AI internet of things based constant temperature and constant humidity intelligent control system and method for smart farm

Abstract

The application discloses an AI-based intelligent control system and method for constant temperature and humidity of a smart farm, and belongs to the technical field of temperature and humidity control.The system comprises a data acquisition module, a data preprocessing module, a data analysis module, a schedule simulation module, a climate simulation module and an execution module.The data acquisition module monitors key parameters of a breeding environment in real time through a sensor, and all collected data is transmitted to the data preprocessing module for processing.The data preprocessing module is responsible for cleaning, denoising and synchronous processing of original collected data, and the preprocessed data is timestamped and transmitted to the data analysis module.The system can adjust temperature and humidity set values according to circadian rhythm changes through the combination of the schedule simulation module and the climate simulation module, and energy waste is reduced and economic benefits of system operation are improved through optimization of temperature and humidity change curves and control strategies.

Description

Technical Field

[0001] This invention relates to the field of temperature and humidity control technology, specifically to an AI IoT-based intelligent control system and method for constant temperature and humidity in smart farms. Background Technology

[0002] Temperature and humidity, as core parameters of the breeding environment, have a crucial impact on animal growth, health, and reproduction. An ideal breeding environment can improve animal growth rate and feed conversion rate, reduce disease incidence, and enhance animal welfare.

[0003] Existing temperature and humidity control systems rely on fixed setpoints to control temperature and humidity, which cannot flexibly cope with changes between day and night. Most systems simply adjust heating and ventilation equipment based on indoor temperature and humidity data, lacking the ability to monitor and dynamically adjust air quality.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an AI-based smart farm temperature and humidity control system and method.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solution: an AI IoT-based smart farm constant temperature and humidity intelligent control system and method, comprising: a data acquisition module, a data preprocessing module, a data analysis module, a schedule simulation module, a climate simulation module, and an execution module;

[0007] The data acquisition module monitors key parameters of the aquaculture environment in real time through sensors, and all collected data is transmitted to the data preprocessing module for processing.

[0008] The data preprocessing module is responsible for cleaning, denoising, and synchronizing the raw collected data. The preprocessed data will be timestamped and transmitted to the data analysis module.

[0009] The data analysis module extracts the features most relevant to environmental control, analyzes animal activity data and environmental quality through decision trees to determine the health status of the breeding environment, and calculates the air quality index (AQI) by combining temperature, humidity, carbon dioxide and ammonia concentration data to provide a reference for air quality.

[0010] The schedule simulation module generates a temperature and humidity offset value Delta based on the diurnal rhythm and temperature and humidity change patterns, and adjusts the hourly temperature and humidity settings to meet the natural physiological needs of animals.

[0011] The climate simulation module combines local historical meteorological data to build a dynamic regulation model. The model takes long-term climate statistics as input and outputs corresponding temperature and humidity adjustment strategies.

[0012] The execution module is the core of the system, responsible for translating control strategies into actual temperature and humidity regulation behaviors. Based on the regulation strategies provided by the data analysis module and the climate simulation module, this module controls the temperature and humidity equipment to regulate the farm environment.

[0013] The data acquisition module is responsible for collecting environmental parameters in the breeding environment in real time. It uses temperature and humidity sensors to monitor the temperature and humidity in the breeding environment; it uses a carbon dioxide concentration sensor to detect the carbon dioxide concentration in the air; and it uses an ammonia concentration sensor to monitor the ammonia concentration. All collected data are transmitted to the data preprocessing module.

[0014] The data preprocessing module is responsible for cleaning and processing the raw data transmitted from the data acquisition module; for ammonia and carbon dioxide concentration data, the Z-score noise reduction algorithm is used to remove extreme data points; for temperature and humidity data, the moving average algorithm is used to smooth the data and reduce data deviation caused by sensor errors; the SHAP technology is used to perform feature selection and optimization on the data collected by the sensor, remove redundant features, and the processed data is transmitted to the data analysis module.

[0015] The data analysis module calculates the Air Quality Index (AQI) based on the preprocessed data to measure the environmental health status and transmits it to the execution module. The AQI calculation is based on data from temperature and humidity sensors, carbon dioxide concentration sensors, and ammonia concentration sensors to measure the air quality within the farm. The AQI is calculated using the following formula:

[0016]

[0017] Among them, w1, w2, and w3 are the weighting coefficients of each gas concentration, which are adjusted according to the actual needs of the breeding environment; C is the carbon dioxide concentration value inside the breeding farm, N is the ammonia concentration value inside the breeding farm, and H is the humidity value inside the breeding farm.

[0018] The schedule simulation module generates daily temperature and humidity schedule offset values ​​by combining the day-night rhythm and the environmental temperature and humidity change patterns at different times, and makes fine adjustments to the set target temperature and humidity, dynamically adjusting the environmental temperature and humidity settings throughout the day.

[0019] The schedule simulation module pre-stores day-night temperature and humidity variation curves, uses sine / cosine functions to fit the 24-hour cycle, and the algorithm calculates the corresponding offset value based on the current time, using the hour of the day as input. The current temperature and humidity offset value Delta is obtained, where A is the amplitude, t is the current hourly value, and phi is the phase adjustment parameter.

[0020] The key parameters of the schedule offset algorithm include daily cycle, offset amplitude, and phase. The amplitude determines the deviation of the daytime maximum and nighttime minimum temperature and humidity relative to the reference value, which is set according to the habits and comfort range of the farmed species. The phase adjustment parameter phi is used to control the time when the peak occurs, setting the highest temperature point in the afternoon and the lowest point at dawn. The parameter selection principle is to conform to the activity habits of animals and plants. The schedule offset value is updated hourly.

[0021] The climate simulation module combines historical meteorological data and weather information to construct a climate simulation model, which is used to correct indoor environmental parameters in a timely manner according to seasonal and real-time climate changes, so that the farm can simulate the real climate.

[0022] The input data required for the climate simulation model includes long-term climate statistics and real-time weather data. Long-term climate statistics include local annual average temperature and humidity, typical temperature and humidity levels and trends in each season, as well as extreme climate conditions such as maximum and minimum temperatures and seasonal humidity fluctuations. This historical data is obtained from meteorological departments. The real-time weather data is obtained through a weather API, providing weather forecast information for the current day and the next few days. The model construction uses a machine learning-based predictive model to dynamically adjust the strategy, uses a rule base to correct the set values, and trains the model using historical climate and environmental control data. The output of the climate simulation model is the temperature and humidity setting strategy, which is transmitted to the execution module. The adjustment strategy output by the climate simulation module needs to be superimposed with the schedule offset, and the schedule offset is superimposed on the target value set by the basic settings to form the final temperature and humidity adjustment value.

[0023] The execution module is responsible for converting temperature and humidity adjustment values ​​into actual temperature and humidity adjustment behaviors, including the selection of specific controllers and the execution of temperature and humidity setting strategies. This module drives temperature control equipment and humidity control equipment to achieve precise adjustment of the farm environment.

[0024] The execution module includes a temperature controller and a humidity controller, which are used to regulate the heat and humidity of the environment respectively. The temperature controller uses an industrial thermostat to connect the heater and the refrigeration device. The electric heater and the ventilation fan are all uniformly scheduled by the temperature controller. The humidity controller is connected to the humidifier and the dehumidification device. A closed-loop feedback control strategy is adopted to keep the environment within the target range. The control algorithm includes traditional PID control and intelligent control. The PID control adjusts the heating / humidification power in real time according to the temperature and humidity deviation through proportional calculation.

[0025] The execution module further sets a health threshold. When the AQI value exceeds the health threshold, the execution module will control the ventilation fan to turn on. When the AQI value is less than the health threshold, the ventilation fan will stop running.

[0026] The specific method of the AI ​​IoT-based smart farm constant temperature and humidity intelligent control method is as follows:

[0027] S1. The data acquisition module monitors various environmental parameters in the breeding environment in real time through sensors and transmits the collected data to the data preprocessing module.

[0028] S2. The data preprocessing module receives the raw data from the data acquisition module, performs cleaning, noise reduction and synchronization processing, and the data analysis module calculates the AQI value of the air quality in the farm based on the preprocessed data.

[0029] S3, the schedule simulation module generates temperature and humidity offset values ​​based on the day-night rhythm and temperature and humidity change patterns, and adjusts the temperature and humidity settings every hour;

[0030] S4. The climate simulation module outputs temperature and humidity control strategies; these strategies are then superimposed with the schedule offset values ​​to form the final temperature and humidity adjustment values.

[0031] S5. The execution module receives the temperature and humidity adjustment values ​​and converts them into actual temperature and humidity adjustment behaviors.

[0032] This invention provides an AI-based IoT-based intelligent control system and method for constant temperature and humidity in smart farms. Compared with existing technologies, it has the following advantages:

[0033] This invention combines a schedule simulation and a climate simulation module, enabling the system to adjust temperature and humidity setpoints according to diurnal rhythm changes. By optimizing temperature and humidity change curves and control strategies, energy waste is reduced and the economic efficiency of system operation is improved.

[0034] This invention adjusts environmental parameters such as temperature, humidity, and air quality in a farm by combining sensor data and control strategies; ensuring that the environment in the farm is in an optimal state, adapting to environmental needs at different times, and improving the growth efficiency and health of animals.

[0035] This invention monitors air quality in farms by calculating the Air Quality Index (AQI) and adjusts the operation of ventilation equipment based on the AQI value. This mechanism effectively prevents the accumulation of harmful gases, reduces the negative impact of environmental pollution on animals, and improves the sustainability of farming and animal health. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the principle framework of the present invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] Please see Figure 1 This application provides an AI IoT-based smart farm constant temperature and humidity intelligent control system and method, including a data acquisition module, a data preprocessing module, a data analysis module, a schedule simulation module, a climate simulation module, and an execution module;

[0039] The data acquisition module monitors key parameters of the aquaculture environment in real time through sensors, and all collected data is transmitted to the data preprocessing module for processing.

[0040] The data preprocessing module is responsible for cleaning, denoising, and synchronizing the raw collected data. The preprocessed data will be timestamped and transmitted to the data analysis module.

[0041] The data analysis module extracts the features most relevant to environmental control, analyzes animal activity data and environmental quality through decision trees to determine the health status of the breeding environment, and calculates the air quality index (AQI) by combining temperature, humidity, carbon dioxide and ammonia concentration data to provide a reference for air quality.

[0042] The schedule simulation module generates a temperature and humidity offset value Delta based on the diurnal rhythm and temperature and humidity change patterns, and adjusts the hourly temperature and humidity settings to meet the natural physiological needs of animals.

[0043] The climate simulation module combines local historical meteorological data to build a dynamic regulation model. The model takes long-term climate statistics as input and outputs corresponding temperature and humidity adjustment strategies.

[0044] The execution module is the core of the system, responsible for translating control strategies into actual temperature and humidity regulation behaviors. Based on the regulation strategies provided by the data analysis module and the climate simulation module, this module controls the temperature and humidity equipment to regulate the farm environment.

[0045] The data acquisition module is responsible for collecting environmental parameters in the breeding environment in real time. It uses temperature and humidity sensors to monitor the temperature and humidity in the breeding environment; it uses a carbon dioxide concentration sensor to detect the carbon dioxide concentration in the air; and it uses an ammonia concentration sensor to monitor the ammonia concentration. All collected data is transmitted to the data preprocessing module.

[0046] The data preprocessing module is responsible for cleaning and processing the raw data transmitted from the data acquisition module; for ammonia and carbon dioxide concentration data, the Z-score denoising algorithm is used to remove extreme data points; for temperature and humidity data, the moving average algorithm is used to smooth the data and reduce data deviation caused by sensor errors; SHAP technology is used to perform feature selection and optimization on the data collected by the sensor, remove redundant features, and the processed data is transmitted to the data analysis module.

[0047] The data analysis module calculates the Air Quality Index (AQI) based on the preprocessed data to measure the environmental health status and transmits it to the execution module. The AQI calculation is based on data from temperature and humidity sensors, carbon dioxide concentration sensors, and ammonia concentration sensors to measure air quality within the farm. The AQI is calculated using the following formula:

[0048]

[0049] Among them, w1, w2, and w3 are the weighting coefficients of each gas concentration, which are adjusted according to the actual needs of the breeding environment; C is the carbon dioxide concentration value inside the breeding farm, N is the ammonia concentration value inside the breeding farm, and H is the humidity value inside the breeding farm.

[0050] The schedule simulation module generates daily temperature and humidity schedule offset values ​​by combining the day-night rhythm and the changes in ambient temperature and humidity at different times, and makes fine adjustments to the set target temperature and humidity, dynamically adjusting the ambient temperature and humidity settings throughout the day.

[0051] The schedule simulation module pre-stores day-night temperature and humidity variation curves, uses sine / cosine functions to fit the 24-hour cycle, and the algorithm calculates the corresponding offset value based on the current time, using the hour of the day as input. The current temperature and humidity offset value Delta is obtained, where A is the amplitude, t is the current hourly value, and phi is the phase adjustment parameter.

[0052] The key parameters of the schedule offset algorithm include daily cycle, offset amplitude, and phase. The amplitude determines the deviation of the daytime maximum and nighttime minimum temperature and humidity relative to the reference value, which is set according to the habits and comfort range of the farmed species. The phase adjustment parameter phi is used to control the time when the peak occurs, setting the highest temperature point in the afternoon and the lowest point at dawn. The parameter selection principle is to conform to the activity habits of animals and plants. The schedule offset value is updated hourly.

[0053] Offset range: The offset value is usually limited to ±5% to 10% of the baseline setting to ensure that the adjustment is within a reasonable range. For example, when the temperature target is 20℃, the schedule offset can be adjusted up to 22℃ or down to 18℃ at most; when the humidity target is 60%, the schedule offset is controlled between 54% and 66%. The specific range is set according to the tolerance of the farmed animals. If the farmed animals are sensitive to temperature changes, a smaller offset (such as ±1℃) is used. In any case, the offset range will be constrained to avoid exceeding the animal's comfort range.

[0054] For example, if the base temperature is set to 20℃, when the schedule module generates an offset of +1.0℃ at noon, the actual control target is raised to 21.0℃; when it generates an offset of -1.0℃ at midnight, the target drops to 19.0℃. The same applies to humidity. By offsetting, appropriate increases and decreases are achieved between day and night. Such fine-tuning ensures that environmental parameters fluctuate slightly within the daily cycle, simulating natural day-night changes to make organisms feel more comfortable, and also avoiding the disruption of physiological rhythms caused by constant energy.

[0055] The climate simulation module combines historical meteorological data and weather information to build a climate simulation model, which is used to correct indoor environmental parameters in a timely manner according to seasonal and real-time climate changes, so that the farm can simulate the real climate.

[0056] The input data required for the climate simulation model includes long-term climate statistics and real-time weather data. Long-term climate statistics include local annual average temperature and humidity, typical temperature and humidity levels and trends in each season, as well as extreme climate conditions such as maximum and minimum temperatures and seasonal humidity fluctuations. This historical data is obtained from meteorological departments, while real-time weather data is obtained through weather APIs for the current day and the weather forecast information for the next few days. The model construction adopts a machine learning-based predictive model to dynamically adjust the strategy, uses a rule base to correct the set values, and trains the model using historical climate and environmental control data. The output of the climate simulation model is the temperature and humidity setting strategy, which is transmitted to the execution module. The adjustment strategy output by the climate simulation module needs to be superimposed with the schedule offset, and the schedule offset is superimposed on the target value of the basic setting to form the final temperature and humidity adjustment value.

[0057] In practice, model prediction is used to optimize the set trajectory for the next 24 hours by using climate prediction as a feedforward. Both rules and learning models need to be regularly verified and updated: the rule base needs to be revised according to new climate data, and the climate simulation model continuously updates its parameters online with new data to ensure that the prediction matches the actual situation.

[0058] In the implementation of the coordinated regulation mechanism, when the schedule simulation requires a nighttime temperature drop, and the climate model detects a sharp drop in outdoor temperature tonight, the overall result can be to reduce the temperature drop to ensure the biological rhythm needs while preventing the room temperature from becoming too low. In practice, coordinated regulation is accomplished through a weighted average or priority mechanism: climate offset is assigned a certain weight according to the urgency of the weather impact, and works together with the schedule offset. If the external climate changes drastically, the climate offset has the main weight to ensure environmental safety; otherwise, the schedule regulation takes the lead to maintain normal rhythm. Through such coordination, the system can both follow daily routines and respond to abnormal weather, ensuring that the breeding environment is always maintained within the optimal range.

[0059] For example, Mediterranean climate regulation strategies:

[0060] This is used to ensure a cool and humid breeding environment, avoiding stress reactions in animals caused by high temperatures and low humidity.

[0061] Indoor temperature setting:

[0062] Daytime: 24°C - 26°C (The system will automatically adjust to this range when the outdoor temperature is above 30°C).

[0063] Nighttime: 22°C - 24°C (the temperature may be lowered depending on the outside temperature and the animal's rest needs).

[0064] Humidity setting:

[0065] Daytime: 60% - 70% (Maintain humidity using humidifiers to prevent low humidity from causing water loss in the animals).

[0066] Nighttime: 65% - 75% (Increase humidity to maintain a suitable breathing environment and prevent respiratory problems caused by dry air)

[0067] The execution module is responsible for converting temperature and humidity adjustment values ​​into actual temperature and humidity adjustment behaviors, including the selection of specific controllers and the execution of temperature and humidity setting strategies. This module drives temperature control equipment and humidity control equipment to achieve precise adjustment of the farm environment.

[0068] The execution module includes one set of temperature controller and one set of humidity controller, which are used to regulate the heat and humidity of the environment respectively. The temperature controller uses an industrial thermostat to connect the heater and the refrigeration unit. The electric heater and the ventilation fan are all uniformly scheduled by the temperature controller. The humidity controller is connected to the humidifier and dehumidification equipment. A closed-loop feedback control strategy is adopted to keep the environment within the target range. The control algorithm includes traditional PID control and intelligent control. The PID control adjusts the heating / humidification power in real time according to the temperature and humidity deviation through proportional calculation.

[0069] The execution module transmits control signals to the actuator hardware in the field through various interfaces. Analog outputs (4-20mA current loop or 0-10V voltage) are used to control valve opening and fan speed; digital switch outputs control relays to achieve equipment on / off control; and wireless communication is also available for connecting IoT devices. In this system, the temperature controller controls the heater on / off through the relay interface and adjusts the fan speed through the analog interface to achieve precise temperature control; the humidity controller controls the humidifier's water supply start and stop through the solenoid valve drive interface. The transmission and electrical connection of all interface signals comply with industry standards.

[0070] The execution module further sets health thresholds. When the AQI value exceeds the health threshold, the execution module will control the ventilation fan to turn on. When the AQI value is less than the health threshold, the ventilation fan will stop running.

[0071] The specific method of AI-based smart farm temperature and humidity control is as follows:

[0072] S1. The data acquisition module monitors various environmental parameters in the breeding environment in real time through sensors and transmits the collected data to the data preprocessing module.

[0073] S2. The data preprocessing module receives the raw data from the data acquisition module, performs cleaning, noise reduction and synchronization processing, and the data analysis module calculates the AQI value of the air quality in the farm based on the preprocessed data.

[0074] S3, the schedule simulation module generates temperature and humidity offset values ​​based on the day-night rhythm and temperature and humidity change patterns, and adjusts the temperature and humidity settings every hour;

[0075] S4. The climate simulation module outputs temperature and humidity control strategies; these strategies are then superimposed with the schedule offset values ​​to form the final temperature and humidity adjustment values.

[0076] S5. The execution module receives the temperature and humidity adjustment values ​​and converts them into actual temperature and humidity adjustment behaviors.

[0077] Furthermore, by combining schedule simulation and climate simulation modules, the system can adjust temperature and humidity setpoints according to diurnal rhythm changes; by optimizing temperature and humidity change curves and control strategies, energy waste is reduced and the economic efficiency of system operation is improved.

[0078] This invention adjusts environmental parameters such as temperature, humidity, and air quality in a farm by combining sensor data and control strategies; it ensures that the environment in the farm is in an optimal state, adapts to environmental needs at different times, and improves the growth efficiency and health of animals.

[0079] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0080] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An AI-based IoT-based intelligent temperature and humidity control system for smart farms, characterized in that: include: The system includes a data acquisition module, a data preprocessing module, a data analysis module, a schedule simulation module, a climate simulation module, and an execution module. The data acquisition module monitors key parameters of the aquaculture environment in real time through sensors, and all collected data is transmitted to the data preprocessing module for processing. The data preprocessing module is responsible for cleaning, denoising, and synchronizing the raw collected data. The preprocessed data will be timestamped and transmitted to the data analysis module. The data analysis module extracts the features most relevant to environmental control, analyzes animal activity data and environmental quality through decision trees to determine the health status of the breeding environment, and calculates the air quality index (AQI) by combining temperature, humidity, carbon dioxide and ammonia concentration data to provide a reference for air quality. The schedule simulation module generates a temperature and humidity offset value Delta based on the diurnal rhythm and temperature and humidity change patterns, and adjusts the hourly temperature and humidity settings to meet the natural physiological needs of animals. The schedule simulation module generates daily temperature and humidity schedule offset values ​​by combining the circadian rhythm and the environmental temperature and humidity change patterns at different times, and makes fine adjustments to the set target temperature and humidity, dynamically adjusting the environmental temperature and humidity settings throughout the day. The schedule simulation module pre-stores diurnal temperature and humidity variation curves, uses sine / cosine functions to fit the 24-hour cycle, and the algorithm calculates the corresponding offset value based on the current time, using the hour of the day as input. The current temperature and humidity offset value Delta is obtained, where A is the amplitude, t is the current hourly value, and phi is the phase adjustment parameter. The key parameters of the schedule offset algorithm include daily cycle, offset amplitude, and phase. The amplitude determines the deviation of the daytime maximum and nighttime minimum temperature and humidity relative to the reference value, which is set according to the habits and comfort range of the farmed species. The phase adjustment parameter phi is used to control the time of peak occurrence, setting the highest temperature point in the afternoon and the lowest point at dawn. The parameter selection principle is to conform to the activity habits of animals and plants. The schedule offset value is updated hourly. The climate simulation module combines local historical meteorological data to build a climate simulation model, inputs long-term climate statistics, and outputs temperature and humidity setting strategies. The execution module is the core of the system, responsible for translating control strategies into actual temperature and humidity regulation behaviors. Based on the regulation strategies provided by the data analysis module and the climate simulation module, this module controls the temperature and humidity equipment to regulate the farm environment.

2. The AI ​​IoT-based intelligent temperature and humidity control system for smart farms according to claim 1, characterized in that, The data acquisition module is responsible for collecting environmental parameters in the breeding environment in real time. It uses temperature and humidity sensors to monitor the temperature and humidity in the breeding environment; it uses a carbon dioxide concentration sensor to detect the carbon dioxide concentration in the air; and it uses an ammonia concentration sensor to monitor the ammonia concentration. All collected data are transmitted to the data preprocessing module.

3. The AI ​​IoT-based smart farm temperature and humidity intelligent control system according to claim 1, characterized in that, The data preprocessing module is responsible for cleaning and processing the raw data transmitted from the data acquisition module; for ammonia and carbon dioxide concentration data, the Z-score noise reduction algorithm is used to remove extreme data points; for temperature and humidity data, the moving average algorithm is used to smooth the data and reduce data deviation caused by sensor errors; the SHAP technology is used to select and optimize features of the data collected by the sensor, remove redundant features, and transmit the processed data to the data analysis module.

4. The AI ​​IoT-based intelligent temperature and humidity control system for smart farms according to claim 1, characterized in that, The data analysis module calculates the Air Quality Index (AQI) based on the preprocessed data to measure the environmental health status and transmits it to the execution module. The AQI calculation is based on data from temperature and humidity sensors, carbon dioxide concentration sensors, and ammonia concentration sensors to measure the air quality within the farm. The AQI is calculated using the following formula: Among them, w1, w2, and w3 are the weighting coefficients of each gas concentration, which are adjusted according to the actual needs of the breeding environment; C is the carbon dioxide concentration value inside the breeding farm, N is the ammonia concentration value inside the breeding farm, and H is the humidity value inside the breeding farm.

5. The AI ​​IoT-based intelligent temperature and humidity control system for smart farms according to claim 1, characterized in that, The climate simulation module combines historical meteorological data and weather information to construct a climate simulation model, which is used to correct indoor environmental parameters in a timely manner according to seasonal and real-time climate changes, so that the farm can simulate the real climate.

6. The AI ​​IoT-based intelligent temperature and humidity control system for smart farms according to claim 1, characterized in that, The input data required for the climate simulation model includes long-term climate statistics and real-time weather data. Long-term climate statistics include local annual average temperature and humidity, typical temperature and humidity levels and trends in the four seasons, as well as extreme climate conditions such as maximum and minimum temperatures and seasonal humidity fluctuations. This historical data is obtained from meteorological departments. The real-time weather data is obtained through weather API to obtain weather forecast information for the current day and the next few days. The climate simulation model is constructed using a machine learning-based predictive model to dynamically adjust the policy. A rule base is used to correct the set values, and the climate simulation model is trained using historical climate and environmental control data. The output of the climate simulation model is the temperature and humidity setting policy, which is transmitted to the execution module. The adjustment policy output by the climate simulation module needs to be superimposed with the schedule offset. The schedule offset is superimposed on the target value of the basic setting to form the final temperature and humidity adjustment value.

7. The AI ​​IoT-based intelligent temperature and humidity control system for smart farms according to claim 1, characterized in that, The execution module is responsible for converting the temperature and humidity adjustment values ​​into actual temperature and humidity adjustment behaviors, including the selection of specific controllers and the execution of temperature and humidity setting strategies. The execution module drives the temperature control equipment and humidity control equipment to achieve precise adjustment of the farm environment. The execution module includes a temperature controller and a humidity controller, which are used to regulate the heat and humidity of the environment respectively. The temperature controller uses an industrial thermostat to connect the heater and the refrigeration device. The electric heater and the ventilation fan are all uniformly scheduled by the temperature controller. The humidity controller is connected to the humidifier and the dehumidification device. A closed-loop feedback control strategy is adopted to keep the environment within the target range. The control algorithm includes traditional PID control and intelligent control. The PID control adjusts the heating or humidification power in real time according to the temperature and humidity deviation through proportional calculation. The execution module further sets a health threshold. When the AQI value exceeds the health threshold, the execution module will control the ventilation fan to turn on. When the AQI value is less than the health threshold, the ventilation fan will stop running.

8. A method for intelligent temperature and humidity control in smart farms based on AI and IoT, applied to the intelligent temperature and humidity control system for smart farms based on AI and IoT as described in any one of claims 1-7, characterized in that, The specific method of the AI ​​IoT-based smart farm constant temperature and humidity intelligent control method is as follows: S1. The data acquisition module monitors various environmental parameters in the breeding environment in real time through sensors and transmits the collected data to the data preprocessing module. S2. The data preprocessing module receives the raw data from the data acquisition module, performs cleaning, noise reduction and synchronization processing, and the data analysis module calculates the AQI value of the air quality in the farm based on the preprocessed data. S3, the schedule simulation module generates a temperature and humidity offset value Delta based on the diurnal rhythm and temperature and humidity change patterns, and adjusts the temperature and humidity settings every hour. S4. The climate simulation module outputs temperature and humidity control strategies; these strategies are then superimposed with the schedule offset values ​​to form the final temperature and humidity adjustment values. S5. The execution module receives the temperature and humidity adjustment values ​​and converts them into actual temperature and humidity adjustment behaviors.

Images