A method and system for managing and controlling an MES system based on feed production intelligent manufacturing

Abstract

The present application relates to the technical field of feed production manufacturing, and particularly relates to an MES system management and control method and system based on feed production manufacturing. The method comprises the following steps: selecting a target feed formula in an MES system and generating a production batch, and obtaining structural parameters of each feed raw material; determining mixing equipment parameters according to the structural parameters of each feed raw material, and constructing a mixing state curve during the mixing process; determining the raw material mixing degree according to the mixing state curve, dynamically adjusting the mixing equipment parameters until the mixing degree meets the uniformity condition; after the raw material mixing degree meets the preset uniformity condition, the mixed material is granulated and formed, and granule structural feature data is obtained; the structural consistency state is determined based on the granule structural feature data, and when the structural consistency state deviates from a preset range; the present application improves the production batch traceability and controllability through feed production manufacturing, and ensures the stability of raw material mixing quality from the source.

Description

Technical Field

[0001] This invention relates to the field of intelligent feed production technology, and in particular to a method and system for managing an MES system based on intelligent feed production. Background Technology

[0002] In feed production, the mixing, pelleting, and hydrothermal treatment processes typically rely on empirical parameters for control, lacking real-time monitoring and dynamic adjustment mechanisms. This leads to uneven mixing, inconsistent pellet structures, and significant fluctuations in product quality. Particularly during mixing and hydrothermal treatment, it is difficult to simultaneously collect and correlate changes in raw material physical properties and process parameters, making it challenging to pinpoint abnormal processes in a timely manner, thus impacting production efficiency and finished product qualification rates. Furthermore, existing methods lack robust recording and feedback mechanisms for parameter adjustments, failing to provide cross-batch optimization and traceability, and thus hindering intelligent management of the production process. To address these issues, this invention provides a feed production control method based on a MES system. By acquiring raw material structural parameters, constructing mixing state curves, dynamically adjusting mixing and hydrothermal treatment parameters, acquiring pellet structure characteristic data, and recording and analyzing changes in parameters and material states at each stage, this method achieves real-time monitoring, anomaly localization, and closed-loop optimization of the production process. Summary of the Invention

[0003] Therefore, it is necessary to provide a method and system for MES system management based on intelligent feed production manufacturing to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a management and control method for an MES system based on intelligent feed production includes the following steps: Step S1: Select the target feed formula and generate a production batch in the MES system, and obtain the structural parameters of each feed ingredient; Step S2: Determine the mixing equipment parameters based on the structural parameters of each feed ingredient, and construct a mixing state curve during the mixing process; determine the degree of mixing of the raw materials based on the mixing state curve, and dynamically adjust the mixing equipment parameters until the degree of mixing meets the uniformity condition; Step S3: After the raw material mixing degree meets the preset uniformity condition, the mixture is granulated and the particle structure characteristic data is obtained; the structural consistency state is determined based on the particle structure characteristic data, and when the structural consistency state deviates from the preset range, the mixing equipment parameters or hydrothermal treatment parameters are adjusted. Step S4: Record the parameter adjustment process and material status data in each process, and determine the abnormal process steps based on the parameter adjustment process and material status data; write back the parameter correction results corresponding to the abnormal process steps to the MES system and record them.

[0005] This invention also provides a management and control system for an MES system based on intelligent feed production manufacturing, used to execute the management and control method for an MES system based on intelligent feed production manufacturing as described above. The management and control system for an MES system based on intelligent feed production manufacturing includes: The structural parameter acquisition module is used to select the target feed formula and generate the production batch in the MES system, and to acquire the structural parameters of each feed ingredient. The mixing equipment parameter determination module is used to determine the mixing equipment parameters based on the structural parameters of each feed ingredient, and to construct a mixing state curve during the mixing process; based on the mixing state curve, the degree of mixing of the raw materials is determined, and the mixing equipment parameters are dynamically adjusted until the degree of mixing meets the uniformity condition; The pelletizing module is used to pelletize the mixture after the raw materials meet the preset uniformity conditions and to acquire particle structure characteristic data; based on the particle structure characteristic data, the structural consistency status is determined, and when the structural consistency status deviates from the preset range, the mixing equipment parameters or hydrothermal treatment parameters are adjusted. The abnormal process identification module is used to record the parameter adjustment process and material status data in each process, and to identify abnormal process links based on the parameter adjustment process and material status data; the parameter correction results corresponding to the abnormal process links are written back to the MES system and recorded.

[0006] The beneficial effects of this invention are as follows: The mixing equipment parameters are determined based on the structural parameters of each feed ingredient, and a mixing state curve is constructed during the mixing process. By monitoring the mixing state in real time and dynamically adjusting the mixing equipment parameters, the uniformity of the raw materials during the mixing process can be ensured. This technical feature can quickly identify mixing deviations, correct parameters in a timely manner, achieve high-precision mixing control, significantly reduce the risk of local material accumulation or stratification, and improve production efficiency and product quality consistency.

[0007] After the raw materials are mixed to a predetermined uniformity, granulation is performed, and particle structure characteristic data is acquired. Simultaneously, the structural consistency is assessed based on these characteristics. When the structural consistency deviates from the predetermined range, the mixing or hydrothermal treatment parameters are adjusted. This ensures that the granulated particles meet process requirements in terms of size, density, and structural consistency. This technology enables closed-loop quality control of the granulation process, reducing rework or waste caused by substandard particle quality, and improving raw material utilization and finished product qualification rate.

[0008] By recording the parameter adjustment process and material status data for each step, and analyzing the trend of material status changes to pinpoint abnormal process steps, the system simultaneously writes the parameter correction results back to the MES system, forming a complete parameter feedback and optimization closed loop. This technology can promptly detect production anomalies, accurately locate problematic steps, provide targeted parameter adjustment suggestions, achieve continuous optimization across batches and improve quality stability, while also enhancing the intelligence and traceability of production management. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating the steps of a MES system control method based on intelligent feed production manufacturing. Figure 2 This is a schematic diagram of the MES system control system based on intelligent feed production and manufacturing. Figure 3 A schematic diagram of the mixing state curve for feed production; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0010] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0011] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0012] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0013] To achieve the above objectives, please refer to Figures 1 to 3 A method for managing an MES system based on intelligent feed production manufacturing includes the following steps: All specific values ​​involved in this embodiment are exemplary parameters used to clearly illustrate the technical operation process and are not the only limitation of the present invention.

[0014] Step S1: Select the target feed formula and generate a production batch in the MES system, and obtain the structural parameters of each feed ingredient; Step S2: Determine the mixing equipment parameters based on the structural parameters of each feed ingredient, and construct a mixing state curve during the mixing process; determine the degree of mixing of the raw materials based on the mixing state curve, and dynamically adjust the mixing equipment parameters until the degree of mixing meets the uniformity condition; Step S3: After the raw material mixing degree meets the preset uniformity condition, the mixture is granulated and the particle structure characteristic data is obtained; the structural consistency state is determined based on the particle structure characteristic data, and when the structural consistency state deviates from the preset range, the mixing equipment parameters or hydrothermal treatment parameters are adjusted. Step S4: Record the parameter adjustment process and material status data in each process, and determine the abnormal process steps based on the parameter adjustment process and material status data; write back the parameter correction results corresponding to the abnormal process steps to the MES system and record them.

[0015] In one embodiment, the MES system receives production task instructions, calls a preset feed formula library according to the production task, selects a target feed formula, and generates a corresponding production batch number. Based on the production batch number, it reads the type and ratio information of each feed ingredient in the formula and drives the raw material metering system to complete the weighing and feeding of each ingredient. During the feeding process, the particle size distribution and bulk density of each feed ingredient are collected online by a particle size screening device and a density detection device set in the raw material conveying path. At the same time, combined with the ratio information of powder and pellet in the formula, a corresponding structural parameter dataset is formed, and the structural parameter dataset is written into the MES system for subsequent mixing control.

[0016] Based on the structural parameter data obtained in step S1, the differences in particle size and bulk density of each feed ingredient are analyzed to determine the settling and floating trends of different ingredients during the mixing process, and the stratification risk level is determined accordingly. When a significant settling or floating trend is detected, the feeding system is controlled to feed the ingredients in batches, and the easily settling ingredients are added later. At the same time, a lower speed is set in the early stage of mixing to reduce stratification disturbance, and the speed is increased in the later stage to enhance the mixing effect. During the operation of the mixing equipment, the motor current value and the stirring shaft torque value are collected in real time through current transformers and torque sensors, and a mixing state curve is constructed in chronological order. Based on the mixing state curve, it is determined whether there are local accumulation or unmixed areas in the mixing process. When uneven mixing is detected, the speed is increased or the mixing time is extended to adjust until the mixing state curve tends to stabilize and meets the uniformity judgment condition, thereby outputting a uniformly mixed material.

[0017] After the mixture reaches a homogeneous state, it is conveyed to a conditioner. The current moisture content of the mixture is obtained through an online moisture content detection module and compared with the preset target moisture content for granulation. The amount of water to be added is determined based on the moisture content deviation, and the corresponding amount of steam is added to the material through a steam injection device. The steam releases heat and condenses into water at the same time, thereby simultaneously adjusting the moisture content and temperature of the material. When the material temperature and moisture content meet the granulation conditions, the material is conveyed to the pellet mill, where it is pressed and shaped by the action of the pressure rollers and the die structure. An online detection device is set at the pellet outlet to collect the length, diameter, and density of the particles, forming particle structure characteristic data, which is compared with the preset standard range to determine the consistency of the structure. When particle size deviation or abnormal density is detected, the corresponding mixing or hydrothermal treatment process is traced back, and the relevant parameters are adjusted.

[0018] During the mixing, conditioning, and granulation processes, the parameters of the mixing equipment, hydrothermal treatment parameters, and corresponding mixing degree data, hydrothermal state data, and particle structure characteristic data are recorded in real time and stored sequentially according to production batches and time. Parameter adjustment records are time-aligned with the corresponding material state data to establish a correspondence between parameter changes and material state changes. Based on this correspondence, the trend of material state changes before and after parameter adjustments is analyzed to determine whether the material state converges towards the preset target range. If the material state continues to deviate from the target range after parameter adjustments, it is determined that the parameter adjustment has not achieved the expected effect. The corresponding process is traced back based on the time node of the first deviation to locate the process step where the anomaly occurred. For the abnormal process, the corresponding parameter adjustment records and state change characteristics are extracted, parameter correction results are generated, and written back to the process parameter library of the MES system for subsequent production batches.

[0019] In another embodiment, suppose a production batch formulation includes corn flour, soybean meal, and pellet premix, wherein the corn flour has a particle size range of 0.3~0.8mm and a bulk density of 0.55. The soybean meal has a particle size range of 0.5~1.2mm and a bulk density of 0.62. The granular premix has a particle size of 2.5~3.5mm and a bulk density of 0.75. The three components account for 50%, 30%, and 20% of the total mass, respectively. The particle size distribution curve is obtained through an online screening device, and the average bulk density of each raw material is obtained through a density detection module. The above parameters are combined to form structural parameter data, which is then linked to the current production batch to provide input data for subsequent stratified risk assessment.

[0020] Assume that among the three raw materials obtained in step S1, the particle size difference between the granular premix and the powder is greater than 2 mm, and the bulk density difference is greater than 0.15. If the mixture is not mixed, it is considered to be at high risk. The control system adopts a two-stage mixing strategy: the first stage runs at 50% of the rated speed for 60 seconds, mixing only the powder portion; the second stage adds granular material and increases the speed to 90% of the rated speed, continuing mixing for 120 seconds. During the mixing process, current and torque data are collected every 100ms, and a set of data is formed every 10 samples. The average current and torque fluctuation value are calculated and a mixing state curve is plotted. When the current change rate of 5 consecutive sets of data is less than 5% and the torque fluctuation value is less than 8% of the rated torque, it is determined that the mixing has reached a uniform state, the mixing process ends and the mixed material is output to the next process.

[0021] Assuming the initial moisture content of the mixture is 10.5% and the target granulation moisture content is 15%,... The moisture content deviation is 4.5. Based on the steam condensation efficiency, the required steam amount is calculated to be 0.045 kg / kg of material, and the steam action time is set to 30 seconds to reduce the material temperature from 25°C. Increased to 75 During the granulation process, the pressure of the pressure roller was set to 3.5 MPa and the diameter of the die hole was 4 mm. Online detection results showed that the particle length was 8~12 mm, the diameter was 3.8~4.2 mm, and the density was 0.85~0.92. When the density of a batch of particles dropped to 0.78, it was determined that the structural consistency had deviated. Adjustments were made by increasing the steam treatment time to 35 s or appropriately increasing the pressure of the pressure roller to restore the stability of the particle structure.

[0022] Suppose that during a certain batch of production, the mixing speed was increased from 80% to 100%, corresponding to an increase in mixing uniformity from 0.92 to 0.95. However, in the subsequent granulation stage, the particle density decreased from 0.90 to 0.78. Time alignment analysis revealed that the density anomaly occurred after the steam treatment time was adjusted from 30s to 20s, and the material moisture content decreased from 15% to 12%. Based on this, the anomaly was determined to originate from the hydrothermal treatment process, and a correction strategy was generated: restore the steam treatment time to 30s and increase the steam input by 10%. This correction result was written into the MES system and called upon in the next batch of production to verify that the particle density was restored to the range of 0.88~0.92, thus achieving closed-loop optimization of production parameters.

[0023] Preferably, step S2 includes: Based on the structural parameters of each feed ingredient, assess the risk level of ingredient stratification and determine the initial mixing equipment parameters; During the operation of the raw material mixing equipment, the motor current value and the stirring shaft torque value are collected at fixed time intervals. The continuously collected data are calculated in groups and a mixing state curve is constructed in time sequence. The current change rate and torque fluctuation value are calculated based on the mixed state curve, and a uniform judgment result is output according to the preset judgment conditions. When the uniformity determination result is non-uniform, the mixing speed or mixing time is adjusted according to the degree of deviation, and the data acquisition and uniformity determination are re-executed.

[0024] In one embodiment, the structural parameters of each feed ingredient obtained in step S1, including particle size distribution, bulk density, and powder / particle ratio, are acquired in the MES system. The settling or floating trend of each ingredient during the mixing process is analyzed based on particle size and density differences, and the stratification risk level (high or low) is assessed accordingly. Initial mixing equipment parameters are set according to the stratification risk level: for high stratification risk, a batch feeding strategy is adopted, with the initial mixing speed at 40% of the rated speed. ~60 Later, the percentage is increased to 80%~100%; for low-level stratification risk, a single feeding method is adopted, with a feed rate of 70%. ~90 The mixing process is carried out at a constant speed. During the mixing process, the current value of the main motor of the mixer and the torque value of the stirring shaft are collected at fixed time intervals (e.g., every 100ms). The continuously collected data are grouped (e.g., 10 groups of data per group) to calculate the average current and torque fluctuation values, and the mixing state curve is plotted in chronological order.

[0025] The system calculates the current change rate and torque fluctuation value based on the mixing state curve and compares them with preset uniformity judgment conditions: when the current change rate is less than 5%~10% and the torque fluctuation amplitude is less than 5%~10% of the rated torque, the material is judged to be uniform; otherwise, it is judged to be non-uniform. When the judgment result is non-uniform, the system automatically adjusts the mixing speed or extends the mixing time according to the degree of deviation, and re-collects current / torque data and reconstructs the mixing state curve until the uniformity judgment conditions are met.

[0026] In another embodiment, suppose a production batch formula includes 50 kg of corn flour, 30 kg of soybean meal, and 20 kg of pellet premix, wherein the corn flour has a particle size of 0.3~0.8 mm and a bulk density of 0.55. Soybean meal particle size 0.5~1.2mm, bulk density 0.62 The granular premix has a particle size of 2.5~3.5mm and a bulk density of 0.75. Based on particle size differences greater than 2 mm and density differences greater than 0.15... It was determined to be a high-risk level.

[0027] The initial mixing equipment parameters were set as follows: powder was added first and mixed at low speed for 60 seconds (50% of the rated speed), then granular material was added and the speed was increased to 90%, and mixing continued for 120 seconds. The sampling system synchronously collected motor current and stirring shaft torque values ​​at 100ms intervals, with each set of 10 samples calculating the average current and torque fluctuation, and plotting a mixing state curve. Assuming the initial calculation results showed a current change rate of 12% and torque fluctuation of 18% of the rated torque, failing to meet the uniformity criteria (current change rate ≤ 5%, torque fluctuation ≤ 10%), the system automatically increased the speed from 90% to 100% and extended the mixing time by 15 seconds.

[0028] After adjustment, 10 sets of data were collected again. The current change rate was reduced to 4%, and the torque fluctuation was reduced to 7% of the rated torque. The uniformity judgment condition was met, and the uniform mixture was output to the next process.

[0029] Preferably, during the operation of the raw material mixing equipment, the motor current value and the stirring shaft torque value are collected at fixed time intervals. The continuously collected data are calculated in groups and a mixing state curve is constructed in chronological order, including: A current transformer is installed at the input end of the main motor of the mixing equipment, and a torque sensor is installed at the output end of the stirring shaft, and they are activated synchronously when the equipment is started. The motor current value and the stirring shaft torque value at the same moment are sampled synchronously with a fixed sampling period, and the continuously sampled data are divided into several acquisition groups according to the time sequence. The average current value is calculated for the current value in each acquisition group, and the torque fluctuation value is calculated by the difference between the maximum and minimum torque values. The calculation results are then marked with time sequence. A mixed-state curve is constructed with the acquisition sequence as the horizontal axis and the average current and torque fluctuation as the vertical axis.

[0030] In one embodiment, during the operation of the raw material mixing equipment, a current transformer is installed at the input end of the main motor and a torque sensor is installed at the output end of the stirring shaft. These sensors are activated synchronously upon equipment startup. During operation, the motor current and stirring shaft torque values ​​are sampled synchronously at a fixed sampling period (e.g., every 100ms). The continuously collected data is divided into several sampling groups according to time sequence, with each group containing a fixed number of continuous sampled values. The average current value is calculated for each sampling group, and the torque fluctuation value is calculated by the difference between the maximum and minimum torque values. Time series information is marked on the calculation results. A mixing state curve is plotted using the sampling group sequence as the horizontal axis and the average current value and torque fluctuation value as the vertical axis to reflect the real-time state of the raw materials within the mixing equipment and the trend of mixing uniformity. Mixing uniformity is evaluated based on preset judgment conditions (e.g., current change rate ≤ 5%, torque fluctuation amplitude ≤ 10%). If the judgment result is non-uniform, the system can automatically adjust the mixing speed or extend the mixing time, and re-execute sampling, calculation, and state curve construction until the uniformity judgment conditions are met.

[0031] In another embodiment, it is assumed that the production batch processed by the MES system includes 50 kg of corn flour, 30 kg of soybean meal, and 20 kg of pellet premix, wherein the corn flour has a particle size of 0.3~0.8 mm and a bulk density of 0.55. Soybean meal has a particle size of 0.5~1.2mm and a bulk density of 0.62g / cm³, while pellet premix has a particle size of 2.5~3.5mm and a bulk density of 0.75g / cm³. The main motor of the mixing equipment has a rated speed of 1000 rpm. Upon startup, the current transformer and torque sensor are simultaneously activated, collecting 500 consecutive frames of current and torque values ​​at a sampling period of 100 ms, with each set of 10 frames constituting a sampling group. The average current value is calculated for each group, and the maximum and minimum difference in torque values ​​is calculated to obtain the torque fluctuation value. The time series is then marked, and a mixing state curve is constructed. Initial calculations show that the current change rate in some sampling groups is 12%, and the torque fluctuation is 18% of the rated torque, failing to meet the uniformity judgment criteria (current change rate ≤ 5%, torque fluctuation ≤ 10%). Based on the degree of deviation, the system increases the mixing speed from 900 rpm to 1000 rpm and extends the mixing time by 15 seconds before resampling. After adjustment, the calculation results show that the current change rate is 4%, and the torque fluctuation is 7% of the rated torque, meeting the uniformity judgment criteria. The mixed material is then output to the next process. This embodiment fully demonstrates the entire process of sampling, calculation, curve construction, judgment, and dynamic adjustment through assumed numerical values, providing a quantitative reference for MES system control methods.

[0032] Please refer to [link / reference needed] for further information. Figure 3The horizontal axis represents the data acquisition sequence, and the vertical axis represents the curves of average current and torque fluctuation. The green vertical line marks the speed adjustment time (speed 900→1000 rpm with a 15-second extension of mixing). Before speed adjustment, the current change rate was 12% and the torque fluctuation was 18%, exceeding the threshold; after speed adjustment, they decreased to 4% and 7% respectively, meeting the uniformity judgment condition.

[0033] Preferably, the average current value is calculated for the current values ​​in each acquisition group, and the torque fluctuation value is calculated by the difference between the maximum and minimum torque values. The calculation results are then marked with the following time sequence: Sum the motor current values ​​and divide by the number of samples to obtain the average current value of the corresponding sampling group; The torque values ​​of the stirring shaft are sorted, and the maximum and minimum values ​​are extracted and the difference is calculated to obtain the torque fluctuation value. The current characterization value and the torque fluctuation characterization value are output sequentially according to the order in which they are generated by the acquisition group, forming a continuously changing data sequence, which serves as the basis for constructing the mixed state curve.

[0034] In one embodiment, during the operation of the raw material mixing equipment, a current transformer is installed at the input end of the main motor and a torque sensor is installed at the output end of the stirring shaft. These sensors are activated synchronously upon equipment startup. During operation, the motor current and stirring shaft torque values ​​are sampled synchronously at a fixed sampling period. The continuously sampled data is divided into several acquisition groups according to time sequence. The motor current values ​​in each acquisition group are summed and divided by the number of samples to obtain the average current value for that group. The stirring shaft torque values ​​are sorted, and the maximum and minimum values ​​are extracted and their differences are calculated to obtain the torque fluctuation value for that group. Subsequently, the average current value and torque fluctuation value are output sequentially according to the acquisition group sequence, forming a continuously changing data sequence as the basis for constructing the mixing state curve. Based on the constructed mixing state curve, the system can determine the mixing uniformity. When the determination result indicates that the uniformity condition has not been met, the mixing speed is automatically adjusted or the mixing time is extended according to the degree of deviation, and data is re-acquired for state curve updates and uniformity determination.

[0035] In another embodiment, it is assumed that the production batch being processed includes 50 kg of corn flour, 30 kg of soybean meal, and 20 kg of pellet premix, wherein the corn flour has a particle size of 0.3~0.8 mm and a bulk density of 0.55 g / cm³, and the soybean meal has a particle size of 0.5~1.2 mm and a bulk density of 0.62 g / cm³. The granular premix has a particle size of 2.5~3.5mm and a bulk density of 0.75. The main motor of the mixing equipment has a rated speed of 1000 rpm. Upon startup, the current transformer and torque sensor are simultaneously activated, continuously collecting 500 frames of current and torque values ​​at a sampling period of 100 ms, with each set of 10 frames forming a sampling group. The average current value is obtained by summing the current values ​​in each group and dividing by the number of samples. The maximum and minimum torque values ​​are extracted, and the difference is calculated to obtain the torque fluctuation value. The average current value and torque fluctuation value of each sampling group are output in chronological order to construct a mixing state curve. Initial calculations show that the current change rate in some sampling groups is 12%, and the torque fluctuation is 18% of the rated torque, failing to meet the uniformity judgment criteria (current change rate ≤ 5%, torque fluctuation ≤ 10%). Based on the degree of deviation, the system increases the mixing speed from 900 rpm to 1000 rpm and extends the mixing time by 15 seconds before resampling. After adjustment, the current change rate is 4%, and the torque fluctuation is 7% of the rated torque, meeting the uniformity judgment criteria. The mixing process is then completed, and the material is output to the next process. This embodiment demonstrates the entire process of sampling, calculation, curve construction, judgment, and dynamic adjustment by assuming complete numerical values, providing a quantifiable technical implementation reference for MES system management.

[0036] Preferably, the calculation of the current change rate and torque fluctuation value based on the mixed state curve, and the output of a uniform judgment result according to preset judgment conditions, includes: Calculate the rate of change of current and torque fluctuation based on the mixed state curve; When the torque fluctuation value of the mixing equipment fluctuates periodically during the mixing process and the fluctuation amplitude exceeds 15%~25% of the rated torque, it is determined that there is local accumulation of material. This can be addressed by increasing the mixing speed to 110%~130% of the rated speed or extending the mixing time by 10%~30%. When the rate of change of motor current decreases to within 5% to 10% of the rated current and tends to stabilize over time, it is determined that the overall mixing of materials tends to be uniform. When the torque fluctuation value decreases to within 5%~10% of the rated torque and the current fluctuation amplitude decreases to within 3%~8% of the rated current, it is determined that the raw materials have reached a uniform distribution state inside the mixer, and a uniformity judgment result is output.

[0037] In one embodiment, during the operation of the raw material mixing equipment, the system calculates the current change rate and torque fluctuation value based on the established mixing state curve, using the average motor current and stirring shaft torque fluctuation value of each data acquisition group. Statistical analysis is performed on the motor current change rate to obtain the maximum, minimum, and average change amplitude within the continuous acquisition period. Periodic analysis is performed on the torque fluctuation value to identify periods where the fluctuation amplitude exceeds a preset threshold, and the corresponding time points are recorded. If the torque fluctuation value exhibits periodic fluctuations and the amplitude exceeds 15%~25% of the rated torque, the system determines that there is localized material accumulation and can automatically increase the mixing speed to 110%~130% of the rated speed or appropriately extend the mixing time by 10%~30% according to the control strategy, while continuing to acquire current and torque data for status updates. Subsequently, when the motor current change rate decreases to within 5%~10% of the rated current and tends to stabilize over time, while the torque fluctuation value decreases to within 5%~10% of the rated torque and the current fluctuation amplitude stabilizes within 3%~8% of the rated current, the system determines that the raw materials have reached a uniform distribution state inside the mixer and outputs a uniform determination result, providing a control basis for subsequent material conveying or processing.

[0038] In another embodiment, it is assumed that the production batch being processed consists of 50 kg of corn flour, 30 kg of soybean meal, and 20 kg of pellet premix. The mixer's rated speed is 1000 rpm, rated current is 15 A, and rated torque is 5 Nm. Based on the mixing state curve analysis, the initial current change rate is 12%, and the torque fluctuation is 20% of the rated torque, indicating the presence of localized accumulation. According to a preset control strategy, the system increases the mixing speed to 1100 rpm (110% of the rated speed) and extends the mixing time by 20%. After resampling, the current change rate decreases to 8%, and the torque fluctuation decreases to 9% of the rated torque, meeting the preset uniformity judgment condition. Under this condition, the system determines that the raw materials are uniformly distributed within the mixer and outputs the uniformity judgment result. Simultaneously, this state is recorded in the MES system database for batch tracking and production scheduling optimization. This embodiment demonstrates the complete control process of current and torque change analysis, automatic speed adjustment and delay control, uniformity judgment, and result output using assumed values.

[0039] Preferably, step S3 includes: Based on the mixture materials that meet the homogeneity condition, determine the corresponding hydrothermal treatment parameters and output hydrothermal treatment control commands; During the execution of hydrothermal treatment control commands, material temperature and moisture content data are collected, and the material hydrothermal state is generated; The material is granulated in a hydrothermal state, and particle structure characteristic data is generated. The structural consistency state is determined based on the particle structure characterization results, and parameter adjustment results are generated when the structural consistency state deviates from the preset range.

[0040] In one embodiment, based on the homogeneity of the mixture, corresponding hydrothermal treatment parameters (including heating temperature, heating time, steam humidity, etc.) are determined, and hydrothermal treatment control commands are generated to control the hydrothermal treatment device to heat and humidify the mixture. During the execution of the control commands, the MES system collects material temperature and moisture content data in real time, and generates a material hydrothermal state curve through sensors or infrared / microwave detection modules to describe the temperature and moisture content distribution of the material at various time points. After hydrothermal treatment, the material enters the granulation stage, where the system collects structural feature data such as particle size, density, and surface texture to generate particle structure characterization results.

[0041] Subsequently, the MES system judges the consistency of the structure based on the particle structure characterization results. When the consistency of the particle structure deviates from the preset range (such as size deviation exceeding ±5% or density difference exceeding ±10%), it automatically generates parameter adjustment results and feeds them back to the hydrothermal treatment or granulation process to optimize control and achieve controllable material particle uniformity and production quality.

[0042] In another embodiment, assuming the batch of mixed feed being processed consists of 60 kg of corn flour, 25 kg of soybean meal, and 15 kg of premix, initial uniform mixing is deemed acceptable. The system determines the hydrothermal treatment parameters based on empirical rules: heating temperature 75℃, heating time 15 minutes, and steam humidity 60%. During execution, the material temperature over time was collected as [70, 72, 74, 75, 74, 73, 75, 76, 75, 74]℃, and the moisture content was [12, 13, 13.5, 14, 14, 13.8, 14.2, 14, 13.9, 14]%. After pelleting, the average pellet size was 6.2 mm, with a maximum deviation of 0.35 mm, and the average pellet density was 0.72 g / cm³, with a maximum deviation of 0.05 g / cm³. Based on the pellet structure characterization results, the system determines that the structural consistency is within the preset range, and no parameter adjustment is required. If it is assumed that the particle density deviation reaches 0.08 g / cm³, the system will generate parameter adjustment results, such as increasing the hydrothermal treatment humidity to 65% or extending the heating time by 2 minutes, to correct the particle structure and achieve uniform granulation and stable quality output.

[0043] Preferably, based on the state of the mixture where the degree of mixing meets the homogeneity condition, generating corresponding hydrothermal treatment parameters and outputting hydrothermal treatment control commands includes: After mixing, the moisture content of the materials is tested to obtain the initial moisture content of the materials; The initial moisture content of the material is compared with the target granulation moisture content to calculate the moisture content deviation; When the moisture content deviation is greater than the preset range, the amount of water to be added is determined according to the moisture content deviation, and the amount of water to be added is converted into the amount of steam added according to the ratio of steam condensation to water. Based on the determined amount of steam added, the steam treatment time is adjusted according to the effect of steam heat release on material temperature to keep the material temperature within the allowable range for granulation, thereby obtaining the hydrothermal treatment parameters.

[0044] In one embodiment, the system detects the moisture content of the mixed material to obtain its initial moisture content value. Then, it compares the initial moisture content with the target granulation moisture content to calculate the moisture content deviation. If the moisture content deviation exceeds a preset range, the required amount of water to be added is determined based on the magnitude of the deviation. Combining this with the proportional relationship between steam condensation and water conversion, the required amount of water is converted into the corresponding amount of steam added. The system dynamically corrects the steam application time based on the impact of the heat released by the steam on the material temperature, ensuring that the material temperature remains within the allowable range during granulation. The MES system integrates parameters such as the amount of water added, the amount of steam added, and the application time to generate hydrothermal treatment parameters, and sends these parameters to the hydrothermal treatment device in the form of control commands, achieving precise control of the material's hydrothermal state.

[0045] In another embodiment, assuming the initial moisture content of a batch of mixed materials is 12.5% ​​and the target granulation moisture content is 14%, the moisture content deviation is 1.5%. Based on experimental or empirical ratios, the steam condensation conversion rate is 70%, thus calculating that the required water supplement is approximately 1.5 kg, corresponding to a steam addition of approximately 2.1 kg. The heat released by the steam raises the material temperature by approximately 3°C / minute. Considering the allowable granulation temperature range of 70°C~80°C, the system corrects the steam action time to 8 minutes. The generated hydrothermal treatment parameters are: water supplement 1.5 kg, steam addition 2.1 kg, and action time 8 minutes. Control commands are then sent to the hydrothermal treatment device via the MES system to ensure that the material reaches the expected hydrothermal state before granulation.

[0046] Preferably, the process of granulating the material in a hydrothermal state and generating particle structure characteristic data includes: When the hydrothermal state data meets the granulation moisture content and temperature conditions, the material is transported to the granulation equipment and pressed and shaped under the set pressure roller pressure and die hole structure to obtain the initial granules after granulation. The initial particles after granulation are collected online to obtain particle length and diameter data, and particle density characterization data are obtained based on the stress of the particles during the pressing process. The particle length and diameter data are compared with the preset particle size range to obtain the size deviation results, and the particle density characterization data are compared with the preset density range to obtain the density deviation results. Particle structure feature data are generated based on the size deviation results and the density deviation results.

[0047] In one embodiment, when the material's hydrothermal state data meets the moisture content and temperature requirements for granulation, the system conveys the material to the granulation equipment. Under the set pressure of the pressure rollers and the die structure, the material is pressed and shaped to obtain initial granules. Subsequently, the system measures the granulated granules using an online acquisition device, acquiring the length and diameter data of each granule, and combines this with the stress on the granules during the pressing process to generate granule density characterization data. Next, the granule length and diameter data are compared with a preset granule specification range to calculate the dimensional deviation results. Simultaneously, the granule density characterization data is compared with a preset density range to obtain density deviation results. Based on the dimensional deviation results and density deviation results, the system generates granule structure characteristic data, providing data support for subsequent product quality monitoring or process adjustment.

[0048] In another embodiment, assuming the material moisture content before granulation is 14% and the temperature is 75°C, the granulation equipment is set with a pressure roller pressure of 2.5 MPa and a die orifice diameter of 5 mm. After granulation, the online collected particle length is 4.9 mm to 5.2 mm, the diameter is 4.8 mm to 5.1 mm, and the particle density characterization value is 0.92 to 0.96. Comparing the particle length with the preset specification of 5 mm ± 0.2 mm, the size deviation result is calculated to be ± 0.1 mm; comparing the density characterization value with the preset density range of 0.9 to 0.95, the density deviation is obtained to be 0.01 to 0.06. The system integrates the size deviation and density deviation to generate particle structure feature data, which is used to judge the granulation quality and guide subsequent parameter adjustments.

[0049] Of particular importance, step S4 includes: During the operation of each production process, the records of mixing equipment parameter adjustment, hydrothermal treatment parameter adjustment, and corresponding mixing degree data, hydrothermal state data, and particle structure characteristic data are collected synchronously and stored in sequence according to production batch and time. Match and analyze the parameter adjustment records of each process with the corresponding material status data, identify the trend of material status changes before and after parameter adjustment, and locate the process link where the anomaly occurred based on the time when the material status deviates from the preset range. For identified abnormal process steps, extract the corresponding parameter adjustment records and material status change characteristics, generate parameter correction results, and write the parameter correction results back to the corresponding process parameter library of the MES system for use in subsequent production batches.

[0050] In one embodiment, during the operation of each production process, the system synchronously collects records of mixing equipment parameter adjustments, hydrothermal treatment parameter adjustments, and corresponding data on mixing degree, hydrothermal state, and particle structure characteristics. These data are then stored sequentially by production batch and time. The system matches and analyzes the parameter adjustment records of each process with the corresponding material state data to identify trends in material state changes before and after parameter adjustments. Based on the time points when the material state deviates from a preset range, the system locates the process steps where an anomaly occurred. For identified abnormal process steps, the system extracts the corresponding parameter adjustment records and material state change characteristics, generates parameter correction results, and writes these results back to the corresponding process parameter library in the MES system for subsequent production batches, achieving process optimization and quality control.

[0051] In another embodiment, assuming that in three consecutive batches of production, the mixing equipment speed is adjusted to 105 rpm, 110 rpm, and 115 rpm, respectively, and the hydrothermal treatment temperature is adjusted to 72℃, 75℃, and 78℃, respectively. The mixing degree data collected by the system simultaneously are 85%, 88%, and 82%, the water content of the hydrothermal state data is 13.8%, 14.1%, and 13.5%, and the particle density is 0.91, 0.94, and 0.87, respectively. Through matching analysis, it was found that the third batch had low material moisture content and low particle density in the hydrothermal treatment stage, and the abnormal stage was located as insufficient hydrothermal treatment temperature. The system extracts the hydrothermal parameter adjustment records and material state change characteristics of the third batch, and generates parameter correction results: increase the hydrothermal temperature to 75℃~77℃ and extend the treatment time by 5 minutes, and write the correction results back to the MES system process parameter library for automatic recall in subsequent batches to achieve continuous optimization control.

[0052] Most importantly, the parameter adjustment records of each process are matched and analyzed with the corresponding material status data to identify the trend of material status changes before and after parameter adjustments, and to pinpoint the process steps where anomalies occur based on the time when the material status deviates from the preset range. According to the production batch and time sequence, the parameter adjustment records of each process are aligned with the material status data at the corresponding time to establish the correspondence between parameter changes and material status changes. Based on the correspondence, extract the material state data within the continuous time period before and after parameter adjustment, calculate the magnitude of material state change, and determine whether the material state change converges to the preset target range or continues to deviate. When the material status continues to deviate from the preset range after parameter adjustment, it is determined that the corresponding parameter adjustment has not achieved the expected effect, and the process is traced back to the time point of the first deviation to locate the process link where the abnormality occurred.

[0053] In one embodiment, the system aligns the parameter adjustment records of each process with the material status data at the corresponding time according to the production batch and time sequence, establishing a correspondence between parameter changes and material status changes. Based on this correspondence, the system extracts material status data within consecutive time periods before and after parameter adjustments, calculates the magnitude of material status changes, and determines whether the material status changes converge towards a preset target range or continue to deviate. When the material status continues to deviate from the preset range after parameter adjustments, the system determines that the corresponding parameter adjustment has not achieved the expected effect, and traces back to the corresponding process based on the time node of the first deviation, thereby locating the process as the link where the anomaly occurred, providing a basis for subsequent parameter correction.

[0054] In another embodiment, assuming that in a certain production batch, the mixing speed is adjusted from 100 rpm to 110 rpm at time t1, and the hydrothermal treatment temperature is adjusted from 72℃ to 75℃ at time t2. Time alignment analysis reveals that the mixing degree remains at 82% 10 minutes after t1, lower than the target of 85%~90%; simultaneously, the moisture content of the hydrothermal state is still 13.5% 15 minutes after t2, lower than the target moisture content of 14%~14.5%. Calculations of the material state change show that the deviation has not converged, indicating that the parameter adjustments have not met expectations. Tracing back to the time point of the first deviation reveals that the mixing stage at t1 and the hydrothermal stage at t2 are abnormal process stages. Based on this, the system marks the corresponding stages and generates subsequent parameter correction suggestions for optimization control in the next batch.

[0055] This invention also provides a management and control system for an MES system based on intelligent feed production manufacturing, used to execute the management and control method for an MES system based on intelligent feed production manufacturing as described above. The management and control system for an MES system based on intelligent feed production manufacturing includes: The structural parameter acquisition module 101 is used to select the target feed formula and generate the production batch in the MES system, and to acquire the structural parameters of each feed ingredient. The mixing equipment parameter determination module 102 is used to determine the mixing equipment parameters based on the structural parameters of each feed ingredient, and to construct a mixing state curve during the mixing process; based on the mixing state curve, the degree of mixing of the raw materials is determined, and the mixing equipment parameters are dynamically adjusted until the degree of mixing meets the uniformity condition. The pelletizing module 103 is used to pelletize the mixture after the raw material mixing degree meets the preset uniformity conditions and to obtain particle structure characteristic data; to determine the structural consistency state based on the particle structure characteristic data; and to adjust the mixing equipment parameters or hydrothermal treatment parameters when the structural consistency state deviates from the preset range. The abnormal process identification module 104 is used to record the parameter adjustment process and material status data in each process, and to identify the abnormal process step based on the parameter adjustment process and material status data; and to write back the parameter correction result corresponding to the abnormal process step to the MES system and record it.

[0056] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A management and control method for an MES system based on intelligent feed production manufacturing, characterized in that, Includes the following steps: Step S1: Select the target feed formula and generate a production batch in the MES system, and obtain the structural parameters of each feed ingredient; Step S2: Determine the mixing equipment parameters based on the structural parameters of each feed ingredient, and construct a mixing state curve during the mixing process; determine the degree of mixing of the raw materials based on the mixing state curve, and dynamically adjust the mixing equipment parameters until the degree of mixing meets the uniformity condition; Step S3: After the raw material mixing degree meets the preset uniformity condition, the mixture is granulated and the particle structure characteristic data is obtained; the structural consistency state is determined based on the particle structure characteristic data, and when the structural consistency state deviates from the preset range, the mixing equipment parameters or hydrothermal treatment parameters are adjusted. Step S4: Record the parameter adjustment process and material status data in each process, and determine the abnormal process steps based on the parameter adjustment process and material status data; write back the parameter correction results corresponding to the abnormal process steps to the MES system and record them.

2. The MES system control method based on intelligent feed production manufacturing according to claim 1, characterized in that, Step S2 includes: Based on the structural parameters of each feed ingredient, assess the risk level of ingredient stratification and determine the initial mixing equipment parameters; During the operation of the raw material mixing equipment, the motor current value and the stirring shaft torque value are collected at fixed time intervals. The continuously collected data are calculated in groups and a mixing state curve is constructed in time sequence. The current change rate and torque fluctuation value are calculated based on the mixed state curve, and a uniform judgment result is output according to the preset judgment conditions. When the uniformity determination result is non-uniform, the mixing speed or mixing time is adjusted according to the degree of deviation, and the data acquisition and uniformity determination are re-executed.

3. The MES system control method based on intelligent feed production manufacturing according to claim 2, characterized in that, Based on the structural parameters of each feed ingredient, assess the risk level of ingredient stratification and determine the initial mixing equipment parameters, including: The particle size distribution and bulk density of each feed ingredient are obtained based on its structural parameters. Based on particle size distribution and bulk density, determine the settling or floating trend of each raw material during the mixing process; When the difference in the ratio of easily settling components to easily floating components exceeds a preset range, it is judged as a high risk of stratification; otherwise, it is judged as a low risk of stratification. When there is a high risk of stratification, the order of batch feeding should be determined according to the settling and floating trends. The easily settling components should be added later, and the mixing speed should be reduced to 40% to 60% of the rated speed in the early stage of mixing and increased to 80% to 100% of the rated speed in the later stage. When the risk of stratification is low, the material is fed in one batch and mixed at a constant speed of 70% to 90% of the rated speed to form the initial mixing equipment parameters and write them into the process control register.

4. The MES system control method based on intelligent feed production manufacturing according to claim 2, characterized in that, During the operation of the raw material mixing equipment, motor current and stirring shaft torque values ​​are collected at fixed time intervals. The continuously collected data are calculated in groups and a mixing state curve is constructed in chronological order, including: A current transformer is installed at the input end of the main motor of the mixing equipment, and a torque sensor is installed at the output end of the stirring shaft, and they are activated synchronously when the equipment is started. The motor current value and the stirring shaft torque value at the same moment are sampled synchronously with a fixed sampling period, and the continuously sampled data are divided into several acquisition groups according to the time sequence. The average current value is calculated for the current value in each acquisition group, and the torque fluctuation value is calculated by the difference between the maximum and minimum torque values. The calculation results are then marked with time sequence. A mixed-state curve is constructed with the acquisition sequence as the horizontal axis and the average current and torque fluctuation as the vertical axis.

5. The MES system control method based on intelligent feed production manufacturing according to claim 4, characterized in that, The average current value is calculated for each acquisition group, and the torque fluctuation value is calculated by the difference between the maximum and minimum torque values. The calculation results are then labeled with the time sequence, including: Sum the motor current values ​​and divide by the number of samples to obtain the average current value of the corresponding sampling group; The torque values ​​of the stirring shaft are sorted, and the maximum and minimum values ​​are extracted and the difference is calculated to obtain the torque fluctuation value. The current characterization value and the torque fluctuation characterization value are output sequentially according to the order in which they are generated by the acquisition group, forming a continuously changing data sequence, which serves as the basis for constructing the mixed state curve.

6. The MES system control method based on intelligent feed production manufacturing according to claim 2, characterized in that, The current change rate and torque fluctuation value are calculated based on the mixed state curve, and a uniform judgment result is output according to preset judgment conditions, including: Calculate the rate of change of current and torque fluctuation based on the mixed state curve; When the torque fluctuation value of the mixing equipment fluctuates periodically during the mixing process and the fluctuation amplitude exceeds 15%~25% of the rated torque, it is determined that there is local accumulation of material. This can be addressed by increasing the mixing speed to 110%~130% of the rated speed or extending the mixing time by 10%~30%. When the rate of change of motor current decreases to within 5% to 10% of the rated current and tends to stabilize over time, it is determined that the overall mixing of materials tends to be uniform. When the torque fluctuation value decreases to within 5%~10% of the rated torque and the current fluctuation amplitude decreases to within 3%~8% of the rated current, it is determined that the raw materials have reached a uniform distribution state inside the mixer, and a uniformity judgment result is output.

7. The MES system control method based on intelligent feed production manufacturing according to claim 1, characterized in that, Step S3 includes: Based on the mixture materials that meet the homogeneity condition, determine the corresponding hydrothermal treatment parameters and output hydrothermal treatment control commands; During the execution of hydrothermal treatment control commands, material temperature and moisture content data are collected, and the material hydrothermal state is generated; The material is granulated in a hydrothermal state, and particle structure characteristic data is generated. The structural consistency state is determined based on the particle structure characterization results, and parameter adjustment results are generated when the structural consistency state deviates from the preset range.

8. The MES system control method based on intelligent feed production manufacturing according to claim 7, characterized in that, Based on the state of the mixture meeting the homogeneity condition, corresponding hydrothermal treatment parameters are generated, and hydrothermal treatment control commands are output, including: After mixing, the moisture content of the materials is tested to obtain the initial moisture content of the materials; The initial moisture content of the material is compared with the target granulation moisture content to calculate the moisture content deviation; When the moisture content deviation is greater than the preset range, the amount of water to be added is determined according to the moisture content deviation, and the amount of water to be added is converted into the amount of steam added according to the ratio of steam condensation to water. Based on the determined amount of steam added, the steam treatment time is adjusted according to the effect of steam heat release on material temperature to keep the material temperature within the allowable range for granulation, thereby obtaining the hydrothermal treatment parameters.

9. The MES system control method based on intelligent feed production manufacturing according to claim 7, characterized in that, The material is granulated in a hydrothermal state, and particle structure characteristic data is generated, including: When the hydrothermal state data meets the granulation moisture content and temperature conditions, the material is transported to the granulation equipment and pressed and shaped under the set pressure roller pressure and die hole structure to obtain the initial granules after granulation. The initial particles after granulation are collected online to obtain particle length and diameter data, and particle density characterization data are obtained based on the stress of the particles during the pressing process. The particle length and diameter data are compared with the preset particle specification range to obtain the size deviation results, and the particle density characterization data are compared with the preset density range to obtain the density deviation results. Particle structure feature data are generated based on the size deviation results and the density deviation results.

10. A MES system control system based on intelligent feed production manufacturing, characterized in that, For executing the MES system control method based on intelligent feed production manufacturing as described in claim 1, the MES system control system based on intelligent feed production manufacturing includes: The structural parameter acquisition module is used to select the target feed formula and generate the production batch in the MES system, and to acquire the structural parameters of each feed ingredient. The mixing equipment parameter determination module is used to determine the mixing equipment parameters based on the structural parameters of each feed ingredient, and to construct a mixing state curve during the mixing process; based on the mixing state curve, the degree of mixing of the raw materials is determined, and the mixing equipment parameters are dynamically adjusted until the degree of mixing meets the uniformity condition; The pelletizing module is used to pelletize the mixture after the raw materials meet the preset uniformity conditions and to acquire particle structure characteristic data; based on the particle structure characteristic data, the structural consistency status is determined, and when the structural consistency status deviates from the preset range, the mixing equipment parameters or hydrothermal treatment parameters are adjusted. The abnormal process identification module is used to record the parameter adjustment process and material status data in each process, and to identify abnormal process links based on the parameter adjustment process and material status data; the parameter correction results corresponding to the abnormal process links are written back to the MES system and recorded.

Images