Test point environment self-adaptive regulation and precise incubation management system

Abstract

The invention discloses a test point environment adaptive regulation and precise incubation management system, which comprises a distributed edge computing architecture, and is characterized in that the distributed edge computing architecture comprises a cloud server, edge computing nodes and terminal equipment; the multi-mode sensing network comprises a temperature sensor, a humidity sensor, a gas sensor and an image acquisition device; the digital twinborn regulation and control module is used for establishing a virtual model of a hatching environment and adjusting control parameters in real time; and the optical mark tracking system is used for carrying out unique identification and dynamic tracking on the hatching eggs. Through cooperative use of the distributed edge computing architecture and the multi-mode sensing network, the effects of local real-time decision making and precise environment regulation and control are achieved, and the problem of response delay caused by cloud centralized control in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of poultry incubation environment control, specifically to an experimental site environment adaptive regulation and precision incubation management system. Background Technology

[0002] Modern poultry hatching production is developing towards intelligence and precision. Traditional hatching management mainly relies on manual experience to adjust environmental parameters such as temperature and humidity, which suffers from problems such as lagging control and poor uniformity. With the development of technologies such as the Internet of Things and artificial intelligence, intelligent hatching systems are gradually being applied in production practice. These systems collect environmental data through sensor networks and automatically adjust the operating parameters of hatching equipment in combination with control algorithms.

[0003] Furthermore, the quality of hatching eggs is influenced by multiple factors, including temperature, humidity, oxygen concentration, carbon dioxide concentration, and egg-turning frequency, with complex coupling relationships among these parameters. Existing research confirms that even small fluctuations in environmental parameters during incubation can significantly affect embryonic development. Therefore, developing intelligent incubation systems capable of precise environmental control and adaptive optimization has significant application value.

[0004] Several intelligent production management systems for poultry incubation are currently available on the market, such as the one disclosed in patent CN107491050A. This system employs a central control architecture, collecting environmental data through sensors deployed within the incubator, which is then processed by a cloud server before control commands are issued. However, when network communication experiences delays or interruptions, the central control architecture leads to system lag, making it difficult to adjust incubation environment parameters in a timely manner. This is particularly problematic in large-scale hatcheries where multiple incubation devices operate simultaneously, placing significant computational and communication pressure on the cloud server and potentially causing delays in control command transmission, thus affecting the stability of the incubation environment. Summary of the Invention

[0005] The purpose of this invention is to provide an adaptive control and precise incubation management system for experimental sites, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The pilot site environmental adaptive control and precision incubation management system includes

[0008] A distributed edge computing architecture, comprising cloud servers, edge computing nodes, and terminal devices;

[0009] A multimodal sensing network, comprising a temperature sensor, a humidity sensor, a gas sensor, and an image acquisition device;

[0010] A digital twin control module, which is used to establish a virtual model of the incubation environment and adjust control parameters in real time;

[0011] An optical tagging and tracking system, wherein the optical tagging and tracking system is used to uniquely identify and dynamically track hatching eggs;

[0012] An intelligent decision-making platform is used to generate optimized control strategies based on perceived data.

[0013] In this invention, the edge computing node uses an ARM architecture processor, is deployed inside the incubation device, and is connected to the cloud server via wireless communication.

[0014] In this invention, the temperature sensor has a measurement accuracy of ±0.1℃, and the humidity sensor has a measurement accuracy of ±1%RH.

[0015] In this invention, the gas sensor includes an oxygen sensor, a carbon dioxide sensor, and an ammonia sensor.

[0016] In this invention, the image acquisition device includes an infrared thermal imager and a visible light camera.

[0017] In this invention, the digital twin control module includes

[0018] An environmental parameter acquisition unit is used to acquire real-time data of the incubation environment.

[0019] A virtual model building unit, which is used to establish a digital twin model of the incubation process;

[0020] A control instruction generation unit is used to generate control instructions based on model differences.

[0021] In this invention, the optical marker tracking system includes

[0022] A quantum dot labeling device for forming fluorescent markings on the surface of hatching eggs;

[0023] An optical identification device, wherein the optical identification device is used to read the fluorescent tag;

[0024] A data storage device for recording hatching data of fertilized eggs.

[0025] In this invention, the intelligent decision-making platform uses the ant colony algorithm to optimize the control strategy.

[0026] A precise incubation management method using the system includes the following steps:

[0027] Step S1: Optical marking is applied to the hatching eggs;

[0028] Step S2: Collect incubation environment parameters and hatching egg status data;

[0029] Step S3: Establish a digital twin model and calculate control parameters;

[0030] Step S4: Perform environmental control operations;

[0031] Step S5: Record and analyze the incubation process data.

[0032] In this invention, step S3 includes comparing real-time collected data with a digital twin model, and generating a new control strategy when the difference exceeds a set threshold.

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] 1. This invention achieves local real-time decision-making and precise environmental control through the combined use of a distributed edge computing architecture and a multimodal sensing network, solving the response delay problem caused by centralized cloud control in the prior art;

[0035] 2. This invention achieves precise simulation and dynamic optimization of the incubation process through the combined use of a digital twin control module and an intelligent decision-making platform, solving the problem of inaccurate parameter adjustment in traditional incubation systems. Attached Figure Description

[0036] Figure 1 This is a system architecture diagram of the present invention;

[0037] Figure 2 This is a flowchart of the dynamic parameter optimization process of the present invention;

[0038] Figure 3 This is a timing diagram comparing the temperature control of the present invention;

[0039] Figure 4 A Gantt chart comparing the hatching effects of this invention. Detailed Implementation

[0040] 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.

[0041] Example 1

[0042] This invention addresses the problems of lagging environmental parameter control and inaccurate monitoring of hatching egg status in traditional incubation systems. It achieves adaptive and precise control of the incubation environment through distributed edge computing and digital twin collaborative control. Due to the involvement of multi-physics coupling analysis and real-time decision-making, the following technical objectives need to be achieved based on the hardware architecture:

[0043] Achieve millisecond-level response latency for environmental parameters;

[0044] Maintain temperature fluctuation range ≤ ±0.3℃;

[0045] Establish a digital mapping of the individual developmental trajectory of hatching eggs.

[0046] Based on the above technical requirements, this embodiment adopts the following... Figure 1 The "edge-cloud collaborative control" architecture shown:

[0047] The sensing and acquisition layer consists of a hexahedral monitoring network of 24 DS18B20 temperature sensors, spaced 30cm apart. These sensors are connected in series via a 1-Wire bus to the GPIO2 pin of the edge node. The gas detection unit uses an SCD40-CO2 sensor and an SGP30-TVOC sensor to form a cross-validation array, transmitting data via an I2C bus (SCL = GPIO3, SDA = GPIO4).

[0048] The edge computing layer uses a Rockchip RK3588 (quad-core Cortex-A76@2.4GHz) as the core processor, and the real-time control algorithm is deployed on the Xenomai3 real-time kernel. The thread priority is set to level 99, and communication with the cloud uses the MQTT overTLS1.3 protocol with a heartbeat interval of 60 seconds.

[0049] Digital twin layer, 3D modeling using COMSOL The software uses the Delaunay triangulation algorithm for mesh generation, and the thermal field calculation is based on the Fourier heat conduction equation, using the following formula:

[0050]

[0051] Where ρ represents air density, c p Q represents specific heat capacity, k represents thermal conductivity. egg This represents the heat generated by the metabolism of hatching eggs.

[0052] like Figure 2 As shown, the specific process of the dynamic parameter optimization method executed on this architecture includes:

[0053] Step S1: Environmental parameter acquisition and preprocessing. Median filtering is applied to the temperature sensor data, with a window width of 5. Gas concentration data compensation is calculated using the following formula:

[0054] C actual =C raw ×(1+0.003×(T sensor -25))

[0055] Among them, T sensor This is expressed as the sensor's own temperature.

[0056] Step S2: The digital twin model is updated, and a CFD simulation is performed every 60 seconds. The turbulence model uses the k_w STT equations:

[0057]

[0058] Step S3: Control command generation, using fuzzy PID control algorithm, with proportional coefficient K. p Dynamically adjusts according to error e:

[0059]

[0060] Among them, K p It is represented as the proportional control coefficient, and e represents the deviation between the temperature measurement value and the set value. The temperature threshold in the condition judgment is determined based on the egg embryo development sensitivity test.

[0061] Step S4: The actuator is driven, and the heater power adjustment adopts PWM control. The duty cycle calculation formula is:

[0062]

[0063] Wherein, the integration time T i =120s, differential time T d =30s.

[0064] In this embodiment, the edge computing node can independently complete the collection, analysis and control command generation of environmental parameters, and can still ensure the stability of the incubation environment when network communication is delayed or interrupted, which significantly improves the system response speed and reliability.

[0065] Furthermore, the system can dynamically update the digital twin model based on real-time data acquisition, and automatically optimize the control strategy through ant colony algorithm to achieve coordinated and precise control of multiple parameters such as temperature, humidity, and gas concentration, keeping the fluctuation of the incubation environment within ±0.1℃.

[0066] Example 2

[0067] like Figure 3-4 As shown, this embodiment verifies the technical effect through comparative experiments, and the specific implementation is as follows:

[0068] Experimental and control group setup:

[0069] Experimental group: 2000 AA+ broiler hatching eggs (numbered E1-E2000) using the technology of this invention.

[0070] Average weight of hatching eggs: 62.5 ± 0.3 g.

[0071] Eggshell thickness: 0.34±0.02mm (measured using an ultrasonic thickness gauge).

[0072] Control group: 2000 hatching eggs (numbered C1-C2000) from the same batch controlled by traditional PID.

[0073] Symmetrical compartments located in the same incubator.

[0074] Except for the control system, all other conditions are exactly the same.

[0075] The monitoring system configuration is shown in the table below:

[0076]

[0077] 24 hours before incubation, the eggs were pretreated by equilibrating them in a 38°C, 75% RH preheating chamber for 12 hours, and then sprayed with a 0.02% peracetic acid solution for disinfection (contact time 15 minutes). Cracked eggs were removed by light transmission detection (rejection rate 3.2%).

[0078] The equipment was debugged and the incubator compartments were calibrated (BINDER KBF720 constant temperature chamber). The experimental group was loaded with this control system, while the control group used the EurotrolEY530-PID controller.

[0079] The incubation phase operation procedure is as follows (standardized operation from day 1 to day 18):

[0080] Daily fixed operation sequence:

[0081] time Operation content Technical parameter requirements 06:00 Candling inspection (using an LED cold light source) Light intensity ≤2000 lux, duration ≤30 seconds 08:00 Automatic egg flipping (experimental group with dynamic angle adjustment) Control group: fixed tilt at 45°, once per hour 12:00 Egg weight measurement (30 eggs randomly sampled) Electronic balance stabilization time ≥ 30 seconds 15:00 <![CDATA[CO2 concentration calibration]]> Using NIST standard gas (GBW08152) 18:00 Data backup and outlier checking Storage to RAID6 array

[0082] Temperature step test (day 3):

[0083] The temperature was manually set to drop from 37.8℃ to 36.5℃.

[0084] The time required for the experimental group to recover to 37.5℃ was recorded as 4 minutes and 28 seconds.

[0085] Recovery time for the control group: 8 minutes and 15 seconds.

[0086] Peak metabolic thermogenesis (days 12-15):

[0087] The experimental group activated adaptive damper control: the air intake volume increased from 12m³ / h. 3 / h increased to 18m 3 / h, wind speed distribution uniformity ≥90% (passed by smoke tracing test).

[0088] The control group showed localized overheating (two hot spots ≥38.2℃ were detected).

[0089] Peak metabolic thermogenesis (days 12-15):

[0090] The experimental group activated adaptive damper control: the air intake volume increased from 12m³ / h. 3 / h increased to 18m 3 / h, wind speed distribution uniformity ≥90% (passed by smoke tracing test).

[0091] The control group showed localized overheating (two hot spots ≥38.2℃ were detected).

[0092] The following comparative data was obtained on day 18 of incubation:

[0093] The standard deviation of temperature in the experimental group was 0.28℃ (n = 10080 data points).

[0094] The standard deviation of temperature in the control group was 0.67℃.

[0095] Improvement effect: Temperature fluctuation reduced by 58.2%.

[0096] CO2 gradient in the experimental group: 0.12% → 0.09% (from the air inlet to the air outlet).

[0097] CO2 gradient in the control group: 0.15% → 0.13%.

[0098] Uniformity improved by 25%.

[0099] The biological indicators are shown in the table below:

[0100] parameter experimental group control group Increase Hatching rate 92.7％ 85.9％ +6.8％ Average weight of chicks 42.3g 40.1g +5.5％ Weak chick rate 1.2％ 3.8％ -68.4％

[0101] Monitoring during the hatching stage (days 19-21):

[0102] The concentrated hatching time window for chicks in the experimental group was 8.5 hours (06:00-14:30 on day 20).

[0103] Hatching time window for the control group: 14.2 hours (02:00-16:12 on day 20).

[0104] The quality assessment is shown in the table below:

[0105] Evaluation indicators experimental group control group Umbilical cord closure completeness rate 98.3％ 91.7％ Feather drying time 2.1 ± 0.3 hours 3.5 ± 0.6 hours Standing reaction time 8.7 ± 1.2 minutes 14.3 ± 2.1 minutes

[0106] Based on the comparative experimental data from Example 2, the poultry egg incubation control system of the present invention exhibits the following significant advantages compared to the traditional PID control system:

[0107] The experimental group had a temperature standard deviation of 0.28℃, which was significantly lower than the control group's 0.67℃, and the stability was improved by 58.2%. The CO2 concentration gradient (from the air inlet to the air outlet) in the experimental group was 0.12%→0.09%, which was 25% more uniform than the control group's 0.15%→0.13%. In the temperature step test, the experimental group took 4 minutes and 28 seconds to recover to 37.5℃, which was 3 minutes and 47 seconds faster than the control group.

[0108] The incubation performance indicators are shown in the table below:

[0109]

[0110]

[0111] Hatching quality:

[0112] The hatching time window for the experimental group was 8.5 hours, which was 5.7 hours shorter than that for the control group.

[0113] Umbilical cord closure completeness rate: 98.3% in the experimental group vs. 91.7% in the control group.

[0114] Feather drying time: 2.1 hours for the experimental group vs. 3.5 hours for the control group.

[0115] Standing reaction time: 8.7 minutes in the experimental group vs. 14.3 minutes in the control group.

[0116] 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.

[0117] 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. An experimental site environment adaptive control and precise incubation management system, characterized by: include A distributed edge computing architecture, comprising cloud servers, edge computing nodes, and terminal devices; A multimodal sensing network, comprising a temperature sensor, a humidity sensor, a gas sensor, and an image acquisition device; A digital twin control module, which is used to establish a virtual model of the incubation environment and adjust control parameters in real time; An optical tagging and tracking system, wherein the optical tagging and tracking system is used to uniquely identify and dynamically track hatching eggs; An intelligent decision-making platform is used to generate optimized control strategies based on perceived data.

2. The experimental site environment adaptive control and precise incubation management system according to claim 1, characterized in that: The edge computing node uses an ARM architecture processor, is deployed inside the incubation device, and is connected to the cloud server via wireless communication.

3. The experimental site environment adaptive control and precise incubation management system according to claim 1, characterized in that: The temperature sensor has a measurement accuracy of ±0.1℃, and the humidity sensor has a measurement accuracy of ±1%RH.

4. The experimental site environment adaptive control and precise incubation management system according to claim 1, characterized in that: The gas sensors include an oxygen sensor, a carbon dioxide sensor, and an ammonia sensor.

5. The experimental site environment adaptive control and precise incubation management system according to claim 1, characterized in that: The image acquisition device includes an infrared thermal imager and a visible light camera.

6. The experimental site environment adaptive control and precise incubation management system according to claim 1, characterized in that: The digital twin control module includes An environmental parameter acquisition unit is used to acquire real-time data of the incubation environment. A virtual model building unit, which is used to establish a digital twin model of the incubation process; A control instruction generation unit is used to generate control instructions based on model differences.

7. The experimental site environment adaptive control and precise incubation management system according to claim 1, characterized in that: The optical tag tracking system includes A quantum dot labeling device for forming fluorescent markings on the surface of hatching eggs; An optical identification device, wherein the optical identification device is used to read the fluorescent tag; A data storage device for recording hatching data of fertilized eggs.

8. The experimental site environment adaptive control and precise incubation management system according to claim 1, characterized in that: The intelligent decision-making platform uses the ant colony algorithm to optimize the control strategy.

9. A precise incubation management method using the system described in any one of claims 1-8, characterized in that: Includes the following steps: Step S1: Optical marking is applied to the hatching eggs; Step S2: Collect incubation environment parameters and hatching egg status data; Step S3: Establish a digital twin model and calculate control parameters; Step S4: Perform environmental control operations; Step S5: Record and analyze the incubation process data.

10. The method according to claim 9, characterized in that: Step S3 includes comparing the real-time collected data with the digital twin model, and generating a new control strategy when the difference exceeds a set threshold.

Images