Intelligent ventilation adjusting method and system for livestock and poultry breeding

Abstract

The invention relates to the technical field of intelligent ventilation adjustment, in particular to an intelligent ventilation adjustment method and system for livestock breeding. The method comprises the following steps: carrying out all-weather gas state monitoring on a livestock and poultry farm through a sensor, and obtaining gas temperature and humidity and ammonia / carbon dioxide concentration time sequence change data; then, gas deposition adsorption effect quantification is carried out, and deposition thermal entropy increase effect data are obtained through deposition thermal entropy increase effect simulation calculation; and then, designing ventilation logic of the livestock and poultry farm based on the deposition heat entropy increase effect data, and generating ventilation logic data of the livestock and poultry farm. And finally, intelligent adjustment firmware design is carried out by utilizing the ventilation logic data of the livestock and poultry farm, the firmware is uploaded to the cloud platform, and intelligent ventilation adjustment is executed. The intelligent ventilation adjusting technology is optimized, so that the intelligent ventilation adjusting technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the field of intelligent ventilation regulation technology, and in particular to an intelligent ventilation regulation method and system for livestock and poultry farming. Background Art

[0002] The air quality inside livestock and poultry farms directly affects the growth rate, reproductive capacity and disease control efficiency of animals. Farms usually have problems such as high temperature, high humidity, high ammonia and carbon dioxide concentrations. These factors not only affect the growth environment of animals, but also lead to the spread of diseases and reduced breeding benefits. Therefore, how to effectively manage and control the ventilation environment of farms has become the key to improving livestock and poultry breeding benefits and animal welfare. In recent years, with the development of Internet of Things technology, sensor technology and intelligent control systems, intelligent breeding has gradually become a trend in the development of the industry. Through real-time monitoring of the breeding environment by sensors, it is possible to accurately obtain data such as gas composition, temperature and humidity in the farm, and realize precise control of the breeding environment through data analysis. The intelligent ventilation system can automatically adjust the operating status of the ventilation equipment according to real-time environmental data, achieve precise climate regulation, improve air quality, and enhance breeding benefits. However, the traditional ventilation adjustment method has the problem of inaccurate identification of the polluted gas structure in livestock and poultry farms, and the inability to quickly and accurately control ventilation. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent ventilation adjustment method and system for livestock and poultry farming to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a livestock and poultry farming intelligent ventilation adjustment method is provided, the method comprising the following steps: Step S1: Performing all-weather gas status monitoring on livestock and poultry farms through sensors to obtain all-weather gas status monitoring data; extracting the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas status monitoring data to obtain gas temperature and humidity time series change data and ammonia / carbon dioxide concentration time series change data respectively; Step S2: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series change data and the ammonia / carbon dioxide concentration time series change data to obtain the gas deposition adsorption effect quantification data; performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain the deposition heat entropy increase effect data; Step S3: performing ventilation logic design for livestock and poultry farms according to the quantitative data of gas deposition adsorption effect and the data of deposition thermal entropy increase effect, and obtaining ventilation logic data for livestock and poultry farms; Step S4: Design intelligent adjustment firmware based on the ventilation logic data of livestock and poultry farms to obtain intelligent adjustment firmware for ventilation of livestock and poultry farms, and send the intelligent adjustment firmware for ventilation of livestock and poultry farms to the cloud platform to execute intelligent ventilation adjustment for livestock and poultry farming.

[0005] Preferably, step S1 comprises the following steps: Step S11: monitoring the gas status of livestock and poultry farms around the clock through sensors to obtain all-weather gas status monitoring data; Step S12: Fill missing values ​​in the all-weather gas state monitoring data to obtain gas state monitoring filling data; Step S13: performing time series state analysis on the gas state monitoring filling data to obtain gas state monitoring time series state data; Step S14: extracting the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas state monitoring data based on the gas state monitoring time series state data, and obtaining the time series change data of gas temperature and humidity and the time series change data of ammonia / carbon dioxide concentration respectively.

[0006] Preferably, step S2 comprises the following steps: Step S21: Acquire livestock and poultry farm structural data; perform topological structure analysis on the livestock and poultry farm structural data to obtain livestock and poultry farm topological structure data; Step S22: performing all-weather natural ventilation structure analysis based on the livestock and poultry farm topological structure data to obtain all-weather natural ventilation structure data; Step S23: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series variation data and the ammonia / carbon dioxide concentration time series variation data according to the all-weather natural ventilation structure data to obtain gas deposition adsorption effect quantification data; Step S24: performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain deposition heat entropy increase effect data.

[0007] Preferably, step S23 includes the following steps: Step S231: performing ventilation driving force fluctuation analysis on all-weather natural ventilation structure data to obtain natural ventilation driving force fluctuation data; Step S232: performing vertical layer density calculation on the ammonia / carbon dioxide concentration time series variation data to obtain vertical layer density data of ammonia / carbon dioxide concentration; Step S233: performing vertical pressure gradient difference calculation on the ammonia / carbon dioxide concentration time series change data based on the ammonia / carbon dioxide concentration vertical layered density data to obtain vertical pressure gradient difference difference data; Step S234: estimating the gradient increment ratio of the gas temperature and humidity time series change data to obtain the temperature and humidity gradient increment ratio; Step S235: estimating the ammonia / carbon dioxide pressure potential energy action amount on the vertical pressure gradient difference differential data according to the temperature and humidity gradient increment ratio, and obtaining the ammonia / carbon dioxide pressure potential energy action data; Step S236: estimating the gas adsorption degree constraint based on the ammonia / carbon dioxide pressure potential energy action data and the gas temperature and humidity time series change data to obtain adsorption degree constraint data; Step S237: quantifying the gas deposition adsorption effect on the ammonia / carbon dioxide pressure potential energy data and the adsorption degree constraint data according to the natural ventilation driving force fluctuation data to obtain the gas deposition adsorption effect quantification data.

[0008] Preferably, step S236 includes the following steps: The molecular interaction force relationship is deduced from the ammonia / carbon dioxide pressure potential energy data to obtain the molecular interaction force relationship deduction data; Based on the molecular interaction force relationship deduction data and the gas temperature and humidity time series change data, the molecular adsorption efficiency fluctuation is evaluated to obtain the molecular adsorption efficiency fluctuation data; According to the gas temperature and humidity time series change data, the molecular adsorption efficiency fluctuation data is analyzed by the temperature and humidity-adsorption efficiency ratio to obtain the temperature and humidity-adsorption efficiency ratio; Based on the temperature and humidity-adsorption efficiency ratio, the molecular adsorption efficiency fluctuation data is sampled according to the adsorption efficiency normal distribution to obtain the adsorption efficiency normal distribution sampling data; The Langmuir equation is used to estimate the gas adsorption degree constraint of the adsorption efficiency normal distribution sampling data to obtain the adsorption degree constraint data.

[0009] Preferably, step S24 includes the following steps: Step S241: evaluating the deposition heat increment rate based on the quantified data of the gas deposition adsorption effect to obtain deposition heat increment rate data; Step S242: performing dynamic heat flow field energy distribution analysis on the gas deposition adsorption effect quantification data according to the deposition heat increment rate data to obtain dynamic heat flow field energy distribution data; Step S243: performing entropy value dynamic offset calculation on the dynamic heat flow field energy distribution data to obtain heat flow field entropy value dynamic offset data; Step S244: performing a simulation calculation of the deposition heat entropy increase effect based on the dynamic offset data of the thermal flow field entropy value to obtain deposition heat entropy increase effect data.

[0010] Preferably, step S3 comprises the following steps: Step S31: performing gas deposition quality evaluation on the gas deposition adsorption effect quantified data to obtain gas deposition quality data; Step S32: evaluating the gas deposition volume expansion based on the deposition thermal entropy increase effect data to obtain the gas deposition volume expansion data; Step S33: Performing ventilation logic design for livestock and poultry farms on the all-weather natural ventilation structure data according to the gas deposition mass data and the gas deposition volume expansion data to obtain ventilation logic data for livestock and poultry farms.

[0011] Preferably, step S33 includes the following steps: Step S331: performing expansion geometry analysis on the gas deposition volume expansion data to obtain gas deposition expansion geometry data; Step S332: performing geometric quality regional difference identification on the gas deposition expansion geometric shape data according to the gas deposition quality data to obtain geometric quality regional difference data; Step S333: reconstructing ventilation airflow paths between different regions of the all-weather natural ventilation structure data based on the geometric quality regional difference data to obtain ventilation airflow path reconstruction data; Step S334: iteratively learning the ventilation airflow path reconstruction data to obtain ventilation airflow path reconstruction iterative data; Step S335: Perform ventilation logic design for livestock and poultry farms according to the ventilation airflow path reconstruction iteration data to obtain ventilation logic data for livestock and poultry farms.

[0012] Preferably, step S333 includes the following steps: Obtain ventilation equipment control parameters; According to the regional difference data of geometric quality, the ventilation equipment control parameters and the all-weather natural ventilation structure data are matched between different regions to obtain the airflow velocity output data; According to the regional difference data of geometric quality, the wind direction output angles of ventilation equipment control parameters and all-weather natural ventilation structure data are matched between different regions to obtain wind direction output angle matching data; Based on the geometric quality regional difference data, wind direction output angle matching data and airflow velocity output data, ventilation output compensation is performed on the all-weather natural ventilation structure data to obtain ventilation output compensation data; The ventilation airflow paths between different areas are reconstructed according to the airflow velocity output data, the wind direction output angle matching data and the ventilation volume output compensation data to obtain the ventilation airflow path reconstruction data.

[0013] Preferably, the present invention further provides an intelligent ventilation and regulation system for livestock and poultry farming, which is used to execute the intelligent ventilation and regulation method for livestock and poultry farming as described above, and the intelligent ventilation and regulation system for livestock and poultry farming comprises: The environmental data acquisition module is used to monitor the gas status of livestock and poultry farms around the clock through sensors to obtain all-weather gas status monitoring data; extract the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas status monitoring data to obtain the time series change data of gas temperature and humidity and the time series change data of ammonia / carbon dioxide concentration respectively; The gas deposition analysis module is used to quantify the gas deposition adsorption effect on the gas temperature and humidity time series change data and the ammonia / carbon dioxide concentration time series change data to obtain the gas deposition adsorption effect quantification data; the gas deposition adsorption effect quantification data is used to simulate and calculate the deposition heat entropy increase effect to obtain the deposition heat entropy increase effect data; The ventilation logic design module is used to design ventilation logic for livestock and poultry farms based on the quantitative data of gas deposition adsorption effect and deposition heat entropy increase effect data, and obtain ventilation logic data for livestock and poultry farms; The intelligent adjustment firmware design module is used to design intelligent adjustment firmware based on the ventilation logic data of livestock and poultry farms, obtain the intelligent adjustment firmware for ventilation of livestock and poultry farms, and send the intelligent adjustment firmware for ventilation of livestock and poultry farms to the cloud platform to execute intelligent ventilation adjustment for livestock and poultry farming.

[0014] The beneficial effect of the present invention is that by monitoring the gas state around the clock through sensors in livestock and poultry farms, temperature and humidity and gas concentration data such as ammonia and carbon dioxide can be collected in real time. These data are extracted through time series changes to obtain gas temperature and humidity time series change data and ammonia / carbon dioxide concentration time series change data respectively. This process provides basic data support for subsequent analysis, so that the climate conditions and pollutant gas changes in the breeding environment can be accurately monitored, which helps to improve the refinement level of environmental management. After obtaining the temperature and humidity change and concentration change data of the gas, a quantitative analysis of the gas deposition and adsorption effect is performed to evaluate the deposition and adsorption characteristics of the gas in the farm under different conditions. Through the simulation calculation of the deposition heat entropy increase effect, the thermodynamic effects of these gases on the environment can be further analyzed, especially the changes in thermal energy during the deposition of the gas. This process helps to deeply understand the climate regulation mechanism of the farm, provide a theoretical basis for subsequent ventilation design, and optimize the breeding environment. Through the analysis of the quantitative data of the gas deposition adsorption effect and the deposition heat entropy increase effect data, the logical design of the ventilation system of the livestock and poultry farm can be carried out. This step involves optimizing the ventilation strategy according to the gas concentration, temperature and humidity changes and thermodynamic effects in the environment to achieve better air quality control and climate regulation. Through reasonable ventilation design, the accumulation of harmful gases can be effectively reduced, while maintaining appropriate temperature and humidity levels, ensuring the healthy growth of livestock and poultry and improving breeding efficiency. Based on the aforementioned ventilation logic data, an intelligent adjustment firmware is designed, which can automatically adjust the working state of the ventilation equipment according to the real-time gas monitoring data, thereby realizing the intelligent adjustment of the farm environment. These firmwares can be sent to the cloud platform, through which the ventilation system can be remotely managed and optimized in real time, and remote monitoring and adjustment of data can be realized. This process will further improve the level of intelligence in farm management, reduce manual intervention, and be able to adjust environmental parameters more accurately. Therefore, the present invention is an optimization treatment of a traditional intelligent ventilation adjustment method for livestock and poultry farming, which solves the problem that a traditional intelligent ventilation adjustment method for livestock and poultry farming has inaccurate identification of the polluted gas structure of livestock and poultry farms, and cannot quickly and accurately perform ventilation control, improves the accuracy of identifying the polluted gas structure of livestock and poultry farms, and improves the accuracy and ventilation efficiency of ventilation control. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the steps of an intelligent ventilation adjustment method for livestock and poultry farming; 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] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0017] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0018] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0019] To achieve this, please refer to Figures 1 to 3 , an intelligent ventilation adjustment method for livestock and poultry farming, the method comprising the following steps: Step S1: Performing all-weather gas status monitoring on livestock and poultry farms through sensors to obtain all-weather gas status monitoring data; extracting the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas status monitoring data to obtain gas temperature and humidity time series change data and ammonia / carbon dioxide concentration time series change data respectively; Step S2: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series change data and the ammonia / carbon dioxide concentration time series change data to obtain the gas deposition adsorption effect quantification data; performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain the deposition heat entropy increase effect data; Step S3: performing ventilation logic design for livestock and poultry farms according to the quantitative data of gas deposition adsorption effect and the data of deposition thermal entropy increase effect, and obtaining ventilation logic data for livestock and poultry farms; Step S4: Design intelligent adjustment firmware based on the ventilation logic data of livestock and poultry farms to obtain intelligent adjustment firmware for ventilation of livestock and poultry farms, and send the intelligent adjustment firmware for ventilation of livestock and poultry farms to the cloud platform to execute intelligent ventilation adjustment for livestock and poultry farming.

[0020] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of an intelligent ventilation adjustment method for livestock and poultry farming according to the present invention. In this example, the intelligent ventilation adjustment method for livestock and poultry farming includes the following steps: Step S1: Performing all-weather gas status monitoring on livestock and poultry farms through sensors to obtain all-weather gas status monitoring data; extracting the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas status monitoring data to obtain gas temperature and humidity time series change data and ammonia / carbon dioxide concentration time series change data respectively; In an embodiment of the present invention, a group of multifunctional gas sensors are first deployed in a livestock and poultry farm. These sensors have the functions of monitoring temperature, humidity, ammonia and carbon dioxide concentrations, and can continuously collect gas state data. This group of sensors adopts precise gas detection technology, in which the temperature and humidity sensors use capacitive or thermal conductivity principles to collect temperature and humidity data, while the ammonia and carbon dioxide concentration sensors use non-dispersive infrared technology (NDIR) or electrochemical sensors to detect gas concentrations. The monitoring data is transmitted in real time through the data acquisition unit to form all-weather gas state monitoring data. The gas state monitoring data includes time series data of four dimensions: temperature, humidity, ammonia concentration, and carbon dioxide concentration. For this data, missing value processing is first performed, and the missing data generated by sensor failure or signal interference is filled by linear interpolation method. Subsequently, the time series change analysis of temperature and humidity and ammonia / carbon dioxide concentration is performed respectively. The specific method is to extract the change trend of temperature, humidity and gas concentration every hour or every minute through the sliding window method, and these change trends are used as the characteristics of the time series data. The extraction of temperature and humidity time series data is performed by performing differential calculation on the temperature and humidity data at each time point to obtain the change rate of temperature and humidity. The extraction of the time series changes of ammonia and carbon dioxide concentrations is based on the continuous time window difference of the concentration data, the rate of concentration change is calculated, and the concentration change rate sequence at each moment is generated. These data serve as the basis for further analysis and processing, and can accurately reflect the dynamic changes of the gas environment in livestock and poultry farms.

[0021] Step S2: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series change data and the ammonia / carbon dioxide concentration time series change data to obtain the gas deposition adsorption effect quantification data; performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain the deposition heat entropy increase effect data; In the embodiment of the present invention, the quantification of the gas deposition adsorption effect is based on the analysis of the temperature and humidity time series data and the ammonia / carbon dioxide concentration time series data obtained in step S1. The core of this process is to quantify the gas adsorption and deposition process by combining the physical properties of gas deposition with the principle of fluid dynamics. In the implementation process, a dynamic simulation method based on gas molecule diffusion is used to calculate the influence of temperature and humidity and gas concentration on the gas deposition adsorption effect. By setting the air flow rate, temperature and humidity gradient and concentration difference, the gas molecule kinematic analysis is performed to obtain the degree of adsorption of gas deposited on the surface of different positions in the farm in different time periods. In the specific operation, the concentration gradient of ammonia and carbon dioxide is first calculated by the collected data, and the diffusion rate of the gas in the airflow is analyzed in combination with the temperature and humidity data. Then, based on the physical properties of gas diffusion and adsorption (such as adsorption constant, surface roughness, etc.), the interaction force between the gas and the surface of the object in the farm is comprehensively considered to obtain the quantitative data of the gas deposition adsorption effect. The simulation calculation of the deposition thermal entropy increase effect further considers the change of heat in the gas deposition process, especially the thermal effect generated in the gas adsorption process. According to the amount and energy change of gas deposition, the entropy increase theory of thermodynamics is used to calculate the change of thermal entropy generated by gas deposition. Specifically, by considering the temperature changes and the interaction forces between gas molecules during the gas deposition process, combined with the calculation of the dynamic shift of the entropy value, the deposition thermal entropy increase effect data is obtained.

[0022] Step S3: performing ventilation logic design for livestock and poultry farms according to the quantitative data of gas deposition adsorption effect and the data of deposition thermal entropy increase effect, and obtaining ventilation logic data for livestock and poultry farms; In an embodiment of the present invention, after obtaining the quantitative data of gas deposition adsorption effect and the data of deposition heat entropy increase effect, the ventilation logic design of the livestock and poultry farm is started. This design is based on the gas deposition effect and heat change, formulates the strategy of the ventilation system, and optimizes the air circulation and gas exchange efficiency. In the design process, the ventilation requirements of different areas of the farm are first analyzed by the gas deposition quality and thermal effect data. The calculation method based on fluid dynamics and heat transfer theory is adopted to simulate and optimize the air flow of the farm. Through detailed modeling of the farm structure (such as walls, roofs, vents, etc.), the airflow path, wind speed distribution and temperature and humidity changes in each area are calculated. The deposition heat entropy increase effect data is used as a reference to formulate the ventilation intensity and frequency of different areas to ensure that air circulation can effectively eliminate the impact of gas deposition on air quality. According to the gas deposition quality and thermal effect data, the ventilation path and wind speed are further adjusted. If the gas concentration in some areas is high or the deposition effect is strong, it is necessary to increase the ventilation intensity of the area to ensure that harmful gases are removed in time and fresh air is guided in. The final result of this step is to generate the ventilation logic data of the livestock and poultry farm, which includes the specific ventilation control strategy of each area.

[0023] Step S4: Design intelligent adjustment firmware based on the ventilation logic data of livestock and poultry farms to obtain intelligent adjustment firmware for ventilation of livestock and poultry farms, and send the intelligent adjustment firmware for ventilation of livestock and poultry farms to the cloud platform to execute intelligent ventilation adjustment for livestock and poultry farming.

[0024] In the embodiment of the present invention, based on the ventilation logic data in step S3, the design of intelligent adjustment firmware is carried out. The core of the firmware design is to automatically adjust the operating parameters of the ventilation system, including wind speed, wind direction and air volume, according to the real-time gas state data and ventilation demand in the farm. The design process adopts the hardware abstraction layer solution to enable the firmware to be compatible with various hardware devices (such as fans, exhaust devices, etc.) in the farm. In specific operation, the firmware dynamically adjusts the working state of the ventilation equipment by real-time monitoring of the data fed back by the gas sensor. When designing the intelligent adjustment firmware, the adjustment strategy is first determined, such as automatically increasing the wind speed or starting more ventilation equipment when the gas concentration exceeds the set threshold. Through the algorithm integrated in the firmware, a quick response is made at the moment of sensing the change in gas concentration. To ensure the efficient operation of the ventilation system, the firmware also includes equipment fault detection and adaptive adjustment functions, which can adjust the equipment parameters in real time to optimize the ventilation effect. After the design is completed, the intelligent adjustment firmware is uploaded to the cloud platform through wireless communication technology (such as Wi-Fi or LoRaWAN). The cloud platform receives and stores data from various sensors and devices in the farm, and can remotely adjust the ventilation system of the farm according to the feedback of the cloud algorithm. The cloud platform also has real-time monitoring capabilities, which can visualize the system status and allow farm managers to manually intervene and make adjustments.

[0025] Step S1 includes the following steps: Step S11: monitoring the gas status of livestock and poultry farms around the clock through sensors to obtain all-weather gas status monitoring data; Step S12: Fill missing values ​​in the all-weather gas state monitoring data to obtain gas state monitoring filling data; Step S13: performing time series state analysis on the gas state monitoring filling data to obtain gas state monitoring time series state data; Step S14: extracting the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas state monitoring data based on the gas state monitoring time series state data, and obtaining the time series change data of gas temperature and humidity and the time series change data of ammonia / carbon dioxide concentration respectively.

[0026] In an embodiment of the present invention, in a livestock and poultry farm, a series of gas sensors are precisely arranged to monitor the breeding environment around the clock. In specific implementation, the sensor selection is based on its stability and accuracy, including temperature and humidity sensors, ammonia concentration sensors and carbon dioxide concentration sensors. The temperature and humidity sensor adopts capacitive technology, which can provide high-precision temperature and humidity measurement, and is particularly suitable for humidity changes in a breeding environment. The monitoring of ammonia and carbon dioxide concentrations adopts non-dispersive infrared (NDIR) technology. This sensor has good selectivity and low cross sensitivity, and is suitable for continuous monitoring of harmful gas concentrations. The monitoring data is converted into a processable signal in real time through the analog / digital converter in the sensor, and transmitted to the data acquisition unit through the wireless module (such as Wi-Fi or LoRa) integrated in the sensor. The data acquisition unit is responsible for further processing and storage of sensor signals, and regularly uploads data to the cloud platform or local storage. The monitored data includes information such as temperature and humidity, ammonia concentration, carbon dioxide concentration, etc. at each moment, ensuring that the gas state changes in all time periods within 24 hours can be covered. The data includes an accurate timestamp to ensure that the time information of each data point is consistent with its corresponding gas state. Because the sensor is affected by environmental interference, hardware failure and other factors, there are missing values ​​in the all-weather gas state monitoring data. In order to ensure the accuracy of subsequent data analysis, these missing values ​​need to be filled. The specific steps are as follows: First, identify the missing values ​​in the data. These missing values ​​are usually expressed as NaN or blank values, marked as data loss. You can use the data exploration tool to scan each column (temperature and humidity, ammonia, carbon dioxide concentration, etc.) to find the missing values ​​in each time period. According to the characteristics of the data, adopt an appropriate filling strategy. For temperature and humidity data, linear interpolation is used for filling. The linear interpolation method calculates the filling value through the adjacent data points before and after to ensure that the continuity of the filled data is consistent with the trend. For ammonia and carbon dioxide concentration data, the Lagrange interpolation method is used. This method can use the trend of multiple surrounding points for interpolation to avoid the influence of a single neighboring value, which is particularly suitable for situations where the gas concentration fluctuates greatly. After filling, use data smoothing technology (such as sliding average) to test the filled data to ensure that the filled data is stable and consistent with the actual gas change trend. Normalize the gas state data after filling, and convert all data into a unified dimension range (such as between 0 and 1) to avoid gas data of different magnitudes affecting the analysis results. Perform periodic analysis on the data of each time period through the sliding window method. For example, set a time window (such as 10 minutes or 30 minutes) and calculate the average, maximum, minimum and standard deviation of the data in the window. The sliding window can be gradually moved forward in the data to extract the gas state characteristics in each time period. Analyze the periodic changes of gas concentration data through Fourier transform (FFT).Fourier transform can convert time series data into frequency domain, so as to extract the main periodic components in the data, which is crucial for understanding the fluctuation law of gas concentration in different time periods. Using peak detection algorithm (such as threshold-based method or local extreme value-based detection method), significant change points or peaks are identified from the time series data of temperature, humidity and gas concentration. This algorithm can help identify the moments when temperature and humidity change sharply or gas concentration fluctuates greatly, providing a basis for subsequent ventilation adjustment. The results of time series state analysis are organized into time series state data, which contains statistical characteristics and periodic components in each time period as a description of the trend of gas state change. Based on the temperature and humidity data in the time series state analysis, the rate of change of temperature and humidity is analyzed. The difference method is used to calculate the temperature and humidity change between each time point and the previous time point. The change rate data is calculated through the time window, and then the fluctuation trend and change rate of temperature and humidity are extracted. For ammonia and carbon dioxide concentration data, the first-order difference method is used to calculate the concentration change rate. By performing differential calculation on the gas concentration at each moment, the rate data of concentration change is obtained. In addition, the sliding window method can be combined to calculate the mean and standard deviation of concentration changes in order to further analyze the trend of concentration fluctuations. The temperature and humidity change and gas concentration change data for each period are organized into independent time-series change data sets. Each data set contains time, temperature and humidity change rate, ammonia and carbon dioxide concentration change rate, forming complete gas state change data. The temperature and humidity time-series change data and the ammonia / carbon dioxide concentration time-series change data will be saved as independent data tables, including the change rate and related statistical characteristics at each moment, providing a scientific basis for subsequent intelligent ventilation adjustment.

[0027] Step S2 includes the following steps: Step S21: Acquire livestock and poultry farm structural data; perform topological structure analysis on the livestock and poultry farm structural data to obtain livestock and poultry farm topological structure data; Step S22: performing all-weather natural ventilation structure analysis based on the livestock and poultry farm topological structure data to obtain all-weather natural ventilation structure data; Step S23: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series variation data and the ammonia / carbon dioxide concentration time series variation data according to the all-weather natural ventilation structure data to obtain gas deposition adsorption effect quantification data; Step S24: performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain deposition heat entropy increase effect data.

[0028] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: Acquire livestock and poultry farm structural data; perform topological structure analysis on the livestock and poultry farm structural data to obtain livestock and poultry farm topological structure data; In an embodiment of the present invention, all structural information of a livestock and poultry farm is collected through physical measurement and existing architectural drawings, including the area, floor height, roof shape, wall structure, size and distribution of windows and vents of the building. All data are entered into the data acquisition system through on-site investigation and digital processing of the original building blueprint. The value of each measurement point needs to be corrected by a high-precision laser rangefinder or a digital measuring tool to ensure that the collected data meets the precise standard. All collected structural data are standardized, and the units are unified into international standard units such as meters (m), square meters (㎡), and cubic meters (m³), and stored in a database. In order to improve the efficiency of subsequent data analysis, a structured storage method is used to classify and store the data into different categories such as rooms, vents, walls, and roofs. After the structural data is processed, a comprehensive data set containing the dimensions of each room, the distribution of ventilation facilities, and the air permeability of the wall is generated. The structural data is finally organized into a building model data set of a livestock and poultry farm, which contains key information such as the spatial dimensions of each area, the number and size of ventilation windows, and the air permeability of the wall, as the basic data for subsequent topological structure analysis.

[0029] Step S22: performing all-weather natural ventilation structure analysis based on the livestock and poultry farm topological structure data to obtain all-weather natural ventilation structure data; In the embodiment of the present invention, first, the size, position and layout of all vents (such as windows, ventilation windows, roof skylights, etc.) are determined according to the structural data of the livestock and poultry farm. According to the house structure of the farm, a vent distribution map is established, and the area of ​​each vent is calculated. The flow path and flow rate of indoor air are analyzed by calculation methods based on physical principles (such as the Bernoulli equation and the basic equation of fluid dynamics). The smoke experiment method (using a smoke machine to simulate air flow) and the wind speed sensor are used for field testing to evaluate the rate, flow rate and flow direction of air flow under natural ventilation conditions to ensure that the distribution and design of the vents meet actual needs. The meteorological data (such as temperature, humidity, wind speed and wind direction) of different time periods are input into the ventilation structure analysis model to simulate and analyze the natural ventilation effect under different climatic conditions. For example, when the temperature is high in summer, the air flow when the ventilation window is opened is evaluated; when the temperature is low in winter, the efficiency of the ventilation system is simulated to evaluate whether excessive heat loss will occur during the ventilation process. Finally, the all-weather natural ventilation structure data is obtained by calculation, including indicators such as the efficiency, air flow, and air exchange frequency of each vent. This dataset can describe in detail the air flow patterns and ventilation efficiency in the farm under different weather conditions, providing a scientific basis for subsequent intelligent ventilation adjustment.

[0030] Step S23: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series variation data and the ammonia / carbon dioxide concentration time series variation data according to the all-weather natural ventilation structure data to obtain gas deposition adsorption effect quantification data; In the embodiment of the present invention, based on the theory of interaction between gas molecules and solid surfaces, the Langmuir adsorption model is used to describe the adsorption phenomenon of gas. The model assumes that there is a certain adsorption equilibrium between gas molecules and surface molecules, and the gas concentration is proportional to the surface adsorption amount during the adsorption process. According to the time series change data of gas concentration, combined with the physical properties of each surface in the farm (such as adsorption coefficient, surface roughness, etc.), the amount of gas deposited on each surface at each moment is calculated. The specific steps include: according to the gas concentration data, the amount of gas adsorption at a certain moment is calculated, and the adsorption amount of each surface is accumulated to obtain the total amount of surface adsorption; since the gas concentration changes with time, its adsorption effect needs to be dynamically analyzed. A time-varying adsorption model (Langmuir adsorption model) is used to consider the fluctuation of gas concentration over time, and the gas deposition amount in different time periods is obtained. This model can more accurately reflect the impact of gas on the surface at different time points.

[0031] Step S24: performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain deposition heat entropy increase effect data.

[0032] In an embodiment of the present invention, the entropy increase principle in the second law of thermodynamics is used to calculate the thermal entropy increment of each surface during the gas deposition process through the adsorption and release process of gas on different surfaces. Specifically, when gas molecules undergo adsorption or desorption processes with the surface, the thermal entropy of the system will change, and this change is closely related to factors such as gas concentration, temperature, and adsorption capacity. The quantitative data of gas deposition adsorption effect is combined with environmental variables such as air temperature and humidity, and simulated and calculated using the heat balance equation. Through iterative calculation, the thermal entropy increase effect generated by surface gas deposition in each time period is obtained. Considering the changes in temperature, humidity and gas concentration in the farm, the deposition thermal entropy increase effect also changes with time. Therefore, a dynamic thermodynamic model (such as the finite difference method) is used to calculate the thermal entropy increment of each time period. Through this method, the thermal entropy change in the farm and the influence of the gas deposition effect on the indoor temperature at each time node can be accurately calculated. Through simulation calculation, the deposition thermal entropy increase effect data is finally obtained. This data set records the thermal entropy changes in the gas deposition process in each time period, and provides an optimized temperature control basis for subsequent ventilation system adjustment.

[0033] Step S23 includes the following steps: Step S231: performing ventilation driving force fluctuation analysis on all-weather natural ventilation structure data to obtain natural ventilation driving force fluctuation data; Step S232: performing vertical layer density calculation on the ammonia / carbon dioxide concentration time series variation data to obtain vertical layer density data of ammonia / carbon dioxide concentration; Step S233: performing vertical pressure gradient difference calculation on the ammonia / carbon dioxide concentration time series change data based on the ammonia / carbon dioxide concentration vertical layered density data to obtain vertical pressure gradient difference difference data; Step S234: estimating the gradient increment ratio of the gas temperature and humidity time series change data to obtain the temperature and humidity gradient increment ratio; Step S235: estimating the ammonia / carbon dioxide pressure potential energy action amount on the vertical pressure gradient difference differential data according to the temperature and humidity gradient increment ratio, and obtaining the ammonia / carbon dioxide pressure potential energy action data; Step S236: estimating the gas adsorption degree constraint based on the ammonia / carbon dioxide pressure potential energy action data and the gas temperature and humidity time series change data to obtain adsorption degree constraint data; Step S237: quantifying the gas deposition adsorption effect on the ammonia / carbon dioxide pressure potential energy data and the adsorption degree constraint data according to the natural ventilation driving force fluctuation data to obtain the gas deposition adsorption effect quantification data.

[0034] In the embodiment of the present invention, the ventilation driving force fluctuation analysis is performed on the all-weather natural ventilation structure data, the purpose of which is to study the fluctuation of the natural ventilation driving force in the livestock and poultry farm caused by changes in the external environment (such as wind speed, wind direction, air pressure, etc.). The specific implementation process includes the following steps: First, the all-weather natural ventilation structure data is obtained, and the data includes information such as air pressure, wind speed, wind direction, etc. in different time periods. Then, these data are differentially processed to extract the differences between each time point to determine the fluctuation amplitude of the natural ventilation driving force. By calculating these difference values, the driving force fluctuation amplitude at each moment is obtained, and recorded, and a set of natural ventilation driving force fluctuation data is obtained, which reflects the influence of wind speed fluctuation or air pressure fluctuation at different time points on the airflow movement in the livestock and poultry farm. The purpose of performing vertical layered density calculation on the time series change data of ammonia / carbon dioxide concentration is to evaluate the gas concentration distribution at different height positions, especially the distribution characteristics of ammonia or carbon dioxide concentration in different areas of the livestock and poultry farm. The specific implementation process is as follows: First, the time series change data of ammonia or carbon dioxide concentration is obtained. The data includes gas concentration information at different time points. On this basis, the farm is divided according to its vertical height (e.g. different levels from the ground to the roof), and the gas concentration of each layer is recorded in layers according to the measured values. Then, based on these layer data, the average concentration of each layer is calculated, and the density distribution is analyzed according to the gradient change of the concentration. The specific calculation method is: ;in, Indicates The gas concentration density of the layer, Indicates The gas concentration of the layer, Indicates The vertical height difference of the layer; based on the vertical stratified density data of ammonia / carbon dioxide concentration, the vertical pressure gradient difference difference calculation is performed on the ammonia / carbon dioxide concentration time series change data, the purpose is to analyze the pressure difference caused by the vertical distribution of the gas inside the farm. The implementation process of this step is as follows: First, according to the vertical stratified density data of ammonia or carbon dioxide concentration obtained from step S232, the pressure gradient between each layer is calculated. Assuming that the pressure of the gas is proportional to the concentration, the pressure gradient difference data between each layer of gas concentration can be obtained by differential calculation, thereby obtaining the pressure difference in the vertical direction. In this step, the temperature and humidity change amount of the gas temperature and humidity time series change data is first calculated. By calculating the temperature and humidity changes between time t and t-1, that is, the temperature increment ΔT=T(t)-T(t-1) and the humidity increment ΔH=H(t)-H(t-1), the temperature and humidity changes at each moment are obtained. Next, the temperature and humidity gradient increment ratio is calculated, which represents the ratio of the changes between temperature and humidity. The specific calculation formula is: temperature and humidity increment ratio = temperature increment divided by humidity increment. This ratio reflects the degree of influence of the temperature and humidity changes of the gas on the airflow and ventilation. Through these calculations, the temperature and humidity gradient increment ratio data is obtained, which can be used to estimate the pressure change of the gas and its influence on ventilation under different temperature and humidity change conditions. According to the temperature and humidity gradient increment ratio data obtained in step S234, enter this step, and use the temperature and humidity gradient to estimate the amount of action of the vertical pressure gradient difference of the gas. First, by calculating the vertical pressure difference of the gas concentration in each layer, the vertical pressure gradient difference data of the gas is obtained. Then, combined with the temperature and humidity gradient increment ratio, the pressure potential energy action of the vertical pressure difference on gases such as ammonia and carbon dioxide is estimated. The pressure potential energy action of the gas can be calculated by integration, and the formula is: ammonia / carbon dioxide pressure potential energy action = temperature and humidity gradient increment ratio multiplied by vertical pressure gradient difference. The calculation result represents the pressure potential energy generated by the gas in the vertical direction under the action of the temperature and humidity changes of the gas. The data is further used to analyze the changes in gas deposition and adsorption. Based on the ammonia / carbon dioxide pressure potential energy action data and the gas temperature and humidity time series change data obtained in the previous step, a constrained estimation of the gas adsorption degree is performed. First, by analyzing the concentration data of ammonia or carbon dioxide, combined with the pressure potential energy action, the degree of gas adsorption inside the farm is calculated. The degree of adsorption is affected by the gas concentration, the distribution of the gas in space, and the temperature and humidity gradient. Therefore, the adsorption constraint of the gas is estimated by combining these factors. Specifically, the adsorption constraint is estimated by the following relationship: Adsorption constraint = ammonia / carbon dioxide pressure potential energy action × temperature and humidity gradient. This constraint data indicates the amount of gas adsorption that occurs in the farm environment and the potential impact of the gas on the ventilation system.Based on the natural ventilation driving force fluctuation data obtained in step S231, combined with the ammonia / carbon dioxide pressure potential energy data and adsorption degree constraint data obtained in steps S235 and S236, the gas deposition adsorption effect is quantified. The natural ventilation driving force fluctuation data reflects the airflow changes in the external environment, which have an important influence on the deposition and adsorption of the gas. By combining these data, the deposition effect of the gas is quantified. The quantification of the gas deposition adsorption effect can be expressed as: gas deposition adsorption effect = ammonia / carbon dioxide pressure potential energy data × adsorption degree constraint data × ventilation driving force fluctuation. This result can provide the deposition and adsorption behavior of the gas inside the farm under certain natural ventilation conditions, and provide basic data for subsequent ventilation adjustment plans.

[0035] Step S236 includes the following steps: The molecular interaction force relationship is deduced from the ammonia / carbon dioxide pressure potential energy data to obtain the molecular interaction force relationship deduction data; Based on the molecular interaction force relationship deduction data and the gas temperature and humidity time series change data, the molecular adsorption efficiency fluctuation is evaluated to obtain the molecular adsorption efficiency fluctuation data; According to the gas temperature and humidity time series change data, the molecular adsorption efficiency fluctuation data is analyzed by the temperature and humidity-adsorption efficiency ratio to obtain the temperature and humidity-adsorption efficiency ratio; Based on the temperature and humidity-adsorption efficiency ratio, the molecular adsorption efficiency fluctuation data is sampled according to the adsorption efficiency normal distribution to obtain the adsorption efficiency normal distribution sampling data; The Langmuir equation is used to estimate the gas adsorption degree constraint of the adsorption efficiency normal distribution sampling data to obtain the adsorption degree constraint data.

[0036] In an embodiment of the present invention, the intermolecular interaction forces of ammonia and carbon dioxide are deduced. The intermolecular interaction forces mainly include van der Waals forces, electric field forces, etc. The deduction process is based on the distance between gas molecules, relative motion and their behavior patterns in a specific environment. It is assumed that under a specific temperature and humidity, the interaction forces between ammonia and carbon dioxide molecules follow the London force (i.e., the interaction force between the instantaneous dipole and the induced dipole) and the Coulomb force (the electric field force between charged molecules). According to the molecular characteristics of ammonia and carbon dioxide, the statistical physics method is used to deduce the interaction force model between them. The specific steps are as follows: by analyzing the hydrogen bonds and van der Waals force characteristics of ammonia and carbon dioxide molecules, the intermolecular interaction forces are calculated; according to the laws of gas molecular motion and pressure potential energy data, the intermolecular forces are deduced; by calculating the intermolecular interaction force strength of ammonia and carbon dioxide under different temperature and humidity conditions, the intermolecular interaction force relationship deduction data is obtained. Combined with the molecular interaction force relationship deduction data and the gas temperature and humidity time series change data, the molecular adsorption efficiency fluctuation is evaluated. First, the adsorption efficiency is affected by the interaction force between gas molecules and the ambient temperature and humidity. Therefore, the two can be combined to derive the volatility of molecular adsorption efficiency. The specific steps are as follows: According to the strength of the intermolecular interaction force, combined with the gas temperature and humidity time series change data, the relationship between molecular adsorption efficiency and environmental conditions is established; by calculating the adsorption efficiency fluctuation of the gas at each moment (that is, the response of the adsorption efficiency under temperature and humidity changes), the adsorption efficiency fluctuation data is obtained; according to the adsorption efficiency fluctuation data, the adsorption behavior of the gas under different environmental conditions is analyzed to reflect the dynamic adsorption efficiency of the gas. Based on the gas temperature and humidity time series change data and the molecular adsorption efficiency fluctuation data, the ratio between temperature and humidity and adsorption efficiency is analyzed. First, according to the influence of gas temperature and humidity changes on adsorption efficiency, the quantitative relationship between temperature and humidity and adsorption efficiency is analyzed. The specific steps are as follows: by analyzing the gas temperature and humidity time series change data and the molecular adsorption efficiency fluctuation data, the degree of influence of temperature and humidity changes on adsorption efficiency is identified; the proportional relationship between temperature and humidity changes and adsorption efficiency is calculated, that is, the adsorption efficiency change caused by each unit temperature and humidity change; by establishing a functional relationship between temperature and humidity and adsorption efficiency, the temperature and humidity-adsorption efficiency ratio data is obtained. The molecular adsorption efficiency fluctuation data is sampled in a normal distribution through the temperature and humidity-adsorption efficiency ratio data. First, according to the statistical characteristics of the adsorption efficiency fluctuation, it is assumed that it follows a normal distribution. On this basis, the temperature and humidity-adsorption efficiency ratio is used to perform normal distribution sampling to obtain sample data of gas adsorption efficiency. The specific steps are as follows: according to the mean and standard deviation of the adsorption efficiency fluctuation data, the parameters of the normal distribution are set; the adsorption efficiency fluctuation data is normalized through the temperature and humidity-adsorption efficiency ratio; the adsorption efficiency fluctuation data is sampled using the normal distribution formula to obtain adsorption efficiency data samples that conform to the normal distribution.This process can quantify the fluctuating characteristics of gas adsorption efficiency under different environments, and further provide data support for subsequent constraint estimation. The Langmuir equation is used to constrain the gas adsorption degree for the adsorption efficiency normal distribution sampling data. The Langmuir equation describes the adsorption phenomenon between gas molecules and solid surfaces. Here, the adsorption efficiency can be constrained by this equation. The specific steps are as follows: According to the Langmuir equation, the gas adsorption degree is related to factors such as gas pressure, adsorption surface characteristics, and interaction forces between adsorbed molecules. The adsorption amount is substituted into the Langmuir equation, and the adsorption constant is combined to estimate the constraint data of the adsorption degree. The gas adsorption amount at each moment is calculated using the temperature and humidity-adsorption efficiency ratio and the adsorption efficiency normal distribution sampling data; the adsorption amount is substituted into the Langmuir equation, and the adsorption constant is combined to estimate the constraint data of the adsorption degree.

[0037] Step S24 includes the following steps: Step S241: evaluating the deposition heat increment rate based on the quantified data of the gas deposition adsorption effect to obtain deposition heat increment rate data; Step S242: performing dynamic heat flow field energy distribution analysis on the gas deposition adsorption effect quantification data according to the deposition heat increment rate data to obtain dynamic heat flow field energy distribution data; Step S243: performing entropy value dynamic offset calculation on the dynamic heat flow field energy distribution data to obtain heat flow field entropy value dynamic offset data; Step S244: performing a simulation calculation of the deposition heat entropy increase effect based on the dynamic offset data of the thermal flow field entropy value to obtain deposition heat entropy increase effect data.

[0038] In the embodiment of the present invention, the quantitative data of gas deposition adsorption effect is used to evaluate the deposition heat increment rate. The deposition heat increment rate reflects the change of the heat generated by gas molecules during the deposition process over time. According to the adsorption heat effect of the gas on the surface and the adsorption amount during the deposition process, the basic principles of thermodynamics are used for estimation. The specific steps are as follows: using the obtained quantitative data of gas deposition adsorption effect, the heat generated in the adsorption process per unit time is determined. The deposition heat is generated by the interaction between the gas molecules and the solid surface, which can be inferred from the change of the adsorption isotherm and the adsorption amount; by integrating the gas deposition effect in different time periods, the total amount of deposition heat is obtained, and the heat increment rate per unit time is further calculated; these data are combined with the actual measured ambient temperature, humidity and other conditions, and the influence of these conditions on the deposition heat increment rate is taken into account to obtain the deposition heat increment rate data. Based on the deposition heat increment rate data obtained in the previous step, the gas deposition adsorption effect quantitative data is subjected to the energy distribution analysis of the dynamic thermal flow field. The energy distribution of the thermal flow field reflects how the heat caused by gas deposition is distributed and propagated within a certain spatial range. The specific implementation steps are as follows: the deposition heat increment rate data is combined with the gas deposition adsorption effect quantitative data to obtain the heat distribution in different areas. According to the heat conduction equation, the energy distribution of the heat flow field can be inferred by the change in heat flux density; the energy distribution model of the heat flow field is established based on the space coordinates and time variables using the energy equation of the heat flow field. At this time, considering the movement of gas molecules, the degree of deposition and the heat exchange between them and the solid surface, the heat distribution at different positions is calculated using a mathematical model; according to the time step, the heat distribution at each moment in the heat flow field is output as dynamic heat flow field energy distribution data. The dynamic offset data of the entropy value of the heat flow field is obtained by calculating the dynamic offset of the entropy value of the dynamic heat flow field energy distribution data. Entropy is an indicator of the disorder of the system in thermodynamics, and its dynamic offset reflects the uncertainty or disorder change in the energy transfer process in the heat flow field. The specific steps are as follows: According to the second law of thermodynamics, the change of entropy value is closely related to the transfer of heat, the distribution of energy and the disorder of the system. The initial value of entropy value is calculated by combining the dynamic heat flow field energy distribution data through the entropy value formula; as time goes by, the entropy value will change dynamically due to the change of heat transfer and adsorption effect. By calculating the energy distribution of the thermal flow field moment by moment, the entropy value change at each moment is obtained; the change in entropy value is associated with the characteristics of time, space and gas deposition to obtain the dynamic offset data of the thermal flow field entropy value. Based on the dynamic offset data of the thermal flow field entropy value obtained in the previous step, a simulation calculation of the deposition thermal entropy increase effect is performed. The thermal entropy increase effect refers to the effect of increasing the entropy value in the system due to the influence of heat transfer and adsorption processes during the gas deposition process. The specific steps are as follows: According to the dynamic offset data of the entropy value of the thermal flow field, the entropy increase trend during the gas deposition process is analyzed.Thermodynamic formulas are used to calculate the increase in system entropy during gas molecule adsorption and heat conduction. Combined with the influence of environmental conditions such as temperature and humidity on the entropy increase effect, mathematical modeling is used to predict the change in entropy under different deposition conditions. During the simulation calculation, the entropy growth rate and system stability need to be considered. The deposition thermal entropy increase effect data are output to reflect the increase in entropy during gas deposition and its effect on the thermal flow field.

[0039] Step S3 includes the following steps: Step S31: performing gas deposition quality evaluation on the gas deposition adsorption effect quantified data to obtain gas deposition quality data; Step S32: evaluating the gas deposition volume expansion based on the deposition thermal entropy increase effect data to obtain the gas deposition volume expansion data; Step S33: Performing ventilation logic design for livestock and poultry farms on the all-weather natural ventilation structure data according to the gas deposition mass data and the gas deposition volume expansion data to obtain ventilation logic data for livestock and poultry farms.

[0040] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: performing gas deposition quality evaluation on the gas deposition adsorption effect quantified data to obtain gas deposition quality data; In an embodiment of the present invention, the gas deposition quality is evaluated based on the quantitative data of the gas deposition adsorption effect. The gas deposition quality mainly refers to the amount of gas adsorbed on the solid surface, and the influence of the thermal effect of this adsorption process on the system quality. The specific operation steps are as follows: through the quantitative data of the gas deposition adsorption effect, first determine the heat change and adsorption amount of each gas molecule in the adsorption process. Use standard adsorption isotherms (such as Langmuir isotherms or BET isotherms) to calculate the maximum adsorption amount of gas molecules under different conditions; on this basis, combined with environmental factors such as gas temperature, humidity, and pressure, the mass change per unit gas deposition process is calculated. Since the thermal effect in the gas deposition process has a certain influence on the system quality, the thermal expansion effect of the gas molecules in the adsorption process should be considered to further calculate the change in mass during the deposition process; combined with the heat generated in the adsorption process and the adsorption amount, the basic principles of thermodynamics are used for quality evaluation; finally, the gas deposition quality data obtained by the above calculation can be used for subsequent gas deposition volume expansion evaluation and ventilation system design.

[0041] Step S32: evaluating the gas deposition volume expansion based on the deposition thermal entropy increase effect data to obtain the gas deposition volume expansion data; In an embodiment of the present invention, the expansion effect of the gas deposition volume is evaluated based on the deposition thermal entropy increase effect data. Due to temperature changes and pressure changes during the gas deposition process, the gas volume will expand, so it is necessary to accurately evaluate the volume expansion. The specific operating steps are as follows: using the deposition thermal entropy increase effect data, analyze the change in thermal entropy of the gas during the deposition process. Since the thermal entropy increase effect is usually accompanied by an increase in temperature and an expansion of volume, it is necessary to deduce the change in gas volume in combination with thermodynamic relations; the ideal gas state equation is used to describe the volume change of the gas during the deposition process. Based on the changes in temperature and pressure during the gas deposition process, the expansion of the gas volume is calculated. The expansion amount can be estimated by the proportional relationship of the volume change. The volume expansion data of different gases under different deposition conditions are comprehensively analyzed to obtain the gas deposition volume expansion data, which provides a basis for the subsequent ventilation design of livestock and poultry farms.

[0042] Step S33: Performing ventilation logic design for livestock and poultry farms on the all-weather natural ventilation structure data according to the gas deposition mass data and the gas deposition volume expansion data to obtain ventilation logic data for livestock and poultry farms.

[0043] In an embodiment of the present invention, the ventilation logic design of livestock and poultry farms is performed on the all-weather natural ventilation structure data based on the gas deposition quality data and the gas deposition volume expansion data. The ventilation design needs to adjust the working mode of the ventilation system according to the impact of the gas deposition process on the environment to ensure air circulation and temperature and humidity control. The specific operation steps are as follows: First, analyze the gas accumulation in different areas based on the gas deposition quality data. In livestock and poultry farms, the quality of gas deposition will affect the concentration of harmful gases such as ammonia and carbon dioxide in the air, thereby affecting the demand for the ventilation system; secondly, combined with the gas deposition volume expansion data, the air flow changes caused by the gas volume expansion are calculated. During the deposition process, the expansion of the gas volume will cause changes in air flow, so it is necessary to adjust the ventilation volume to avoid uneven ventilation caused by changes in air density; based on the above two data, combined with the all-weather natural ventilation structure data, a reasonable ventilation logic is designed. The design of the ventilation system includes aspects such as air flow direction, vent setting, and wind speed adjustment. By adjusting the opening of each air vent, the operation mode of the fan and the ventilation cycle, the gas exchange and temperature and humidity regulation in the farm can be optimized; finally, according to the output parameters of the ventilation design, a specific ventilation strategy is formulated, including how to adjust the ventilation strategy according to seasonal changes, external environmental conditions and other factors, and how to adjust the working status of the ventilation system through real-time monitoring to obtain the ventilation logic data of livestock and poultry farms.

[0044] Step S33 includes the following steps: Step S331: performing expansion geometry analysis on the gas deposition volume expansion data to obtain gas deposition expansion geometry data; Step S332: performing geometric quality regional difference identification on the gas deposition expansion geometric shape data according to the gas deposition quality data to obtain geometric quality regional difference data; Step S333: reconstructing ventilation airflow paths between different regions of the all-weather natural ventilation structure data based on the geometric quality regional difference data to obtain ventilation airflow path reconstruction data; Step S334: iteratively learning the ventilation airflow path reconstruction data to obtain ventilation airflow path reconstruction iterative data; Step S335: Perform ventilation logic design for livestock and poultry farms according to the ventilation airflow path reconstruction iteration data to obtain ventilation logic data for livestock and poultry farms.

[0045] In the embodiment of the present invention, the geometric morphology analysis of the gas deposition volume expansion data is first performed to understand the geometric characteristics of the gas volume expansion under different conditions. The expansion of gas deposition is usually caused by changes in temperature and pressure, and the expansion mode of the gas is closely related to factors such as its deposition position, deposition time, and gas type. Through the geometric analysis of the volume expansion data, guidance can be provided for the design of the ventilation path. The specific implementation steps are: first, the expansion data during the gas deposition process is collected, and its change law in different time periods and under different environmental conditions is analyzed. Through mathematical modeling, using thermodynamic equations and basic principles of fluid mechanics, combined with the theory of gas expansion, a geometric morphology analysis model for gas expansion is established. Based on this model, the gas expansion data is spatially analyzed, and the flow field changes during gas expansion are considered to obtain the geometric morphology data of gas deposition expansion. This data includes the spatial distribution of gas expansion, the expansion rate, and the volume changes in different regions during the expansion process. Based on the combination of gas deposition mass data and expansion geometric morphology data, regional differences are identified. The deposition quality of different regions in the gas deposition process is different, so the expansion geometry after gas deposition will also be different in different regions. By comparing the gas deposition mass data with the expansion geometry data, the differences in different regions are identified. First, the spatial distribution information of gas deposition mass data is compared with the expansion geometry data to find the relationship between the area with higher deposition mass and the area with larger expansion volume. Specifically, different quality areas are divided by cluster analysis of deposition mass data, and the volume expansion of different areas is analyzed in combination with the expansion geometry data. This can be achieved through differential analysis in a two-dimensional or three-dimensional coordinate system. Finally, the geometric quality regional difference data is obtained, which reflects the relationship between the quality and expansion morphology of each area, providing a basis for the design of subsequent ventilation airflow paths. Based on the geometric quality regional difference data, the airflow path of the all-weather natural ventilation structure data is reconstructed. The geometric quality regional difference data obtained by the above steps can accurately identify the differences in airflow in different areas of the livestock and poultry farm. Based on these differences, the ventilation airflow path is reconstructed to ensure that the airflow is evenly distributed throughout the breeding environment. The specific steps include: first, analyzing the natural ventilation structure data of the livestock and poultry farm to understand the airflow direction and wind speed distribution in the current ventilation structure. Then, combined with the geometric quality regional difference data, identify areas where airflow is blocked or the flow rate is uneven. These areas usually cause gas accumulation and affect the air quality in the farm. Based on these analysis results, the airflow path is redesigned to ensure that the airflow can evenly cover the entire breeding area. The specific implementation method includes adjusting the vents and fans to change the direction and speed of the airflow to ensure smooth air flow between different areas and achieve the best ventilation effect. The ventilation airflow path reconstruction data obtained in the previous step is iteratively learned to optimize the design of the ventilation path.The reconstruction of ventilation airflow paths will be affected by many factors, such as climate change, interference with internal air flow, etc., so it is necessary to continuously optimize the airflow path through iterative learning. The implementation method is as follows: First, use a simulation calculation method based on airflow dynamics to calculate the airflow distribution of the ventilation system under different environmental conditions. According to the preliminary airflow path reconstruction data, the airflow path and wind speed are continuously adjusted through the simulation system to observe the trend and effect of airflow changes. After each adjustment, the quality of the airflow flow is evaluated, and the evaluation results are used as the basis for the next adjustment for iterative updates. This process continues until the optimal airflow state is reached, that is, the distribution of airflow can not only ensure the efficiency of air exchange, but also avoid gas retention and accumulation. Through multiple iterative learning, the iterative data of ventilation airflow path reconstruction are finally obtained, which can provide a theoretical basis for the actual ventilation system adjustment. Based on the iterative data of ventilation airflow path reconstruction obtained in the previous step, the ventilation logic design of livestock and poultry farms is carried out. The ventilation logic design is to formulate a specific ventilation strategy based on the distribution and flow mode of airflow to ensure the effective exchange of gas and the appropriate temperature and humidity in the farm. The specific implementation methods include: first, analyzing the iterative data of ventilation airflow path reconstruction to understand the airflow distribution, wind speed and flow direction in each area. On this basis, design a reasonable ventilation strategy. For example, according to the changes in the external environment, determine the start and shutdown timing of the fan, reasonably adjust the wind speed, and ensure that the airflow between different areas is not hindered; secondly, combine the building structure and use function of the farm to determine the opening of the vents and the setting of the air duct. Finally, formulate an automated control logic to automatically adjust the working state of the ventilation system by real-time monitoring of air quality and temperature and humidity. This process ensures that the air quality and environmental conditions in the livestock and poultry farm are always in the best state through the cooperation of precise control algorithms and sensors. Finally, through these designs, the ventilation logic data of livestock and poultry farms is obtained, providing a detailed operation plan for actual operation.

[0046] Step S333 includes the following steps: Obtain ventilation equipment control parameters; According to the regional difference data of geometric quality, the ventilation equipment control parameters and the all-weather natural ventilation structure data are matched between different regions to obtain the airflow velocity output data; According to the regional difference data of geometric quality, the wind direction output angles of ventilation equipment control parameters and all-weather natural ventilation structure data are matched between different regions to obtain wind direction output angle matching data; Based on the geometric quality regional difference data, wind direction output angle matching data and airflow velocity output data, ventilation output compensation is performed on the all-weather natural ventilation structure data to obtain ventilation output compensation data; The ventilation airflow paths between different areas are reconstructed according to the airflow velocity output data, the wind direction output angle matching data and the ventilation volume output compensation data to obtain the ventilation airflow path reconstruction data.

[0047] In an embodiment of the present invention, control parameters related to ventilation equipment are first obtained. Control parameters generally include fan speed, air volume, air pressure, airflow direction, start and shut down time, etc. These parameters determine the working state of ventilation equipment, thereby affecting the flow and distribution of airflow. The way to obtain these parameters includes extracting data from the existing equipment control system, or collecting the operating state data of the equipment in real time through sensors and automatic control devices. According to different types of ventilation equipment, corresponding control parameters are selected for analysis. These parameters play a core role in the design of the entire ventilation system because they directly affect the output characteristics of the airflow and the final air quality. Through data acquisition and real-time monitoring, it is ensured that the equipment control parameters reflect the current actual working state of the equipment so as to accurately match them in the subsequent airflow path design. The airflow velocity is output matched to ensure that the airflow can flow smoothly between different areas and maintain an appropriate velocity distribution. According to the geometric quality regional difference data, the airflow requirements of different areas are first identified, including the requirements of flow velocity and ventilation volume. By combining these requirements with the ventilation equipment control parameters (such as fan speed and wind pressure, etc.), the equipment is adjusted to ensure that the output of the airflow in different areas reaches the expected flow velocity. In the specific implementation, the control equations in fluid mechanics are used, combined with the physical characteristics of the equipment (such as the power and pressure output characteristics of the fan), to dynamically calculate the airflow velocity. According to these calculation results, the airflow velocity output data of different areas are matched, which will serve as the basis for the subsequent adjustment of wind direction and air volume to ensure that the airflow of the entire farm is balanced in each area. By analyzing the regional difference data of geometric quality, the ventilation needs in different areas are determined, and the wind direction output of the ventilation equipment is further matched. First, based on the data of gas deposition quality, deposition expansion, etc., the airflow flow characteristics and wind speed distribution in different areas are identified. On this basis, by combining the fan control parameters (such as fan angle adjustment control) with the natural ventilation structure data, it is analyzed how the wind direction of the fan should be adjusted in different areas to achieve the best airflow distribution. According to the geometric differences in each area, the wind direction output angle is adjusted so that the airflow can flow evenly in each area and effectively combine with other airflow paths. When realizing wind direction matching, the wind direction vector analysis in fluid mechanics is used to calculate the adjustment of the fan blade angle in different areas, and obtain the wind direction output angle matching data for each area. These data provide the necessary wind direction information for subsequent ventilation compensation and airflow path reconstruction. By integrating the above data, the ventilation output is compensated to ensure the uniformity of ventilation in each area. The key to ventilation compensation is to reasonably adjust the output power and wind speed of the fan so that the airflow in different areas meets the predetermined requirements.First, the regional difference data of geometric quality are analyzed to determine the ventilation requirements of each area (such as air flow, ventilation times, etc.), and then the wind direction output angle matching data is combined to ensure that the airflow can flow in the expected direction in each area. Then, according to the airflow velocity output data, evaluate whether the airflow in each area reaches the target value. If the airflow in some areas is insufficient, the wind speed or number of fans is adjusted to compensate for this deficiency to ensure the overall efficiency of the ventilation system. During the compensation process, the basic theory of airflow dynamics is used, combined with the output characteristics of each fan, to calculate and adjust the working parameters of the ventilation equipment to achieve precise control of the ventilation volume. Finally, the ventilation volume output compensation data is obtained, which can effectively ensure that the ventilation volume in each area of ​​the farm meets the design standard. Based on the airflow velocity output data, wind direction output angle matching data and ventilation volume output compensation data obtained in the above steps, the ventilation airflow path is reconstructed. First, the airflow velocity output data and wind direction output angle matching data are used to analyze the flow direction and speed of the airflow in each area, and the optimal path of the airflow is determined in combination with the natural ventilation structure data. By simulating and optimizing the ventilation path, we ensure that the airflow can pass smoothly through each area of ​​the farm and avoid air stagnation or dead corners in the process. When reconstructing the airflow path, the optimal flow path of the airflow in each area is calculated based on parameters such as wind speed, wind pressure, and airflow direction through fluid mechanics calculation formulas. Finally, according to the output compensation data of the ventilation volume, it is ensured that the reconstructed airflow path meets the overall ventilation needs and maintains appropriate air flow and temperature and humidity in each area. The reconstructed airflow path will provide a detailed operation plan for the ventilation system in the farm to ensure that the airflow path can be adaptively adjusted under different environmental conditions to maintain good air quality and ventilation effects.

[0048] The present invention also provides an intelligent ventilation and regulation system for livestock and poultry farming, which is used to execute the intelligent ventilation and regulation method for livestock and poultry farming as described above. The intelligent ventilation and regulation system for livestock and poultry farming comprises: The environmental data acquisition module is used to monitor the gas status of livestock and poultry farms around the clock through sensors to obtain all-weather gas status monitoring data; extract the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas status monitoring data to obtain the time series change data of gas temperature and humidity and the time series change data of ammonia / carbon dioxide concentration respectively; The gas deposition analysis module is used to quantify the gas deposition adsorption effect on the gas temperature and humidity time series change data and the ammonia / carbon dioxide concentration time series change data to obtain the gas deposition adsorption effect quantification data; the gas deposition adsorption effect quantification data is used to simulate and calculate the deposition heat entropy increase effect to obtain the deposition heat entropy increase effect data; The ventilation logic design module is used to design ventilation logic for livestock and poultry farms based on the quantitative data of gas deposition adsorption effect and deposition heat entropy increase effect data, and obtain ventilation logic data for livestock and poultry farms; The intelligent adjustment firmware design module is used to design intelligent adjustment firmware based on the ventilation logic data of livestock and poultry farms, obtain the intelligent adjustment firmware for ventilation of livestock and poultry farms, and send the intelligent adjustment firmware for ventilation of livestock and poultry farms to the cloud platform to execute intelligent ventilation adjustment for livestock and poultry farming.

[0049] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0050] 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. An intelligent ventilation adjustment method for livestock and poultry breeding, characterized in that: The following steps are involved: Step S1: Performing all-weather gas status monitoring on livestock and poultry farms through sensors to obtain all-weather gas status monitoring data; extracting the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas status monitoring data to obtain gas temperature and humidity time series change data and ammonia / carbon dioxide concentration time series change data respectively; Step S2: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series change data and the ammonia / carbon dioxide concentration time series change data to obtain the gas deposition adsorption effect quantification data; performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain the deposition heat entropy increase effect data; Step S3: performing ventilation logic design for livestock and poultry farms according to the quantitative data of gas deposition adsorption effect and the data of deposition thermal entropy increase effect, and obtaining ventilation logic data for livestock and poultry farms; Step S4: Design intelligent adjustment firmware based on the ventilation logic data of livestock and poultry farms to obtain intelligent adjustment firmware for ventilation of livestock and poultry farms, and send the intelligent adjustment firmware for ventilation of livestock and poultry farms to the cloud platform to execute intelligent ventilation adjustment for livestock and poultry farming.

2. The intelligent ventilation adjustment method for livestock and poultry farming according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: monitoring the gas status of livestock and poultry farms around the clock through sensors to obtain all-weather gas status monitoring data; Step S12: Fill missing values ​​in the all-weather gas state monitoring data to obtain gas state monitoring filling data; Step S13: performing time series state analysis on the gas state monitoring filling data to obtain gas state monitoring time series state data; Step S14: extracting the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas state monitoring data based on the gas state monitoring time series state data, and obtaining the time series change data of gas temperature and humidity and the time series change data of ammonia / carbon dioxide concentration respectively.

3. The intelligent ventilation adjustment method for livestock and poultry farming according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Acquire livestock and poultry farm structural data; perform topological structure analysis on the livestock and poultry farm structural data to obtain livestock and poultry farm topological structure data; Step S22: performing all-weather natural ventilation structure analysis based on the livestock and poultry farm topological structure data to obtain all-weather natural ventilation structure data; Step S23: quantifying the gas deposition adsorption effect on the gas temperature and humidity time series variation data and the ammonia / carbon dioxide concentration time series variation data according to the all-weather natural ventilation structure data to obtain gas deposition adsorption effect quantification data; Step S24: performing deposition heat entropy increase effect simulation calculation on the gas deposition adsorption effect quantification data to obtain deposition heat entropy increase effect data.

4. The intelligent ventilation adjustment method for livestock and poultry farming according to claim 3 is characterized in that: Step S23 includes the following steps: Step S231: performing ventilation driving force fluctuation analysis on all-weather natural ventilation structure data to obtain natural ventilation driving force fluctuation data; Step S232: performing vertical layer density calculation on the ammonia / carbon dioxide concentration time series variation data to obtain vertical layer density data of ammonia / carbon dioxide concentration; Step S233: performing vertical pressure gradient difference calculation on the ammonia / carbon dioxide concentration time series change data based on the ammonia / carbon dioxide concentration vertical layered density data to obtain vertical pressure gradient difference difference data; Step S234: estimating the gradient increment ratio of the gas temperature and humidity time series change data to obtain the temperature and humidity gradient increment ratio; Step S235: estimating the ammonia / carbon dioxide pressure potential energy action amount on the vertical pressure gradient difference differential data according to the temperature and humidity gradient increment ratio, and obtaining the ammonia / carbon dioxide pressure potential energy action data; Step S236: estimating the gas adsorption degree constraint based on the ammonia / carbon dioxide pressure potential energy action data and the gas temperature and humidity time series change data to obtain adsorption degree constraint data; Step S237: quantifying the gas deposition adsorption effect on the ammonia / carbon dioxide pressure potential energy data and the adsorption degree constraint data according to the natural ventilation driving force fluctuation data to obtain the gas deposition adsorption effect quantification data.

5. The intelligent ventilation adjustment method for livestock and poultry breeding according to claim 4 is characterized in that: Step S236 includes the following steps: The molecular interaction force relationship is deduced from the ammonia / carbon dioxide pressure potential energy data to obtain the molecular interaction force relationship deduction data; Based on the molecular interaction force relationship deduction data and the gas temperature and humidity time series change data, the molecular adsorption efficiency fluctuation is evaluated to obtain the molecular adsorption efficiency fluctuation data; According to the gas temperature and humidity time series change data, the molecular adsorption efficiency fluctuation data is analyzed by the temperature and humidity-adsorption efficiency ratio to obtain the temperature and humidity-adsorption efficiency ratio; Based on the temperature and humidity-adsorption efficiency ratio, the molecular adsorption efficiency fluctuation data is sampled according to the adsorption efficiency normal distribution to obtain the adsorption efficiency normal distribution sampling data; The Langmuir equation is used to estimate the gas adsorption degree constraint of the adsorption efficiency normal distribution sampling data to obtain the adsorption degree constraint data.

6. The intelligent ventilation adjustment method for livestock and poultry farming according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: evaluating the deposition heat increment rate based on the quantified data of the gas deposition adsorption effect to obtain deposition heat increment rate data; Step S242: performing dynamic heat flow field energy distribution analysis on the gas deposition adsorption effect quantification data according to the deposition heat increment rate data to obtain dynamic heat flow field energy distribution data; Step S243: performing entropy value dynamic offset calculation on the dynamic heat flow field energy distribution data to obtain heat flow field entropy value dynamic offset data; Step S244: performing a simulation calculation of the deposition heat entropy increase effect based on the dynamic offset data of the thermal flow field entropy value to obtain deposition heat entropy increase effect data.

7. The intelligent ventilation adjustment method for livestock and poultry farming according to claim 3 is characterized in that: Step S3 includes the following steps: Step S31: performing gas deposition quality evaluation on the gas deposition adsorption effect quantified data to obtain gas deposition quality data; Step S32: evaluating the gas deposition volume expansion based on the deposition thermal entropy increase effect data to obtain the gas deposition volume expansion data; Step S33: Performing ventilation logic design for livestock and poultry farms on the all-weather natural ventilation structure data according to the gas deposition mass data and the gas deposition volume expansion data to obtain ventilation logic data for livestock and poultry farms.

8. The intelligent ventilation adjustment method for livestock and poultry farming according to claim 7, characterized in that: Step S33 includes the following steps: Step S331: performing expansion geometry analysis on the gas deposition volume expansion data to obtain gas deposition expansion geometry data; Step S332: performing geometric quality regional difference identification on the gas deposition expansion geometric shape data according to the gas deposition quality data to obtain geometric quality regional difference data; Step S333: reconstructing ventilation airflow paths between different regions of the all-weather natural ventilation structure data based on the geometric quality regional difference data to obtain ventilation airflow path reconstruction data; Step S334: iteratively learning the ventilation airflow path reconstruction data to obtain ventilation airflow path reconstruction iterative data; Step S335: Perform ventilation logic design for livestock and poultry farms according to the ventilation airflow path reconstruction iteration data to obtain ventilation logic data for livestock and poultry farms.

9. The intelligent ventilation adjustment method for livestock and poultry farming according to claim 7, characterized in that: Step S333 includes the following steps: Obtain ventilation equipment control parameters; According to the regional difference data of geometric quality, the ventilation equipment control parameters and the all-weather natural ventilation structure data are matched between different regions to obtain the airflow velocity output data; According to the regional difference data of geometric quality, the wind direction output angles of ventilation equipment control parameters and all-weather natural ventilation structure data are matched between different regions to obtain wind direction output angle matching data; Based on the geometric quality regional difference data, wind direction output angle matching data and airflow velocity output data, ventilation output compensation is performed on the all-weather natural ventilation structure data to obtain ventilation output compensation data; The ventilation airflow paths between different areas are reconstructed according to the airflow velocity output data, the wind direction output angle matching data and the ventilation volume output compensation data to obtain the ventilation airflow path reconstruction data.

10. An intelligent ventilation and adjustment system for livestock and poultry breeding, characterized in that: Used to execute the intelligent ventilation and regulation method for livestock and poultry farming according to claim 1, the intelligent ventilation and regulation system for livestock and poultry farming comprises: The environmental data acquisition module is used to monitor the gas status of livestock and poultry farms around the clock through sensors to obtain all-weather gas status monitoring data; extract the time series changes of temperature and humidity and ammonia / carbon dioxide concentration from the all-weather gas status monitoring data to obtain the time series change data of gas temperature and humidity and the time series change data of ammonia / carbon dioxide concentration respectively; The gas deposition analysis module is used to quantify the gas deposition adsorption effect on the gas temperature and humidity time series change data and the ammonia / carbon dioxide concentration time series change data to obtain the gas deposition adsorption effect quantification data; the gas deposition adsorption effect quantification data is used to simulate and calculate the deposition heat entropy increase effect to obtain the deposition heat entropy increase effect data; The ventilation logic design module is used to design ventilation logic for livestock and poultry farms based on the quantitative data of gas deposition adsorption effect and deposition heat entropy increase effect data, and obtain ventilation logic data for livestock and poultry farms; The intelligent adjustment firmware design module is used to design intelligent adjustment firmware based on the ventilation logic data of livestock and poultry farms, obtain the intelligent adjustment firmware for ventilation of livestock and poultry farms, and send the intelligent adjustment firmware for ventilation of livestock and poultry farms to the cloud platform to execute intelligent ventilation adjustment for livestock and poultry farming.

Images