Mobile henhouse ventilation regulation and control method and system based on environment model

Abstract

The invention provides a mobile henhouse ventilation regulation and control method and system based on an environment model, and relates to the technical field of intelligent breeding, and the method comprises the steps: obtaining original temperature data, original humidity data, a three-dimensional space wind speed component, an opening geometric distribution data set, and original latitude and longitude coordinate data and time data; calculating a dynamic environment weight coefficient matrix according to the original latitude and longitude coordinate sequence and the time data; generating a self-adaptive heat exchange flow field according to the dynamic environment weight coefficient matrix, the original temperature data and the original humidity data; according to the self-adaptive heat exchange flow field and the trepanning geometric distribution data set, a ventilation compensation amount demand curve is obtained through calculation; generating a ventilation intensity adjusting instruction set according to the ventilation compensation amount demand curve; and according to the ventilation intensity adjusting instruction set, outputting an optimal ventilation control parameter. According to the method, ventilation response self-adaptive accurate matching, airflow dead zone self-suppression and energy consumption-effect dynamic balance under the moving sudden change working condition are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent farming technology, and in particular to a ventilation control method and system for a mobile chicken house based on an environmental model. Background Art

[0002] Mobile chicken houses, a key component of modern intensive farming, optimize pasture resource utilization and ecological restoration through periodic spatial displacement. However, the motion-environment interaction during movement significantly alters the boundary conditions of traditional ventilation control. Existing technologies primarily employ environmental threshold control strategies similar to those used in fixed chicken houses, triggering a stepwise start and stop of fans based on preset temperature and humidity parameters. While effective in static scenarios, these strategies struggle to adapt to mobile conditions. Firstly, the inertial force field disturbances and three-dimensional wind field variations caused by chicken house movement are not incorporated into the control model, resulting in systematic deviations between wind speed sensor data and the actual ambient airflow field. Secondly, the spatial heterogeneity of the opening distribution in the enclosure exacerbates the internal airflow dead zone effect under the influence of movement acceleration. Conventional technologies only estimate natural infiltration based on the static state and fail to account for the dynamic infiltration characteristics caused by trajectory changes. Especially when the direction of travel changes suddenly, traditional methods, lacking a synergistic coupling mechanism between motion parameters and environmental infiltration, often exhibit delayed ventilation response or overcompensation, leading to both a sharp increase in energy consumption and drastic fluctuations in the chicken microenvironment.

[0003] This inherent defect of using static rules to deal with dynamic processes seriously restricts the environmental control accuracy and energy efficiency of mobile poultry and livestock breeding equipment. Based on the shortcomings of the above-mentioned existing technologies, there is an urgent need for a mobile chicken house ventilation control method and system based on environmental models. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for controlling ventilation in a mobile chicken house based on an environmental model to improve the above-mentioned problem. To achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows: In a first aspect, the present application provides a method for controlling ventilation of a mobile chicken house based on an environmental model, comprising: Obtain the original temperature data inside and outside the mobile chicken house, original humidity data, three-dimensional wind speed components, the opening geometry distribution data set on the chicken house surface, and the original latitude and longitude coordinate data and time data during the chicken house movement; Constructing a position change rate field based on the original latitude and longitude coordinate sequence and the time data, and calculating a dynamic environment weight coefficient matrix based on the spatial distribution difference of the three-dimensional wind speed component; Fitting the environmental permeability gradient according to the dynamic environmental weight coefficient matrix, the original temperature data, and the original humidity data to generate an adaptive heat exchange flow field; Based on the adaptive heat exchange flow field and the opening geometric distribution data set, a preset fluid impedance network model is applied to invert the internal gas retention area, and a ventilation compensation demand curve for maintaining minimum airflow dead corners is calculated; Perform fan dynamic response modeling based on the ventilation compensation demand curve and the position change rate field to generate a ventilation intensity adjustment instruction set; According to the ventilation intensity adjustment instruction set and the three-dimensional space wind speed component, a dynamic game optimization algorithm is used to iteratively correct the fan action sequence, and output the optimal ventilation control parameters that meet the energy consumption-effect balance.

[0005] In a second aspect, the present application also provides a mobile chicken house ventilation control system based on an environmental model, comprising: The acquisition module is used to obtain the original temperature data inside and outside the mobile chicken house, the original humidity data, the three-dimensional wind speed component, the opening geometry distribution data set on the chicken house surface, and the original latitude and longitude coordinate data and time data during the chicken house movement; A construction module is used to construct a position change rate field based on the original latitude and longitude coordinate sequence and the time data, and calculate a dynamic environment weight coefficient matrix based on the spatial distribution difference of the three-dimensional wind speed component; A fitting module, configured to fit the environmental permeability gradient according to the dynamic environmental weight coefficient matrix, the original temperature data, and the original humidity data, to generate an adaptive heat exchange flow field; an inversion module for inverting the internal gas retention area using a preset fluid impedance network model based on the adaptive heat exchange flow field and the opening geometric distribution data set, and calculating a ventilation compensation demand curve for maintaining a minimum airflow dead zone; a modeling module, configured to perform fan dynamic response modeling based on the ventilation compensation demand curve and the position change rate field, and generate a ventilation intensity adjustment instruction set; The output module is used to iteratively correct the fan action sequence according to the ventilation intensity adjustment instruction set and the three-dimensional space wind speed component using a dynamic game optimization algorithm to output the optimal ventilation control parameters that meet the energy consumption-effect balance.

[0006] The beneficial effects of the present invention are: The present invention constructs a dynamic coupling mechanism between the position change rate field and three-dimensional environmental data, combines the spatial fluid network inversion of the opening distribution of the enclosure structure with the ventilation time lag compensation algorithm, and constructs a ventilation control mechanism with dynamic-structure-environment collaborative coupling, which realizes adaptive and precise matching of ventilation response under mobile mutation conditions, self-suppression of airflow dead zones, and dynamic balance between energy consumption and effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0008] Figure 1 A flow chart of a mobile chicken house ventilation control method based on an environmental model according to an embodiment of the present invention; Figure 2 This is a structural schematic diagram of the mobile chicken house ventilation control system based on the environmental model described in an embodiment of the present invention. Markings in the figure: 901, acquisition module; 902, construction module; 903, fitting module; 904, inversion module; 905, modeling module; 906, output module. DETAILED DESCRIPTION

[0009] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0010] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0011] Example 1:

[0012] This embodiment provides a ventilation control method for a mobile chicken house based on an environmental model.

[0013] See also Figure 1 , the figure shows that the method includes steps S100 to S600.

[0014] Step S100: Obtaining original temperature data inside and outside the mobile chicken house, original humidity data, three-dimensional wind speed components, a geometric distribution data set of openings on the chicken house surface, and original latitude and longitude coordinate data and time data during the chicken house movement process; Based on the dynamic environmental interference characteristics faced by mobile chicken houses during displacement in complex pasture terrain, the basic data of internal and external physical fields are synchronously collected, especially the original acquisition of the geometric topological characteristics of the open structure and the spatiotemporal imprint of the movement trajectory, providing the underlying input for subsequent dynamic coupling analysis that is not interfered by the preset model.

[0015] Step S200: constructing a position change rate field based on the original latitude and longitude coordinate sequence and time data, and calculating a dynamic environment weight coefficient matrix based on the spatial distribution difference of the three-dimensional wind speed component; To address the core problem of wind speed signal distortion caused by the movement of mobile devices, this step converts discrete position information into a continuous speed-direction field. By decoupling the spatial difference between the motion vector and the ambient wind speed, a real wind field weight is constructed to eliminate mechanical displacement artifacts.

[0016] Step S300: Fitting the environmental permeability gradient according to the dynamic environmental weight coefficient matrix and the original temperature data and the original humidity data to generate an adaptive heat exchange flow field; It can be understood that this step considers the interactive effect of the spatial non-uniform distribution of the temperature and humidity field and the moving inertia in the pasture environment, and through the differential reconstruction of the thermal and humidity parameters by the dynamic weight matrix, the traditional independent analysis of temperature and humidity is transformed into a continuous fitting of the thermodynamic integrated driving potential field, revealing the spontaneous infiltration law of the enclosing structure in a moving state.

[0017] Step S400: Based on the adaptive heat exchange flow field and the opening geometry distribution data set, a preset fluid impedance network model is applied to invert the internal gas retention area, and a ventilation compensation demand curve for maintaining the minimum airflow dead zone is calculated; To address the problem of non-uniform opening layout exacerbating airflow stagnation during turbulent movement, this step uses the differential mapping relationship between the structural topological network and the flow field to transform the physical hole distribution into a dynamic connection diagram of the fluid resistance nodes, realizing the causal inversion of structural characteristics and the formation mechanism of airflow dead spots.

[0018] Step S500: Perform fan dynamic response modeling based on the ventilation compensation demand curve and the position change rate field to generate a ventilation intensity adjustment instruction set; It should be noted that in order to address the problem of ventilation system response delay caused by sudden changes in mobile acceleration, this step establishes a time-varying coupling model of position change characteristics and demand curves, and actively pre-compensates for the delay effect through real-time quantification of mobile state mutation parameters, so that the ventilation action and the equipment motion state form dynamic synergy.

[0019] Step S600: Based on the ventilation intensity adjustment instruction set and the three-dimensional space wind speed component, a dynamic game optimization algorithm is used to iteratively correct the fan action sequence, and output optimal ventilation control parameters that meet the energy consumption-effect balance.

[0020] It is understandable that based on the dual constraints of natural wind mutability and energy consumption sensitivity in the pasture scenario, an equivalent game mechanism between instructions and real-time wind field kinetic energy is proposed, and the critical inflection point of the wind turbine characteristic curve is used as the energy consumption constraint boundary. A decision space that can be autonomously adjusted with the effect deviation is constructed to achieve control resilience optimization under complex mobile working conditions.

[0021] Furthermore, step S200 includes steps S210 to S230.

[0022] Step S210: Perform dynamic modeling of the movement trajectory based on the original latitude and longitude coordinate sequence and time data, and calculate the incremental ratio of the spatial distance and time difference between adjacent coordinate points to obtain a position change rate field including the movement speed value and the movement direction angle; Step S220: Perform environmental wind speed compensation processing based on the position change rate field, and obtain the real environmental wind speed vector that eliminates the influence of the chicken house's own movement by performing vector subtraction operation on the projection value of the three-dimensional wind speed component along the moving direction; Step S230: quantify the environmental effects based on the acceleration characteristics of the real environmental wind speed vector and the position change rate field, and map the weight coefficients through the coupling strength function of the moving direction mutation angle and the environmental wind speed vector to generate a dynamic environment weight coefficient matrix.

[0023] Specifically, this process targets the motion-environment coupling interference problem caused by mobile chicken houses moving on irregular terrain in pastures, and pioneers a method to reconstruct the weight of environmental effects from underlying physical quantities: first, based on the original sequence of latitude and longitude coordinates and timestamps, the real-time ratio of the Euclidean distance of adjacent points to the time interval is calculated to directly generate a position change rate field describing the motion state of the equipment. In this process, the spatial distance increment calculation avoids the dependence on GPS speed data, and can accurately capture the instantaneous speed and direction mutations when the pasture is steep or turning sharply; then the three-dimensional wind speed components are decomposed into east-west, north-south, and vertical axis data, and the motion direction is projected according to the direction angle in the position change rate field. The pollution of the equipment's self-movement on wind speed monitoring is removed by vector subtraction operation, which solves the data distortion problem of "headwind to tailwind" caused by mechanical displacement of the chicken house in traditional mobile equipment monitoring; finally, the acceleration characteristics of the position change rate field are combined with the angle of the real environmental wind speed vector Φ , construct the coupling strength function , where w represents the coupling strength function and k represents the adjustment coefficient, which is used to adjust the amplitude of the overall weight and the direction of the sudden change acceleration Strengthen the environmental impact weight of bumpy roads, cos Φ Dynamic adjustment is achieved based on the forward and reverse relationship between wind direction and equipment movement (for example, the weight of the feeding port area on the leeward side needs to be reduced), forming a dynamic environmental weight coefficient matrix that adapts to pasture displacement mutations and microenvironmental heterogeneity.

[0024] Furthermore, step S300 includes steps S310 to S330.

[0025] Step S310: Discretize the environmental effect space according to the dynamic environmental weight coefficient matrix, divide the heat and humidity effect sub-regions according to the physical property differences between the temperature field and the humidity field, and generate a discrete environmental factor influence spectrum; Step S320: Perform heat and mass exchange equivalent conversion processing based on the discrete environmental factor influence spectrum and the original temperature data and original humidity data, and obtain the comprehensive heat and moisture exchange potential field through bidirectional correction of the air enthalpy differential operator and the dew point change gradient; Step S330: Perform flux mapping processing on the chicken house enclosure structure according to the comprehensive potential field of heat and moisture exchange, and generate an adaptive heat exchange flow field by performing spatial convolution operation on the equivalent pore size distribution function of the porous medium and the potential gradient.

[0026] In response to the coupling effect of the spatial heterogeneity of the temperature and humidity field of the pasture environment and the microclimate response of mobile equipment, this application constructs a hierarchical heat and humidity driving field reconstruction mechanism: first, based on the spatial distribution characteristics of the dynamic environmental weight coefficient matrix, the inside and outside of the chicken house are divided into physical sub-areas with different heat and mass exchange sensitivities, such as high temperature and low humidity, low temperature and high humidity, etc. (such as the strong radiation area on the sunny side and the shadow area on the leeward side), and the discrete environmental factor influence spectrum is generated by quantitative partitioning of the differences in the physical characteristics of the temperature and humidity field; then, based on the influence spectrum, the original temperature data and humidity data are uniformly converted in terms of thermodynamic essence, and the heat and mass equivalence is quantified using the comprehensive characterization ability of air enthalpy for temperature and humidity. The method is used to process the moisture migration hysteresis effect by introducing the dew point change gradient and the two-way correction of the moisture migration hysteresis effect (such as the high humidity accumulation phenomenon in the bottom manure belt area) to construct a comprehensive heat and moisture exchange potential field that integrates sensible heat and latent heat. This potential field automatically enhances the humidity driving force weight in areas with intense grass evaporation. Finally, combined with the porous media characteristics of the mobile chicken house, such as the open side panels and ventilation windows, the equivalent pore size distribution function is used as the spatial convolution kernel. Through the three-dimensional convolution operation with the gradient of the moisture potential field, the adaptive flow mapping is realized to increase the natural infiltration flux in areas with dense structural openings and suppress eddy loss in areas with complex feeding port structures, and the heat and mass exchange capacity of the chicken house shell under the moving and bumpy state is quantified.

[0027] The formula for generating the influence spectrum of discrete environmental factors is: ;in Indicates the environmental factor affecting the spectrum value at position (x, y); W TRepresents the temperature sensitivity factor in the dynamic environment weight coefficient matrix (the value is 0.8-0.9 on the sun-facing side and 0.3-0.4 on the shaded side); Indicates the intensity of temperature gradient (maximum temperature difference between the calculation point and adjacent points, <2°C in grass-shaded area, >5°C in bare area); W H It represents the humidity sensitivity factor (the value is 0.7-0.8 in the bottom manure belt area and 0.2-0.3 in the top ventilation area); Represents the humidity diffusion gradient (evaporation effect coefficient in pasture covered area, 1.2-1.5 in rainy season).

[0028] The formula for constructing the comprehensive heat and moisture exchange potential field is: ; Where ψ represents the potential field value of the comprehensive heat and moisture exchange; c p represents the specific heat capacity of air at constant pressure; dT represents the differential increment of temperature; h fg represents the latent heat of water vaporization; dH represents the differential increment of humidity; λ represents the grass evaporation inhibition coefficient (0.6 when the grass height is >30 cm, and 0.3 in short grass areas); represents the dew point change gradient operator; e represents the natural base.

[0029] The formula for generating the adaptive heat exchange flow field is expressed as: ; where Φ(x,y) represents the heat exchange flow at position (x,y); A represents the equivalent pore size distribution function; S represents the structural attenuation factor (0.7 for screen structure and 0.9 for thin steel plate opening); η represents the bump compensation coefficient (1.3 for gravel road and 0.8 for flat grass); represents the normal gradient of the potential field (vertical change rate of the enclosure structure), Ψ represents the potential field value of the comprehensive effect of heat and moisture exchange, dx represents the differential length in the x direction, and dy represents the differential length in the y direction.

[0030] Furthermore, step S400 includes steps S410 to S430.

[0031] Step S410: Perform pore fluid dynamics modeling based on the pore geometry distribution dataset, and generate a dynamic pore connectivity network diagram by determining the topological connectivity of the angles between the spatial distance vectors of adjacent pores and the normals. Step S420: Identify the retention area based on the dynamic aperture connectivity network diagram and the adaptive heat exchange flow field, and determine the geometric boundary characteristics of the gas retention area by calculating the spatial differential relationship between the mean gradient of the inter-pore flow difference and the local static pressure difference. Step S430: Iteratively solve the compensation air volume based on the geometric boundary characteristics of the gas retention area, and generate a ventilation compensation demand curve through the flow distribution ratio optimization algorithm under the minimum airflow velocity threshold constraint.

[0032] This chain of steps uses a preset fluid impedance network model as its physical core. During the hole fluid dynamics modeling process, the geometric distribution of the openings is converted into a dynamic network diagram with directional impedance properties based on predefined inter-hole connectivity judgment rules (i.e., when the angle between the normal lines of adjacent openings is less than a preset threshold of 45 degrees, an impedance path is automatically generated). During the retention area identification stage, the inherent impedance characteristics of the network are directly involved in the differential operation of the mean gradient of the inter-hole flow difference, ensuring that the vortex effect generated by the bumps and vibrations of the gravel road surface is quantified as a static pressure anomaly under the impedance constraint. Finally, when solving the compensation air volume, the minimum airflow velocity threshold is converted into an equivalent pressure difference boundary through the preset impedance-flow conversion equation, driving the iterative optimization of the flow distribution ratio within the impedance network topology framework, thereby ensuring that high-impedance areas such as the feeding port receive sufficient compensation air volume under the steering and braking conditions to avoid haystacks. The flow distribution ratio optimization algorithm under the minimum airflow velocity threshold constraint is expressed as: Among them, Q comp (t) represents the total compensation air volume demand at time t; A i represents the equivalent ventilation area of ​​the ith retention zone; represents the total area of ​​all detention areas; i represents the detention area number; n represents the total number of detention areas; α represents the basic area allocation coefficient; β represents the dynamic compensation factor for steering conditions; represents the direction change response intensity of the i-th area; v min Indicates the minimum airflow velocity threshold; Indicates the road bump attenuation coefficient. The value is 0.7-0.8 (high-frequency suppression) on gravel roads and 1.0 (no attenuation) on flat grass.

[0033] Furthermore, step S500 includes steps S510 to S530.

[0034] Step S510: Performing a motion dynamics feature extraction process based on the position change rate field, and obtaining motion state mutation feature parameters by calculating the directional derivative of the velocity vector and the acceleration modulus; Step S520: quantify the time lag effect based on the movement state mutation characteristic parameter and the ventilation compensation demand curve, and generate a ventilation delay compensation time constant by performing a differential correction operation on the slope of the demand curve using acceleration; Step S530: Perform fan action pre-compensation processing according to the ventilation delay compensation time constant, reconstruct the response attenuation compensation coefficient by time axis translation of the demand curve and acceleration constraint, and generate a ventilation intensity adjustment instruction set.

[0035] Specifically, to address the ventilation response hysteresis problem caused by sudden movements such as sudden stops and turns in mobile chicken houses under unstructured road conditions on pastures, this application constructs an inertia-time-delay collaborative compensation mechanism: first, based on the spatial distribution characteristics of the velocity vector in the position change rate field, the characteristic parameters characterizing the sudden movement of the equipment are solved by fusion calculation of the velocity direction derivative (i.e., the rate of change of the angle of the travel direction per unit time) and the synthetic acceleration scalar. This process quantifies the sharp turning angular velocity changes during pasture pile avoidance and the acceleration impact during steep slope climbing into recognizable dynamic fingerprints; then, the sudden change characteristic parameters are differentially corrected with the real-time slope of the ventilation compensation demand curve. The calculation is performed (i.e., when a sharp sudden change in direction is detected, the steep downward trend of the slope of the demand curve is enhanced), and a ventilation delay compensation time constant adapted to different bump intensities is generated. The technical essence is to reversely infer the theoretical hysteresis of the hydraulic response of the fan system through the intensity of the mechanical motion mutation; finally, the fan action pre-compensation is implemented in combination with this time constant. On the one hand, the demand curve is moved forward along the time axis to eliminate the inherent time lag; on the other hand, the response attenuation compensation coefficient is dynamically reconstructed according to the acceleration amplitude, and a ventilation intensity adjustment instruction set matching the complex road conditions of the pasture is comprehensively generated. This processing particularly optimizes the ability of the mobile chicken house walking mechanism to suppress air volume overshoot under short-term strong vibration conditions when turning between haystacks.

[0036] The formula for the characteristic parameter of mobile state mutation is: ; Wherein, K represents the characteristic parameter of the mobile state mutation; Indicates the rate of change of the angular direction; a eff represents the equivalent acceleration modulus; ω c represents the trajectory curvature factor.

[0037] The ventilation delay compensation time constant is generated by the formula: ;in, represents the ventilation delay compensation time constant; represents the instantaneous slope of the demand curve; represents the curvature of the demand curve; μ represents the hydraulic damping coefficient of the fan; σ represents the pasture road attenuation factor; φ represents the overshoot suppression gain.

[0038] The ventilation intensity instruction reconstruction formula is: ;in, Indicates the ventilation intensity command value; represents the time-shifted demand curve; ζ represents the impeller inertia coefficient; represents the second-order derivative of the directional angle; ε represents the surge suppression factor, Indicates the effective speed of the impeller.

[0039] Furthermore, step S600 includes steps S610 to S630.

[0040] Step S610: Perform ventilation effect deviation quantification processing based on the ventilation intensity adjustment instruction set and the three-dimensional space wind speed component, and obtain a ventilation effect deviation characteristic value by converting and calculating the kinetic energy equivalent of the command air volume and the measured wind speed vector; Step S620: Perform energy consumption constraint boundary modeling based on the ventilation effect deviation characteristic value, and generate a dynamic energy consumption constraint boundary function by detecting the inflection point of the second-order derivative of the fan power-air volume characteristic curve; Step S630: Perform multi-objective collaborative optimization processing based on the ventilation effect deviation characteristic value and the dynamic energy consumption constraint boundary function, and output the optimal ventilation control parameter sequence through variable weight gradient descent iteration of the effect-energy consumption game matrix.

[0041] It should be noted that, based on the dual constraints of ventilation stability and equipment energy consumption sensitivity of mobile chicken houses under the sudden change of natural wind in pastures, this process creates a dynamic balanced intelligent decision-making mechanism: first, the theoretical air volume of the ventilation instruction is converted into equivalent air kinetic energy, and at the same time, the real wind field kinetic energy is reconstructed according to the measured values ​​of the east-west / north-south / vertical three-dimensional wind speed components. The deviation value of the ventilation effect is converted into a kinetic energy equivalent through the deviation value of the two (essentially, the energy level benchmarking to eliminate the interference of equipment movement). This processing process directly quantifies the airflow energy loss rate when the grass gust penetrates the side mesh; then the wind is triggered according to the deviation characteristic value. The flexible adjustment mechanism of the fan system energy consumption constraint analyzes the second-order derivative characteristics of the curve of fan power changing with air volume (that is, detecting the turning point of power efficiency changing with flow rate) to automatically calibrate the optimal energy consumption boundary function under the current working conditions. This technology avoids the rigid defects of fixed energy consumption threshold under the battery life limit of ranch equipment; finally, a dynamic game matrix with ventilation effect deviation as the vertical axis and energy consumption ratio as the horizontal axis is established, and a gradient descent optimization strategy with autonomous adjustment of weight coefficient with deviation amplitude is adopted to iteratively generate the optimal control parameter sequence that takes into account sudden environmental disturbances and equipment life while ensuring the minimum airflow velocity constraint of the chicken house.

[0042] Example 2:

[0043] like Figure 2 As shown, this embodiment provides a mobile chicken house ventilation control system based on an environmental model, the system comprising: Acquisition module 901 is used to obtain the original temperature data inside and outside the mobile chicken house, the original humidity data, the three-dimensional wind speed component, the opening geometry distribution data set on the chicken house surface, and the original latitude and longitude coordinate data and time data during the chicken house movement; Construction module 902 is used to construct a position change rate field based on the original latitude and longitude coordinate sequence and time data, and calculate the dynamic environment weight coefficient matrix based on the spatial distribution difference of the three-dimensional wind speed component; Fitting module 903, for fitting the environmental permeability gradient according to the dynamic environmental weight coefficient matrix and the original temperature data and the original humidity data to generate an adaptive heat exchange flow field; Inversion module 904 is used to apply a preset fluid impedance network model to invert the internal gas retention area based on the adaptive heat exchange flow field and the opening geometry distribution data set, and calculate the ventilation compensation demand curve to maintain the minimum airflow dead zone; Modeling module 905, used to perform fan dynamic response modeling based on the ventilation compensation demand curve and the position change rate field, and generate a ventilation intensity adjustment instruction set; The output module 906 is used to adjust the ventilation intensity instruction set and the three-dimensional space wind speed component, iteratively correct the fan action sequence using a dynamic game optimization algorithm, and output the optimal ventilation control parameters that meet the energy consumption-effect balance.

[0044] In a specific embodiment of the present application, the building block 902 includes: The first construction unit is used to perform dynamic modeling of the movement trajectory based on the original latitude and longitude coordinate sequence and time data, and calculate the incremental ratio of the spatial distance and time difference between adjacent coordinate points to obtain a position change rate field including the movement speed value and the movement direction angle; The second construction unit is used to perform environmental wind speed compensation processing according to the position change rate field, and obtain the real environmental wind speed vector that eliminates the influence of the chicken house's own movement through vector subtraction operation of the projection value of the three-dimensional wind speed component along the moving direction; The third construction unit is used to quantify the environmental effects according to the acceleration characteristics of the real environmental wind speed vector and the position change rate field, and to generate a dynamic environmental weight coefficient matrix by mapping the weight coefficient through the coupling strength function of the moving direction mutation angle and the environmental wind speed vector.

[0045] In a specific embodiment of the present application, the fitting module 903 includes: The first fitting unit is used to discretize the environmental action space according to the dynamic environmental weight coefficient matrix, divide the thermal and humidity action sub-areas according to the physical property differences between the temperature field and the humidity field, and generate a discrete environmental factor influence spectrum; The second fitting unit is used to perform heat and mass exchange equivalent conversion processing based on the discrete environmental factor influence spectrum and the original temperature data and original humidity data, and obtain the comprehensive heat and moisture exchange potential field through the two-way correction of the air enthalpy differential operator and the dew point change gradient; The third fitting unit is used to perform flux mapping processing on the enclosure structure of the chicken house according to the comprehensive potential field of heat and moisture exchange, and to generate an adaptive heat exchange flow field through the spatial convolution operation of the equivalent pore size distribution function of the porous medium and the potential gradient.

[0046] In a specific embodiment of the present application, the inversion module 904 includes: The first inversion unit is used to perform pore fluid dynamics modeling based on the pore geometry distribution data set, and generate a dynamic pore connectivity network diagram by determining the topological connectivity of the angles between the spatial distance vectors of adjacent pores and the normals; The second inversion unit is used to identify the retention area based on the dynamic pore connectivity network diagram and the adaptive heat exchange flow field, and to determine the geometric boundary characteristics of the gas retention area by calculating the spatial differential relationship between the mean gradient of the inter-pore flow difference and the local static pressure difference; The third inversion unit is used to perform iterative solution processing of the compensation air volume according to the geometric boundary characteristics of the gas retention area, and generate a ventilation compensation demand curve through a flow distribution ratio optimization algorithm under the constraint of a minimum airflow velocity threshold.

[0047] In a specific embodiment of the present application, the modeling module 905 includes: The first modeling unit is used to extract and process the movement dynamics characteristics according to the position change rate field, and obtain the movement state mutation characteristic parameters by calculating the directional derivative of the velocity vector and the acceleration modulus; The second modeling unit is used to quantify the time lag effect based on the characteristic parameters of the sudden change of the movement state and the ventilation compensation demand curve, and generate the ventilation delay compensation time constant by performing a differential correction operation on the slope of the demand curve by applying acceleration; The third modeling unit is used to perform pre-compensation processing on the fan action according to the ventilation delay compensation time constant, and to generate a ventilation intensity adjustment instruction set by reconstructing the response attenuation compensation coefficient of the demand curve time axis translation and acceleration constraint.

[0048] In a specific embodiment of the present application, the output module 906 includes: The first output unit is used to perform ventilation effect deviation quantification processing based on the ventilation intensity adjustment instruction set and the three-dimensional spatial wind speed component, and obtain the ventilation effect deviation characteristic value by converting and calculating the kinetic energy equivalent of the command air volume and the measured wind speed vector; The second output unit is used to perform energy consumption constraint boundary modeling processing according to the ventilation effect deviation characteristic value, and generate a dynamic energy consumption constraint boundary function by detecting the inflection point of the second-order derivative of the fan power-air volume characteristic curve; The third output unit is used to perform multi-objective collaborative optimization processing based on the ventilation effect deviation eigenvalue and the dynamic energy consumption constraint boundary function, and output the optimal ventilation control parameter sequence through variable weight gradient descent iteration of the effect-energy consumption game matrix.

[0049] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A ventilation control method for a mobile chicken house based on an environmental model, characterized in that: include: Obtain the original temperature data inside and outside the mobile chicken house, original humidity data, three-dimensional wind speed components, the opening geometry distribution data set on the chicken house surface, and the original latitude and longitude coordinate data and time data during the chicken house movement; Constructing a position change rate field based on the original latitude and longitude coordinate sequence and the time data, and calculating a dynamic environment weight coefficient matrix based on the spatial distribution difference of the three-dimensional wind speed component; Fitting the environmental permeability gradient according to the dynamic environmental weight coefficient matrix, the original temperature data, and the original humidity data to generate an adaptive heat exchange flow field; Based on the adaptive heat exchange flow field and the opening geometric distribution data set, a preset fluid impedance network model is applied to invert the internal gas retention area, and a ventilation compensation demand curve for maintaining minimum airflow dead corners is calculated; Perform fan dynamic response modeling based on the ventilation compensation demand curve and the position change rate field to generate a ventilation intensity adjustment instruction set; According to the ventilation intensity adjustment instruction set and the three-dimensional space wind speed component, a dynamic game optimization algorithm is used to iteratively correct the fan action sequence, and output the optimal ventilation control parameters that meet the energy consumption-effect balance.

2. The method for controlling ventilation of a mobile chicken house based on an environmental model according to claim 1, characterized in that: A position change rate field is constructed based on the original latitude and longitude coordinate sequence and the time data, and a dynamic environment weight coefficient matrix is ​​calculated based on the spatial distribution difference of the three-dimensional wind speed component, including: Performing dynamic modeling of the movement trajectory based on the original latitude and longitude coordinate sequence and the time data, and calculating the incremental ratio of the spatial distance and time difference between adjacent coordinate points to obtain a position change rate field including a movement speed value and a movement direction angle; Performing ambient wind speed compensation processing according to the position change rate field, and obtaining a true ambient wind speed vector that eliminates the influence of the chicken house's own movement by performing vector subtraction operation on the projection value of the three-dimensional wind speed component along the moving direction; The environmental effects are quantified according to the acceleration characteristics of the real environmental wind speed vector and the position change rate field, and a dynamic environmental weight coefficient matrix is ​​generated by mapping weight coefficients through the coupling strength function of the moving direction mutation angle and the environmental wind speed vector.

3. The method for controlling ventilation of a mobile chicken house based on an environmental model according to claim 1, wherein: Fitting the environmental permeability gradient according to the dynamic environmental weight coefficient matrix, the original temperature data, and the original humidity data to generate an adaptive heat exchange flow field includes: Discrete processing of the environmental action space is performed according to the dynamic environmental weight coefficient matrix, and the heat and humidity action sub-areas are divided according to the physical property differences between the temperature field and the humidity field to generate a discrete environmental factor influence spectrum; Performing heat and mass exchange equivalent conversion processing on the discrete environmental factor influence spectrum and the original temperature data and the original humidity data, and obtaining a comprehensive heat and moisture exchange potential field through bidirectional correction of the air enthalpy differential operator and the dew point change gradient; The flux mapping process of the chicken house enclosure structure is performed according to the comprehensive potential field of heat and moisture exchange, and an adaptive heat exchange flow field is generated through the spatial convolution operation of the equivalent pore size distribution function of the porous medium and the potential gradient.

4. The method for controlling ventilation of a mobile chicken house based on an environmental model according to claim 1, wherein: Based on the adaptive heat exchange flow field and the opening geometric distribution data set, a preset fluid impedance network model is applied to invert the internal gas retention area, and a ventilation compensation demand curve for maintaining the minimum airflow dead corner is calculated, including: Performing pore fluid dynamics modeling based on the pore geometry distribution dataset, and generating a dynamic pore connectivity network diagram by determining the topological connectivity of the angles between the spatial distance vectors of adjacent pores and their normals; Performing retention area identification processing based on the dynamic pore connectivity network diagram and the adaptive heat exchange flow field, and determining the geometric boundary characteristics of the gas retention area by calculating the spatial differential relationship between the mean gradient of the inter-pore flow difference and the local static pressure difference; The compensation air volume is iteratively solved according to the geometric boundary characteristics of the gas stagnation area, and a ventilation compensation volume demand curve is generated through a flow distribution ratio optimization algorithm under the constraint of a minimum airflow velocity threshold.

5. The method for controlling ventilation of a mobile chicken house based on an environmental model according to claim 1, characterized in that: Performing fan dynamic response modeling based on the ventilation compensation demand curve and the position change rate field to generate a ventilation intensity adjustment instruction set includes: Performing movement dynamics feature extraction processing based on the position change rate field, and obtaining movement state mutation feature parameters by calculating the directional derivative of the velocity vector and the acceleration modulus; The time lag effect is quantified based on the characteristic parameters of the sudden change of the movement state and the ventilation compensation demand curve, and the ventilation delay compensation time constant is generated by performing a differential correction operation on the slope of the demand curve by applying acceleration; The fan action pre-compensation processing is performed according to the ventilation delay compensation time constant, and the ventilation intensity adjustment instruction set is generated by reconstructing the response attenuation compensation coefficient through the time axis translation of the demand curve and the acceleration constraint.

6. A mobile chicken house ventilation control system based on an environmental model, characterized in that: include: The acquisition module is used to obtain the original temperature data inside and outside the mobile chicken house, the original humidity data, the three-dimensional wind speed component, the opening geometry distribution data set on the chicken house surface, and the original latitude and longitude coordinate data and time data during the chicken house movement; A construction module is used to construct a position change rate field based on the original latitude and longitude coordinate sequence and the time data, and calculate a dynamic environment weight coefficient matrix based on the spatial distribution difference of the three-dimensional wind speed component; A fitting module, configured to fit the environmental permeability gradient according to the dynamic environmental weight coefficient matrix, the original temperature data, and the original humidity data, to generate an adaptive heat exchange flow field; an inversion module for inverting the internal gas retention area using a preset fluid impedance network model based on the adaptive heat exchange flow field and the opening geometric distribution data set, and calculating a ventilation compensation demand curve for maintaining a minimum airflow dead zone; a modeling module, configured to perform fan dynamic response modeling based on the ventilation compensation demand curve and the position change rate field, and generate a ventilation intensity adjustment instruction set; The output module is used to iteratively correct the fan action sequence according to the ventilation intensity adjustment instruction set and the three-dimensional space wind speed component using a dynamic game optimization algorithm to output the optimal ventilation control parameters that meet the energy consumption-effect balance.

7. The mobile chicken house ventilation control system based on the environmental model according to claim 6, characterized in that: The building blocks include: A first construction unit is configured to perform dynamic modeling of a movement trajectory based on the original latitude and longitude coordinate sequence and the time data, and obtain a position change rate field including a movement speed value and a movement direction angle by calculating an incremental ratio of a spatial distance to a time difference between adjacent coordinate points; The second construction unit is used to perform environmental wind speed compensation processing according to the position change rate field, and obtain a real environmental wind speed vector that eliminates the influence of the chicken house's own movement by vector subtraction operation of the projection value of the three-dimensional wind speed component along the moving direction; The third construction unit is used to quantify the environmental effects based on the acceleration characteristics of the real environmental wind speed vector and the position change rate field, and map the weight coefficients by the coupling strength function of the moving direction mutation angle and the environmental wind speed vector to generate a dynamic environment weight coefficient matrix.

8. The mobile chicken house ventilation control system based on the environmental model according to claim 6, characterized in that: The fitting module includes: A first fitting unit is configured to discretize the environmental effect space according to the dynamic environmental weight coefficient matrix, divide the thermal and humidity effect sub-regions according to the physical property differences between the temperature field and the humidity field, and generate a discrete environmental factor influence spectrum; a second fitting unit, configured to perform heat and mass exchange equivalent conversion processing based on the discrete environmental factor influence spectrum and the original temperature data and the original humidity data, and obtain a comprehensive heat and moisture exchange potential field through bidirectional correction of the air enthalpy differential operator and the dew point change gradient; The third fitting unit is used to perform flux mapping processing on the chicken house enclosure structure according to the comprehensive potential field of heat and moisture exchange, and to generate an adaptive heat exchange flow field by performing spatial convolution operation on the equivalent pore size distribution function of the porous medium and the potential gradient.

9. The mobile chicken house ventilation control system based on the environmental model according to claim 6, characterized in that: The inversion module includes: A first inversion unit is configured to perform pore fluid dynamics modeling based on the pore geometric distribution data set, and generate a dynamic pore connectivity network diagram by determining the topological connectivity of the angles between the spatial distance vectors of adjacent pores and the normal lines; A second inversion unit is configured to perform retention area identification processing based on the dynamic pore connectivity network diagram and the adaptive heat exchange flow field, and determine the geometric boundary characteristics of the gas retention area by calculating the spatial differential relationship between the mean gradient of the inter-pore flow difference and the local static pressure difference; The third inversion unit is used to perform iterative solution processing of the compensation air volume according to the geometric boundary characteristics of the gas retention area, and generate a ventilation compensation demand curve through a flow distribution ratio optimization algorithm under the constraint of a minimum airflow velocity threshold.

10. The mobile chicken house ventilation control system based on the environmental model according to claim 6, characterized in that: The modeling module includes: A first modeling unit is configured to extract and process movement dynamics characteristics based on the position change rate field, and obtain movement state mutation characteristic parameters by calculating the directional derivative of the velocity vector and the acceleration modulus; The second modeling unit is used to quantify the time lag effect according to the movement state mutation characteristic parameter and the ventilation compensation demand curve, and generate a ventilation delay compensation time constant by performing a differential correction operation on the slope of the demand curve by applying acceleration; The third modeling unit is used to perform fan action pre-compensation processing according to the ventilation delay compensation time constant, and generate a ventilation intensity adjustment instruction set by reconstructing the response attenuation compensation coefficient of the demand curve time axis translation and acceleration constraint.

Images