Rotor speed regulation and control method and system based on uniform flow field classification

Abstract

The invention relates to the technical field of cement production equipment, in particular to a grading rotor speed regulation and control method and system based on a uniform flow field, which has the advantages of high dynamic adaptability, high accuracy, simplicity and convenience in operation, high predictability and high expandability by introducing the grading rotor speed regulation and control method based on the uniform flow field. The energy consumption and the maintenance cost are reduced, and the working efficiency of cement production grinding operation and the quality of cement products are improved; the method comprises the following steps: acquiring target granularity of grinding operation and cement material granularity distribution data; dividing the cement material particle size distribution data based on the target particle size to obtain cement material grading characteristic information, the cement material grading characteristic information including the target particle size, a target particle size mass ratio, a non-target particle size and a non-target particle size mass ratio; obtaining characteristic information of the graded rotor; and carrying out data fusion on the classification rotor characteristic information and the cement material classification characteristic information.

Description

Technical Field

[0001] The invention relates to the technical field of cement production equipment, and in particular to a method and system for regulating rotor speed based on uniform flow field classification. Background Art

[0002] In the cement production process, the goal of grinding operations is to grind cement materials to a specific particle size to meet different engineering requirements. During the grinding process, the particle size distribution of the material has a decisive influence on the performance of the final product. In order to obtain a uniform particle size distribution of the material, the grinding equipment, especially the speed of the grading rotor, needs to be precisely controlled.

[0003] Most of the existing classification rotor speed control methods are based on fixed process parameter settings, while ignoring the dynamic relationship between material characteristics and the classification rotor's own characteristics during the grinding operation. As a result, in practical applications, it is difficult to repeatedly obtain consistent grinding effects even under similar process conditions. Especially when processing materials with different particle size distribution characteristics, traditional fixed speed control strategies often cannot meet the needs of precise control of product particle size distribution. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a grading rotor speed control method based on uniform flow field, which has the advantages of strong dynamic adaptability, high precision, simple operation, strong predictability and strong scalability, reduces energy consumption and maintenance costs, and improves the work efficiency of cement production grinding operations and the quality of cement products. The method and system.

[0005] In a first aspect, the present invention provides a method for controlling rotor speed based on a uniform flow field, the method comprising:

[0006] Obtain the target particle size of the grinding operation and the particle size distribution data of cement materials;

[0007] Dividing the cement material particle size distribution data based on the target particle size to obtain cement material classification characteristic information, wherein the cement material classification characteristic information includes the target particle size, the target particle size mass ratio, the non-target particle size, and the non-target particle size mass ratio;

[0008] Obtaining classification rotor characteristic information;

[0009] The classification rotor characteristic information and cement material classification characteristic information are data-fused to obtain a multi-dimensional feature set of the grinding operation;

[0010] Input the multi-dimensional feature set of the grinding operation into the pre-built grinding uniform flow field prediction model to obtain the uniform flow field feature vector of this grinding operation;

[0011] The uniform flow field characteristic vector obtained is used as an index mark, and matching is performed in the pre-built flow field grading rotor reference space to map the optimal grading rotor speed corresponding to the uniform flow field characteristic vector, and the grading rotor operation is controlled according to the optimal grading rotor speed.

[0012] Furthermore, the method for obtaining particle size distribution data comprises:

[0013] Select standard sieves according to the particle size range of cement materials, and arrange the sieve hole sizes in order from large to small;

[0014] The cement material is dried, crushed and pre-screened, and then the cement material is weighed and the initial total weight is recorded;

[0015] Stack the sieves in descending order of aperture, place the cover on the top and the receiving tray on the bottom, sprinkle the cement material evenly on the top sieve, and use mechanical vibration to make the cement material pass through the sieve with the corresponding aperture until it falls into the bottom tray;

[0016] Stop vibration after all cement materials have passed through the penetrable sieve;

[0017] After stopping the vibration, weigh the residue on each layer of sieve separately;

[0018] Compare the weight of the material on each sieve with the initial total weight and calculate the percentage of material in each particle size range;

[0019] The sieve hole size is the horizontal axis, and the percentage of material passing through each sieve hole is the vertical axis, and a particle size distribution curve or a cumulative particle size distribution curve is drawn.

[0020] Furthermore, the graded rotor characteristic information includes rotor size, rotor mass, blade angle, blade quantity, blade material, and inlet and outlet diameters.

[0021] Furthermore, the method for data fusion of the stage rotor characteristic information and the cement material classification characteristic information comprises:

[0022] Remove the data points of the classification rotor characteristic information and the cement material classification characteristic information to handle the missing values;

[0023] Identify the features of the fusion target and exclude irrelevant features;

[0024] Select fusion algorithm according to data type and fusion target;

[0025] Apply fusion algorithms to merge the data into a unified data set;

[0026] Verify the accuracy of the fusion results and check whether there are unreasonable data points.

[0027] Furthermore, the method for constructing the multi-dimensional feature set includes:

[0028] Verify the acquired data of the classification characteristic information of the cement material and the characteristic information of the classification rotor;

[0029] Standardizing the data of the grading characteristic information of cement materials and the characteristic information of the grading rotor;

[0030] According to the actual needs of grinding operations and existing industry experience, the characteristic information that has the greatest impact on the grinding effect is selected as the key feature;

[0031] Arrange the selected features in order to form a feature vector;

[0032] Use data fusion algorithm to fuse each feature vector into a multi-dimensional feature set.

[0033] Furthermore, the method for constructing the grinding uniform flow field prediction model comprises:

[0034] Collect records of past grinding operations and record environmental variables related to the grinding process;

[0035] Remove abnormal data and process missing data, and convert data of different dimensions and scales to the same scale;

[0036] Analyze the correlation between features and target variables through coefficient matrix;

[0037] Recursive feature elimination and principal component analysis were used to reduce feature dimensions and remove redundant features;

[0038] Based on the nature of the problem, select candidate evaluation models;

[0039] The data set was divided into training set, validation set and test set. The K-fold cross-validation method was used to evaluate the generalization ability of the grinding uniform flow field prediction model. The grid search and random search methods were used to adjust the parameters of the grinding uniform flow field prediction model.

[0040] The grinding uniform flow field prediction model was trained on the training set using the optimized parameters, and the performance of the grinding uniform flow field prediction model was evaluated on the validation set and the test set.

[0041] According to the evaluation results, return to the grinding uniform flow field prediction model selection stage for adjustment so that the performance of the grinding uniform flow field prediction model meets the preset standards.

[0042] Furthermore, the flow field classification rotor control space construction method is as follows:

[0043] Collect detailed operating data from the grinding operation, clean the collected operating data, remove outliers and fill in missing values, and perform standard processing on the operating data;

[0044] Based on the theoretical and practical experience of grinding operations, select the features that have the greatest impact on the grinding effect, try different feature combinations, and determine the feature combination that best represents the state and effect of the grinding operation through correlation analysis and statistical tests;

[0045] Based on the selected features, a feature vector is created for each historical job instance;

[0046] For each historical operation instance, the grinding effect is evaluated, and based on the evaluation results, the optimal classifying rotor speed corresponding to each feature vector is determined;

[0047] Pair the feature vectors with the corresponding optimal graded rotor speeds to form data pairs; use data mining or machine learning techniques to construct a queryable comparison space;

[0048] Use independent validation set data to test whether the classifying rotor speed predicted by the control space can actually bring about the expected grinding effect. According to the validation results, adjust the feature selection, grinding uniform flow field prediction model parameters and optimization strategy;

[0049] The control space is integrated into the control system of the grinding operation to automatically adjust the speed of the classifying rotor according to the feature vector collected in real time.

[0050] On the other hand, the present application also provides a uniform flow field based graded rotor speed control system, the system comprising:

[0051] The material property analysis module is used to obtain the target particle size of the grinding operation and the original particle size distribution data of the cement material; analyze and extract the classification property information of the cement material, including the target particle size, the mass proportion of the target particle size, the non-target particle size and the mass proportion of the non-target particle size;

[0052] A rotor characteristic reading module, used to obtain the physical characteristic information of the grading rotor, wherein the physical characteristic information of the grading rotor includes rotor size, rotor mass, blade angle, blade number, blade material and inlet and outlet diameters;

[0053] A data fusion module is used to integrate the cement material classification characteristic information output by the material characteristic analysis module with the rotor characteristic information provided by the rotor characteristic reading module to form a multi-dimensional feature set of the grinding operation;

[0054] The flow field prediction module is used to receive the multi-dimensional feature set output by the data fusion module; use the pre-trained grinding uniform flow field prediction model to calculate the uniform flow field feature vector of this grinding operation;

[0055] The rotor speed optimization module is used to use the uniform flow field feature vector output by the flow field prediction module as a query condition in the flow field classification rotor comparison space; execute the matching algorithm to find the rotor speed setting that best matches the feature vector; output the optimal classification rotor speed to the execution unit to control the classification rotor to run at the speed;

[0056] The control and execution module is used to adjust the actual operating speed of the graded rotor according to the optimal graded rotor speed instruction provided by the rotor speed optimization module. In a third aspect, the present application provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the steps in any one of the above methods are implemented.

[0057] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0058] Compared with the prior art, the present invention has the following beneficial effects: by real-time monitoring and analysis of material properties and the physical properties of the grading rotor, the speed of the grading rotor can be automatically adjusted under changing operating conditions, the adaptability to different material properties can be improved, and more flexible grinding operation control can be achieved; the material particle size distribution data is combined with the grading rotor characteristics, and the optimal grading rotor speed is calculated through a prediction model, which is convenient for accurately controlling the particle size distribution of the material so that the quality of the product meets the engineering requirements; a dynamic adjustment strategy based on material properties is adopted to maintain a stable grinding effect when processing materials with different particle size distribution characteristics, thereby improving product quality and consistency; by optimizing the speed of the grading rotor , reducing energy consumption and the occurrence of over-grinding or under-grinding, reducing production costs and energy consumption; through flow field prediction models and data fusion technology, improving the control intelligence of grinding operations, reducing manual dependence, and improving the degree of automation of the production process; based on dynamic analysis of material and rotor characteristic data, adjustments and optimizations are made as new material types and production needs change, with good scalability and adaptability; by introducing a graded rotor speed control method based on uniform flow field, it has the advantages of strong dynamic adaptability, high precision, simple operation, strong predictability and strong scalability, reducing energy consumption and maintenance costs, and improving the work efficiency of cement production grinding operations and the quality of cement products. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow chart of the present invention;

[0060] Figure 2 It is a flow chart of the method for constructing a grinding uniform flow field prediction model;

[0061] Figure 3 It is a structural diagram of the graded rotor speed control system based on uniform flow field. DETAILED DESCRIPTION

[0062] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0063] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0064] The acquisition, storage, use, and processing of data in the technical solution of this application comply with relevant legal provisions.

[0065] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0066] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0067] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0068] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0069] The present application is described below in conjunction with the drawings in the present application.

[0070] Embodiment 1: Figure 1 to Figure 2 As shown, the method for controlling rotor speed based on uniform flow field classification of the present invention specifically includes the following steps:

[0071] S1. Obtaining target particle size of grinding operation and particle size distribution data of cement material;

[0072] The specific S1 implementation steps are as follows:

[0073] The target particle size of the grinding operation is set according to the final use and performance requirements of the cement; in cement production, the setting of the target particle size should refer to the following factors, including:

[0074] First, analyze the final use and performance requirements of cement. Different projects have different requirements for cement hydration rate, early strength, final strength, fluidity and durability. The above properties are directly related to the particle size distribution of cement. For projects that require rapid hardening, finer cement particle size is required to accelerate the hydration process. For concrete preparation that requires good fluidity, the cement particle size distribution needs to be controlled to avoid excessive fineness that affects fluidity. Refer to national or international standards, such as ASTM and EN, which have clear provisions on cement particle size distribution. Consult relevant standards to determine the reasonable range of target particle size. Industry specifications and internal standards of enterprises also provide specific particle size requirements. Investigate the market demand for cement products, especially the preference for cement particle size in different application fields. Customers' special requirements, such as ultrafine cement and low-alkali cement, will directly affect the setting of target particle size. Through experimental research, evaluate the impact of different particle size distributions on cement performance, and then use historical production data to analyze successful particle size distribution cases in similar products or applications as a reference for setting target particle size. Determine the target particle size of grinding operations based on the above information to improve the applicability of cement products.

[0075] The particle size distribution data of cement materials refers to the distribution of the particle size of cement materials before entering the grinding equipment. The particle size distribution data of cement materials directly reflects the original particle size state of the materials, which is convenient for evaluating the effect of grinding operation and adjusting grinding parameters. The particle size distribution data is expressed in the form of a particle size distribution curve or histogram, where the horizontal axis represents the particle size and the vertical axis represents the mass or volume ratio of particles within the corresponding particle size range. The method for obtaining the particle size distribution data is as follows:

[0076] Screening method: select standard sieves according to the particle size range of cement materials, and arrange the sieve hole sizes in order from large to small; dry the cement materials, crush them and pre-screen them; weigh part of the cement materials and record the initial total weight; stack the sieves in order from large to small apertures, place a lid on the top and a receiving tray on the bottom; sprinkle the cement materials evenly on the top sieve, use mechanical vibration to make the cement materials pass through the sieve with the corresponding aperture, fall into the next sieve or bottom plate, and screen until all the cement materials pass through the penetrable sieve or remain on a certain sieve and no longer move; after stopping the vibration, weigh the residue on each layer of sieve separately; compare the weight of the material on each layer of sieve with the initial total weight, and calculate the percentage of materials in each particle size segment; draw a particle size distribution curve or a cumulative particle size distribution curve with the sieve hole size as the horizontal coordinate and the percentage of materials passing through each sieve hole as the vertical coordinate;

[0077] Laser particle size analysis: using the principle of laser scattering, the particle size distribution of the material is calculated by measuring the intensity distribution of scattered light;

[0078] Image analysis: Take images of particles using a microscope or scanning electron microscope, and then use image processing software to analyze the particle size distribution;

[0079] Sedimentation method: Applicable to fine particles, the particle size distribution is determined by measuring the sedimentation velocity of particles in liquid;

[0080] Determine the end use of cement by comprehensively considering the end use, performance requirements, market trends, special customer requirements and industry standards to ensure the rationality and applicability of the target particle size; refer to national or international standards to ensure that the quality of cement products meets industry specifications and improve the market competitiveness of products; evaluate the impact of different particle size distributions on cement performance through experimental research to ensure the scientificity and feasibility of setting the target particle size; analyze successful cases based on historical production data to provide empirical evidence for setting the target particle size and reduce trial and error costs; according to the different requirements for cement particle size in different engineering applications, the target particle size is flexible in setting and can adapt to changing market and customer needs;

[0081] The use of screening, laser particle size analysis, image analysis and sedimentation methods can provide accurate particle size distribution data to ensure precise control of grinding operations; different particle size analysis methods are suitable for materials with different particle size ranges, ensuring the comprehensiveness of data acquisition, covering materials from coarse particles to very fine particles; the application of modern technologies such as laser particle size analysis and image analysis methods improves the efficiency and accuracy of particle size distribution data acquisition; accurate particle size distribution data provides a data basis for monitoring and quality control of grinding operations, facilitating timely adjustment of process parameters and improving the stability of product quality.

[0082] S2. Dividing the cement material particle size distribution data based on the target particle size to obtain cement material classification characteristic information, wherein the cement material classification characteristic information includes target particle size, target particle size mass ratio, non-target particle size, and non-target particle size mass ratio;

[0083] The specific S2 implementation steps are as follows:

[0084] First, the particle size distribution data of cement materials is divided based on the target particle size; the target particle size of the grinding operation is clarified, and the original particle size distribution data of the cement materials is obtained by experimental methods; the particle size distribution data is displayed in the form of a particle size distribution curve or a histogram, where the horizontal axis is the particle size and the vertical axis is the material mass or volume percentage of each particle size segment; the original particle size distribution data is divided according to the target particle size; the particle size distribution curve is divided into two parts: "target particle size" and "non-target particle size"; the "target particle size" part includes all particle size intervals that fall within the target particle size range; the "non-target particle size" part It covers all particle size ranges beyond the target particle size range, including coarse particles larger than the target particle size and too fine particles smaller than the target particle size; calculate the mass proportion of the material within the target particle size range, that is, the percentage of the material less than or equal to the target particle size in the total material mass; then calculate the mass proportion of the material within the non-target particle size range, that is, the percentage of the material beyond the target particle size range in the total material mass; analyze the mass proportion of the target particle size range and the non-target particle size range to evaluate the grading characteristics of the material; facilitate understanding of the particle size state of the material before the grinding operation, and the degree of improvement that needs to be achieved through the grinding operation;

[0085] Then, the cement material classification characteristic information is extracted, and the extracted cement material classification characteristic information includes the following:

[0086] Target particle size: Target particle size refers to the material particle size standard that the grinding operation aims to achieve, which is set according to the final use and performance requirements of cement;

[0087] Target particle size mass ratio: refers to the total mass percentage of materials that meet the target particle size requirements in the particle size distribution of cement materials;

[0088] Non-target particle size: Non-target particle size refers to materials whose particle size is larger or smaller than the target particle size range;

[0089] Non-target particle size mass ratio: Non-target particle size mass ratio refers to the mass percentage of non-target particle size materials in the total material;

[0090] By refining the particle size distribution data into two parts, target particle size and non-target particle size, the refined management of material particle size distribution is achieved, which facilitates the precise control of the particle size output of the grinding operation; the standard particle size setting gives the grinding operation a clear direction, ensuring that the production process focuses on achieving the predetermined particle size standard and improving the pertinence and efficiency of production; by calculating and analyzing the mass proportion of target particle size and non-target particle size, data support is provided for the parameter adjustment of the grinding operation; a mechanism for real-time monitoring of changes in material particle size distribution is provided, so that production managers can quickly identify and respond to problems that arise during the grinding process; over-grinding or under-grinding is reduced, unnecessary energy consumption and material loss are reduced, and resource utilization efficiency and economic benefits are improved; by precisely controlling the material particle size distribution, the quality stability and consistency of cement products are ensured to meet the specific needs of different engineering projects; in summary, this step improves the efficiency of the grinding operation and the quality of cement products, promotes the rational use of resources and environmental protection, and improves the refined management and technological innovation in cement production.

[0091] S3, obtaining characteristic information of the grading rotor, wherein the characteristic information of the grading rotor includes rotor size, rotor mass, blade angle, number of blades, blade material, and inlet and outlet diameters;

[0092] The characteristic information of the grading rotor is as follows:

[0093] Rotor size: Use measuring tools to measure the diameter and length of the rotor and record the data in detail; the diameter and length of the rotor determine the rotor processing capacity and grinding efficiency; a larger diameter generally represents a higher processing capacity, while the rotor length affects the residence time of the material in the classification area and the classification effect;

[0094] Rotor mass: Calculate the rotor mass based on the rotor size and material density, or obtain the accurate mass through actual weighing; the rotor mass affects the dynamic balance and dynamic stability of the rotor when it rotates at high speed. The larger the rotor mass, the higher the dynamic balance and dynamic stability of the rotor when it rotates at high speed.

[0095] Blade angle: Use an angle measuring tool to measure the blade angle and obtain the blade angle; the blade angle design will change the distribution of airflow inside the rotor and affect the classification effect of the material. A suitable blade angle helps to achieve a uniform material particle size distribution.

[0096] Number of blades: Obtain the number of blades by visual inspection; more blades can provide finer grading, but too many blades will increase air resistance, reduce air flow speed, and affect the grading effect;

[0097] Blade material: Get the material of the blade by checking the material list of the rotor; different materials have different wear resistance, density and hardness. Choosing the right material can extend the service life of the blade and reduce maintenance costs;

[0098] Inlet and outlet diameter: Use measuring tools to measure and record the inlet and outlet diameters; the size of the inlet and outlet diameters directly affects the inlet and outlet speed of materials and airflow, and affects the classification efficiency; appropriate inlet and outlet diameter design can optimize the material passing rate and airflow distribution;

[0099] By recording the rotor size, quality, blade angle, quantity, material and inlet and outlet diameters in detail, the refined management of the grading rotor can be achieved, which is convenient for precise control of the rotor speed and ensures that the material is graded according to the expected particle size; the information on rotor size and quality is convenient for optimizing the rotor's processing capacity and dynamic balance, and improving the stability and efficiency of the rotor under high-speed operation; the optimization of blade angle and number can improve the airflow distribution, improve the classification accuracy, reduce the airflow resistance caused by too many blades, and maintain efficient classification effect; understand the characteristics of blade materials, select high-wear-resistant materials, extend the service life of the rotor, reduce maintenance frequency and cost, and improve production continuity and economy; reasonable inlet and outlet diameter design can optimize material passing rate and airflow distribution, reduce unnecessary energy consumption, and improve grinding efficiency; by understanding the comprehensive characteristics of the grading rotor, the rotor parameters can be flexibly adjusted according to different material characteristics and particle size distribution requirements, and the adaptability and flexibility of the grinding operation can be improved; the optimization of rotor quality and dynamic balance reduces the risk of equipment failure and unexpected downtime, and improves the safety and reliability of production; by comprehensively collecting and analyzing the characteristic information of the grading rotor, it provides a basis for the optimization of the grinding operation, reduces resource waste, and improves production efficiency and product quality.

[0100] S4, fusing the classification rotor characteristic information and the cement material classification characteristic information to obtain a multi-dimensional feature set of the grinding operation;

[0101] The specific S4 implementation steps are as follows:

[0102] The classification rotor characteristic information and cement material classification characteristic information are integrated. The specific method is as follows:

[0103] Data preprocessing: remove invalid or erroneous data points of the classification rotor characteristic information and cement material classification characteristic information, and process missing values; convert the data to the same scale to avoid the impact of differences in dimensions or numerical ranges on subsequent processing; convert the data into a form suitable for fusion as needed;

[0104] Feature extraction: Identify the most important features for the fusion target and exclude redundant or irrelevant features; extract key information from the raw data using dimensionality reduction techniques such as principal component analysis or independent component analysis;

[0105] Fusion algorithm selection: Select an appropriate fusion algorithm based on the data type and fusion target. Common fusion algorithms include weighted average, Bayesian fusion, neural network fusion, and fuzzy logic fusion.

[0106] Data fusion implementation: Apply the selected fusion algorithm to merge data from different sources into a unified data set or feature vector; during the fusion process, it is necessary to assign weights to the features of different data sources;

[0107] Result verification and optimization: Verify the accuracy and consistency of the fusion results, and check whether there are abnormal or unreasonable data points; adjust the parameters or feature selection of the fusion algorithm according to the verification results to optimize the fusion process;

[0108] Application of fusion results: Use the fused data for downstream tasks;

[0109] Data fusion integrates material characteristics and equipment characteristics to reflect the multi-dimensional feature set of the grinding operation status; it is convenient to improve the prediction accuracy and control the grinding effect in the subsequent prediction of the uniform flow field of grinding;

[0110] The specific method of constructing a multi-dimensional feature set is as follows:

[0111] Data preparation: First, check the obtained cement material classification characteristic information and classification rotor characteristic information data, the above data must be accurate;

[0112] Data standardization: Standardize or normalize the data of the grading characteristic information of cement materials and the characteristic information of the grading rotor, so as to facilitate fair comparison and combination of different types of characteristic information in the subsequent data fusion process;

[0113] Feature selection and weight determination: According to the actual needs of the grinding operation and existing industry experience, the characteristic information that has the greatest impact on the grinding effect is selected as the key feature; and the weight of each feature is determined to reflect the importance of the feature in the grinding operation;

[0114] Construct feature vector: Arrange the selected features in a certain order to form a feature vector, which contains all the key characteristic information of the grinding operation;

[0115] Fusion of feature vectors: Using data fusion algorithm, each feature vector is fused into a multi-dimensional feature set; the multi-dimensional feature set fully describes the characteristics of the grinding operation and provides complete input information for subsequent uniform flow field prediction;

[0116] Through data fusion, material characteristics and equipment characteristics are comprehensively considered to form a multi-dimensional feature set that comprehensively reflects the state of the grinding operation; it provides input data for the grinding uniform flow field prediction model; standardization processing ensures fair comparison of different features in the grinding uniform flow field prediction model, and improves the accuracy and reliability of the prediction; based on the multi-dimensional feature set, the grinding operation dynamically adjusts the grading rotor speed when processing materials with different characteristics, which facilitates more precise material grading control, improves the grinding effect and product quality; the result verification and optimization in the data fusion process help detect abnormal or unreasonable data points, adjust the fusion algorithm or feature selection in time, and optimize the control strategy of the grinding operation; by reasonably selecting features and optimizing fusion algorithms, the processing of redundant data is reduced, the data processing efficiency is improved, and the cost waste caused by invalid operations is reduced; through data fusion and the construction of multi-dimensional feature sets, the control accuracy and production efficiency of the grinding operation are improved, providing support for the continuous optimization and technological innovation of the cement production process.

[0117] S5, inputting the multi-dimensional feature set of the grinding operation into a pre-built grinding uniform flow field prediction model to obtain a uniform flow field feature vector of this grinding operation;

[0118] Step S5 is specifically implemented as follows:

[0119] First, a grinding uniform flow field prediction model is constructed, as follows:

[0120] Collect detailed records of past grinding operations, including material size distribution, classifier rotor operating parameters, equipment characteristics information, and operating efficiency and energy consumption data; record environmental variables related to the grinding process, such as temperature, humidity, and grinding system operating status parameters;

[0121] Remove abnormal data, process missing data, and ensure data quality; convert data of different dimensions and scales to the same scale to facilitate the processing of the grinding uniform flow field prediction model; select or construct features that are helpful for prediction based on professional knowledge;

[0122] The correlation between features and target variables is analyzed through correlation coefficient matrix, mutual information and other methods; the feature dimension is reduced and redundant features are removed through recursive feature elimination and principal component analysis, so as to improve the efficiency of the grinding uniform flow field prediction model;

[0123] Select candidate evaluation models based on the nature of the problem; determine the metrics for evaluating model performance;

[0124] The data set is divided into training set, validation set and test set; the generalization ability of the grinding uniform flow field prediction model is evaluated by using methods such as K-fold cross validation; the parameters of the grinding uniform flow field prediction model are adjusted by using methods such as grid search and random search to find the optimal parameter combination;

[0125] The grinding uniform flow field prediction model was trained on the training set using the optimized parameters; and the performance of the grinding uniform flow field prediction model was evaluated on the validation set and the test set;

[0126] According to the evaluation results, return to the feature engineering or grinding uniform flow field prediction model selection stage for adjustment; continue to adjust and optimize until the performance of the grinding uniform flow field prediction model meets the preset standards;

[0127] Afterwards, the multi-dimensional feature set is checked and preprocessed, and the processed multi-dimensional feature set is used as input data and input into the grinding uniform flow field prediction model; after receiving the input multi-dimensional feature set, the grinding uniform flow field prediction model performs calculations according to the internal algorithms and parameters; after the calculations are completed, the grinding uniform flow field prediction model will output a uniform flow field feature vector, which describes the flow state of the material in the grading rotor under the current grinding operation conditions; the uniform flow field feature vector reflects the flow of the material in the grading rotor, including parameters such as flow velocity, flow rate and pressure distribution; by comparing and analyzing the uniform flow field feature vectors under different conditions, the working performance and efficiency of the grading rotor are evaluated, and by evaluating the working performance and efficiency of the grading rotor, the speed of the grading rotor can be easily regulated;

[0128] By collecting and analyzing detailed data of historical grinding operations, combined with environmental variables and equipment status parameters, the grinding uniform flow field prediction model is established on the basis of sufficient data, which improves the comprehensiveness and accuracy of the prediction; outlier removal, missing value processing and data standardization in the data preprocessing stage ensure the accuracy of the grinding uniform flow field prediction model training and avoid prediction deviations caused by data quality problems; through correlation analysis and feature selection technology, noise and redundant features are reduced, the efficiency of the grinding uniform flow field prediction model and the effective capture of key features are improved; through the use of multi-feature selection, feature dimensionality reduction and parameter optimization steps, the grinding uniform flow field prediction model is continuously optimized and adjusted to improve the generalization ability and prediction accuracy of the grinding uniform flow field prediction model, so as to better adapt to different grinding operation conditions; through continuous evaluation and Adjust the grinding uniform flow field prediction model, establish a closed-loop system from the construction of the grinding uniform flow field prediction model to the optimization, and ensure the continuous improvement and adaptability of the grinding uniform flow field prediction model; the output uniform flow field characteristic vector provides an intuitive and quantitative evaluation index for the grinding operation, which is convenient for intuitively understanding the working state of the grading rotor and the material flow field characteristics, and provides a data basis for the precise control of the grading rotor speed; through refined prediction and control, the grading rotor speed can be dynamically adjusted to achieve more efficient material grading, reduce energy consumption, and improve product quality and production efficiency; through the combination of data-driven and grinding uniform flow field prediction model prediction, multi-dimensional feature fusion, model optimization and adjustment, and precise control and evaluation, the precise control of the grading rotor speed in the cement production process is achieved, and the product quality and performance stability are improved.

[0129] S6, using the obtained uniform flow field characteristic vector as an index mark, matching it in the pre-built flow field grading rotor reference space, mapping out the optimal grading rotor speed corresponding to the uniform flow field characteristic vector, and controlling the grading rotor operation according to the optimal grading rotor speed;

[0130] The implementation method of step S6 is as follows:

[0131] First, build the flow field classification rotor control space, specifically:

[0132] Collect detailed operating data from the grinding operation, including various operating speeds of the classifying rotor, detailed equipment parameters, material characteristics, environmental parameters and performance indicators of the grinding operation; clean the collected operating data to remove outliers and fill in missing values; standardize or normalize the data to ensure comparability of data from different sources;

[0133] Based on the theoretical and practical experience of grinding operations, select the features that have the greatest impact on the grinding effect, including flow field characteristics, equipment characteristics and material characteristics, and build a feature set; try different feature combinations, and determine the feature combination that best represents the state and effect of the grinding operation through correlation analysis and statistical tests;

[0134] According to the selected features, a feature vector is created for each historical operation instance, and the historical operation feature vector contains key information reflecting the flow field state and equipment operation status;

[0135] For each historical operation instance, evaluate its grinding effect; based on the evaluation results, determine the optimal classification rotor speed corresponding to each feature vector;

[0136] Pair the feature vector with the corresponding optimal graded rotor speed to form a data pair; use data mining or machine learning technology to construct a queryable reference space; the reference space should be able to quickly find the corresponding optimal speed based on the input feature vector;

[0137] Use independent validation set data to test whether the classifying rotor speed predicted by the control space can actually bring about the expected grinding effect; according to the validation results, adjust the feature selection, grinding uniform flow field prediction model parameters and optimization strategy until the prediction performance of the control space reaches a satisfactory level;

[0138] Integrate the control space into the control system of the grinding operation to automatically adjust the classifying rotor speed according to the feature vector collected in real time; continuously update and optimize the control space as more operation data is accumulated;

[0139] Then, the uniform flow field feature vector is used as a query condition to match it in the constructed flow field grading rotor reference space; after matching the corresponding flow field feature, the optimal grading rotor speed that matches it is extracted from the reference space; the optimal grading rotor speed value is based on historical experience and the prediction model of the uniform flow field of grinding, and is considered to be able to achieve the best material grading effect under the specific flow field conditions; according to the mapped optimal grading rotor speed, the actual operating speed of the grading rotor is adjusted through the automatic control system; the control process needs to respond in real time to ensure that the grading rotor speed can be quickly adjusted to the theoretical optimal value to adapt to the changes in material properties during the grinding process; by monitoring the real-time effect of the grinding operation and comparing it with the expected particle size distribution, the grading rotor speed is fine-tuned according to the deviation to achieve closed-loop control and optimize the grinding effect;

[0140] By constructing a flow field classification rotor reference space based on historical operation data, it is possible to match the optimal classification rotor speed for each specific flow field feature vector, ensuring the high personalization and dynamic adaptability of the control strategy when facing different material characteristics and operating conditions; based on the collection, cleaning, standardization and feature selection of a large amount of data, it ensures the scientificity and accuracy of the control decision, reduces the limitations of traditional fixed parameter settings, and improves the efficiency of grinding operations and product quality; by using the verification set data to verify the performance of the grinding uniform flow field prediction model, and continuously adjusting the feature selection, grinding uniform flow field prediction model parameters and optimization strategy based on the feedback results, it ensures that the prediction performance of the reference space continues to improve, forming a closed-loop system of continuous learning and optimization. system; the control space integrated into the control system can automatically adjust the speed of the grading rotor according to the real-time collected feature vectors, achieve rapid response and real-time control, reduce delays and misjudgments of human intervention, and improve production efficiency; through real-time monitoring of the grinding operation effect, fine-tuning is performed according to the deviation between the actual particle size distribution and the expected target to achieve closed-loop control and ensure the stability and consistency of the grinding process; comprehensive consideration is given to multiple factors such as flow field characteristics, equipment characteristics and material characteristics, and through the optimization of feature combinations, the key variables affecting the grinding effect are fully captured to improve the comprehensive effectiveness of the control strategy; through highly data-based and intelligent means, the accuracy and flexibility of the grading rotor speed control in the grinding operation, as well as the quality and efficiency control in the cement production process, are improved.

[0141] Embodiment 2: Figure 3 As shown, the uniform flow field graded rotor speed control system of the present invention specifically includes the following modules:

[0142] The material property analysis module is used to obtain the target particle size of the grinding operation and the original particle size distribution data of the cement material; analyze and extract the classification property information of the cement material, including the target particle size, the mass proportion of the target particle size, the non-target particle size and the mass proportion of the non-target particle size;

[0143] A rotor characteristic reading module, used to obtain the physical characteristic information of the grading rotor, wherein the physical characteristic information of the grading rotor includes rotor size, rotor mass, blade angle, blade number, blade material and inlet and outlet diameters;

[0144] A data fusion module is used to integrate the cement material classification characteristic information output by the material characteristic analysis module with the rotor characteristic information provided by the rotor characteristic reading module to form a multi-dimensional feature set of the grinding operation;

[0145] The flow field prediction module is used to receive the multi-dimensional feature set output by the data fusion module; use the pre-trained grinding uniform flow field prediction model to calculate the uniform flow field feature vector of this grinding operation;

[0146] The rotor speed optimization module is used to use the uniform flow field feature vector output by the flow field prediction module as a query condition in the flow field classification rotor comparison space; execute the matching algorithm to find the rotor speed setting that best matches the feature vector; output the optimal classification rotor speed to the execution unit to control the classification rotor to run at the speed;

[0147] The control and execution module is used to adjust the actual operating speed of the grading rotor according to the optimal grading rotor speed instruction provided by the rotor speed optimization module.

[0148] By analyzing material characteristics and rotor characteristics in real time, the uniform flow field-based grading rotor speed control system can automatically adjust the speed of the grading rotor according to different materials and operating conditions, dynamically optimize the grinding process, and better adapt to different types of cement materials; based on material characteristic analysis and rotor characteristic reading, the uniform flow field-based grading rotor speed control system can generate a multi-dimensional feature set, calculate the uniform flow field feature vector through the flow field prediction model, improve the accuracy of rotor speed control, and facilitate obtaining a more uniform material particle size distribution, thereby improving the quality of cement products; by optimizing the rotor speed, the system can ensure consistent grinding effects between different grinding batches, reducing product inconsistency caused by fluctuations in process parameters, At the same time, it also helps to improve production efficiency and resource utilization; precise rotor speed control reduces over-grinding and under-grinding, reduces energy waste and raw material waste, and reduces production costs; the design of the uniform flow field classification rotor speed control system reduces the need for manual intervention and improves the overall intelligence level of the production line; the modular design enables the uniform flow field classification rotor speed control system to be integrated with existing cement production equipment, which is convenient for later maintenance and upgrades to cope with future technological advances or changes in production needs; the uniform flow field classification rotor speed control system solves the problems of low efficiency and product quality fluctuations in traditional grinding operations, reduces production costs, and improves grinding operation efficiency and product quality in cement production.

[0149] The various variations and specific embodiments of the method for controlling rotor speed based on uniform flow field grading in the aforementioned embodiment 1 are also applicable to the rotor speed control system based on uniform flow field grading in the present embodiment. Through the aforementioned detailed description of the method for controlling rotor speed based on uniform flow field grading, those skilled in the art can clearly understand the implementation method of the rotor speed control system based on uniform flow field grading in the present embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0150] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0151] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling rotor speed based on uniform flow field classification, characterized in that: The method comprises: Obtain the target particle size of the grinding operation and the particle size distribution data of cement materials; Dividing the cement material particle size distribution data based on the target particle size to obtain cement material classification characteristic information, wherein the cement material classification characteristic information includes the target particle size, the target particle size mass ratio, the non-target particle size, and the non-target particle size mass ratio; Obtaining classification rotor characteristic information; The classification rotor characteristic information and cement material classification characteristic information are data-fused to obtain a multi-dimensional feature set of the grinding operation; Input the multi-dimensional feature set of the grinding operation into the pre-built grinding uniform flow field prediction model to obtain the uniform flow field feature vector of this grinding operation; The uniform flow field characteristic vector obtained is used as an index mark, and matching is performed in the pre-built flow field grading rotor reference space to map the optimal grading rotor speed corresponding to the uniform flow field characteristic vector, and the grading rotor operation is controlled according to the optimal grading rotor speed.

2. The method for controlling rotor speed based on uniform flow field classification according to claim 1, characterized in that: The method for obtaining the particle size distribution data comprises: Select standard sieves according to the particle size range of cement materials, and arrange the sieve hole sizes in order from large to small; The cement material is dried, crushed and pre-screened, and then the cement material is weighed and the initial total weight is recorded; Stack the sieves in descending order of aperture, place the cover on the top and the receiving tray on the bottom, sprinkle the cement material evenly on the top sieve, and use mechanical vibration to make the cement material pass through the sieve with the corresponding aperture until it falls into the bottom tray; Stop vibration after all cement materials have passed through the penetrable sieve; After stopping the vibration, weigh the residue on each layer of sieve separately; Compare the weight of the material on each sieve with the initial total weight and calculate the percentage of material in each particle size range; The sieve hole size is the horizontal axis, and the percentage of material passing through each sieve hole is the vertical axis, and a particle size distribution curve or a cumulative particle size distribution curve is drawn.

3. The method for controlling rotor speed based on uniform flow field classification according to claim 1, characterized in that: The graded rotor characteristic information includes rotor size, rotor mass, blade angle, blade quantity, blade material, and inlet and outlet diameters.

4. The method for controlling rotor speed based on uniform flow field classification according to claim 1, characterized in that: The method for data fusion of the stage rotor characteristic information and the cement material classification characteristic information comprises: Remove the data points of the classification rotor characteristic information and the cement material classification characteristic information to handle the missing values; Identify the features of the fusion target and exclude irrelevant features; Select fusion algorithm according to data type and fusion target; Apply fusion algorithms to merge the data into a unified data set; Verify the accuracy of the fusion results and check whether there are unreasonable data points.

5. The method for controlling rotor speed based on uniform flow field classification according to claim 1, characterized in that: The method for constructing the multi-dimensional feature set includes: Verify the acquired data of the classification characteristic information of the cement material and the characteristic information of the classification rotor; Standardizing the data of the grading characteristic information of cement materials and the characteristic information of the grading rotor; According to the actual needs of grinding operations and existing industry experience, the characteristic information that has the greatest impact on the grinding effect is selected as the key feature; Arrange the selected features in order to form a feature vector; Use data fusion algorithm to fuse each feature vector into a multi-dimensional feature set.

6. The method for controlling rotor speed based on uniform flow field classification according to claim 1, characterized in that: The method for constructing the grinding uniform flow field prediction model comprises: Collect records of past grinding operations and record environmental variables related to the grinding process; Remove abnormal data and process missing data, and convert data of different dimensions and scales to the same scale; Analyze the correlation between features and target variables through coefficient matrix; Recursive feature elimination and principal component analysis were used to reduce feature dimensions and remove redundant features; Based on the nature of the problem, select candidate evaluation models; The data set was divided into training set, validation set and test set. The K-fold cross-validation method was used to evaluate the generalization ability of the grinding uniform flow field prediction model. The grid search and random search methods were used to adjust the parameters of the grinding uniform flow field prediction model. The grinding uniform flow field prediction model was trained on the training set using the optimized parameters, and the performance of the grinding uniform flow field prediction model was evaluated on the validation set and the test set. According to the evaluation results, return to the grinding uniform flow field prediction model selection stage for adjustment so that the performance of the grinding uniform flow field prediction model meets the preset standards.

7. The method for controlling rotor speed based on uniform flow field classification according to claim 1, characterized in that: The method for constructing the flow field classification rotor control space is as follows: Collect detailed operating data from the grinding operation, clean the collected operating data, remove outliers and fill in missing values, and perform standard processing on the operating data; Based on the theoretical and practical experience of grinding operations, select the features that have the greatest impact on the grinding effect, try different feature combinations, and determine the feature combination that best represents the state and effect of the grinding operation through correlation analysis and statistical tests; Based on the selected features, a feature vector is created for each historical job instance; For each historical operation instance, the grinding effect is evaluated, and based on the evaluation results, the optimal classifying rotor speed corresponding to each feature vector is determined; Pair the feature vectors with the corresponding optimal graded rotor speeds to form data pairs; use data mining or machine learning techniques to construct a queryable comparison space; Use independent validation set data to test whether the classifying rotor speed predicted by the control space can actually bring about the expected grinding effect. According to the validation results, adjust the feature selection, grinding uniform flow field prediction model parameters and optimization strategy; The control space is integrated into the control system of the grinding operation to automatically adjust the speed of the classifying rotor according to the feature vector collected in real time.

8. A rotor speed control system based on uniform flow field classification, characterized in that: The system comprises: The material property analysis module is used to obtain the target particle size of the grinding operation and the original particle size distribution data of the cement material; analyze and extract the classification property information of the cement material, including the target particle size, the mass proportion of the target particle size, the non-target particle size and the mass proportion of the non-target particle size; A rotor characteristic reading module, used to obtain the physical characteristic information of the grading rotor, wherein the physical characteristic information of the grading rotor includes rotor size, rotor mass, blade angle, blade number, blade material and inlet and outlet diameters; A data fusion module is used to integrate the cement material classification characteristic information output by the material characteristic analysis module with the rotor characteristic information provided by the rotor characteristic reading module to form a multi-dimensional feature set of the grinding operation; The flow field prediction module is used to receive the multi-dimensional feature set output by the data fusion module; use the pre-trained grinding uniform flow field prediction model to calculate the uniform flow field feature vector of this grinding operation; The rotor speed optimization module is used to use the uniform flow field feature vector output by the flow field prediction module as a query condition in the flow field classification rotor comparison space; execute the matching algorithm to find the rotor speed setting that best matches the feature vector; output the optimal classification rotor speed to the execution unit to control the classification rotor to run at the speed; The control and execution module is used to adjust the actual operating speed of the grading rotor according to the optimal grading rotor speed instruction provided by the rotor speed optimization module.

9. An electronic device for controlling rotor speed based on uniform flow field classification, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images