. The fitting process does not use a regression model, but rather performs numerical interpolation by constructing a three-dimensional data table (time window, temperature change rate, gas concentration difference), and uses a bilinear interpolation method to achieve diffusion increment completion between data to obtain the gas diffusion accumulation value in each time window. After obtaining the carbon dioxide / ammonia diffusion accumulation data, an ammonia inhalation risk assessment mechanism is introduced. This mechanism estimates the probability of stress based on the relationship between the ammonia concentration in the sheep house and the standard respiratory rate of meat goats. The specific method is to establish an ammonia concentration classification threshold (such as: <10ppm is low risk, 10-25ppm is medium risk, >25ppm is high risk), combined with the respiratory rate of meat goats under high altitude conditions (based on field measurements, an average of 34 times per minute), and use a piecewise linear mapping method to quantify the inhaled amount corresponding to the ammonia concentration and the respiratory rate. Finally, the probability of respiratory stress due to ammonia intake in each time period is calculated, and the output is a continuous value between 0 and 1.

[0019] Step S3: mapping the ammonia safety content interval according to the probability of respiratory stress caused by ammonia intake to obtain the ammonia safety content interval; performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data based on the ammonia safety content interval to obtain ventilation parameter balance design data; performing oxygen content compensation processing in the sheep house based on the ventilation parameter balance design data to obtain oxygen content compensation data; In an embodiment of the present invention, in step S3, a mapping operation of the ammonia safety content interval is performed based on the probability of respiratory stress caused by ammonia intake estimated in the previous step. This operation is based on the established correspondence table between the ammonia concentration threshold and the stress probability for classification mapping, and a suitable safety concentration interval is divided, specifically: stress probability <0.2 corresponds to ammonia concentration <10ppm, 0.20.5 corresponds to 1020ppm, >0.5 corresponds to >20ppm. After the mapping is completed, the ventilation system of the sheep house is subjected to parameter balancing processing in combination with the carbon dioxide / ammonia diffusion accumulation data. The ventilation parameter balancing processing includes three contents: wind pressure regulation, optimization of the opening angle of the air inlet and outlet, and wind speed control. The wind pressure regulation is reverse calculated based on the measured wind speed data, with the goal of increasing the wind speed in the high-concentration accumulation area to above 0.3m / s; the inlet and outlet angles are adjusted in real time according to the layout of the sheep house structure, with a control range of 15° to 45° to ensure that the convection path is connected; the wind speed control uses a PWM speed controller to achieve fine adjustment of the centrifugal fan speed, with a wind speed setting range of 0.20.8m / s. After completing the ventilation parameter balance design, the oxygen content is further compensated. The oxygen content compensation process is adjusted based on the difference between the ventilation volume and the external air pressure. A high-precision oxygen sensor (such as Maxtec MaxO2+A) is used to monitor the oxygen concentration in the house in real time. When the oxygen concentration in the house is lower than 19.5%, the oxygen supplement device is started and the ventilation frequency is increased to ensure that the oxygen concentration is maintained within a safe range of 20.5%±0.5%.

[0020] Step S4: Formulate an automatic control strategy for the sheep house environment based on the ventilation parameter balance design data and the oxygen content compensation data, obtain the automatic control strategy for the sheep house environment, and send the automatic control strategy for the sheep house environment to the terminal to execute the automatic control method for the meat goat house environment.

[0021] In an embodiment of the present invention, in step S4, the ventilation parameter balance design data and oxygen content compensation data obtained in step S3 are integrated to formulate an automatic control strategy for the sheep house environment. The control strategy formulation includes ventilation strategy, exhaust frequency strategy, humidity control strategy and gas concentration early warning linkage strategy. The ventilation strategy is based on the wind pressure-concentration distribution diagram to determine the start and stop time points of the fan and the wind speed setting value; the exhaust frequency strategy automatically increases the exhaust frequency based on the peak time period of the 24-hour fluctuation curve of carbon dioxide, and the interval is set to exhaust once every 30 minutes from 10 am to 4 pm, and each time lasts for 5 minutes; the humidity control strategy sets the upper and lower limits according to the temperature and humidity coupling relationship to keep the relative humidity in the house between 55% and 65%; the gas concentration early warning linkage strategy sets the ammonia concentration to automatically start forced exhaust when it exceeds 25ppm, and emits an audible and visual alarm. All control strategies are sent to the PLC control terminal via the RS485 data bus to realize real-time linkage control of various actuators (fans, exhaust devices, oxygen supplementation systems, alarms). The control process performs closed-loop feedback in units of control cycles, refreshing environmental data and control instructions every 5 minutes to ensure timely system response, precise control, and a stable environment.

[0022] Step S1 includes the following steps: Step S11: collecting all-weather data of the high-altitude environment of the goats in the goat shed through sensors to obtain all-weather environmental data of the high-altitude goat shed; Step S12: Filling missing values ​​in the all-weather environmental data of the high-altitude sheep house to obtain environmental filling data of the high-altitude sheep house; Step S13: extract the temperature, humidity and carbon dioxide / ammonia all-weather time series fluctuations of the high-altitude sheep house environment filling data, and obtain the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data in the sheep house respectively.

[0023] In an embodiment of the present invention, a variety of sensors are used to collect data about the environment in a goat house around the clock. First, a temperature sensor, a humidity sensor, a carbon dioxide sensor, and an ammonia sensor are installed inside the goat house. These sensors are connected to a data acquisition module via an I2C or SPI interface. The data acquisition module is a Raspberry Pi 4, which has multi-channel data acquisition capabilities and powerful processing capabilities. The sampling frequency of the sensor is set to once per minute to ensure the continuity and accuracy of the data. The data acquisition module transmits the data to a cloud server in real time via a wireless network and stores it in a database. The database uses MySQL to facilitate subsequent data storage and query. During the data acquisition process, the accuracy of the data is ensured by calibrating the sensor. For example, the temperature sensor needs to be calibrated before installation to ensure the accuracy of its readings. The humidity sensor needs to be calibrated before installation to ensure the accuracy of its readings. The carbon dioxide sensor needs to be zero-calibrated before installation to ensure the accuracy of its readings. The ammonia sensor needs to be calibrated for ammonia concentration before installation to ensure the accuracy of its readings. Through the above steps, the collection of all-weather environmental data in a high-altitude goat house is realized. During the data acquisition process, data loss may occur due to network interruption or sensor failure. In order to ensure the integrity of the data, missing values ​​need to be filled. First, the missing values ​​are filled using linear interpolation. For temperature and humidity data, linear interpolation is performed using the average of the two data points before and after. For carbon dioxide and ammonia data, linear interpolation is performed using the average of the two data points before and after. If the missing value exceeds a certain period of time, the mean filling method is used. For example, if the temperature data is missing for more than 10 minutes in a row, the mean temperature in this period is used for filling. After filling the data, the filled data is stored back in the database through a database query statement. In the process of filling the data, Python programming language is used to process the data using the Pandas library. The Pandas library provides a wealth of data processing functions that can be used to easily operate the data. Through the above steps, the missing value filling of the environmental data in the high-altitude sheep house is realized. After filling the data, the all-weather time series fluctuation extraction of the environmental data in the high-altitude sheep house is performed. First, the time series fluctuation extraction of the temperature and humidity data is performed. The temperature and humidity data are smoothed using the moving average method to remove the noise in the data. Then, the fluctuation amplitude of the temperature and humidity data is calculated. For example, for temperature data, the temperature difference between two adjacent data points is calculated to obtain temperature fluctuation data. For humidity data, the humidity difference between two adjacent data points is calculated to obtain humidity fluctuation data. For carbon dioxide and ammonia data, the same method is used for processing. The carbon dioxide and ammonia data are smoothed using the moving average method, and then the fluctuation amplitude of the carbon dioxide and ammonia data is calculated.For example, for carbon dioxide data, the carbon dioxide difference between two adjacent data points is calculated to obtain carbon dioxide fluctuation data. For ammonia data, the ammonia difference between two adjacent data points is calculated to obtain ammonia fluctuation data. Through the above steps, the temperature and humidity of the environmental data in the high-altitude sheep house and the extraction of all-weather time series fluctuations of carbon dioxide / ammonia are realized.

[0024] Step S2 includes the following steps: Step S21: performing a low oxygen environment concentration fluctuation analysis on the all-weather environmental data in the high-altitude sheep house to obtain low oxygen environment concentration fluctuation data; Step S22: evaluating the respiratory rate demand acceleration of meat goats based on the hypoxic environment concentration fluctuation data to obtain respiratory rate demand acceleration data; Step S23: performing carbon dioxide / ammonia diffusion accumulation increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; Step S24: Estimating the probability of respiratory stress caused by ammonia intake based on the carbon dioxide / ammonia diffusion accumulation data according to the respiratory rate demand acceleration data to obtain the probability of respiratory stress caused by ammonia intake.

[0025] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing a low oxygen environment concentration fluctuation analysis on the all-weather environmental data in the high-altitude sheep house to obtain low oxygen environment concentration fluctuation data; In an embodiment of the present invention, first, an oxygen sensor (such as MX-ZRO2) is used to monitor the oxygen concentration in the sheep house around the clock. The oxygen sensor measures the oxygen concentration through an electrode reaction, and its output signal is a voltage signal. The data acquisition module is a Raspberry Pi 4, which has multi-channel data acquisition capabilities and powerful processing capabilities. The output signal of the oxygen sensor is converted into a digital signal through an analog-to-digital converter (ADC) and connected to the data acquisition module through an I2C interface. The data acquisition module transmits the data to the cloud server in real time and stores it in a database. The database uses MySQL to facilitate subsequent data storage and query. During the data collection process, the accuracy of the data is ensured by calibrating the sensor. For example, the oxygen sensor needs to be calibrated before installation to ensure the accuracy of its readings. Through the above steps, the collection of all-weather environmental data in the high-altitude sheep house is realized. For the collected oxygen concentration data, the moving average method is used to smooth the data to remove noise in the data. Then, the oxygen concentration difference between two adjacent data points is calculated to obtain the low oxygen environment concentration fluctuation data. For example, if the oxygen concentration drops at a certain moment, the difference between the oxygen concentration at that moment and the previous moment is calculated to obtain the low oxygen environment concentration fluctuation data. Through the above steps, the low oxygen environment concentration fluctuation analysis of the environmental data in the high-altitude sheep house is realized.

[0026] Step S22: evaluating the respiratory rate demand acceleration of meat goats based on the hypoxic environment concentration fluctuation data to obtain respiratory rate demand acceleration data; In the embodiment of the present invention, in the data processing stage, a normal respiratory frequency benchmark database of meat goats is first established, and the respiratory frequency data of meat goats in areas below 500 meters above sea level are collected. The respiratory frequency distribution is obtained through long-term monitoring, and the sampling period is set to 10 seconds. The data is stored in a time series format, and data cleaning is performed to remove outliers. Basic statistical characteristics are calculated, including mean, median, standard deviation and distribution density function. The analysis results show that under a standard environment with an oxygen concentration of 20.9%, the normal respiratory frequency range of meat goats is 20-30 times per minute, the respiratory frequency is normally distributed, and the coefficient of variation is small. Based on the normal respiratory frequency data, the high altitude hypoxic environment simulation algorithm is used to calculate the high altitude hypoxic environment. The influence of environment on the respiratory rate of meat goats was studied. Oxygen partial pressure was selected as the main variable, and a regression model was established based on the functional relationship between oxygen partial pressure and respiratory rate. The Bayesian inference method was used to estimate the changes in respiratory rate under high altitude environment. The oxygen partial pressure was set to drop to three gradients of 80%, 70%, and 60% for simulation calculation. The results showed that when the oxygen partial pressure dropped to 80%, the average respiratory rate of meat goats increased to 32 times per minute. When the oxygen partial pressure further dropped to 70%, the respiratory rate increased to 38 times per minute. When the oxygen partial pressure dropped below 60%, the respiratory rate rose rapidly to more than 45 times per minute. The calculation results were stored in the database and used as the basic parameters for subsequent ventilation control and oxygen content compensation.

[0027] Step S23: performing carbon dioxide / ammonia diffusion accumulation increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; In an embodiment of the present invention, the diffusion accumulation increment of carbon dioxide / ammonia is fitted according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data. First, a time series data set is constructed to record the temperature, carbon dioxide concentration and ammonia concentration at different time points in the high-altitude sheep house. The data sampling interval is set to 10 seconds. The time series data is segmented by a sliding window method, and each window contains at least 600 data points to ensure the stability of the data and the accuracy of the trend analysis. Then, the autoregressive integrated moving average (ARIMA, autoregressive moving average model) is used to fit the change trend of carbon dioxide and ammonia concentrations, and their growth rates are calculated respectively. The reference temperature range is set and the diffusion rates of carbon dioxide and ammonia under different temperature conditions are calculated. The Kruskal-Wallis test is used to perform a significance analysis on the diffusion rate data under different temperature conditions to determine the degree of influence of temperature on the diffusion trend. Subsequently, a multivariate regression model is established, with the temperature fluctuation data as the independent variable and the concentration changes of carbon dioxide and ammonia as the dependent variable, to calculate the diffusion accumulation increments of carbon dioxide and ammonia. After the model fitting is completed, the Monte Carlo (Monte The confidence interval of the prediction results of the model is evaluated by the Carlo random sampling method to ensure the reliability of the data, and finally the carbon dioxide / ammonia diffusion and accumulation data are generated, which specifically refers to the diffusion process of carbon dioxide and ammonia in the sheep house and their accumulation in a specific area. Based on the time series fluctuation data of temperature, carbon dioxide and ammonia, the diffusion trend and accumulation rate of carbon dioxide and ammonia are calculated, and their change increments are fitted, so as to predict the future accumulation trend and store it in the database.

[0028] Step S24: Estimating the probability of respiratory stress caused by ammonia intake based on the carbon dioxide / ammonia diffusion accumulation data according to the respiratory rate demand acceleration data to obtain the probability of respiratory stress caused by ammonia intake.

[0029] In the embodiment of the present invention, the probability of ammonia intake respiratory stress is estimated based on the carbon dioxide / ammonia diffusion accumulation data according to the respiratory rate demand acceleration data. First, the respiratory rate change data of meat goats in a high-altitude environment are interpolated to generate a continuously changing respiratory rate curve. The top 10% of the sample data with the highest respiratory rate are selected as high-risk samples to establish a probability density distribution. Then, Lagrange interpolation is used to calculate the respiratory rate change rate under different oxygen partial pressures. The ammonia concentration distribution at different spatial positions in the goat house is calculated based on the diffusion accumulation data. The ammonia diffusion process is numerically simulated using the finite difference method to solve the steady-state distribution of ammonia under different ventilation conditions. Subsequently, the ammonia concentration distribution data is matched with the respiratory rate data of meat goats to calculate the ammonia intake per unit time. According to the toxicological cumulative exposure theory, the Weibull-Fisher distribution is used to calculate the ammonia intake per unit time. The relationship between ammonia intake and the probability of respiratory stress was fitted based on the quantile regression method, and the probability model of respiratory stress caused by ammonia intake was obtained. Finally, the probability of respiratory stress under different ammonia concentration thresholds was calculated based on the quantile regression method and stored in the database.

[0030] Step S23 includes the following steps: Step S231: analyzing the carbon dioxide content rising period on the carbon dioxide / ammonia time series fluctuation data, and then analyzing the greenhouse effect enhancement period based on the temperature time series fluctuation data to obtain the greenhouse effect enhancement period; Step S232: identifying the thermal pressure enhancement gradient during the greenhouse effect enhancement period to obtain thermal pressure enhancement gradient data; Step S233: performing thermal convection accumulation vertical azimuth analysis on the carbon dioxide / ammonia time series fluctuation data based on the thermal pressure enhancement gradient data to obtain carbon dioxide / ammonia accumulation vertical azimuth data; Step S234: Perform carbon dioxide / ammonia diffusion accumulation increment fitting based on the heat pressure enhancement gradient data and the carbon dioxide / ammonia accumulation vertical orientation data to obtain carbon dioxide / ammonia diffusion accumulation data.

[0031] In an embodiment of the present invention, the carbon dioxide / ammonia time series fluctuation data is analyzed for the period of rising carbon dioxide content. First, the time series data is segmented, and 24 hours a day is divided into 144 periods, each period lasting 10 minutes, so as to more accurately capture the changing trend of carbon dioxide concentration. The local weighted regression (LOESS, local weighted scatter point smoothing) method is used to smooth the time series data, and the first-order derivative is calculated after removing the high-frequency noise to identify the rising trend interval of carbon dioxide concentration. The Markov Chain Monte Carlo (MCMC, Markov Chain Monte Carlo) method is used to estimate the transition probability of rising carbon dioxide concentration, and the changing law of carbon dioxide concentration in different time periods is judged. Subsequently, based on the temperature time series fluctuation data, the wavelet transform (Wavelet Transform) is used to decompose the temperature signal, extract the temperature change characteristics of different frequency bands, calculate the high-frequency temperature fluctuation interval overlapping with the period of rising carbon dioxide concentration, match the two to obtain the greenhouse effect enhancement period, and store them in the database. In the period of enhanced greenhouse effect, the thermal pressure intensification gradient is identified. First, the temperature data is gridded, and the temperature distribution model is constructed using the three-dimensional Kriging Interpolation method. The temperature changes at different heights of the sheep house are calculated at a height interval of 0.5 meters. The areas with temperature gradients greater than the set threshold are selected as high temperature gradient areas. The principal component analysis (PCA) method is used to reduce the dimension and extract the main influencing factors. The time series data of temperature, carbon dioxide concentration and humidity are feature extracted, the covariance matrix of each variable is calculated, the main component vector is obtained, and the thermal stress level of the greenhouse effect enhanced area is calculated according to the heat stress index (HSI). The thermal pressure intensification gradient data are normalized and stored in the database. Based on the thermal pressure enhancement gradient data, the vertical azimuth analysis of thermal convection accumulation of carbon dioxide / ammonia time series fluctuation data was carried out. The Laplace equation was used to solve the steady-state distribution of the thermal field. The thermal pressure enhancement gradient data was used as the input variable to construct a thermal convection model. The heat flux density at different heights was calculated by finite element analysis, and the thermal convection pattern of the air in the sheep house was simulated. The numerical integration method was used to calculate the carbon dioxide and ammonia concentration distribution at each altitude layer. The Lagrangian particle tracking method was used to simulate the transmission path of carbon dioxide and ammonia with the airflow, and finally the vertical azimuth data of carbon dioxide / ammonia accumulation was generated.According to the thermal pressure intensification gradient data and the vertical azimuth data of carbon dioxide / ammonia accumulation, the carbon dioxide / ammonia diffusion accumulation increment fitting is carried out. Firstly, a multivariate regression model is established, with temperature gradient, air humidity, carbon dioxide concentration and ammonia concentration as independent variables, and the changes in carbon dioxide and ammonia concentrations at each altitude layer as dependent variables. The ridge regression method is used to optimize the model parameters to prevent overfitting. Subsequently, the Monte Carlo random sampling method is used to evaluate the confidence interval of the model's prediction results to ensure the stability of the data. Finally, the carbon dioxide / ammonia diffusion accumulation data are obtained and stored in the database.

[0032] Step S24 includes the following steps: Step S241: numerically integrating the ammonia accumulation pressure of the carbon dioxide / ammonia diffusion accumulation data to obtain ammonia accumulation pressure data; Step S242: performing agglomeration distribution robust regression analysis on the carbon dioxide / ammonia diffusion accumulation data according to the ammonia accumulation pressure data to obtain ammonia accumulation distribution pressure regression data; Step S243: performing a pressure logarithmic transformation on the ammonia gas accumulation distribution pressure regression data to obtain ammonia gas accumulation pressure logarithmic transformation data; Step S244: obtaining the body characteristic data of the goats; performing the logarithmic conversion data of the ammonia accumulation pressure on the gas inhalation amount of the goats with different body characteristics per unit time according to the respiratory rate demand acceleration data and the body characteristic data of the goats, and obtaining the gas inhalation amount calculation data per unit time; Step S245: performing ammonia respiratory dissolution rate simulation estimation on the gas inhalation amount calculation data based on the body characteristic data of the goat to generate ammonia respiratory dissolution rate estimation data; Step S246: Estimating the probability of respiratory stress caused by ammonia ingestion based on the ammonia respiratory dissolution rate estimation data to obtain the probability of respiratory stress caused by ammonia ingestion.

[0033] In an embodiment of the present invention, when the ammonia accumulation pressure is numerically integrated for the carbon dioxide / ammonia diffusion accumulation data, the carbon dioxide / ammonia diffusion accumulation data is first discretized according to the spatial coordinates, and the sheep house is spatially divided by the grid method (GridMethod), and the side length of the grid is set to 1 meter. The carbon dioxide and ammonia concentrations in the grid are obtained using gas sensor measurement data, and the gas concentration is weighted averaged for each grid unit to calculate the pressure of each small area. On this basis, the Gaussian integral method is used for numerical integration to ensure the integration accuracy. By optimizing the number of Gaussian points (Gauss Points), 9-point Gaussian integrals are used in a 1×1 square meter area to improve the calculation accuracy. The ammonia diffusion pressure in the entire space is quantified by this integral method, and the ammonia accumulation pressure data is finally obtained. The unit of the data is Pa·m², which indicates the pressure accumulation of the gas per unit area, and the ammonia accumulation pressure data of the entire space is obtained after integration. At this time, the numerical range of the accumulation pressure is between 0 and 100 Pa·m², and the specific value varies according to the gas concentration and temperature conditions. The processed data is convenient for analyzing the subsequent gas diffusion trend. When performing a robust regression analysis of the agglomeration distribution of carbon dioxide / ammonia diffusion accumulation data based on ammonia accumulation pressure data, a robust regression algorithm is used to analyze the ammonia accumulation pressure data and carbon dioxide / ammonia diffusion accumulation data. The goal is to fit the relationship between carbon dioxide / ammonia concentration and agglomeration pressure. The sensitivity of the traditional least squares regression method to outliers is avoided by using the Theil-Sen estimation method. The regression coefficient of this method is calculated based on the median to avoid the impact of local outliers on the data fitting results. The iterative algorithm is calculated 500 times to optimize the coefficient. In the regression analysis, the standard error of the coefficient of each independent variable is less than 5%, and R² (goodness of fit) reaches more than 0.95. Finally, the regression data of carbon dioxide and ammonia accumulation pressure distribution are obtained. The regression data show that the relationship between carbon dioxide concentration and pressure is a linear relationship, while the relationship between ammonia concentration and pressure shows nonlinear characteristics. When performing pressure logarithm transformation on the ammonia accumulation distribution pressure regression data, the natural logarithm transformation (LnTransformation) is first used to transform the pressure data obtained in the regression analysis. The conversion method is to take the natural logarithm of each pressure data point value, and the converted pressure data is used to remove the exponential growth part in the original data. In the specific operation, for the pressure data P in the regression result, a logarithmic transformation is performed to obtain the logarithmic value of the pressure data: ln(P). The pressure data is transferred from the linear space to the logarithmic space. The converted pressure data unit remains in Pa·m², and the range is usually changed from the original pressure value range of 0-100 Pa·m² to the range of 0 to 4.61 (ln100). The data after logarithmic transformation becomes smoother, greatly reducing the impact of large pressure data, which is conducive to further analysis.When obtaining the body characteristic data of meat goats, we first measured the goats with high precision through image processing technology, and used video monitoring and image processing systems combined with deep convolutional neural networks (CNN) to obtain body data. During the processing, the video resolution was set to 1920×1080 pixels, and 30 frames of video were collected per second. The edge information of the goats was extracted through pre-processing methods such as denoising, edge detection, and contour extraction. After that, the pre-trained CNN model was used to extract the body parameters such as weight, body length, shoulder height, and chest circumference of each meat goat. In the experiment, the body length of meat goats is usually between 70 and 100 cm, the shoulder height is usually between 60 and 90 cm, the chest circumference is between 80 and 110 cm, and the weight is between 25 and 45 kg. After calibration, the image data is accurate to 0.5 kg of weight and 1 cm of body data. When calculating the gas inhalation volume of goats with different body characteristics per unit time based on the logarithmic transformation data of ammonia accumulation pressure according to the respiratory rate demand acceleration data and the body characteristics data of goats, the respiratory rate model is first established according to the body characteristics data, and the relationship between the respiratory rate and body data is fitted by polynomial regression. It is assumed that the respiratory rate demand of goats in high-altitude environments is 30% higher than that in normal conditions, and it is used as an acceleration factor in the calculation process. The gas inhalation volume of each goat is calculated with a unit time (1 minute) as a cycle and combined with the gas concentration data. It is assumed that in a high-concentration ammonia environment, the amount of ammonia inhaled per kilogram of body weight of goats per minute is 0.5 mL, and in a low-concentration environment it is 0.1 mL. Finally, the gas inhalation volume calculation data under different body characteristics is obtained by calculation, and the unit is mL / min / kg. The results are usually between 0.1 mL / min / kg and 0.8 mL / min / kg. The specific data depends on the body shape of the goats and the changes in gas concentration. When simulating and estimating the ammonia respiratory dissolution rate of the gas inhalation calculation data based on the physical characteristics data of meat goats, the fluid dynamics model was used to model the ammonia dissolution process. During the simulation process, the Navier-Stokes Equation was used to accurately model the air flow, and factors such as air flow rate, ammonia concentration, goat body shape and respiratory frequency were considered. Based on this model, the ammonia dissolution rate in the respiratory tract of meat goats was calculated. The simulation results showed that under normal conditions, the ammonia dissolution rate of meat goats per kilogram of body weight was about 0.25 mL / (kg·min). At high altitudes, considering the thin oxygen, the dissolution rate increased by 30% to 0.325 mL / (kg·min). This rate was used for subsequent stress probability assessment.When estimating the probability of respiratory stress caused by ammonia intake based on the estimated data of ammonia respiratory dissolution rate, the log-normal distribution model was first used to describe the ammonia intake process, and the relationship between the amount of ammonia intake and the stress probability was derived in combination with Bayesian Inference. In the specific calculation process, the prior distribution of Bayesian inference was set to a uniform distribution. Based on historical experimental data, the posterior distribution was gradually adjusted to simulate the probability of ammonia intake under different environmental conditions, and the stress probability of meat goats under different ammonia concentrations was obtained. The results showed that when the ammonia concentration was higher than 50 ppm, the stress probability of meat goats began to rise sharply. Usually, when the ammonia concentration was 80 ppm, the stress probability of meat goats reached 80%. This data will be used in the environmental control system to formulate corresponding ventilation strategies and adjustment measures.

[0034] Step S245 includes the following steps: According to the physical characteristics of meat goats, the gas inhalation calculation data were used to evaluate the cumulative exposure of ammonia breathing between different physical characteristics, and the cumulative exposure data of ammonia were obtained; The ammonia absorption rate is calculated based on the ammonia cumulative exposure data and the respiratory rate demand acceleration data to obtain the ammonia absorption rate; Ammonia solubility parameter correction calculation is performed based on ammonia cumulative exposure data and ammonia absorption rate to obtain ammonia respiratory solubility correction data; The ammonia respiratory dissolution rate is simulated and estimated based on the ammonia respiratory dissolution correction data to generate the ammonia respiratory dissolution rate estimation data.

[0035] In the embodiment of the present invention, when evaluating the cumulative exposure of ammonia breathing between different body characteristics for the gas inhalation calculation data, the gas inhalation model is first established through the body characteristic data of meat goats. The specific data include weight (kg), shoulder height (cm), body length (cm), etc. It is assumed that under standard conditions, there is a linear relationship between weight and gas inhalation per minute. For example, the amount of ammonia inhaled per minute by meat goats per kilogram of body weight in a high-altitude environment can be set to 0.12mL / kg·min, while it is 0.1mL / kg·min in a low-altitude environment. The breathing frequency of meat goats varies with environmental changes. It is assumed that the breathing frequency in a high-altitude environment increases by 30%, that is, the breathing frequency of meat goats per minute is 40 to 55 times (relative to 30 times in the normal state). Based on these parameters, the gas inhalation of each meat goat per unit time is first calculated, and the exposure to ammonia is calculated through the relationship with the concentration of the gas. Assume that the exposure changes linearly with the increase of each kilogram of body weight. For example, the gas inhalation volume per hour of a 30kg goat in a high altitude environment is 30×0.12×55=198mL. If the concentration of the inhaled gas per unit time is between 100ppm (parts per million) and 500ppm, the gas exposure volume is between 10mL and 200mL. After this process, the ammonia exposure data is evaluated and the ammonia exposure data per unit time is finally obtained. On this basis, when calculating the ammonia absorption rate based on the cumulative ammonia exposure data and the respiratory rate demand acceleration data, the absorption rate is first adjusted according to the relationship between the inhaled gas volume per unit body weight and its absorption capacity, combined with the respiratory rate demand acceleration data. Under normal circumstances, it is assumed that the ammonia absorption rate of meat goats per kilogram of body weight per unit time is 0.04mL / (kg·min), and in a high altitude environment, the ammonia absorption rate increases due to the increase in respiratory rate. Assuming that the absorption rate increases by 30%, that is, 0.04×1.3=0.052mL / (kg·min). On this basis, the relationship between gas concentration and inhaled volume is used to calculate the amount absorbed per unit time. In the experiment, the gas concentration in different high-altitude environments was set to 50ppm to 300ppm. Assuming that the gas concentration fluctuates over time, the gas inhaled volume and the absorption rate model can be calibrated to calculate the change trend of the absorption rate under different gas concentrations. For example, if the gas concentration is 200ppm, the absorption per unit time can be calculated by combining 0.052mL / (kg·min) with the concentration data to obtain specific absorption rate data. The absorption rate data that can be obtained through this model will eventually be between 0.05 and 0.1mL / (kg·min), and the absorption rate increases with the acceleration of the breathing rate.When calculating the ammonia solubility parameter correction based on the cumulative exposure data and ammonia absorption rate, the gas solubility constant correction model was used, based on Henry's Law, which states the relationship between the solubility of a gas in a solution and the pressure and solubility constant of the gas. Assuming that the standard solubility constant of ammonia is 0.9 mol / L·atm, the solubility constant will decrease by 20% in a high-altitude environment due to the decrease in air pressure, that is, the solubility constant is 0.72 mol / L·atm. By combining the gas concentration and environmental conditions, the final ammonia solubility data is calculated using the correction of the gas inhalation amount and the solubility constant. In this calculation, the solubility of the gas can be calculated by multiplying the unit gas inhalation amount by the solubility constant. Assuming that the solubility constant of the gas is corrected to 0.72 mol / L·atm, the amount of ammonia dissolved per unit will be lower than normal. During the calculation process, the final ammonia dissolution correction data was obtained using the data corrected by gas concentration changes and ammonia solubility, ranging from 0.05 to 0.8 mol / L·atm. When simulating and estimating the ammonia respiratory dissolution rate based on the ammonia respiratory dissolution correction data, the gas dissolution process was simulated using a fluid dynamics model. First, it was assumed that the ammonia respiratory dissolution rate of meat goats was 0.1 mL / (min·kg) per unit time, and the change in dissolution rate was calculated by adjusting the rate. For example, when the gas concentration was 200 ppm and the temperature was 25°C, the model calculated that the dissolution rate of meat goats was 0.12 mL / (min·kg). When the temperature rose to 30°C, the dissolution rate increased by 15%, that is, 0.12×1.15=0.138 mL / (min·kg). In addition, changes in air humidity and air pressure also affect the dissolution rate. Assuming that the humidity is 80%, the dissolution rate will increase by another 10%, resulting in a dissolution rate of 0.138×1.1=0.152mL / (min·kg). Through this process, the respiratory dissolution rate of ammonia can be simulated, and finally the estimated data of the respiratory dissolution rate of ammonia can be generated.

[0036] Step S3 includes the following steps: Step S31: normalizing the probability of respiratory stress caused by ammonia ingestion to obtain normalized data of the probability of respiratory stress; Step S32: mapping the respiratory rate demand acceleration data to the ammonia safety content intervals between different respiratory frequencies according to the respiratory stress probability normalization data, to obtain the ammonia safety content interval; Step S33: matching the humidity content in the sheep house based on the safe content range of ammonia to obtain humidity content matching data; Step S34: performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data according to the humidity content matching data to obtain ventilation parameter balance design data; Step S35: Based on the humidity content matching data and the ventilation parameter balance design data, oxygen content compensation processing is performed in the sheep house to obtain oxygen content compensation data.

[0037] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: normalizing the probability of respiratory stress caused by ammonia ingestion to obtain normalized data of the probability of respiratory stress; In an embodiment of the present invention, the probability of respiratory stress caused by ammonia intake is normalized. First, all historical data need to be extracted from the existing ammonia intake respiratory stress probability data set, a normalization standard is set, and all data points are subjected to minimum-maximum normalization (Min-Max Normalization). The calculation method is to set an ammonia intake probability range [0,1], map the minimum value of the historical data to 0, map the maximum value to 1, and scale other values ​​proportionally. Assuming that the probability range of respiratory stress caused by ammonia intake in the historical data is 0.02 to 0.85, the new data range after normalization is mapped to [0,1]. This processing method can make the data change trend more obvious, which is conducive to subsequent analysis.

[0038] Step S32: mapping the respiratory rate demand acceleration data to the ammonia safety content intervals between different respiratory frequencies according to the respiratory stress probability normalization data, to obtain the ammonia safety content interval; In the embodiment of the present invention, according to the normalized respiratory stress probability data, the ammonia safety content interval is mapped to the acceleration data of different respiratory frequency requirements. First, the air intake per unit time needs to be calculated according to different respiratory frequencies. Assuming that the basic respiratory rate of meat goats is 30 times / minute, the maximum accelerated respiratory rate is 90 times / minute, and the amount of air inhaled each time is 5 liters, the air intake under the basic state is 150 liters / minute, and the air intake under the maximum respiratory acceleration state is 450 liters / minute. On this basis, the gas partial pressure law is used to calculate the ammonia safety content interval. Assuming that the maximum ammonia concentration acceptable to meat goats is 20 ppm (parts per million), the ammonia intake is calculated at different respiratory frequencies, and the safety content interval is delineated accordingly. The safe ammonia concentration corresponding to the low respiratory rate (30 times / minute) can be set to 15-20 ppm, the safe interval corresponding to the medium respiratory rate (60 times / minute) is 10-15 ppm, and the safety interval corresponding to the high respiratory rate (90 times / minute) needs to be reduced to 5-10 ppm.

[0039] Step S33: matching the humidity content in the sheep house based on the safe content range of ammonia to obtain humidity content matching data; In the embodiment of the present invention, the humidity content in the sheep house is matched based on the ammonia safety content range. First, high-precision temperature and humidity sensors are arranged at different positions in the sheep house to collect air humidity data in real time. The sensor spacing is set to 2 meters, and they are arranged at three different heights of 0.5 meters, 1.5 meters, and 2.5 meters from the ground to obtain vertical humidity gradient data. At the same time, a laser scattering dust sensor is used to measure the concentration of suspended particles in the air, and the proportion of moisture-attached particles in the air is calculated to infer the effect of humidity on gas diffusion. The sensor sampling frequency is set to once every 10 seconds, and the data is uploaded to the central control unit through the wireless communication module. After obtaining the real-time humidity data, the sheep house space was divided into small units of 0.5 cubic meters using the finite element mesh division method according to the internal airflow model of the sheep house, and the humidity values ​​in each unit were interpolated. The 3D Kriging interpolation method was used to establish a humidity spatial distribution model to determine the humidity distribution state of each area in the sheep house. At the same time, combined with the ammonia diffusion simulation data, the effect of humidity on the ammonia dissolution rate was calculated. According to the solubility curve of ammonia in water, the decrease rate of ammonia concentration under different humidity conditions was determined. Assuming that the initial ammonia concentration is 15 ppm, the ammonia concentration decay rate is 0.1 ppm / min at a relative humidity of 50%, and the decay rate can be increased to 0.3 ppm / min at a relative humidity of 80%. Therefore, the ammonia concentration in the sheep house can be effectively controlled by adjusting the humidity level. According to the calculation results of the humidity spatial distribution model, the humidity control device is controlled for fine adjustment. An ultrasonic humidifier is used for humidification. It is started when the humidity is 5% lower than the target value and stopped when the humidity reaches the target value. The mist output of the humidifier is set at 3 L / h to prevent the internal environment of the sheep house from being too humid due to excessive humidity. At the same time, the forced ventilation system is used to diffuse the humidity so that the humidity reaches the target level within 5 minutes. If the humidity is more than 5% higher than the target value, the dehumidifier is activated. The condensation dehumidification method is used to condense and discharge water vapor by lowering the air temperature. The dehumidification capacity per hour is set to 2 L / h, and it is dynamically adjusted according to the ventilation volume of the sheep house to ensure the accuracy of humidity control.

[0040] Step S34: performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data according to the humidity content matching data to obtain ventilation parameter balance design data; In an embodiment of the present invention, ventilation parameter balance processing is performed on the carbon dioxide / ammonia diffusion and accumulation data according to the humidity matching data. First, the air flow data inside the sheep house needs to be obtained, including air flow rate, air flow distribution, ventilation rate, etc. It is assumed that the basic ventilation rate inside the sheep house is 6 times / hour. When the ammonia accumulation is high, the ventilation rate can be increased to 12 times / hour. The ventilation wind speed in the sheep house is calculated using a fluid dynamics model. The dynamic pressure change of the air flow is calculated according to the Bernoulli equation. The wind speed range is set at 0.3-1.2 m / s to ensure uniform air flow in the sheep house. At the same time, it is necessary to evaluate the effect of different air flow rates on ammonia diffusion. If the ammonia concentration is high and accumulates at the top of the sheep house, the height of the air inlet and the exhaust port can be appropriately adjusted so that the exhaust port is set in the ammonia accumulation area to improve the exhaust efficiency.

[0041] Step S35: Based on the humidity content matching data and the ventilation parameter balance design data, oxygen content compensation processing is performed in the sheep house to obtain oxygen content compensation data.

[0042] In an embodiment of the present invention, based on the humidity content matching data and the ventilation parameter balance design data, the oxygen content in the sheep house is compensated. First, the oxygen concentration in the sheep house needs to be monitored. Assuming that the normal oxygen content is 20.9%, in high altitude areas, due to the thin air, the oxygen content is reduced to 18.5%-19.5%. At this time, oxygen content compensation is required. The compensation method can be calculated by gas mixing. According to the inverse relationship between the concentrations of oxygen and carbon dioxide, the carbon dioxide concentration in the sheep house is controlled not to exceed 0.08% to ensure sufficient oxygen supply. The method for calculating the oxygen compensation amount is to use the product relationship between oxygen concentration and air flow rate. Assuming that the current oxygen content is 19.0% and the target oxygen content is 20.5%, it is necessary to compensate for 1.5% of the oxygen concentration by increasing the ventilation volume or the oxygen supplement device. At the same time, the effect of oxygen compensation on the respiratory rate of meat goats is monitored to ensure that the oxygen concentration adjustment does not cause accelerated breathing, thereby affecting the health of meat goats.

[0043] Step S34 includes the following steps: Step S341: performing ventilation humidity loss compensation matching according to the humidity content matching data to obtain ventilation humidity loss compensation data; Step S342: performing accumulation density difference analysis on the carbon dioxide / ammonia diffusion accumulation data to obtain carbon dioxide / ammonia accumulation density difference data; Step S343: performing ventilation wind pressure matching of the sheep house based on the carbon dioxide / ammonia accumulation density difference data to obtain ventilation wind pressure matching data of the sheep house; Step S344: Design ventilation structure parameters based on the carbon dioxide / ammonia accumulation density difference data and the sheep house ventilation wind pressure matching data to obtain ventilation structure parameters; Step S345: Perform ventilation parameter balance processing according to the ventilation humidity loss compensation data and the ventilation structure parameters to obtain ventilation parameter balance design data.

[0044] In the embodiment of the present invention, ventilation humidity loss compensation matching is performed according to the humidity content matching data. First, the difference method is used to calculate the loss of humidity due to airflow during ventilation. Under the conditions of ventilation wind speed of 2 m / s and relative humidity of 60%, the air water vapor content loss rate is set to 0.02 g / m³ / s. When the wind speed is increased to 4 m / s, the loss rate increases to 0.05 g / m³ / s. In order to ensure the stability of humidity after ventilation, a spray humidification system is used for compensation. The humidification nozzle is arranged in the air inlet area of ​​the sheep house, and the nozzle flow is set to 5L / h. It is adjusted in real time through the humidity feedback control system. The PID (proportional-integral-differential) control algorithm is used to calculate the humidity loss compensation demand to ensure that the humidity inside the sheep house is maintained within the target range. If the humidity loss caused by ventilation exceeds 5%, the humidification amount is automatically increased. If the humidity is too high, the spray flow is reduced or the dehumidification system is enabled. The accumulation density difference analysis was performed on the carbon dioxide / ammonia diffusion and accumulation data. A gas sensor array was used to monitor the carbon dioxide and ammonia concentrations in different areas of the sheep house in real time. The sensors were arranged at a spacing of 1.5 meters and the acquisition frequency was 1 Hz. At the same time, three-dimensional computational fluid dynamics (CFD) modeling was used to analyze the flow characteristics of the gas in the sheep house. Based on the gas molecular diffusion equation, the accumulation density differences of carbon dioxide and ammonia in different areas were calculated. The carbon dioxide safety threshold in the sheep house was set at 2000 ppm, and the ammonia safety threshold was set at 10 ppm. If the concentration in a certain area was more than 20% higher than the average value, it was determined to be a high accumulation area. The gas density of the area was recorded, and the concentration gradient with the low accumulation area was calculated to determine the demand for airflow transport. The ventilation wind pressure of the sheep house is matched based on the difference data of carbon dioxide / ammonia accumulation density. A pressure sensor is used to measure the pressure difference inside and outside the sheep house. The sensor measurement accuracy is set to ±0.1 Pa, and the data update frequency is 10 Hz. When the pressure difference is less than 2 Pa, the wind speed is increased by adjusting the opening of the air inlet and exhaust outlet to enhance the air flow transport capacity. If the pressure difference exceeds 5 Pa, the exhaust outlet opening is reduced to prevent temperature and humidity fluctuations caused by excessive ventilation. A variable frequency fan is used to control the wind pressure. The fan speed adjustment range is set to 500-1500 rpm, and the fan power is dynamically adjusted according to the real-time wind pressure data.The ventilation structure parameters are designed based on the carbon dioxide / ammonia accumulation density difference data and the sheep house ventilation wind pressure matching data. First, according to the gas diffusion simulation data, the air flow velocity requirements in different areas of the sheep house are calculated, local vents are added in high accumulation areas, and the ventilation duct layout is optimized to make the airflow evenly distributed. The vent size is set based on fluid mechanics calculations to ensure that the air flow rate is between 1.5-3.5 m / s. At the same time, a streamlined deflector is used to adjust the airflow direction to prevent air flow short-circuiting from affecting ventilation efficiency. An adjustable ventilation window is added to the top of the sheep house to control the opening range of 10-100% to ensure smooth air convection. The ventilation parameter balance is processed according to the ventilation humidity loss compensation data and ventilation structure parameters. The dynamic ventilation control system is used to integrate multi-dimensional data such as humidity, wind pressure, and gas concentration. The fuzzy control algorithm is used to jointly adjust the fan speed, vent opening, and humidification device operating status. The goal is to keep the humidity in the sheep house at 55-65%, the carbon dioxide concentration below 1800 ppm, and the ammonia concentration below 8 ppm. The system updates the data every 5 seconds and makes predictive adjustments based on historical data to ensure the accuracy of the ventilation parameter balance design data.

[0045] Step S344 includes the following steps: Acquire sheep house structural design data; extract ventilation paths from the sheep house structural design data to obtain sheep house ventilation path data; Based on the carbon dioxide / ammonia accumulation density difference data, the carbon dioxide / ammonia accumulation pressure difference on the sheep house ventilation path data is analyzed to obtain the carbon dioxide / ammonia accumulation pressure difference between ventilation paths; According to the sheep house ventilation wind pressure matching data, the wind speed and flow rate are matched with the carbon dioxide / ammonia accumulation pressure difference to obtain the wind speed and flow rate matching data; Performing repeated behavior learning on the accumulated pressure difference of carbon dioxide / ammonia to obtain accumulated pressure behavior learning data; Based on the sheep house ventilation wind pressure matching data and wind speed flow matching data, the accumulated pressure behavior learning data is intelligently matched with the ventilation rate to obtain the ventilation rate intelligent matching data; The ventilation structure parameters are designed according to the wind speed and flow matching data, the sheep house ventilation pressure matching data and the air change rate intelligent matching data to obtain the ventilation structure parameters.

[0046] In an embodiment of the present invention, the structural design data of the sheep house is obtained. First, the internal and external structures of the sheep house are scanned by a 3D laser scanner (3D laserscanner), and the scanning accuracy is set to 1 mm to obtain complete geometric structure data. At the same time, combined with the architectural design drawings, key structural parameters such as walls, ceilings, windows, vents, and air ducts are extracted. Computer-aided design (CAD) software is used for data modeling to generate a complete three-dimensional sheep house structural model. The model contains detailed information such as vent size, wall material, and air duct layout to ensure the accuracy of ventilation path calculation. The ventilation path was extracted from the sheep house structural design data, and the computational fluid dynamics (CFD) software was used to simulate the airflow inside the sheep house. The initial boundary conditions were set, including an external wind speed of 3 m / s, an internal temperature of 25℃, and a relative humidity of 60%. Based on the airflow streamline analysis method, the natural ventilation path and forced ventilation path were extracted. The natural ventilation path was mainly calculated based on the shortest path of the airflow from the air inlet to the exhaust outlet, and the forced ventilation path was simulated and calculated based on the fan layout. At the same time, the velocity vector field was used to analyze the air flow inside the sheep house, and the main airflow channels in different areas were extracted to generate the ventilation path data of the sheep house. Based on the carbon dioxide / ammonia accumulation density difference data, the carbon dioxide / ammonia accumulation pressure difference on the ventilation path data of the sheep house was analyzed. First, carbon dioxide and ammonia sensors were arranged in different areas of the sheep house. The sensor measurement accuracy was set to 1 ppm and the data acquisition frequency was 1 Hz. The average concentration of carbon dioxide / ammonia in each area was calculated through long-term data monitoring, and the gas accumulation pressure difference on each ventilation path was calculated using the pressure gradient equation. If the carbon dioxide concentration on a certain path exceeds 2000 ppm and the ammonia concentration exceeds 10 ppm, its pressure gradient is calculated and the cause of gas accumulation is analyzed. At the same time, combined with CFD simulation data, the air pressure difference between high and low concentration areas is compared, and the pressure distribution between ventilation paths inside the sheep house is calculated to obtain the carbon dioxide / ammonia accumulation pressure difference data.According to the ventilation wind pressure matching data of the sheep house, the wind speed and flow are matched with the accumulation pressure difference of carbon dioxide / ammonia. First, the wind speed of each ventilation path of the sheep house is measured by a wind speed sensor (anemometer). The wind speed measurement range is set to 0-10m / s, and the accuracy is ±0.1 m / s. In the area where the wind speed is less than 2 m / s, the required compensation air volume is calculated. If the wind speed of a ventilation path is lower than 1 m / s, a deflector is installed on the path to change the airflow direction, and an auxiliary fan (axial fan) is added at the necessary position. The fan flow is set to 500-1500 m³ / h, and the wind speed control range is 2-5 m / s. At the same time, the real-time wind speed data is used to adjust the fan speed to ensure that the air flow meets the set target, and finally the wind speed and flow matching data are calculated. The accumulation repeated behavior learning of the carbon dioxide / ammonia accumulation pressure difference is carried out, and the long short-term memory network (LSTM) algorithm is used to analyze the gas accumulation trend in different areas of the sheep house. The input data includes the carbon dioxide / ammonia concentration change curve, wind speed and direction data, vent opening and closing status, etc. in the past 30 days. Through deep learning model training, the high-incidence areas and time periods of gas accumulation are identified. For example, when the temperature drops and ventilation weakens at night, the probability of carbon dioxide accumulation in the middle of the sheep house increases. The model automatically marks the area as a key monitoring area and outputs the accumulation pressure behavior learning data. Based on the sheep house ventilation wind pressure matching data and wind speed and flow matching data, the accumulated pressure behavior learning data is intelligently matched with the ventilation rate. First, the target ventilation rate inside the sheep house is set to 10 times / h. The ventilation rate calculation is based on the volume of the sheep house and the ventilation flow. The intelligent ventilation control system is used to dynamically adjust the operating status of the ventilation fan. When the ventilation rate is lower than 8 times / h, the fan power is automatically increased, and the opening of the air inlet and exhaust port is adjusted to ensure that the ventilation rate is stable at the target value. At the same time, based on the accumulated pressure behavior learning data, the gas accumulation trend is predicted in advance. If the model predicts that the carbon dioxide concentration in a certain area will exceed 1800 ppm in the next 30 minutes, the system will increase the ventilation volume in advance to ensure that the air quality meets the standard, and finally output the ventilation rate intelligent matching data.The ventilation structure parameters are designed according to the wind speed and flow matching data, the sheep house ventilation pressure matching data and the air change rate intelligent matching data, and the sizes of the air inlet and outlet are optimized to ensure uniform wind speed distribution. For example, adjustable louvers are set on both sides of the sheep house with an opening range of 10-100% to control the air flow entry angle and prevent short-circuit airflow from affecting the ventilation effect. At the same time, a mechanical exhaust system is installed on the top of the sheep house with a fan speed control range of 500-1200 rpm. Dynamic adjustments are made according to real-time air quality data to ensure the stability of the sheep house ventilation system and finally generate ventilation structure parameter data.

[0047] Preferably, the present invention also provides an automatic control system for the environment of a meat goat house, which is used to execute the automatic control method for the environment of a meat goat house as described above, and the automatic control system for the environment of a meat goat house comprises: The environmental data acquisition module is used to collect all-weather data in the high-altitude environment of the meat goats through sensors to obtain all-weather environmental data in the high-altitude goat house; extract the temperature, humidity and carbon dioxide / ammonia all-weather time series fluctuations of the all-weather environmental data in the high-altitude goat house, and obtain the temperature time series fluctuation data and carbon dioxide / ammonia time series fluctuation data in the goat house respectively; A stress probability estimation module is used to perform carbon dioxide / ammonia diffusion increment fitting based on the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; perform ammonia intake respiratory stress probability estimation on the carbon dioxide / ammonia diffusion accumulation data to obtain the ammonia intake respiratory stress probability; The safety content interval mapping module is used to map the ammonia safety content interval according to the probability of respiratory stress caused by ammonia intake to obtain the ammonia safety content interval; based on the ammonia safety content interval, the ventilation parameter balance processing is performed on the carbon dioxide / ammonia diffusion accumulation data to obtain the ventilation parameter balance design data; based on the ventilation parameter balance design data, the oxygen content compensation processing is performed in the sheep house to obtain the oxygen content compensation data; The automatic control strategy formulation module is used to formulate an automatic control strategy for the sheep house environment based on ventilation parameter balance design data and oxygen content compensation data, obtain the automatic control strategy for the sheep house environment, and send the automatic control strategy for the sheep house environment to the terminal to execute the automatic control method for the meat goat house environment.

[0048] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for automatically controlling the environment of a goat house, characterized in that: The following steps are involved: Step S1: collecting all-weather data in the high-altitude environment of the goats through sensors to obtain all-weather environmental data in the high-altitude goat house; extracting the all-weather time series fluctuations of temperature and carbon dioxide / ammonia in the high-altitude goat house to obtain the time series fluctuation data of temperature in the goat house and the time series fluctuation data of carbon dioxide / ammonia in the goat house; Step S2: performing carbon dioxide / ammonia diffusion increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; The probability of respiratory stress caused by ammonia intake is estimated based on the carbon dioxide / ammonia diffusion accumulation data to obtain the probability of respiratory stress caused by ammonia intake; Step S3: mapping the ammonia safety content interval according to the probability of respiratory stress caused by ammonia intake to obtain the ammonia safety content interval; performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data based on the ammonia safety content interval to obtain ventilation parameter balance design data; performing oxygen content compensation processing in the sheep house based on the ventilation parameter balance design data to obtain oxygen content compensation data; Step S4: Formulate an automatic control strategy for the sheep house environment based on the ventilation parameter balance design data and the oxygen content compensation data, obtain the automatic control strategy for the sheep house environment, and send the automatic control strategy for the sheep house environment to the terminal to execute the automatic control method for the meat goat house environment.

2. The automatic control method for the environment of a goat house according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting all-weather data of the high-altitude environment of the goats in the goat shed through sensors to obtain all-weather environmental data of the high-altitude goat shed; Step S12: Filling missing values ​​in the all-weather environmental data of the high-altitude sheep house to obtain environmental filling data of the high-altitude sheep house; Step S13: extract the temperature, humidity and carbon dioxide / ammonia all-weather time series fluctuations of the high-altitude sheep house environment filling data, and obtain the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data in the sheep house respectively.

3. The automatic control method for the meat goat house environment according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing a low oxygen environment concentration fluctuation analysis on the all-weather environmental data in the high-altitude sheep house to obtain low oxygen environment concentration fluctuation data; Step S22: evaluating the respiratory rate demand acceleration of meat goats based on the hypoxic environment concentration fluctuation data to obtain respiratory rate demand acceleration data; Step S23: performing carbon dioxide / ammonia diffusion accumulation increment fitting according to the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; Step S24: Estimating the probability of respiratory stress caused by ammonia intake based on the carbon dioxide / ammonia diffusion accumulation data according to the respiratory rate demand acceleration data to obtain the probability of respiratory stress caused by ammonia intake.

4. The automatic control method for the meat goat house environment according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: analyzing the carbon dioxide content rising period on the carbon dioxide / ammonia time series fluctuation data, and then analyzing the greenhouse effect enhancement period based on the temperature time series fluctuation data to obtain the greenhouse effect enhancement period; Step S232: identifying the thermal pressure enhancement gradient during the greenhouse effect enhancement period to obtain thermal pressure enhancement gradient data; Step S233: performing thermal convection accumulation vertical azimuth analysis on the carbon dioxide / ammonia time series fluctuation data based on the thermal pressure enhancement gradient data to obtain carbon dioxide / ammonia accumulation vertical azimuth data; Step S234: Perform carbon dioxide / ammonia diffusion accumulation increment fitting based on the heat pressure enhancement gradient data and the carbon dioxide / ammonia accumulation vertical orientation data to obtain carbon dioxide / ammonia diffusion accumulation data.

5. The automatic control method for the meat goat house environment according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: numerically integrating the ammonia accumulation pressure of the carbon dioxide / ammonia diffusion accumulation data to obtain ammonia accumulation pressure data; Step S242: performing agglomeration distribution robust regression analysis on the carbon dioxide / ammonia diffusion accumulation data according to the ammonia accumulation pressure data to obtain ammonia accumulation distribution pressure regression data; Step S243: performing a pressure logarithmic transformation on the ammonia gas accumulation distribution pressure regression data to obtain ammonia gas accumulation pressure logarithmic transformation data; Step S244: obtaining the body characteristic data of the goats; performing the logarithmic conversion data of the ammonia accumulation pressure on the gas inhalation amount of the goats with different body characteristics per unit time according to the respiratory rate demand acceleration data and the body characteristic data of the goats, and obtaining the gas inhalation amount calculation data per unit time; Step S245: performing ammonia respiratory dissolution rate simulation estimation on the gas inhalation amount calculation data based on the body characteristic data of the goat to generate ammonia respiratory dissolution rate estimation data; Step S246: Estimating the probability of respiratory stress caused by ammonia ingestion based on the ammonia respiratory dissolution rate estimation data to obtain the probability of respiratory stress caused by ammonia ingestion.

6. The automatic control method for the environment of a goat house according to claim 4, characterized in that: Step S245 includes the following steps: According to the physical characteristics of meat goats, the gas inhalation calculation data were used to evaluate the cumulative exposure of ammonia breathing between different physical characteristics, and the cumulative exposure data of ammonia were obtained; The ammonia absorption rate is calculated based on the ammonia cumulative exposure data and the respiratory rate demand acceleration data to obtain the ammonia absorption rate; Ammonia solubility parameter correction calculation is performed based on ammonia cumulative exposure data and ammonia absorption rate to obtain ammonia respiratory solubility correction data; The ammonia respiratory dissolution rate is simulated and estimated based on the ammonia respiratory dissolution correction data to generate the ammonia respiratory dissolution rate estimation data.

7. The automatic control method for the meat goat house environment according to claim 3, characterized in that: Step S3 includes the following steps: Step S31: normalizing the probability of respiratory stress caused by ammonia ingestion to obtain normalized data of the probability of respiratory stress; Step S32: mapping the respiratory rate demand acceleration data to the ammonia safety content intervals between different respiratory frequencies according to the respiratory stress probability normalization data, to obtain the ammonia safety content interval; Step S33: matching the humidity content in the sheep house based on the safe content range of ammonia to obtain humidity content matching data; Step S34: performing ventilation parameter balance processing on the carbon dioxide / ammonia diffusion accumulation data according to the humidity content matching data to obtain ventilation parameter balance design data; Step S35: Based on the humidity content matching data and the ventilation parameter balance design data, oxygen content compensation processing is performed in the sheep house to obtain oxygen content compensation data.

8. The automatic control method for the meat goat house environment according to claim 7, characterized in that: Step S34 includes the following steps: Step S341: performing ventilation humidity loss compensation matching according to the humidity content matching data to obtain ventilation humidity loss compensation data; Step S342: performing accumulation density difference analysis on the carbon dioxide / ammonia diffusion accumulation data to obtain carbon dioxide / ammonia accumulation density difference data; Step S343: performing ventilation wind pressure matching of the sheep house based on the carbon dioxide / ammonia accumulation density difference data to obtain ventilation wind pressure matching data of the sheep house; Step S344: Design ventilation structure parameters based on the carbon dioxide / ammonia accumulation density difference data and the sheep house ventilation wind pressure matching data to obtain ventilation structure parameters; Step S345: Perform ventilation parameter balance processing according to the ventilation humidity loss compensation data and the ventilation structure parameters to obtain ventilation parameter balance design data.

9. The automatic control method for the environment of a goat house according to claim 8, characterized in that: Step S344 includes the following steps: Acquire sheep house structural design data; extract ventilation paths from the sheep house structural design data to obtain sheep house ventilation path data; Based on the carbon dioxide / ammonia accumulation density difference data, the carbon dioxide / ammonia accumulation pressure difference on the sheep house ventilation path data is analyzed to obtain the carbon dioxide / ammonia accumulation pressure difference between ventilation paths; According to the sheep house ventilation wind pressure matching data, the wind speed and flow rate are matched with the carbon dioxide / ammonia accumulation pressure difference to obtain the wind speed and flow rate matching data; Performing repeated behavior learning on the accumulated pressure difference of carbon dioxide / ammonia to obtain accumulated pressure behavior learning data; Based on the sheep house ventilation wind pressure matching data and wind speed flow matching data, the accumulated pressure behavior learning data is intelligently matched with the ventilation rate to obtain the ventilation rate intelligent matching data; The ventilation structure parameters are designed according to the wind speed and flow matching data, the sheep house ventilation pressure matching data and the air change rate intelligent matching data to obtain the ventilation structure parameters.

10. An automatic control system for the environment of a goat house, characterized in that: Used to execute the automatic control method of the meat goat house environment according to claim 1, the meat goat house environment automatic control system comprises: The environmental data acquisition module is used to collect all-weather data in the high-altitude environment of the meat goats through sensors to obtain all-weather environmental data in the high-altitude goat house; extract the temperature, humidity and carbon dioxide / ammonia all-weather time series fluctuations of the all-weather environmental data in the high-altitude goat house, and obtain the temperature time series fluctuation data and carbon dioxide / ammonia time series fluctuation data in the goat house respectively; A stress probability estimation module is used to perform carbon dioxide / ammonia diffusion increment fitting based on the temperature time series fluctuation data and the carbon dioxide / ammonia time series fluctuation data to obtain carbon dioxide / ammonia diffusion accumulation data; perform ammonia intake respiratory stress probability estimation on the carbon dioxide / ammonia diffusion accumulation data to obtain the ammonia intake respiratory stress probability; The safety content interval mapping module is used to map the ammonia safety content interval according to the probability of respiratory stress caused by ammonia intake to obtain the ammonia safety content interval; based on the ammonia safety content interval, the ventilation parameter balance processing is performed on the carbon dioxide / ammonia diffusion accumulation data to obtain the ventilation parameter balance design data; based on the ventilation parameter balance design data, the oxygen content compensation processing is performed in the sheep house to obtain the oxygen content compensation data; The automatic control strategy formulation module is used to formulate an automatic control strategy for the sheep house environment based on ventilation parameter balance design data and oxygen content compensation data, obtain the automatic control strategy for the sheep house environment, and send the automatic control strategy for the sheep house environment to the terminal to execute the automatic control method for the meat goat house environment.

Images