Livestock breeding environment autonomous regulation method and system based on internet of things

Abstract

The application relates to the technical field of livestock breeding environment regulation, in particular to a livestock breeding environment autonomous regulation method and system based on the Internet of Things, which solves the technical problem of inaccurate jet flow state judgment in the prior art. The method comprises the following steps: acquiring environment parameters of a breeding house; the environment parameters comprise an air inlet negative pressure value, an indoor-outdoor temperature difference and an animal activity layer temperature sequence; the animal activity layer temperature sequence comprises animal activity layer temperatures at the current moment and multiple historical moments; based on the animal activity layer temperature sequence, a distribution asymmetry coefficient for representing temperature distribution asymmetry is determined; based on the distribution asymmetry coefficient, the air inlet negative pressure value and the indoor-outdoor temperature difference, a jet flow instability risk index is determined; and according to the jet flow instability risk index, a control instruction for adjusting the opening degree of the air inlet of the breeding house is generated.

Description

Technical Field

[0001] This application relates to the field of livestock breeding environment control technology, specifically to a method and system for autonomous control of livestock breeding environment based on the Internet of Things. Background Technology

[0002] In the livestock farming industry, enclosed breeding sheds are typically used to effectively isolate external environmental interference and facilitate centralized management. During the cold season, enclosed breeding sheds usually employ negative pressure ventilation mode for environmental control. By utilizing the high-speed jet of cold air generated at the air inlet, the cold air is guided to fully mix and preheat with the warm air inside the shed at high altitude using the wall effect before settling down to the animal activity layer, thereby providing a suitable growth temperature environment for livestock and poultry.

[0003] However, existing technologies mainly rely on monitoring surface temperature or static pressure difference to determine whether the jet is stable. But these methods are difficult to accurately reflect the actual state of the jet and are prone to misjudgment or omission. This results in an inability to accurately address the cold stress caused by the jet sinking, affecting the healthy growth of livestock and poultry and reducing breeding efficiency. Summary of the Invention

[0004] To address the technical problem of inaccurate jet state judgment in existing technologies, this application aims to provide an IoT-based method for autonomous control of livestock farming environments. The specific technical solution adopted is as follows: Obtain environmental parameters of the breeding shed; environmental parameters include intake negative pressure value, temperature difference between inside and outside the shed, and temperature sequence of animal activity layer; the temperature sequence of animal activity layer includes the current and multiple historical time points of animal activity layer temperature.

[0005] Based on the temperature sequence of the animal activity layer, the distribution asymmetry coefficient used to characterize the asymmetry of temperature distribution was determined.

[0006] Based on the distribution asymmetry coefficient, the negative pressure value of the air intake, and the temperature difference between inside and outside the house, the jet instability risk index is determined. The jet instability risk index is used to quantify the risk of the air intake jet in the breeding house deviating from the preset wall trajectory and sinking.

[0007] Based on the jet instability risk index, control commands are generated to adjust the opening of the air inlet of the breeding house.

[0008] In one possible implementation, a distribution asymmetry coefficient for characterizing temperature distribution asymmetry is determined based on the animal activity layer temperature sequence, including: determining the temperature fluctuation amplitude according to the animal activity layer temperature sequence; when the temperature fluctuation amplitude is greater than a first preset threshold, calculating the skewness of the animal activity layer temperature sequence and using the skewness as the distribution asymmetry coefficient.

[0009] In one possible implementation, the method further includes: when the temperature fluctuation amplitude is less than or equal to a first preset threshold, determining the distribution asymmetry coefficient as 0.

[0010] One possible implementation involves determining the jet instability risk index based on the distribution asymmetry coefficient, the intake negative pressure value, and the temperature difference between the inside and outside of the chamber. This includes: determining the cold air judgment weight based on the distribution asymmetry coefficient; determining the jet stability margin based on the intake negative pressure value and the temperature difference between the inside and outside of the chamber; the jet stability margin is used to characterize the theoretical stability margin of the current intake jet; and determining the jet instability risk index based on the weighted sum of the jet stability margin and the cold air judgment weight.

[0011] In one possible implementation, the cold air judgment weight is determined based on the distribution asymmetry coefficient, including: if the distribution asymmetry coefficient is greater than or equal to a second preset threshold, the cold air judgment weight is set to zero; if the distribution asymmetry coefficient is less than the second preset threshold, the cold air judgment weight is determined based on the absolute value of the distribution asymmetry coefficient.

[0012] In one possible implementation, the jet instability risk index is determined based on the weighted sum of the jet stability margin and the cold air judgment weight. This includes: obtaining the temperature fluctuation amplitude of the animal activity layer temperature sequence; determining a first component based on the jet stability margin; wherein, when the jet stability margin is non-negative, the first component is zero; when the jet stability margin is negative, the first component is negatively correlated with the jet stability margin; multiplying the temperature fluctuation amplitude by the cold air judgment weight to obtain a second component; and determining the jet instability risk index based on the weighted sum of the first and second components.

[0013] In one possible implementation, a control command for adjusting the opening of the air inlet of the breeding house is generated based on the jet instability risk index, including: determining the cumulative risk intensity of the previous moment at the current moment; wherein, if the current moment is the initial moment, the cumulative risk intensity of the previous moment is a preset value, and if the current moment is not the initial moment, the cumulative risk intensity of the previous moment is the actual calculated value; attenuating the cumulative risk intensity of the previous moment based on a forgetting factor, and determining the cumulative risk intensity of the current moment based on the attenuated cumulative risk intensity of the previous moment and the jet instability risk index at the current moment; if the cumulative risk intensity of the current moment is greater than a third preset threshold, a control command for reducing the opening of the air inlet is generated, and the cumulative risk intensity of the current moment is reset.

[0014] In one possible implementation, after generating a control command to reduce the air inlet opening, the method further includes: maintaining the air inlet opening unchanged for a preset time period and pausing the process of determining the cumulative risk intensity.

[0015] In one possible implementation, the method further includes: if the cumulative risk intensity at the current moment is less than a fourth preset threshold, and the jet stability margin determined based on the intake negative pressure value and the temperature difference between the inside and outside of the chamber is greater than a fifth preset threshold, then a control command for increasing the intake port opening is generated.

[0016] This application also provides an IoT-based autonomous control system for livestock farming environment, which includes: The acquisition unit is used to acquire environmental parameters of the breeding house; the environmental parameters include the intake negative pressure value, the temperature difference between inside and outside the house, and the temperature sequence of the animal activity layer; the temperature sequence of the animal activity layer includes the current and multiple historical time points of the animal activity layer temperature.

[0017] The feature calculation unit is used to determine the distribution asymmetry coefficient, which characterizes the asymmetry of temperature distribution, based on the temperature sequence of the animal activity layer.

[0018] The risk fusion unit is used to determine the jet instability risk index based on the distribution asymmetry coefficient, the air intake negative pressure value, and the temperature difference between inside and outside the house. The jet instability risk index is used to quantify the risk of the air intake jet in the breeding house deviating from the preset wall trajectory and sinking.

[0019] The control unit is used to generate control commands for adjusting the opening of the air inlet of the breeding house based on the jet instability risk index.

[0020] This application offers the following advantages: The extracted asymmetric coefficient captures the asymmetric characteristics of temperature distribution, providing a crucial basis for distinguishing the causes of different temperature fluctuations; the jet instability risk index, constructed by integrating physical parameters and statistical characteristics, achieves precise quantification of jet sinking risk, balancing theoretical mechanisms with practical feedback; the control commands generated based on the risk index can directly act on the inlet actuator, dynamically adjusting jet stability. Therefore, this application, through multi-dimensional parameter fusion and precise feature extraction, solves the problem of inaccurate jet state judgment in existing technologies, improves the targeting and reliability of environmental control, effectively reduces the risk of cold stress in livestock and poultry, and ensures a suitable growth environment in the breeding sheds. Attached Figure Description

[0021] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating an IoT-based autonomous control method for livestock farming environment, provided as an embodiment of this application; Figure 2 This is a schematic diagram of the system architecture of an IoT-based autonomous control system for livestock farming environment, provided as an embodiment of this application. Detailed Implementation

[0023] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an IoT-based autonomous control method for livestock farming environment proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0025] Unless otherwise specified, the normalization function Norm() mentioned in this application uses maximum and minimum value normalization. The maximum and minimum values ​​are preset empirical extreme values ​​derived from a large amount of historical experimental data. If the calculation result exceeds the [0,1] interval, a truncation function is used to limit it to the [0,1] range (i.e., if the result is less than 0, it is taken as 0; if it is greater than 1, it is taken as 1) to eliminate the influence of outliers on the evaluation index.

[0026] The following description, in conjunction with the accompanying drawings, details a specific scheme for an IoT-based autonomous control method for livestock farming environment provided in this application.

[0027] Please see Figure 1 It illustrates a flowchart of a method for autonomous regulation of the livestock farming environment based on the Internet of Things, as provided in one embodiment of this application. Figure 1 As shown, the method includes the following steps: Step 101: Obtain the environmental parameters of the breeding shed.

[0028] The environmental parameters include the intake negative pressure value, the temperature difference between inside and outside the enclosure, and the animal activity layer temperature sequence. The animal activity layer temperature sequence includes the current and multiple historical time points.

[0029] It should be noted that the intake negative pressure value refers to the difference between the atmospheric pressure outside the breeding house and the static pressure inside the house. It is used to reflect the initial kinetic potential of the driving air injected into the house. This parameter can be obtained by a micro differential pressure transmitter installed on the side wall of the air inlet. To ensure stable readings, the pressure tap of the transmitter should be equipped with a windproof cover to avoid direct airflow. The temperature difference between inside and outside the breeding house is the difference between the average temperature inside the breeding house and the temperature outside the house. It reflects the density difference of the cold air mass relative to the indoor environment. It can be calculated by collecting the average temperature inside the house and the temperature outside the house separately.

[0030] The animal activity layer temperature sequence is a dataset reflecting the temperature change trend in the animal activity area. It includes the animal activity layer temperature at the current moment and multiple historical moments. The animal activity layer temperature refers to the temperature at a height of 0.3 to 0.5 meters above the ground (corresponding to the height of the livestock's back), which can be collected by a temperature probe installed at this height directly below the air inlet. For example, this temperature sequence can be maintained by constructing a fixed-capacity First-In-First-Out (FIFO) queue. The queue length can be set according to the actual size of the livestock shed and the required control precision; for example, setting it to 60 would include the animal activity layer temperature data for the past 60 seconds, ensuring that the sequence reflects the temperature change characteristics over a period of time.

[0031] Optionally, when acquiring environmental parameters, data from each parameter should be read in parallel via an IoT sensor interface, and spatiotemporal alignment processing of multi-source data should be performed to ensure consistency of different parameters in the time dimension, providing accurate and synchronized basic data for subsequent calculations. Simultaneously, in the initial stage after system power-on or reset, if the temperature sequence has not accumulated sufficient data samples (not reaching the set queue length), a cold start safety protection strategy must be implemented to lock the air intake opening to a preset safe value or maintain the effective position before power failure. The formal control process should only be initiated after data accumulation is complete to avoid malfunctions due to insufficient data.

[0032] Step 102: Based on the temperature sequence of the animal activity layer, determine the distribution asymmetry coefficient used to characterize the temperature distribution asymmetry.

[0033] Among them, the distribution asymmetry coefficient is used to distinguish different causes of temperature changes. By analyzing the statistical distribution characteristics of the temperature sequence of the animal activity layer, the distribution differences caused by different temperature fluctuation sources can be captured.

[0034] Optionally, when determining this coefficient, the temperature sequence of the animal activity layer should first be preprocessed to ensure the validity of the data, for example, by removing obvious outliers (such as data exceeding the reasonable temperature range due to sensor malfunction). Then, based on the preprocessed temperature sequence, a parameter characterizing the distribution asymmetry is calculated using statistical analysis methods; this parameter is the distribution asymmetry coefficient. The distribution asymmetry coefficient is essentially the skewness of the temperature sequence. Skewness is a statistic that describes the degree of asymmetry in the data distribution, reflecting the direction and extent of the data distribution's tilt relative to the mean.

[0035] The distribution asymmetry coefficient can provide key feature support for distinguishing between cold air sinking and biological heat source interference, and solve the problem that a single temperature value is difficult to distinguish the causes of different temperature fluctuations.

[0036] Step 103: Determine the jet instability risk index based on the distribution asymmetry coefficient, the intake negative pressure value, and the temperature difference between the inside and outside of the chamber.

[0037] Among them, the jet instability risk index is used to quantify the risk of the air intake jet in the breeding house deviating from the preset wall trajectory and sinking.

[0038] Optionally, the stability of the intake jet depends on the dynamic balance between horizontal inertial force and vertical gravity buoyancy. The intake negative pressure value is directly related to the horizontal inertial force (intake velocity), and the temperature difference between the inside and outside is directly related to the vertical gravity buoyancy (density difference of cold air mass). The two together constitute the physical basis for the stability of the jet. The distribution asymmetry coefficient can reflect the cause of the actual temperature fluctuation, that is, whether it is caused by the sinking of cold air, and is a measured characteristic to verify the jet state.

[0039] Understandably, this step constructs a jet instability risk index by integrating physical parameters (inlet negative pressure value, temperature difference between inside and outside the chamber) and statistical characteristics (distribution asymmetry coefficient), thereby achieving a quantitative assessment of jet sinking risk. This integration process takes into account both physical mechanisms and experimental feedback, considering both theoretical jet stability conditions and temperature change characteristics in the actual environment. This ensures that the risk index accurately and comprehensively reflects the actual situation of jet instability, avoiding judgment bias caused by relying on only a single parameter.

[0040] Step 104: Based on the jet instability risk index, generate control instructions for adjusting the opening of the air inlet of the breeding house.

[0041] Among them, the air inlet opening is a key factor affecting the intake negative pressure and intake speed. By adjusting the air inlet opening, the horizontal inertial force driving the jet can be changed, thereby adjusting the stability of the jet.

[0042] Specifically, when generating control commands, the first step is to set a threshold for the jet instability risk index. This threshold can be determined through experimental calibration or historical data statistics, based on factors such as the type of livestock shed, livestock breed, and growth stage. Then, the currently calculated jet instability risk index is compared with the set threshold. If the risk index is higher than the threshold, it indicates a high risk of jet instability, requiring a reduction in the air inlet opening to increase the negative pressure value of the air inlet, thereby increasing the horizontal inertial force of the jet and suppressing jet sinking. If the risk index is lower than the threshold and other safety conditions are met (such as sufficient jet stability), the air inlet opening can be appropriately increased to achieve energy savings. If the risk index is in the transition range near the threshold, the current air inlet opening is maintained, and changes in environmental parameters and the risk index are continuously monitored.

[0043] Optionally, after generating the control command, the control command is sent to the air inlet actuator. The actuator adjusts the opening precisely according to the command. At the same time, a certain stabilization waiting period should be set after adjustment to keep the opening unchanged and suspend the cumulative calculation of the risk index. Monitoring and control can be resumed after the flow field is reconstructed and stabilized to avoid over-adjustment caused by flow field lag.

[0044] Based on the above technical solutions, the asymmetric coefficient extracted in this application captures the asymmetric characteristics of temperature distribution, providing a key basis for distinguishing the causes of different temperature fluctuations. The jet instability risk index, constructed by integrating physical parameters and statistical characteristics, achieves precise quantification of jet sinking risk, taking into account both theoretical mechanisms and practical feedback. Control commands generated based on the risk index can directly act on the inlet actuator, dynamically adjusting jet stability. Therefore, this application, through multi-dimensional parameter fusion and precise feature extraction, solves the problem of inaccurate jet state judgment in existing technologies, improves the targeting and reliability of environmental control, effectively reduces the risk of cold stress in livestock and poultry, and ensures a suitable growth environment in the breeding sheds.

[0045] In one possible implementation, the above steps—specifically, determining the distribution asymmetry coefficient to characterize temperature distribution asymmetry based on the animal activity layer temperature sequence—include: Step 201: Determine the temperature fluctuation range based on the temperature sequence of the animal activity layer.

[0046] Among them, temperature fluctuation amplitude is a statistical measure that reflects the degree of dispersion of data in the temperature sequence. It can characterize the degree of drastic change in the temperature of the animal activity layer over a period of time. Specifically, temperature fluctuation amplitude is the sample standard deviation of the temperature sequence of the animal activity layer.

[0047] For example, the calculation process for the temperature fluctuation amplitude includes: calculating the arithmetic mean of the temperature sequence of the animal activity layer. Then, calculate the sum of squares of the differences between each temperature data point in the sequence and the average value, divide by the sequence length L minus 1 (i.e., degree of freedom correction), and finally take the square root of the result to obtain the temperature fluctuation amplitude. As an example, temperature fluctuation amplitude The calculation formula can be expressed as: in, The first in the temperature sequence The temperature of the animal activity layer at time L is the length of the temperature sequence (i.e., the queue capacity). This is the arithmetic mean of the temperature sequence of the animal activity layer.

[0048] Step 202: When the temperature fluctuation amplitude is greater than the first preset threshold, calculate the skewness of the temperature sequence of the animal activity layer and use the skewness as the distribution asymmetry coefficient.

[0049] The first preset threshold is a critical value used to determine whether there is significant thermal fluctuation in the environment. If the temperature fluctuation is greater than this threshold, it indicates that there is a significant temperature change, which may be caused by cold wind sinking or interference from biological heat sources. In this case, it is necessary to further distinguish through skewness. Therefore, the skewness of the temperature sequence is calculated as the distribution asymmetry coefficient.

[0050] For example, the first preset threshold can be set to 0.05℃. This value is the boundary between environmental thermal quiescence and significant fluctuations, which is derived from a large amount of experimental data and can effectively filter out meaningless small temperature fluctuations.

[0051] As an example, the asymmetric coefficient distribution in this step Satisfy the following formula: Step 203: When the temperature fluctuation amplitude is less than or equal to the first preset threshold, the distribution asymmetry coefficient is set to 0.

[0052] Understandably, if the temperature fluctuation is small, it means that the current environment is in a thermally quiescent state (no wind and no animal activity). At this time, there is no temperature fluctuation source that needs to be distinguished. Setting the distribution asymmetry coefficient to 0 can avoid subsequent invalid fusion calculations and prevent numerical problems caused by the denominator approaching zero when calculating the skewness due to the extremely small fluctuation amplitude, thereby improving the stability and efficiency of the system calculation.

[0053] Based on the above technical solution, this application, by calculating the temperature fluctuation amplitude and comparing it with a first preset threshold, can first screen out scenarios with significant thermal fluctuations. Skewness calculation is then performed only in these scenarios, avoiding ineffective processing of calm environments and improving computational efficiency. Simultaneously, different methods for determining the distribution asymmetry coefficient are set for scenarios with different fluctuation amplitudes, ensuring the accuracy of feature extraction in scenarios with significant fluctuations while avoiding numerical problems and ineffective calculations in scenarios with minor fluctuations. Therefore, the determination of the distribution asymmetry coefficient in this application is more targeted and reasonable, providing more reliable feature input for the accurate calculation of the subsequent risk index, further improving the accuracy and stability of the entire control method.

[0054] In one possible implementation, the process of determining the jet instability risk index based on the distribution asymmetry coefficient, the intake negative pressure value, and the temperature difference between the inside and outside of the chamber specifically includes: Step 301: Determine the cold air judgment weight based on the distribution asymmetry coefficient.

[0055] The cold wind determination weight is an indicator used to quantify the credibility of cold wind sinking as represented by the distribution asymmetry coefficient. Its value ranges from [0,1]. A larger weight indicates a higher credibility that temperature fluctuations originate from cold wind sinking. This weight is determined based on the ability of the distribution asymmetry coefficient to distinguish the causes of temperature fluctuations. By transforming abstract statistical characteristics into a normalized confidence index, it facilitates subsequent risk fusion.

[0056] Optionally, this step can be implemented as follows: if the distribution asymmetry coefficient is greater than or equal to the second preset threshold, then the cold air judgment weight is set to zero; if the distribution asymmetry coefficient is less than the second preset threshold, then the cold air judgment weight is determined according to the absolute value of the distribution asymmetry coefficient.

[0057] The second preset threshold is a critical value for distinguishing the causes of temperature fluctuations, and its value is determined based on the physical meaning of the distribution asymmetry coefficient. Since the temperature distribution caused by cold air sinking exhibits a negative skewness (low-temperature tail), while the temperature distribution caused by biological heat source interference exhibits a positive skewness (high-temperature bulge), the second preset threshold should be set to a value that can distinguish the significantly negatively skewed distribution from other distribution states. For example, the second preset threshold can be set to -0.1, a value calibrated through extensive experimental data that can effectively distinguish the distribution characteristics corresponding to cold air sinking and biological heat source interference.

[0058] Specifically, when the distribution asymmetry coefficient is greater than or equal to -0.1, it indicates that the temperature distribution is positively skewed or slightly negatively skewed, and the temperature fluctuations are caused by biological heat source interference or random noise. At this time, the credibility of cold wind sinking is extremely low. Therefore, the weight of cold wind judgment is set to 0 to physically shield the impact of such false fluctuations on risk assessment. When the distribution asymmetry coefficient is less than -0.1, it indicates that the temperature distribution is significantly negatively skewed, and the credibility of temperature fluctuations being caused by cold wind sinking is relatively high. At this time, the absolute value of the distribution asymmetry coefficient is used as the weight of cold wind judgment, and it is processed by upper limit clamping (maximum value is 1.0) to ensure that the weight is within a reasonable range and to quantify the credibility of cold wind sinking.

[0059] Step 302: Determine the jet stability margin based on the intake negative pressure value and the temperature difference between the inside and outside of the chamber.

[0060] Among them, the jet stability margin is used to characterize the theoretical stability margin of the current intake jet.

[0061] The jet stability margin is a physical index derived from fluid dynamics principles. It assesses the theoretical stability of a jet by quantifying the balance between horizontal inertial force and vertical gravity buoyancy. The greater the inlet negative pressure, the stronger the horizontal inertial force, and the more stable the jet; the greater the temperature difference between the inside and outside of the jet, the stronger the vertical gravity buoyancy, and the more prone the jet is to instability.

[0062] Optionally, this application calculates the jet thrust-to-weight ratio based on the intake negative pressure value and the temperature difference between the inside and outside of the chamber, and further calculates the jet stability margin based on the jet thrust-to-weight ratio.

[0063] As an example, jet thrust-to-weight ratio Satisfy the following formula: in, This is the intake structure factor, used to correct the effects of intake geometry, deflector angle, and air density variations on theoretical formulas. It is set through field calibration. . This is the intake negative pressure value. To account for the temperature difference between inside and outside the building. These are parameter tuning coefficients, and their values ​​should be extremely small positive numbers (e.g., 0.001) to avoid denominators of 0.

[0064] As yet another example, the jet stability margin satisfies the following formula: in, To theoretically maintain the threshold, the minimum thrust-to-weight ratio boundary characterizing the jet's ability to overcome gravity and maintain adhesion to the wall is taken as (in this embodiment, it is taken as...). ).

[0065] when At this time, the intake kinetic energy is theoretically sufficient to support the weight of the cold air, and the flow field is in the theoretically stable region.

[0066] when At this time, the intake kinetic energy is insufficient to overcome gravity, the flow field is in the theoretically unstable region, and there is a physical risk of cold air sinking.

[0067] Step 303: Determine the jet instability risk index based on the weighted sum of the jet stability margin and the cold air judgment weight.

[0068] The weighted summation method balances the credibility of physical theoretical criteria and measured statistical criteria, avoiding the limitations of a single criterion. By assigning reasonable weight coefficients to the jet stability margin and cold air determination weights, both play their respective roles in risk assessment: physical theoretical criteria can provide early warning of potential jet instability risks, while measured statistical criteria can verify whether cold air sinking has actually occurred. The combination of the two provides dual protection of preventive warning and factual confirmation, ensuring that the jet instability risk index can comprehensively and accurately quantify jet sinking risk.

[0069] Optionally, the process can be implemented as follows: obtaining the temperature fluctuation amplitude of the animal activity layer temperature sequence; determining the first component based on the jet stability margin; wherein, when the jet stability margin is non-negative, the first component takes the value of zero; when the jet stability margin is negative, the first component is negatively correlated with the jet stability margin; multiplying the temperature fluctuation amplitude by the cold air judgment weight to obtain the second component; and determining the jet instability risk index based on the weighted sum of the first component and the second component.

[0070] The first component is a risk component based on physical theory criteria, used to characterize the theoretical jet instability risk. When the jet stability margin is non-negative, it indicates that the current inlet kinetic energy is theoretically sufficient to support the weight of the cold air, the flow field is in the theoretically stable region, and there is no theoretical jet instability risk; therefore, the first component is set to 0. When the jet stability margin is negative, it indicates that the inlet kinetic energy is insufficient to overcome gravity, the flow field is in the theoretically unstable region, and there is a physical risk of cold air sinking. Moreover, the larger the negative value of the stability margin, the higher the theoretical risk; therefore, the first component is negatively correlated with the stability margin.

[0071] For example, the first component can be calculated using a linear rectified function (such as a rectified linear unit (ReLU)). The ReLU function retains only non-negative input values ​​and discards negative values. The specific calculation logic is as follows: The first component is: ,in This is the jet stability margin. When hour,- , The function outputs 0; when hour,- , Function output - At this time, the first component and The negative correlation aligns with the quantitative logic of theoretical risk.

[0072] The second component is a risk component based on measured statistical criteria, used to characterize the actual intensity of cold stress. Temperature fluctuation amplitude reflects the severity of temperature changes, while the cold wind determination weight reflects the reliability of the fluctuation originating from descending cold wind. Multiplying these two components together comprehensively reflects the severity of the actual cold stress: if the fluctuation amplitude is large and the reliability of the cold wind is high, the second component is large, indicating severe actual cold stress; if either parameter is small, the second component is small, indicating milder actual cold stress or low reliability. Based on this, the fluctuation characteristics of measured temperature and the reliability of its causes can be effectively integrated, ensuring that the second component accurately reflects the actual cold stress situation.

[0073] As an example, the injection instability risk index Satisfy the following formula: in, For the first component mentioned above, For the second component mentioned above, The weighting coefficient for the first component represents the importance of the physical theory criterion in risk assessment. The weighting coefficient of the second component represents the importance of the measured statistical criteria in risk assessment. The weighted sum fusion method allows theoretical risk and actual risk to complement each other: even if the theoretical risk is zero (first component = 0), if significant cold stress is actually detected (second component > 0), the total risk index will still increase, avoiding missed detections caused by "false safety"; if the theoretical risk is high but no cold stress is actually detected (second component = 0), the total risk index is determined by the first component, which can achieve early warning.

[0074] Based on the above technical solution, the first component can provide early warning of theoretical risks and achieve preventive control; the second component can accurately reflect the actual cold stress intensity, ensuring the objectivity of risk assessment; by weighting and fusing the first and second components, the weights of theory and measurement are balanced, avoiding the limitations of a single criterion and completely eliminating the problem of missed judgments caused by false safety; this makes the calculation of the radiation instability risk index more scientific and accurate, and can comprehensively capture the theoretical risks and actual situation of radiation instability, providing a more reliable basis for the generation of subsequent control instructions, and further improving the robustness and effectiveness of environmental control.

[0075] In one possible implementation, the above steps—generating control commands for adjusting the opening of the air inlet of the livestock shed based on the jet instability risk index—include: Step 401: Determine the cumulative risk intensity of the previous time step.

[0076] Specifically, if the current time is the initial time, the cumulative risk intensity of the previous time is a preset value; if the current time is not the initial time, the cumulative risk intensity of the previous time is the actual calculated value.

[0077] It should be noted that cumulative risk intensity is an indicator that reflects the degree of accumulation of jet instability risk over a period of time. Since animals have physiological tolerance to instantaneous airflow disturbances, and the risk index at a single moment may be subject to noise interference, cumulative assessment is needed to filter out noise and accurately judge the risk trend.

[0078] Step 402: Attenuate the cumulative risk intensity of the previous moment based on the forgetting factor, and determine the cumulative risk intensity of the current moment based on the attenuated cumulative risk intensity of the previous moment and the current moment's instability risk index.

[0079] Specifically, in order to prevent the unlimited accumulation of historical risks over a long period from causing integral saturation (wind-up), a recursive decay integral algorithm with a forgetting factor is adopted. This algorithm enables past risk values ​​to decay exponentially over time, ensuring that the cumulative risk intensity can dynamically reflect recent risk trends.

[0080] For example, the formula for calculating cumulative risk intensity is: in, The cumulative risk intensity at the current time t; This represents the cumulative risk intensity at the previous time t-1; The forgetting factor, with a value range of (0,1), represents the decay rate of historical risk. In this embodiment, it is set as follows: =0.95; Let t be the injection instability risk index at the current time t.

[0081] For the historical cumulative risk after decay, the forgetting factor A value less than 1 causes historical risk values ​​to gradually decrease over time. The closer it is to 1, the longer the memory of historical risks lasts; The closer it is to 0, the shorter the memory period of historical risks; The newly added risks at the current moment reflect the current instability risks of the injection system; the sum of the two yields the cumulative risk intensity at the current moment, which retains the impact of recent historical risks and incorporates current risks, thus achieving a dynamic cumulative assessment of risks.

[0082] Cumulative risk intensity The higher the value, the greater the accumulation of recent injection instability risk, requiring timely control measures; the lower the value, the lower the recent risk accumulation and the more stable the current environment. This indicator can filter high-frequency noise, avoiding mis-controls caused by risk fluctuations at a single moment, while also capturing the accumulation trend of risk, ensuring the timeliness and effectiveness of control measures.

[0083] Step 403: If the cumulative risk intensity at the current moment is greater than the third preset threshold, a control command is generated to reduce the air intake opening and the cumulative risk intensity at the current moment is reset.

[0084] The third preset threshold is the critical value that triggers the intake contraction regulation. Its value is determined by experimental calibration based on factors such as the cold stress tolerance of livestock and poultry and the characteristics of the breeding house environment. For example, the third preset threshold is set to 5.0.

[0085] when This indicates that the risk of air jet instability has accumulated to a certain level recently, and the downward trend of cold air has become persistent. If not controlled in time, it will lead to cold stress in livestock and poultry. At this time, a control command to reduce the air inlet opening is generated, indicating the air inlet opening degree. As an example, the air inlet opening degree... Satisfying the formula: in, The intake opening for the next moment. Set the minimum mechanical limit for the air intake (for example, set it to 10%). The current air intake opening. Set the shrinkage step size (for example, set it to 5%).

[0086] Thus, with the exhaust volume remaining constant, reducing the cross-sectional area of ​​the air inlet will increase the intake resistance, forcing a negative intake pressure. Increase, based on the jet thrust-to-weight ratio and The positive correlation between the two will increase the horizontal inertial force of the jet, thereby lifting the originally descending cold wind trajectory back to the high altitude and eliminating cold stress at its source.

[0087] At the same time, after issuing the contraction command, the cumulative risk intensity is immediately reset to 0 to avoid repeated adjustments due to the high integral value after one adjustment, thus ensuring the rationality and stability of the regulation.

[0088] Based on the above technical solution, this application clarifies the initial conditions and inheritance logic of cumulative risk intensity, ensuring data continuity; it adopts a decay integral algorithm with a forgetting factor, which filters high-frequency noise and avoids integral saturation, dynamically reflecting recent risk trends and improving the accuracy of risk assessment; it sets a third preset threshold as a control trigger condition to ensure the timeliness of control measures, and through a scientific opening adjustment formula and risk reset logic, it achieves effective intervention in jet stability, eliminating cold stress risk at its source. This solution makes the generation of control commands more logical and targeted, and can dynamically adjust the air inlet opening according to the risk accumulation, further improving the effectiveness and stability of environmental control and protecting the growth environment of livestock and poultry.

[0089] In one possible implementation, after step 403 above, the method further includes: Step 404: Keep the air inlet opening unchanged within the preset time period and pause the process of determining the cumulative risk intensity.

[0090] The preset time period is the adjustment stabilization waiting period, and its value is determined based on the state hysteresis characteristics of the fluid system. For example, it is set to 30 seconds. Since it takes a certain amount of time (usually 10-30 seconds) for the static pressure inside the chamber to be established and a new flow pattern to be formed after the air inlet is activated, if risk accumulation and regulation continue during this period, it will cause the controller to make over-shooting adjustments based on outdated flow field data.

[0091] Therefore, during the 30-second waiting period, the following procedure is executed: Maintain opening: The intake actuator maintains the opening determined in step 403. This remains unchanged, ensuring that the new flow field can be stably established.

[0092] Pause integration: The system continues to collect environmental parameters and calculate the jet instability risk index. Used for observation, but the cumulative risk intensity is stopped. The cumulative update is kept at the reset value of 0 to avoid false alarms triggered by transient fluctuations during the flow field reconstruction process.

[0093] Data refresh: During the waiting period, the temperature observation sequence will be gradually filled with data under the new flow field, preparing data for the next round of closed-loop control and ensuring that subsequent regulation is based on stable and accurate data.

[0094] Step 405: If the cumulative risk intensity at the current moment is less than the fourth preset threshold, and the jet stability margin determined based on the intake negative pressure value and the temperature difference between the inside and outside of the chamber is greater than the fifth preset threshold, then a control command for increasing the intake port opening is generated.

[0095] The fourth preset threshold is a critical value for determining whether there is no significant risk in the near future; for example, it is set to 0.1. This indicates that there are no obvious cold wind sinking characteristics on the surface recently, and the environment is in a stable state; the fifth preset threshold is set as the safe hysteresis. (Example,) When the jet stability margin This indicates that the current intake kinetic energy is not only sufficient to maintain jet adhesion (i.e., thrust-to-weight ratio) Greater than the theoretical maintenance threshold , exemplary =1.2), and the margin exceeds the safety hysteresis (actual thrust-to-weight ratio). + ,in, + =1.5), indicating potential for energy saving.

[0096] When both of the above conditions are met simultaneously, a control command to increase the intake port opening is generated to ensure the safety of the expansion adjustment and avoid adjustment oscillations that collapse immediately upon opening. As an example, the specific calculation formula for the control command is as follows: in, To expand the step size (for example, set to 2%). The function is used to limit the maximum mechanical limit of the air inlet opening to no more than 100%. Under the premise of sufficient jet flow and no risk, increasing the air inlet opening can reduce the intake resistance and lower the intake negative pressure, thereby reducing the fan energy consumption, while ensuring sufficient intake volume, thus balancing energy saving and air quality.

[0097] Please see Figure 2 This diagram illustrates a system architecture of an IoT-based autonomous control system for livestock farming environment according to an embodiment of the present invention. The system includes an acquisition unit 201, a feature calculation unit 202, a risk fusion unit 203, and a control unit 204. The units communicate bidirectionally via communication links to ensure real-time interaction of collected data and analysis results. The communication links can employ wired or wireless transmission methods to meet the communication needs of different monitoring scenarios.

[0098] The acquisition unit 201 is used to acquire environmental parameters of the breeding house; the environmental parameters include the negative pressure value of the air intake, the temperature difference between inside and outside the house, and the temperature sequence of the animal activity layer; the temperature sequence of the animal activity layer includes the current temperature and the temperature of the animal activity layer at multiple historical moments.

[0099] The feature calculation unit 202 is used to determine the distribution asymmetry coefficient, which characterizes the asymmetry of temperature distribution, based on the temperature sequence of the animal activity layer.

[0100] Risk fusion unit 203 is used to determine the jet instability risk index based on the distribution asymmetry coefficient, the air intake negative pressure value, and the temperature difference between inside and outside the house; the jet instability risk index is used to quantify the risk of the air intake jet in the breeding house deviating from the preset wall trajectory and sinking.

[0101] The control unit 204 is used to generate control commands for adjusting the opening of the air inlet of the breeding house based on the jet instability risk index.

[0102] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for autonomous control of livestock farming environment based on the Internet of Things, characterized in that, The method includes: The environmental parameters of the breeding shed are obtained; the environmental parameters include the negative pressure value of the intake air, the temperature difference between inside and outside the shed, and the temperature sequence of the animal activity layer; the temperature sequence of the animal activity layer includes the current temperature and the temperature of the animal activity layer at multiple historical moments. Based on the temperature sequence of the animal activity layer, a distribution asymmetry coefficient is determined to characterize the temperature distribution asymmetry. Based on the distribution asymmetry coefficient, the air intake negative pressure value, and the temperature difference between inside and outside the house, the jet instability risk index is determined; the jet instability risk index is used to quantify the risk of the air intake jet in the breeding house deviating from the preset wall-attached trajectory and sinking. Based on the jet instability risk index, control commands are generated to adjust the opening of the air inlet of the breeding house.

2. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 1, characterized in that, Based on the temperature sequence of the animal activity layer, the distribution asymmetry coefficient used to characterize the temperature distribution asymmetry is determined, including: The temperature fluctuation amplitude is determined based on the temperature sequence of the animal activity layer; When the temperature fluctuation amplitude is greater than a first preset threshold, the skewness of the temperature sequence of the animal activity layer is calculated, and the skewness is used as the distribution asymmetry coefficient.

3. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 2, characterized in that, The method further includes: When the temperature fluctuation amplitude is less than or equal to the first preset threshold, the distribution asymmetry coefficient is determined to be 0.

4. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 1, characterized in that, Based on the distribution asymmetry coefficient, the intake negative pressure value, and the temperature difference between the inside and outside of the chamber, the jet instability risk index is determined, including: The cold air determination weight is determined based on the aforementioned distribution asymmetry coefficient; The jet stability margin is determined based on the intake negative pressure value and the temperature difference between the inside and outside of the chamber; the jet stability margin is used to characterize the theoretical stability margin of the current intake jet. The jet instability risk index is determined by weighting the jet stability margin and the cold air determination weight.

5. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 4, characterized in that, Based on the aforementioned distribution asymmetry coefficient, the weight for determining cold air is determined, including: If the distribution asymmetry coefficient is greater than or equal to the second preset threshold, then the cold air determination weight is set to zero; If the distribution asymmetry coefficient is less than the second preset threshold, the cold air determination weight is determined based on the absolute value of the distribution asymmetry coefficient.

6. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 4, characterized in that, The jet instability risk index is determined by a weighted sum of the jet stability margin and the cold air determination weight, including: Obtain the temperature fluctuation amplitude of the animal activity layer temperature sequence; A first component is determined based on the jet stability margin; wherein, when the jet stability margin is non-negative, the first component is zero; when the jet stability margin is negative, the first component is negatively correlated with the jet stability margin. Multiply the temperature fluctuation amplitude by the cold air determination weight to obtain the second component; The injection instability risk index is determined based on the weighted sum of the first component and the second component.

7. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 4, characterized in that, Based on the aforementioned jet instability risk index, control commands are generated for adjusting the opening of the air inlet of the livestock shed, including: Determine the cumulative risk intensity of the previous time step at the current time step; wherein, if the current time step is the initial time step, the cumulative risk intensity of the previous time step is a preset value, and if the current time step is not the initial time step, the cumulative risk intensity of the previous time step is an actual calculated value. The cumulative risk intensity of the previous moment is attenuated based on the forgetting factor, and the cumulative risk intensity of the current moment is determined based on the attenuated cumulative risk intensity of the previous moment and the current moment's instability risk index. If the cumulative risk intensity at the current moment is greater than a third preset threshold, a control command is generated to reduce the air intake opening, and the cumulative risk intensity at the current moment is reset.

8. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 7, characterized in that, After generating a control command for reducing the intake port opening, the method further includes: During a preset time period, the air inlet opening is kept constant, and the process of determining the cumulative risk intensity is paused.

9. The method for autonomous regulation of livestock farming environment based on the Internet of Things according to claim 7, characterized in that, The method further includes: If the cumulative risk intensity at the current moment is less than the fourth preset threshold, and the jet stability margin determined based on the intake negative pressure value and the temperature difference between the inside and outside of the chamber is greater than the fifth preset threshold, then a control command for increasing the intake port opening is generated.

10. An Internet of Things-based autonomous control system for livestock farming environment, characterized in that, The system includes: The acquisition unit is used to acquire environmental parameters of the breeding house; the environmental parameters include the negative pressure value of the air intake, the temperature difference between inside and outside the house, and the temperature sequence of the animal activity layer; the temperature sequence of the animal activity layer includes the current and multiple historical time points of the animal activity layer temperature; The feature calculation unit is used to determine the distribution asymmetry coefficient, which characterizes the temperature distribution asymmetry, based on the temperature sequence of the animal activity layer. The risk fusion unit is used to determine the jet instability risk index based on the distribution asymmetry coefficient, the air intake negative pressure value, and the temperature difference between the inside and outside of the house; the jet instability risk index is used to quantify the risk of the air intake jet in the breeding house deviating from the preset wall attachment trajectory and sinking. The control unit is used to generate control commands for adjusting the opening of the air inlet of the breeding house based on the jet instability risk index.

Images