A whole-process networking monitoring and intelligent management and control system for feed production and processing

Abstract

The application discloses a kind of feed production processing whole process networking monitoring and intelligent management and control system, it is related to industrial production process intelligent control technical field, and the system includes raw material warehousing, crushing, batching mixing, granulation conditioning, cooling screening, finished product warehousing monitoring module, and networking data transmission, edge collaborative processing, global intelligent decision-making, field execution regulation and control, whole-process safety protection module;Each monitoring module collects corresponding process operation and quality parameters, three-level data processing architecture completes data interaction and decision generation, and execution module adjusts equipment operating parameters, and safety module monitors abnormal state and executes protection action.The application realizes multi-dimensional monitoring of whole process of feed production, eliminates data island, three-level architecture cooperates to complete real-time control and global optimization, improves product quality stability and equipment operation reliability, strengthens production safety protection, and overall improves the intelligent level of feed production control.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control for industrial production processes, and particularly relates to a whole-process networked monitoring and intelligent management and control system for feed production and processing. Background Art

[0002] Feed production and processing includes multiple processes such as raw material warehousing, crushing, batching and mixing, pelleting and conditioning, cooling and screening, and finished product storage. The process parameters of each process are interrelated and directly affect the final product quality and production safety. Traditional feed production mostly adopts a management and control mode combining manual inspection and stand-alone automation. Production data collection relies on manual records and single-point sensors, with a single collection dimension, which can only obtain basic equipment operation parameters, and cannot synchronously collect key quality indicators such as raw material nutritional components, material uniformity, and particle forming rate, resulting in insufficient data continuity and accuracy. The equipment of each process operates independently, and the control logics are isolated from each other, lacking a cross-process collaborative regulation mechanism. The quality deviation of the previous process cannot be transmitted to subsequent processes in time for compensation, which easily leads to product quality fluctuations. Production process management and control relies on the experience of operators, and the adjustment of process parameters lags behind, making it difficult to adapt to changes in raw material quality and fluctuations in production load.

[0003] Most of the existing feed production management and control systems are partial automation transformations, and no whole-process networked monitoring system is constructed. Data transmission adopts a point-to-point mode, which has high transmission delay and poor stability, and cannot realize real-time sharing and centralized processing of production data. Data processing is mostly concentrated on local industrial personal computers, with limited computing capacity, which can only complete simple threshold alarms, and cannot perform trend analysis and process optimization based on whole-process historical data. Although some systems introduce cloud management platforms, they only realize the functions of data display and report generation, do not establish a mathematical model of the production process, lack the capabilities of intelligent decision-making and automatic regulation, and cannot dynamically adjust process parameters according to the real-time production state. Equipment operation state monitoring only focuses on basic parameters such as current and rotating speed, lacks a multi-dimensional health assessment mechanism, and equipment maintenance adopts a regular maintenance mode, which is prone to over-maintenance or missed fault detection.

[0004] There are safety risks such as dust, high temperature and high pressure in the feed production process. Traditional safety protection mostly adopts independent limit switches and emergency stop buttons, lacks a whole-process multi-parameter linkage protection mechanism, and cannot identify potential safety hazards in advance. The response speed to abnormal states is slow, which easily causes equipment damage or production accidents. The product quality traceability system is imperfect, which can only record the information of raw material batches and finished product outbound, and cannot associate the process parameters of each process in the production process, making it difficult to locate the specific cause when quality problems occur. As the feed industry's requirements for product quality stability, production efficiency and production safety continue to increase, traditional management and control modes can no longer meet the needs of modern feed production, and it is urgent to construct a whole-process networked monitoring and intelligent management and control system to realize digital, intelligent and integrated management and control of the production process. Contents of the Invention

[0005] This invention proposes a networked monitoring and intelligent control system for the entire feed production and processing process to solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a networked monitoring and intelligent control system for the entire feed production and processing process, comprising the following modules: The raw material warehousing monitoring module is used to collect data on raw material type, moisture content, crude protein content, crude fiber content, impurity ratio, warehousing weight, and storage environment temperature and humidity parameters. The pulverization process monitoring module is used to collect pulverization speed, feed flow rate, pulverized particle size, cavity temperature, motor current and equipment vibration parameters; The ingredient mixing monitoring module is used to collect parameters such as ingredient accuracy, feeding sequence, mixing time, stirring speed, material uniformity, and chamber pressure. The granulation and conditioning monitoring module is used to collect parameters such as conditioning temperature, conditioning moisture, steam pressure, granulation speed, die pressure, and granulation rate. The cooling and screening monitoring module is used to collect parameters such as cooling air volume, cooling temperature, screening speed, finished product particle size, breakage rate and dust concentration. The finished product storage monitoring module is used to collect parameters such as temperature and humidity of finished product storage, material level, weight of outbound products, packaging sealing and shelf life. The network data transmission module adopts a wired industrial bus and wireless Internet of Things architecture to realize real-time data interaction and remote transmission between various monitoring modules and processing modules; The edge collaborative processing module is used to complete on-site data preprocessing, abnormal data identification, and local real-time control command generation; The global intelligent decision-making module is used to integrate data from the entire process to build production models, perform trend analysis, and generate global optimization strategies. The on-site control module is connected to the actuators of the crusher, mixer, granulator, cooler, and screening machine, respectively, and is used to adjust the equipment operating parameters according to control commands; The full-process safety protection module is used to monitor conditions such as over-temperature, over-pressure, overload, material blockage, and excessive dust, and to execute safety protection actions.

[0007] Furthermore, it also includes a production process quality balance control unit, which calculates the optimal combination of process parameters based on the quality correlation of multiple processes. The calculation formula is as follows: ; in, This is the optimal control coefficient for the production process. For the first Quality weighting coefficient of each process For the first Real-time quality indicators for each process step. For the first Standard quality indicators for each process This is the process correlation deviation coefficient. This represents the quality transfer deviation value between adjacent processes. This represents the total number of production processes.

[0008] Furthermore, it also includes an equipment operating status health assessment unit, which assesses the equipment health level based on multi-dimensional operating parameters. The calculation formula is as follows: ; in, This is the equipment health assessment value. For the first Weighting coefficients of class runtime parameters, For the first Real-time runtime parameters for the class For the first Class-standard operating parameters, This is the temperature deviation weighting coefficient. This refers to the temperature difference value during continuous operation of the equipment. This represents the total number of categories of equipment operating parameters.

[0009] Furthermore, the raw material warehousing monitoring module includes a raw material spectral rapid detection device, a moisture sensor, a weight sensor, a temperature and humidity sensor, and an RFID reader. The raw material spectral rapid detection device is used for non-contact rapid detection of the nutrient content of raw materials. The moisture sensor is used to collect the moisture value of raw materials in real time. The weight sensor is used to accurately measure the weight of raw materials entering the warehouse. The temperature and humidity sensor is used to collect the storage environment parameters of raw materials. The RFID reader is used to read the batch information and traceability code of raw materials. All detection data is uploaded to the edge collaborative processing module in real time to complete the full-element quality verification and information archiving of raw materials entering the warehouse.

[0010] Furthermore, the crushing process monitoring module includes a speed sensor, a flow sensor, a particle size detection device, a temperature sensor, a current sensor, and a vibration sensor. The speed sensor collects the real-time operating speed of the crusher rotor, the flow sensor collects the real-time feed flow of the crusher, the particle size detection device detects the particle size distribution of the crushed material online, the temperature sensor collects the internal temperature of the crusher cavity, the current sensor collects the operating current of the crusher motor, and the vibration sensor collects the vibration amplitude of the equipment body. The edge processing module judges the crushing status in real time based on the collected data and synchronously adjusts the matching relationship between the crusher speed and the feed flow.

[0011] Furthermore, the batching and mixing monitoring module includes a high-precision batching scale, a feeding sequence controller, a time relay, a speed detection device, a uniformity detection sensor, and a pressure sensor. The high-precision batching scale enables accurate metering and feeding of each component raw material, the feeding sequence controller controls the timing and interval of raw material feeding, the time relay records the actual running time of the mixer, the speed detection device collects the mixing speed of the mixer, the uniformity detection sensor detects the uniformity of the mixed material online, the pressure sensor collects the internal working pressure of the mixer, and the global intelligent decision-making module optimizes the batching ratio and mixing process parameters based on the collected data.

[0012] Furthermore, the pelleting conditioning monitoring module includes a temperature sensor, a moisture detector, a pressure sensor, a speed sensor, a die pressure detection device, and a pelleting rate detection device. The temperature sensor collects the temperature of the material inside the conditioner, the moisture detector collects the moisture content of the material after conditioning, the pressure sensor collects the working pressure of the steam pipeline, the speed sensor collects the speed of the pellet mill rollers, the die pressure detection device collects the pressure value of the material passing through the die, the pelleting rate detection device calculates the feed pelleting ratio online, and the edge processing module dynamically adjusts the steam supply and pellet mill operating parameters based on real-time data.

[0013] Furthermore, the cooling and screening monitoring module includes an airflow sensor, a temperature sensor, a speed sensor, a particle size screening device, a breakage rate detector, and a dust concentration sensor. The airflow sensor collects the airflow of the cooler, the temperature sensor collects the temperature of the material after cooling, the speed sensor collects the operating speed of the screening machine, the particle size screening device screens the particle size distribution of the finished feed, the breakage rate detector counts the breakage ratio of particles, and the dust concentration sensor collects the dust content at the production site. The on-site execution control module adjusts the cooling airflow and the speed of the screening machine based on the monitoring data.

[0014] Furthermore, the finished product storage monitoring module includes a storage temperature and humidity sensor, a continuous level gauge, an outbound weighing sensor, a packaging sealing detection device, and a time recorder. The storage temperature and humidity sensor monitors the environmental parameters of the finished product storage environment in real time, the continuous level gauge collects the material level height inside the silo, the outbound weighing sensor measures the weight of the finished product leaving the warehouse, the packaging sealing detection device detects the sealing status of the finished product packaging, the time recorder records the time of entry into the warehouse and the shelf life information of the finished product, and the network data transmission module synchronously uploads the finished product data to the cloud.

[0015] Furthermore, the network data transmission module, edge collaborative processing module, and global intelligent decision-making module form a three-tiered data processing architecture. The edge collaborative processing module performs filtering and noise reduction, data standardization, and real-time anomaly detection on the on-site monitoring data. The detection results are uploaded to the global intelligent decision-making module through the network data transmission module. The global intelligent decision-making module establishes a production process optimization model based on historical and real-time data throughout the entire process, generates long-term optimization strategies and parameter adjustment schemes, and transmits them to the edge collaborative processing module to be converted into specific control commands. The on-site execution and control module adjusts equipment parameters according to these commands. The full-process safety protection module receives the status signals transmitted by the three-tiered architecture and independently triggers safety protection actions in abnormal states.

[0016] Compared with existing technologies, the beneficial effects of this invention are: This invention constructs a multi-module monitoring system covering the entire process from raw material warehousing to finished product delivery, enabling synchronous collection of data from all production elements and improving the comprehensiveness and accuracy of production process monitoring. It employs a networked data transmission architecture combining wired industrial bus and wireless IoT to ensure real-time and stable data transmission, eliminate data silos between processes, and achieve global sharing of production data. A three-tiered data processing architecture enables collaborative real-time edge control and cloud-based global optimization. The edge collaborative processing module completes on-site data preprocessing and local real-time control, improving system response speed. The global intelligent decision-making module builds a production model based on full-process data and generates scientifically sound optimization strategies.

[0017] The production process quality balance control unit integrates quality deviations from each process and inter-process transmission deviations to achieve synergistic optimization of process parameters throughout the entire process. This reduces the impact of raw material quality fluctuations and process errors on product quality, improving the stability of feed product quality. The equipment operation status health assessment unit quantitatively assesses equipment health levels based on multi-dimensional operating parameters, providing data support for equipment maintenance, identifying potential equipment failures in advance, extending equipment lifespan, and reducing unplanned downtime.

[0018] The end-to-end safety protection module is deployed at key nodes of the production line to monitor abnormal conditions such as over-temperature, over-pressure, and overload in real time, independently triggering safety protection actions to improve the safety of the production process. The finished product storage monitoring module, combined with networked data transmission, enables full lifecycle traceability management of finished products, comprehensively recording parameters of each process and finished product flow information, facilitating rapid location and handling of quality issues. The system as a whole achieves end-to-end networked monitoring and intelligent control of feed production and processing, improving the automation and intelligence level of the production process, maintaining stable production line operation, and ensuring continuous controllable product quality. Attached Figure Description

[0019] Figure 1This invention presents the overall operational architecture and business logic diagram of a networked monitoring and intelligent control system for the entire feed production and processing process. Figure 2 A diagram of a three-tiered data processing and intelligent decision-making architecture; Figure 3 A flowchart for quality balancing and coordinated control in production processes; Figure 4 This is a flowchart of the end-to-end monitoring and management process for raw materials and finished products. Figure 5 This is a logic diagram for the entire process of safety protection and health assessment. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0022] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.

[0023] Reference Figures 1 to 5A networked monitoring and intelligent control system for the entire feed production and processing process, comprising the following modules: The raw material inbound monitoring module is deployed at the raw material inlet and storage area to collect data on raw material type, moisture content, crude protein content, crude fiber content, impurity ratio, inbound weight, and storage environment temperature and humidity parameters. The crushing process monitoring module is deployed at the feed end and discharge end of the crusher to collect crushing speed, feed flow rate, crushing particle size, cavity temperature, motor current and equipment vibration parameters; The batching and mixing monitoring module is deployed at the batching scale and mixer to collect parameters such as batching accuracy, feeding sequence, mixing time, stirring speed, material uniformity and chamber pressure. The granulation and conditioning monitoring module is deployed at the conditioner and granulator to collect parameters such as conditioning temperature, conditioning moisture, steam pressure, granulation speed, die pressure and granulation rate. The cooling and screening monitoring module is deployed at the location of the cooler and the screening machine to collect parameters such as cooling air volume, cooling temperature, screening speed, finished product particle size, breakage rate and dust concentration. The finished product storage monitoring module is deployed in the finished product warehouse and outbound workstation to collect parameters such as finished product storage temperature and humidity, material level, outbound weight, packaging sealing and shelf life. The network data transmission module adopts a wired industrial bus and wireless Internet of Things architecture to realize real-time data interaction and remote transmission between various monitoring modules and processing modules; The edge collaborative processing module is deployed inside the control cabinet at the production site to complete on-site data preprocessing, abnormal data identification, and local real-time control command generation; The global intelligent decision-making module is deployed on a remote cloud server to integrate data from the entire process to build a production model, perform trend analysis, and generate global optimization strategies. The on-site control module is connected to the actuators of the crusher, mixer, granulator, cooler, and screening machine, respectively, and is used to adjust the equipment operating parameters according to control commands; The full-process safety protection module is deployed at key nodes throughout the production line to monitor conditions such as over-temperature, over-pressure, overload, material blockage, and excessive dust, and to execute safety protection actions.

[0024] This invention also includes a production process quality balancing and control unit, which is electrically connected to the global intelligent decision-making module and the on-site execution control module. This unit is used to calculate the optimal combination of process parameters based on the quality correlation of multiple processes. The calculation formula is as follows: ; in, The optimal control coefficient for the production process is dimensionless. For the first The quality weighting coefficient for each process step is dimensionless. For the first Real-time quality indicators for each process step, dimensionless. For the first The standard quality indicators for each process are dimensionless. This is the process correlation deviation coefficient, dimensionless. This represents the dimensionless deviation value for quality transfer between adjacent processes. The total number of production processes is dimensionless. It integrates the quality deviations of each process and the transfer deviations between processes to achieve synergistic optimization of quality parameters throughout the entire process and maintain the stability of feed product quality.

[0025] This invention also includes a device operation status health assessment unit, which is electrically connected to the edge collaborative processing module and the full-process security protection module. This unit is used to assess the device health level based on multi-dimensional operating parameters, and the calculation formula is as follows: ; in, These are equipment health assessment values, dimensionless. For the first The weighting coefficients of the class's runtime parameters are dimensionless. For the first Real-time runtime parameters, dimensionless. For the first Standard operating parameters, dimensionless. This is the temperature deviation weighting factor, expressed in degrees Celsius. This represents the temperature difference during continuous operation of the equipment, expressed in degrees Celsius. It represents the total number of categories of equipment operating parameters, dimensionless, and integrates the effects of equipment operating parameter deviations and temperature changes to achieve accurate quantitative assessment of equipment health status, providing data support for equipment maintenance and safety protection.

[0026] In this invention, the raw material warehousing monitoring module includes a raw material spectral rapid detection device, a moisture sensor, a weight sensor, a temperature and humidity sensor, and an RFID reader. The raw material spectral rapid detection device is used for non-contact rapid detection of the nutrient content of raw materials. The moisture sensor is used to collect the moisture value of raw materials in real time. The weight sensor is used to accurately measure the weight of raw materials entering the warehouse. The temperature and humidity sensor is used to collect the storage environment parameters of raw materials. The RFID reader is used to read the batch information and traceability code of raw materials. All detection data is uploaded to the edge collaborative processing module in real time to complete the full-element quality verification and information archiving of raw materials entering the warehouse.

[0027] In this invention, the crushing process monitoring module includes a speed sensor, a flow sensor, a particle size detection device, a temperature sensor, a current sensor, and a vibration sensor. The speed sensor collects the rotor speed of the crusher in real time, the flow sensor collects the feed flow rate of the crusher in real time, the particle size detection device detects the particle size distribution of the crushed material online, the temperature sensor collects the internal temperature of the crusher cavity, the current sensor collects the operating current of the crusher motor, and the vibration sensor collects the vibration amplitude of the equipment body. The edge processing module judges the crushing status in real time based on the collected data and synchronously adjusts the matching relationship between the crusher speed and the feed flow rate.

[0028] In this invention, the batching and mixing monitoring module includes a high-precision batching scale, a feeding sequence controller, a time relay, a speed detection device, a uniformity detection sensor, and a pressure sensor. The high-precision batching scale enables accurate metering and feeding of each component raw material. The feeding sequence controller controls the timing and interval of raw material feeding. The time relay records the actual running time of the mixer. The speed detection device collects the mixing speed of the mixer. The uniformity detection sensor detects the uniformity of the mixed material online. The pressure sensor collects the internal working pressure of the mixer. The global intelligent decision-making module optimizes the batching ratio and mixing process parameters based on the collected data.

[0029] In this invention, the pelleting conditioning monitoring module includes a temperature sensor, a moisture detector, a pressure sensor, a speed sensor, a die orifice pressure detection device, and a pelleting rate detection device. The temperature sensor collects the temperature of the material inside the conditioner, the moisture detector collects the moisture content of the material after conditioning, the pressure sensor collects the working pressure of the steam pipeline, the speed sensor collects the rotational speed of the pellet mill roller, the die orifice pressure detection device collects the pressure value of the material passing through the die orifice, the pelleting rate detection device calculates the pelleting ratio of feed pellets online, and the edge collaborative processing module dynamically adjusts the steam supply and pellet mill operating parameters based on real-time data.

[0030] In this invention, the cooling and screening monitoring module includes an airflow sensor, a temperature sensor, a speed sensor, a particle size screening device, a breakage rate detector, and a dust concentration sensor. The airflow sensor collects the airflow of the cooler, the temperature sensor collects the temperature of the material after cooling, the speed sensor collects the operating speed of the screening machine, the particle size screening device screens the particle size distribution of the finished feed, the breakage rate detector counts the breakage ratio of the particles, and the dust concentration sensor collects the dust content at the production site. The on-site execution control module adjusts the cooling airflow and the speed of the screening machine according to the monitoring data to maintain the quality of the finished particles and the safety of the production environment.

[0031] In this invention, the finished product storage monitoring module includes a storage temperature and humidity sensor, a continuous level gauge, an outbound weighing sensor, a packaging sealing detection device, and a time recorder. The storage temperature and humidity sensor monitors the environmental parameters of the finished product storage environment in real time, the continuous level gauge collects the material level height inside the silo, the outbound weighing sensor measures the weight of the finished product leaving the warehouse, the packaging sealing detection device detects the sealing status of the finished product packaging, the time recorder records the time of entry into the warehouse and the shelf life information of the finished product, and the network data transmission module synchronously uploads the finished product data to the cloud to realize the full life cycle traceability management of the finished product.

[0032] In this invention, a three-tiered data processing architecture is formed by a networked data transmission module, an edge collaborative processing module, and a global intelligent decision-making module. On-site monitoring data is first filtered and denoised, standardized, and real-time anomaly determined by the edge collaborative processing module. The determination results are then uploaded to the global intelligent decision-making module via the networked data transmission module. The global intelligent decision-making module establishes a production process optimization model based on historical and real-time data from the entire process, generating long-term optimization strategies and parameter adjustment schemes. These schemes are then transmitted to the edge collaborative processing module and converted into specific control instructions. The on-site execution and control module adjusts equipment parameters according to these instructions. The full-process safety protection module synchronously receives status signals transmitted from the three-tiered architecture and independently triggers safety protection actions in abnormal states to maintain stable production line operation and controllable product quality.

[0033] The feed production and processing end-to-end networked monitoring and intelligent control system of this invention uses multi-dimensional data collection throughout the entire process, three-level collaborative data processing, balanced production quality control, intelligent equipment health assessment, and end-to-end safety protection as its core technologies to construct an integrated intelligent control system covering raw material warehousing to finished product delivery. This system is adaptable to feed production scenarios of different scales and categories, and can solve the problems of severe data silos, delayed process parameter adjustments, large product quality fluctuations, passive equipment maintenance, and insufficient safety protection in traditional feed production. The invention will be further described in detail below with reference to two specific embodiments.

[0034] Example 1: This embodiment is applied to a large-scale livestock and poultry compound feed production base. The base has multiple parallel production lines and mainly produces compound feed for pigs, chickens and other livestock and poultry. The raw materials cover a variety of categories such as corn, soybean meal, wheat bran and mineral additives. The daily output is large, the production continuity requirement is high, and the requirements for product quality stability and production safety control are strict.

[0035] The system adopts a distributed deployment architecture, with dedicated monitoring modules deployed for each production process. The raw material receiving monitoring module installs a rapid spectral detection device and a moisture sensor at the raw material inlet, deploys a temperature and humidity sensor array in the raw material storage area, and installs a weight sensor and RFID reader at the weighbridge. Upon raw material arrival, the rapid spectral detection device scans the raw material non-contactly, detecting moisture, crude protein, crude fiber content, and impurity ratio in real time. The weight sensor measures the weight upon arrival, and the RFID reader records the raw material batch and traceability information. All data is synchronously uploaded to the edge collaborative processing module to complete raw material quality verification and information archiving.

[0036] The crushing process monitoring module installs a flow sensor at the feed end of each crusher, a particle size detection device at the discharge end, a speed sensor on the rotor, a temperature sensor inside the chamber, a current sensor at the motor terminals, and a vibration sensor on the machine base. The edge processing module collects these parameters in real time and dynamically adjusts the crusher speed and feed flow rate based on changes in particle size and chamber temperature via the on-site control module, maintaining stable crushing efficiency and particle size.

[0037] The ingredient mixing monitoring module is equipped with a high-precision batching scale installed below the batching silo, a feeding sequence controller at the feeding port, a speed detection device on the mixer's main shaft, and internal uniformity and pressure sensors. A time relay is connected to the control circuit. The global intelligent decision-making module automatically optimizes the ingredient ratio based on the raw material nutrient composition analysis results. The feeding sequence controller controls the interval and order of ingredient addition according to a preset timing sequence. The time relay precisely controls the mixing time, and the uniformity sensor provides real-time feedback on the mixing effect, ensuring uniform material mixing.

[0038] The pelletizing and conditioning monitoring module installs temperature sensors and moisture detectors inside the conditioner, pressure sensors in the steam pipeline, speed sensors on the pellet mill rollers, die pressure detection devices at the die holes, and pellet forming rate detection devices at the discharge port. The edge processing module dynamically adjusts the steam valve opening based on the temperature and moisture parameters of the conditioned material to control the steam supply. Simultaneously, it adjusts the pellet mill speed based on the die pressure and pellet forming rate to ensure pellet forming quality.

[0039] The cooling and screening monitoring module is equipped with an airflow sensor at the air inlet of the cooler, a temperature sensor inside, a speed sensor on the main shaft of the screening machine, a particle size screening device and a breakage rate detector at the discharge end, and a dust concentration sensor on the top of the production workshop. The on-site control module adjusts the cooling airflow according to the temperature of the cooled material, adjusts the screening machine speed according to the particle size distribution of the finished product, and automatically activates the workshop ventilation and dust removal equipment when the dust concentration exceeds the standard.

[0040] The finished product storage monitoring module is equipped with continuous level gauges and temperature and humidity sensors inside the finished product silo, and outbound weighing sensors and packaging seal detection devices at the outbound workstations. The control system is connected to a time recorder. When finished products enter the warehouse, the entry time and shelf life information are automatically recorded. During storage, temperature, humidity, and material level are monitored in real time. When products leave the warehouse, weight measurement and packaging seal detection are completed. All finished product data is synchronized to the cloud via a networked data transmission module, enabling full lifecycle traceability.

[0041] The networked data transmission module uses wired industrial Ethernet to connect fixed monitoring equipment and control cabinets, and wireless IoT nodes to connect mobile detection devices and sensors in remote areas, building a low-latency, highly reliable transmission network. The edge collaborative processing module is deployed in the industrial control cabinet on the production floor, prioritizing filtering, noise reduction, standardization, and real-time anomaly detection of on-site data. For minor anomalies, it directly generates control commands for local adjustment. The global intelligent decision-making module is deployed on a remote cloud server, integrating historical and real-time data from the entire production line to establish a production process optimization model, generate long-term optimization strategies, and download them to the edge. The full-process safety protection module deploys monitoring devices at key nodes in each process, monitoring for over-temperature, over-pressure, overload, material blockage, and excessive dust levels in real time. When an anomaly occurs, it independently triggers equipment shutdown and audible / visual alarms.

[0042] The production process quality balance control unit works in conjunction with the global intelligent decision-making module to collect quality indicators for each process in real time, analyze quality transfer deviations between processes, and collaboratively adjust process parameters for each process to compensate for quality fluctuations in the preceding process. The equipment operation status health assessment unit continuously collects equipment operating parameters, combines the impact of temperature changes to quantitatively assess the equipment health level, identify potential equipment failures in advance, and generate maintenance recommendations.

[0043] Table 1: Comparison of Management and Control Effects of Large-Scale Livestock and Poultry Feed Production Bases Table 1 presents the application effects of this invention in large-scale livestock and poultry feed production bases through five core indicators. The comprehensiveness of production data collection increased from 62% to 95%, thanks to a multi-dimensional monitoring module covering the entire process, simultaneously collecting equipment operation, process parameters, and quality indicator data, eliminating data blind spots. The product quality pass rate increased from 85% to 96%, relying on the production process quality balancing control unit to achieve collaborative optimization of process parameters across processes, reducing the impact of raw material fluctuations and process errors. The equipment operation reliability rate increased from 88% to 97%, relying on a multi-dimensional equipment health assessment mechanism to identify potential faults in advance, transforming passive maintenance into proactive maintenance. The safety protection response time was shortened from 120 seconds to 15 seconds, thanks to a full-process linkage protection mechanism that can quickly trigger protection actions under abnormal conditions. The automation rate of production control increased from 45% to 92%, achieving collaboration between edge real-time control and cloud-based global optimization through a three-level data processing architecture, reducing manual intervention.

[0044] Example 2: This embodiment is applied to a special aquatic feed production workshop, which mainly produces special aquatic feeds such as fish and shrimp. The raw materials include fine components such as fish meal, shrimp meal, oil, and vitamin additives. The product formula is complex and has extremely high requirements for ingredient accuracy, particle hardness, and stability in water. There are many production batches and frequent switching, which requires strict flexibility in the system.

[0045] The system is adapted to the characteristics of specialty feed production. The raw material warehousing monitoring module uses a high-precision spectral rapid detection device to accurately detect the nutritional components and freshness indicators of high-priced raw materials such as fishmeal. The temperature and humidity sensors in the storage area are of high precision to strictly control the storage environment of easily oxidized raw materials. When raw materials are received, the system automatically compares the raw material detection data with the formula requirements. Raw materials that do not meet the standards automatically trigger an alarm and are prohibited from being stored and used.

[0046] The grinding process monitoring module, designed for the high hardness and fine particle size requirements of special feed raw materials, employs a high-sensitivity particle size detection device and vibration sensor to monitor the particle size distribution and equipment vibration status in real time. The edge processing module automatically adjusts the grinding mill's operating parameters based on the grinding characteristics of different raw materials. For materials prone to sticking to the walls, such as fishmeal, it appropriately increases the rotor speed and controls the feed flow rate to prevent cavity blockage and uneven particle size.

[0047] The ingredient mixing monitoring module uses a higher-precision micro-scale feed scale to achieve accurate metering of trace additives. The feeding sequence controller supports rapid switching between multiple batch formulas. Multiple uniformity sensors are installed inside the mixer to ensure uniform dispersion of trace additives in the materials. The global intelligent decision-making module stores a database of various aquatic feed production process parameters. When switching production batches, it can automatically recall the corresponding formula and process parameters, eliminating the need for manual adjustments.

[0048] The pelleting and conditioning monitoring module addresses the water stability requirements of aquatic feed by installing multiple temperature sensors and a moisture meter within the conditioner to precisely control conditioning temperature and moisture content. The pellet mill employs a dual-roller speed synchronous detection device to ensure smooth roller operation, and a die pressure detection device monitors die wear in real time, promptly prompting die replacement. The edge processing module dynamically adjusts steam conditioning time and pelleting pressure based on the formulation characteristics of different aquatic feeds, improving pellet hardness and water stability.

[0049] The cooling and screening monitoring module employs a frequency converter-controlled cooling fan and a multi-layer vibrating screen. Airflow and temperature sensors provide real-time feedback on the cooling effect. The on-site control module automatically adjusts the cooling airflow and cooling time based on particle size and moisture content. The multi-layer screen can simultaneously separate finished particles of different sizes to meet the needs of aquatic animals at different growth stages. The dust concentration sensor features an explosion-proof design, monitoring the workshop dust content in real time to ensure production safety.

[0050] The finished product storage monitoring module, designed for the short shelf life of specialty feeds, incorporates an automatic environmental control function. When temperature and humidity exceed preset ranges, dehumidification and ventilation equipment are automatically activated. The packaging sealing detection device utilizes vacuum detection principles to accurately identify micro-leakage in the packaging, preventing finished products from becoming damp and spoiling. A time recorder automatically tracks the storage time of the finished product and issues an automatic warning when it approaches its expiration date.

[0051] The network data transmission module employs an industrial-grade wireless gateway to ensure the continuity and accuracy of data transmission during multi-batch switching. The edge collaborative processing module possesses multi-formula parallel processing capabilities, enabling simultaneous management of different batch production tasks across multiple production lines. The global intelligent decision-making module establishes a specialized production model for specialty feeds, automatically optimizing process parameters and improving product quality by considering the characteristics of different raw materials and seasonal variations. The end-to-end safety protection module, addressing the high oil content characteristic of specialty feed production, adds oil temperature monitoring and fire early warning functions to further enhance production safety.

[0052] The production process quality balance control unit, addressing the complex formulations and process sensitivity of specialty feeds, refines the quality weight coefficients for each process, focusing on controlling ingredient accuracy and conditioning parameters to ensure product quality meets the requirements of specialty aquaculture. The equipment operation status health assessment unit, targeting production modes with frequent start-stop cycles, adds an assessment dimension for equipment start-stop impact, accurately assessing equipment health status and rationally scheduling maintenance.

[0053] Table 2: Comparison of Control Effects in Aquatic Specialty Feed Production Workshops Table 2 illustrates the advantages of this invention in aquatic specialty feed production workshops through five core indicators. The relative error of micro-feeding is reduced from ±2.5% to ±0.3%, thanks to high-precision batching scales and precise feeding control, ensuring accurate addition of micro-additives. Single-batch switching time is shortened from 120 minutes to 25 minutes, benefiting from the formula parameter library and automatic recall function, reducing manual adjustment time and enabling rapid production transition. The quality compliance rate of specialty feeds increases from 82% to 94%, meeting the requirements of aquatic feeds for particle hardness and water stability through targeted process parameter optimization and quality balance control. The compliance rate of storage temperature and humidity increases from 75% to 96%, relying on automatic temperature and humidity control and shelf-life warning to prevent easily oxidized raw materials and finished product deterioration. The number of varieties supported by a single system increases from 8 to 35, adapting to multi-variety, small-batch specialty feed production modes through parallel processing of multiple formulas and adaptive parameter adjustment.

[0054] Reference Figure 1 This diagram illustrates the synergistic relationship between material flow and information flow throughout the entire feed production process. At the center are the three core control levels: edge processing, global decision-making, and on-site execution. Material flow proceeds in the sequence of "raw material warehousing—crushing—mixing—granulation and conditioning—cooling and screening—finished product storage." Simultaneously, each monitoring module aggregates real-time data to the edge layer for rapid response and uploads it to the cloud for global optimization. The resulting control commands are ultimately fed back to the various execution mechanisms on the production line, achieving closed-loop control of the entire process.

[0055] Reference Figure 2 This diagram illustrates the system's data processing logic using a hierarchical structure. The bottom layer consists of a sensor network distributed throughout the production line, responsible for collecting all data elements. The middle layer comprises edge collaborative processing modules deployed on-site, performing filtering and noise reduction, data standardization, and local real-time anomaly detection. The top layer is the cloud server, which builds a production process model based on historical data from the entire process and distributes optimization strategies. This architecture achieves a highly efficient collaborative model of "real-time response at the edge, complex decision-making in the cloud."

[0056] Reference Figure 3 This diagram highlights the quality correlation and feedback control mechanism between various processes. The system not only monitors the quality indicators of individual processes but also pays attention to quality transfer deviations between adjacent processes. For example, in the grinding process, the system dynamically adjusts the rotation speed according to the needs of subsequent ingredient mixing; in the pelleting and conditioning stage, it controls the steam supply in real time based on the moisture content and temperature after conditioning. Through this cross-process collaboration, the system can calculate the optimal combination of process parameters to maintain the stability of the final feed product quality.

[0057] Reference Figure 4This diagram illustrates the system's quality verification and traceability logic at both ends of the production line. At the warehousing end, rapid spectral detection and RFID technology are used to ensure the authenticity of raw material composition and origin. At the finished product end, the focus is on material level control, packaging sealing inspection, and shelf-life recording. Through a networked data transmission module, data from both ends converge in the cloud, forming a full lifecycle traceability chain covering raw material batches, processing parameters, and outbound status.

[0058] Reference Figure 5 This diagram illustrates how the system ensures production line safety through multi-dimensional parameters. The safety protection module monitors key risk points such as over-temperature, over-pressure, overload, material blockage, and dust concentration in real time. The health assessment unit combines equipment operating temperature difference, current deviation, and vibration frequency to perform a graded quantitative health assessment of the equipment. Once an abnormal state is detected, the system can trigger safety protection actions independently of business logic, such as emergency shutdown or dust removal, thereby ensuring a safe production environment and long-term equipment operation.

[0059] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A networked monitoring and intelligent control system for the entire feed production and processing process, characterized in that, Includes the following modules: The raw material warehousing monitoring module is used to collect data on raw material type, moisture content, crude protein content, crude fiber content, impurity ratio, warehousing weight, and storage environment temperature and humidity parameters. The pulverization process monitoring module is used to collect pulverization speed, feed flow rate, pulverized particle size, cavity temperature, motor current and equipment vibration parameters; The ingredient mixing monitoring module is used to collect parameters such as ingredient accuracy, feeding sequence, mixing time, stirring speed, material uniformity, and chamber pressure. The granulation and conditioning monitoring module is used to collect parameters such as conditioning temperature, conditioning moisture, steam pressure, granulation speed, die pressure, and granulation rate. The cooling and screening monitoring module is used to collect parameters such as cooling air volume, cooling temperature, screening speed, finished product particle size, breakage rate and dust concentration. The finished product storage monitoring module is used to collect parameters such as temperature and humidity of finished product storage, material level, weight of outbound products, packaging sealing and shelf life. The network data transmission module adopts a wired industrial bus and wireless Internet of Things architecture to realize real-time data interaction and remote transmission between various monitoring modules and processing modules; The edge collaborative processing module is used to complete on-site data preprocessing, abnormal data identification, and local real-time control command generation; The global intelligent decision-making module is used to integrate data from the entire process to build production models, perform trend analysis, and generate global optimization strategies. The on-site control module is connected to the actuators of the crusher, mixer, granulator, cooler, and screening machine, respectively, and is used to adjust the equipment operating parameters according to control commands; The full-process safety protection module is used to monitor conditions such as over-temperature, over-pressure, overload, material blockage, and excessive dust, and to execute safety protection actions.

2. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, It also includes a production process quality balance control unit, which calculates the optimal combination of process parameters based on the quality correlation of multiple processes. The calculation formula is as follows: ； in, This is the optimal control coefficient for the production process. For the first Quality weighting coefficient of each process For the first Real-time quality indicators for each process step. For the first Standard quality indicators for each process This is the process correlation deviation coefficient. This represents the quality transfer deviation value between adjacent processes. This represents the total number of production processes.

3. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, It also includes a device health assessment unit, which evaluates the device health level based on multi-dimensional operating parameters. The calculation formula is as follows: ； in, This is the equipment health assessment value. For the first Weighting coefficients of class runtime parameters, For the first Real-time runtime parameters for the class For the first Class-standard operating parameters, This is the temperature deviation weighting coefficient. This refers to the temperature difference value during continuous operation of the equipment. This represents the total number of categories of equipment operating parameters.

4. The feed production and processing end-to-end networked monitoring and intelligent control system according to claim 1, characterized in that, The raw material warehousing monitoring module includes a raw material spectral rapid detection device, a moisture sensor, a weight sensor, a temperature and humidity sensor, and an RFID reader. The raw material spectral rapid detection device is used for non-contact rapid detection of the nutrient content of raw materials. The moisture sensor is used to collect the moisture value of raw materials in real time. The weight sensor is used to accurately measure the weight of raw materials entering the warehouse. The temperature and humidity sensor is used to collect the storage environment parameters of raw materials. The RFID reader is used to read the batch information and traceability code of raw materials. All detection data is uploaded to the edge collaborative processing module in real time to complete the full-element quality verification and information archiving of raw materials entering the warehouse.

5. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, The crushing process monitoring module includes a speed sensor, a flow sensor, a particle size detection device, a temperature sensor, a current sensor, and a vibration sensor. The speed sensor collects the real-time operating speed of the crusher rotor, the flow sensor collects the real-time feed flow of the crusher, the particle size detection device detects the particle size distribution of the crushed material online, the temperature sensor collects the internal temperature of the crusher cavity, the current sensor collects the operating current of the crusher motor, and the vibration sensor collects the vibration amplitude of the equipment body. The edge processing module judges the crushing status in real time based on the collected data and synchronously adjusts the matching relationship between the crusher speed and the feed flow.

6. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, The batching and mixing monitoring module includes a high-precision batching scale, a feeding sequence controller, a time relay, a speed detection device, a uniformity detection sensor, and a pressure sensor. The high-precision batching scale enables accurate metering and feeding of each component raw material. The feeding sequence controller controls the timing and interval of raw material feeding. The time relay records the actual running time of the mixer. The speed detection device collects the mixing speed of the mixer. The uniformity detection sensor detects the uniformity of the mixed material online. The pressure sensor collects the internal working pressure of the mixer. The global intelligent decision-making module optimizes the batching ratio and mixing process parameters based on the collected data.

7. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, The pelleting and conditioning monitoring module includes a temperature sensor, a moisture analyzer, a pressure sensor, a speed sensor, a die pressure detection device, and a pelleting rate detection device. The temperature sensor collects the temperature of the material inside the conditioner, the moisture analyzer collects the moisture content of the material after conditioning, the pressure sensor collects the working pressure of the steam pipeline, the speed sensor collects the speed of the pellet mill rollers, the die pressure detection device collects the pressure value of the material passing through the die, and the pelleting rate detection device calculates the proportion of feed pellets formed online. The edge processing module dynamically adjusts the steam supply and pellet mill operating parameters based on real-time data.

8. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, The cooling and screening monitoring module includes an airflow sensor, a temperature sensor, a speed sensor, a particle size screening device, a breakage rate detector, and a dust concentration sensor. The airflow sensor collects the airflow of the cooler, the temperature sensor collects the temperature of the material after cooling, the speed sensor collects the operating speed of the screening machine, the particle size screening device screens the particle size distribution of the finished feed, the breakage rate detector counts the breakage ratio of particles, and the dust concentration sensor collects the dust content at the production site. The on-site execution control module adjusts the cooling airflow and the speed of the screening machine based on the monitoring data.

9. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, The finished product storage monitoring module includes a storage temperature and humidity sensor, a continuous level gauge, an outbound weighing sensor, a packaging sealing detection device, and a time recorder. The storage temperature and humidity sensor monitors the environmental parameters of the finished product storage in real time, the continuous level gauge collects the material level height inside the silo, the outbound weighing sensor measures the weight of the finished product leaving the warehouse, the packaging sealing detection device detects the sealing status of the finished product packaging, the time recorder records the time of entry into the warehouse and the shelf life information of the finished product, and the network data transmission module synchronously uploads the finished product data to the cloud.

10. The feed production and processing network monitoring and intelligent control system according to claim 1, characterized in that, The network data transmission module, the edge collaborative processing module, and the global intelligent decision-making module form a three-level data processing architecture; The edge collaborative processing module filters and reduces noise, standardizes data, and performs real-time anomaly detection on the on-site monitoring data. The detection results are uploaded to the global intelligent decision-making module via the network data transmission module. The global intelligent decision-making module establishes a production process optimization model based on historical and real-time data from the entire process, generates long-term optimization strategies and parameter adjustment schemes, and transmits them to the edge collaborative processing module to be converted into specific control commands. The on-site execution and control module adjusts equipment parameters according to these commands. The full-process safety protection module receives status signals transmitted by the three-level architecture and independently triggers safety protection actions in abnormal states.

Images