Self-adaptive regulation and control method and system for poultry house environment

Abstract

The invention relates to the technical field of poultry breeding, and discloses a poultry house environment self-adaptive regulation and control method and system. The method comprises the following steps: acquiring poultry physiological data through a sensor array to obtain a weight growth rate curve and a metabolic intensity fluctuation curve, and determining a physiological demand vector in combination with a preset feather development model; the poultry feather development degree is evaluated based on the physiological demand vector, a quantitative score is obtained, the relevance between the quantitative score and the physiological demand vector is analyzed, and a wind speed adjustment parameter is calculated based on the relevance; based on the wind speed adjusting parameters, generating an airflow distribution mode sequence, judging whether fluctuation abnormity exists or not, obtaining a wind speed control signal, transmitting the wind speed control signal to ventilation equipment, and adjusting wind speed intensity and ventilation frequency; collecting air quality feedback data in the poultry house in real time, inputting the data into the feather development model, determining a physiological demand vector adjustment value of the next period, and generating a breeding benefit evaluation report according to the adjustment value and the dynamic fluctuation data. The poultry breeding efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of poultry breeding, and in particular to a method and system for adaptive regulation of a poultry house environment. BACKGROUND

[0002] In the poultry breeding industry, environmental regulation plays a crucial role in the growth and development of poultry. Existing poultry house environmental regulation techniques mainly rely on fixed parameter settings to adjust the breeding environment of poultry. However, this method has many defects. First, traditional techniques usually rely on timing and simple wind speed adjustment to ensure air circulation and temperature and humidity regulation. However, these methods fail to adjust in real time to the changing needs of poultry at different growth stages, resulting in lagging environmental regulation and poultry not being able to obtain real-time adaptive environments, which leads to stress reactions and affects the health and production efficiency of poultry. Second, existing techniques often lack real-time dynamic response to environmental regulation and fail to fully utilize real-time changes in physiological data (such as body weight gain rate and metabolic intensity) and environmental data (such as temperature and humidity, carbon dioxide concentration, etc.), which makes environmental regulation unable to accurately match the specific needs of poultry and cannot avoid unnecessary resource waste, causing energy consumption and resource waste problems. Third, traditional techniques ignore the complex relationship between environmental factors and physiological needs of poultry, and cannot accurately adjust individualized parameters such as wind speed, temperature and humidity, leading to excessive or insufficient regulation of the ventilation system and affecting the growth of poultry. Moreover, the adjustment method of these systems usually lacks adaptability and cannot make real-time optimizations based on environmental and physiological changes, lacking intelligent regulation capabilities. At the same time, existing techniques lack data integration and prediction capabilities, and traditional systems usually rely on a single data source without effectively integrating and analyzing multidimensional data, resulting in low regulation accuracy and poor regulation effect, ultimately affecting breeding efficiency and resource utilization efficiency. Due to these defects, existing techniques cannot effectively improve the management level of the poultry house environment, resulting in serious resource waste and negatively affecting the healthy growth of poultry.

[0003] Therefore, there is an urgent need for an intelligent and adaptive regulation-based environmental control system to provide more accurate and flexible environmental regulation solutions, thereby improving the production efficiency and breeding efficiency of poultry. SUMMARY

[0004] To solve the above technical problems, the present application provides a method and system for adaptive regulation of a poultry house environment to improve the growth efficiency of poultry, reduce resource waste, and optimize breeding efficiency.

[0005] In a first aspect, the present application provides a method for adaptive regulation of a poultry house environment, comprising:

[0006] Step S1: collecting poultry physiological data through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve, and determining a physiological demand vector according to the body weight growth rate curve and the metabolic intensity fluctuation curve in combination with a preset feather development model;

[0007] Step S2: evaluating a feather development degree of the poultry based on the physiological demand vector to obtain a quantitative score, analyzing a correlation between the quantitative score and the physiological demand vector, and calculating a wind speed adjustment parameter based on the correlation;

[0008] Step S3: generating a sequence of air flow distribution patterns based on the wind speed adjustment parameter, judging whether there is a fluctuation anomaly, optimizing to obtain a wind speed control signal, and transmitting the wind speed control signal to a ventilation device, the ventilation device adjusting a wind speed intensity and a ventilation frequency;

[0009] Step S4: collecting air quality feedback data in a poultry house in real time, inputting the air quality feedback data into the feather development model to determine an adjustment value of the physiological demand vector in a next period, and generating a breeding benefit evaluation report according to the adjustment value and dynamic fluctuation data.

[0010] In combination with the first aspect, in a first implementation manner of the first aspect of the present application, the poultry physiological data is collected through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve, including:

[0011] The poultry physiological data collected through the sensor array includes poultry weight data and metabolic index signals, the poultry weight data and the metabolic index signals are subjected to signal filtering processing to remove noise interference, a body weight growth rate is calculated according to the data after filtering processing to generate a body weight growth rate curve, and metabolic intensity changes are analyzed according to the metabolic index signals after filtering processing to generate a metabolic intensity fluctuation curve.

[0012] In combination with the first aspect, in a second implementation manner of the first aspect of the present application, the physiological demand vector of a current growth stage is obtained, including:

[0013] Characteristic data of the body weight growth rate curve and the metabolic intensity fluctuation curve is extracted through a parameter fusion algorithm, a feather development model is established and trained based on historical poultry growth data and physiological index data, the characteristic data is input into the feather development model, the feather development model divides a growth process of the poultry into multiple growth stages, a current growth stage of the poultry is judged based on a threshold value of the characteristic data, a physiological demand vector corresponding to the current growth stage is obtained, including a nutritional demand, a temperature demand and a ventilation demand component.

[0014] In a third implementation form of the first aspect, the method further includes: evaluating the feather development degree of the poultry based on the physiological demand vector to obtain a quantitative score, including: determining whether the physiological demand vector exceeds a preset threshold; and if the physiological demand vector exceeds the preset threshold, activating a dynamic evaluation module.

[0015] determining whether the physiological demand vector exceeds a preset threshold; and if the physiological demand vector exceeds the preset threshold, activating a dynamic evaluation module.

[0016] loading an image acquisition device to acquire an image of the poultry.

[0017] extracting feather texture features of the image of the poultry based on a convolutional neural network algorithm, and calculating a feather coverage density.

[0018] calculating a quantitative score of the feather development degree according to the feather coverage density.

[0019] In a fourth implementation form of the first aspect, the method further includes: calculating the feather coverage density, including:

[0020] performing pixel-level segmentation on a feather region of the image of the poultry based on a semantic segmentation algorithm, calculating a feather coverage area proportion based on a segmentation result, and obtaining the feather coverage density.

[0021] In a fifth implementation form of the first aspect, the method further includes: calculating the wind speed adjustment parameter based on the correlation, including:

[0022] mapping the quantitative score and the physiological demand vector to a preset fuzzy set through a fuzzy logic algorithm, performing fuzzy reasoning in combination with a rule base to obtain a correlation value between the physiological demand of the poultry and the environmental control parameter;

[0023] multiplying the correlation value by a preset weight factor to obtain a preliminary coefficient, limiting the preliminary coefficient in a preset range through linear interpolation, and generating a wind speed intensity adjustment coefficient;

[0024] generating a wind volume transition parameter according to the wind speed intensity adjustment coefficient, wherein the wind volume transition parameter gradually transitions from a current wind volume to a target wind volume in a sequence form;

[0025] performing smoothing processing on the wind volume transition parameter to obtain a stable wind speed adjustment parameter.

[0026] In a sixth implementation form of the first aspect, the method further includes: generating a sequence of airflow distribution patterns based on the wind speed adjustment parameter, and determining whether there is a fluctuation anomaly, including:

[0027] inputting the wind speed adjustment parameter into a sequence generation function to calculate an initial sequence of airflow distribution patterns;

[0028] computing the difference of wind speed values between adjacent time points in the initial airflow distribution pattern sequence to obtain a fluctuation amplitude sequence, comparing the fluctuation amplitude sequence with a preset fluctuation threshold, and marking as abnormal if exceeding the threshold;

[0029] If there is an abnormality, correcting the wind speed distribution weight based on the position of the abnormal point, and using an iterative optimization algorithm to adjust the wind speed, in each iteration, using the gradient descent method to minimize the fluctuation amplitude, until the fluctuation standard deviation is lower than the preset threshold or the maximum number of iterations is reached, and outputting the optimized airflow distribution pattern;

[0030] According to the optimized airflow distribution pattern, extracting the time series wind speed value, and using the spline interpolation method to generate a continuous signal, and performing low-pass filtering on the continuous signal to obtain a smooth transition wind speed control signal.

[0031] In combination with the first aspect, in a seventh implementation manner of the first aspect of the present application, the ventilation equipment adjusts the wind speed intensity and the ventilation frequency, including:

[0032] The wind speed control signal is converted into a digital instruction sequence and transmitted to the ventilation equipment actuator, and the ventilation equipment actuator parses the digital instruction sequence to obtain the wind speed intensity value and the ventilation frequency parameter.

[0033] In combination with the first aspect, in an eighth implementation manner of the first aspect of the present application, determining the physiological demand vector adjustment value of the next period, including:

[0034] The air quality feedback data is input into the feather development model, the weight parameters of the feather development model are updated through a machine learning algorithm, the body weight growth rate curve and the metabolic intensity fluctuation curve are recalculated according to the updated model, the growth slope and the peak point are extracted from the body weight growth rate curve, the fluctuation amplitude and the cycle length are extracted from the metabolic intensity fluctuation curve, and the extracted parameters are mapped to the physiological demand vector space to generate the physiological demand vector adjustment value of the next period.

[0035] Secondly, the present application provides an adaptive control system for a poultry house environment, which comprises:

[0036] The acquisition module acquires physiological data of poultry through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve, and determines a physiological demand vector based on the body weight growth rate curve and the metabolic intensity fluctuation curve in combination with a preset feather development model;

[0037] The evaluation module evaluates the feather development degree of poultry based on the physiological demand vector to obtain a quantitative score, analyzes the correlation between the quantitative score and the physiological demand vector, and calculates a wind speed adjustment parameter based on the correlation;

[0038] An adjusting module generates a sequence of air flow distribution patterns based on the wind speed adjustment parameters, judges whether there is a fluctuation anomaly, optimizes a wind speed control signal, and transmits the wind speed control signal to a ventilation device, which adjusts the wind speed intensity and ventilation frequency.

[0039] A feedback module collects air quality feedback data in the poultry house in real time, inputs the air quality feedback data into the feather development model, determines an adjustment value of the physiological demand vector in the next period, and generates a breeding benefit evaluation report according to the adjustment value and the dynamic fluctuation data.

[0040] Compared with the prior art, the present application has at least the following advantages:

[0041] The present application provides a poultry house environment adaptive regulation method, which can adjust environmental parameters such as temperature and ventilation in real time according to physiological data such as poultry weight gain rate and metabolic intensity fluctuation, and optimize the internal environment of the poultry house. In the method of the present application, physiological data of poultry are collected by a sensor array, a physiological demand vector of poultry is accurately calculated in combination with a feather development model, and wind speed and ventilation frequency are adjusted in real time based on these demands, thereby effectively reducing unnecessary energy consumption. At the same time, the wind speed is adjusted by a fuzzy logic algorithm, so that the response of the ventilation system is more sensitive and accurate, and fluctuations and errors caused by fixed threshold adjustment in traditional methods are avoided, thereby significantly improving the stability and sustainability of the ventilation effect. The present application can also dynamically adjust the ventilation and temperature control parameters according to different growth stages of poultry and environmental changes, reduce the negative impact of stress reaction on poultry growth, improve the comfort and health level of poultry, and thereby optimize the breeding benefit. In addition, by collecting air quality feedback data in real time and inputting it into the feather development model, the physiological demand vector can be further adjusted to provide more accurate basis for the environmental regulation in the next period, effectively realize the high matching between environmental control and poultry demand, improve the breeding efficiency, reduce the energy consumption and improve the overall health and production benefit of poultry. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without any creative labor.

[0043] Figure 1 An embodiment schematic diagram of a poultry house environment adaptive regulation method in the present application;

[0044] Figure 2 A flowchart of fluctuation anomaly judgment processing in the present application;

[0045] Figure 3 A ventilation effect comparison chart in the embodiment of the present application;

[0046] Figure 4 An embodiment schematic diagram of a poultry house environment adaptive regulation system in the embodiment of the present application. DETAILED DESCRIPTION

[0047] The embodiment of the present application provides a poultry house environment adaptive regulation method and system. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0048] For the convenience of understanding, the specific process of the embodiment of the present application is described below. Please refer to Figure 1 An embodiment of a poultry house environment adaptive regulation method in the embodiment of the present application comprises the following steps.

[0049] Step S1, acquiring poultry physiological data through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve, and determining a physiological demand vector according to the body weight growth rate curve and the metabolic intensity fluctuation curve in combination with a preset feather development model.

[0050] In modern poultry (such as chickens, ducks, geese, etc.) breeding process, environmental factors have an important influence on the growth and development of poultry, especially the fluctuation of physiological indicators such as body weight gain and metabolic intensity, which directly determines the health status and breeding benefit of poultry. The traditional breeding environment regulation method mostly relies on manual experience and single sensor monitoring, lacking precise understanding and dynamic adjustment of the physiological needs of poultry. In order to improve the breeding efficiency and reduce the cost, the present application acquires the physiological data of poultry in real time through the sensor array, and dynamically determines the physiological demand vector of poultry combined with the preset feather development model, so as to intelligently regulate the environmental parameters. Specifically, a plurality of sensor arrays are arranged in the poultry house, including weighing sensors, infrared sensors and the like, which are used to acquire the physiological data of poultry in real time, including poultry weight data and metabolic index data (such as body temperature, respiratory rate, etc.). The acquired weight data is subjected to median filtering to remove outliers and noise, and then the weight increment per unit time is calculated to generate a body weight gain rate curve. The metabolic index signal is subjected to low-pass filtering to remove high-frequency noise and interference, and the change trend of metabolic intensity is extracted to generate a metabolic intensity fluctuation curve. The characteristic data of the body weight gain rate curve and the metabolic intensity fluctuation curve are input into the preset feather development model, and the feather development model outputs the analysis results of the body weight gain rate and the metabolic intensity to generate the physiological demand vector of the current poultry. The vector includes environmental parameters such as temperature demand, humidity demand and ventilation demand. In order to facilitate subsequent environmental regulation, the obtained physiological demand vector is subjected to standardization processing, and the value of each demand item is mapped to the [0, 1] interval through the minimum-maximum normalization method, ensuring the consistency and comparability of the data. By dynamically generating the environmental parameters required for poultry growth based on real-time physiological data, it ensures that the environmental control equipment can respond to the needs of poultry in real time, significantly improving the accuracy and dynamic adaptability of environmental regulation.

[0051] Step S2, based on the physiological demand vector, the feather development degree of poultry is evaluated to obtain a quantitative score, the correlation between the quantitative score and the physiological demand vector is analyzed, and a wind speed adjustment parameter is calculated based on the correlation.

[0052] Specifically, in poultry breeding, feather development is strongly affected by physiological needs (such as nutrition, temperature, humidity, etc.), in order to accurately regulate the breeding environment, the application proposes to evaluate the degree of feather development of poultry based on the physiological demand vector, if a dimension of the physiological demand vector exceeds the preset threshold, the subsequent evaluation process is triggered, the poultry is photographed using an image acquisition device, image data of the poultry feathers is obtained, the image data is input into a convolutional neural network algorithm, the feather texture features are extracted, based on the extracted feather texture features, the feather coverage density is calculated, according to the feather coverage density, it is mapped to a quantitative score of 0-100, the correlation between the quantitative score and the physiological demand vector is analyzed through a fuzzy logic algorithm, based on the correlation value multiplied by a preset weight factor, a preliminary coefficient is generated, and the preliminary coefficient is limited in a preset range through linear interpolation to obtain a wind speed intensity adjustment coefficient. Through the correlation analysis of the quantitative score and the physiological demand vector, the wind speed adjustment parameter is accurately calculated, the air circulation and temperature and humidity control in the poultry house are optimized, the comfort of the breeding environment is significantly improved, the negative impact of stress reaction on poultry growth is reduced, and the breeding benefit is improved.

[0053] Step S3, based on the wind speed adjustment parameter, a sequence of air flow distribution patterns is generated, and it is judged whether there is a fluctuation anomaly, and a wind speed control signal is optimized, the wind speed control signal is transmitted to the ventilation equipment, and the ventilation equipment adjusts the wind speed intensity and the ventilation frequency.

[0054] Specifically, in the modern poultry breeding process, the air quality and air flow distribution in the poultry house directly affect the growth and health of poultry. Wind speed and ventilation frequency are important parameters for regulating air circulation, maintaining appropriate temperature and humidity in the poultry house. The wind speed adjustment parameter is input into the air flow distribution pattern generation function to generate a preliminary air flow distribution pattern sequence. The sequence represents a series of wind speed values at corresponding time points, ensuring that the wind speed covers the entire poultry house space, thereby achieving uniform air circulation. The generated air flow distribution pattern sequence is subjected to fluctuation analysis. The difference between the wind speed values at adjacent time points is calculated to obtain a fluctuation amplitude sequence, which is compared with a preset fluctuation threshold. If the fluctuation amplitude exceeds the threshold, it is marked as abnormal, indicating uneven air flow distribution, which may cause local high-temperature or low-oxygen areas, affecting poultry health. If a fluctuation anomaly is detected, an iterative optimization algorithm is started to smooth the wind speed changes by adjusting the air flow distribution pattern. Based on the optimized air flow distribution pattern, continuous wind speed control signals are generated. The generated wind speed control signals are subjected to low-pass filtering to remove high-frequency noise and ensure smooth signal transitions. The optimized wind speed control signals are stored in a database for subsequent use. The wind speed control signals are transmitted to the actuator of the ventilation equipment through a wireless communication module to drive the ventilation equipment to adjust the wind speed intensity and ventilation frequency in real time. According to the real-time physiological needs and environmental feedback, the wind speed and ventilation frequency in the poultry house are dynamically adjusted to avoid stress reactions and environmental instability caused by excessive wind speed fluctuations. The optimized air flow distribution pattern not only improves the uniformity of air circulation in the poultry house but also ensures the smooth operation of the ventilation equipment, thereby improving the comfort and growth efficiency of poultry and reducing the negative impact of the environment on growth.

[0055] Step S4, real-time collection of air quality feedback data in the poultry house, input of the air quality feedback data into the feather development model to determine the physiological demand vector adjustment value for the next period, generation of a breeding benefit evaluation report according to the adjustment value and dynamic fluctuation data.

[0056] Specifically, using air quality sensors installed at key locations in the poultry house, real-time collection of carbon dioxide concentration, ammonia level, and temperature and humidity, etc. Air quality data, pre-processing of collected air quality data, removing noise and irregular fluctuations, obtaining air quality feedback data, inputting real-time collected air quality feedback data into the feather development model, the model is trained by historical growth data, combined with the influence of air quality changes on poultry growth, output the physiological demand vector of the current growth stage, including temperature demand, humidity demand, ventilation demand, etc. Component, thereby dynamically adjusting the environmental control strategy. By analyzing the trend of air quality data such as temperature and carbon dioxide concentration, combined with the metabolic intensity fluctuation curve, it is judged whether the air speed or ventilation frequency needs to be adjusted, according to the adjusted physiological demand vector and dynamic fluctuation data, generate breeding benefit evaluation report, which includes breeding efficiency, energy consumption analysis, temperature and humidity optimization effect and poultry health status evaluation content. Based on the dynamic physiological demand adjustment of real-time air quality data, ensure that the environmental regulation accurately adapts to the physiological changes of poultry, avoid excessive or insufficient adjustment, and the combination of air quality feedback and feather development model effectively improves the comfort of the breeding environment, reduces the occurrence of stress response, and thus improves the growth efficiency and breeding benefit of poultry. In addition, through the generation of breeding benefit evaluation report, potential problems can be identified in time, further optimizing the environmental control strategy, and improving the intelligent level of breeding management.

[0057] In a specific embodiment, the poultry physiological data collected by the sensor array includes the following steps:

[0058] The poultry physiological data collected by the sensor array includes poultry weight data and metabolic index signals. The poultry weight data and metabolic index signals are subjected to signal filtering processing to remove noise interference. According to the data after filtering processing, the weight gain rate is calculated to generate a weight gain rate curve. According to the metabolic index signals after filtering processing, the metabolic intensity change is analyzed to generate a metabolic intensity fluctuation curve.

[0059] Specifically, the weight change of the poultry is captured in real time using a load cell, and the weight data is recorded every minute. Metabolic indicator data such as body temperature and respiratory rate are collected by an infrared sensor. The collected weight data and metabolic indicator signals are filtered to remove noise and interference. For the weight data, a median filter is applied with a window size of 5 sampling points to effectively remove sudden noise caused by the activity of the poultry. For the metabolic indicator data, a low-pass filter is used to suppress high-frequency interference and retain the core frequency band of the metabolic signal to ensure signal smoothness. The filtered weight data is subjected to difference calculation to obtain the weight increment per unit time. A least squares method is used to fit a polynomial curve to generate a smooth weight gain rate curve. The metabolic indicator signal is subjected to Fourier transform to extract periodic fluctuation components and identify the metabolic intensity fluctuation pattern. Based on the Fourier transform analysis results, a spline interpolation method is used to smoothly connect the data points to generate a smooth metabolic intensity fluctuation curve, further quantifying the fluctuation amplitude. The generated weight gain rate curve and metabolic intensity fluctuation curve are converted to a standard format, time stamps and poultry identifiers are added to each curve data, and stored in a database to ensure data traceability. The stored weight gain rate curve and metabolic intensity fluctuation curve can be used as basic data for subsequent physiological demand vector generation and input into the feather development model for further analysis of the physiological needs of the poultry and real-time adjustment of the breeding environment.

[0060] In a specific embodiment, obtaining the physiological demand vector of the current growth stage specifically includes the following steps:

[0061] Through a parameter fusion algorithm, the characteristic data of the weight gain rate curve and the metabolic intensity fluctuation curve are extracted. A feather development model is established and trained based on historical poultry growth data and physiological indicator data. The characteristic data is input into the feather development model. The feather development model divides the growth process of the poultry into multiple growth stages. The current growth stage of the poultry is determined based on the threshold value of the characteristic data. The physiological demand vector corresponding to the current growth stage is obtained, including the nutritional demand, temperature demand, and ventilation demand components.

[0062] Specifically, based on historical poultry growth data and physiological indicators, a Logistic growth function is used to establish a feather development model. This model is used to describe the change of feather coverage rate over time, and the formula is as follows: wherein, is the maximum feather coverage rate, is the growth rate, For the inflection point time, the parameters of the model are determined by fitting the historical poultry growth data and physiological indicators by the least squares method, and the key feature data in the body weight growth rate and metabolic intensity fluctuation curve are extracted using a parameter fusion algorithm, such as using a weighted average fusion method to weight the sum of the slope peak value of the body weight growth rate curve and the amplitude variance of the metabolic intensity fluctuation curve, and the weight is calculated based on the Pearson correlation coefficient. The principal component analysis (PCA) is applied to the fused feature vector, and the first two principal components are retained as the extracted feature data. The feature data is input into the feather development model, and the feather development model determines the growth stage of the poultry according to the threshold value of the feature data, such as the neonatal period, the growth period and the mature period. For example, when the average growth rate exceeds 0.04 kg / day, the poultry is classified as the growth period, and the corresponding physiological demand vector is generated, such as [25°C, 60% humidity, 0.5 m / s wind speed]. Through the above steps, the physiological demand vector that meets the current growth stage is dynamically generated according to the body weight growth rate and metabolic intensity fluctuation of the poultry, which not only provides a scientific basis for subsequent environmental control, but also ensures the real-time optimization of the breeding environment, avoiding the negative impact of excessive or insufficient ventilation, temperature and humidity adjustment on poultry growth.

[0063] In a specific embodiment, the evaluation of the degree of feather development of the poultry based on the physiological demand vector to obtain a quantitative score specifically includes the following steps:

[0064] determining whether the physiological demand vector exceeds a preset threshold value, and if the preset threshold value is exceeded, activating the dynamic evaluation module;

[0065] The dynamic evaluation module loads the image acquisition device to collect the images of the poultry;

[0066] extracting the feather texture features of the poultry images based on the convolutional neural network algorithm, and calculating the feather coverage density;

[0067] According to the feather coverage density, the quantitative score of the feather development degree is calculated.

[0068] Specifically, the values of each dimension in the physiological demand vector, such as nutritional demand, temperature demand, and ventilation demand, are compared with the preset threshold value. If a certain dimension exceeds 80% of the threshold value (for example, the nutritional demand is greater than 80%), it is determined that the overall physiological demand vector exceeds the threshold value, and the dynamic assessment module is activated. This module loads image acquisition devices (such as cameras or infrared imagers) to capture image data of the bird's feathers. Through image recognition algorithms such as convolutional neural network algorithms, the collected bird images are first preprocessed to remove background noise, highlight the feather area, and extract feather texture features such as feather edges and color changes from the image. The feather coverage density is calculated, and the specific calculation method is described later. According to the feather coverage density, it is mapped to a quantitative score of 0-100 points through a weight formula. Combined with historical data (such as the average feather coverage density in the previous period), the quantitative score is calculated using a weighted formula: Quantitative score = density x 0.8 + historical average x 0.2. For example, if the current feather coverage density is 75% and the historical average is 70%, the quantitative score = 75 x 0.8 + 70 x 0.2 = 74. In different poultry farming scenarios (such as chicks and adult chickens), the density threshold and score calculation method are different. For example, for chicks, the density threshold is set to 50%, and the age factor is integrated into the calculation, such as For adult chickens, the uniformity of feather density is emphasized, Score = average density x uniformity coefficient. By combining the physiological demand vector with image recognition algorithms, the degree of feather development in poultry is accurately assessed, and a quantitative score is generated. This dynamically responds to changes in the growth stage of poultry, optimizes the regulation of the breeding environment, and avoids the impact of excessive or insufficient environmental regulation on poultry.

[0069] In a specific embodiment, calculating the feather coverage density specifically includes the following steps:

[0070] Based on the semantic segmentation algorithm, the feather area of the poultry image is segmented at the pixel level. Based on the segmentation results, the feather coverage area ratio is calculated to obtain the feather coverage density.

[0071] Specifically, a convolutional neural network model, especially U-Net or MaskR-CNN in deep learning, is used for semantic segmentation. The model assigns a label to each pixel in the poultry image, marking it as a feather area or a background area. The pixel count of the feather area is calculated by counting the pixels in the semantically segmented image. Assuming that the total number of pixels in the image is , the number of pixels in the feather area is , and the feather coverage density is calculated based on the following formula: . Assuming that the resolution of the collected poultry image is 1000x1000 pixels, = 1000000 pixels, and the number of pixels in the feather area is identified by the semantic segmentation algorithm = 700000 pixels, the plumage coverage density of the bird is 70%, meaning that 70% of the area in the image is covered by plumage. However, the color and texture of the plumage can be similar to the background color, causing segmentation errors. To improve the accuracy of the calculation, a template matching method can be used to compare the current image with a standard plumage template and adjust the deviation of the segmentation result.

[0072] In a specific embodiment, the calculating the wind speed adjustment parameter based on the correlation specifically comprises the following steps:

[0073] Mapping the quantification score and the physiological demand vector to a preset fuzzy set through a fuzzy logic algorithm, and performing fuzzy reasoning combined with a rule base to obtain a correlation value between the physiological demand of the bird and the environmental control parameter;

[0074] Multiplying the correlation value by a preset weight factor to obtain a preliminary coefficient, and limiting the preliminary coefficient within a preset range through linear interpolation to generate a wind speed intensity adjustment coefficient;

[0075] Generating a wind volume transition parameter according to the wind speed intensity adjustment coefficient, wherein the wind volume transition parameter gradually transitions from the current wind volume to the target wind volume in a sequence;

[0076] Performing smoothing processing on the wind volume transition parameter to obtain a stable wind speed adjustment parameter.

[0077] Specifically, the quantification score and the physiological demand vector are mapped to three fuzzy sets of "low", "medium", and "high", respectively. For example, if the quantification score is less than 0.4, it is mapped to the "low" fuzzy set; if the quantification score is between 0.4 and 0.7, it is mapped to the "medium" fuzzy set; and if the quantification score is greater than 0.7, it is mapped to the "high" fuzzy set. Assuming that the temperature demand component in the physiological demand vector is 0.6 and the wind speed demand component is 0.8, the temperature demand component 0.6 is mapped to the "medium" fuzzy set, and the wind speed demand component 0.8 is mapped to the "high" fuzzy set. In combination with the parameter fusion of the poultry feather development model, a fuzzy rule base is set, which defines the relevance between the quantification score and the physiological demand vector. For example, if the quantification score is mapped to the "low" fuzzy set and the wind speed demand component in the physiological demand vector is mapped to the "high" fuzzy set, the relevance is strong, indicating that the ventilation needs to be strengthened to meet the air demand caused by high metabolic intensity. If the quantification score is mapped to the "high" fuzzy set and the temperature demand in the physiological demand vector is mapped to the "medium" fuzzy set, the relevance is weak, indicating that the environmental change has a low requirement for temperature. A fuzzy reasoning method such as the Mamdani method is used for fuzzy reasoning. The relevance value between the quantification score and the physiological demand vector is obtained by calculating the values of the fuzzy sets and the rules in the rule base. For example, the quantification score is 0.3 (mapped to the "low" fuzzy set), and the wind speed demand is 0.8 (mapped to the "high" fuzzy set). According to the rule base, the relevance of this combination is strong. For another example, the quantification score is 0.5 (mapped to the "medium" fuzzy set), and the wind speed demand is 0.2 (mapped to the "low" fuzzy set). According to the rule base, the relevance of this combination is weak. Through the minimum maximum operation, the fuzzy reasoning result is converted into a numerical value between 0 and 1, representing the closeness between the physiological demand and the environmental control. For example, the calculated relevance is 0.8 (indicating that the physiological demand strongly matches the demand of the environmental control), and if the quantification score is "medium" and the wind speed demand is "low", the relevance is 0.3. According to the relevance value, the wind speed intensity adjustment coefficient is calculated. Assuming that the relevance value is 0.8, the wind speed intensity adjustment coefficient will be higher, and vice versa, if the relevance value is 0.3, the coefficient will be lower. Finally, the wind speed adjustment parameter is generated according to the coefficient, ensuring that the ventilation equipment adjusts the wind speed to meet the physiological needs of the poultry.

[0078] In a specific embodiment, generating the air flow distribution pattern sequence based on the wind speed adjustment parameter and determining whether there is a fluctuation anomaly specifically includes the following steps:

[0079] The wind speed adjustment parameter is input into the sequence generation function, and the initial air flow distribution pattern sequence is calculated;

[0080] The difference between the wind speed values at adjacent time points in the initial air flow distribution pattern sequence is calculated to obtain a fluctuation amplitude sequence. The fluctuation amplitude sequence is compared with a preset fluctuation threshold value. If it exceeds the threshold value, it is marked as an anomaly.

[0081] If an anomaly is found, the wind speed distribution weight is adjusted based on the location of the anomaly point, and an iterative optimization algorithm is used to adjust the wind speed. In each iteration, the gradient descent method is used to minimize the fluctuation amplitude until the standard deviation of the fluctuation is lower than the preset threshold or the maximum number of iterations is reached, at which point the optimized airflow distribution pattern is output.

[0082] The time series wind speed values ​​are extracted based on the optimized airflow distribution pattern, and a continuous signal is generated using spline interpolation. The continuous signal is then low-pass filtered to obtain a smooth-transition wind speed control signal.

[0083] Specifically, such as Figure 2 The diagram shows a flowchart for handling abnormal fluctuations. Wind speed adjustment parameters are input into an airflow distribution pattern generation function. This function calculates a series of wind speed distribution pattern sequences at different time points based on the input parameters. Assuming the wind speed adjustment parameters include a wind speed adjustment coefficient and ventilation frequency, and assuming the initial wind speed in the poultry house is 10 cubic meters per minute under basic conditions, the airflow distribution pattern generation function calculates the corresponding wind speed value at each time point using a wind speed adjustment coefficient of 1.5 and a ventilation frequency of 6 times per hour. Assuming the generated initial airflow distribution pattern is [10, 12, 14, 16, 15] (unit: cubic meters per minute), the difference in wind speed values ​​between adjacent time points in the initial airflow distribution pattern sequence is calculated to obtain a fluctuation amplitude sequence: [2, 2, 2, -1]. This fluctuation amplitude sequence is compared with a preset fluctuation threshold, assuming the preset threshold is 0.5 m / s. If the absolute value of the fluctuation amplitude is greater than this threshold, an abnormal fluctuation is considered to exist. In the above fluctuation amplitude sequence, the absolute values ​​of 2 and -1 both exceed 0.5, therefore they are marked as abnormal. If abnormal fluctuations are detected, the weights in the wind speed distribution pattern are adjusted based on the location of the abnormal point. For example, if a sudden increase or decrease in wind speed is detected at a certain moment (such as the third time point), the system will adjust the wind speed weights near that point to make the wind speed changes more stable. During the wind speed adjustment process, an iterative optimization algorithm (such as gradient descent) is applied to minimize the fluctuation amplitude. By gradually updating the wind speed distribution pattern, the fluctuation amplitude is ensured to be reduced below the threshold. In each iteration, the parameters of the wind speed distribution are adjusted by calculating the gradient of the loss function to reduce the fluctuation amplitude and obtain an optimized airflow distribution pattern. Wind speed values ​​are extracted from the optimized airflow distribution pattern, and a continuous wind speed control signal is generated using spline interpolation. Spline interpolation can connect discrete wind speed points by fitting a smooth curve to ensure a smooth transition of the wind speed control signal. By combining fuzzy logic algorithms with optimization algorithms, the wind speed distribution can be corrected through iterative optimization algorithms when abnormal wind speed fluctuations occur, making wind speed adjustments more accurate and ensuring the comfort of poultry at different growth stages.

[0084] In one specific embodiment, adjusting the wind speed intensity and ventilation frequency of the ventilation equipment specifically includes the following steps:

[0085] The wind speed control signal is converted into a digital instruction sequence and transmitted to the ventilation equipment actuator, which parses the digital instruction sequence to obtain the wind speed intensity value and the ventilation frequency parameter.

[0086] Specifically, the wind speed control signal is converted into a digital instruction sequence using a preset encoding protocol, which includes numerical value encoding of wind speed, ventilation frequency and other parameters through ASCII encoding or binary encoding method into digital signals, and necessary checksum and encryption. Assuming that the wind speed intensity is 4 m / s and the ventilation frequency is 6 times per hour, the generated digital instruction sequence is "V4.0T6.0", where "V" represents the wind speed intensity, "T" represents the ventilation frequency, and the digital instruction sequence is sent to the actuator interface through a wireless communication module (such as Wi-Fi, Bluetooth, Zigbee, etc.). In actual application, multiple control signals may be transmitted simultaneously, and these signals need to be prioritized. Generally, the priority of the wind speed adjustment signal depends on the urgency of the adjustment. For instructions that require significant adjustment of wind speed (such as from 2 m / s to 4 m / s), the priority is high. Through the priority sorting mechanism, the wind speed control signal can be efficiently transmitted to the actuator and start adjusting in the shortest time, avoiding the impact of transmission delay on the real-time performance of the poultry house ventilation. After the actuator receives the digital instruction sequence, it first parses and extracts the wind speed intensity and ventilation frequency values, such as extracting the wind speed intensity of 4 m / s and the ventilation frequency of 6 times / hour from the instruction "V4.0T6.0". According to the parsed parameters, the actuator drives the motor to adjust the fan speed. The wind speed intensity range is usually set between 2 and 5 m / s, and the ventilation frequency is set according to the growth needs of poultry, which is 4 to 8 times per hour. If the wind speed is adjusted to 4 m / s, the actuator will control the motor speed to reach that wind speed. The wind speed and ventilation frequency of the fan need to be accurately adjusted according to the current growth stage and physiological needs of the poultry. Through the above method, the wind speed control signal can be accurately and timely transmitted to the ventilation equipment actuator, and the actuator can accurately adjust the speed and wind speed of the fan according to the parsed wind speed intensity and ventilation frequency. The priority sorting mechanism ensures that the signal can respond quickly, thereby optimizing the air quality in the poultry house.

[0087] In a specific embodiment, determining the physiological demand vector adjustment value of the next period specifically includes the following steps:

[0088] The air quality feedback data is input into the feather development model, the weight parameters of the feather development model are updated through a machine learning algorithm, the body weight growth rate curve and the metabolic intensity fluctuation curve are recalculated according to the updated model, the growth slope and peak point are extracted from the body weight growth rate curve, the fluctuation amplitude and cycle length are extracted from the metabolic intensity fluctuation curve, and the extracted parameters (such as growth slope, fluctuation amplitude, etc.) are mapped to the physiological demand vector space to generate the physiological demand vector adjustment value of the next cycle.

[0089] Specifically, after the ventilation equipment adjusts the wind speed intensity and ventilation frequency, real-time air quality feedback data is collected, assuming that the air quality feedback data includes a carbon dioxide concentration of 650 ppm, an ammonia concentration of 35 ppm, a temperature of 28°C, and a humidity of 60%, the collected air quality feedback data is input into the feather development model, the feather development model is trained based on historical body weight data and physiological indicators, and the physiological needs of the poultry are predicted in combination with environmental data, the weight parameters of the model are updated through a machine learning algorithm, and the body weight growth rate curve of the next cycle is calculated through the model according to the body weight data of the current growth stage, assuming that the body weight growth rate of the poultry in the current growth stage is 0.05 kg per day, the updated prediction model may predict that the growth rate increases to 0.07 kg per day according to the needs of environmental adjustment; according to the same updated model, the metabolic intensity fluctuation curve is calculated, assuming that the current metabolic intensity fluctuation amplitude is 20%, after the updated model, the metabolic intensity fluctuation curve may appear a new periodic fluctuation, reflecting the influence of environmental changes on metabolic intensity; the growth slope is extracted from the body weight growth rate curve, indicating the weight gain rate of the poultry in the current stage, and the fluctuation amplitude and cycle length are extracted from the metabolic intensity fluctuation curve, the extracted parameters (such as growth slope, fluctuation amplitude, etc.) are mapped to the physiological demand vector space to generate the physiological demand vector adjustment value of the next cycle, for example, the slope of the body weight growth rate is 0.07 kg / day, and the fluctuation amplitude of the metabolic intensity is 25%, the generated physiological demand vector adjustment value may be: nutritional demand [10% increase], temperature demand [keep unchanged], ventilation demand [15% increase]. Based on the real-time collected air quality feedback data and the machine learning algorithm to update the weight parameters of the feather development model, the physiological demand vector adjustment value of the poultry can be accurately calculated. Through this process, the system can dynamically adapt to environmental changes, ensuring that environmental adjustment parameters such as wind speed, temperature, and ventilation frequency accurately match the actual needs of the poultry in different growth stages, reducing unnecessary resource waste, improving the comfort of the poultry and promoting healthy growth.

[0090] For example, Figure 3As shown, it is a comparison chart of ventilation effect, traditional method ventilation (gray solid line): this line shows the change of ventilation intensity in the poultry house under the traditional method, which usually adjusts ventilation according to the set fixed threshold, which may not be flexible enough, and the fluctuation of ventilation intensity is large, which reflects that the traditional method responds slowly to environmental changes, and there may be over-ventilation or insufficient ventilation. The ventilation of the method of the present application (black dotted line): this line shows the ventilation adjustment based on the method of the present application, which adjusts in real time according to the physiological needs of poultry, feather development, metabolic intensity and other data, can more finely control the ventilation intensity, makes it more stable and responds to environmental changes, through this adaptive regulation, the fluctuation of ventilation intensity is relatively small, and is better maintained in the appropriate range.

[0091] The above describes a poultry house environment adaptive regulation method in an embodiment of the present application, and the following describes a poultry house environment adaptive regulation system in an embodiment of the present application, please refer to Figure 4 An embodiment of a poultry house environment adaptive regulation system in an embodiment of the present application includes:

[0092] The acquisition module acquires physiological data of poultry through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve, and determines a physiological demand vector according to the body weight growth rate curve and the metabolic intensity fluctuation curve in combination with a preset feather development model;

[0093] The evaluation module evaluates the feather development degree of poultry based on the physiological demand vector to obtain a quantitative score, analyzes the relevance between the quantitative score and the physiological demand vector, and calculates a wind speed adjustment parameter based on the relevance;

[0094] The adjustment module generates an air flow distribution pattern sequence based on the wind speed adjustment parameter, judges whether there is a fluctuation anomaly, optimizes to obtain a wind speed control signal, transmits the wind speed control signal to a ventilation equipment, and the ventilation equipment adjusts the wind speed intensity and the ventilation frequency;

[0095] The feedback module acquires air quality feedback data in the poultry house in real time, inputs the air quality feedback data into the feather development model to determine an adjustment value of the physiological demand vector in the next period, and generates a breeding benefit evaluation report according to the adjustment value and dynamic fluctuation data.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, system and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0097] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0098] The above description and the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of adaptive regulation of an aviary environment, characterized in that, The method comprises: Step S1: acquiring poultry physiological data through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve, and determining a physiological demand vector according to the body weight growth rate curve and the metabolic intensity fluctuation curve in combination with a preset feather development model; Step S2: evaluating a feather development degree of the poultry based on the physiological demand vector to obtain a quantitative score, analyzing the correlation between the quantitative score and the physiological demand vector, and calculating a wind speed adjustment parameter based on the correlation; Step S3: generating an air flow distribution mode sequence based on the wind speed adjustment parameter, judging whether there is a fluctuation anomaly, and optimizing to obtain a wind speed control signal, wherein the wind speed control signal is transmitted to a ventilation device, and the ventilation device adjusts wind speed intensity and ventilation frequency; Step S4: acquiring air quality feedback data in a poultry house in real time, inputting the air quality feedback data into the feather development model to determine an adjustment value of the physiological demand vector in a next period, and generating a breeding benefit evaluation report according to the adjustment value and dynamic fluctuation data.

2. The method of claim 1, wherein, Acquiring poultry physiological data through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve comprises: The poultry physiological data acquired through the sensor array comprises poultry weight data and metabolic index signals, the poultry weight data and the metabolic index signals are subjected to signal filtering processing to remove noise interference, a body weight growth rate is calculated according to the data after filtering processing to generate a body weight growth rate curve, and metabolic intensity changes are analyzed according to the metabolic index signals after filtering processing to generate a metabolic intensity fluctuation curve.

3. The method of claim 1, wherein, Obtaining a physiological demand vector of a current growth stage comprises: Characteristic data of the body weight growth rate curve and the metabolic intensity fluctuation curve are extracted through a parameter fusion algorithm, a feather development model is established and trained based on historical poultry growth data and physiological index data, the characteristic data are input into the feather development model, the feather development model divides a growth process of the poultry into multiple growth stages, a current growth stage of the poultry is judged based on a threshold value of the characteristic data, a physiological demand vector corresponding to the current growth stage is obtained, and the physiological demand vector comprises a nutritional demand, a temperature demand and a ventilation demand component.

4. The method of claim 1, wherein, Evaluating a feather development degree of the poultry based on the physiological demand vector to obtain a quantitative score comprises: It is judged whether the physiological demand vector exceeds a preset threshold value, and if so, a dynamic evaluation module is activated; The dynamic evaluation module loads an image acquisition device to acquire poultry images; Feather texture features of the poultry images are extracted based on a convolutional neural network algorithm to calculate a feather coverage density; A quantitative score of the feather development degree is calculated according to the feather coverage density.

5. The method of claim 4, wherein, Calculating the feather coverage density comprises: An image segmentation algorithm is used to perform pixel-level segmentation on a feather region of the poultry image, a feather coverage area proportion is calculated based on a segmentation result to obtain the feather coverage density.

6. The method of claim 1, wherein, Calculating a wind speed adjustment parameter based on the correlation comprises: The quantitative score and the physiological demand vector are mapped to a preset fuzzy set through a fuzzy logic algorithm, fuzzy reasoning is performed in combination with a rule base to obtain a correlation value between poultry physiological demands and environmental control parameters; and The correlation value is multiplied by a preset weight factor to obtain a preliminary coefficient, and the preliminary coefficient is limited in a preset range by linear interpolation to generate a wind speed intensity adjustment coefficient; A wind volume transition parameter is generated according to the wind speed intensity adjustment coefficient, wherein the wind volume transition parameter gradually transitions from a current wind volume to a target wind volume in a sequence form; The wind volume transition parameter is smoothed to obtain a stable wind speed adjustment parameter.

7. The method of claim 1, wherein, Based on the wind speed adjustment parameter, a sequence of airflow distribution patterns is generated, and it is determined whether there is a fluctuation anomaly, including: The wind speed adjustment parameter is input into a sequence generation function to calculate an initial sequence of airflow distribution patterns; The difference between the wind speed values at adjacent time points in the initial sequence of airflow distribution patterns is calculated to obtain a fluctuation amplitude sequence, and the fluctuation amplitude sequence is compared with a preset fluctuation threshold value, and if it exceeds the threshold value, it is marked as abnormal; If there is an abnormality, the wind speed distribution weight is corrected based on the position of the abnormal point, and an iterative optimization algorithm is used for wind speed adjustment, and in each iteration, the gradient descent method is used to minimize the fluctuation amplitude until the fluctuation standard deviation is lower than the preset threshold value or the maximum number of iterations is reached, and the optimized airflow distribution pattern is output; According to the optimized airflow distribution pattern, a time sequence wind speed value is extracted, and a spline interpolation method is used to generate a continuous signal, and the continuous signal is low-pass filtered to obtain a smoothly transitioned wind speed control signal.

8. The method of claim 1, wherein, The ventilation equipment adjusts the wind speed intensity and ventilation frequency, including: The wind speed control signal is converted into a digital instruction sequence and transmitted to a ventilation equipment actuator, and the ventilation equipment actuator parses the digital instruction sequence to obtain a wind speed intensity value and a ventilation frequency parameter.

9. The method of claim 1, wherein, Determining the physiological demand vector adjustment value of the next period includes: The air quality feedback data is input into a feather development model, the weight parameters of the feather development model are updated through a machine learning algorithm, the body weight growth rate curve and the metabolic intensity fluctuation curve are recalculated according to the updated model, the growth slope and peak point are extracted from the body weight growth rate curve, the fluctuation amplitude and cycle length are extracted from the metabolic intensity fluctuation curve, and the extracted parameters are mapped to the physiological demand vector space to generate the physiological demand vector adjustment value of the next period.

10. A poultry house environment adaptive regulation system for implementing a poultry house environment adaptive regulation method according to any one of claims 1-9, characterized in that, The system includes: A collection module acquires physiological data of poultry through a sensor array to obtain a body weight growth rate curve and a metabolic intensity fluctuation curve, and determines a physiological demand vector based on the body weight growth rate curve and the metabolic intensity fluctuation curve in combination with a preset feather development model; An evaluation module evaluates the feather development degree of poultry based on the physiological demand vector to obtain a quantitative score, analyzes the correlation between the quantitative score and the physiological demand vector, and calculates a wind speed adjustment parameter based on the correlation; An adjustment module generates a sequence of airflow distribution patterns based on the wind speed adjustment parameter and determines whether there is a fluctuation anomaly, optimizes to obtain a wind speed control signal, and transmits the wind speed control signal to a ventilation equipment, and the ventilation equipment adjusts the wind speed intensity and ventilation frequency. The feedback module collects air quality feedback data in the poultry house in real time, inputs the air quality feedback data into the feather development model, determines an adjustment value of the physiological demand vector in the next period, and generates a breeding benefit evaluation report according to the adjustment value and the dynamic fluctuation data.

Images