Unpowered powder concentrator air volume control method and system

Abstract

The invention relates to the technical field of powder concentrator control, in particular to an unpowered powder concentrator air volume control method and system, which reduce the time and frequency of shutdown adjustment, improve the continuity and stability of a production line and finally improve the overall production efficiency through real-time and dynamic control. The method comprises the following steps: collecting a plurality of material grading samples obtained by grading and powder selecting of an unpowered powder selecting machine; based on preset material grading target features, target deviation feature extraction is carried out on each material grading sample, and a material grading deviation vector corresponding to the collection time is obtained; obtaining material grading deviation vectors at a plurality of collection times, and arranging the material grading deviation vectors according to a time sequence to obtain a material grading deviation matrix; and inputting the material grading deviation matrix into a pre-constructed powder concentrator grading precision evaluation model to obtain a material grading precision index corresponding to the unpowered powder concentrator.

Description

Technical Field

[0001] The invention relates to the technical field of powder classifier control, and in particular to an air volume control method and system for an unpowered powder classifier. Background Art

[0002] In the process of material processing and screening, unpowered powder classifier is a common equipment, which realizes material classification and powder selection through unpowered sources such as natural wind or mechanical wind. However, in actual application, due to the influence of various factors such as material properties, environmental conditions and the equipment itself, the classification and powder selection effect of unpowered powder classifier is often difficult to achieve the expected goal, resulting in low material classification accuracy, affecting the quality and production efficiency of cement and other products.

[0003] The existing air volume control method of unpowered powder classifier often relies on the operator's experience for adjustment, which is not only inefficient but also difficult to ensure the accuracy and stability of air volume adjustment. At the same time, due to the lack of real-time monitoring and evaluation of material classification effect, operators are often unable to promptly discover and solve problems in the classification and powder selection process, thereby further reducing material classification accuracy and production efficiency. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for controlling the air volume of an unpowered powder classifier through real-time and dynamic control, reducing the time and frequency of shutdown adjustments, improving the continuity and stability of the production line, and finally improving the overall production efficiency.

[0005] In a first aspect, the present invention provides an air volume control method for an unpowered powder classifier, the method comprising:

[0006] Collect several kinds of material classification samples obtained by classification and powder selection of unpowered powder classifier;

[0007] Based on the preset material classification target features, target deviation features are extracted for each material classification sample to obtain the material classification deviation vector corresponding to the collection time;

[0008] Obtain material classification deviation vectors at multiple acquisition times, and arrange them in chronological order to obtain a material classification deviation matrix;

[0009] Inputting the material classification deviation matrix into a pre-constructed classifier classification accuracy evaluation model to obtain a material classification accuracy index corresponding to the unpowered classifier;

[0010] Based on the material classification accuracy index, the optimal air volume control parameters corresponding to the unpowered powder classifier are mapped in the preset air volume control parameter database;

[0011] According to the optimal air volume control parameters, the air volume of the unpowered powder classifier is controlled.

[0012] Furthermore, the material grading deviation vector is composed of a number of deviation characteristic values, each deviation characteristic value corresponds to a material grading sample, and the material grading target characteristics include a target particle size and a target particle size mass proportion corresponding to each material grading sample. The deviation characteristic value refers to the difference between the mass proportion of the material of the target particle size in the material grading sample and the target particle size mass proportion.

[0013] Furthermore, the deviation characteristic values ​​corresponding to the same target particle size in the material classification deviation matrix and collected at different times are located in the same column, and the deviation characteristic values ​​corresponding to different target particle sizes collected at the same time are located in the same row;

[0014] The material classification deviation matrix is ​​as follows:

[0015]

[0016] Among them, dmn is an element in the material classification deviation matrix, representing the deviation characteristic value of the nth particle size level at the mth collection time; the mth row contains the deviation characteristic values ​​of all particle size levels, corresponding to the mth collection time point; the nth column contains the deviation characteristic values ​​of the nth particle size level at all collection time points.

[0017] Furthermore, a method for collecting several material classification samples obtained by classifying powder by an unpowered powder classifier includes:

[0018] Determine the sampling position of the unpowered powder classifier and conduct sampling; the sampling position includes the graded feed inlets and discharge outlets of the powder classifier at different levels;

[0019] Determine the sampling frequency and cycle according to production needs and equipment operating conditions;

[0020] Select sampling tools and equipment for sampling;

[0021] Select the sampling method based on the location of the sampling point and the nature of the material; the sampling methods include continuous flow sampling, manual assisted sampling and mechanical assisted sampling;

[0022] After sampling is completed, each collected material classification sample shall be marked and recorded, including sampling time, sampling point and sample number information.

[0023] Furthermore, the method for constructing the classifier classification accuracy evaluation model comprises:

[0024] Collect the information of materials before and after classification of the unpowered powder classifier under different air volume control parameter settings as the training basis of the powder classifier classification accuracy evaluation model;

[0025] Determine the target particle size range and the particle size distribution curve of the target mass proportion of each particle size segment;

[0026] Extracting features from the classified material, the material extraction features including the percentage of material in different particle size segments, the recovery ratio of coarse powder and fine powder, and the recovery rate of fine powder minus the proportion of fine powder in coarse powder;

[0027] Calculate the deviation between the actual particle size distribution and the target particle size distribution;

[0028] Select machine learning algorithm to build a classifier classification accuracy evaluation model;

[0029] Use the material classification deviation matrix and the corresponding classification accuracy index in the historical data as the training data set to train the classification accuracy evaluation model of the powder classifier; and adjust the parameters of the classification accuracy evaluation model of the powder classifier;

[0030] Independent validation sets and test sets were used to evaluate the generalization ability of the classifier classification accuracy evaluation model.

[0031] Furthermore, the method for constructing the air volume control parameter database includes:

[0032] List the air volume control parameters that affect the classification effect; design an experimental matrix, wherein the experimental matrix includes the air volume control parameters that affect the classification effect;

[0033] Perform the experiment and change only one air volume control parameter during the experiment, while keeping other air volume control parameters unchanged. Perform multiple experiments according to the number of air volume control parameters, and record the parameter settings and results of each experiment.

[0034] Check and clean the experimental data, remove outliers and erroneous data points, convert the cleaned experimental data into a unified format, and store the converted experimental data in the database;

[0035] Design a database to store and query experimental data. The database structure includes tables, fields, and data types.

[0036] Use the database management module to create an air volume control parameter database and import the preprocessed data.

[0037] Furthermore, the air volume control parameters include air inlet opening, air outlet opening, air guide blade angle, wind pressure, and temperature and humidity inside and outside the powder selector silo.

[0038] On the other hand, the present application also provides an air volume control system for an unpowered powder classifier, the system comprising:

[0039] The sample collection module is used to collect various material classification samples during the classification and powder selection process of the unpowered powder classifier;

[0040] The feature extraction module is used to analyze each material classification sample through the preset material classification target feature, calculate and extract the difference between the actual mass proportion of the target particle size material and the target set value, and generate a material classification deviation vector;

[0041] Deviation matrix generation module, used to collect and organize material classification deviation vectors at multiple time points to form a material classification deviation matrix of time series; the columns of the material classification deviation matrix represent the deviation characteristic values ​​at different time points, and the rows represent the deviation characteristic values ​​of different target particle sizes at the same time point;

[0042] The classification accuracy evaluation module is used to receive the deviation matrix as input, and calculate the material classification accuracy index of the unpowered powder classifier by using the pre-built powder classifier classification accuracy evaluation model;

[0043] A parameter mapping module is used to search and map the optimal air volume control parameters that best match the unpowered powder classifier in a preset air volume control parameter database according to the calculated material classification accuracy index;

[0044] The execution module is used to receive the optimal air volume control parameters from the air volume control parameter mapping module, dynamically adjust the air volume of the unpowered powder selection machine, and optimize the effect of graded powder selection.

[0045] In a third aspect, the present application provides an electronic device, 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 the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0046] 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.

[0047] Compared with the prior art, the beneficial effects of the present invention are as follows: by collecting material classification samples, extracting target deviation features, and constructing a material classification deviation matrix, the classification accuracy is evaluated based on a pre-constructed classifier classification accuracy evaluation model, and the optimal air volume control parameters are mapped to achieve the intelligence and automation of the entire air volume control process, thereby improving work efficiency; by collecting and evaluating the effect of material classification in real time, the air volume control parameters are dynamically adjusted according to the evaluation results to ensure that the unpowered classifier always works in the best state, thereby improving material classification accuracy and production efficiency; by using the preset material classification target features and the classifier classification accuracy evaluation model, the material classification accuracy index is accurately calculated, and the material classification accuracy index based on the material classification target features is automatically calculated. The material classification accuracy index maps the optimal air volume control parameters in the database to improve the accuracy and stability of air volume adjustment; by adapting to changes in different material properties, environmental conditions and equipment status, the air volume control parameters are dynamically adjusted to optimize the effect of classification and powder selection, and improve the adaptability and flexibility of classification and powder selection; by reducing human intervention, reducing operating difficulty and error rate, and improving the reliability and stability of the production process; by optimizing the effect of classification and powder selection, it can ensure that the material classification accuracy reaches the preset target and improve the quality of cement and other products; through real-time and dynamic control, the time and frequency of shutdown adjustments are reduced, the continuity and stability of the production line are improved, and finally the overall production efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flow chart of the present invention;

[0049] Figure 2 It is a flow chart of the construction method of the classification accuracy evaluation model of the powder selector;

[0050] Figure 3 It is the structural diagram of the air volume control system of the unpowered powder classifier. DETAILED DESCRIPTION

[0051] 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.

[0052] 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.

[0053] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0054] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] The present application is described below in conjunction with the drawings in the present application.

[0059] Embodiment 1: Figure 1 to Figure 2 As shown, the air volume control method of the unpowered powder classifier of the present invention specifically includes the following steps:

[0060] S1. Collect several kinds of material classification samples obtained by classification and powder selection by unpowered powder selection machine;

[0061] The collection of material classification samples is carried out as follows:

[0062] First, determine the sampling position of the unpowered powder classifier and conduct sampling; the selection of sampling points can reflect the material classification inside the powder classifier, including the different levels of classification feed and discharge ports of the powder classifier;

[0063] Determine the sampling frequency and cycle according to production needs and equipment operation status; the setting of sampling frequency and cycle can capture the influence of material properties, environmental conditions and equipment status factors on the classification effect;

[0064] Select appropriate sampling tools and equipment for sampling; sampling tools and equipment can accurately collect material samples without contaminating or damaging the materials;

[0065] Select the appropriate sampling method based on the location of the sampling point and the properties of the material; for materials with good fluidity, use continuous flow sampling; for materials with poor fluidity, use manual or mechanical assisted sampling;

[0066] After sampling is completed, each collected material classification sample shall be marked and recorded, including sampling time, sampling point and sample number information;

[0067] Properly process the collected material classification samples to facilitate subsequent analysis, and finally properly store the processed material classification samples to avoid contamination or deterioration;

[0068] Material classification samples are the data basis for evaluating the classification effect of the unpowered powder classifier; by analyzing and comparing samples of different classifications, we can understand the particle size distribution, mass proportion and other indicators of the materials in each classification, and judge whether the classification effect has reached the expected goal; the analysis results of material classification samples guide adjustments in the production process; when it is found that the quality of a certain classification of materials does not meet the requirements, the air volume control parameters and screen aperture of the unpowered powder classifier are adjusted in time to improve the classification effect, product quality and production efficiency; by regularly collecting and analyzing material classification samples, problems in the production process can be discovered in time, and corresponding measures can be taken to solve them to ensure the stability and consistency of product quality.

[0069] S2. Based on the preset material classification target feature, target deviation feature extraction is performed on each material classification sample to obtain a material classification deviation vector corresponding to the acquisition time; the material classification deviation vector is composed of a plurality of deviation feature values, each deviation feature value corresponds to a material classification sample, the material classification target feature includes a target particle size and a target particle size mass proportion corresponding to each material classification sample, and the deviation feature value refers to the difference between the mass proportion of the material of the target particle size in the material classification sample and the mass proportion of the target particle size;

[0070] Step S2 extracts the target deviation feature of each material classification sample based on the preset material classification target feature to obtain the material classification deviation vector corresponding to the acquisition time. The steps are as follows: first, the target feature of material classification is clarified; the target feature of materials such as cement includes the target particle size and the target particle size mass ratio corresponding to each material classification sample;

[0071] For each collected material classification sample, calculate the deviation between the actual particle size distribution of the material classification sample and the target particle size distribution; this is achieved by measuring the mass proportion of the material in each particle size range in the sample;

[0072] Then the actual mass proportion measured is compared with the preset target particle size mass proportion, and the difference, i.e., the deviation characteristic value, is calculated; the deviation characteristic value indicates the difference between the material mass proportion of the current material classification sample within the target particle size range and the target value;

[0073] For each material classification sample, a corresponding deviation characteristic value will be obtained, and the above deviation characteristic values ​​together constitute the material classification deviation vector corresponding to the collection time;

[0074] The material classification deviation vector is an array containing multiple deviation characteristic values; each deviation characteristic value corresponds to a material classification sample, indicating the deviation between the material mass proportion of the sample within a specific particle size range and the target value;

[0075] The length of the material classification deviation vector depends on the type and number of material classification samples we collect, as well as the number of particle size ranges we are concerned about;

[0076] The calculation process of the deviation characteristic value needs to be precise and reliable to ensure that the effect of material classification can be accurately evaluated; after the deviation characteristic value is calculated, the deviation characteristic value is arranged and recorded in a specific order to facilitate subsequent analysis and processing;

[0077] By collecting material classification samples in real time and calculating their deviation characteristic values, the effect of current material classification can be reflected; it is convenient for operators to respond quickly and adjust the air volume control parameters, thereby ensuring the continuous improvement of material classification accuracy; at the same time, accurate measurement and calculation methods are adopted to ensure the accuracy of deviation characteristic values, thereby improving the accuracy of evaluation results; based on the preset material classification target characteristics and objective data analysis, the interference of human factors is avoided, the objectivity and fairness of evaluation results are improved, and the effect of material classification is accurately reflected; considering the influence of different material classification samples and particle size ranges, by calculating multiple deviation characteristic values ​​and forming material classification deviation vectors, the effect of material classification is comprehensively evaluated, which has better adaptability and flexibility By evaluating the effect of material grading and calculating the deviation characteristic value, it can provide clear guidance information for operators to understand the problems existing in the current material grading and the direction of improvement; at the same time, since the effect of material grading is reflected in real time, it is convenient for operators to predictably adjust the air volume control parameters, reduce potential problems and improve production efficiency; based on data analysis and machine learning and other technologies, it can realize automatic evaluation and optimization of material grading effects; improve the intelligence and automation of the air volume control process, reduce the need for manual intervention, and improve the stability and reliability of production; by real-time collection and analysis of the data of material grading samples, it can accurately evaluate the effect of material grading and optimize the air volume control parameters, thereby improving material grading accuracy and production efficiency.

[0078] S3. Obtain material classification deviation vectors at multiple collection times and arrange them in chronological order to obtain a material classification deviation matrix; in the material classification deviation matrix, the deviation characteristic values ​​collected at different times corresponding to the same target particle size are located in the same column, and the deviation characteristic values ​​corresponding to different target particle sizes collected at the same time are located in the same row

[0079] In step S2, the material classification deviation vector at a single collection time point is obtained. The material classification deviation vector quantifies the deviation between the actual classification effect and the preset target. However, the data at a single time point can only reflect the situation at that time, and cannot represent the trend or fluctuation of the classification effect over time, nor can it provide sufficient information for long-term performance evaluation or prediction. Therefore, step S3 collects and organizes the deviation vectors at multiple time points to construct a material classification deviation matrix, which is convenient for more data analysis. The material classification deviation matrix construction method is as follows:

[0080] In step S2, material classification deviation vectors at multiple collection time points are collected, each vector corresponds to a specific collection time point, and multiple classification deviation vectors contain information on the deviation between the classification effect of materials at different particle size levels and the target setting, that is, the deviation characteristic value;

[0081] Each column of the material classification deviation matrix represents a specific particle size level; each column contains the deviation characteristic values ​​corresponding to the particle size level collected from all acquisition time points; it is convenient to view the trend of a specific particle size level over time longitudinally;

[0082] Each row of the material classification deviation matrix represents a specific collection time point; each row contains the deviation characteristic values ​​of all particle size levels at the same time point; it is convenient to compare the classification effects of different particle size levels at a certain time point horizontally;

[0083] The number of rows of the material classification deviation matrix is ​​equal to the total number of acquisition time points, and the number of columns is equal to the number of particle size levels considered; so that the material classification deviation matrix can clearly reflect the overall picture of the classification effect over time, as well as the relationship between different particle size levels;

[0084] The rows of the material classification deviation matrix are arranged in chronological order; this ensures that when analyzing the material classification deviation matrix, the evolution trend of the classification effect over time can be identified; the time ordering facilitates the use of time series analysis techniques, such as sliding window averaging and trend line fitting, to identify potential patterns or anomalies;

[0085] The material classification deviation matrix is ​​as follows:

[0086]

[0087] Where dmn is an element in the material classification deviation matrix, representing the deviation characteristic value of the nth particle size level at the mth collection time; the mth row contains the deviation characteristic values ​​of all particle size levels, corresponding to the mth collection time point; the nth column contains the deviation characteristic values ​​of the nth particle size level at all collection time points;

[0088] By collecting material classification deviation vectors at multiple time points, the material classification deviation matrix can fully reflect the trend and fluctuation of classification effect over time, making subsequent data analysis more accurate and effective; each column of the material classification deviation matrix represents a specific particle size level, showing the trend of material classification effect of this particle size level over time; it is easy to quickly identify the changing trend of classification effect and take corresponding adjustment measures; each row represents a specific collection time point, which can compare the classification effects of different particle size levels at the same time point; horizontal comparison helps to identify the mutual influence and potential problems between different particle size levels, providing a basis for subsequent optimization; the number of rows in the material classification deviation matrix =Equal to the total number of acquisition time points, and the number of columns is equal to the number of particle size levels considered; the clear data structure enables operators to intuitively understand the overall picture of the classification effect over time and the relationship between different particle size levels; the rows of the material classification deviation matrix are arranged in chronological order, which is convenient for applying time series analysis technology to identify potential patterns or anomalies; it is easy to timely discover and solve problems in the classification and powder selection process, and improve material classification accuracy and production efficiency; in summary, the material classification deviation matrix constructed in step S3 provides data support and analysis tools for the air volume control and performance optimization of the unpowered powder selection machine, reduces the errors existing in human operation, and improves the accuracy and production efficiency of material classification.

[0089] S4, inputting the material classification deviation matrix into a pre-constructed classifier classification accuracy evaluation model to obtain a material classification accuracy index corresponding to the unpowered classifier;

[0090] Step S4 is to evaluate the classification accuracy of the unpowered powder classifier. By inputting the material classification deviation matrix into the pre-built classification accuracy evaluation model, an accuracy index that can comprehensively reflect the classification effect is calculated. The specific steps are as follows:

[0091] The construction process of the classifier classification accuracy evaluation model includes:

[0092] Data preparation: Collect historical data and use the material classification deviation matrix corresponding to the historical data as the input feature of the classifier classification accuracy evaluation model; the material classification deviation matrix represents the deviation between the actual classification effect and the target classification effect, and is the information for evaluating the classification accuracy; define the material classification accuracy index corresponding to the material classification deviation matrix as the output label of the model; the material classification accuracy index is a quantitative indicator that reflects the overall quality of the classification effect;

[0093] Model selection: Based on the problem of quantifying the grading effect, select appropriate machine learning algorithms to build a classifier grading accuracy evaluation model, including linear regression, support vector machine, random forest, and neural network. Use historical data, i.e., the material grading deviation matrix and the corresponding grading accuracy index, as the training data set to train the classifier grading accuracy evaluation model to learn the relationship between input features and output labels.

[0094] Model training: Use the training data set to train the selected algorithm and adjust the parameters of the powder classifier classification accuracy evaluation model until the powder classifier classification accuracy evaluation model can better fit the training data; use independent validation sets and test sets to evaluate the generalization ability of the powder classifier classification accuracy evaluation model to ensure that the powder classifier classification accuracy evaluation model can also give accurate classification accuracy index predictions on unseen data;

[0095] Model application: The classifying accuracy evaluation model for powder classifier receives the material classification deviation matrix as input. Each row in the matrix represents a set of deviation characteristic values ​​at a collection time point, and each column represents the change of deviation characteristic values ​​of different particle size levels over time. The classifying accuracy evaluation model for powder classifier outputs the material classification accuracy index, which quantifies the classification effect of the unpowered powder classifier under specific operating conditions.

[0096] Dynamic adjustment: During the production process, the classifier classification accuracy evaluation model receives the latest material classification deviation matrix in real time, calculates the classification accuracy index, and provides a basis for the dynamic adjustment of the air volume control parameters; the classification accuracy index is used as a feedback signal, combined with the preset air volume control parameter database, to find the optimal air volume control parameters, thereby optimizing the classification effect;

[0097] Performance optimization and update: As more data accumulates, the classifier classification accuracy evaluation model is regularly updated to adapt to changes in material properties, environmental conditions and equipment status, and continuously optimize the prediction ability of the classification accuracy index; the prediction accuracy of the classifier classification accuracy evaluation model is regularly evaluated, and the classifier classification accuracy evaluation model is tuned or retrained when necessary to ensure the effectiveness and accuracy of the classifier classification accuracy evaluation model;

[0098] After the classifying accuracy evaluation model of the powder selector is constructed and verified, the material classification accuracy index of the unpowered powder selector is calculated as follows:

[0099] Prepare samples of materials to be classified: Select representative materials to ensure that the selected materials represent the common material types and particle size distributions in actual production; Prepare standard classification conditions and define a set of standard classification conditions, such as wind speed and feed rate, to facilitate classification under consistent conditions;

[0100] Conduct classification experiment: operate the classifier under selected conditions to classify the prepared material samples; collect the classified materials from each outlet, and the materials are classified into coarse, fine and intermediate grades;

[0101] Determine particle size distribution: Use particle size analysis equipment, such as laser diffractometer and sieving test, to determine the particle size distribution of each part of the material after classification;

[0102] Data collation: record the original data, including the material particle size distribution before classification and the particle size distribution of each part after classification; data standardization, express all data with the same particle size level and unit to facilitate subsequent comparison;

[0103] Calculate the deviation: Compare the target distribution, compare the graded particle size distribution with the expected target particle size distribution, and calculate the deviation; Quantify the deviation, use appropriate methods such as root mean square error RMSE and mean absolute error MAE to quantify the degree of deviation of each particle size level;

[0104] Application accuracy evaluation model: Input the deviation data into the classifier classification accuracy evaluation model. The classifier classification accuracy evaluation model will output an index representing the material classification accuracy based on the input deviation data. The material classification accuracy index is between 0 and 1. The higher the value, the better the classification effect.

[0105] Analysis results: Analyze the obtained material classification accuracy index to judge the classification performance of the powder selector under given conditions; if the material classification accuracy index is lower than expected, it is necessary to identify potential problems in the classification process and consider whether it is necessary to adjust the classification conditions or optimize the powder selector design;

[0106] Adjustment and verification: According to the analysis results, make necessary adjustments to the operating parameters of the powder classifier, such as changing the air volume and adjusting the speed, etc.; conduct classification experiments again to confirm the effect of the adjustments until a satisfactory material classification accuracy index is achieved;

[0107] By collecting material sample data before and after classification, the classification accuracy evaluation model of the powder classifier is constructed based on the material sample data, which reduces the dependence on manual experience and improves the objectivity and accuracy of the classification accuracy evaluation; the classification accuracy evaluation model of the powder classifier calculates the influence of different operating conditions on the classification effect, which is convenient for more refined management of the powder classifier and improves the classification effect; the classification accuracy evaluation model of the powder classifier evaluates the classification effect in real time, quickly identifies the deviation from the ideal state, and adjusts the operating parameters in time to improve the stability and efficiency of the classification process; the training and verification of the classification accuracy evaluation model of the powder classifier facilitates the continuous optimization of the classification accuracy evaluation model of the powder classifier, and through continuous optimization, it is convenient to improve the classification accuracy, adapt to the changes in the production environment, and improve the working efficiency of the powder classifier; by analyzing the changing trend of the classification effect, predicting potential equipment failures or improper operation, taking measures in advance, and reducing the risk of production interruption; in different material types or on different production lines, the classification accuracy evaluation model of the powder classifier can be adapted by adjusting the parameters of the classification accuracy evaluation model of the powder classifier or retraining, which has strong flexibility and adaptability; by accurately controlling the classification process, the waste of resources and errors caused by human operation due to poor classification effect can be reduced, and the quality of the final product and the classification accuracy of the powder classifier can be improved.

[0108] S5. Based on the material classification accuracy index, the optimal air volume control parameter corresponding to the unpowered powder concentrator is mapped in a preset air volume control parameter database;

[0109] Step S5 uses the material classification accuracy index as a feedback signal to select the most appropriate air volume setting from the preset air volume control parameter database to optimize the classification effect of the unpowered powder classifier; the air volume control parameters specifically include:

[0110] Air inlet opening: The opening size of the air inlet determines the air flow entering the powder classifier. By adjusting the opening of the air inlet, the air volume can be indirectly controlled, thereby affecting the material classification;

[0111] Air outlet opening: The air outlet opening also affects the air volume distribution and air pressure. Proper adjustment of the air outlet opening helps to optimize the air flow distribution in the powder classifier and improve the classification effect.

[0112] Angle of air guide blades: The powder classifier is equipped with adjustable air guide blades. Adjustment of the angle will also affect the air volume and direction, thus affecting the classification of the material;

[0113] Wind pressure: Maintaining proper wind pressure inside the powder classifier is the basis for ensuring the classification effect. Too low or too high wind pressure will affect the suspension state of the material, thus affecting the classification accuracy.

[0114] Air volume compensation factor: The difference in temperature and humidity inside and outside the powder classifier silo will affect the actual effect of the air volume. By adjusting the difference in temperature and humidity inside and outside, the purpose of adjusting the air volume can be achieved to maintain the stability of the classification effect;

[0115] First, build the air volume control parameter database, including:

[0116] List all variables that affect the classification effect, including the air inlet opening, air outlet opening, air guide blade angle, wind pressure, and temperature and humidity inside and outside the classifier silo; design an experimental matrix that covers all variables that affect the classification effect to ensure that the experiment covers a wide range of operating conditions;

[0117] Perform the experiment according to the experimental plan, ensuring that only one variable is changed in each experiment while other variables remain unchanged to ensure data comparability; record the detailed parameter settings and results of each experiment, including the material classification accuracy index and other relevant performance indicators;

[0118] Check and clean the data to remove outliers and erroneous data points; convert the data into a unified format, such as converting all air volume data into the same unit; store the organized data in a structured database to ensure data integrity and accessibility;

[0119] Design the database structure, including tables, fields, and data types, to ensure that experimental data can be effectively stored and queried; define the relationship between different tables, such as the relationship between air volume and classification effect; use the database management module to create an air volume control parameter database and import the preprocessed data;

[0120] Use statistical analysis or data mining techniques to analyze data and identify factors that affect the classification effect; based on the data analysis results, establish a prediction model to predict the classification effect under different air volume settings, such as the material classification accuracy index;

[0121] Create indexes for key fields in the air volume control parameter database to improve query speed; optimize query statements to ensure that the optimal air volume control parameters can be quickly retrieved; if there are no directly matching records in the air volume control parameter database, use the pre-trained classification accuracy evaluation model to predict the classification effect under different air volume control parameters and select the resulting air volume control parameters; after selecting the air volume control parameters, verify the effect through small-scale experiments or simulations to ensure that the expected classification accuracy is achieved in actual production;

[0122] Develop an API or interface that allows direct access to the air volume control parameter database and real-time adjustment of the optimal air volume control parameters based on the classification accuracy index;

[0123] Regularly collect new data and update the air volume control parameter database to ensure that it reflects the latest operating conditions and classification effects; continuously monitor the performance of the air volume control parameter database, and regularly optimize and maintain it to ensure stability and efficiency;

[0124] By collecting a large amount of experimental data and building an air volume control parameter database, decisions are made based on actual classification effect data to improve the accuracy and reliability of decisions; the construction and maintenance of the air volume control parameter database allows real-time or regular updates of the optimal air volume control parameters to ensure that the unpowered powder classifier can adapt to changes in material properties and environmental conditions and achieve dynamic optimization; by accurately controlling the air volume, the classification efficiency is improved, energy consumption is reduced, and material waste and reprocessing costs caused by inaccurate classification are reduced; the air volume control parameter database and prediction model are updated regularly to continuously optimize the classification effect, improve product quality and production efficiency, and adapt to changes in production needs; the maintenance of the air volume control parameter database provides a historical record of operating parameters and classification effects, which is convenient for tracing and analyzing the root causes of problems and improving the transparency of the production process; by adjusting the prediction model parameters and the experimental matrix, changes in the production environment can be flexibly responded to; by real-time monitoring of the classification accuracy index and comparing it with the optimal parameters in the database, closed-loop control is achieved to ensure that the classification effect is always in the best state; by building and utilizing the air volume control parameter database, the classification effect of the unpowered powder classifier can be accurately controlled and continuously optimized, production efficiency and product quality can be improved, and operating costs can be reduced.

[0125] S6. Control the air volume of the unpowered powder classifier according to the optimal air volume control parameters;

[0126] Step S6 is the execution stage of the air volume control method of the unpowered powder classifier. According to the determined optimal air volume control parameters, the air volume of the unpowered powder classifier is adjusted to optimize the classification effect. The detailed steps are as follows:

[0127] Ensure communication with the air volume control parameter database and read the optimal air volume control parameters; generate specific air volume adjustment instructions based on the received optimal parameters;

[0128] The air volume of the unpowered powder classifier is adjusted by the actuator to achieve the optimal air volume control parameters; during the production process, the air volume is dynamically adjusted according to the real-time monitored material classification accuracy index to adapt to changes in material characteristics and environmental conditions;

[0129] Deploy a real-time monitoring module to continuously track the classification effect after the air volume is adjusted to ensure that the classification accuracy index reaches or approaches the optimal value; the monitoring module should have an abnormality detection function to identify situations where the classification effect after the air volume is adjusted does not meet expectations and issue an alarm in a timely manner;

[0130] The classification effect will be monitored in real time to ensure the continuous optimization of air volume adjustment; through continuous adjustment and monitoring, it can learn and adapt to different operating conditions and improve the stability of the classification effect;

[0131] Set safety thresholds. When the air volume adjustment exceeds the safety range, the emergency shutdown procedure is triggered to avoid equipment damage or safety accidents. Allow operators to manually intervene in the air volume adjustment to deal with emergencies or special needs.

[0132] Record the time, parameters and results of each air volume adjustment to facilitate later analysis and optimization; generate performance reports regularly to summarize the effectiveness of air volume control methods and provide a basis for improvement

[0133] Check the function of the actuator regularly to ensure it operates normally;

[0134] By reading the optimal air volume control parameters from the database and generating the volume adjustment instructions, the inaccuracy and inefficiency of manual adjustment are reduced; the air volume is adjusted by the actuator, making it fast and accurate, reducing the response time and human error; the dynamic adjustment of the air volume enables the classifier to adapt to the changes in material characteristics and environmental conditions in real time, maintain a stable classification effect, and maintain a high classification accuracy; the deployment of the real-time monitoring module ensures the continuous tracking of the classification effect, which is convenient for immediate discovery of problems and corrective measures, and reduces the product quality degradation caused by classification deviation; the abnormal detection function enhances safety, responds quickly when the classification effect deviates from the target, and reduces potential losses; the closed-loop control mechanism achieves continuous optimization through the feedback loop, ensuring the accuracy of air volume adjustment and the stability of the classification effect; the setting of safety thresholds and emergency shutdown procedures prevents equipment overload or failure, and protects the safety of equipment and operators; the generation of operation logs and performance reports provides detailed analysis data to help technicians understand and optimize control strategies and promote continuous improvement; the air volume control level of the unpowered classifier is improved through intelligent and automated means, and accurate air volume control improves classification accuracy and production efficiency, and also enhances overall production efficiency and reliability.

[0135] Embodiment 2: Figure 3 As shown, the air volume control system of the unpowered powder classifier of the present invention specifically includes the following modules:

[0136] The sample collection module is used to collect various material classification samples during the classification and powder selection process of the unpowered powder classifier;

[0137] The feature extraction module is used to analyze each material classification sample through the preset material classification target feature, calculate and extract the difference between the actual mass proportion of the target particle size material and the target set value, and generate a material classification deviation vector;

[0138] Deviation matrix generation module, used to collect and organize material classification deviation vectors at multiple time points to form a material classification deviation matrix of time series; the columns of the material classification deviation matrix represent the deviation characteristic values ​​at different time points, and the rows represent the deviation characteristic values ​​of different target particle sizes at the same time point;

[0139] The classification accuracy evaluation module is used to receive the deviation matrix as input, and calculate the material classification accuracy index of the unpowered powder classifier by using the pre-built powder classifier classification accuracy evaluation model;

[0140] A parameter mapping module is used to search and map the optimal air volume control parameters that best match the unpowered powder classifier in a preset air volume control parameter database according to the calculated material classification accuracy index;

[0141] The execution module is used to receive the optimal air volume control parameters from the air volume control parameter mapping module, dynamically adjust the air volume of the unpowered powder selection machine, and optimize the effect of graded powder selection.

[0142] Through automatic sample collection, data analysis, accuracy evaluation and parameter adjustment, the automation of air volume control is realized, the uncertainty of human experience adjustment is avoided, and the accuracy and stability of control are improved; the construction of material classification deviation vector and deviation matrix can monitor the classification effect in real time, timely discover the deviation from the target setting, and quickly respond and adjust to ensure the consistency of classification accuracy; the classification accuracy evaluation model is based on data analysis, and by calculating the material classification accuracy index, it ensures that the air volume adjustment is based on objective data rather than subjective judgment, thereby improving the scientificity and reliability of decision-making; by dynamically adjusting the air volume, the expected classification effect can be achieved more effectively, the material classification accuracy can be improved, and the Improve the quality of cement and other products and the overall efficiency of the production line; automated and precise air volume control reduces material rework and loss caused by inaccurate grading, reduces production costs, and saves energy consumption; automatically adjusts air volume control parameters according to different material properties and environmental conditions to improve the adaptability of equipment under variable working conditions and operational flexibility; as more and more data is collected, the grading accuracy evaluation model is continuously optimized through machine learning technology to improve its own prediction and evaluation capabilities and achieve continuous improvement of the system; through automated and real-time control, it reduces the time for human intervention and downtime adjustment, and improves the continuity, stability, product quality and production efficiency of the production line.

[0143] The various variations and specific embodiments of the unpowered powder classifier air volume control method in the aforementioned embodiment 1 are also applicable to the unpowered powder classifier air volume control system of this embodiment. Through the aforementioned detailed description of the unpowered powder classifier air volume control method, those skilled in the art can clearly know the implementation method of the unpowered powder classifier air volume control system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0144] 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.

[0145] 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 the air volume of an unpowered powder classifier, characterized in that: The method comprises: Collect several kinds of material classification samples obtained by classification and powder selection of unpowered powder classifier; Based on the preset material classification target features, target deviation features are extracted for each material classification sample to obtain the material classification deviation vector corresponding to the collection time; Obtain material classification deviation vectors at multiple acquisition times, and arrange them in chronological order to obtain a material classification deviation matrix; Inputting the material classification deviation matrix into a pre-constructed classifier classification accuracy evaluation model to obtain a material classification accuracy index corresponding to the unpowered classifier; Based on the material classification accuracy index, the optimal air volume control parameters corresponding to the unpowered powder classifier are mapped in the preset air volume control parameter database; According to the optimal air volume control parameters, the air volume of the unpowered powder classifier is controlled.

2. The air volume control method of the unpowered powder selector according to claim 1, characterized in that: The material classification deviation vector is composed of several deviation characteristic values, each deviation characteristic value corresponds to a material classification sample, the material classification target characteristics include the target particle size and the target particle size mass proportion corresponding to each material classification sample, and the deviation characteristic value refers to the difference between the mass proportion of the material of the target particle size in the material classification sample and the target particle size mass proportion.

3. The air volume control method of the unpowered powder selector according to claim 1, characterized in that: The deviation characteristic values ​​corresponding to the same target particle size in the material classification deviation matrix and collected at different times are located in the same column, and the deviation characteristic values ​​corresponding to different target particle sizes collected at the same time are located in the same row; The material classification deviation matrix is ​​as follows: Among them, dmn is an element in the material classification deviation matrix, representing the deviation characteristic value of the nth particle size level at the mth collection time; the mth row contains the deviation characteristic values ​​of all particle size levels, corresponding to the mth collection time point; the nth column contains the deviation characteristic values ​​of the nth particle size level at all collection time points.

4. The air volume control method of the unpowered powder selector according to claim 3, characterized in that: Methods for collecting several material classification samples obtained by unpowered powder classifier classification, including: Determine the sampling position of the unpowered powder classifier and conduct sampling; the sampling position includes the graded feed inlets and discharge outlets of the powder classifier at different levels; Determine the sampling frequency and cycle according to production needs and equipment operating conditions; Select sampling tools and equipment for sampling; Select the sampling method based on the location of the sampling point and the nature of the material; the sampling methods include continuous flow sampling, manual assisted sampling and mechanical assisted sampling; After sampling is completed, each collected material classification sample shall be marked and recorded, including sampling time, sampling point and sample number information.

5. The air volume control method of the unpowered powder concentrator according to claim 1, characterized in that: The method for constructing the classifier classification accuracy evaluation model comprises: Collect the information of materials before and after classification of the unpowered powder classifier under different air volume control parameter settings as the training basis of the powder classifier classification accuracy evaluation model; Determine the target particle size range and the particle size distribution curve of the target mass proportion of each particle size segment; Extracting features from the classified material, the material extraction features including the percentage of material in different particle size segments, the recovery ratio of coarse powder and fine powder, and the recovery rate of fine powder minus the proportion of fine powder in coarse powder; Calculate the deviation between the actual particle size distribution and the target particle size distribution; Select machine learning algorithm to build a classifier classification accuracy evaluation model; Use the material classification deviation matrix and the corresponding classification accuracy index in the historical data as the training data set to train the classifier classification accuracy evaluation model; and adjust the parameters of the classifier classification accuracy evaluation model; Independent validation sets and test sets were used to evaluate the generalization ability of the classifier classification accuracy evaluation model.

6. The air volume control method of the unpowered powder classifier according to claim 1, characterized in that: The method for constructing an air volume control parameter database comprises: List the air volume control parameters that affect the classification effect; design an experimental matrix, wherein the experimental matrix includes the air volume control parameters that affect the classification effect; Perform the experiment and change only one air volume control parameter during the experiment, while keeping other air volume control parameters unchanged. Perform multiple experiments according to the number of air volume control parameters, and record the parameter settings and results of each experiment. Check and clean the experimental data, remove outliers and erroneous data points, convert the cleaned experimental data into a unified format, and store the converted experimental data in the database; Design a database to store and query experimental data. The database structure includes tables, fields, and data types. Use the database management module to create an air volume control parameter database and import the preprocessed data.

7. The air volume control method of the unpowered powder selector according to claim 6, characterized in that: The air volume control parameters include the air inlet opening, the air outlet opening, the air guide blade angle, the wind pressure, and the temperature and humidity inside and outside the powder selector silo.

8. An air volume control system for an unpowered powder selector, characterized in that: The system comprises: The sample collection module is used to collect various material classification samples during the classification and powder selection process of the unpowered powder classifier; The feature extraction module is used to analyze each material classification sample through the preset material classification target feature, calculate and extract the difference between the actual mass proportion of the target particle size material and the target set value, and generate the material classification deviation vector; Deviation matrix generation module, used to collect and organize material classification deviation vectors at multiple time points to form a material classification deviation matrix of time series; the columns of the material classification deviation matrix represent the deviation characteristic values ​​at different time points, and the rows represent the deviation characteristic values ​​of different target particle sizes at the same time point; The classification accuracy evaluation module is used to receive the deviation matrix as input, and calculate the material classification accuracy index of the unpowered powder classifier by using the pre-built powder classifier classification accuracy evaluation model; A parameter mapping module is used to search and map the optimal air volume control parameters that best match the unpowered powder classifier in a preset air volume control parameter database according to the calculated material classification accuracy index; The execution module is used to receive the optimal air volume control parameters from the air volume control parameter mapping module, dynamically adjust the air volume of the unpowered powder selection machine, and optimize the effect of graded powder selection.

9. An electronic device for controlling the air volume of an unpowered powder selector, 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