Automatic control method and system for production of egg fermented feed capable of reducing blood sugar

Abstract

The invention relates to the technical field of automatic control, and discloses an automatic control method and system for production of a blood-sugar-reducing egg fermented feed. The method comprises the following steps: intelligently identifying raw materials, accurately proportioning, acquiring digital fingerprints by using multiple groups of sensors, and performing double-speed blanking to realize proportioning; feeding the materials into a parameterized mixing system, and performing multi-stage variable-speed stirring to generate a parameter report; self-adaptive fermentation, multi-point sensing monitoring and self-adaptive PID adjustment are carried out according to report conditions to obtain a fermentation material; and performing post-processing to obtain a feed product and a digital file. The technical problems of accurate identification and intelligent proportioning of raw materials in the production process of the blood-sugar-reducing egg fermented feed, uniformity control and accurate regulation and control of fermentation conditions in the mixing process of the functional feed and full-flow digital management and quality tracing of the blood-sugar-reducing functional feed are solved.

Description

Technical Field

[0001] The present application relates to the field of automated control technology, and in particular to an automated control method and system for producing hypoglycemic egg fermented feed. Background Art

[0002] With the development of animal husbandry, the demand for functional feeds, especially hypoglycemic feeds, continues to increase. Traditional feed production relies primarily on manual experience to control process parameters and lacks precise automated control systems, resulting in large fluctuations in product quality and unstable functional ingredient content. Existing feed production lines typically use a single control mode, making it difficult to fine-tune the process based on the characteristics of different raw materials and functional requirements. This makes it particularly difficult to ensure the stable production of hypoglycemic substances during the production of hypoglycemic egg fermented feeds.

[0003] Existing technologies suffer from numerous shortcomings. First, raw material identification and proportioning in traditional feed production rely primarily on manual judgment and lack a precise identification system, resulting in low ingredient accuracy and an inability to meet the precise formulation requirements of functional feeds. Second, conventional mixing equipment struggles to optimize and adjust for different material characteristics, leading to uneven mixing and uneven distribution of functional trace ingredients. Furthermore, the fermentation process is crudely controlled, with no ability to dynamically adjust process parameters based on changes in various fermentation indicators, leading to unstable production of hypoglycemic active substances. Furthermore, the post-processing process lacks precise granulation control and full-process quality traceability, making it impossible to guarantee the functional stability and traceability of the final product.

[0004] To address these challenges, there is an urgent need to develop a highly intelligent and precise automated control method for the production of hypoglycemic egg fermented feed. This method requires precise identification and proportioning of raw materials, which in turn raises the challenge of achieving multi-stage mixing control to ensure uniform distribution of functional ingredients. Once this uniformity is achieved, the challenge remains: precisely controlling fermentation conditions based on material characteristics to promote the production of hypoglycemic active substances. Finally, during post-processing, maintaining functional activity through precise drying and granulation processes and establishing a comprehensive quality traceability system remain key challenges. Summary of the Invention

[0005] The present application provides an automated control method and system for the production of hypoglycemic egg fermented feed, which is used to solve the technical problems of accurate identification and intelligent proportioning of raw materials in the production process of hypoglycemic egg fermented feed, uniformity control of functional feed mixing process and precise regulation of fermentation conditions, as well as digital management and quality traceability of the entire process of hypoglycemic functional feed.

[0006] In the first aspect, the present application provides an automated control method for the production of hypoglycemic egg fermented feed, which includes: intelligent identification and precise ingredient control of raw materials, obtaining digital fingerprints of raw materials through multiple groups of identification sensors, implementing a dual-speed feeding strategy, and realizing material ratio; inputting materials into a parameterized mixing system, uniformly stirring the materials through a multi-stage variable speed mixing strategy, and generating a mixed material parameter report; conditionally adaptively fermenting the mixed materials based on the mixed material parameter report, monitoring fermentation indicators in real time through a multi-point sensing network, and executing adaptive PID control adjustment to obtain fermented materials; post-processing the fermented materials, including multi-stage temperature drying, intelligent granulation and molding, and quality traceability management, to generate feed products and digital archives.

[0007] Optionally, the intelligent identification and precise batching control of raw materials, obtaining the digital fingerprint of raw materials through multiple sets of identification sensors, executing a dual-speed unloading strategy, and achieving material proportioning include:

[0008] The raw materials entering the system are scanned by optical recognition sensors, near-infrared spectroscopy sensors and weight sensors to collect raw material feature data, which are then compared and analyzed with the raw material digital fingerprint library to obtain raw material type identification results and quality grade determination;

[0009] Based on the raw material type identification result and the preset hypoglycemic egg fermented feed formula information, various raw materials are accurately measured and calculated to generate ingredient execution parameters, which include the amount of each raw material, the order of addition, and the rate of addition;

[0010] The batching execution parameters are input into the feeding control device, and the raw materials are initially fed quickly to a first preset threshold value, and then automatically switched to a slow feeding mode. The dynamic drop compensation value is calculated in real time based on the material falling characteristic parameters, and the optimal cutting point position is determined to obtain the raw materials accurately fed;

[0011] The precisely delivered raw materials are monitored in real time, and the actual delivery amount, delivery time and delivery rate of each raw material are recorded. When it is detected that the deviation of the ingredients exceeds the second preset threshold, compensation adjustment is performed through the micro-adjustment device.

[0012] Optionally, the material is input into a parameterized mixing system, and the material is uniformly stirred through a multi-stage variable speed mixing strategy to generate a mixed material parameter report, including:

[0013] Execute equipment self-check procedures on input materials, detect the status of key components of the mixing device through a distributed sensor network, build a digital twin model of the device, and generate equipment readiness instructions based on the device operating status data;

[0014] Based on the equipment ready instruction, the material is controlled to enter the mixing system, and the material capacity data is collected in real time through the sensor network of the self-organizing topology structure. When the material capacity reaches the preset capacity threshold, the feed valve is closed to complete the material loading;

[0015] The material is input into a multi-stage variable speed mixing control module, and multi-stage mixing control is performed according to a preset mixing strategy. The multi-stage mixing control includes a low-speed premixing stage, a medium-speed mixing stage, a high-speed mixing stage, and a stable mixing stage. The mixing time and speed of each stage are adjusted in real time through a dynamic parameter adjustment network;

[0016] The material status during the mixing process is continuously monitored, and load change data is collected through a torque sensor. The data is input into the mixing uniformity evaluation deep neural network for real-time analysis. The mixing uniformity index is calculated in combination with the material property model. When the mixing uniformity index reaches the threshold condition, a mixing completion signal and a mixed material parameter report are generated.

[0017] Optionally, the step of inputting the material into a multi-stage variable speed mixing control module and performing multi-stage mixing control according to a preset mixing strategy includes:

[0018] Inputting material property data and hypoglycemic functional requirement data into a hybrid strategy generator, analyzing and processing the data through a material property neural network to generate a multi-stage hybrid control strategy, wherein the multi-stage hybrid control strategy includes speed parameters, duration parameters, and transition strategy parameters for each stage;

[0019] Based on the multi-stage mixing control strategy, a low-speed premixing operation is performed on the material, and the speed of the mixing device is adjusted to the premixing speed range through the servo control system for a preset time period to perform preliminary dispersion processing on the material;

[0020] Perform medium-speed and high-speed mixing operations on the premixed materials, monitor the mixing resistance changes in real time through the mixing load feedback system, and dynamically adjust the mixing speed and angular acceleration parameters according to the resistance change curve;

[0021] The high-speed mixed material is input into the stabilization processing unit, and the material flow characteristics are continuously monitored by the material circulation analysis system. When it is detected that the mixed flow state reaches the stable condition, the mixing speed is reduced to the stable range to obtain uniformly mixed materials.

[0022] Optionally, the method of performing conditional adaptive fermentation on the mixed material based on the mixed material parameter report, monitoring fermentation indicators in real time through a multi-point sensor network, and performing adaptive PID control adjustment to obtain the fermented material includes:

[0023] Inputting the mixed material parameter report into the fermentation process parameter library, analyzing the material characteristics through the parameter matching algorithm, and generating the fermentation process parameter set for this batch, wherein the fermentation process parameter set includes a temperature control curve, a pH range, and a dissolved oxygen control strategy;

[0024] The fermentation system is sterilized and the materials are introduced into the fermentation tank. Real-time data of the fermentation process, including temperature distribution data, pH value change data, dissolved oxygen concentration data, and gas composition data, are collected through a multi-point sensor network to establish a real-time model of the fermentation status.

[0025] The fermentation activity index and metabolite production rate are calculated based on the real-time fermentation state model, and the temperature, pH value and ventilation volume are dynamically adjusted by an adaptive PID controller to maintain the fermentation index within the target range and promote the production of hypoglycemic active substances;

[0026] The quality of materials in the late stage of fermentation is evaluated online, the content of hypoglycemic active substances is detected by a spectrometer, the fermentation endpoint is determined based on the pH stability and dissolved oxygen recovery rate, and a fermentation completion instruction and fermentation process data report are generated.

[0027] Optionally, the fermentation material is subjected to post-processing, including multi-stage temperature drying, intelligent granulation and quality traceability management, to generate feed products and digital archives, including:

[0028] The fermentation material is dried in multiple stages, and the drying temperature and air flow parameters are controlled in stages, and the moisture change curve of the material is monitored to obtain the dried material;

[0029] The dried material is fed into a pelletizing system, a quantitative steam is added through a conditioning device, and extrusion molding and pelletizing operations are performed to obtain feed pellets;

[0030] Cooling the feed pellets, controlling the temperature gradient through a laminar cooling bed, and monitoring the surface temperature distribution of the pellets to obtain finished feed;

[0031] The finished feed is subjected to quality inspection and traceability marking, and a product QR code and a full-process digital file are generated.

[0032] Optionally, the step of inputting the dry material into a pelletizing system, adding a fixed amount of steam through a conditioning device, performing extrusion molding and pelletizing operations to obtain feed pellets comprises:

[0033] Analyze the physical properties of the dried material, measure the particle size distribution, bulk density and fluidity parameters through the material property detection device, and generate granulation process parameters based on the test results;

[0034] The dried material is fed into a conditioning device, a quantitative steam is added to the material through a precision steam injection system, and a mixer is controlled to perform uniform stirring to obtain a conditioned material;

[0035] Performing an extrusion molding operation on the quenched and tempered material, maintaining a constant extrusion pressure through a servo-driven pressure control system, and adjusting the material passing rate in combination with real-time temperature monitoring to obtain an extruded material strip;

[0036] The extruded material strips are fed into the pelletizing system, and the variable frequency speed regulating cutter performs precise cutting according to the target particle length parameters while monitoring the particle uniformity to obtain feed pellets.

[0037] In a second aspect, the present application provides an automated control system for the production of hypoglycemic egg fermented feed, the automated control system for the production of hypoglycemic egg fermented feed comprising:

[0038] The control module is used for intelligent identification and precise batching control of raw materials. It obtains the digital fingerprint of raw materials through multiple sets of identification sensors, implements a dual-speed feeding strategy, and realizes material proportioning.

[0039] A processing module is used to input materials into the parameterized mixing system, uniformly mix the materials through a multi-stage variable speed mixing strategy, and generate a mixed material parameter report;

[0040] A monitoring module is used to perform conditional adaptive fermentation on the mixed material based on the mixed material parameter report, monitor the fermentation index in real time through a multi-point sensor network, and perform adaptive PID control adjustment to obtain fermentation material;

[0041] The traceability module is used to post-process the fermentation materials, including multi-stage temperature drying, intelligent granulation and molding, and quality traceability management, to generate feed products and digital archives.

[0042] In a third aspect, an automated control device for the production of hypoglycemic egg fermented feed is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory to enable the automated control device for the production of hypoglycemic egg fermented feed to execute the above-mentioned automated control method for the production of hypoglycemic egg fermented feed.

[0043] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the above-mentioned automated control method for the production of hypoglycemic egg fermented feed.

[0044] The technical solution provided in this application utilizes a multi-point temperature sensor array deployed inside and on the surface of building materials. This array collects temperature gradient data and combines it with mass change rate data to generate a freeze-drying process characteristic dataset. This approach enables comprehensive and accurate acquisition of key state information about building materials during the freeze-drying process. The temperature gradient data reflects the uneven temperature distribution within the building materials, while the mass change rate data is directly related to important processes such as water sublimation. The combined characteristic dataset provides a solid data foundation for subsequent precise control. Based on this characteristic dataset, a chaotic butterfly effect algorithm is applied to identify nonlinear transition points during the freezing process of building materials and generate ice crystal growth trend predictions. This algorithm is capable of capturing the complex nonlinear changes during the freeze-drying process, and its computational approach and data processing capabilities enable more accurate and timely identification of nonlinear transition points. This specific feature fully accounts for the inherent complexity and uncertainty of the freeze-drying process, leveraging algorithmic features to precisely locate key nodes in the freeze-drying process and subsequently predict ice crystal growth trends. This is crucial for the freeze-drying quality of building materials, as ice crystal growth directly impacts the material's microstructure and ultimate performance. By accurately predicting the growth trend of ice crystals, corresponding control measures can be taken in advance to avoid material defects caused by abnormal ice crystal growth.

[0045] The thermal conductivity distribution of building materials is evaluated based on the results of ice crystal growth trend prediction, and the materials are divided into a core area, an intermediate area, and a surface area, which reflects the scheme's in-depth understanding and precise control of material properties. The difference in thermal conductivity between different areas will lead to differences in temperature changes during the freeze-drying process. By reasonably dividing the areas, it can provide a basis for subsequent differentiated control. Cooling curves with different slopes are designed for different areas, and a multi-area collaborative cooling control parameter set is generated. The control instructions are calculated based on the parameter set and transmitted synchronously to the corresponding execution equipment to achieve multi-level collaborative control, making the freeze-drying process more refined and intelligent. Different cooling strategies are used in different areas to better adapt to the temperature change law inside the material, improve freeze-drying efficiency and quality, and reduce energy consumption. When the chaotic butterfly effect algorithm is applied in the identification and prediction of nonlinear changes in the freeze-drying process, the present application achieves comprehensive and precise control of the freeze-drying process of building materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1This is a schematic diagram of an embodiment of the automated control method for producing hypoglycemic egg fermented feed in an embodiment of the present application;

[0048] Figure 2 This is a schematic diagram of an embodiment of an automated control system for producing hypoglycemic egg fermented feed in an embodiment of the present application;

[0049] Figure 3 This is a schematic block diagram of the structure of the automated control equipment for producing hypoglycemic egg fermented feed in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The embodiments of the present application provide an automated control method and system for the production of hypoglycemic egg fermented feed. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0051] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 One embodiment of the automated control method for producing hypoglycemic egg fermented feed in the embodiment of the present application includes:

[0052] Step S101: Intelligently identify and precisely control raw materials, obtain digital fingerprints of raw materials through multiple sets of identification sensors, implement a dual-speed unloading strategy, and achieve material proportioning;

[0053] Step S102: Input the material into the parameterized mixing system, uniformly mix the material through a multi-stage variable speed mixing strategy, and generate a mixed material parameter report;

[0054] Step S103: performing conditional adaptive fermentation on the mixed material based on the mixed material parameter report, monitoring the fermentation index in real time through a multi-point sensor network, and performing adaptive PID control adjustment to obtain a fermented material;

[0055] Step S104: post-processing the fermented material, including multi-stage temperature drying, intelligent granulation and quality traceability management, to generate feed products and digital files.

[0056] It is understandable that the execution subject of this application can be the automated control system for the production of hypoglycemic egg fermented feed, or it can be a terminal or a server, and the specific implementation is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0057] Specifically, intelligent raw material identification and ingredient control are achieved through the collaborative work of multiple sensor groups. Optical recognition sensors capture surface texture images of the raw materials, near-infrared spectroscopy sensors acquire molecular structural characteristics, and weight sensors accurately measure mass data. These three types of data together constitute the raw material's digital fingerprint. When the raw materials enter the system, the sensor array scans the raw materials and compares the collected characteristic data with a pre-established digital fingerprint library. The cosine similarity calculation formula is used to determine the degree of match, thereby determining the raw material type and quality grade. Based on the identification results and the formula of the hypoglycemic egg fermented feed, the system calculates the precise amount of each raw material to be released and generates ingredient execution parameters including the release amount, release sequence, and release rate. The material discharge control adopts a dual-speed strategy, initially releasing in fast mode to approximately 80% of the target value, then automatically switching to slow mode for fine-tuning. A dynamic drop compensation algorithm is also used to predict the actual weight of the material after it has been dropped. For example, when the system identifies a batch of plant-based protein ingredients requiring 23.5 kg, it initially feeds to 18.8 kg before switching to slow mode. Using the material's drop characteristics, it calculates a dynamic drop compensation value of 0.3 kg. Therefore, feed is cut off when the actual weight reaches 23.2 kg, ultimately achieving a batching accuracy of ±0.5%. The equipment's self-check program monitors the status of key components of the mixing unit through a distributed sensor network, building a digital twin model of the unit to monitor its operational status. Once the equipment is ready, the material enters the mixing system, where the material volume is monitored in real time via a self-organizing sensor network. The feed valve closes when a preset threshold is reached. The material then enters a multi-stage variable-speed mixing control strategy consisting of four stages: low-speed premixing (10-15 rpm, 120 seconds), medium-speed mixing (25-30 rpm, 180 seconds), high-speed mixing (40-50 rpm, 240 seconds), and steady-state mixing (15-20 rpm, 120 seconds). The mixing time and speed at each stage are optimized in real time based on material characteristics using a dynamic parameter adjustment network. During the mixing process, a torque sensor continuously collects load change data. A deep neural network for mixing uniformity assessment analyzes the mixing state and calculates the mixing uniformity index. This network uses convolutional layers to extract features, LSTM layers to capture temporal variations, and fully connected layers to output uniformity assessment results. When the uniformity index reaches above 95%, the system generates a mixing completion signal and a detailed report on the mixed material parameters, providing data support for subsequent fermentation.

[0058] The system performs adaptive fermentation based on mixed material parameter reports. The reported data is first entered into a fermentation process parameter library. A parameter matching algorithm analyzes material characteristics and generates the optimal fermentation process parameter set for the batch. After sterilization, the fermentation system introduces the materials. A multi-point sensor network collects real-time data from the fermentation process, including temperature distribution, pH changes, dissolved oxygen concentration, and gas composition. This data is used to construct a real-time model of the fermentation state, from which the system calculates the fermentation activity index and metabolite production rate. An adaptive PID controller dynamically adjusts control parameters based on real-time data. The correction formula is: Output = Kp × Error + Ki × Error Integral + Kd × Error Differential, where Kp, Ki, and Kd values ​​are adjusted in real time based on the fermentation state. For example, if the production rate of hypoglycemic active substances is detected to be lower than expected, the system increases the stirring frequency and fine-tunes the temperature setpoint to maintain the fermentation pH within the optimal range of 5.8-6.2, promoting the production of functional substances. In the later stages of fermentation, the system uses spectral analysis to detect the content of hypoglycemic active substances. The fermentation endpoint is determined by combining pH stability and dissolved oxygen recovery rate, generating a fermentation completion signal and a fermentation process data report. The fermented material undergoes a multi-stage drying process, divided into a preheating phase (55±2°C), a constant-rate drying phase (60±2°C), a reduced-rate drying phase (50±2°C), and an equilibrium phase (40±2°C). The system continuously monitors the material's temperature distribution and moisture content using an infrared temperature sensor array and a microwave online moisture detector. The drying process is complete when the average moisture content reaches 10-12% and meets uniformity requirements. The dried material enters the pelletizing system, where it undergoes a physical property analysis to generate pelletizing process parameters. A conditioning unit then adds a fixed amount of steam to the material, partially gelatinizing the starch and enhancing pelletizing quality. During extrusion, a servo-driven pressure control system maintains a constant extrusion pressure (approximately 180 MPa) and adjusts the material throughput rate using real-time temperature monitoring. The pelletizing system uses a variable-frequency speed-controlled cutter to precisely cut the pellets to the target length (1.5-2.5 times the product diameter). After quality inspection of the finished feed, the system generates a unique QR code for each batch, creating a digital archive of the entire process from raw materials to finished product, enabling complete quality traceability. This all-round automated control method effectively solves problems in traditional feed production, such as low ingredient accuracy, unstable fermentation condition control, and difficulty in quality traceability.

[0059] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0060] The raw materials entering the system are scanned by optical recognition sensors, near-infrared spectrum sensors and weight sensors to collect raw material feature data. The feature data is compared and analyzed with the raw material digital fingerprint library to obtain the raw material type identification results and quality grade determination;

[0061] Based on the raw material type identification results and the preset hypoglycemic egg fermented feed formula information, various raw materials are accurately measured and calculated to generate ingredient execution parameters. The ingredient execution parameters include the amount of each raw material, the order of addition, and the rate of addition;

[0062] Input the batching execution parameters into the feeding control device, and automatically switch to slow feeding mode after performing initial rapid feeding of the raw materials to the first preset threshold value. Combined with the material falling characteristic parameters, the dynamic drop compensation value is calculated in real time to determine the optimal cutting point position, so as to obtain the raw materials accurately fed;

[0063] The precisely delivered raw materials are monitored in real time, and the actual delivery amount, delivery time and delivery rate of each raw material are recorded. When it is detected that the deviation of the ingredients exceeds the second preset threshold, compensation adjustment is made through the micro-adjustment device.

[0064] Specifically, three types of sensors work together to collect characteristic data on raw materials. The optical recognition sensor uses a high-resolution camera to capture visible features such as the raw material's surface texture, color, and shape. It segments the image into multiple regions and extracts color histograms, texture features, and edge features. The near-infrared spectroscopy sensor illuminates the raw material with a beam of light of a specific wavelength, measuring absorption and reflection spectra to obtain information about the raw material's internal molecular structure. This spectral data reflects properties such as the raw material's chemical composition and moisture content. The weight sensor records the raw material's mass, density distribution, and looseness. After cleaning and normalization, the data from these three sensor types is fused to form a digital fingerprint of the raw material, consisting of dozens of feature vectors. When a new batch of raw materials enters the system, the sensor array collects data in real time. The data is compared with a pre-established digital fingerprint database using algorithms such as cosine similarity, calculating the degree of similarity and ranking the data to identify the most compatible raw material type. Furthermore, quality grade is determined by analyzing key quality indicators such as protein content, purity, and active ingredient content.

[0065] The system calculates the ingredients based on the raw material identification results and the preset formula for a hypoglycemic egg fermented feed. This formula information includes the required ratios for each raw material at different quality levels, the precise dosage of functional additives, and the specific order of addition. The ingredient calculation process first fine-tunes the formula based on the raw material quality level. For example, if the protein content of a batch of soy protein raw material is detected to be below the standard, the system calculates the supplemental amount based on the nutritional balance of the formula. It then calculates the absolute dosage of each raw material based on the total required amount and determines the optimal dosage rate based on the raw material's physical properties, such as flowability and density. The dosage order is then ranked based on the interaction characteristics between the raw materials and the required mixing efficiency. These calculated results are integrated into the ingredient execution parameters and transmitted to the feeding control system. The feeding control uses a dual-speed strategy to precisely control the feeding process. The ingredient execution parameters are first input into the feeding control device, and the system sets a first preset threshold based on the amount of feeding, typically 80-85% of the target value. When material feeding begins, the system begins rapid feeding, delivering large quantities at a rate of several kilograms per second. When the accumulated weight approaches a preset threshold, it automatically and smoothly switches to slow feeding mode, reducing the rate to 1 / 5-1 / 10 of the original rate, to fine-tune the final portion of the feed. Simultaneously, the system calculates dynamic drop compensation based on real-time data collected from the material's drop curve. This compensation measures the additional weight of the material from the cutoff point to its complete drop into the hopper. This compensation calculation takes into account factors such as material density, particle size, and moisture content, establishes a material drop characteristic model, and predicts the optimal cutoff point in real time, ensuring final drop accuracy within ±0.5%.

[0066] The real-time monitoring process records the actual amount, time, and rate of each raw material added to the database in detail, forming a digital archive of the batching process. The monitoring system continuously collects hopper weight data through high-frequency sampling and calculates the deviation between the actual amount added and the target value. When the batching deviation of a certain raw material exceeds a second preset threshold (usually ±0.3%), the micro-adjustment device automatically initiates the compensation process. For powdered raw materials, micro-adjustment uses a screw feeder to supplement gram-level metering accuracy; for liquid additives, micro-adjustments are made using a high-precision metering pump.

[0067] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0068] Execute equipment self-check procedures on input materials, detect the status of key components of the mixing device through a distributed sensor network, build a digital twin model of the device, and generate equipment readiness instructions based on the device operating status data;

[0069] Based on the equipment ready instruction, the material enters the mixing system, and the material capacity data is collected in real time through the sensor network with a self-organizing topology. When the material capacity reaches the preset capacity threshold, the feed valve is closed to complete the material loading.

[0070] The material is input into the multi-stage variable speed mixing control module, and the multi-stage mixing control is performed according to the preset mixing strategy. The multi-stage mixing control includes a low-speed premixing stage, a medium-speed mixing stage, a high-speed mixing stage, and a stable mixing stage. The mixing time and speed of each stage are adjusted in real time through the dynamic parameter adjustment network;

[0071] The material status during the mixing process is continuously monitored, and load change data is collected through a torque sensor. The data is input into the mixing uniformity evaluation deep neural network for real-time analysis. The mixing uniformity index is calculated in combination with the material property model. When the mixing uniformity index reaches the threshold condition, a mixing completion signal and a mixed material parameter report are generated.

[0072] Specifically, the equipment self-test program executes, comprehensively testing the mixing unit via a distributed sensor network. This distributed sensor network is a monitoring system comprised of multiple interconnected sensor nodes, including temperature, vibration, pressure, and current sensors, installed in key locations such as the mixing motor, drive system, seals, and bearings. The self-test program collects this sensor data and compares it against preset normal operating parameter ranges to determine whether each component is functioning properly. Simultaneously, the collected real-time data is used to construct a digital twin model of the unit—a virtual representation of the equipment that reflects its physical state and operating parameters in real time. Using this digital twin model, the processor predicts potential failures and, when all indicators are within safe ranges, generates a ready signal. Upon receiving the ready signal, the feed system begins introducing material into the mixing system. A sensor network with a self-organizing topology is a network structure capable of autonomously adjusting information transmission paths. It consists of multiple sensor nodes that automatically adjust communication paths based on signal strength and data reliability. The network monitors the accumulation of material in the mixing tank in real time. When it detects that the material volume is approaching a preset threshold (typically 85%-90% of the tank's design capacity), the controller issues a command to close the feed valve to prevent material overflow and ensure mixing efficiency. Once material loading is complete, the mixing system is ready to proceed to the next stage.

[0073] The materials then enter a multi-stage variable speed mixing control link. This control strategy divides the entire mixing process into four different stages. The low-speed premixing stage runs at a speed of 10-15 rpm for about 120 seconds. The purpose is to initially disperse the various raw materials and avoid agglomeration. The medium-speed mixing stage increases the speed to 25-30 rpm and lasts for about 180 seconds to enhance the mutual penetration between the materials. The high-speed mixing stage further increases the speed to 40-50 rpm and lasts for about 240 seconds to ensure that trace functional ingredients (such as hypoglycemic active additives) are fully dispersed. The final stable mixing stage reduces the speed to 15-20 rpm and lasts for about 120 seconds to stabilize the mixing state and reduce stratification. The dynamic parameter adjustment network is an adaptive control algorithm that dynamically calculates and adjusts the optimal mixing time and speed for each stage by analyzing material property data (such as density, viscosity, particle size distribution) and real-time mixing state feedback to adapt to the changes in the characteristics of different batches of materials.

[0074] During the mixing process, the torque sensor continuously monitors the torque changes of the stirring shaft, and these data reflect the changes in the state of the mixture. The deep neural network for mixing uniformity assessment is a machine learning algorithm designed specifically for the mixing process, which includes an input layer, multiple hidden layers, and an output layer. The input layer receives torque change data, stirring power curve, and temperature change information; the hidden layer extracts time series features through multi-layer convolution and loop structures; and the output layer generates a mixing uniformity index. The network is trained with a large amount of historical mixing data to learn to identify characteristic patterns under different uniformity states. The material property model takes into account the viscosity, fluidity, density and other characteristics of the material, and provides a reference factor for uniformity calculation. When the calculated mixing uniformity index reaches the preset threshold (usually above 95%), the controller generates a mixing completion signal and outputs a parameter report containing complete mixing process data.

[0075] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0076] Inputting material property data and hypoglycemic functional requirement data into a hybrid strategy generator, the material property neural network is used to analyze and process the data to generate a multi-stage hybrid control strategy, which includes speed parameters, duration parameters, and transition strategy parameters for each stage;

[0077] Based on the multi-stage mixing control strategy, the material is pre-mixed at a low speed. The servo control system adjusts the mixing speed to the pre-mixing speed range for a preset period of time to perform preliminary dispersion of the material.

[0078] Perform medium-speed and high-speed mixing operations on the premixed materials, monitor the mixing resistance changes in real time through the mixing load feedback system, and dynamically adjust the mixing speed and angular acceleration parameters according to the resistance change curve;

[0079] The high-speed mixed material is input into the stabilization processing unit, and the material flow characteristics are continuously monitored by the material circulation analysis system. When it is detected that the mixed flow state reaches the stable condition, the mixing speed is reduced to the stable range to obtain uniformly mixed materials.

[0080] Specifically, the system receives material property data and functional requirement data for blood sugar reduction. Material property data includes physical parameters such as particle size distribution, density, flowability, and moisture content, while functional requirement data includes information such as the type, concentration, and dispersion requirements of the functional ingredients. The mixing strategy generator is an algorithmic unit that processes this data and generates an optimal mixing strategy. Its core is a material property neural network. This network utilizes a multi-layer perceptron architecture. The input layer receives material properties and functional requirement parameters, the hidden layer uses activation functions to process data correlations, and the output layer generates optimal mixing parameters for each stage. The neural network learns from historical mixing data to establish a mapping between material properties and the optimal mixing strategy. After processing, it generates a multi-stage mixing control strategy, which includes speed parameters for each stage (e.g., the appropriate speed range for each stage), duration parameters (e.g., the optimal duration for each stage), and transition strategy parameters (e.g., how to smoothly transition between stages to avoid material stratification). Based on the generated multi-stage mixing control strategy, the first stage, a low-speed premixing operation, is executed. A servo control system is a closed-loop system that precisely controls motor operation and consists of a servo motor, encoder, driver, and controller. The system receives the premixing speed parameter (usually 10-15rpm) in the mixing strategy and controls the motor operation through the PID algorithm to achieve precise speed regulation and smooth transition. The controller continuously compares the deviation between the set value and the actual speed, dynamically adjusts the output power, and stabilizes the actual speed within the target range. The main purpose of the premixing stage is to preliminarily disperse the various raw materials to prevent agglomeration, which is especially important for the preliminary dispersion of trace ingredients such as hypoglycemic functional additives. The premixing duration is usually calculated by the material property neural network based on the material properties, and is generally in the range of 90-150 seconds.

[0081] After premixing is complete, the medium- and high-speed mixing stages begin. The mixing load feedback system uses torque and current sensors to monitor load changes during mixing in real time. These data reflect the dynamic changes in the material state during mixing. The system filters the collected load data to eliminate noise interference, then calculates the load change rate and fluctuation amplitude to generate a resistance change curve. This curve reflects the dynamic changes in mixing uniformity. When the curve tends to be stable, it indicates that the material is close to a uniform state. The controller dynamically adjusts the mixing speed based on the resistance change curve. For example, if a sudden increase in resistance is detected, the speed is appropriately reduced or the angular acceleration parameter (the rate at which the agitator accelerates or decelerates) is adjusted to avoid overload. When resistance fluctuations decrease, the speed is appropriately increased to promote mixing. The medium-speed stage is typically in the range of 25-30 rpm, and the high-speed stage can reach 40-50 rpm. The angular acceleration is controlled in the range of 3-5 rpm / s to ensure that the material does not stratify or splash due to excessive speed changes.

[0082] Finally, the high-speed mixed material is sent to the stabilization processing unit. The material circulation analysis system monitors the flow characteristics of the material, including surface fluctuations, particle motion trajectories and internal flow patterns, through optical sensor arrays and acoustic sensors. The data collected by the system is subjected to feature extraction, and the fluid motion consistency index and turbulence intensity are calculated to determine whether the mixed flow state has reached stability. Stability conditions include reduced surface fluctuation amplitude, regularization of internal flow patterns, and improved uniformity of particle distribution. When the mixed flow state reaches stable conditions, the controller reduces the mixing speed to a stable range (usually 15-20rpm) and performs the final stable mixing process. The purpose of stable mixing is to eliminate stratification that may be caused by high-speed mixing.

[0083] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0084] Input the mixed material parameter report into the fermentation process parameter library, analyze the material characteristics through the parameter matching algorithm, and generate the fermentation process parameter set for this batch, which includes the temperature control curve, pH range and dissolved oxygen control strategy;

[0085] The fermentation system is sterilized and the materials are introduced into the fermentation tank. Real-time data of the fermentation process, including temperature distribution data, pH value change data, dissolved oxygen concentration data, and gas composition data, are collected through a multi-point sensor network to establish a real-time model of the fermentation status.

[0086] The fermentation activity index and metabolite production rate are calculated based on a real-time fermentation state model. The temperature, pH value, and ventilation volume are dynamically adjusted through an adaptive PID controller to maintain the fermentation index within the target range and promote the production of hypoglycemic active substances.

[0087] The quality of materials in the late stage of fermentation is evaluated online, the content of hypoglycemic active substances is detected by a spectrometer, the fermentation endpoint is determined based on the pH stability and dissolved oxygen recovery rate, and a fermentation completion instruction and fermentation process data report are generated.

[0088] Specifically, the mixed material parameter report is entered into the fermentation process parameter library. This parameter report contains key information such as material composition, particle size distribution, and moisture content. The fermentation process parameter library is a dataset containing optimal fermentation parameters for different recipes and conditions. The parameter matching algorithm uses case-based reasoning and similarity calculation to compare the current material characteristics with historical successful cases, identifying the most similar parameter set as a benchmark and then fine-tuning it based on the specific characteristics of the current material. The resulting fermentation process parameter set includes a temperature control curve (temperature trajectory throughout the fermentation process), a pH control range (optimal pH range at different fermentation stages), and a dissolved oxygen control strategy (strategy for adjusting ventilation volume and stirring frequency). Together, these parameters form the optimal fermentation plan for the current batch of materials. Before materials are introduced, the fermentation system undergoes sterilization, including UV sterilization and high-temperature steam disinfection, to ensure the sterility of the fermentation environment. After the materials are introduced into the fermenter, the multi-point sensing network begins operation. The network consists of a variety of sensors distributed across the fermentation tank, including a temperature sensor array (to monitor temperature distribution in different areas of the tank), a pH electrode (to measure changes in the pH of the fermentation liquid), a dissolved oxygen probe (to detect oxygen content in the liquid), and a gas composition analyzer (to analyze the gas composition produced during the fermentation process). These sensors collect data in real time, which is then filtered, processed for outliers, and standardized before being fed into a data fusion algorithm. The algorithm integrates information from each sensor to create a real-time model reflecting the current fermentation status, including multi-dimensional information such as temperature gradient distribution maps, pH trend curves, and time-series data on dissolved oxygen concentration.

[0089] After the real-time fermentation status model is formed, two key indicators are calculated: the fermentation activity index and the metabolite production rate. The fermentation activity index is calculated by analyzing the pH change rate, dissolved oxygen consumption rate, and heat production rate, reflecting the level of microbial activity. The metabolite production rate estimates the production rate of hypoglycemic substances through indirect indicators such as gas production rate and pH change characteristics. Based on these calculation results, an adaptive PID controller dynamically adjusts key parameters. Unlike traditional PID controllers, the adaptive PID controller automatically adjusts the proportional, integral, and differential parameters based on the fermentation status, achieving more precise control. If fermentation activity is lower than expected, the controller automatically increases the stirring frequency and fine-tunes the temperature. If the pH value deviates from the target range, the controller automatically adds regulator via the acid-base regulating pump. If the dissolved oxygen is insufficient, the aeration volume or stirring speed is increased. These adjustments ensure that fermentation indicators remain within the optimal range (typically pH 5.8-6.2, temperature 28-30°C, and dissolved oxygen 30-40%), promoting the production of hypoglycemic substances.

[0090] As fermentation enters its later stages, the online quality assessment system begins operating. Using near-infrared spectroscopy, the spectrometer non-destructively detects the content of hypoglycemic active substances in the fermentation broth, while also monitoring pH stability (the pH change rate drops to a very low level) and dissolved oxygen recovery rate (dissolved oxygen begins to rise due to reduced microbial activity). Fermentation is determined to have reached its endpoint when all three indicators simultaneously meet the preset conditions: the active substance content reaches the target value, the pH change rate is less than 0.01 / hour and remains stable for more than six hours, and the dissolved oxygen recovery rate exceeds 1% / hour and persists for more than three hours. At this point, a fermentation completion instruction is generated, and a report containing complete fermentation process data is output as a reference for subsequent drying and granulation processes. For example, in the production of a batch of hypoglycemic egg fermented feed, a parameter matching algorithm generated a temperature control curve (initial 29°C, rising to 30°C after 24 hours, and falling to 28°C after 48 hours), a pH control range (5.6-6.0 in the initial stage, 5.8-6.2 in the middle stage, and 5.5-5.8 in the late stage), and a dissolved oxygen control strategy (40% in the initial stage, 35% in the middle stage, and 30% in the late stage) based on the characteristics of the batch containing a specific ratio of corn protein and functional additives. During the fermentation process, a multi-point sensor network monitors various indicators in real time. When it is detected that the pH value is lower than 5.7 and continues to decline after 28 hours, the adaptive PID controller immediately adjusts the amount of alkali solution added to adjust the pH value back to the target range, ensuring the stable production of hypoglycemic active substances and solving the technical problem of extensive control of traditional fermentation processes.

[0091] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0092] The fermentation material is dried in multiple stages, and the drying temperature and air flow parameters are controlled in stages, and the moisture change curve of the material is monitored to obtain the dried material;

[0093] The dry material is fed into the pelletizing system, a fixed amount of steam is added through the conditioning device, and then extrusion molding and pelletizing operations are performed to obtain feed pellets;

[0094] The feed pellets are cooled, the temperature gradient is controlled by a laminar cooling bed, and the surface temperature distribution of the pellets is monitored to obtain the finished feed;

[0095] Conduct quality inspection and traceability marking on finished feed, and generate product QR codes and full-process digital files.

[0096] Specifically, the fermented material undergoes a multi-stage drying process, divided into a preheating phase, a constant-rate drying phase, a deceleration drying phase, and an equilibrium phase. During the preheating phase, the drying equipment temperature is gradually raised to approximately 55°C to uniformly increase the material temperature. During the constant-rate drying phase, the temperature is maintained at approximately 60°C, allowing for a rapid and stable water evaporation rate. During the deceleration drying phase, the temperature is lowered to approximately 50°C to prevent surface hardening, which would hinder internal water dissipation. During the equilibrium phase, the temperature is further lowered to approximately 40°C to achieve a balanced moisture distribution. During the drying process, an infrared temperature sensor array and an online microwave moisture detection device continuously monitor the material's temperature distribution and moisture content, generating a moisture profile. Drying is considered complete when the moisture content reaches 10-12% and meets uniformity requirements (moisture content deviation ≤1% across all components). A drying control algorithm dynamically adjusts the duration and end points of each phase based on the evaporation rate to prevent over-drying and loss of blood sugar-lowering functional components. After drying is complete, the material enters the granulation system. First, the dried material is analyzed using a physical property testing device to measure parameters such as particle size distribution, bulk density, and flowability, which are then used to generate granulation process parameters. A conditioning unit then adds a fixed amount of steam to the material, typically 2-4% by weight, at a temperature of approximately 105°C and a pressure of approximately 0.8 MPa. This addition process is precisely controlled by a flow meter and temperature sensor to ensure uniform moisture distribution. Conditioning partially gelatinizes the starch in the material, improving granulation quality. The material then enters the extrusion process, where a servo-driven pressure control system maintains a constant extrusion pressure (approximately 180 MPa) as it passes through the die into a continuous strand. The granulation temperature is monitored by an embedded temperature sensor and maintained at approximately 85°C, ensuring plasticization without destroying the active ingredients. The pelletizing system uses a variable-frequency speed-controlled cutter to precisely cut pellets to the target length (typically 1.5-2.5 times the pellet diameter). Pellets are also monitored for uniformity, ensuring a coefficient of variation of ≤8%.

[0097] After granulation, the hot granules immediately enter the cooling process and are cooled by a laminar cooling bed. The laminar cooling bed is a specially designed cooling device that can generate a uniform and stable airflow to avoid particle damage caused by turbulence. The cooling process adopts a temperature gradient control strategy to gradually reduce the temperature of the cooling airflow from about 35°C in the upper layer to the room temperature in the lower layer. The airflow speed is maintained at about 0.8 m / s to ensure uniform cooling of the granules. The infrared temperature scanning array monitors the surface temperature distribution of the granules in real time. When the difference between the surface temperature of the granules and the ambient temperature drops to within 5°C and remains stable, the cooling is determined to be complete. The cooling control algorithm dynamically adjusts the cooling time according to the rate of change of the surface temperature of the granules to avoid internal stress caused by excessive cooling and ensure that the granule strength reaches the target hardness of 4.5-6.0 kgf.

[0098] Finally, the finished feed is subjected to comprehensive quality testing, including physical property testing (particle size distribution, bulk density, fluidity), functional property testing (content of hypoglycemic active ingredients, stability) and safety testing (microbial limits, mycotoxins). The test data is transmitted to the quality management system in real time via a high-speed data bus, automatically compared with the preset quality standards, and a quality assessment report is generated. Qualified products enter the traceability identification link, and the intelligent coding system generates a unique QR code for each batch of products. The coding content includes production batch number, production date, expiration date, raw material traceability code, quality grade and other information. At the same time, a full-process digital archive is established. The archive uses blockchain technology to ensure that the data cannot be tampered with, and records the complete production history including raw material sources, ingredient parameters, mixing process, fermentation conditions, drying parameters, granulation process and final product test results.

[0099] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0100] Analyze the physical properties of the dried material, measure the particle size distribution, bulk density and fluidity parameters through the material property detection device, and generate granulation process parameters based on the test results;

[0101] The dried material is fed into the conditioning device, and a quantitative amount of steam is added to the material through the precision steam injection system. At the same time, the mixer is controlled to perform uniform stirring to obtain the conditioned material;

[0102] The quenched and tempered material is extruded, and a servo-driven pressure control system maintains a constant extrusion pressure. The material throughput rate is adjusted in combination with real-time temperature monitoring to obtain extruded material strips.

[0103] The extruded material strips are fed into the pelletizing system, where the variable frequency speed cutter performs precise cutting according to the target particle length parameters while monitoring the particle uniformity to obtain feed pellets.

[0104] Specifically, the physical properties of the dried material are analyzed, and key parameters are obtained using a dedicated material property testing device. This device consists of multiple testing units, including a laser particle size analyzer, a bulk density meter, and a flowability tester. The laser particle size analyzer utilizes the principle of laser diffraction. When material particles pass through a laser beam, a specific scattering pattern is formed. This pattern is captured by a photodetector and a particle size distribution curve is calculated, including particle size parameters such as D10, D50, and D90. The bulk density meter uses a standard volumetric cylinder and a high-precision balance to measure the material's bulk density—the mass per unit volume. The flowability tester measures the material's discharge angle, angle of repose, and flow rate, reflecting its flow properties. These parameters are normalized and input into a pelletizing parameter generator. Based on historical data and the specific requirements of hypoglycemic feeds, the generator calculates the optimal pelletizing process parameters, including conditioning temperature, steam addition, pressure setting, die selection, and pelletizing frequency. After the pelletizing parameters are generated, the dried material enters the conditioning device for steam conditioning. The precision steam injection system consists of a temperature controller, a pressure regulating valve, a flow meter, and multiple nozzles, enabling precise control of steam temperature, pressure, and addition. The system calculates the required steam volume based on the moisture content and particle size characteristics of the material, typically 2-4% of the material weight. The steam temperature is controlled at 105±2°C and the pressure at 0.8±0.05MPa. Steam is evenly sprayed into the material through the nozzles, while the mixer in the conditioning cylinder rotates at 30±2rpm to ensure even steam distribution. The mixer features a multi-layer, staggered stirring blade design to prevent local overheating of the material. During the conditioning process, the material temperature rises to 85±3°C, partially gelatinizing the starch, improving the material's cohesiveness and plasticity, and enhancing the quality of the granulation. Temperature and humidity sensors monitor the conditioning process in real time. Conditioning is complete when the parameters reach the set range and remain stable for 45±5 seconds.

[0105] After conditioning, the material enters the extrusion molding stage. A servo-driven pressure control system is the core of the pelletizing process. This system, consisting of a servo motor, pressure sensor, temperature sensor, and controller, ensures constant extrusion pressure through closed-loop control. The controller continuously collects pressure sensor data, compares it with the setpoint (typically 180 ± 10 MPa), calculates the deviation, and adjusts the servo motor output power to keep pressure fluctuations within ±5%. An embedded temperature sensor also monitors the internal temperature of the die cavity. If the temperature exceeds a safe range (typically no more than 95°C), the control system automatically adjusts the material throughput rate, slowing down the feed rate to prevent overheating and inactivation of the hypoglycemic functional ingredients. During the extrusion process, the material passes through the die under high pressure, forming a continuous extruded strand. Die selection is based on product requirements and material properties. For hypoglycemic feeds, dies with a diameter of 2.5-3.5 mm are typically used. The extruded strands then enter the pelletizing system for cutting. The variable-frequency speed cutter, consisting of a variable-frequency motor, cutter, and control system, is key to achieving precise cutting. The control system calculates the required cutter speed based on the target particle length parameter (usually 1.5-2.5 times the particle diameter) and the extrusion speed. For example, when the extrusion speed is 0.5 m / s and the target particle length is 7.5 mm, the cutter speed should be set to 400 rpm (calculation formula: speed = extrusion speed ÷ target length × 60). The control system adjusts the motor speed in real time through the frequency converter to ensure cutting accuracy. At the same time, the high-speed camera and image processing system continuously monitor the uniformity of particle length and calculate the length coefficient of variation. If the coefficient of variation exceeds 8%, the system automatically fine-tunes the cutter speed or extrusion speed to maintain cutting consistency.

[0106] The above describes the automated control method for producing hypoglycemic egg fermented feed in the embodiment of the present application. The following describes the automated control system for producing hypoglycemic egg fermented feed in the embodiment of the present application. Figure 2 In one embodiment of the present application, an automated control system for producing hypoglycemic egg fermented feed includes:

[0107] The control module 201 is used for intelligent identification and precise batching control of raw materials. It obtains the digital fingerprint of raw materials through multiple sets of identification sensors, implements a dual-speed feeding strategy, and realizes material proportioning.

[0108] Processing module 202 is used to input materials into the parameterized mixing system, uniformly mix the materials through a multi-stage variable speed mixing strategy, and generate a mixed material parameter report;

[0109] A monitoring module 203 is configured to perform conditional adaptive fermentation on the mixed material based on the mixed material parameter report, monitor fermentation indicators in real time through a multi-point sensor network, and perform adaptive PID control to obtain fermented material;

[0110] The traceability module 204 is used to perform post-processing on the fermentation material, including multi-stage temperature drying, intelligent granulation and molding, and quality traceability management, to generate feed products and digital archives.

[0111] above Figure 2 The automated control system for the production of hypoglycemic egg fermented feed in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The automated control equipment for the production of hypoglycemic egg fermented feed in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0112] Reference Figure 3 In the embodiment of the present invention, there is also provided an automated control device for producing egg fermented feed with a reduced blood sugar content. The automated control device for producing egg fermented feed with a reduced blood sugar content can be a server, and its internal structure can be as follows: Figure 3 As shown. The automated control equipment for producing fermented egg feed that reduces blood sugar includes a processor, a memory, a display screen, an input device, a network interface, and a database connected via a system bus. The computer-designed processor is used to provide computing and control capabilities. The memory of the automated control equipment for producing fermented egg feed that reduces blood sugar includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the automated control equipment for producing fermented egg feed that reduces blood sugar is used to store the corresponding data in this embodiment. The network interface of the automated control equipment for producing fermented egg feed that reduces blood sugar is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0113] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the automated control equipment for producing hypoglycemic egg fermented feed to which the solution of the present invention is applied.

[0114] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions. When the instructions are run on a computer, the computer executes the steps of the automated control method for producing hypoglycemic egg fermented feed.

[0115] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling an automated control device for the production of hypoglycemic egg fermented feed (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An automated control method for the production of egg fermented feed for lowering blood sugar, characterized in that: The method comprises: Intelligently identify raw materials and precisely control their proportions. Multiple sets of identification sensors are used to obtain digital fingerprints of raw materials, and a dual-speed unloading strategy is implemented to achieve material proportioning. Input the material into the parameterized mixing system, uniformly mix the material through a multi-stage variable speed mixing strategy, and generate a mixed material parameter report; Based on the mixed material parameter report, the mixed material is subjected to conditional adaptive fermentation, fermentation indicators are monitored in real time through a multi-point sensor network, and adaptive PID control adjustment is performed to obtain a fermentation material; The fermentation material is subjected to post-processing, including multi-stage temperature drying, intelligent granulation and molding, and quality traceability management, to generate feed products and digital archives.

2. The automated control method for producing hypoglycemic egg fermented feed according to claim 1, characterized in that: The intelligent identification and precise batching control of raw materials, obtaining the digital fingerprint of raw materials through multiple sets of identification sensors, implementing a dual-speed feeding strategy, and achieving material proportioning include: The raw materials entering the system are scanned by optical recognition sensors, near-infrared spectroscopy sensors and weight sensors to collect raw material feature data, which are then compared and analyzed with the raw material digital fingerprint library to obtain raw material type identification results and quality grade determination; Based on the raw material type identification result and the preset hypoglycemic egg fermented feed formula information, various raw materials are accurately measured and calculated to generate ingredient execution parameters, which include the amount of each raw material, the order of addition, and the rate of addition; The batching execution parameters are input into the feeding control device, and the raw materials are initially fed quickly to a first preset threshold value, and then automatically switched to a slow feeding mode. The dynamic drop compensation value is calculated in real time based on the material falling characteristic parameters, and the optimal cutting point position is determined to obtain the raw materials accurately fed; The precisely delivered raw materials are monitored in real time, and the actual delivery amount, delivery time and delivery rate of each raw material are recorded. When it is detected that the deviation of the ingredients exceeds the second preset threshold, compensation adjustment is performed through the micro-adjustment device.

3. The automated control method for producing hypoglycemic egg fermented feed according to claim 1, characterized in that: The material is input into the parameterized mixing system, and the material is uniformly stirred through a multi-stage variable speed mixing strategy to generate a mixed material parameter report, including: Execute equipment self-check procedures on input materials, detect the status of key components of the mixing device through a distributed sensor network, build a digital twin model of the device, and generate equipment readiness instructions based on the device operating status data; Based on the equipment ready instruction, the material is controlled to enter the mixing system, and the material capacity data is collected in real time through the sensor network of the self-organizing topology structure. When the material capacity reaches the preset capacity threshold, the feed valve is closed to complete the material loading; The material is input into a multi-stage variable speed mixing control module, and multi-stage mixing control is performed according to a preset mixing strategy. The multi-stage mixing control includes a low-speed premixing stage, a medium-speed mixing stage, a high-speed mixing stage, and a stable mixing stage. The mixing time and speed of each stage are adjusted in real time through a dynamic parameter adjustment network; The material status during the mixing process is continuously monitored, and load change data is collected through a torque sensor. The data is input into the mixing uniformity evaluation deep neural network for real-time analysis. The mixing uniformity index is calculated in combination with the material property model. When the mixing uniformity index reaches the threshold condition, a mixing completion signal and a mixed material parameter report are generated.

4. The automated control method for producing hypoglycemic egg fermented feed according to claim 3, characterized in that: The material is input into the multi-stage variable speed mixing control module, and the multi-stage mixing control is performed according to the preset mixing strategy, including: Inputting material property data and hypoglycemic functional requirement data into a hybrid strategy generator, analyzing and processing the data through a material property neural network to generate a multi-stage hybrid control strategy, wherein the multi-stage hybrid control strategy includes speed parameters, duration parameters, and transition strategy parameters for each stage; Based on the multi-stage mixing control strategy, a low-speed premixing operation is performed on the material, and the speed of the mixing device is adjusted to the premixing speed range through the servo control system for a preset time period to perform preliminary dispersion processing on the material; Perform medium-speed and high-speed mixing operations on the premixed materials, monitor the mixing resistance changes in real time through the mixing load feedback system, and dynamically adjust the mixing speed and angular acceleration parameters according to the resistance change curve; The high-speed mixed material is input into the stabilization processing unit, and the material flow characteristics are continuously monitored by the material circulation analysis system. When it is detected that the mixed flow state reaches the stable condition, the mixing speed is reduced to the stable range to obtain uniformly mixed materials.

5. The automated control method for producing hypoglycemic egg fermented feed according to claim 1, characterized in that: The method of performing conditional adaptive fermentation on the mixed material based on the mixed material parameter report, monitoring fermentation indicators in real time through a multi-point sensor network, and performing adaptive PID control adjustment to obtain a fermentation material includes: Inputting the mixed material parameter report into the fermentation process parameter library, analyzing the material characteristics through the parameter matching algorithm, and generating the fermentation process parameter set for this batch, wherein the fermentation process parameter set includes a temperature control curve, a pH range, and a dissolved oxygen control strategy; The fermentation system is sterilized and the materials are introduced into the fermentation tank. Real-time data of the fermentation process, including temperature distribution data, pH value change data, dissolved oxygen concentration data, and gas composition data, are collected through a multi-point sensor network to establish a real-time model of the fermentation status. The fermentation activity index and metabolite production rate are calculated based on the real-time fermentation state model, and the temperature, pH value and ventilation volume are dynamically adjusted by an adaptive PID controller to maintain the fermentation index within the target range and promote the production of hypoglycemic active substances; The quality of materials in the late stage of fermentation is evaluated online, the content of hypoglycemic active substances is detected by a spectrometer, the fermentation endpoint is determined based on the pH stability and dissolved oxygen recovery rate, and a fermentation completion instruction and fermentation process data report are generated.

6. The automated control method for producing hypoglycemic egg fermented feed according to claim 1, characterized in that: The post-processing of the fermented material includes multi-stage temperature drying, intelligent granulation and quality traceability management, and the generation of feed products and digital archives, including: The fermentation material is dried in multiple stages, and the drying temperature and air flow parameters are controlled in stages, and the moisture change curve of the material is monitored to obtain the dried material; The dried material is fed into a pelletizing system, a quantitative steam is added through a conditioning device, and extrusion molding and pelletizing operations are performed to obtain feed pellets; Cooling the feed pellets, controlling the temperature gradient through a laminar cooling bed, and monitoring the surface temperature distribution of the pellets to obtain finished feed; The finished feed is subjected to quality inspection and traceability marking, and a product QR code and a full-process digital file are generated.

7. The automated control method for producing hypoglycemic egg fermented feed according to claim 6, characterized in that: The dry material is fed into a pelletizing system, a quantitative steam is added through a conditioning device, and extrusion molding and pelletizing operations are performed to obtain feed pellets, including: Analyze the physical properties of the dried material, measure the particle size distribution, bulk density and fluidity parameters through the material property detection device, and generate granulation process parameters based on the test results; The dried material is fed into a conditioning device, a quantitative steam is added to the material through a precision steam injection system, and a mixer is controlled to perform uniform stirring to obtain a conditioned material; Performing an extrusion molding operation on the quenched and tempered material, maintaining a constant extrusion pressure through a servo-driven pressure control system, and adjusting the material passing rate in combination with real-time temperature monitoring to obtain an extruded material strip; The extruded material strips are fed into the pelletizing system, and the variable frequency speed regulating cutter performs precise cutting according to the target particle length parameters while monitoring the particle uniformity to obtain feed pellets.

8. An automated control system for the production of egg fermented feed for lowering blood sugar, characterized in that: A method for realizing an automated control method for producing a hypoglycemic egg fermented feed according to any one of claims 1 to 7, wherein the automated control system for producing a hypoglycemic egg fermented feed comprises: The control module is used for intelligent identification and precise batching control of raw materials. It obtains the digital fingerprint of raw materials through multiple sets of identification sensors, implements a dual-speed feeding strategy, and realizes material proportioning. A processing module is used to input materials into the parameterized mixing system, uniformly mix the materials through a multi-stage variable speed mixing strategy, and generate a mixed material parameter report; A monitoring module is used to perform conditional adaptive fermentation on the mixed material based on the mixed material parameter report, monitor the fermentation index in real time through a multi-point sensor network, and perform adaptive PID control adjustment to obtain fermentation material; The traceability module is used to post-process the fermentation materials, including multi-stage temperature drying, intelligent granulation and molding, and quality traceability management, to generate feed products and digital archives.

9. An automated control device for producing egg fermented feed for lowering blood sugar, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the automated control method for the production of hypoglycemic egg fermented feed according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor is caused to execute the automated control method for producing hypoglycemic egg fermented feed according to any one of claims 1 to 7.

Images