Intelligent management system for feed granulation operation and quality based on big data analysis

Abstract

The present application relates to the technical field of feed production, and discloses a feed granulation operation and quality intelligent management system based on big data analysis. The system comprises a distributed sensing network, an intelligent process decision module, a multi-actuator collaborative regulation module and a full-chain data traceability platform. The distributed sensing network is provided with multiple sets of high-precision sensors at a to-be-granulated bin, an outlet of a conditioner, an outlet of a cooler and a post-spraying station to collect material moisture, temperature, pressure and current signals in real time. The present application solves the problems of high energy consumption, quality fluctuation, low department collaboration efficiency and cost control difficulty caused by reliance on manual experience in traditional feed production, realizes collaborative optimization of six core indexes of granulation temperature, moisture, hardness, pulverization rate, production efficiency and post-spraying effect, and improves the intelligence, standardization and economic benefits of feed production.

Description

Technical Field

[0001] This invention belongs to the field of feed processing automation and intelligent manufacturing technology, specifically relating to an intelligent management system for feed pelleting operation and quality based on big data analysis. Background Technology

[0002] Pelleted feed is a core input in modern animal husbandry and aquaculture, and its quality directly affects animal growth performance and economic benefits. Currently, there are some long-standing and unresolved core issues in pelleted feed production.

[0003] Traditional feed production has long relied on the experience and judgment of operators. Control of key process parameters such as pelleting temperature and moisture content often varies from person to person and shift to shift, leading to significant fluctuations in product quality. Conflicting performance targets among production, quality control, and technology departments frequently result in information silos and internal bottlenecks. While partial automation can improve individual processes, it lacks end-to-end coordination, failing to achieve comprehensive optimization of quality, energy consumption, and efficiency. Moisture control relies on manual estimation, easily causing intangible losses; and delayed quality inspection cannot provide real-time guidance for production adjustments. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the existing defects and provide a feed pelleting operation and quality intelligent management system based on big data analysis to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a smart management system for feed pelleting operation and quality based on big data analysis, comprising:

[0006] A distributed sensing network is used to collect material status parameters and equipment operating parameters at multiple key nodes in the entire feed pelleting process in real time.

[0007] The process intelligent decision-making module is communicatively connected to the distributed sensing network and is used to generate multi-objective collaborative optimization control strategies based on the collected parameters, the preset process knowledge base and the adaptive learning model.

[0008] The multi-actuator coordinated adjustment module is communicatively connected to the process intelligent decision module and is used to coordinately adjust the operating parameters of the feeding system, steam supply system, cooling system and post-coating system according to the control strategy.

[0009] The full-chain data traceability platform communicates with the process intelligent decision-making module to realize the recording, analysis, visualization, and remote monitoring of data throughout the entire production process.

[0010] Furthermore, the distributed sensing network includes:

[0011] The first sensing unit, located in the granulation bin, is used to collect the initial moisture and temperature of the material before conditioning.

[0012] The second sensing unit located at the outlet of the conditioner is used to collect the instantaneous moisture, temperature and steam pressure of the material after conditioning;

[0013] The third sensing unit, located at the outlet of the cooler, is used to collect the moisture content, temperature, and main motor current of the pellet mill after cooling.

[0014] The fourth sensing unit, located at the post-coating station, is used to collect the surface grease distribution and temperature of the finished product after coating.

[0015] Furthermore, the intelligent process decision-making module includes:

[0016] The process knowledge base stores a set of target process parameters based on feed type, raw material formulation and seasonal environmental factors, including target pelleting temperature, target moisture range, target hardness, pulverization rate threshold, maximum allowable current and post-coating process parameters.

[0017] The adaptive learning model dynamically optimizes control parameters and strategies based on historical production data, real-time operating data, and feedback adjustment effects to adapt to equipment wear, changes in raw material characteristics, and environmental fluctuations.

[0018] Furthermore, the multi-actuator coordinated adjustment module includes:

[0019] The feeding speed control unit is used to adjust the feeder speed according to the strategy to control the production capacity and the time it takes for the material to pass through the conditioner.

[0020] The precise steam supply unit is used to adjust the opening and pressure of the steam valve according to the strategy, so as to achieve rapid response and stable control of the granulation temperature.

[0021] The cooling air volume and material level coordinated adjustment unit is used to adjust the fan frequency and discharge mechanism of the cooler according to the strategy, so as to optimize the cooling efficiency and finished product moisture content.

[0022] The post-spraying temperature and flow rate adjustment unit is used to adjust the heating temperature and spray flow rate of the spraying oil according to the strategy.

[0023] Furthermore, the intelligent process decision-making module adopts a three-point closed-loop linkage algorithm of "moisture-temperature-current" to adjust the steam supply and feeding speed in real time based on the moisture data of the first, second and third sensing units, so as to ensure that the moisture content of the finished product after cooling meets the preset target and is not lower than the moisture content before conditioning, thereby achieving precise control of moisture balance.

[0024] Furthermore, the three-point closed-loop linkage algorithm improves production efficiency by monitoring the downward trend of the main motor current of the pellet mill. When the current decreases significantly, it automatically instructs the feeding speed regulation execution unit to increase the speed, thereby achieving a safe and efficient increase in production line output.

[0025] Furthermore, the system supports multiple automated production modes, including standard quality mode, high-yield and energy-saving mode, nighttime anti-blocking mode, and new product debugging mode, which users can switch with one click according to production plans and market demands.

[0026] Furthermore, the full-chain data traceability platform has cloud data synchronization capabilities, supporting real-time viewing of production reports, energy consumption analysis, quality trends, and equipment status via web pages and mobile apps. The report content covers electricity consumption per ton, gas consumption per ton, granulation temperature pass rate, moisture control standard deviation, production efficiency, and formula cost correlation analysis.

[0027] Furthermore, the system also includes a remote diagnostic and optimization service module, which can receive algorithm updates, fault warning reports, and process parameter packages optimized for specific formulations from the cloud service center via a secure network connection.

[0028] A control method for a feed pelleting operation and quality intelligent management system based on big data analysis includes the following steps:

[0029] Step S1: System initialization, select feed category according to production task, and load corresponding process parameter set;

[0030] Step S2: The distributed sensing network collects material and equipment data from key nodes throughout the entire process in real time;

[0031] Step S3: The intelligent process decision-making module calculates the deviation between the current state and the target state based on the collected data, the process knowledge base and the adaptive learning model, and generates collaborative control instructions that include multiple variables such as feeding, steam, cooling and post-spraying.

[0032] Step S4: The multi-actuator collaborative adjustment module synchronously executes control commands and provides real-time feedback on the execution effect, forming a closed-loop control;

[0033] Step S5: The full-chain data traceability platform records and analyzes data throughout the entire process, generates visual reports, and supports production management decisions and remote supervision.

[0034] Compared with existing technologies, this invention provides a smart management system for feed pelleting operations and quality based on big data analysis, which has the following beneficial effects:

[0035] This invention constructs a full-process data perception and intelligent decision-making system, transforming manual experience into standardized and reproducible process models, fundamentally stabilizing key quality indicators. It breaks down data barriers between production, quality control, and technology departments, supporting collaborative operations with unified and objective real-time data and resolving conflicting objectives. The system achieves closed-loop, interconnected control across multiple stages, from conditioning and pelleting to cooling and coating, simultaneously optimizing quality, energy consumption, and efficiency, avoiding overall losses caused by localized optimization. Moisture is precisely dynamically balanced, reducing unexpected losses; real-time traceability of quality data shifts management from post-production inspection to process prevention. This invention not only improves the standardization and economic efficiency of production but also drives the deep transformation of feed production towards digitalization and intelligence. Attached Figure Description

[0036] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention, but do not constitute a limitation thereof. In the drawings:

[0037] Figure 1 This is a diagram of the overall system architecture proposed in this invention;

[0038] Figure 2 This is a schematic diagram of the distributed sensing network proposed in this invention;

[0039] Figure 3 This is a schematic diagram of the intelligent process decision-making module proposed in this invention;

[0040] Figure 4 This is a schematic diagram of the multi-actuator coordinated adjustment module proposed in this invention. Detailed Implementation

[0041] 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.

[0042] Please see Figure 1-4 This invention provides a technical solution: an intelligent management system for feed pelleting operation and quality based on big data analysis, comprising:

[0043] A distributed sensing network is used to collect material status parameters and equipment operating parameters at multiple key nodes in the entire feed pelleting process in real time.

[0044] The process intelligent decision-making module communicates with the distributed sensing network and is used to generate multi-objective collaborative optimization control strategies based on the collected parameters, the preset process knowledge base and the adaptive learning model.

[0045] The multi-actuator coordinated adjustment module communicates with the process intelligent decision module and is used to coordinately adjust the operating parameters of the feeding system, steam supply system, cooling system and post-coating system according to the control strategy.

[0046] The full-chain data traceability platform communicates and connects with the process intelligent decision-making module to realize the recording, analysis, visualization, and remote monitoring of data throughout the entire production process.

[0047] In this invention, preferably, the distributed sensing network includes:

[0048] The first sensing unit, located in the granulation bin, is used to collect the initial moisture and temperature of the material before conditioning.

[0049] The second sensing unit located at the outlet of the conditioner is used to collect the instantaneous moisture, temperature and steam pressure of the material after conditioning;

[0050] The third sensing unit, located at the outlet of the cooler, is used to collect the moisture content, temperature, and main motor current of the pellet mill after cooling.

[0051] The fourth sensing unit, located at the post-coating station, is used to collect the surface grease distribution and temperature of the finished product after coating.

[0052] In this invention, preferably, the intelligent process decision-making module includes:

[0053] The process knowledge base stores a set of target process parameters based on feed type, raw material formulation and seasonal environmental factors, including target pelleting temperature, target moisture range, target hardness, pulverization rate threshold, maximum allowable current and post-coating process parameters.

[0054] The adaptive learning model dynamically optimizes control parameters and strategies based on historical production data, real-time operating data, and feedback adjustment effects to adapt to equipment wear, changes in raw material characteristics, and environmental fluctuations.

[0055] In this invention, preferably, the multi-actuator coordinated adjustment module includes:

[0056] The feeding speed control unit is used to adjust the feeder speed according to the strategy to control the production capacity and the time it takes for the material to pass through the conditioner.

[0057] The precise steam supply unit is used to adjust the opening and pressure of the steam valve according to the strategy, so as to achieve rapid response and stable control of the granulation temperature.

[0058] The cooling air volume and material level coordinated adjustment unit is used to adjust the fan frequency and discharge mechanism of the cooler according to the strategy, so as to optimize the cooling efficiency and finished product moisture content.

[0059] The post-spraying temperature and flow rate adjustment unit is used to adjust the heating temperature and spray flow rate of the spraying oil according to the strategy.

[0060] In this invention, preferably, the process intelligent decision-making module adopts a three-point closed-loop linkage algorithm of "moisture-temperature-current" to adjust the steam supply and feeding speed in real time according to the moisture data of the first, second and third sensing units, so as to ensure that the moisture content of the finished product after cooling meets the preset target and is not lower than the moisture content before conditioning, thereby achieving precise control of moisture balance.

[0061] In this invention, preferably, the three-point closed-loop linkage algorithm improves production efficiency by monitoring the decreasing trend of the main motor current of the pellet mill. When the current decreases significantly, it automatically instructs the feeding speed regulation execution unit to increase the speed, thereby achieving a safe and efficient increase in production line output.

[0062] In this invention, preferably, the system supports multiple automated production modes, including standard quality mode, high-yield and energy-saving mode, nighttime anti-blockage mode, and new product debugging mode, which users can switch with one click according to production plans and market demands.

[0063] In this invention, preferably, the full-chain data traceability platform has cloud data synchronization function, which supports real-time viewing of production reports, energy consumption analysis, quality trends and equipment status through web page and mobile APP. The report content covers electricity consumption per ton, gas consumption per ton, granulation temperature qualification rate, moisture control standard deviation, production efficiency and formula cost correlation analysis.

[0064] In this invention, preferably, the system also includes a remote diagnostic and optimization service module, which can receive algorithm updates, fault warning reports, and process parameter packages optimized for specific formulations from a cloud service center via a secure network connection.

[0065] A control method for a feed pelleting operation and quality intelligent management system based on big data analysis includes the following steps:

[0066] Step S1: System initialization, select feed category according to production task, and load corresponding process parameter set;

[0067] Step S2: The distributed sensing network collects material and equipment data from key nodes throughout the entire process in real time;

[0068] Step S3: The intelligent process decision-making module calculates the deviation between the current state and the target state based on the collected data, the process knowledge base and the adaptive learning model, and generates collaborative control instructions that include multiple variables such as feeding, steam, cooling and post-spraying.

[0069] Step S4: The multi-actuator collaborative adjustment module synchronously executes control commands and provides real-time feedback on the execution effect, forming a closed-loop control;

[0070] Step S5: The full-chain data traceability platform records and analyzes data throughout the entire process, generates visual reports, and supports production management decisions and remote supervision.

[0071] Example 1: In the integrated application of a large-scale poultry feed production enterprise, the enterprise has multiple automated feed production lines, mainly producing pelleted feed for poultry such as broilers and laying hens. Faced with fierce market competition and increasing cost pressure in the industry, the enterprise urgently needs to achieve refined management of the production process and effective control of energy consumption through technological upgrades.

[0072] This system was fully deployed on the company's typical pelleted feed production line. First, based on the material characteristics and process requirements of its main product, broiler fattening feed, the system's process knowledge base was used to initially configure the corresponding target process parameter set, including key indicators such as target pelleting temperature, finished product moisture range, hardness, and pulverization rate threshold. Key sensing units of the distributed sensing network were precisely installed at the pelleting hopper, conditioner outlet, cooler outlet, and post-coating station, enabling real-time, high-frequency acquisition of material moisture, temperature, pressure, and equipment current signals throughout the entire process from raw materials to finished products.

[0073] After a short period of data accumulation and initial training of the adaptive learning model, the system quickly completed the modeling and calibration of the specific production line equipment characteristics and raw material conditions. Once put into formal operation, the system demonstrated significant application effects. Based on real-time collected data and preset targets in the process knowledge base, the intelligent process decision-making module dynamically coordinated the feeding speed and steam supply through a three-point closed-loop linkage algorithm of "moisture-temperature-current," achieving a precise balance in moisture migration during the conditioning and cooling processes. This significantly narrowed the fluctuation range of finished product moisture content, maintaining it stably within the preset target range, effectively reducing weight loss or quality degradation caused by improper moisture control.

[0074] Meanwhile, the multi-actuator coordinated adjustment module coordinates and controls the feeder, steam valve, cooling fan and post-coating unit according to the decision instructions. This not only ensures that the core quality indicators are consistently met, but also automatically and gradually increases the feeding speed by intelligently identifying the stable downward trend of the main motor current of the pellet mill, while ensuring equipment safety. This unlocks the potential capacity of the production line and effectively increases the hourly output.

[0075] The full-chain data traceability platform records and visualizes all production process data and equipment status in real time, automatically generating daily and monthly reports covering electricity consumption per ton, gas consumption per ton, temperature qualification rate, moisture standard deviation, and production efficiency. Enterprise managers can grasp the production status and historical trends anytime and anywhere through web pages and mobile apps. Production, quality control, and technology departments communicate and make decisions based on a unified, objective, and timely data platform, breaking down previous information silos and significantly improving departmental collaboration efficiency.

[0076] Ultimately, through the application of this system, the production line has made significant progress in product quality stability, production efficiency, and energy cost control. Overall operating costs have been improved, the return on investment cycle has met the company's expectations, and it has provided a reliable practical example and data support for the intelligent transformation of other production lines in the company.

[0077] Example 2: In enterprises that focus on the production of high-end extruded aquatic feed, their products have extremely stringent requirements for the stability, hardness, water resistance, and nutrient retention of the pellets in water. Traditional production methods rely heavily on the experience of master craftsmen for adjustments, resulting in poor process reproducibility and large quality fluctuations between different batches, making it difficult to consistently meet the needs of high-end customers.

[0078] To address this specific application scenario, the system has undergone targeted enhancements to its infrastructure. It deeply embeds high-standard process parameter sets and control logic for various aquatic feed categories into the process knowledge base, with particular emphasis on refined management strategies for conditioning temperature, time, ring mold parameters, and post-coating processes.

[0079] After system deployment, the high-precision sensors of the distributed sensing network closely monitor every critical node from powder conditioning to particle cooling and spraying, especially the instantaneous moisture temperature at the conditioner outlet and the final product moisture content at the cooler outlet, providing a real-time data foundation for precise system control. Based on the specific process objectives of high hardness and high water resistance in aquatic feed, the intelligent process decision module drives a multi-actuator collaborative adjustment module to perform highly coordinated control actions. For example, it precisely controls the saturated dryness and injection volume of steam to ensure full starch gelatinization, adjusts conditioning time and temperature to improve protein denaturation, and precisely manages cooling airflow and material layer thickness to remove excess moisture while preventing particle surface cracking, thereby ensuring a dense particle structure and meeting hardness standards.

[0080] The system's "New Product Debugging Mode" assists process engineers in systematically exploring and recording the effects of different combinations of process parameters on the final product's water resistance time, hardness, and powdering rate. It helps quickly locate the optimal process window and transforms these valuable practical experiences into reproducible and inheritable digital process knowledge, which is then stored in the process knowledge base.

[0081] Through the stable operation of this system, the company has successfully achieved standardization and intelligentization of its high-end aquatic feed production process. The water resistance time and hardness of its pelleted feed are reliably guaranteed, and batch-to-batch consistency has been significantly improved. Product quality has consistently reached industry-leading levels, significantly enhancing market competitiveness and customer trust. Simultaneously, the system reduces absolute reliance on the individual experience of specific senior operators, making tacit knowledge explicit and standardized, accumulating valuable digital assets for the company, and supporting its high-end brand positioning and sustainable development.

[0082] Example 3: Facing the challenges of feed production with diverse raw material sources and frequent fluctuations in characteristics, a comprehensive feed processing enterprise has long been plagued by problems such as instability in the pelleting process, fluctuations in product quality, and low production efficiency caused by changes in parameters such as raw material moisture, protein content, and fiber level. Traditional fixed-parameter control modes are difficult to adapt to the dynamic changes in raw materials, often requiring frequent manual intervention, with unsatisfactory results.

[0083] After applying this system, its powerful adaptive learning capability plays a crucial role in this scenario. During the system initialization phase, the process knowledge base contains a wide range of target parameters based on different raw material formulations. Real-time data continuously collected by the distributed sensing network, especially the initial moisture content and temperature of the raw materials in the granulation bin, provides the system with "first-hand information" for sensing changes in the raw materials.

[0084] The adaptive learning model in the process intelligence decision-making module continuously receives data streams from the entire production process, including raw material characteristics, real-time operating conditions, actuator actions, and final product quality feedback. It dynamically analyzes the complex nonlinear relationship between raw material characteristics and optimal process parameters using machine learning algorithms. When the raw material moisture content is detected to be significantly higher than usual, the model can automatically adjust its strategy. In the conditioning stage, it appropriately reduces the amount of steam added and may fine-tune the feeding speed to maintain a suitable conditioning moisture content. In the cooling stage, it improves the fan frequency to ensure the final moisture content meets the standard. Conversely, when faced with raw materials with high fiber content and poor flowability, the model can learn to adjust the conditioning temperature and time to improve material gelatinization and plasticity. Simultaneously, it carefully controls the feeding load based on pellet mill current feedback to prevent blockage.

[0085] This continuous adaptive improvement enables the system to respond flexibly to raw material fluctuations, much like a seasoned expert, minimizing the disruptions caused by these changes. The end-to-end data traceability platform meticulously records the system adjustment parameters and final quality results corresponding to each raw material change, forming a valuable "raw material-process-quality" correlation database. This provides enterprises with in-depth data insights for raw material procurement assessment, formula improvement, and production cost prediction.

[0086] By applying this system, the company can enhance its adaptability to various raw materials and the flexibility of its production plan without sacrificing product quality. This reduces downtime and quality risks caused by raw material fluctuations, thereby improving the resilience of the overall production system.

[0087] Example 4: For feed companies dedicated to producing export-standard and high-end pet food, product safety, traceability, and extremely stringent quality consistency requirements are key concerns. These products often need to comply with the regulations and standards of the importing country or region and meet consumers' expectations for high-quality pet nutrition.

[0088] The system's end-to-end data traceability platform and precise process control capabilities perfectly meet this requirement. After the system is implemented, everything from the batch information of each batch of raw materials to the process parameters (such as temperature, moisture, and pressure at various points), equipment operating status (such as current and valve opening), actuator operation records, and finally the inspection data of the final product, is automatically, completely, and immutably recorded by the system and linked to a unique production batch number.

[0089] The end-to-end data traceability platform not only enables forward traceability from raw materials to finished products and reverse traceability from finished products back to raw materials within an enterprise, but its cloud data synchronization function and standardized data interfaces also facilitate external audits and customer inquiries. When customers or regulatory agencies need to understand the detailed production history of a batch of products, the enterprise can quickly provide a comprehensive electronic report with clear timestamps, clearly demonstrating whether the batch of products remained within the preset process parameter specifications throughout the entire production process.

[0090] On the other hand, the intelligent process decision-making module ensures a high degree of consistency in the production process of each batch of products by strictly implementing a set of process parameters customized according to export standards or high-end pet food formulas. The precise control of the multi-actuator collaborative adjustment module reliably guarantees the temperature and uniformity of heat-sensitive nutrients such as vitamins and amino acids added in the post-coating stage, avoiding nutrient loss or uneven distribution due to process fluctuations. The system's supported "standard quality mode" is set as the default production mode, prioritizing the accurate achievement and ultimate stability of all quality indicators.

[0091] Through the in-depth application of this system, the company has successfully built a digital quality management system that meets high international standards. This not only significantly improves the consistency and safety of product quality, but also enhances brand reputation with transparent and reliable production data traceability capabilities. It meets the stringent quality and compliance requirements of high-end markets and export businesses, providing solid technical support for the company to expand into high-end markets.

[0092] Example 5: For many small and medium-sized feed production enterprises facing severe pressure to save energy and reduce consumption, as well as the difference between peak and off-peak electricity prices, the key to improving their survival and competitiveness is how to significantly reduce energy consumption and flexibly utilize off-peak electricity prices to save costs while ensuring basic production quality.

[0093] This system offers scenario-based functions such as "High-Yield Energy-Saving Mode" and "Nighttime Anti-Blocking Mode," providing practical and intelligent solutions for such enterprises. After implementing this system, enterprises can flexibly choose operating modes according to their production plans. When the "High-Yield Energy-Saving Mode" is selected, the process intelligent decision-making module will automatically improve control strategies to minimize energy consumption per unit output, while ensuring the minimum required product quality. For example, the system finely adjusts the steam supply to avoid steam waste while ensuring the minimum necessary conditioning effect; it reduces power consumption while maintaining the moisture content of qualified finished products by collaboratively improving the feeding speed and cooling fan operating frequency; and the adaptive learning model will continuously explore the potential for energy efficiency improvement in specific production lines.

[0094] When businesses plan to produce during off-peak electricity prices at night, they can switch to "Nighttime Anti-Blocking Mode" with a single click. This mode automatically adopts more conservative and robust control strategies to address the lower ambient temperatures and reduced staffing at night. For example, it appropriately increases the conditioning temperature setting to ensure material plasticity, uses a specific feeding acceleration curve to avoid excessive instantaneous load during startup and operation, and strengthens monitoring and early warning of pellet mill current fluctuations. This significantly reduces the risk of production interruptions such as machine blockages during unmanned or minimally staffed periods, ensuring the stability of continuous production. This allows businesses to safely and fully utilize off-peak electricity prices for production, directly reducing energy costs.

[0095] The energy consumption analysis reports provided by the full-chain data traceability platform display detailed electricity and gas consumption data per ton of product under different modes and time periods, helping enterprises clearly quantify energy-saving achievements and providing intuitive basis for management decisions. Through the application of this system, small and medium-sized feed enterprises can effectively reduce production costs and improve operational efficiency through intelligent management and control without large-scale hardware upgrades, thereby enhancing their ability to withstand market fluctuations and improving profitability.

[0096] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart management system for feed pelleting operation and quality based on big data analysis, characterized in that, include: A distributed sensing network is used to collect material status parameters and equipment operating parameters at multiple key nodes in the entire feed pelleting process in real time. The process intelligent decision-making module is communicatively connected to the distributed sensing network and is used to generate multi-objective collaborative optimization control strategies based on the collected parameters, the preset process knowledge base and the adaptive learning model. The multi-actuator coordinated adjustment module is communicatively connected to the process intelligent decision module and is used to coordinately adjust the operating parameters of the feeding system, steam supply system, cooling system and post-coating system according to the control strategy. The full-chain data traceability platform communicates with the process intelligent decision-making module to realize the recording, analysis, visualization, and remote monitoring of data throughout the entire production process.

2. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 1, characterized in that, The distributed sensing network includes: The first sensing unit, located in the granulation bin, is used to collect the initial moisture and temperature of the material before conditioning. The second sensing unit located at the outlet of the conditioner is used to collect the instantaneous moisture, temperature and steam pressure of the material after conditioning; The third sensing unit, located at the outlet of the cooler, is used to collect the moisture content, temperature, and main motor current of the pellet mill after cooling. The fourth sensing unit, located at the post-coating station, is used to collect the surface grease distribution and temperature of the finished product after coating.

3. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 1, characterized in that, The intelligent process decision-making module includes: The process knowledge base stores a set of target process parameters based on feed type, raw material formulation and seasonal environmental factors, including target pelleting temperature, target moisture range, target hardness, pulverization rate threshold, maximum allowable current and post-coating process parameters. The adaptive learning model dynamically optimizes control parameters and strategies based on historical production data, real-time operating data, and feedback adjustment effects to adapt to equipment wear, changes in raw material characteristics, and environmental fluctuations.

4. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 1, characterized in that, The multi-actuator coordinated adjustment module includes: The feeding speed control unit is used to adjust the feeder speed according to the strategy to control the production capacity and the time it takes for the material to pass through the conditioner. The precise steam supply unit is used to adjust the opening and pressure of the steam valve according to the strategy, so as to achieve rapid response and stable control of the granulation temperature. The cooling air volume and material level coordinated adjustment unit is used to adjust the fan frequency and discharge mechanism of the cooler according to the strategy, so as to optimize the cooling efficiency and finished product moisture content. The post-spraying temperature and flow rate adjustment unit is used to adjust the heating temperature and spray flow rate of the spraying oil according to the strategy.

5. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 1, characterized in that, The intelligent process decision-making module adopts a three-point closed-loop linkage algorithm of "moisture-temperature-current" to adjust the steam supply and feeding speed in real time based on the moisture data of the first, second and third sensing units, so as to ensure that the moisture content of the finished product after cooling meets the preset target and is not lower than the moisture content before conditioning, thereby achieving precise control of moisture balance.

6. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 5, characterized in that, The three-point closed-loop linkage algorithm improves production efficiency by monitoring the downward trend of the main motor current of the pellet mill. When the current decreases significantly, it automatically instructs the feeding speed regulation execution unit to increase the speed, thereby achieving a safe and efficient increase in production line output.

7. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 1, characterized in that, The system supports multiple automated production modes, including standard quality mode, high-yield and energy-saving mode, nighttime anti-blocking mode, and new product debugging mode. Users can switch between these modes with a single click according to production plans and market demands.

8. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 1, characterized in that, The full-chain data traceability platform has cloud data synchronization function, which supports real-time viewing of production reports, energy consumption analysis, quality trends and equipment status through web page and mobile APP. The report content covers electricity consumption per ton, gas consumption per ton, granulation temperature qualification rate, moisture control standard deviation, production efficiency and formula cost correlation analysis.

9. The intelligent management system for feed pelleting operation and quality based on big data analysis according to claim 1, characterized in that, The system also includes a remote diagnostic and optimization service module, which can receive algorithm updates, fault warning reports, and process parameter packages optimized for specific formulations from the cloud service center via a secure network connection.

10. The control method for a feed pelleting operation and quality intelligent management system based on big data analysis according to any one of claims 1-9, characterized in that, Includes the following steps: Step S1: System initialization, select feed category according to production task, and load corresponding process parameter set; Step S2: The distributed sensing network collects material and equipment data from key nodes throughout the entire process in real time; Step S3: The intelligent process decision-making module calculates the deviation between the current state and the target state based on the collected data, the process knowledge base and the adaptive learning model, and generates collaborative control instructions that include multiple variables such as feeding, steam, cooling and post-spraying. Step S4: The multi-actuator collaborative adjustment module synchronously executes control commands and provides real-time feedback on the execution effect, forming a closed-loop control; Step S5: The full-chain data traceability platform records and analyzes data throughout the entire process, generates visual reports, and supports production management decisions and remote supervision.

Images