Automated control system for pellet mills based on real-time particle size feedback

Abstract

This invention discloses an automated control system for a granulator based on real-time particle size feedback. The system includes: real-time acquisition of particle size distribution statistics at different times during the granulation process; calculation of indicators such as particle size change trend and relative growth rate; and accurate determination of each growth stage of granulation by combining the spraying state and inlet air temperature, achieving real-time perception and accurate identification of particle growth status. This invention calculates particle size distribution width and exceedance only during the aggregation / layering growth stage, obtaining a control necessity index through a sigmoid function, and precisely triggering control based on a threshold, avoiding meaningless adjustments. When control is required, the system uses the particle size change trend and D50(t) as core inputs, and dynamically adjusts the binder spraying rate based on the MPC algorithm predicted by DMD, achieving a fine match between process parameters and the granulation process response, effectively improving the problem of excessively wide particle size distribution and enhancing particle uniformity.

Description

Technical Field

[0001] This invention belongs to the field of pellet production technology and relates to an automated control system for pellet mills based on real-time particle size feedback. Background Technology

[0002] In key industrial sectors such as pharmaceuticals and chemicals, granulation is a crucial step in determining the core quality attributes of products (such as particle size distribution and uniformity). Its process stability directly impacts product performance and market competitiveness. With the in-depth development of Process Analysis Technology (PAT), intelligent manufacturing concepts, and the widespread application of Quality by Design (QbD) in industrial production, modern production places higher demands on the refinement, intelligence, and flexibility of granulation processes. However, traditional granulation processes suffer from numerous insurmountable technical bottlenecks. Traditional granulation processes heavily rely on operator experience and fixed parameter settings, resulting in low-frequency and discrete adjustment modes. Due to the long particle size analysis cycle, parameter corrections can only be performed a limited number of times per granulation batch, making it impossible to capture particle growth processes in real time. The continuous dynamic changes during the process make it impossible to precisely match process parameters with process response, leading to uncontrolled particle growth trajectory and a wide particle size distribution in the product. Furthermore, the subjective nature of judgment based on human experience makes it susceptible to individual differences in operators and environmental fluctuations, resulting in significant batch-to-batch product quality variations and difficulty in consistently ensuring the consistency of key quality attributes. Fixed parameter settings are also difficult to adapt to raw materials with different characteristics, and delayed endpoint judgments can easily lead to overproduction or underproduction, reducing raw material utilization, increasing scrap rates, and hindering production efficiency improvements. These technical shortcomings mean that traditional granulation processes cannot meet the stringent requirements of modern industry for refined and highly consistent product quality, and also contradict the data-driven production model advocated by intelligent manufacturing. Therefore, a technical solution capable of real-time sensing of particle growth status and dynamic adjustment of process parameters is urgently needed to solve these problems. Summary of the Invention

[0003] The purpose of this invention is to solve the problems in the existing technology of traditional granulation process that relies on manual experience and fixed parameter settings. Due to the long analysis cycle, it is impossible to capture the continuous dynamic changes in particle growth, which makes it difficult to accurately match parameters and process response, resulting in uncontrolled particle growth trajectory, wide particle size distribution of products, and large quality fluctuations between batches. The invention provides an automated control system for granulators based on real-time particle size feedback.

[0004] To achieve the above objectives, the present invention employs the following technical solution: an automated control system for a granulator based on real-time particle size feedback, comprising: a data acquisition module, an acquisition module, a first calculation module, a judgment module, a second calculation module, and a control module; the data acquisition module collects the particle size distribution statistics at different times during the granulation process in real time; the acquisition module acquires the particle size distribution statistics based on the collected particle size distribution statistics. Particle size variation trend ;in, express The particle size at which the cumulative distribution ratio in the collected particle size distribution data reaches 50% at a given time; the first calculation module is based on the acquired... and Calculate based on the cumulative amount of adhesive added per unit time. The relative growth rate of particles at that time The judgment module is based on the trend of particle size variation. and relative growth rate The first module, by combining the liquid spraying status, air inlet temperature, and target particle size of the granulator, determines the current growth stage of the granulation process. The second calculation module, at the growth stage requiring particle size control, calculates the particle size distribution statistics collected at different times. Particle size distribution width at time t and exceeding the limit Combined with the excessive particle size The necessity index for regulation is calculated using the sigmoid function. The control module determines the control necessity index. If the particle size exceeds a preset threshold, then the particle size variation trend will be considered. and As the core input, the MPC algorithm based on DMD prediction dynamically adjusts the adhesive spraying rate in the granulator to obtain granules that meet the preset standards.

[0005] A further improvement of the present invention is that: the acquisition module collects the particle size distribution statistics at different times during the granulation process of the granulator in real time, specifically by setting... The particle size distribution statistics collected at time t are The express The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 10% at a given time is defined as follows: express The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 50% at a given time is defined as follows: express The particle size at which the cumulative distribution accounts for 90% of the collected particle size distribution data at a given time.

[0006] Furthermore, the acquisition Particle size variation trend Specifically: ; in, Indicates the sampling interval time. The value is 1 second; It means from arrive During this period of time, the first The particle size change at a given time is analyzed in the current context. The weighting of particle size change trends at different times is considered. Given that data from a single time point is insufficient to represent the current particle size change trend, a comprehensive analysis combining particle size changes over the previous 30 seconds is performed. Different weights are assigned to particle sizes at different times when calculating the particle size change trend, with weights increasing as the size approaches the desired value. Moment Value, corresponding weight Larger particle sizes tend to increase the trend of particle size variation. The accuracy of reflecting real-time growth status.

[0007] Furthermore, the first calculation module is based on the acquired and Calculate based on the cumulative amount of adhesive added per unit time. The relative growth rate of particles at that time Specifically: in, This indicates the cumulative amount of adhesive added per unit time; the relative growth rate of the particles. pass The absolute increase in particle size is converted into a relative percentage increase.

[0008] Furthermore, the judgment module is based on the trend of particle size variation. and relative growth rate Based on the liquid spraying status, inlet air temperature, and target particle size of the granulator, determine the current growth stage of the granulation process. Specifically: If Close to the initial powder value, and If the intake air temperature is higher than the dew point temperature and liquid injection has not started or has just started, it is in the preheating stage. The dew point temperature is the temperature at which air reaches saturation under constant air pressure and constant moisture content. If liquid injection has already started... Less than the preset trend threshold and If the value is positive, it indicates slow growth, which is considered the nucleation and moistening period; if... The relative growth rate of the particles is not less than the preset trend threshold. If the growth rate is within the preset range, it is in the aggregation / layering growth stage; if Reaching the lower limit of the target range and If this process is maintained for a certain period of time, it constitutes the endpoint / equilibrium phase; the target range is a preset particle size range.

[0009] Furthermore, the second calculation module calculates the particle size distribution statistics collected at different times based on the aggregation / stratification growth stage that needs to be regulated. Particle size distribution width at time t and exceeding the limit Specifically: ; in, This indicates the width of the particle size distribution. Before the system parameters are set, there exists a standard range ( ). , ); express The span exceeds the limit at any given moment; Minimum value of particle size distribution width; The maximum value of the particle size distribution width.

[0010] Furthermore, the excessive binding particle size The necessity index for regulation is calculated using the sigmoid function. Specifically: in, Indicates the preset ideal state under the condition of The particle size at which the cumulative distribution accounts for 50% of the collected particle size distribution data at a given time. It means that in The relative deviation of particle size at a given time, during the aggregation / layering growth stage. At this time, the particle size deviation is large, and the current particle size is calculated. Normal time beyond the system's set current time If the range is large, then the need for dynamic adjustment of the granulator at that time is greater.

[0011] Furthermore, the control module determines the control necessity index. Whether it is greater than a preset threshold, specifically: the preset threshold is... When the necessity index for regulation When this occurs, it is determined that dynamic adjustment is required.

[0012] Compared with existing technologies, this invention has the following advantages: By collecting particle size distribution statistics at different times during the granulation process in real time, this invention calculates indicators such as particle size change trends and relative growth rates. Combined with the spraying state and inlet air temperature, it can accurately determine each growth stage of granulation, achieving real-time perception and accurate identification of particle growth status. This invention only calculates the particle size distribution width and exceedance during the aggregation / layering growth stage. It obtains a control necessity index through the sigmoid function and precisely triggers control based on a threshold, avoiding meaningless adjustments. When control is needed, using the particle size change trend and D50(t) as core inputs, it dynamically adjusts the binder spraying rate based on the MPC algorithm predicted by DMD, achieving a fine match between process parameters and the granulation process response, effectively improving the problem of excessively wide particle size distribution and enhancing particle uniformity. This invention uses data-driven control to reduce the impact of human and environmental factors, reduce batch-to-batch quality fluctuations, ensure product quality consistency, accurately determine the granulation endpoint, improve raw material utilization, reduce scrap rate, and increase production efficiency. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the automated control system for a pellet mill based on real-time particle size feedback according to the present invention. Figure 2 This is a schematic diagram of the process of the automatic control method for a pellet mill based on real-time particle size feedback according to the present invention. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0016] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0017] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0018] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present 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, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0020] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0021] The present invention will now be described in further detail with reference to the accompanying drawings: See also Figure 1 This invention discloses an automated control system for a granulator based on real-time particle size feedback, comprising: a data acquisition module, an acquisition module, a first calculation module, a judgment module, a second calculation module, and a control module.

[0022] The acquisition module collects statistical data on particle size distribution at different times during the granulation process of the granulator in real time; and sets... The particle size distribution statistics collected at time t are The express The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 10% at a given time is defined as follows: express The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 50% at a given time is defined as follows: express The particle size at which the cumulative distribution accounts for 90% of the collected particle size distribution data at a given time.

[0023] The acquisition module acquires data based on the collected particle size distribution statistics. Particle size variation trend ; ; in, Indicates the sampling interval time. The value is 1 second; It means from arrive During this period of time, the first The particle size change at a given time is analyzed in the current context. The weighting of particle size change trends at different times is considered. Given that data from a single time point is insufficient to represent the current particle size change trend, a comprehensive analysis combining particle size changes over the previous 30 seconds is performed. Different weights are assigned to particle sizes at different times when calculating the particle size change trend, with weights increasing as the size approaches the desired value. Moment Value, corresponding weight Larger particle sizes tend to increase the trend of particle size variation. The accuracy of reflecting real-time growth status.

[0024] The first calculation module is based on the acquired and Calculate based on the cumulative amount of adhesive added per unit time. The relative growth rate of particles at that time ; in, This indicates the cumulative amount of adhesive added per unit time; the relative growth rate of the particles. pass The absolute increase in particle size is converted into a relative percentage increase.

[0025] The judgment module is based on the trend of particle size change. and relative growth rate Based on the liquid spraying status, inlet air temperature, and target particle size of the granulator, determine the current growth stage of the granulation process; if Close to the initial powder value, and If the intake air temperature is higher than the dew point temperature and liquid injection has not started or has just started, it is in the preheating stage. The dew point temperature is the temperature at which air reaches saturation under constant air pressure and constant moisture content. If liquid injection has already started... Less than the preset trend threshold and If the value is positive, it indicates slow growth, which is considered the nucleation and moistening period; if... The relative growth rate of the particles is not less than the preset trend threshold. If the growth rate is within the preset range, it is in the aggregation / layering growth stage; if Reaching the lower limit of the target range and If this process is maintained for a certain period of time, it constitutes the endpoint / equilibrium phase; the target range is a preset particle size range.

[0026] The second calculation module calculates the particle size distribution statistics collected at different times during the growth stage where particle growth needs to be regulated. Particle size distribution width at time t and exceeding the limit Combined with the excessive particle size The necessity index for regulation is calculated using the sigmoid function. The growth stage that needs to be regulated for particles is the aggregation / stratification growth stage; the calculation is based on the collected particle size distribution statistics at different times. Particle size distribution width at time t and exceeding the limit Specifically: ; in, This indicates the width of the particle size distribution. Before the system parameters are set, there exists a standard range ( ). , ); express The span exceeds the limit at any given moment; Minimum value of particle size distribution width; The maximum value of the particle size distribution width.

[0027] The excessive binding particle size The necessity index for regulation is calculated using the sigmoid function. Specifically: in, Indicates the preset ideal state under the condition of The particle size at which the cumulative distribution accounts for 50% of the collected particle size distribution data at a given time. It means that in The relative deviation of particle size at a given time, during the aggregation / layering growth stage. At this time, the particle size deviation is large, and the current particle size is calculated. Normal time beyond the system's set current time If the range is large, then the need for dynamic adjustment of the granulator at that time is greater.

[0028] The control module determines the control necessity index. If the particle size exceeds a preset threshold, then the particle size variation trend will be considered. and As the core input, the MPC algorithm based on DMD prediction dynamically adjusts the adhesive spraying rate in the granulator to obtain granules that meet the preset standards.

[0029] The preset threshold is When the necessity index for regulation When this occurs, it is determined that dynamic adjustment is required.

[0030] The MPC algorithm based on DMD prediction dynamically adjusts the adhesive spraying rate in the granulator to obtain granules that meet a preset standard. Specifically, it utilizes the particle size... and its changing trends Historical process data are used to extract the dynamic modes of the system through the Dynamic Mode Decomposition (DMD) method, and a linear state-space model is constructed to describe the dynamic relationship between particle size and spray rate.

[0031] The DMD model is embedded into the MPC framework for MPC controller initialization. In each control cycle, the following operations are performed: The current particle size D50(t) and its changing trend ∆D50(t) are measured or estimated in real time as the current system state; based on the current state and the DMD model, the evolution trajectory of the particle size over a future period is predicted; quadratic programming is used to minimize the deviation between the particle size and the set value, while considering the smoothness of the spray rate, to obtain the optimal spray rate sequence in the future time domain; the spray rate adjustment amount at the current moment in the optimized sequence is applied to the granulator; at the next sampling moment, the system state is reacquired, and the above steps are repeated to achieve dynamic adjustment.

[0032] See Figure 2 This invention discloses an automated control method for a granulator based on real-time particle size feedback, comprising: S101, a data acquisition module acquiring real-time particle size distribution statistics at different times during the granulation process; S102, obtaining... Particle size variation trend S103, based on the acquired and Calculate based on the cumulative amount of adhesive added per unit time. The relative growth rate of particles at that time S104, based on particle size variation trend and relative growth rate Based on the liquid spraying status, inlet air temperature, and target particle size of the granulator, determine the current growth stage of the granulation process; S105, in the growth stage where particle size distribution needs to be regulated, calculate based on the collected particle size distribution statistics at different times. Particle size distribution width at time t and exceeding the limit Combined with the excessive particle size The necessity index for regulation is calculated using the sigmoid function. S106, Index for Judging the Necessity of Regulation If the particle size exceeds a preset threshold, then the particle size variation trend will be considered. and As the core input, the MPC algorithm based on DMD prediction dynamically adjusts the adhesive spraying rate in the granulator to obtain granules that meet the preset standards.

[0033] Example: This invention discloses an automated control method for a granulator based on real-time particle size feedback, comprising: firstly, obtaining particle size data collected in real-time at different times. During the granulation process, each sampling instant measures tens of thousands of particles in the detection area; therefore, this method is set... The particle size distribution statistics collected at time t are .in express The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 10% at a given time. express The particle size at which the cumulative distribution accounts for 50% of the collected particle size distribution data at a given time is determined. express The particle size at which the cumulative distribution accounts for 90% of the collected particle size distribution data at a given time.

[0034] If a sample has D10=3μm, D50=10μm, and D90=12μm, and the particles are distributed from smallest to largest, it means that in the entire particle system that makes up the sample, particles smaller than or equal to 3μm account for 10%; particles smaller than or equal to 10μm account for 50%; and particles smaller than or equal to 12μm account for 90%.

[0035] The center value representing particle size is the core control target. During granulation, particles undergo multiple granulation stages, each with different standard particle sizes. To facilitate real-time particle size feedback adjustment, it's crucial to first understand which stage the granulation process is currently in. The specific analysis process is as follows: First, calculate... At this moment The trend of particle size variation, representing particle size: ; in, This represents the sampling interval, set to 1 second. It means from arrive During this period of time, the first The particle size change at a given time is analyzed in the current context. The weight of the particle size change trend at any given time.

[0036] Formula Logic: The above formula primarily analyzes the particle size change trend at the current moment based on continuous particle size variations. Considering that data from a single moment is insufficient to represent the current particle size change trend, we combine the particle size changes over the previous 30 seconds for a comprehensive analysis. Here, different weights are assigned to particle sizes at different times when calculating the particle size change trend, with the weight closest to the current moment being considered more significant. The greater the time, the higher the corresponding weight value.

[0037] The above analysis This involves analyzing the trend of particle size growth over time, but considering the previous period... This might be normal, but in the later stages, the same... This could indicate uncontrolled growth and a serious risk of clumping. (Just looking at...) The controller may mistakenly interpret this as "good growth," when in reality the process has deviated from its normal trajectory. Therefore, further analysis of the current situation is necessary. The relative growth rate of particle size at the given time: In the formula, This indicates the cumulative amount of adhesive added per unit time. pass Converting the absolute increase in particle size to a relative percentage increase eliminates the influence of the base effect. During the ideal steady-state growth period, the RGR should remain at a relatively stable high level. This indicates that the binder is being used effectively, and the particles are growing uniformly with optimal efficiency.

[0038] Based on the trend of particle size variation and relative growth rate Based on the liquid spraying status, inlet air temperature, and target particle size of the granulator, determine the current growth stage of the granulation process. Specifically: If Close to the initial powder value, and If the intake air temperature is higher than the dew point temperature, and liquid injection has not yet started or has just begun, this is the preheating stage. No feedback adjustment is required during this stage. The dew point temperature is the temperature at which air reaches saturation under constant water vapor content and air pressure.

[0039] After the spraying begins, Less than the preset trend threshold and If the value is positive, it is considered that the growth is slow, which is the nucleation and moistening period, and no feedback adjustment is needed during this stage.

[0040] like The relative growth rate of the particles is not less than the preset trend threshold. If the growth rate is within a preset range, it enters the aggregation / layering growth stage; the threshold is based on a preset value. Here, a preset value of 2.2 is given. Meanwhile, when the above analysis shows Relative growth rate of particle size at time t If the value is within a reasonable range and is predetermined by the system, set before system operation, then it falls under the clustering / layering growth stage. During this stage, system parameters need to be continuously adjusted to ensure... Generate along the target trajectory.

[0041] like Reaching the lower limit of the target range and If this process is maintained for a certain period of time, it constitutes the endpoint / equilibrium phase; the target range is a preset particle size range. During this phase, the system will cease growth intervention without requiring feedback adjustment.

[0042] The above process completes the particle growth stage for the current moment. When the granulation process enters the aggregation / layering growth stage, it needs to be based on the current... Dynamic adjustment is performed based on data and related data such as span. The specific analysis steps are as follows: First, it is necessary to calculate the current... Moment Wait for data to be considered for analysis and calculation. Whether dynamic granulation control is needed at any given time, calculation Particle size distribution width at time t and exceeding the limit Specifically: ;

[0043] ;

[0044] In the formula, The width of the particle size distribution is a key indicator for measuring product uniformity. Before setting parameters in the system, there exists a standard range. , ). express The span exceeds the limit at any given moment; Minimum value of particle size distribution width; The maximum value of the particle size distribution width.

[0045] in, Indicates the preset ideal state under the condition of The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 50% at a given time. It means that in The relative deviation of particle size at a given time, during the aggregation / layering growth stage. At this time, the particle size deviation is large, and the current particle size is calculated. Normal time beyond the system's set current time If the range is large, then the need for dynamic adjustment of the granulator at that time is greater.

[0046] Set threshold When calculated The necessity of dynamic adjustment of the granulator at all times At that time, the current situation is considered... Currently, the granulator needs to precisely track the speed of the adhesive spraying liquid. This will allow it to... The performance of the various parameters obtained at each moment is as follows: , Using the model predictive control algorithm as the main input, the adhesive spraying rate is dynamically and continuously adjusted to achieve active and precise regulation, ensuring that the particle size meets the system's generation standards.

[0047] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An automated control system for a pellet mill based on real-time particle size feedback, characterized in that, include: The system comprises a data acquisition module, an acquisition module, a first calculation module, a judgment module, a second calculation module, and a control module. The acquisition module collects the particle size distribution statistics at different times during the granulation process of the granulator in real time; the acquisition module acquires the particle size distribution statistics based on the collected statistics. Particle size variation trend ;in, express The particle size at which the cumulative distribution ratio in the collected particle size distribution data reaches 50% at a given time; the first calculation module is based on the acquired... and Calculate based on the cumulative amount of adhesive added per unit time. The relative growth rate of particles at that time The judgment module is based on the trend of particle size variation. and relative growth rate The first module, by combining the liquid spraying status, air inlet temperature, and target particle size of the granulator, determines the current growth stage of the granulation process. The second calculation module, at the growth stage requiring particle size control, calculates the particle size distribution statistics collected at different times. Particle size distribution width at time t and exceeding the limit Combined with the excessive particle size The necessity index for regulation is calculated using the sigmoid function. The control module determines the control necessity index. If the particle size exceeds a preset threshold, then the particle size variation trend will be considered. and As the core input, the MPC algorithm based on DMD prediction dynamically adjusts the adhesive spraying rate in the granulator to obtain granules that meet the preset standards.

2. The automated control system for a granulator based on real-time particle size feedback according to claim 1, characterized in that, The acquisition module collects statistical data on particle size distribution at different times during the granulation process of the granulator in real time. Specifically, it sets... The particle size distribution statistics collected at time t are The express The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 10% at a given time is defined as follows: express The particle size at which the cumulative distribution percentage in the collected particle size distribution data reaches 50% at a given time is defined as follows: express The particle size at which the cumulative distribution accounts for 90% of the collected particle size distribution data at a given time.

3. The automated control system for a granulator based on real-time particle size feedback according to claim 2, characterized in that, The acquisition Particle size variation trend Specifically: ; in, Indicates the sampling interval time. The value is 1 second; It means from arrive During this period of time, the first The particle size change at a given time is analyzed in the current context. The weighting of particle size change trends at different times is considered. Given that data from a single time point is insufficient to represent the current particle size change trend, a comprehensive analysis combining particle size changes over the previous 30 seconds is performed. Different weights are assigned to particle sizes at different times when calculating the particle size change trend, with weights increasing as the size approaches the desired value. Moment Value, corresponding weight Larger particle sizes tend to increase the trend of particle size variation. The accuracy of reflecting real-time growth status.

4. The automated control system for a pellet mill based on real-time particle size feedback according to claim 3, characterized in that, The first calculation module is based on the acquired and Calculate based on the cumulative amount of adhesive added per unit time. The relative growth rate of particles at that time Specifically: in, This indicates the cumulative amount of adhesive added per unit time; the relative growth rate of the particles. pass The absolute increase in particle size is converted into a relative percentage increase.

5. The automated control system for a pellet mill based on real-time particle size feedback according to claim 4, characterized in that, The judgment module is based on the trend of particle size change. and relative growth rate Based on the liquid spraying status, inlet air temperature, and target particle size of the granulator, determine the current growth stage of the granulation process. Specifically: If Close to the initial powder value, and If the intake air temperature is higher than the dew point temperature and liquid injection has not started or has just started, it is in the preheating stage. The dew point temperature is the temperature at which air reaches saturation under constant air pressure and constant moisture content. If liquid injection has already started... Less than the preset trend threshold and If the value is positive, it indicates slow growth, which is considered the nucleation and moistening period; if... The relative growth rate of the particles is not less than the preset trend threshold. If the growth rate is within the preset range, it is in the aggregation / layering growth stage; if Reaching the lower limit of the target range and If this process is maintained for a certain period of time, it constitutes the endpoint / equilibrium phase; the target range is a preset particle size range.

6. The automated control system for a pellet mill based on real-time particle size feedback according to claim 5, characterized in that, The second calculation module calculates the particle size distribution statistics collected at different times based on the aggregation / stratification growth stage that needs to be regulated. Particle size distribution width at time t and exceeding the limit Specifically: ; in, This indicates the width of the particle size distribution. Before the system parameters are set, there exists a standard range ( ). , ); express The span exceeds the limit at any given moment; Minimum value of particle size distribution width; The maximum value of the particle size distribution width.

7. The automated control system for a pellet mill based on real-time particle size feedback according to claim 6, characterized in that, The excessive binding particle size The necessity index for regulation is calculated using the sigmoid function. Specifically: in, Indicates the preset ideal state under the condition of The particle size at which the cumulative distribution accounts for 50% of the collected particle size distribution data at a given time. It means that in The relative deviation of particle size at a given time, during the aggregation / layering growth stage. At this time, the particle size deviation is large, and the current particle size is calculated. Normal time beyond the system's set current time If the range is large, then the need for dynamic adjustment of the granulator at that time is greater.

8. The automated control system for a pellet mill based on real-time particle size feedback according to claim 7, characterized in that, The control module determines the control necessity index. Whether it is greater than a preset threshold, specifically: the preset threshold is... When the necessity index for regulation When this occurs, it is determined that dynamic adjustment is required.

Images