Internet-of-things intelligent regulation and control system for crayfish hatchery in cold region

Abstract

The invention relates to the technical field of aquaculture environment control, and discloses a cold region crayfish hatchery Internet of Things intelligent regulation and control system, which comprises a full-automatic hatching system, and is characterized in that the full-automatic hatching system comprises a hatching unit, an environment regulation module, an identification module, a decision module and an execution unit; the hatching unit divides the crayfish hatching farm into a plurality of groups of hatching sub-units with the same area, and the interiors of the hatching sub-units are provided with the same quantity of crayfish fertilized eggs. The execution unit regulates and controls the heater, the refrigerator, the humidifier and the dehumidifier according to control instructions (first / second / third decisions and abnormal instructions) generated by the decision module and triggers the early warning device to send early warning information to workers in an abnormal state, and an intelligent management and control system with full-process automation and manual intervention cooperation is formed. The hatching success rate and the breeding efficiency are obviously improved.

Description

Technical Field

[0001] This invention relates to the field of aquaculture environmental control technology, and more specifically to an Internet of Things intelligent control system for a cold-region crayfish hatchery. Background Technology

[0002] The crayfish hatching process is highly sensitive to environmental temperature and humidity, especially in cold regions where natural hatching success rates are low and cycles are unstable. Existing hatcheries mostly employ holistic environmental control, which struggles to address localized microenvironmental differences within hatching units, leading to uneven egg development across different areas of the same hatchery. Traditional manual monitoring methods rely on experience to determine hatching stages, resulting in significant subjective errors and delayed responses. Furthermore, conventional temperature and humidity control lacks a dynamic correlation with egg development status, failing to achieve precise on-demand adjustments and easily causing energy waste and decreased hatching rates. Therefore, there is an urgent need for an intelligent system capable of subdividing hatching units, identifying developmental stages in real time, and automatically implementing environmental adjustments. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an Internet of Things intelligent control system for a cold-region crayfish hatchery to solve the technical problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: an Internet of Things (IoT) intelligent control system for a cold-region crayfish hatchery, comprising a fully automated hatching system, wherein the fully automated hatching system includes a hatching unit, an environmental control module, an identification module, a decision-making module, and an execution unit; The incubation unit divides the crayfish hatchery into multiple groups of equally sized incubation sub-units, with each group containing an equal number of crayfish fertilized eggs. Each of the incubation sub-units is equipped with an environmental control module, which is used to dynamically adjust the temperature and humidity parameters within the corresponding sub-unit in real time. The identification module is installed inside the incubation unit to monitor the real-time incubation data of crayfish eggs in each incubation sub-unit. The control unit receives the real-time incubation data and generates corresponding decision instructions through the decision module. The execution unit receives the corresponding decision and controls the environmental adjustment module to perform corresponding environmental adjustment operations.

[0005] Preferably, the specific division process of the multiple groups of incubation sub-units includes: S1. Collect the total area of ​​the crayfish hatchery's internal hatching area using a surveying device; S2. Determine the total number of incubation sub-units based on the total area of ​​the internal incubation area and the pre-set area of ​​a single incubation sub-unit; S3. Each incubation subunit contains an equal number of crayfish fertilized eggs that are appropriate for its internal area; S3. Each of the incubation sub-units is equipped with the same identification module, which is used to monitor the real-time incubation data of crayfish within each incubation sub-unit.

[0006] Preferably, the identification module includes a high-definition image acquisition unit and an image processing unit. The high-definition image acquisition unit is used to periodically acquire visual images of crayfish eggs in each group of incubation sub-units. The image processing unit is used to analyze the visual images and determine the current incubation cycle by recognizing the color characteristics of the crayfish eggs.

[0007] Preferably, the image processing unit determines the hatching cycle by calculating the average color value of the crayfish egg pixels in the target area of ​​the image and comparing it with a predefined hatching cycle color threshold. The specific steps are as follows: Step 1: Convert the acquired RGB color space image to HSL color space; Step 2: For each pixel in the image, normalize its R, G, and B component values ​​to the range of 0 to 1, and then calculate the maximum value M, minimum value m, and chromaticity C of that pixel, where C = Mm; Step 3: Calculate the hue component H of the pixel based on the color channel corresponding to the maximum value M; Step 4: Extract the H component of all target crayfish egg pixel regions in the image, and calculate the average hue value H of the region. 均 and H 均 Transmitted to the decision module.

[0008] Preferably, the formula for calculating the hue component H is: If the maximum value M corresponds to the R component, then ; If the maximum value M corresponds to the G component, then ; If the maximum value M corresponds to the B component, then ; If the calculated H value is less than 0°, then add 360° to make the final H value fall within the range of 0° to 360°.

[0009] Preferably, the decision module is equipped with a threshold module, which divides the crayfish hatching cycle into three different hatching stages based on the crayfish hatching cycle data in the network database: early hatching stage, middle hatching stage, and late hatching stage.

[0010] Preferably, the threshold module uses an AI model and a network database to simulate when more than 85% (including 85%) of the crayfish fertilized eggs in an incubation subunit are in the early stage of incubation, and the image processing unit generates the first simulated H. 均The data is then organized to form the first threshold range; In a second simulated incubation subunit, when more than 85% (including 85%) of the crayfish fertilized eggs are in the mid-incubation stage, the image processing unit generates a second simulated H. 均 The data is then organized to form a second threshold range; When simulating a hatching subunit where more than 85% (including 85%) of crayfish fertilized eggs are in the late stage of hatching, the image processing unit generates a third simulated H. 均 The data was then organized to form a third threshold range. When the third threshold range <H 均 When the value is ≤ the first threshold range, it is determined that the fertilized crayfish eggs inside the incubation subunit are in the early stage of incubation; When the first threshold range <H 均 When the value is ≤ the second threshold range, the crayfish fertilized eggs inside the incubation subunit are determined to be in the middle stage of incubation. When the third threshold range ≤ H 均 When the value is less than the first threshold range, it is determined that the fertilized crayfish eggs inside the incubation subunit are in the late stage of incubation.

[0011] Preferably, the decision module generates a first decision when it determines that the crayfish fertilized eggs inside the incubation subunit are in the early stage of incubation; a second decision when it determines that the crayfish fertilized eggs inside the incubation subunit are in the middle stage of incubation; and a third decision when it determines that the crayfish fertilized eggs inside the incubation subunit are in the late stage of incubation. The execution unit receives the first decision, the second decision, and the third decision, and generates corresponding control instructions, wherein the corresponding control instructions include: the first control instruction, the second control instruction, and the third control instruction.

[0012] Preferably, the environmental control module includes one or more combinations of a heater, a cooler, a humidifier, and a dehumidifier. The execution unit controls the start-up, shutdown, and operating intensity of the heater, cooler, humidifier, or dehumidifier according to the corresponding control command transmitted by the execution unit, so as to adjust the temperature and humidity in the corresponding incubation subunit to the target parameters.

[0013] Preferably, each of the incubation sub-units is also equipped with an independent temperature and humidity sensor to monitor the actual temperature and humidity data inside in real time and feed the data back to the execution unit to form a closed-loop control for environmental regulation operations; The multiple incubation sub-units are physically isolated from each other to avoid mutual interference in temperature, humidity and microbial environment between different sub-units.

[0014] Technical effects and advantages of the present invention: This invention divides the hatching sub-units using a digital twin model and an improved Voronoi diagram algorithm, achieving precise partitioning with a theoretical area error of ≤2%, effectively eliminating blind spots in environmental regulation, and ensuring the synchronicity of fertilized egg development within each unit; This invention integrates hyperspectral imaging and image processing technologies, performs HSL color space conversion and hue component calculation, and combines AI models and network databases to establish a color threshold standard for the incubation cycle, thereby achieving high-precision automatic judgment during the incubation stage. This invention constructs a closed-loop control mechanism between the decision-making module and the execution unit, dynamically adjusting temperature and humidity according to the incubation stage, which not only meets the stability requirements of the cold-region incubation environment but also reduces energy consumption by 15%-20%. This invention avoids environmental interference through physically isolated sub-unit design. The execution unit regulates the heater, cooler, humidifier and dehumidifier according to the control instructions (first / second / third decision and abnormal instructions) generated by the decision module, and triggers the early warning device to send early warning information to the staff in abnormal state, forming an intelligent management and control system that combines full-process automation and manual intervention, which significantly improves the hatching success rate and breeding efficiency. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the operation steps of the fully automated incubation system of the present invention.

[0016] Figure 2 This is a flowchart of the fully automated incubation system of the present invention. Detailed Implementation

[0017] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The IoT intelligent control system for a cold-region crayfish hatchery involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Reference Figures 1 to 2 As shown, the present invention provides an Internet of Things intelligent control system for a cold-region crayfish hatchery, including a fully automatic hatching system, which comprises a hatching unit, an environmental control module, an identification module, a decision-making module, and an execution unit; The hatching unit divides the crayfish hatchery into multiple hatching sub-units of equal area, with each sub-unit containing an equal number of crayfish fertilized eggs; Each incubation sub-unit is equipped with an environmental control module for real-time dynamic adjustment of the temperature and humidity parameters within the corresponding sub-unit; The identification module is set up inside the incubation unit to monitor the real-time incubation data of crayfish eggs in each incubation sub-unit. The control unit receives the real-time incubation data and generates corresponding decision instructions through the decision module. The execution unit receives the corresponding decision and controls the environmental adjustment module to perform the corresponding environmental adjustment operations.

[0019] Reference Figure 1 As shown, this invention provides an IoT-based intelligent control system for crayfish hatcheries in cold regions. The specific division process of multiple hatching sub-units includes: S1. Collect the total area of ​​the crayfish hatchery's internal hatching area using a surveying device; S2. Determine the total number of incubation sub-units based on the total area of ​​the internal incubation area and the pre-set area of ​​a single incubation sub-unit; S3. Each incubation subunit contains an equal number of crayfish fertilized eggs that are appropriate for its internal area; S3. Each incubation sub-unit is equipped with the same identification module, which is used to monitor the real-time incubation data of crayfish within each incubation sub-unit.

[0020] In this embodiment, the mapping device mentioned in step S1 is a lidar mapping device or UAV oblique photography technology. The lidar mapping device or UAV oblique photography technology is used to collect three-dimensional spatial data of the hatching area within the hatchery. Combined with a cold climate database, a digital twin model including temperature gradient, humidity distribution, and terrain features is established. Based on the digital twin model, an improved Voronoi diagram algorithm is used to dynamically divide the hatching area, ensuring that the theoretical area error of each sub-unit is ≤2%. The specific process for the amount of crayfish introduced into each incubation sub-unit in step S2 is as follows: the total number of fertilized eggs in a single sub-unit is calculated based on the biological density standard of crayfish fertilized eggs (the preferred density standard is 5000 eggs / ㎡), and equal distribution with an accuracy of ±1% is achieved through a precision electronic scale and a visual counting system.

[0021] Reference Figure 1 As shown, the present invention provides an Internet of Things intelligent control system for a cold-region crayfish hatchery. The identification module includes a high-definition image acquisition unit and an image processing unit. The high-definition image acquisition unit is used to periodically acquire visual images of crayfish eggs in each group of hatching sub-units. The image processing unit is used to analyze the visual images and determine the current hatching cycle by identifying the color characteristics of the crayfish eggs.

[0022] In this embodiment, the device used by the high-definition image acquisition unit to acquire visual images is: an industrial camera and acquisition card, a hyperspectral imaging system, or other image acquisition equipment. It employs industrial cameras and data acquisition cards, and has the following characteristics: 1. High precision: Professional A / D conversion (e.g., 9-bit / 10-bit), high image signal-to-noise ratio, and good detail reproduction; 2. Abundant Interfaces: Supports multiple video input formats; 3. Professional development support: Provides SDK to support development environments such as VC / VB / Delphi.

[0023] The equipment used in industrial cameras and acquisition cards includes: DH-CG410 image acquisition card; V221 image acquisition card, etc.

[0024] The use of a hyperspectral imaging system has the following characteristics: Beyond visible light: Captures image data of objects across multiple narrow spectral bands; Composition analysis: It can not only examine the appearance, but also analyze the internal components and quality.

[0025] The hyperspectral imaging system uses a hyperspectral camera.

[0026] The image processing unit determines the hatching cycle by calculating the average color value of the crayfish egg pixels in the target area of ​​the image and comparing it with a predefined hatching cycle color threshold. The specific steps are as follows: Step 1: Convert the acquired RGB color space image to HSL color space; Step 2: For each pixel in the image, normalize its R, G, and B component values ​​to the range of 0 to 1, and then calculate the maximum value M, minimum value m, and chromaticity C of that pixel, where C = Mm; Step 3: Calculate the hue component H of the pixel based on the color channel corresponding to the maximum value M; Step 4: Extract the H component of all target crayfish egg pixel regions in the image, and calculate the average hue value H of the region. 均 and H 均 Transmitted to the decision module.

[0027] The formula for calculating the hue component H is: If the maximum value M corresponds to the R component, then ; If the maximum value M corresponds to the G component, then ; If the maximum value M corresponds to the B component, then ; If the calculated H value is less than 0°, then add 360° to make the final H value fall within the range of 0° to 360°.

[0028] In this embodiment of the application, R, G, and B are three basic components in the color model, where R: red; G: green; and B: blue.

[0029] In this embodiment of the application, brightness is typically represented by a numerical range in a digital system. Commonly, it ranges from 0 to 255 (represented by 8-bit binary numbers), but for convenience in scientific calculations, it is usually normalized to the range of 0 to 1. In this embodiment of the application, M=max(R,G,B);m=min(R,G,B).

[0030] The decision-making module includes a threshold module, which divides the crayfish hatching cycle into three different hatching stages based on crayfish hatching cycle data from the network database: early hatching stage, middle hatching stage, and late hatching stage. The threshold module, using an AI model and a network database, simulates the initial stage of incubation of crayfish fertilized eggs within an incubation subunit when over 85% (including 85%) are in the early incubation phase. This is when the image processing unit generates the first simulated H... 均 The data is then organized to form the first threshold range; In a second simulated incubation subunit, when more than 85% (including 85%) of the crayfish fertilized eggs are in the mid-incubation stage, the image processing unit generates a second simulated H. 均 The data is then organized to form a second threshold range; When simulating a hatching subunit where more than 85% (including 85%) of crayfish fertilized eggs are in the late stage of hatching, the image processing unit generates a third simulated H. 均 The data is then organized to form a third threshold range.

[0031] When the third threshold range <H 均 When the value is ≤ the first threshold range, it is determined that the fertilized crayfish eggs inside the incubation subunit are in the early stage of incubation; When the first threshold range <H 均 When the value is ≤ the second threshold range, the crayfish fertilized eggs inside the incubation subunit are determined to be in the middle stage of incubation. When the third threshold range ≤ H 均 When the value is less than the first threshold range, it is determined that the fertilized crayfish eggs inside the incubation subunit are in the late stage of incubation.

[0032] In this embodiment of the application, it is known through AI models and network databases that, in the early stage of incubation, the color of crayfish fertilized eggs is light milky white or light yellow; in the middle stage of incubation, the color of crayfish fertilized eggs is dark brown, and some may have black eye spots; in the late stage of incubation, the color of crayfish fertilized eggs is orange-red.

[0033] According to color theory, the H value for light milky white and light yellow is likely to be in the range of 30-60 degrees; the H value for dark brown is likely to be between 20-40 degrees; and the H value for orange-red is likely to be between 15-30 degrees. Based on this information, I can deduce that the average H value for the three incubation stages should be in the following order: mid-incubation > early incubation > late incubation.

[0034] When the decision module determines that the crayfish fertilized eggs inside the incubation subunit are in the early stage of incubation, it generates a first decision; when the decision module determines that the crayfish fertilized eggs inside the incubation subunit are in the middle stage of incubation, it generates a second decision; when the decision module determines that the crayfish fertilized eggs inside the incubation subunit are in the late stage of incubation, it generates a third decision. The execution unit receives the first decision, the second decision, and the third decision, and generates corresponding control instructions, which include: the first control instruction, the second control instruction, and the third control instruction.

[0035] In this embodiment, the execution unit will also generate abnormal instructions. When the crayfish hatching status in a corresponding set of hatching sub-units cannot generate the first, second, and third decisions through the decision module, the decision module sends an abnormal decision to the execution unit, and the execution unit generates an abnormal control instruction, which sends a warning message to the staff through the system's internal warning device.

[0036] The environmental control module includes one or more combinations of heater, cooler, humidifier and dehumidifier. The execution unit controls the start-up, shutdown and working intensity of the heater, cooler, humidifier or dehumidifier according to the corresponding control command transmitted by the execution unit, so as to adjust the temperature and humidity in the corresponding incubation sub-unit to the target parameters.

[0037] Each incubation subunit is also equipped with an independent temperature and humidity sensor to monitor the actual temperature and humidity data inside in real time and feed the data back to the execution unit to form a closed-loop control of the environmental regulation operation.

[0038] Multiple incubation sub-units are physically isolated from each other to avoid mutual interference in temperature, humidity, and microbial environment between different sub-units.

[0039] Reference Figure 1 As shown, the present invention provides an Internet of Things intelligent control system for a cold-region crayfish hatchery, and the environmental control module is also equipped with an ozone sterilization subunit; The ozone sterilization subunit includes: An ozone generator, located within each incubation sub-unit and electrically connected to the execution unit, is used to release ozone according to control commands; An ozone concentration sensor is installed in each incubation sub-unit to monitor the ozone concentration data inside in real time and feed it back to the execution unit; The control instructions generated by the decision module include sterilization decision instructions corresponding to different incubation stages. The execution unit controls the ozone generator to work at the set intensity and cycle according to the sterilization decision instructions, and combines the feedback data from the ozone concentration sensor to form a closed-loop sterilization control of the microbial environment in the incubation sub-unit.

[0040] In this embodiment of the application, in order to achieve safe and efficient intelligent sterilization, the decision module generates a corresponding sterilization decision instruction based on the incubation stage (early, middle, and late stages) determined by the identification module. This instruction includes a target ozone concentration threshold, action duration, and action cycle that match the biological needs and disease risks of that stage. Upon receiving the instruction, the execution unit drives the ozone generator to operate and adjusts it based on real-time data from the ozone concentration sensor: if the concentration is below the target threshold, the generator's output power is increased or the operating time is extended; if the threshold is reached or exceeded, the power is reduced or operation is paused to maintain the concentration within a safe and effective range. In this part of the application embodiments, by transforming ozone sterilization, a highly efficient means, into a fully automated and precisely adapted intelligent incubation program, the risk of microorganisms is effectively controlled while ensuring incubation safety and embryo health to the greatest extent, which is an important technical guarantee for achieving a high success rate of hatching.

[0041] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0042] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0043] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0044] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An IoT-based intelligent control system for a cold-region crayfish hatchery, characterized in that... It includes a fully automated incubation system, which comprises an incubation unit, an environmental control module, an identification module, a decision-making module, and an execution unit. The incubation unit divides the crayfish hatchery into multiple groups of equally sized incubation sub-units, with each group containing an equal number of crayfish fertilized eggs. Each of the incubation sub-units is equipped with an environmental control module, which is used to dynamically adjust the temperature and humidity parameters within the corresponding sub-unit in real time. The identification module is set inside the incubation unit to monitor the real-time incubation data of crayfish eggs in each incubation sub-unit. The control unit receives the real-time incubation data and generates corresponding decision instructions through the decision module. The execution unit receives the corresponding decision and controls the environmental adjustment module to perform corresponding environmental adjustment operations.

2. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 1, characterized in that... The specific division process of the multiple incubation sub-units includes: S1. Collect the total area of ​​the crayfish hatchery's internal hatching area using a surveying device; S2. Determine the total number of incubation sub-units based on the total area of ​​the internal incubation area and the pre-set area of ​​a single incubation sub-unit; S3. Each incubation subunit contains an equal number of crayfish fertilized eggs that are appropriate for its internal area; S3. Each of the incubation sub-units is equipped with the same identification module, which is used to monitor the real-time incubation data of crayfish within each incubation sub-unit.

3. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 1, characterized in that... The identification module includes a high-definition image acquisition unit and an image processing unit. The high-definition image acquisition unit is used to periodically acquire visual images of crayfish eggs in each group of incubation sub-units. The image processing unit is used to analyze the visual images and determine the current incubation cycle by recognizing the color characteristics of the crayfish eggs.

4. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 3, characterized in that... The image processing unit determines the hatching cycle by calculating the average color value of the crayfish egg pixels in the target area of ​​the image and comparing it with a predefined hatching cycle color threshold. The specific steps are as follows: Step 1: Convert the acquired RGB color space image to HSL color space; Step 2: For each pixel in the image, normalize its R, G, and B component values ​​to the range of 0 to 1, and then calculate the maximum value M, minimum value m, and chromaticity C of that pixel, where C = Mm; Step 3: Calculate the hue component H of the pixel based on the color channel corresponding to the maximum value M; Step 4: Extract the H component of all target crayfish egg pixel regions in the image, and calculate the average hue value H of the region. 均 and H 均 Transmitted to the decision module.

5. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 4, characterized in that... The formula for calculating the hue component H is: If the maximum value M corresponds to the R component, then ; If the maximum value M corresponds to the G component, then ; If the maximum value M corresponds to the B component, then ; If the calculated H value is less than 0°, then add 360° to make the final H value fall within the range of 0° to 360°.

6. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 5, characterized in that... The decision module is equipped with a threshold module, which divides the crayfish hatching cycle into three different hatching stages based on crayfish hatching cycle data in the network database: early hatching stage, middle hatching stage, and late hatching stage.

7. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 6, characterized in that... The threshold module, through an AI model and a network database, simulates the initial incubation stage of crayfish fertilized eggs within an incubation subunit when 85% or more (including 85%) are in the image processing unit. The first simulated H value generated by the image processing unit is then analyzed. 均 The data is then organized to form the first threshold range; In a second simulated incubation subunit, when more than 85% (including 85%) of the crayfish fertilized eggs are in the mid-incubation stage, the image processing unit generates a second simulated H. 均 The data is then organized to form a second threshold range; When simulating a hatching subunit where more than 85% (including 85%) of crayfish fertilized eggs are in the late stage of hatching, the image processing unit generates a third simulated H. 均 The data was then organized to form a third threshold range. When the third threshold range <H 均 When the value is ≤ the first threshold range, it is determined that the crayfish fertilized eggs inside the incubation subunit are in the early stage of incubation; When the first threshold range <H 均 When the value is ≤ the second threshold range, the crayfish fertilized eggs inside the incubation subunit are determined to be in the middle stage of incubation. When the third threshold range ≤ H 均 When the value is less than the first threshold range, it is determined that the fertilized crayfish eggs inside the incubation subunit are in the late stage of incubation.

8. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 7, characterized in that... The decision module generates a first decision when it determines that the fertilized crayfish eggs inside the incubation subunit are in the early stage of incubation; a second decision when it determines that the fertilized crayfish eggs inside the incubation subunit are in the middle stage of incubation; and a third decision when it determines that the fertilized crayfish eggs inside the incubation subunit are in the late stage of incubation. The execution unit receives the first decision, the second decision, and the third decision, and generates corresponding control instructions, wherein the corresponding control instructions include: the first control instruction, the second control instruction, and the third control instruction.

9. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 8, characterized in that... The environmental control module includes one or more combinations of a heater, a cooler, a humidifier, and a dehumidifier. The execution unit controls the start-up, shutdown, and operating intensity of the heater, cooler, humidifier, or dehumidifier according to the corresponding control command transmitted by the execution unit, so as to adjust the temperature and humidity in the corresponding incubation subunit to the target parameters.

10. The IoT intelligent control system for a cold-region crayfish hatchery according to claim 1, characterized in that... Each of the incubation sub-units is also equipped with an independent temperature and humidity sensor to monitor the actual temperature and humidity data inside in real time and feed the data back to the execution unit to form a closed-loop control for environmental regulation operations; The multiple sets of incubation sub-units are physically isolated from each other to avoid mutual interference in temperature, humidity, and microbial environment between different sub-units; The environmental control module is also equipped with an ozone sterilization subunit; The ozone sterilization subunit includes: An ozone generator, located within each incubation sub-unit and electrically connected to the execution unit, is used to release ozone according to control commands; An ozone concentration sensor is installed in each incubation sub-unit to monitor the ozone concentration data inside in real time and feed it back to the execution unit; The control instructions generated by the decision module include sterilization decision instructions corresponding to different incubation stages. The execution unit controls the ozone generator to work at a set intensity and cycle according to the sterilization decision instructions, and combines the feedback data from the ozone concentration sensor to form a closed-loop sterilization control of the microbial environment within the incubation subunit.

Images