Intelligent control method and system for model animal hog house

Abstract

The invention provides an intelligent control method and system for a model animal hog house, and belongs to the technical field of intelligent control, and the method comprises the steps: obtaining the current growth stage parameters of pigs in the hog house; calling a preset pig physiological model, and calculating a metabolic pollution production index and an environmental tolerance threshold value of the pig at the current stage based on the growth stage parameters; constructing an optimization function containing an energy consumption target and a growth target, and solving the optimization function by taking an environment tolerance threshold as a constraint condition to generate an optimal environment control parameter at the current moment; and according to the optimal environment control parameters, adjusting environment control equipment in the hog house, so that the environment parameters in the hog house are maintained in a range limited by the optimal environment control parameters. According to the method, the biological and environment coupling model is constructed, so that self-adaptive dynamic regulation and control based on the actual physiological needs of the pigs are realized, the problems of energy consumption waste and environment mismatching caused by a fixed control mode are effectively solved, and the operation energy consumption is remarkably reduced while the growth performance of the pigs is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to an intelligent control method and system for model animal pig houses. Background Technology

[0002] The breeding environment for specific pathogen-free (SPF) animals, especially model animals like pigs, requires extremely high cleanliness and stability, and usually requires a dedicated control system to maintain the environmental parameters in the pig house to meet the standards.

[0003] Existing technologies typically employ a "fixed ventilation frequency" control method, which sets a fixed number of ventilations based on preset industry standards (such as 12-20 ventilations per hour) and maintains air circulation and temperature and humidity in the pigsty by adjusting equipment such as fans.

[0004] However, this fixed-logic control method fails to consider the physiological differences of pigs at different growth stages. Because it doesn't account for the physiological changes in pigs at different growth stages (such as piglet and finishing stages), it cannot detect real-time differences in metabolic pollution intensity and changes in tolerance to environmental pollutants, resulting in a lack of targeted control strategies. This leads to ventilation equipment often operating at high frequencies when pigs' needs are low, causing significant energy waste; while when pigs' metabolism is high or the environmental load increases, the fixed control amplitude may not meet actual needs, making it difficult to effectively reduce energy consumption while ensuring pig growth performance. Summary of the Invention

[0005] This invention provides an intelligent control method and system for pig houses of model animals, which addresses the shortcomings of existing technologies and enables adaptive and precise control of the pig house environment according to the growth cycle of pigs, thereby significantly reducing operating energy consumption while ensuring the growth performance of pigs.

[0006] This invention provides a method for intelligent control of pig houses for model animals, comprising the following steps: Obtain the current growth stage parameters of the pigs in the pigsty; The system calls a preset pig physiological model and calculates the metabolic pollution indicators and environmental tolerance thresholds of the pig at the current stage based on the growth stage parameters. The pig physiological model is a mathematical model used to characterize the mapping relationship between the pig's physiological state, metabolic characteristics, and environmental adaptability indicators. An optimization function containing energy consumption and growth targets is constructed, and the optimization function is solved with the environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current moment. Adjust the environmental control equipment in the pigsty according to the optimal environmental control parameters so that the environmental parameters in the pigsty are maintained within the range defined by the optimal environmental control parameters.

[0007] According to the present invention, a method for intelligent control of a model animal pig house includes constructing an optimization function comprising energy consumption and growth targets, comprising: Establish a production objective function, which uses pig house environmental parameters as independent variables, pig growth rate as dependent variable, and maximizing the pig growth rate as the first optimization objective. An energy consumption objective function is established, which uses ventilation control parameters and equipment operating power as independent variables, energy consumption value per unit time as dependent variable, and minimizing the energy consumption value as the second optimization objective. The optimization function is constructed based on the output objective function and the energy consumption objective function.

[0008] According to the present invention, a method for intelligent control of a model animal pig house is provided, wherein the optimal environmental control parameters include the optimal air exchange rate and equipment operating parameters; the step of solving the optimization function with the environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current moment includes: Initialize a set of particle swarm position vectors containing random air exchange rates and device control variables; Calculate the fitness value of each particle swarm position vector in the optimization function, and determine whether the predicted environmental state corresponding to each particle swarm position vector meets the environmental tolerance threshold. Perform constraint processing on particles that do not meet the environmental tolerance threshold. By iteratively updating the particle's velocity and position, the global optimal position vector is searched to make the fitness value reach the preset convergence condition. The global optimal position vector is decoded to obtain the optimal number of air changes and the equipment operating parameters.

[0009] According to the present invention, a method for intelligent control of a model animal pig house includes adjusting the environmental control equipment in the pig house according to the optimal environmental control parameters, comprising: A state-space model containing system state vector, control input vector, and external disturbance vector is constructed. The state-space model is used to describe the thermodynamic and aerodynamic characteristics of the pig house. Using the state-space model, calculate the actual control input required to maintain the pig house environment in the state corresponding to the optimal environmental control parameters; The environmental control device is driven to operate based on the actual control input.

[0010] The intelligent control method for a model animal pig house provided by the present invention further includes: Collect real-time meteorological data outside the pigsty, including at least external temperature, light intensity, and wind speed; The real-time meteorological data is mapped to the external disturbance vector and substituted into the state-space model for feedforward compensation calculation, adjusting the actual control input before the environmental parameters change.

[0011] According to the present invention, a method for intelligent control of a model animal pig house, wherein adjusting the environmental control equipment in the pig house according to the optimal environmental control parameters further includes: The actual concentration of pollutants in the pigsty is collected in real time using sensors; When the actual pollutant concentration exceeds the environmental tolerance threshold, the control strategy based on the state space model is suspended, and the operating power of the exhaust equipment is forcibly increased until the actual pollutant concentration drops below the environmental tolerance threshold.

[0012] This invention also provides an intelligent control system for model animal pig houses, comprising the following modules: The parameter acquisition module is used to acquire the current growth stage parameters of the pigs in the pigsty. The model calculation module is used to call a preset pig physiological model and calculate the metabolic pollution indicators and environmental tolerance threshold of the pig at the current stage based on the growth stage parameters; the pig physiological model is a mathematical model used to characterize the mapping relationship between the pig's physiological state, metabolic characteristics and environmental adaptability indicators. The optimization decision module is used to construct an optimization function that includes energy consumption targets and growth targets, and solve the optimization function with the environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current time. The equipment control module is used to adjust the environmental control equipment in the pigsty according to the optimal environmental control parameters, so that the environmental parameters in the pigsty are maintained within the range defined by the optimal environmental control parameters.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent control method for model animal pig houses as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent control method for model animal pig houses as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the intelligent control method for model animal pig houses as described above.

[0016] In summary, one or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: By acquiring parameters of pig growth stages and calling a preset pig physiological model, the metabolic pollution level and environmental tolerance limit of pigs at the current stage are accurately quantified, thus overcoming the shortcomings of traditional control methods that rely solely on fixed ventilation rates while ignoring changes in the actual physiological state of pigs. Furthermore, by constructing an optimization function that includes energy consumption and growth targets, and solving the problem using the calculated environmental tolerance threshold as a constraint, the system automatically seeks the optimal environmental control parameters that balance maximizing production and minimizing energy consumption, while ensuring pig growth performance and biosafety. This solves the problem of energy waste or growth stagnation caused by controlling a single environmental parameter. Finally, by dynamically adjusting the environmental control equipment based on these optimal parameters, the system achieves adaptive and precise control of the pig house environment according to the pig growth cycle, significantly reducing operating energy consumption while ensuring pig growth performance. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is one of the flowcharts illustrating the intelligent control method for model animal pig houses provided by the present invention.

[0019] Figure 2 This is the second flowchart of the intelligent control method for model animal pig houses provided by the present invention.

[0020] Figure 3 This is the third flowchart of the intelligent control method for model animal pig houses provided by the present invention.

[0021] Figure 4 This is the fourth flowchart of the intelligent control method for model animal pig houses provided by the present invention.

[0022] Figure 5 This is the fifth flowchart illustrating the intelligent control method for model animal pig houses provided by this invention.

[0023] Figure 6 This is the sixth flowchart of the intelligent control method for model animal pig houses provided by the present invention.

[0024] Figure 7 This is a structural diagram of the pig coordination control system provided by the present invention.

[0025] Figure 8 This is a schematic diagram of the intelligent control system for pig houses of model animals provided by the present invention.

[0026] Figure 9 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0028] It should be noted that in the description of this invention, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The terms "upper," "lower," etc., indicating orientation or positional relationships according to the accompanying drawings, are only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0029] The terms "first," "second," etc., used in this invention are used to distinguish similar objects, not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0030] The following is combined with Figures 1 to 9 This invention describes the intelligent control method, system, electronic equipment, storage medium, and computer program product for model animal pig houses.

[0031] This embodiment provides an intelligent control method for a model animal pig house. The executing entity of this embodiment is an intelligent control system for model animal pig houses (hereinafter referred to as the system). In a specific application scenario, the intelligent control system for model animal pig houses is deployed in a pig house free of specific pathogens, where a preset number of model animal pigs in the fattening stage are raised.

[0032] Reference Figure 1 , Figure 1 This is one of the flowcharts illustrating the intelligent control method for model animal pig houses provided by this invention. For example... Figure 1 As shown, the intelligent control method for model animal pig houses includes the following steps: Step 101: Obtain the current growth stage parameters of the pigs in the pigsty.

[0033] The system acquires the current growth stage parameters of pigs in a specific pathogen-free pigsty. Growth stage parameters are quantitative data reflecting the physiological development status of the pigs. In one specific implementation, these parameters include the pigs' average age in days and average weight. The system acquires these parameters by receiving values ​​input by the user through the configuration interface. For example, the user inputs that the pigs are currently in the fattening stage with an average weight of 50 kg. In another implementation, the system automatically acquires the pigs' average weight data by communicating with an intelligent weighing system.

[0034] Step 102: Call the preset pig physiological model and calculate the metabolic pollution indicators and environmental tolerance threshold of the pig at the current stage based on the growth stage parameters.

[0035] The system calls a pre-stored swine physiological model. A swine physiological model is a mathematical model used to characterize the mapping relationship between a swine's physiological state, metabolic characteristics, and environmental adaptability indicators. This swine physiological model is a data model built based on a large amount of historical experimental data, and it stores metabolic data on different breeds of pigs at different growth stages.

[0036] The system inputs the growth stage parameters obtained in step 101 into the pig physiological model. The pig physiological model calculates based on the input growth stage parameters and outputs the metabolic pollution indicators and environmental tolerance thresholds for the pig at the current stage. The metabolic pollution indicators include the amount of carbon dioxide produced by a single pig's respiration and the amount of ammonia released in excrement per unit time. The environmental tolerance thresholds include the maximum tolerance limits for ammonia concentration and carbon dioxide concentration for the pig at the current growth stage, as well as the suitable temperature and humidity ranges for growth. For example, when the input growth stage parameter is the fattening stage, the pig physiological model outputs a maximum tolerance limit of 15 ppm for ammonia concentration, a maximum tolerance limit of 1500 ppm for CO2 concentration, and a suitable temperature range of 20°C to 24°C.

[0037] Step 103: Construct an optimization function that includes energy consumption targets and growth targets, and solve the optimization function with environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current moment.

[0038] The system constructs a multi-objective optimization function. This function includes an energy consumption objective and a growth objective. The energy consumption objective is defined as minimizing the operating energy consumption of the environmental control equipment in the specific pathogen-free pigsty. The growth objective is defined as maximizing the rate of weight gain of the pigs within the current time period.

[0039] The system uses the environmental tolerance threshold calculated in step 102 as a constraint in the solution process. The constraint limits the feasible region of the optimization function solution; that is, any solution that causes the environmental parameters to exceed the environmental tolerance threshold will be considered an invalid solution.

[0040] The system utilizes a multi-objective optimization algorithm to solve the optimization function. Through this calculation, the optimal environmental control parameters for the current moment are generated. These optimal environmental control parameters are a combination of environmental setpoints that simultaneously achieve low energy consumption and are conducive to pig growth. The optimal environmental control parameters include the optimal air exchange rate, optimal air intake volume, and optimal target temperature. For example, the system calculates the optimal air exchange rate to be 7.5 times per hour.

[0041] Step 104: Adjust the environmental control equipment in the pigsty according to the optimal environmental control parameters so that the environmental parameters in the pigsty are maintained within the range defined by the optimal environmental control parameters.

[0042] Based on the optimal environmental control parameters generated in step 103, the system sends control commands to the environmental control equipment within the specific pathogen-free pig house. The environmental control equipment includes variable frequency fans, inlet valves, exhaust valves, and temperature control devices. Upon receiving the control commands, the environmental control equipment executes corresponding actions. For example, the variable frequency fan adjusts its speed to achieve 7.5 air changes per hour, and the inlet valve adjusts its opening to match the optimal air intake. By adjusting the environmental control equipment, the system dynamically maintains the actual environmental parameters within the specific pathogen-free pig house within the range defined by the optimal environmental control parameters, thereby achieving precise control of the breeding environment in the physical space.

[0043] The intelligent control method for model animal pig houses provided in this embodiment breaks through the limitations of traditional control methods that rely solely on fixed standards for environmental regulation by establishing a direct correlation between pig growth stage parameters, metabolic pollution indicators, and environmental tolerance thresholds. This method utilizes an optimization function that includes energy consumption and growth targets to automatically find the optimal balance between energy consumption and production while ensuring that the pig house environment always meets biosafety tolerance thresholds. This dynamic regulation mechanism based on the biological needs of the pigs not only significantly reduces energy waste caused by ineffective ventilation but also avoids stress on pig growth caused by environmental fluctuations, thereby achieving efficient, energy-saving, and precise breeding in specific pathogen-free pig houses.

[0044] Reference Figure 2 , Figure 2 This is the second flowchart illustrating the intelligent control method for model animal pig houses provided by this invention. For example... Figure 2 As shown, this embodiment is a further detailed explanation of the step of "constructing an optimization function that includes energy consumption targets and growth targets" in the above embodiments, specifically including the following steps: Step 201: Establish a production objective function. The production objective function uses pig house environmental parameters as independent variables, pig growth rate as dependent variable, and maximizing pig growth rate as the primary optimization objective.

[0045] The system establishes a production objective function. The production objective function is a function that describes the mathematical relationship between environmental conditions and the growth benefits of pigs.

[0046] The production objective function uses pig house environmental parameters as independent variables. These parameters specifically include air temperature, relative humidity, and pollutant concentrations within a specific pathogen-free pig house. Pollutant concentrations include ammonia and carbon dioxide concentrations.

[0047] The production objective function uses the pig growth rate as the dependent variable. The pig growth rate is specifically expressed as the increase in body weight of the pig per unit time.

[0048] The system sets maximizing the pig growth rate as its primary optimization objective. This means that in the calculation logic of the production objective function, the system aims to find the set of pig house environmental parameters that will cause the pig weight gain to reach its peak.

[0049] Step 202: Establish an energy consumption objective function. The energy consumption objective function uses ventilation control parameters and equipment operating power as independent variables, energy consumption per unit time as dependent variable, and minimizing energy consumption as the second optimization objective.

[0050] The system establishes an energy consumption objective function. The energy consumption objective function is a function that describes the mathematical relationship between the control strategy and power consumption.

[0051] The energy consumption objective function uses ventilation control parameters and equipment operating power as independent variables. Ventilation control parameters specifically include the number of air changes per unit time and the opening value of the air inlet valve. Equipment operating power includes the real-time power of the variable frequency fan, the real-time power of the air conditioning unit, and the real-time power of the misting device.

[0052] The energy consumption objective function uses the energy consumption per unit time as the dependent variable. Specifically, the energy consumption is the total electricity consumption of a pathogen-free pigsty during operation.

[0053] The system sets minimizing energy consumption as its second optimization objective. This means that in the calculation logic of the energy consumption objective function, the system aims to find the set of ventilation control parameters that minimizes the total power consumption.

[0054] Step 203: Construct an optimization function based on the output objective function and the energy consumption objective function.

[0055] Based on the output objective function established in step 201 and the energy consumption objective function established in step 202, the system constructs the final optimization function. The optimization function is a multi-objective mathematical model that integrates the output objective function and the energy consumption objective function.

[0056] In this optimization function, the production objective function represents the need to maximize aquaculture benefits, while the energy consumption objective function represents the need to minimize operating costs. The system transforms the environmental control problem into a multi-objective mathematical programming problem through this optimization function.

[0057] This embodiment digitally decouples and reconstructs the often contradictory control objectives of "pig growth" and "energy consumption" by establishing separate objective functions for output and energy consumption. By clearly defining the first optimization objective—driven by pig house environmental parameters—and the second optimization objective—driven by ventilation control parameters—for energy conservation, this scheme provides a precise mathematical basis for finding the optimal compromise between the two. This construction method enables the control system to not only passively maintain environmental stability but also actively seek the optimal operating strategy between "high output" and "low energy consumption," solving the problem of compromise caused by a single control objective in existing technologies.

[0058] Reference Figure 3 , Figure 3 This is the third flowchart illustrating the intelligent control method for model animal pig houses provided by this invention. Figure 3 As shown, this embodiment further details the step of "solving the optimization function with the environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current moment" in the above embodiment. This embodiment uses the particle swarm optimization algorithm to implement the above solution process, specifically including the following steps: Step 301: Initialize a set of particle swarm position vectors containing random air exchange rates and device control variables.

[0059] The system initializes a swarm of particles within the algorithm's search space. Each particle represents a potential solution to the optimization problem. The system assigns an initial position vector to each particle. This position vector consists of a randomly generated air exchange rate value and a device control variable value. The device control variable is a value representing the percentage of air inlet valve opening or the fan operating frequency. For example, the system generates an initial swarm of 50 particles, where the position vector of the first particle contains an air exchange rate of 10 times per hour and a valve opening of 60%.

[0060] Step 302: Calculate the fitness value of each particle swarm position vector in the optimization function, and determine whether the predicted environment state corresponding to each particle swarm position vector meets the environment tolerance threshold. Perform constraint processing on particles that do not meet the environment tolerance threshold.

[0061] The system substitutes the position vector of each particle swarm into the optimization function constructed in the above embodiment for calculation to obtain the fitness value of each particle. The fitness value is a quantitative indicator for evaluating the quality of the control strategy represented by the particle, and the fitness value comprehensively reflects the degree to which the production target and energy consumption target are achieved.

[0062] During the fitness calculation process, the system uses a pigsty thermodynamic model to predict the pigsty environmental state corresponding to the current particle swarm position vector after implementation. The system compares this predicted environmental state with the environmental tolerance threshold determined in the above embodiments. If the predicted environmental state corresponding to a particle exceeds the environmental tolerance threshold, for example, if the predicted ammonia concentration exceeds 15 ppm, the system determines that the particle does not meet the constraints. For particles that do not meet the environmental tolerance threshold, the system performs constraint processing. The specific method of constraint processing is to set the particle's fitness value to a very poor penalty value, or to forcibly reset the particle's position to the boundary of the feasible region, so as to reduce the probability of the particle being selected in subsequent iterations.

[0063] Step 303: By iteratively updating the particle's velocity and position, search for the globally optimal position vector that makes the fitness value reach the preset convergence condition.

[0064] The system executes an iterative loop of the particle swarm optimization algorithm. In each iteration, the system updates the velocity and position vectors of each particle based on its individual historical best position and the global historical best position. The system repeatedly calculates the fitness value and updates the position until the algorithm reaches a preset convergence condition. The preset convergence condition is the basis for determining whether the algorithm terminates, including reaching a preset upper limit on the number of iterations or the change in the global best fitness value being less than a preset threshold. When the preset convergence condition is met, the system outputs the final global best position vector.

[0065] Step 304: Decode the global optimal position vector to obtain the optimal number of air changes and equipment operating parameters.

[0066] The system decodes the global optimal position vector output in step 303. Decoding is the process of converting a mathematical vector into physical control parameters. Optimal environmental control parameters include the optimal air exchange rate and equipment operating parameters. Through decoding, the system extracts specific values ​​from the global optimal position vector to determine the optimal air exchange rate and corresponding equipment operating parameters at the current moment. Equipment operating parameters include specific fan speed setpoints and damper opening setpoints.

[0067] This embodiment employs particle swarm optimization (PSO) to solve a complex environmental control model. By introducing an "environmental tolerance threshold" as a hard constraint and combining it with a targeted constraint handling mechanism, it effectively solves the dead zone problem that may occur in multi-objective optimization, where energy saving may not be safe. This scheme can search for the globally optimal solution from a massive number of control parameter combinations within an extremely short computation cycle, ensuring that the final output of optimal environmental control parameters not only strictly meets the biosafety standards of specific pathogen-free pig houses but also maximizes both growth benefits and energy conservation, achieving rapid and robust control decision-making.

[0068] Reference Figure 4 , Figure 4 This is the fourth flowchart illustrating the intelligent control method for model animal pig houses provided by this invention. Figure 4 As shown, this embodiment is a further detailed explanation of the step of "adjusting the environmental control equipment in the pigsty according to the optimal environmental control parameters" in the above embodiment, specifically including the following steps: Step 401: Construct a state-space model containing system state vectors, control input vectors, and external disturbance vectors. The state-space model is used to describe the thermodynamic and aerodynamic characteristics of the pigsty.

[0069] The system constructs and stores a state-space model in memory. The state-space model is a mathematical model used to describe the dynamic behavior of the physical system of a pathogen-free pig house. The state-space model consists of state equations and output equations.

[0070] The state-space model comprises three core vectors: the system state vector, the control input vector, and the external disturbance vector. The system state vector consists of a set of physical quantities describing the internal environment of the pigsty, including indoor air temperature, indoor air humidity, carbon dioxide concentration, ammonia concentration, and the physiological weight of the pigs. The control input vector consists of a set of variables that can be directly adjusted by the system, including the air supply volume, exhaust volume, the on / off status of the misting system, and the operating status of the blanket rolling machine. The external disturbance vector consists of a set of uncontrollable but observable external environmental factors, including solar radiation intensity, external air temperature, and external wind speed.

[0071] The constructed state equation describes the evolution of the system state vector over time, expressing the functional relationship between the rate of change of the system state vector and the current system state vector, control input vector, and external disturbance vector. The constructed output equation describes the observational relationship between the system output vector and the system state vector, expressing the mapping relationship between output parameters such as actual ambient temperature, relative humidity, air exchange rate, and pollutant concentration and the system state vector.

[0072] The mathematical expression for the state equation is: .

[0073] The mathematical expression for the output equation is: .

[0074] in, represent A dimensional system state vector represent dimensional output vector, represent dimensional control input vector, represent An external perturbation vector of dimension 1. Represents the system state transition function. Represents the output function. For time. The system establishes a dynamic mapping relationship between input variables, disturbance variables, system state, and output variables through the above set of equations.

[0075] Step 402: Using the state-space model, calculate the actual control input required to maintain the pig house environment in the state corresponding to the optimal environmental control parameters.

[0076] The system sets the optimal environmental control parameters generated in the above embodiments as the output vector. The target value is determined by the system's use of the constructed state-space model to perform model solving operations.

[0077] Specifically, the system collects the current system state vector. and external disturbance vector This is then substituted into the state equations and output equations. The system calculates the output vector for the next time step using an inverse solution algorithm or a model predictive control algorithm. The actual control input quantity that must be applied to converge to the value corresponding to the optimal environmental control parameters. .

[0078] For example, the system calculates that the air intake volume should be adjusted to 500 cubic meters per hour, and the spray device should be on to maintain the target humidity.

[0079] Step 403: Drive the environmental control equipment to operate according to the actual control input.

[0080] The system will calculate the actual control input obtained in step 402. The signal is converted into a standard electrical control signal. The system then sends this signal to the corresponding environmental control equipment via an output interface. The environmental control equipment includes frequency converters, electric actuators, and relay modules. The environmental control equipment executes corresponding mechanical actions based on the received actual control input. For example, the air intake valve actuator adjusts the valve angle based on the air intake volume data, and the solenoid valve of the spray system opens based on the spray device's start / stop status data. In this way, the system achieves precise actuation of the environmental control equipment.

[0081] This embodiment achieves a mathematical reconstruction of the complex physical environment of a pigsty by constructing a state-space model that includes system state, control input, and external disturbances. Compared to simple on / off control or traditional PID control, the state-space model can comprehensively consider the coupling relationships between multiple variables (such as the mutual influence of temperature and humidity) and the dynamic impact of external disturbances on the system. The actual control input calculated by this model has higher accuracy and foresight, effectively suppressing system oscillations and ensuring that the pigsty environmental parameters converge smoothly and quickly to the target values ​​set by the optimal environmental control parameters, significantly improving the stability and response speed of the control system.

[0082] Reference Figure 5 , Figure 5 This is the fifth flowchart illustrating the intelligent control method for model animal pig houses provided by this invention. Figure 5 As shown, this embodiment is a further improvement on the state-space model-based control method described in the above embodiments. It adds a feedforward compensation mechanism for external meteorological disturbances, specifically including the following steps: Step 501: Collect real-time meteorological data outside the pigsty. The meteorological data should include at least the outside temperature, light intensity, and wind speed.

[0083] The system connects to a small weather station or weather sensor array installed outside the pigsty, free of specific pathogens, via a communication interface. The system collects real-time weather data from the weather sensor array at a preset sampling frequency. Real-time weather data are physical quantities reflecting the external environmental conditions of the pigsty. Specifically, real-time weather data includes external air temperature, light intensity, and external wind speed. For example, the system reads data from the external temperature sensor every 10 seconds, obtaining a current external air temperature of -5 degrees Celsius.

[0084] Step 502: Map the real-time meteorological data into an external disturbance vector and substitute it into the state-space model for feedforward compensation calculation, adjusting the actual control input before environmental parameters change.

[0085] The system maps the real-time meteorological data collected in step 501 into an external disturbance vector. The mapping process is the process of converting the raw physical values ​​collected by the sensors into standardized input variables acceptable to the state-space model.

[0086] The system will map the external disturbance vector obtained. Substitute this into the state-space model constructed in Example 4. The system uses the state-space model to perform feedforward compensation calculations. Feedforward compensation calculation is a control strategy that introduces a correction signal in advance before the disturbance causes a change in the controlled variable. Specifically, the system calculates the compensation based on the state equations. Analyze external disturbance vectors Changes in the system state vector The potential impact trend. For example, when a sudden drop in outside temperature is detected, the model predicts that if the current control level is maintained, the temperature inside the pigsty will drop by 2 degrees Celsius within the next ten minutes.

[0087] Based on this prediction, the system adjusts the actual control input in advance, before the actual environmental parameters inside the pigsty change. Specific operations for adjusting the actual control input include increasing the output power of the heater in advance or turning off the blanket rolling machine in advance. For example, at the moment a sudden drop in outside temperature is detected, the system immediately advances the blanket rolling machine's shutdown time from the originally scheduled 13:06 to 12:00, while maintaining the same number of air exchanges.

[0088] This embodiment achieves proactive sensing and feedforward compensation of environmental disturbances by collecting real-time meteorological data and converting it into external disturbance vectors in a state-space model. Compared with traditional control that relies solely on feedback from internal sensors, this scheme can pre-adjust the operating status of control equipment before sudden changes in external weather (such as cold waves or drastic changes in light) affect the internal environment of the pigsty. This effectively avoids drastic fluctuations in temperature or humidity in the pigsty, thus providing a more stable and reliable growth environment for pigs that are extremely sensitive to the environment and free from specific pathogens.

[0089] Reference Figure 6 , Figure 6 This is the sixth flowchart illustrating the intelligent control method for model animal pig houses provided by this invention. Figure 6 As shown, this embodiment supplements the control strategy in the above embodiments, adding an emergency response mechanism for pollutant concentration exceeding the standard, specifically including the following steps: Step 601: Collect the actual pollutant concentration in the pigsty in real time using sensors.

[0090] The system connects to gas sensors deployed inside a specific pathogen-free pigsty via a data acquisition interface. These sensors include ammonia, carbon dioxide, and particulate matter concentration sensors. The system periodically reads data from the gas sensors to collect real-time data on the actual pollutant concentrations within the pigsty. These actual pollutant concentrations are measured values ​​reflecting the current air quality in the pigsty. For example, the system detects a current ammonia concentration of 18 ppm.

[0091] Step 602: When the actual pollutant concentration exceeds the environmental tolerance threshold, suspend the execution of the control strategy based on the state space model and forcibly increase the operating power of the exhaust equipment until the actual pollutant concentration drops below the environmental tolerance threshold.

[0092] The system compares the collected actual pollutant concentrations with the calculated environmental tolerance thresholds in real time. The environmental tolerance threshold is the upper limit of pollutant concentrations that pigs can tolerate at their current growth stage, for example, 15 ppm.

[0093] When the comparison results show that the actual pollutant concentration is higher than the environmental tolerance threshold (18ppm > 15ppm), the system determines that the current environment is in a state of biosafety risk. At this time, the system immediately suspends the execution of the conventional control strategy based on the state-space model in the above embodiments. Suspension means that the control variables are no longer calculated based on the goals of optimal energy consumption or optimal growth.

[0094] Next, the system switches to emergency exhaust mode. In emergency exhaust mode, the system forcibly increases the operating power of the exhaust equipment. This forced increase in operating power involves adjusting the valve openings of both the supply and exhaust fans to their maximum values ​​and increasing the fan speed to a high percentage range of their rated speed. For example, the exhaust valve opening is adjusted to 80%, and the air exchange rate is directly increased to more than 10 times per hour.

[0095] The system continuously monitors changes in actual pollutant concentrations. When the actual pollutant concentration is detected to have dropped below the environmental tolerance threshold (e.g., to 12 ppm), the system exits the emergency exhaust mode and resumes executing the regular control strategy based on the state-space model.

[0096] In another possible implementation, this embodiment focuses on describing the hardware architecture, software system integration, and specific operating mechanism of the intelligent control system for model animal pig houses, as well as the implementation of intelligent dynamic control methods.

[0097] Firstly, the system's hardware architecture and interface design are as follows: The intelligent control system for model animal pig houses adopts an embedded development architecture. The core component of the intelligent control system is the hardware module. The hardware module integrates a main central processing unit (CPU). The main CPU uses a high-performance 32-bit microprocessor. This 32-bit microprocessor has a large capacity for information processing and supports hardware upgrades. The main CPU is equipped with analog input / output and digital input / output functions. The digital input function supports at least eight channels. Utilizing high-speed sampling technology, the main CPU achieves real-time monitoring of pig house temperature, humidity, and pollutant concentration through the aforementioned input channels. The main CPU has an independent data upload channel, which ensures that the collected data is quickly and accurately reported to the host computer or cloud server.

[0098] The intelligent control system for model animal pig houses is equipped with an interface unit. This unit features a universal sensor interface compatible with various types of environmental sensing devices, including temperature sensors, humidity sensors, ammonia sensors, carbon dioxide sensors, and particulate matter sensors. The interface unit also includes an RS485 communication interface and a relay drive interface. The relay drive interface is used to connect and drive external actuators, including air supply valves, exhaust valves, spray devices, and blanket rolling machines. Furthermore, the interface unit supports connection to a display and physical buttons for human-machine interaction by on-site personnel.

[0099] Secondly, the software system and communication mechanism are as follows: The intelligent control system for model animal pig houses runs on an embedded Linux-based software system. The embedded Linux operating system ensures real-time performance, guaranteeing a response latency of less than or equal to 100 milliseconds. Simultaneously, it ensures system stability, guaranteeing continuous trouble-free operation for more than or equal to 1000 hours. The software system employs a modular design and open architecture. This architecture allows the intelligent control system to load corresponding functional modules based on the type of connected devices. These devices include sensors and actuators from various brands. Application scenarios include piglet pens and finishing pens. The software system provides reserved third-party function interfaces, enabling the intelligent control system to connect to external systems, including farm management platforms.

[0100] The intelligent control system for model animal pig houses interacts with external systems via a communication module. This module supports multiple communication methods, including wired Ethernet, fiber optic Ethernet, RS232 serial communication, and RS485 serial communication. It supports connection to various terminal devices, such as remote monitoring screens and mobile terminals. Regarding communication distance, Ethernet communication is greater than or equal to 100 meters, and RS485 communication is greater than or equal to 1200 meters without a repeater. In terms of communication protocols, the intelligent control system supports Profibus, CDT, and MODBUS protocols. The module is also compatible with the proprietary protocols of field instruments and intelligent sensor terminals, ensuring broad compatibility for data interaction.

[0101] Thirdly, the system's operating logic and control decisions are as follows: Reference Figure 7 , Figure 7 This is a structural diagram of the coordinated control system for the pig, a model animal, provided by this invention. Figure 7 As shown, the intelligent control system for model animal pig houses constructs a closed-loop coordinated control system. This system mainly consists of a pig growth model, an operation module, a controller, a climate prediction module, and system entities encompassing the pig house environment and the pigs.

[0102] In actual operation, the intelligent control system for model animal pig houses follows... Figure 7 The signal flow shown indicates the execution control logic: Pig growth models, as a fundamental component of control decision-making, receive input information about the pig's growth stages. For example... Figure 7 As shown by the dashed arrows, the pig growth model provides the controller with reference data on the pigs' physiological characteristics (such as environmental tolerance thresholds and metabolic waste production indicators). Simultaneously, the pig growth model also provides auxiliary information to the operation module, allowing users to view current biological parameters on the user interface.

[0103] The system diagram represents the physical entities, including the interconnected pigpen environment and the pigs. Metabolic byproducts produced by the pigs during their growth (such as ammonia and CO2) directly alter the pigpen environment, while changes in the pigpen environment (such as temperature and humidity) in turn affect the pigs' growth rate. For example... Figure 7 As shown by the solid arrow at the bottom, the system feeds back the measured environmental state parameters to the operation module for display, and also feeds them back to the controller as the input basis for closed-loop control.

[0104] The climate prediction module is responsible for processing external environmental information. For example... Figure 7As shown, the external disturbance vector d (including solar radiation intensity, wind speed, etc.) directly affects the system (i.e., the physical pigsty), interfering with the pigsty environment. On the other hand, the external disturbance vector d is input to the climate prediction module. After processing, the climate prediction module sends the meteorological forecast data to the controller, enabling the controller to perform feedforward compensation.

[0105] The controller is the core computing unit of the entire architecture. For example... Figure 7 As shown, the controller comprehensively receives biological constraints from the pig growth model, real-time state feedback from the system, and disturbance prediction information from the climate prediction module. The controller internally employs a state-space algorithm and a multi-objective optimization algorithm to calculate the control input vector U.

[0106] The controller sends the control input vector U to the system. For example... Figure 7 As shown by the solid arrow in the middle, signal U directly drives environmental control equipment (such as fans and blanket rolling machines), thereby regulating the pig house environment to maintain it in an optimal state that meets the growth needs of pigs and minimizes energy consumption.

[0107] Fourthly, the intelligent control system for model animal pig houses provides a wealth of human-computer interaction functions: The user interface features physical buttons and a display. The physical buttons control "automatic / manual mode," "roller machine rises and falls," and "ventilation on / off." The display shows key parameters in real time, including the local IP address, subnet mask, server port, and automatic control cycle. Users can modify parameters such as backlight time and roller opening / closing time via the interface; changes take effect upon system restart. Furthermore, the system provides local maintenance software and a remote maintenance interface, allowing operators to set system parameters, monitor operating status, upload historical data, and remotely start / stop the equipment via the controller display or a remote platform.

[0108] In a preferred embodiment, this application further provides an extension and optimization scheme to address long-term operational risks. This embodiment focuses on resolving risks related to sensor data drift, algorithm adaptability, and equipment compatibility. The implementing entity in this embodiment is an intelligent control system for model animal pig houses.

[0109] Firstly, to address the issue of sensor data drift, the intelligent control system for model animal pig houses integrates an automatic sensor calibration module into its software system. This module is configured to perform periodic data correction tasks.

[0110] Specifically, the intelligent control system for model animal pig houses supports an automatic monthly calibration process. During calibration, the system communicates with a standard calibration device connected to a standard interface, comparing the current readings of the ammonia and carbon dioxide sensors with the reference values ​​from the standard calibration device. Based on the comparison results, the intelligent control system automatically calculates and corrects internal data deviation coefficients, thereby eliminating zero-point drift or sensitivity drift caused by long-term use.

[0111] In addition, the intelligent control system for model animal pig houses is equipped with a data anomaly early warning mechanism. The system monitors the output values ​​of each sensor in real time. When a sensor's value exceeds the upper or lower limit of its physical range (e.g., exceeding ±10%), the system immediately triggers an alarm. This alarm is displayed on the user interface or via a remote terminal. Upon receiving the alarm, staff can promptly manually calibrate or replace the sensor, thus preventing inaccurate pollutant concentration detection due to data drift and subsequent misleading control decisions.

[0112] Secondly, regarding the issue of algorithm adaptability, to address the differences in growth models and environmental requirements among different breeds of model pigs (such as Landrace and Large White pigs), the intelligent control system for model pig houses has established a specific pathogen-free pig breed parameter database in its internal memory. This breed parameter database pre-stores specific model parameters for various pig breeds at different growth stages. These model parameters include metabolic waste production coefficients, environmental tolerance threshold curves, and growth rate parameters for each stage.

[0113] The intelligent control system for model animal pig houses provides users with a selection interface through configuration software. Users can choose breed options matching the currently raised pigs from the breed parameter database through the configuration software's interface. Alternatively, users can manually enter growth parameters for specific breeds through the custom input function. Once the user completes the selection or input, the intelligent control system automatically calls the corresponding model parameters to initialize the pig growth and production models. Furthermore, the intelligent control system supports remote software upgrades. Through software upgrades, the breed parameter database can be continuously expanded to cover more newly bred pig breeds, solving the problem that a single algorithm cannot adapt to multiple pig breeds.

[0114] Thirdly, regarding equipment compatibility issues, specifically addressing the incompatibility of control protocols between different brands of actuators (such as air supply and exhaust valves and blanket rolling machines), the intelligent control system for model animal pig houses has reserved various types of drive circuits in the design phase of its hardware interface units. These drive circuits cover common analog drive, digital pulse drive, and communication bus drive methods.

[0115] Meanwhile, the intelligent control system for model animal pig houses integrates dedicated driver libraries for actuators from various mainstream brands within its software system. Users can directly select the specific actuator model used on-site through the device selection menu in the configuration software. Based on the user's selection, the intelligent control system automatically loads the corresponding dedicated driver, achieving seamless integration and operation of equipment from different brands. Furthermore, before the system is officially deployed and put into operation, the intelligent control system for model animal pig houses also provides equipment compatibility testing services. By running the test program, the intelligent control system can automatically verify the communication and control response with existing on-site equipment, ensuring that the system can immediately and normally drive all actuators after installation.

[0116] Reference Figure 8 , Figure 8 This is a schematic diagram of the intelligent control system for model animal pig houses provided by the present invention. The system includes: The parameter acquisition module is used to acquire the current growth stage parameters of the pigs in the pigsty. The model calculation module is used to call the preset pig physiological model and calculate the metabolic pollution indicators and environmental tolerance threshold of the pig at the current stage based on the growth stage parameters. The pig physiological model is a mathematical model used to characterize the mapping relationship between the physiological state of pigs and metabolic characteristics and environmental adaptability indicators. The optimization decision module is used to construct an optimization function that includes energy consumption targets and growth targets, and solve the optimization function with environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current time. The equipment control module is used to adjust the environmental control equipment in the pigsty according to the optimal environmental control parameters, so that the environmental parameters in the pigsty are maintained within the range defined by the optimal environmental control parameters.

[0117] It should be noted that the intelligent control system for model animal pig houses provided by the present invention can execute the intelligent control method for model animal pig houses of any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0118] Figure 9 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 9As shown, the electronic device may include a processor 910, a communication interface 920, a memory 930, and a communication bus 940. The processor 910, communication interface 920, and memory 930 communicate with each other via the communication bus 940. The processor 910 can call logical instructions stored in the memory 930 to execute the intelligent control method for model animal pig houses provided in the above embodiments.

[0119] Furthermore, the logical instructions in the aforementioned memory 930 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by the computer, the computer is able to execute the intelligent control method for model animal pig houses provided in the above embodiments.

[0121] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the intelligent control method for model animal pig houses provided in the above embodiments.

[0122] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0123] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent control of a model animal pig house, characterized in that, include: Obtain the current growth stage parameters of the pigs in the pigsty; The system calls a preset pig physiological model and calculates the metabolic pollution indicators and environmental tolerance thresholds of the pig at the current stage based on the growth stage parameters. The pig physiological model is a mathematical model used to characterize the mapping relationship between the pig's physiological state, metabolic characteristics, and environmental adaptability indicators. An optimization function containing energy consumption and growth targets is constructed, and the optimization function is solved with the environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current moment. Adjust the environmental control equipment in the pigsty according to the optimal environmental control parameters so that the environmental parameters in the pigsty are maintained within the range defined by the optimal environmental control parameters.

2. The intelligent control method for model animal pig houses according to claim 1, characterized in that, The construction of the optimization function, which includes energy consumption and growth objectives, includes: Establish a production objective function, which uses pig house environmental parameters as independent variables, pig growth rate as dependent variable, and maximizing the pig growth rate as the first optimization objective. An energy consumption objective function is established, which uses ventilation control parameters and equipment operating power as independent variables, energy consumption value per unit time as dependent variable, and minimizing the energy consumption value as the second optimization objective. The optimization function is constructed based on the output objective function and the energy consumption objective function.

3. The intelligent control method for model animal pig houses according to claim 2, characterized in that, The optimal environmental control parameters include the optimal air exchange rate and equipment operating parameters; the process of solving the optimization function using the environmental tolerance threshold as a constraint to generate the optimal environmental control parameters for the current moment includes: Initialize a set of particle swarm position vectors containing random air exchange rates and device control variables; Calculate the fitness value of each particle swarm position vector in the optimization function, and determine whether the predicted environmental state corresponding to each particle swarm position vector meets the environmental tolerance threshold. Perform constraint processing on particles that do not meet the environmental tolerance threshold. By iteratively updating the particle's velocity and position, the global optimal position vector is searched to make the fitness value reach the preset convergence condition. The global optimal position vector is decoded to obtain the optimal number of air changes and the equipment operating parameters.

4. The intelligent control method for model animal pig houses according to claim 1, characterized in that, The method of adjusting the environmental control equipment in the pigsty according to the optimal environmental control parameters includes: A state-space model containing system state vector, control input vector, and external disturbance vector is constructed. The state-space model is used to describe the thermodynamic and aerodynamic characteristics of the pig house. Using the state-space model, calculate the actual control input required to maintain the pig house environment in the state corresponding to the optimal environmental control parameters; The environmental control device is driven to operate based on the actual control input.

5. The intelligent control method for model animal pig houses according to claim 4, characterized in that, Also includes: Collect real-time meteorological data outside the pigsty, including at least external temperature, light intensity, and wind speed; The real-time meteorological data is mapped to the external disturbance vector and substituted into the state-space model for feedforward compensation calculation, adjusting the actual control input before the environmental parameters change.

6. The intelligent control method for model animal pig houses according to claim 4, characterized in that, The environmental control equipment for adjusting the pigsty according to the optimal environmental control parameters further includes: The actual concentration of pollutants in the pigsty is collected in real time using sensors; When the actual pollutant concentration exceeds the environmental tolerance threshold, the control strategy based on the state space model is suspended, and the operating power of the exhaust equipment is forcibly increased until the actual pollutant concentration drops below the environmental tolerance threshold.

7. An intelligent control system for a model animal pig house, characterized in that, include: The parameter acquisition module is used to acquire the current growth stage parameters of the pigs in the pigsty. The model calculation module is used to call a preset pig physiological model and calculate the metabolic pollution indicators and environmental tolerance threshold of the pig at the current stage based on the growth stage parameters; the pig physiological model is a mathematical model used to characterize the mapping relationship between the pig's physiological state, metabolic characteristics and environmental adaptability indicators. The optimization decision module is used to construct an optimization function that includes energy consumption targets and growth targets, and solve the optimization function with the environmental tolerance threshold as a constraint to generate the optimal environmental control parameters at the current time. The equipment control module is used to adjust the environmental control equipment in the pigsty according to the optimal environmental control parameters, so that the environmental parameters in the pigsty are maintained within the range defined by the optimal environmental control parameters.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the intelligent control method for model animal pig houses as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent control method for model animal pig houses as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent control method for model animal pig houses as described in any one of claims 1 to 6.

Images