Intelligent control system for feed production

Abstract

The invention discloses an intelligent control system for feed production, and relates to the technical field of intelligent control for feed production, a data acquisition module acquires and integrates multi-dimensional data such as raw material flow, crusher rotating speed, production line idle time and energy consumption in real time through a raw material flow monitoring unit and an energy consumption and equipment state monitoring unit. A data set W composed of the parameters can provide comprehensive real-time data support for subsequent optimization scheduling and production control, and it is ensured that key information in the production process is not lost. A denoising processing unit in the data processing module adopts a filtering algorithm, random noise generated in the acquisition process is effectively filtered out, and a missing value is filled by using a mean value filling method, so that a more accurate data denoising set WC is generated. By dynamically regulating and controlling the raw material flow and the equipment running speed, accurate management of energy consumption and continuous optimization of the crushing effect are realized, and the stability of feed quality is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of feed production, and in particular to an intelligent control system for feed production. Background Art

[0002] The intelligent control system for feed production belongs to the field of modern intelligent manufacturing technology, especially in the intelligent production management in agriculture and food processing industries. In recent years, intelligent control technology has been widely used in various industrial manufacturing scenarios to improve production efficiency, reduce labor costs and achieve rational allocation of resources. Specifically in feed production, intelligent control can achieve real-time adjustment of equipment parameters through data-driven and algorithm optimization in a complex production environment. Especially for the feed crushing stage, controlling the key parameters of the crusher such as speed and operation time can not only improve the crushing quality, but also optimize energy consumption.

[0003] In the field of feed production, the traditional crushing process relies on manual or preset parameter settings, and it is difficult to dynamically respond to changes in the production process, such as fluctuations in raw material characteristics, equipment status, or environmental parameters. This leads to unstable feed crushing effects, which directly affects the quality of the final product. In traditional production methods, it is difficult to avoid energy waste in the crushing process, and problems such as equipment idling or insufficient raw material crushing occur frequently, reducing overall production efficiency. In response to these situations, traditional feed production often finds it difficult to achieve flexible and efficient production scheduling, with low resource and energy utilization and increased production costs.

[0004] When the nature of raw materials in production changes, the equipment status fluctuates, or the resource allocation is unreasonable, the system cannot adjust in time due to the lack of intelligent scheduling and adaptive control, resulting in long-term idle equipment or uneven load. Ultimately, this defect leads to abnormal effects such as low production efficiency, substandard product quality, and serious waste of resources. It may even cause equipment failure and downtime due to unbalanced equipment load, further increasing production costs and maintenance expenses. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent control system for feed production, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a feed production intelligent control system, including a data acquisition module, a data processing module, a production scheduling optimization module, an intelligent control module, a performance evaluation module and a feedback adjustment module;

[0007] The data acquisition module collects multi-dimensional parameters in the production process in real time through sensors and monitoring devices to form a data set W;

[0008] The data processing module preprocesses the collected data set W, including denoising, filling missing values ​​and data standardization, to obtain a data standard set WB;

[0009] The production scheduling optimization module calculates the data standard set WB by using the particle swarm optimization algorithm to obtain a generation scheduling solution and generate a scheduling plan;

[0010] The intelligent control module adjusts the production parameters according to the scheduling plan and sets a real-time feedback mechanism to update the production parameters according to the production progress;

[0011] The performance evaluation module evaluates the performance of the production process within a fixed period according to the updated production parameters, compares the production efficiency Eff, energy consumption E and raw material utilization rate Uma before and after the adjustment, and generates an evaluation result report;

[0012] The feedback adjustment module continuously adjusts production parameters based on the evaluation result report and real-time data.

[0013] Preferably, the data acquisition module includes a raw material flow monitoring unit and an energy consumption and equipment status monitoring unit;

[0014] The raw material flow monitoring unit monitors the inflow of raw materials in real time through a flow sensor and records the raw material flow Q per unit time;

[0015] The energy consumption and equipment status monitoring unit records the mill speed RPM, production line idle time Tid and energy consumption E in real time through the energy consumption monitor and equipment status sensor, and integrates the raw material flow Q, mill speed RPM, production line idle time Tid and energy consumption E to form a data set W.

[0016] Through the combination of these two units, the data acquisition module can obtain multi-dimensional parameters of the production process in real time, including raw material flow Q, crusher speed RPM, production line idle time Tid and energy consumption E, forming a data set W, which provides a basis for subsequent data processing and optimization.

[0017] Preferably, the data processing module includes a denoising processing unit and a data standardization unit;

[0018] The denoising processing unit performs denoising on the collected data set W using a filtering algorithm to eliminate random noise; fills in missing values ​​using a mean filling method to obtain a denoised data set WC;

[0019] The data standardization unit performs standardization processing on the data denoising set WC by using a Z-score standardization method, converts data of different dimensions into the same standard, and obtains a data standard set WB.

[0020] Preferably, the production scheduling optimization module includes a particle swarm optimization algorithm unit and a scheduling plan generation unit;

[0021] The particle swarm optimization algorithm unit calculates and obtains the device status and resource availability according to the data standard set WB, and generates a scheduling plan by analyzing the device status and resource availability using the particle swarm optimization algorithm;

[0022] The equipment status includes equipment efficiency coefficient Eeff and equipment utilization rate Uep;

[0023] The equipment efficiency coefficient Eeff is obtained by the ratio of the product of the raw material flow rate Q and the pulverizer speed RPM to the unit time; the equipment efficiency coefficient Eeff reflects the efficiency of the equipment when executing the task, ranging from 0 to 1; the equipment utilization rate Uep is obtained by the ratio of the production line idle time Tid to the total production time Tto; the equipment utilization rate Uep indicates the degree of use of the equipment within the planned time;

[0024] The resource availability includes the raw material consumption rate Pco and the resource availability coefficient Are;

[0025] The raw material consumption rate Pco is obtained by multiplying the raw material flow rate Q by the mill speed RPM, and the resource availability coefficient Are is obtained according to the inventory, the total production time Tto and the energy consumption E; the raw material consumption rate Pco represents the raw material consumption required for the production task, and the resource availability coefficient Are reflects the adequacy of the current resources;

[0026] The content of the scheduling plan includes selecting equipment that meets the current task requirements based on the equipment efficiency coefficient Eeff and the equipment utilization rate Uep, constraining resources through the raw material consumption rate Pco and the resource availability coefficient Are, allocating resources according to task requirements, and preventing resource consumption overload.

[0027] Preferably, the scheduling plan generation unit generates a scheduling plan according to the scheduling scheme output by the particle swarm optimization algorithm unit;

[0028] The scheduling plan is specifically as follows:

[0029] When 0.5<equipment efficiency coefficient Eeff<1 and 0.5<equipment utilization rate Uep<1, obtain the first equipment scheduling plan, mark the current equipment as running state X=1, and do not schedule the running state of the current equipment;

[0030] When the equipment efficiency coefficient Eeff is less than 0.5 and the equipment utilization rate Uep is less than 0.5, the second equipment scheduling plan is obtained, and the current equipment is marked as the operating state X=2, the operating state of the current equipment is scheduled, and the work task of the current equipment is assigned to the equipment in the operating state X=1;

[0031] When the resource availability coefficient Are>1, it means that the resources are sufficient, the first resource scheduling plan is obtained, and the current resource usage state Y=1 is marked, and the current resources are scheduled to the device with resource usage state Y=2;

[0032] When the resource availability coefficient Are≤1, it indicates that the resources are tight, the second resource scheduling plan is obtained, and the current resource usage state Y=2 is marked, and the current resources are not scheduled.

[0033] The particle swarm optimization algorithm unit updates the speed and position of particles through continuous iterative calculations, and finally obtains the optimal scheduling solution. The scheduling plan generation unit formulates a specific scheduling plan based on the optimization results, and clarifies the operating time and task allocation of each device. The generated scheduling plan can be exported as a report to facilitate management personnel to perform actual operations and adjustments.

[0034] Preferably, the intelligent control module includes a production parameter adjustment unit and a real-time feedback mechanism unit;

[0035] The production parameter adjustment unit dynamically adjusts the production parameters according to the scheduling plan, including the pulverizer speed RPM and the running time Tr, specifically:

[0036] The production target value is set according to the resource availability coefficient Are and the equipment efficiency coefficient Eeff in the scheduling plan, the crusher speed RPM and the running time Tr are calculated and adjusted, and the planned crusher speed RPMnew and the planned running time Trnew are obtained;

[0037] The planned mill speed RPMnew is obtained by multiplying the mill speed RPM by the resource availability coefficient Are, and the planned operating time Trnew is obtained by multiplying the operating time Tr by the equipment efficiency coefficient Eeff;

[0038] When the resource availability coefficient Are>1 and 0.5<equipment efficiency coefficient Eeff<1, the crusher speed RPM is adjusted to the crusher speed RPM plus the crusher speed RPM multiplied by the difference between the resource availability coefficient Are and 1, and the running time Tr is adjusted to the running time Tr plus the running time Tr multiplied by 1 and the equipment efficiency coefficient Eeff.

[0039] When the resource availability coefficient Are is less than 1 and the equipment efficiency coefficient Eeff is less than 0.5, the crusher speed RPM is adjusted to the crusher speed RPM minus the difference between the crusher speed RPM multiplied by 1 and the resource availability coefficient Are, and the operating time Tr is adjusted to the operating time Tr minus the difference between the operating time Tr multiplied by 0.5 and the equipment efficiency coefficient Eeff.

[0040] Preferably, the real-time feedback mechanism unit establishes a real-time feedback system, updates the production parameters according to the production progress, monitors the crushing quality and output during the production process, and makes judgments with the preset crushing quality threshold and output threshold, and feeds back the judgment results to the production parameter adjustment unit;

[0041] The judgment result is obtained by matching in the following way:

[0042] When the crushing quality is less than the crushing quality threshold, it means that the crushing quality does not meet the standard and the production parameters should be updated;

[0043] When the output is less than the output threshold, it means that the output does not meet the standard and the production parameters are updated;

[0044] When the crushing quality is greater than the crushing quality threshold and the output is greater than the output threshold, it means that the crushing quality and output meet the standards and the current production parameters are maintained;

[0045] When the crushing quality and output are lower than the crushing quality threshold and output threshold, the system will automatically trigger the feedback mechanism and pass the feedback information to the production parameter adjustment unit. The production parameter adjustment unit will recalculate and dynamically adjust the crusher speed RPM and running time Tr.

[0046] The real-time feedback mechanism unit monitors the actual operation of the pulverizer through sensors and feeds back real-time data to the adjustment unit. If the monitored production quality or output does not meet expectations, the production parameter adjustment unit recalculates and adjusts the pulverizer's speed RPM and operating time Tr based on the feedback information.

[0047] Continue the above steps to form a closed-loop control to ensure production efficiency and quality.

[0048] Adaptive control algorithms are introduced to dynamically adjust parameters based on real-time data to improve the flexibility and response speed of the system.

[0049] Use machine learning algorithms to analyze historical data, predict future production trends, adjust production parameters in advance, and optimize production processes. Combine multiple key performance indicators including crushing efficiency, energy consumption, and product quality to form comprehensive feedback and improve the intelligence level of the system. Provide a visual interface to display production parameters and feedback information in real time, which is convenient for operators to monitor and adjust manually in real time.

[0050] Preferably, the performance evaluation module includes a production performance data collection unit and an evaluation report generation unit;

[0051] The production performance data collection unit collects historical data and current data of production efficiency Eff, energy consumption E and raw material utilization rate Uma in real time during a fixed period through sensors and monitoring equipment, obtains the improvement status before and after adjustment, including production efficiency increment ΔEff, energy consumption increment ΔE and raw material utilization rate increment ΔUma, and generates an evaluation index Perf through weighted processing;

[0052] The production efficiency Eff is obtained by the ratio of the product output Pou per unit time to the total production time Tto and the maximum production capacity C of the equipment; the raw material utilization rate Uma is obtained by the ratio of the actual amount of raw materials used Mus to the total amount of raw materials input Min;

[0053] The production efficiency increment ΔEff is obtained by adjusting the percentage change of the production efficiency Eff before and after;

[0054] The energy consumption increment ΔE is obtained by adjusting the percentage change of energy consumption E before and after;

[0055] The raw material usage rate increment ΔUma is obtained by adjusting the percentage change of the raw material usage rate Uma before and after the adjustment.

[0056] Preferably, the evaluation report generating unit generates an evaluation result report according to the obtained production efficiency increment ΔEff, energy consumption increment ΔE, raw material utilization rate increment ΔUma and evaluation index Perf;

[0057] Specifically: compare and analyze the differences in production efficiency Eff, energy consumption E and raw material utilization rate Uma before and after adjustment, monitor the production efficiency increment ΔEff, energy consumption increment ΔE and raw material utilization rate increment ΔUma in real time, and evaluate the overall system performance through the evaluation indicator index Perf, and generate an evaluation result report, including the efficiency improvement percentage, energy consumption change percentage and raw material utilization rate improvement effect.

[0058] During the evaluation process, production parameter changes are dynamically monitored and evaluation indicators are updated in real time to ensure the timeliness and accuracy of the evaluation results.

[0059] Introduce machine learning algorithms to analyze historical and real-time data, predict changes in production efficiency, and identify potential problems in advance.

[0060] Develop interactive visualization tools to present assessment results and help operators and management better understand production performance.

[0061] In addition to efficiency and energy consumption, quality control indicators are also introduced to comprehensively evaluate all aspects of the production process and provide more comprehensive optimization suggestions.

[0062] Preferably, the feedback adjustment module includes an adaptive control unit and a parameter adjustment execution unit;

[0063] The adaptive control unit calculates and adjusts production parameters including the pulverizer speed RPM and the running time Tr according to the evaluation result report and the real-time data, and generates an adjustment plan;

[0064] The parameter adjustment execution unit performs the parameter adjustment operation according to the adjustment scheme, specifically:

[0065] sending production parameter updates generated by the adaptive control unit to the production equipment;

[0066] Monitor the adjusted production effects and feed the results back to the adaptive control unit.

[0067] Advanced intelligent algorithms are introduced to further optimize the parameter adjustment process and improve the efficiency of adaptive control.

[0068] Combined with machine learning technology, predict the impact of production environment changes on production parameters, make adjustments in advance, and enhance the system's responsiveness. Consider multiple goals including efficiency, energy consumption, and quality when adjusting parameters, achieve a balance of multiple goals, and improve overall production performance. Develop an intuitive user interface to display the effect of adjusting parameters and production status in real time, and enhance the operator's decision-making ability.

[0069] The present invention provides an intelligent control system for feed production, which has the following beneficial effects:

[0070] (1) When the system is running, the data acquisition module collects and integrates multi-dimensional data such as raw material flow, crusher speed, production line idle time and energy consumption in real time through the raw material flow monitoring unit and the energy consumption and equipment status monitoring unit. The data set W composed of these parameters can provide comprehensive real-time data support for subsequent optimization scheduling and production control, ensuring that key information in the production process is not missing. The denoising processing unit in the data processing module uses a filtering algorithm to effectively filter out the random noise generated during the acquisition process, and uses the mean filling method to fill the missing values, thereby generating a more accurate data denoising set WC. This processing method can not only significantly improve the accuracy of the data, but also avoid the impact of noise and data missing on the scheduling optimization process. Compared with traditional data processing methods, denoising and completion processing improves data quality, making subsequent production control more reliable and accurate.

[0071] (2) The system uses the particle swarm optimization algorithm in the production scheduling optimization module to effectively analyze real-time data in the production process, generate the optimal production scheduling solution and detailed plan, reduce production idle time, and improve the utilization rate of production resources. This intelligent scheduling method solves the problems of resource waste and equipment idling that are common in traditional production models, significantly improves production efficiency and reduces production costs.

[0072] The intelligent control module can automatically adjust the speed, operation time and other parameters of equipment such as the grinder according to the real-time production progress and feedback data to ensure that the production process is always in the optimal state. By dynamically adjusting the raw material flow and equipment operating speed, accurate management of energy consumption and continuous optimization of the crushing effect are achieved, ensuring the stability of feed quality while reducing energy consumption during equipment operation. Through the performance evaluation module and feedback adjustment module, the system evaluates the efficiency, energy consumption and raw material utilization of the production process within a fixed period and generates a detailed evaluation report. With this evaluation and feedback mechanism, the system can continuously optimize production parameters and reduce efficiency losses caused by improper adjustments. In addition, the evaluation report enables managers to have a clear understanding of the production status, helping them to quickly discover potential production problems and ensure that the entire production process is stable and efficient.

[0073] (3) By introducing the equipment efficiency coefficient Eeff and the equipment utilization rate Uep, the production system can accurately measure the efficiency and utilization of the equipment in task execution. This method realizes a comprehensive evaluation of the equipment status, helps to prioritize the scheduling of efficient equipment, and reduce the usage time of inefficient equipment, thereby improving overall production efficiency. Compared with the traditional evaluation method that relies on a single parameter, this method improves the accuracy and rationality of scheduling, and provides a scientific basis for achieving more efficient equipment management.

[0074] By calculating the raw material consumption rate Pco and the resource availability coefficient Are, dynamic monitoring of resource consumption is achieved, and resources are flexibly allocated according to resource availability. This resource monitoring and allocation method effectively reduces the risk of resource overload that may occur during the production process, ensures the rational use of resources, and avoids unnecessary waste. In this way, it is possible to ensure that the output is maximized when resources are sufficient, and to reasonably adjust the scheduling when resources are tight, effectively improving resource utilization.

[0075] (4) The production parameter adjustment unit dynamically adjusts the pulverizer's speed RPM and operating time Tr according to the equipment efficiency coefficient Eeff and the resource availability coefficient Are, realizing intelligent management of equipment parameters, enabling the equipment status in the production process to quickly respond to changes in resource conditions and task requirements, thereby optimizing resource utilization and equipment efficiency. The real-time feedback mechanism unit monitors the pulverization quality and output during the production process, determines whether it meets the standards, and updates the production parameters in real time. This mechanism can ensure that the product quality and output of the production process meet the preset production standards, avoid the problem of substandard quality or insufficient output due to parameter deviation, and thus improve the stability and reliability of production.

[0076] When the equipment efficiency and resource adequacy change, the production parameter adjustment unit in this embodiment can automatically calculate and adjust the operating parameters of the crusher to ensure that the production equipment operates in a reasonable state. Such adaptive adjustment capabilities effectively avoid inefficient operation caused by equipment overload or insufficient resources, thereby ensuring the scientific nature of production scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 The present invention is a schematic diagram of a feed production intelligent control system block diagram. DETAILED DESCRIPTION

[0078] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0079] Example 1

[0080] The present invention provides an intelligent control system for feed production. Figure 1 , including data acquisition module, data processing module, production scheduling optimization module, intelligent control module, performance evaluation module and feedback adjustment module;

[0081] The data acquisition module collects multi-dimensional parameters in the production process in real time through sensors and monitoring devices to form a data set W;

[0082] The data processing module preprocesses the collected data set W, including denoising, filling missing values ​​and data standardization, to obtain a data standard set WB;

[0083] The production scheduling optimization module calculates the data standard set WB by using the particle swarm optimization algorithm to obtain a generation scheduling solution and generate a scheduling plan;

[0084] The intelligent control module adjusts the production parameters according to the scheduling plan and sets a real-time feedback mechanism to update the production parameters according to the production progress;

[0085] The performance evaluation module evaluates the performance of the production process within a fixed period according to the updated production parameters, compares the production efficiency Eff, energy consumption E and raw material utilization rate Uma before and after the adjustment, and generates an evaluation result report;

[0086] The feedback adjustment module continuously adjusts production parameters based on the evaluation result report and real-time data.

[0087] In this embodiment, the system uses the particle swarm optimization algorithm in the production scheduling optimization module to effectively analyze the real-time data in the production process, generate the optimal production scheduling plan and detailed plan, reduce production idle time, and improve the utilization rate of production resources. This intelligent scheduling method solves the problems of resource waste and equipment idling that are common in traditional production models, significantly improves production efficiency and reduces production costs.

[0088] The intelligent control module can automatically adjust the speed, operation time and other parameters of equipment such as the grinder according to the real-time production progress and feedback data to ensure that the production process is always in the optimal state. By dynamically adjusting the raw material flow and equipment operating speed, accurate management of energy consumption and continuous optimization of the crushing effect are achieved, ensuring the stability of feed quality while reducing energy consumption during equipment operation. Through the performance evaluation module and feedback adjustment module, the system evaluates the efficiency, energy consumption and raw material utilization of the production process within a fixed period and generates a detailed evaluation report. With this evaluation and feedback mechanism, the system can continuously optimize production parameters and reduce efficiency losses caused by improper adjustments. In addition, the evaluation report enables managers to have a clear understanding of the production status, helping them to quickly discover potential production problems and ensure that the entire production process is stable and efficient.

[0089] The data acquisition module and data processing module provide the system with all-round, multi-dimensional real-time data, ensuring that all adjustments and decisions are based on accurate data analysis. Through data standardization, denoising and missing value filling, the data processing module provides an accurate and reliable data standard set, laying a data foundation for subsequent production optimization and intelligent control. This data-driven management model avoids the inefficient way of adjusting parameters based on experience in traditional production processes, and improves the adaptability and accuracy of the system.

[0090] Example 2

[0091] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a raw material flow monitoring unit and an energy consumption and equipment status monitoring unit;

[0092] The raw material flow monitoring unit monitors the inflow of raw materials in real time through a flow sensor and records the raw material flow Q per unit time;

[0093] The energy consumption and equipment status monitoring unit records the mill speed RPM, production line idle time Tid and energy consumption E in real time through the energy consumption monitor and equipment status sensor, and integrates the raw material flow Q, mill speed RPM, production line idle time Tid and energy consumption E to form a data set W.

[0094] The energy consumption E is obtained by the following formula:

[0095]

[0096] In the formula, Eto represents the total energy consumption, E i represents the energy consumption of the i-th device, T i represents the working time of the i-th device, and n represents the total number of devices.

[0097] The production line idle time Tid is obtained by the following formula:

[0098] Tid = Tto-Tr;

[0099] In the formula, Tto represents the total production time, and Tr represents the operating time;

[0100] The data processing module includes a denoising processing unit and a data standardization unit;

[0101] The denoising processing unit performs denoising on the collected data set W using a filtering algorithm to eliminate random noise; fills in missing values ​​using a mean filling method to obtain a denoised data set WC;

[0102] The data standardization unit performs standardization processing on the data denoising set WC by using a Z-score standardization method, converts data of different dimensions into the same standard, and obtains a data standard set WB.

[0103] In this embodiment, the data acquisition module collects and integrates multi-dimensional data such as raw material flow, pulverizer speed, production line idle time and energy consumption in real time through the raw material flow monitoring unit and the energy consumption and equipment status monitoring unit. The data set W composed of these parameters can provide comprehensive real-time data support for subsequent optimization scheduling and production control, ensuring that key information in the production process will not be missing. The denoising processing unit in the data processing module adopts a filtering algorithm to effectively filter out the random noise generated during the acquisition process, and uses the mean filling method to fill the missing values, thereby generating a more accurate data denoising set WC. This processing method can not only significantly improve the accuracy of the data, but also avoid the impact of noise and data missing on the scheduling optimization process. Compared with traditional data processing methods, denoising and completion processing improves data quality, making subsequent production control more reliable and accurate.

[0104] The data standardization unit uses the Z-score standardization method to convert data of different dimensions in the data denoising set WC into the same standard and generate the data standard set WB. This process solves the computational difficulties caused by dimensional differences between different parameters, allowing multi-dimensional data to be analyzed and optimized under the same standard. Data standardization not only improves the efficiency of data processing, but also enhances the adaptability of the system in processing complex data, avoids compatibility issues between data from different units, and provides scientific basic data for production scheduling and intelligent control.

[0105] By optimizing the calculation formula of energy consumption E and production line idle time Tid, this embodiment provides an accurate mathematical model for energy consumption control and idle time analysis of the production line. Through the total energy consumption formula, the system can accurately calculate the energy consumption of each device in the production process and obtain the total energy consumption value, helping managers to effectively monitor and control energy consumption.

[0106] The standardized data set WB, which has been denoised and standardized, serves as the core data source for subsequent optimization control and scheduling plan formulation, enabling the system to achieve accurate production scheduling and intelligent control based on high-quality data analysis. Through this optimized design, the system can dynamically adjust equipment parameters and improve the crushing process in real-time production, ensuring efficient use of production resources and reducing energy consumption and resource waste in the production process.

[0107] Example 3

[0108] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the production scheduling optimization module includes a particle swarm optimization algorithm unit and a scheduling plan generating unit;

[0109] The particle swarm optimization algorithm unit calculates and obtains the device status and resource availability according to the data standard set WB, and generates a scheduling plan by analyzing the device status and resource availability using the particle swarm optimization algorithm;

[0110] The equipment status includes equipment efficiency coefficient Eeff and equipment utilization rate Uep;

[0111] The equipment efficiency coefficient Eeff is obtained by the ratio of the product of the raw material flow rate Q and the pulverizer speed RPM to the unit time; the equipment efficiency coefficient Eeff reflects the efficiency of the equipment when executing the task, ranging from 0 to 1; the equipment utilization rate Uep is obtained by the ratio of the production line idle time Tid to the total production time Tto; the equipment utilization rate Uep indicates the degree of use of the equipment within the planned time;

[0112] The equipment efficiency coefficient Eeff is obtained by the following formula:

[0113]

[0114] In the formula, α represents a very small positive number, in order to prevent the denominator from being zero;

[0115] The equipment utilization Uep is obtained by the following formula:

[0116]

[0117] The resource availability includes the raw material consumption rate Pco and the resource availability coefficient Are;

[0118] The raw material consumption rate Pco is obtained by multiplying the raw material flow rate Q by the mill speed RPM, and the resource availability coefficient Are is obtained according to the inventory, the total production time Tto and the energy consumption E; the raw material consumption rate Pco represents the raw material consumption required for the production task, and the resource availability coefficient Are reflects the adequacy of the current resources;

[0119] The raw material consumption rate Pco is obtained by the following formula:

[0120] Pco=Q*RPM;

[0121] The resource availability coefficient Are is obtained by the following formula:

[0122]

[0123] In the formula, Rs represents the raw material inventory, specifically the total amount of raw materials currently available, and Ea represents the available energy;

[0124] The content of the scheduling plan includes selecting equipment that meets the current task requirements based on the equipment efficiency coefficient Eeff and the equipment utilization rate Uep, constraining resources through the raw material consumption rate Pco and the resource availability coefficient Are, allocating resources according to task requirements, and preventing resource consumption overload;

[0125] The particle swarm optimization algorithm unit is responsible for calculating the startup time and operation time of each device to obtain the maximum production efficiency, iteratively updating the position of particles through the particle swarm algorithm, and finding a scheduling solution;

[0126] The particle swarm optimization algorithm unit receives the data standard set WB to set the initial position and speed of the particle swarm;

[0127] The particle velocity update formula is:

[0128]

[0129] In the formula, represents the new velocity of the ith particle, represents the old velocity of the ith particle, Xi represents the position of the ith particle, represents the best historical position of the ith particle, represents the global optimal position, ω represents the inertia weight value, c 1 and c 2 represents the acceleration constant, r 1 and r 2 Represents a random number ranging from 0 to 1.

[0130] The particle position update formula is:

[0131]

[0132] In the formula, represents the new position of the ith particle, represents the old position of the i-th particle.

[0133] The particle swarm optimization algorithm searches for the optimal solution by updating the velocity and position of the particles. The adjusted parameters control the flexibility of the search and the speed of convergence.

[0134] In each iteration, the fitness of each particle is calculated according to the objective function, and the particle position is updated;

[0135] The iteration is performed until the preset convergence condition is reached and the scheduling plan is output.

[0136] The scheduling plan generation unit generates a scheduling plan according to the scheduling scheme output by the particle swarm optimization algorithm unit;

[0137] The scheduling plan is specifically as follows:

[0138] When 0.5<equipment efficiency coefficient Eeff<1 and 0.5<equipment utilization rate Uep<1, obtain the first equipment scheduling plan, mark the current equipment as running state X=1, and do not schedule the running state of the current equipment;

[0139] When the equipment efficiency coefficient Eeff is less than 0.5 and the equipment utilization rate Uep is less than 0.5, the second equipment scheduling plan is obtained, and the current equipment is marked as the operating state X=2, the operating state of the current equipment is scheduled, and the work task of the current equipment is assigned to the equipment in the operating state X=1;

[0140] When the resource availability coefficient Are>1, it means that the resources are sufficient, the first resource scheduling plan is obtained, and the current resource usage state Y=1 is marked, and the current resources are scheduled to the device with resource usage state Y=2;

[0141] When the resource availability coefficient Are≤1, it indicates that the resources are tight, the second resource scheduling plan is obtained, and the current resource usage state Y=2 is marked, and the current resources are not scheduled.

[0142] The scheduling plan generation unit formulates a specific scheduling plan to clarify the operation sequence and time arrangement of each device;

[0143] Output the scheduling plan report and provide it to system administrators for implementation.

[0144] In this embodiment, by introducing the equipment efficiency coefficient Eeff and the equipment utilization rate Uep, the production system can accurately measure the efficiency and utilization of the equipment in task execution. This method realizes a comprehensive evaluation of the equipment status, helps to prioritize the scheduling of efficient equipment, and reduce the use time of inefficient equipment, thereby improving overall production efficiency. Compared with the traditional evaluation method that relies on a single parameter, this method improves the accuracy and rationality of scheduling, and provides a scientific basis for achieving more efficient equipment management.

[0145] This embodiment realizes dynamic monitoring of resource consumption by calculating the raw material consumption rate Pco and the resource availability coefficient Are, and flexibly allocates resources according to resource availability. This resource monitoring and allocation method effectively reduces the risk of resource overload that may occur in the production process, ensures the rational use of resources, and avoids unnecessary waste. In this way, it can ensure that the output is maximized when resources are sufficient, and reasonably adjust the scheduling when resources are tight, effectively improving resource utilization.

[0146] The particle swarm optimization algorithm unit intelligently optimizes the scheduling plan by using equipment status and resource data. By iteratively updating the position and speed of particles, it continuously searches for the optimal scheduling plan to achieve maximum production efficiency. This algorithm can adaptively adjust the search parameters, improving the flexibility and convergence speed of the scheduling plan. Compared with the static scheduling method, the particle swarm algorithm has the characteristics of self-learning and self-adaptation, and can adjust the optimization direction in real time in a complex production environment, making the scheduling more in line with actual needs.

[0147] The scheduling plan generation unit automatically generates different scheduling plans based on the status data of equipment and resources.

[0148] When the equipment efficiency coefficient Eeff and the equipment utilization rate Uep are both higher than 0.5, the first scheduling plan is executed first to maintain efficient operation of the equipment, reduce unnecessary task transfers, and thus ensure production continuity.

[0149] When the equipment efficiency and utilization rate are both lower than 0.5, the second scheduling plan is activated to transfer the tasks of the inefficient equipment to more efficient equipment, thereby reducing the production bottleneck caused by the inefficient equipment.

[0150] In terms of resources, based on the resource availability coefficient Are, when resources are sufficient, they are dispatched to efficient devices to optimize resource allocation; when resources are tight, current devices are prioritized to reduce frequent resource switching.

[0151] This state-based scheduling method achieves precise matching of equipment and resources, optimizes the continuity and stability of the production process, avoids waste of resources and improves production flexibility.

[0152] The final dispatch plan report output provides clear operation guidance for system managers, including the operation sequence, time arrangement and dynamic allocation plan of resources for each device. Through the dispatch plan generated by the particle swarm optimization algorithm, the dispatch plan generation unit can quickly form the optimal plan report, provide decision-making basis for managers, reduce improper dispatch caused by human intervention, and improve the level of automated management of production.

[0153] Example 4

[0154] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the intelligent control module includes a production parameter adjustment unit and a real-time feedback mechanism unit;

[0155] The production parameter adjustment unit dynamically adjusts the production parameters according to the scheduling plan, including the pulverizer speed RPM and the running time Tr, specifically:

[0156] The production target value is set according to the resource availability coefficient Are and the equipment efficiency coefficient Eeff in the scheduling plan, the crusher speed RPM and the running time Tr are calculated and adjusted, and the planned crusher speed RPMnew and the planned running time Trnew are obtained;

[0157] The planned mill speed RPMnew is obtained by multiplying the mill speed RPM by the resource availability coefficient Are, and the planned operating time Trnew is obtained by multiplying the operating time Tr by the equipment efficiency coefficient Eeff;

[0158] When the resource availability coefficient Are>1 and 0.5<equipment efficiency coefficient Eeff<1, the crusher speed RPM is adjusted to the crusher speed RPM plus the crusher speed RPM multiplied by the difference between the resource availability coefficient Are and 1, and the running time Tr is adjusted to the running time Tr plus the running time Tr multiplied by 1 and the equipment efficiency coefficient Eeff.

[0159] When the resource availability coefficient Are is less than 1 and the equipment efficiency coefficient Eeff is less than 0.5, the crusher speed RPM is adjusted to the crusher speed RPM minus the difference between the crusher speed RPM multiplied by 1 and the resource availability coefficient Are, and the running time Tr is adjusted to the running time Tr minus the difference between the running time Tr multiplied by 0.5 and the equipment efficiency coefficient Eeff;

[0160] And monitor the equipment status to ensure the timeliness and accuracy of production parameter adjustments.

[0161] The real-time feedback mechanism unit establishes a real-time feedback system, updates production parameters according to the production progress, monitors the crushing quality and output during the production process, and makes judgments with preset crushing quality thresholds and output thresholds, and feeds back the judgment results to the production parameter adjustment unit;

[0162] The judgment result is obtained by matching in the following way:

[0163] When the crushing quality is less than the crushing quality threshold, it means that the crushing quality does not meet the standard and the production parameters should be updated;

[0164] When the output is less than the output threshold, it means that the output does not meet the standard and the production parameters are updated;

[0165] When the crushing quality is greater than the crushing quality threshold and the output is greater than the output threshold, it means that the crushing quality and output meet the standards and the current production parameters are maintained;

[0166] When the crushing quality and output are lower than the crushing quality threshold and output threshold, the system will automatically trigger the feedback mechanism and pass the feedback information to the production parameter adjustment unit. The production parameter adjustment unit will recalculate and dynamically adjust the crusher speed RPM and running time Tr.

[0167] In this embodiment, the production parameter adjustment unit dynamically adjusts the rotation speed RPM and operation time Tr of the pulverizer according to the equipment efficiency coefficient Eeff and the resource availability coefficient Are, thereby realizing intelligent management of equipment parameters, enabling the equipment status in the production process to quickly respond to changes in resource conditions and task requirements, thereby optimizing resource utilization and equipment efficiency. The real-time feedback mechanism unit monitors the pulverization quality and output during the production process, determines whether the standards are met, and updates the production parameters in real time. This mechanism can ensure that the product quality and output of the production process meet the preset production standards, avoids the problem of substandard quality or insufficient output due to parameter deviation, and thus improves the stability and reliability of production.

[0168] When equipment efficiency and resource adequacy change, the production parameter adjustment unit in this embodiment can automatically calculate and adjust the operating parameters of the crusher to ensure that the production equipment operates in a reasonable state. Such adaptive adjustment capabilities effectively avoid inefficient operation caused by equipment overload or insufficient resources, thereby ensuring the scientific nature of production scheduling. The dynamic adjustment of production parameters effectively improves the adaptability of equipment under different resource conditions, and significantly improves resource utilization efficiency. Especially in the case of tight resources or low equipment efficiency, reasonable allocation of resources can be achieved by reducing the crusher speed or shortening the operating time, reducing the waste and excessive consumption of production resources.

[0169] Example 5

[0170] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the performance evaluation module includes a production performance data collection unit and an evaluation report generation unit;

[0171] The production performance data collection unit collects historical data and current data of production efficiency Eff, energy consumption E and raw material utilization rate Uma in real time during a fixed period through sensors and monitoring equipment, obtains the improvement status before and after adjustment, including production efficiency increment ΔEff, energy consumption increment ΔE and raw material utilization rate increment ΔUma, and generates an evaluation index Perf through weighted processing;

[0172] The production efficiency Eff is obtained by the ratio of the product output Pou per unit time to the total production time Tto and the maximum production capacity C of the equipment; the raw material utilization rate Uma is obtained by the ratio of the actual amount of raw materials used Mus to the total amount of raw materials input Min;

[0173] The production efficiency Eff is obtained by the following formula:

[0174]

[0175] In the formula, Pou represents the product output per unit time, Tto represents the total production time, and C represents the maximum production capacity of the equipment;

[0176] The raw material utilization rate Uma is obtained by the following formula:

[0177]

[0178] In the formula, Mus represents the actual amount of raw materials used, and Min represents the total amount of raw materials input.

[0179] The production efficiency increment ΔEff is obtained by adjusting the percentage change of the production efficiency Eff before and after;

[0180]

[0181] In the formula, Effnew represents the average production efficiency after adjustment, and Effold represents the average production efficiency before adjustment;

[0182] The energy consumption increment ΔE is obtained by adjusting the percentage change of energy consumption E before and after;

[0183]

[0184] In the formula, Enew represents the average energy consumption after adjustment, and Eold represents the average energy consumption before adjustment;

[0185] The raw material utilization rate increment ΔUma is obtained by adjusting the percentage change of the raw material utilization rate Uma before and after adjustment;

[0186]

[0187] In the formula, Umanew represents the raw material utilization rate after adjustment, and Umaold represents the raw material utilization rate before adjustment;

[0188] The evaluation indicator index Perf is obtained by the following formula:

[0189] Perf = ω 1 *ΔEff+ω 2 *ΔE+ω 3 *ΔUma;

[0190] In the formula, ω 1 ,ω 2 and ω 3 They represent the weight coefficients of production efficiency increment ΔEff, energy consumption increment ΔE and raw material utilization rate increment ΔUma respectively;

[0191] The evaluation report generating unit generates an evaluation result report according to the obtained production efficiency increment ΔEff, energy consumption increment ΔE, raw material utilization rate increment ΔUma and evaluation index Perf;

[0192] Specifically: compare and analyze the differences in production efficiency Eff, energy consumption E and raw material utilization rate Uma before and after adjustment, monitor the production efficiency increment ΔEff, energy consumption increment ΔE and raw material utilization rate increment ΔUma in real time, and evaluate the overall system performance through the evaluation indicator index Perf, and generate an evaluation result report, including the efficiency improvement percentage, energy consumption change percentage and raw material utilization rate improvement effect.

[0193] The feedback adjustment module includes an adaptive control unit and a parameter adjustment execution unit;

[0194] The adaptive control unit calculates and adjusts production parameters including the pulverizer speed RPM and the running time Tr according to the evaluation result report and the real-time data, and generates an adjustment plan;

[0195] The new pulverizer speed RPMx is obtained by the following formula:

[0196] RPMx=RPMnew+L*(RPMnew-RPM);

[0197] Where, L represents the adjustment coefficient;

[0198] The new running time Trx is obtained by the following formula:

[0199] Trx = Trnew + L*(Trnew - Tr);

[0200] The parameter adjustment execution unit performs the parameter adjustment operation according to the adjustment scheme, specifically:

[0201] sending production parameter updates generated by the adaptive control unit to the production equipment;

[0202] Monitor the adjusted production effects and feed the results back to the adaptive control unit.

[0203] In this embodiment, accurate data collection and comprehensive performance evaluation: the system can accurately capture changes in the production process by collecting historical and current data of production efficiency Eff, energy consumption E, and raw material utilization rate Uma in real time through the production performance data collection unit within a fixed period. The evaluation index Perf calculated based on the production efficiency increment ΔEff, energy consumption increment ΔE, and raw material utilization rate increment ΔUma can comprehensively and objectively evaluate the improvement of various performances before and after the adjustment, providing data support for production optimization.

[0204] This embodiment provides a method for calculating production efficiency and raw material utilization rate, ensuring that resource usage can be dynamically acquired and adjusted during the production process. By calculating the production efficiency increment ΔEff and the raw material utilization rate increment ΔUma, the system can optimize the matching of raw material consumption and equipment capacity in real time, reduce waste, improve resource utilization, and significantly improve production efficiency.

[0205] The adaptive control unit of the feedback adjustment module realizes adaptive adjustment of production parameters, including optimization of crusher speed RPM and running time Tr, by analyzing the adjustment plan generated by the evaluation report in real time. This adaptive feedback mechanism can not only respond quickly to changes in real-time data, but also automatically optimize equipment parameters according to the evaluation results, thereby improving the stability and flexibility of the production process. The evaluation report generation unit compares and analyzes the production efficiency, energy consumption and raw material utilization rate before and after the adjustment, and generates an evaluation result report through the evaluation indicator index Perf. The report contains detailed data on efficiency improvement, energy consumption changes and raw material utilization rate improvements, so that managers can intuitively understand the effects of production improvements, which is helpful for decision-making and continuous adjustment of optimization plans. The parameter adjustment execution unit in the feedback adjustment module can automatically execute production parameter updates according to the adjustment plan generated by the adaptive control unit, reducing the need for manual operation and intervention, and improving the automation level of the production process, thereby reducing management costs and improving production efficiency.

[0206] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control system for feed production, characterized in that: It includes data acquisition module, data processing module, production scheduling optimization module, intelligent control module, performance evaluation module and feedback adjustment module; The data acquisition module collects multi-dimensional parameters in the production process in real time through sensors and monitoring devices to form a data set W; The data processing module preprocesses the collected data set W, including denoising, filling missing values ​​and data standardization, to obtain a data standard set WB; The production scheduling optimization module calculates the data standard set WB by using the particle swarm optimization algorithm to obtain a generation scheduling solution and generate a scheduling plan; The intelligent control module adjusts the production parameters according to the scheduling plan and sets a real-time feedback mechanism to update the production parameters according to the production progress; The performance evaluation module evaluates the performance of the production process within a fixed period according to the updated production parameters and generates an evaluation result report; The feedback adjustment module continuously adjusts production parameters based on the evaluation result report and real-time data.

2. The feed production intelligent control system according to claim 1, characterized in that: The data acquisition module includes a raw material flow monitoring unit and an energy consumption and equipment status monitoring unit; The raw material flow monitoring unit monitors the inflow of raw materials in real time through a flow sensor and records the raw material flow Q per unit time; The energy consumption and equipment status monitoring unit records the mill speed RPM, production line idle time Tid and energy consumption E in real time through the energy consumption monitor and equipment status sensor, and integrates the raw material flow Q, mill speed RPM, production line idle time Tid and energy consumption E to form a data set W.

3. The feed production intelligent control system according to claim 1, characterized in that: The data processing module includes a denoising processing unit and a data standardization unit; The denoising processing unit performs denoising on the collected data set W using a filtering algorithm to eliminate random noise; fills in missing values ​​using a mean filling method to obtain a denoised data set WC; The data standardization unit performs standardization processing on the data denoising set WC by using a Z-score standardization method, converts data of different dimensions into the same standard, and obtains a data standard set WB.

4. The feed production intelligent control system according to claim 1, characterized in that: The production scheduling optimization module includes a particle swarm optimization algorithm unit and a scheduling plan generation unit; The particle swarm optimization algorithm unit calculates and obtains the device status and resource availability according to the data standard set WB, and generates a scheduling plan by analyzing the device status and resource availability using the particle swarm optimization algorithm; The equipment status includes equipment efficiency coefficient Eeff and equipment utilization rate Uep; The equipment efficiency coefficient Eeff is obtained by the ratio of the product of the raw material flow rate Q and the pulverizer speed RPM to the unit time; the equipment efficiency coefficient Eeff reflects the efficiency of the equipment when executing the task, ranging from 0 to 1; the equipment utilization rate Uep is obtained by the ratio of the production line idle time Tid to the total production time Tto; the equipment utilization rate Uep indicates the degree of use of the equipment within the planned time; The resource availability includes the raw material consumption rate Pco and the resource availability coefficient Are; The raw material consumption rate Pco is obtained by multiplying the raw material flow rate Q by the mill speed RPM, and the resource availability coefficient Are is obtained according to the inventory, the total production time Tto and the energy consumption E; the raw material consumption rate Pco represents the raw material consumption required for the production task, and the resource availability coefficient Are reflects the adequacy of the current resources; The content of the scheduling plan includes selecting equipment that meets the current task requirements based on the equipment efficiency coefficient Eeff and the equipment utilization rate Uep, constraining resources through the raw material consumption rate Pco and the resource availability coefficient Are, allocating resources according to task requirements, and preventing resource consumption overload.

5. The feed production intelligent control system according to claim 4, characterized in that: The scheduling plan generation unit generates a scheduling plan according to the scheduling scheme output by the particle swarm optimization algorithm unit; The scheduling plan is specifically as follows: When 0.5<equipment efficiency coefficient Eeff<1 and 0.5<equipment utilization rate Uep<1, obtain the first equipment scheduling plan, mark the current equipment as running state X=1, and do not schedule the running state of the current equipment; When the equipment efficiency coefficient Eeff is less than 0.5 and the equipment utilization rate Uep is less than 0.5, the second equipment scheduling plan is obtained, and the current equipment is marked as the operating state X=2, the operating state of the current equipment is scheduled, and the work task of the current equipment is assigned to the equipment in the operating state X=1; When the resource availability coefficient Are>1, it means that the resources are sufficient, the first resource scheduling plan is obtained, and the current resource usage state Y=1 is marked, and the current resources are scheduled to the device with resource usage state Y=2; When the resource availability coefficient Are≤1, it indicates that the resources are tight, the second resource scheduling plan is obtained, and the current resource usage state Y=2 is marked, and the current resources are not scheduled.

6. The feed production intelligent control system according to claim 5, characterized in that: The intelligent control module includes a production parameter adjustment unit and a real-time feedback mechanism unit; The production parameter adjustment unit dynamically adjusts the production parameters according to the scheduling plan, including the pulverizer speed RPM and the running time Tr, specifically: The production target value is set according to the resource availability coefficient Are and the equipment efficiency coefficient Eeff in the scheduling plan, the crusher speed RPM and the running time Tr are calculated and adjusted, and the planned crusher speed RPMnew and the planned running time Trnew are obtained; The planned mill speed RPMnew is obtained by multiplying the mill speed RPM by the resource availability coefficient Are, and the planned operating time Trnew is obtained by multiplying the operating time Tr by the equipment efficiency coefficient Eeff; When the resource availability coefficient Are>1 and 0.5<equipment efficiency coefficient Eeff<1, the crusher speed RPM is adjusted to the crusher speed RPM plus the crusher speed RPM multiplied by the difference between the resource availability coefficient Are and 1, and the running time Tr is adjusted to the running time Tr plus the running time Tr multiplied by 1 and the equipment efficiency coefficient Eeff. When the resource availability coefficient Are is less than 1 and the equipment efficiency coefficient Eeff is less than 0.5, the crusher speed RPM is adjusted to the crusher speed RPM minus the difference between the crusher speed RPM multiplied by 1 and the resource availability coefficient Are, and the operating time Tr is adjusted to the operating time Tr minus the difference between the operating time Tr multiplied by 0.5 and the equipment efficiency coefficient Eeff.

7. The feed production intelligent control system according to claim 6, characterized in that: The real-time feedback mechanism unit establishes a real-time feedback system, updates production parameters according to the production progress, monitors the crushing quality and output during the production process, and makes judgments with preset crushing quality thresholds and output thresholds, and feeds back the judgment results to the production parameter adjustment unit; The judgment result is obtained by matching in the following way: When the crushing quality is less than the crushing quality threshold, it means that the crushing quality does not meet the standard and the production parameters should be updated; When the output is less than the output threshold, it means that the output does not meet the standard and the production parameters are updated; When the crushing quality is greater than the crushing quality threshold and the output is greater than the output threshold, it means that the crushing quality and output meet the standards and the current production parameters are maintained; When the crushing quality and output are lower than the crushing quality threshold and output threshold, the system will automatically trigger the feedback mechanism and pass the feedback information to the production parameter adjustment unit. The production parameter adjustment unit will recalculate and dynamically adjust the crusher speed RPM and running time Tr.

8. The feed production intelligent control system according to claim 1, characterized in that: The performance evaluation module includes a production performance data collection unit and an evaluation report generation unit; The production performance data collection unit collects historical data and current data of production efficiency Eff, energy consumption E and raw material utilization rate Uma in real time during a fixed period through sensors and monitoring equipment, obtains the improvement status before and after adjustment, including production efficiency increment ΔEff, energy consumption increment ΔE and raw material utilization rate increment ΔUma, and generates an evaluation index Perf through weighted processing; The production efficiency Eff is obtained by the ratio of the product output Pou per unit time to the total production time Tto and the maximum production capacity C of the equipment; the raw material utilization rate Uma is obtained by the ratio of the actual amount of raw materials used Mus to the total amount of raw materials input Min; The production efficiency increment ΔEff is obtained by adjusting the percentage change of the production efficiency Eff before and after; The energy consumption increment ΔE is obtained by adjusting the percentage change of energy consumption E before and after; The raw material usage rate increment ΔUma is obtained by adjusting the percentage change of the raw material usage rate Uma before and after the adjustment.

9. The feed production intelligent control system according to claim 8, characterized in that: The evaluation report generating unit generates an evaluation result report according to the obtained production efficiency increment ΔEff, energy consumption increment ΔE, raw material utilization rate increment ΔUma and evaluation index Perf; Specifically: compare and analyze the differences in production efficiency Eff, energy consumption E and raw material utilization rate Uma before and after adjustment, monitor the production efficiency increment ΔEff, energy consumption increment ΔE and raw material utilization rate increment ΔUma in real time, and evaluate the overall system performance through the evaluation indicator index Perf, and generate an evaluation result report, including the efficiency improvement percentage, energy consumption change percentage and raw material utilization rate improvement effect.

10. The feed production intelligent control system according to claim 1, characterized in that: The feedback adjustment module includes an adaptive control unit and a parameter adjustment execution unit; The adaptive control unit calculates and adjusts production parameters including the pulverizer speed RPM and the running time Tr according to the evaluation result report and the real-time data, and generates an adjustment plan; The parameter adjustment execution unit performs the parameter adjustment operation according to the adjustment scheme, specifically: sending production parameter updates generated by the adaptive control unit to the production equipment; Monitor the adjusted production effects and feed the results back to the adaptive control unit.

Images