Temperature-variable animal incubator based on intelligent temperature and humidity regulation and remote monitoring system thereof

Abstract

The application belongs to the technical field of poikilothermic animal culture, and discloses a poikilothermic animal incubator based on intelligent temperature and humidity regulation and a remote monitoring system thereof, which comprises an incubator and a sensor acquisition module, an actuator control module, an intelligent regulation module and a central controller.The intelligent regulation module can automatically judge the deviation between the real-time sensor data and the target value, timely adjust the PID parameters through fuzzy processing, finely control the temperature and humidity output, and predict the future changes in advance by using the AI prediction module, so as to effectively compensate for the control delay, reduce the overshoot and shock risk, and compared with the traditional incubator, the intelligent regulation strategy not only greatly improves the response speed and stability of the environmental regulation, but also can manually regulate the scheme according to different time periods and animal physiological changes, realizes energy saving and consumption reduction and long-term operation of the equipment, and enhances the adaptability and robustness of the system in complex environments.

Description

Technical Field

[0001] This invention belongs to the field of poikilothermic animal culture technology, specifically a poikilothermic animal incubator based on intelligent temperature and humidity control and its remote monitoring system. Background Technology

[0002] Poikilothermic animals are animals that cannot actively maintain a constant body temperature through their own metabolic activities. Their body temperature fluctuates with changes in the external environment temperature. When the external temperature rises, their metabolic activities increase and they move more agilely; when the temperature drops, their metabolism slows down, their mobility decreases, and they may even enter a dormant state.

[0003] Since poikilothermic animals rely on behavioral regulation for survival, such as adjusting their body temperature by basking in the sun or seeking shade to adapt to different environments, specialized incubators are usually used to simulate natural environments and provide suitable living conditions for poikilothermic animals in order to better observe them. These incubators control parameters such as temperature, humidity, and light within the incubator to meet the specific needs of different species.

[0004] However, most incubators currently use traditional PID (proportional-integral-derivative) control algorithms. Although these algorithms are simple in structure and easy to implement, they perform poorly when dealing with nonlinear and time-varying temperature and humidity environments. For example, the culture environment for poikilothermic animals usually needs to simulate diurnal temperature differences or seasonal changes. PID algorithms are prone to overshooting or oscillation when dealing with rapidly changing setpoints, causing temperature and humidity fluctuations to exceed the allowable range. In addition, parameter tuning is difficult in complex environments (such as high humidity and high temperature or low temperature and low humidity), making it difficult for the system to remain stable under different operating conditions. Therefore, it is necessary to improve and optimize these algorithms. Summary of the Invention

[0005] The purpose of this invention is to provide a variable-temperature animal incubator based on intelligent temperature and humidity control and its remote monitoring system, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a variable-temperature animal incubator based on intelligent temperature and humidity control and its remote monitoring system, comprising an incubator, wherein the variable-temperature animal incubator includes a sensor acquisition module, an actuator control module, an intelligent control module and a central controller; The sensor acquisition module includes a temperature sensor, a humidity sensor, and a CO2 sensor. The actuator control module includes a temperature-controlled air conditioner, a humidity controller, and a lighting system. The intelligent control module includes a fuzzy PID control unit, an AI prediction unit, and an anomaly handling unit. The intelligent control module also includes a human-machine interaction platform for setting the target temperature and humidity parameters inside the incubator.

[0007] Preferably, the central controller includes an MCU and an edge controller. Each group of sensors in the sensor acquisition module transmits the acquired data to the central controller. Typically, the MCU in the central controller preprocesses all sensor data. After processing, the central controller transmits the data to the intelligent control module through the internal data bus, and the edge controller directly stores the data in the cache. Then, it periodically uploads the data to the cloud platform through the network interface.

[0008] Preferably, the fuzzy PID control unit includes five fuzzy sets defined by a trapezoidal function: "negative large", "negative small", "close to zero", "positive small", and "positive large". The fuzzy PID control unit also includes a rule base, which stores the PID parameter correction values ​​corresponding to different combinations.

[0009] Preferably, the sensor acquisition module transmits the acquired data to the central controller every five seconds. The fuzzy PID control unit in the intelligent control module performs error calculation after receiving the target value and the actual measured value. ; After the calculation is completed, the error of each sensor is fuzzified through fuzzy set processing to form the corresponding linguistic variable. Then, based on the current fuzzified value, the corresponding PID parameter correction value is calculated by searching and interpolating from the rule base. Finally, the correction value is superimposed on the preset basic PID parameter to obtain the PID parameter used in the current control cycle.

[0010] Preferably, the AI ​​prediction unit includes an LSTM model built using the TensorFlow framework, and its training and deployment steps are as follows: S1 extracts temperature and humidity data stored in the cloud by the edge controller over the past thirty minutes; S2, preprocess the data to adapt it to the input requirements of the neural network; S3, After the model is built, the input is a temperature and humidity sequence over a period of time, and the model will output a prediction of temperature and humidity changes over a future period of time; S4 compresses and transfers the trained model file to the edge controller. The edge controller loads the model, predicts the real-time cached data, and obtains the temperature and humidity trend for the next 10 minutes.

[0011] Preferably, after predicting the output result, the AI ​​prediction unit combines the control output of the fuzzy PID unit with the adjustment suggestions of the AI ​​prediction unit to obtain the final control signal sent to the actuator. If the predicted future temperature and humidity change trends are significantly contrary to the current output, compensation is performed in advance based on the prediction result.

[0012] Preferably, the sensor acquisition module transmits the acquired data to the central controller in real time. The central controller transmits the current data and target data to the intelligent control module. After performing error calculation, fuzzification, and adaptive adjustment of PID parameters, the intelligent control module outputs a basic control signal. The AI ​​prediction unit uses historical data to predict future trends and compensates for the basic control signal. The comprehensively adjusted control signal is then sent to the actuator module to perform environmental adjustment. After the actuator responds, environmental changes are again acquired by the sensor, forming a continuous feedback loop.

[0013] Preferably, the anomaly handling unit includes a data monitoring program. When monitoring sensor data, if the set parameter exceeds the safety threshold, the data monitoring program will switch the control parameter to a conservative value until the data returns to normal.

[0014] Preferably, the remote monitoring system includes a monitoring camera and a user terminal. The monitoring camera transmits the captured animal images to an edge controller, which then transmits the monitoring images to a cloud server. Users can use the user terminal to perform real-time monitoring, remote control, and historical data queries.

[0015] The beneficial effects of this invention are as follows: 1. The intelligent control module of this invention can automatically judge the deviation between the target value and the real-time sensor data, and adjust the PID parameters in a timely manner through fuzzy processing to finely control the temperature and humidity output. At the same time, it uses the AI ​​prediction module to predict future changes in advance, thereby effectively compensating for control delay and reducing the risk of overshoot and oscillation. Compared with traditional incubators, this intelligent control strategy not only greatly improves the response speed and stability of environmental control, but also allows manual switching of control schemes according to different time periods and animal physiological changes, achieving energy saving and consumption reduction and long-term operation of the equipment, and enhancing the system's adaptability and robustness in complex environments.

[0016] 2. This invention achieves precise compensation for current environmental errors through a fuzzy PID control unit, predicts future changes and fine-tunes the control strategy in advance through an AI prediction unit, provides reasonable target settings through a human-computer interaction platform, and adds full-process monitoring by an anomaly handling unit, thus forming an intelligent closed-loop temperature and humidity control system with both adaptive capabilities and advance adjustment functions. Through the collaborative work of these modules, the system ensures that the variable-temperature animal incubator is always in an ideal state under nonlinear and time-varying environments from multiple levels, while maximizing the safety of the equipment and animals.

[0017] 3. Through the setting of a remote monitoring system, users can view the changing trends of key indicators such as temperature, humidity, and light in real time via web pages or mobile devices, and keep abreast of the environmental conditions inside the incubator. At the same time, when environmental parameters exceed the safety threshold, the system will automatically trigger an alarm mechanism and promptly notify the operator to intervene via SMS, email, or App push, thereby reducing the risk to poikilothermic animals caused by equipment failure or external abnormalities. Attached Figure Description

[0018] Figure 1 This is a flowchart of the intelligent control process of the present invention; Figure 2 This is a schematic diagram of the incubator structure of the present invention; Figure 3 This is a diagram showing the internal hardware layout of the incubator of this invention.

[0019] In the diagram: 1. Incubator; 2. Humidity sensor; 3. Temperature sensor; 4. CO2 sensor; 5. Temperature control air conditioner; 6. Lighting system; 7. Intelligent control module; 8. Humidity controller; 9. Central controller. Detailed Implementation

[0020] 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.

[0021] like Figures 1 to 3 As shown, this embodiment of the invention provides a variable-temperature animal incubator based on intelligent temperature and humidity control and its remote monitoring system, including an incubator 1, which includes a sensor acquisition module, an actuator control module, an intelligent control module 7 and a central controller 9; The sensor acquisition module includes a temperature sensor 3, a humidity sensor 2, and a CO2 sensor 4. The actuator control module includes a temperature-controlled air conditioner 5, a humidity controller 8, and a lighting system 6. The intelligent control module 7 includes a fuzzy PID control unit, an AI prediction unit, and an anomaly handling unit. The intelligent control module 7 also includes a human-machine interaction platform for setting the target temperature and humidity parameters inside the incubator.

[0022] By setting up multi-sensor real-time monitoring, intelligent control, and manual switching of preset scenes, the incubator 1 achieves accurate reproduction of the natural environment. It can simulate the diurnal temperature difference, seasonal changes, and special ecological environment according to the physiological needs of organisms, so that the environmental indicators such as temperature, humidity, and light in the incubator are always kept within the ideal range, thereby providing a growth environment for poikilothermic animals that is closer to their natural habitat.

[0023] The central controller 9 includes an MCU and an edge controller. Each group of sensors in the sensor acquisition module transmits the acquired data to the central controller 9. Typically, the MCU in the central controller 9 preprocesses all sensor data. After processing, the central controller 9 transmits the data to the intelligent control module 7 via the internal data bus, and the edge controller directly stores the data in the cache. The data is then periodically uploaded to the cloud platform via the network interface.

[0024] The fuzzy PID control unit includes five fuzzy sets defined by a trapezoidal function: "negative large", "negative small", "close to zero", "positive small", and "positive large". The fuzzy PID control unit also includes a rule base, which stores the PID parameter correction values ​​corresponding to different combinations (error and error change rate) through a rule base (two-dimensional array or structure array).

[0025] The sensor acquisition module transmits the acquired data to the central controller 9 every five seconds. The fuzzy PID control unit in the intelligent control module 7 calculates the error after receiving the target value and the actual measured value. ; Current temperature The current humidity. Target temperature Target humidity After the calculation is completed, the error of each sensor is fuzzified through fuzzy set processing to form the corresponding linguistic variable. Then, based on the current fuzzified value, the corresponding PID parameter correction value is calculated by searching and interpolating from the rule base. Finally, the correction value is superimposed on the preset basic PID parameter to obtain the PID parameter used in the current control cycle.

[0026] The intelligent control module 7 of this application can automatically determine the deviation between the target value and the real-time sensor data, and adjust the PID parameters in a timely manner through fuzzy processing to finely control the temperature and humidity output. At the same time, it uses the AI ​​prediction module to predict future changes in advance, thereby effectively compensating for control delay and reducing the risk of overshoot and oscillation. Compared with traditional incubators, this intelligent control strategy not only greatly improves the response speed and stability of environmental control, but also automatically switches the control scheme according to different time periods and animal physiological changes, achieving energy saving and consumption reduction and long-term operation of the equipment, and enhancing the system's adaptability and robustness in complex environments.

[0027] The AI ​​prediction unit includes an LSTM model built using the TensorFlow framework, and its training and deployment steps are as follows: S1 extracts temperature and humidity data stored in the cloud by the edge controller over the past thirty minutes; S2, preprocess the data to adapt it to the input requirements of the neural network; S3, After the model is built, the input is a temperature and humidity sequence over a period of time, and the model will output a prediction of temperature and humidity changes over a future period of time; S4 compresses and transfers the trained model file to the edge controller. The edge controller loads the model, predicts the real-time cached data, and obtains the temperature and humidity trend for the next 10 minutes.

[0028] The AI ​​prediction unit, after predicting the output result, combines the control output of the fuzzy PID unit with the adjustment suggestions of the AI ​​prediction unit to obtain the final control signal sent to the actuator. If the predicted future temperature or humidity change trend is significantly contrary to the current output, compensation is performed in advance based on the prediction result.

[0029] This module employs a Long Short-Term Memory (LSTM) network model. Due to its advantages in capturing temporal correlations and processing sequential data, it can predict the changing trends of environmental parameters over a future period. Based on the prediction results, the system can anticipate potential large fluctuations and thus pre-adjust control signals. For example, if the predicted temperature will rise sharply in the near future, even if the current error is small, the system can initiate cooling measures in advance or reduce heater output to avoid significant overshoot due to system delay. Similarly, for humidity prediction, humidification or dehumidification devices can be activated in advance to stabilize the environment.

[0030] The sensor acquisition module transmits the acquired data to the central controller 9 in real time. The central controller 9 transmits the current data and target data to the intelligent control module 7. The intelligent control module 7 performs error calculation, fuzzification, and adaptive adjustment of PID parameters, and outputs a basic control signal. The AI ​​prediction unit uses historical data to predict future trends and compensates for the basic control signal. The comprehensively adjusted control signal is sent to the actuator module to perform environmental adjustment. After the actuator responds, the environmental changes are collected by the sensor, forming a continuous feedback loop.

[0031] By using a fuzzy PID control unit to accurately compensate for current environmental errors, an AI prediction unit to anticipate future changes and fine-tune the control strategy in advance, and a human-machine interaction platform to provide reasonable target settings, along with the full-process monitoring by an anomaly handling unit, an intelligent closed-loop temperature and humidity control system is formed that has both adaptive capabilities and pre-adjustment functions. Through the collaborative work of these modules, the system ensures that the variable-temperature animal incubator is always in an ideal state under nonlinear and time-varying environments, while maximizing the safety of the equipment and the animals.

[0032] The anomaly handling unit includes a data monitoring program. When monitoring sensor data, if the set parameters exceed the safety threshold, the data monitoring program will switch the control parameters to a conservative value and issue an alarm until the data returns to normal.

[0033] The system monitors sensor data through a data monitoring program. When abnormal conditions are detected, such as temperature exceeding the limit, an alarm event is generated according to the software's preset rules. When an alarm is triggered, the system can automatically send a notification via SMS, email, or App, and record the alarm information in the database and highlight it on the monitoring interface.

[0034] The remote monitoring system includes a monitoring camera and a user terminal. The monitoring camera transmits the captured animal images to an edge controller, which then transmits the images to a cloud server. Users can use the user terminal to perform real-time monitoring, remote control, and historical data queries.

[0035] By setting up a remote monitoring system, users can view the changing trends of key indicators such as temperature, humidity, and light in real time via web pages or mobile devices, and keep abreast of the environmental conditions inside the incubator. At the same time, when environmental parameters exceed the safety threshold, the system will automatically trigger an alarm mechanism and promptly notify the operator via SMS, email, or App push to intervene, thereby reducing the risks to poikilothermic animals caused by equipment failure or external anomalies.

[0036] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover 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 process, method, article, or apparatus.

[0037] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A variable-temperature animal incubator based on intelligent temperature and humidity control, comprising an incubator (1), characterized in that: The variable temperature animal incubator includes a sensor acquisition module, an actuator control module, an intelligent regulation module (7), and a central controller (9). The sensor acquisition module includes a temperature sensor (3), a humidity sensor (2) and a CO2 sensor (4). The actuator control module includes a temperature control air conditioner (5), a humidity controller (8) and a lighting system (6). The intelligent control module (7) includes a fuzzy PID control unit, an AI prediction unit and an anomaly handling unit. The intelligent control module (7) also includes a human-machine interaction platform for setting the target temperature and humidity parameters in the incubator.

2. The variable-temperature animal incubator based on intelligent temperature and humidity control according to claim 1, characterized in that: The central controller (9) includes an MCU and an edge controller. Each group of sensors in the sensor acquisition module transmits the acquired data to the central controller (9). Usually, the MCU in the central controller (9) preprocesses all sensor data. After processing, the central controller (9) transmits the data to the intelligent control module (7) through the internal data bus, and the edge controller directly stores the data in the cache and then uploads it to the cloud platform through the network interface at regular intervals.

3. The variable-temperature animal incubator based on intelligent temperature and humidity control according to claim 1, characterized in that: The fuzzy PID control unit includes five fuzzy sets defined by a trapezoidal function: "negative large", "negative small", "close to zero", "positive small", and "positive large". The fuzzy PID control unit also includes a rule base, which stores the PID parameter correction values ​​corresponding to different combinations.

4. The variable-temperature animal incubator based on intelligent temperature and humidity control according to claim 1, characterized in that: The sensor acquisition module transmits the acquired data to the central controller (9) every five seconds. The fuzzy PID control unit in the intelligent control module (7) performs error calculation after receiving the target value and the actual measured value. ; After the calculation is completed, the error of each sensor is fuzzified through fuzzy set processing to form the corresponding linguistic variable. Then, based on the current fuzzified value, the corresponding PID parameter correction value is calculated by searching and interpolating from the rule base. Finally, the correction value is superimposed on the preset basic PID parameter to obtain the PID parameter used in the current control cycle.

5. The variable-temperature animal incubator based on intelligent temperature and humidity control according to claim 1, characterized in that: The AI ​​prediction unit includes an LSTM model built using the TensorFlow framework. The training and deployment steps are as follows: S1 extracts temperature and humidity data stored in the cloud by the edge controller over the past thirty minutes; S2, preprocess the data to adapt it to the input requirements of the neural network; S3, After the model is built, the input is a temperature and humidity sequence over a period of time, and the model will output a prediction of temperature and humidity changes over a future period of time; S4 compresses and transfers the trained model file to the edge controller. The edge controller loads the model, predicts the real-time cached data, and obtains the temperature and humidity trend for the next 10 minutes.

6. The variable-temperature animal incubator based on intelligent temperature and humidity control according to claim 1, characterized in that: After predicting the output result, the AI ​​prediction unit combines the control output of the fuzzy PID unit with the adjustment suggestions of the AI ​​prediction unit to obtain the final control signal sent to the actuator. If the predicted future temperature and humidity change trends are significantly contrary to the current output, compensation is performed in advance based on the prediction results.

7. The variable-temperature animal incubator based on intelligent temperature and humidity control according to claim 1, characterized in that: The sensor acquisition module transmits the acquired data to the central controller (9) in real time. The central controller (9) transmits the current data and target data to the intelligent control module (7). After performing error calculation, fuzzification and adaptive adjustment of PID parameters, the intelligent control module (7) outputs the basic control signal. The AI ​​prediction unit uses historical data to predict future trends and compensates for the basic control signal. The comprehensively adjusted control signal is sent to the actuator module to perform environmental adjustment. After the actuator responds, the environmental changes are collected by the sensor, forming a continuous feedback loop.

8. The variable-temperature animal incubator based on intelligent temperature and humidity control according to claim 7, characterized in that: The anomaly handling unit includes a data monitoring program. When monitoring sensor data, if the set parameter exceeds the safety threshold, the data monitoring program will switch the control parameter to a conservative value and issue an alarm until the data returns to normal.

9. A remote monitoring system for a variable-temperature animal incubator based on intelligent temperature and humidity control, characterized in that: The remote monitoring system includes a monitoring camera and a user terminal. The monitoring camera transmits the captured animal images to an edge controller, which then transmits the monitoring images to a cloud server. Users can use the user terminal to perform real-time monitoring, remote control, and historical data queries.

Images