Method and system for monitoring air volume fluctuation of unpowered powder concentrator

Abstract

The present application relates to the technical field of powder concentrator monitoring, in particular to a kind of unpowered powder concentrator air volume fluctuation monitoring method and system, it is by comprehensively considering environmental factors, quantifying environmental fluctuation influence, intelligent air volume fluctuation evaluation, external cause influence correction and real-time and automation etc., improve the accuracy and reliability of air volume monitoring and the classification effect and overall production efficiency of unpowered powder concentrator;Method includes: obtaining the environmental parameter fluctuation vector corresponding to the set time window;The environmental parameter fluctuation vector is input into the pre-constructed environmental fluctuation influence analysis model, and the environmental fluctuation influence factor is obtained;The environmental fluctuation influence factor is used to characterize the influence degree of environmental parameter change on the air volume fluctuation of powder concentrator;Obtain the air volume characteristic matrix of powder concentrator in preset time window;The air volume characteristic matrix of powder concentrator includes the multi-dimensional operating parameter of powder concentrator collected at different time nodes.

Description

Technical Field

[0001] This invention relates to the technical field of air classifier monitoring, and in particular to a method and system for monitoring airflow fluctuations in a non-powered air classifier. Background Technology

[0002] As an important material classification device, the non-powered air classifier is widely used in industrial production for the classification of various materials such as ores, coal, and chemical raw materials. During the operation of the non-powered air classifier, the stability of the air volume is directly related to the classification effect and the product quality. However, there are many uncontrollable factors in the actual production environment, such as changes in ambient humidity, temperature, atmospheric pressure, and wind speed. These factors will affect the air volume inside the air classifier, and thus affect the classification effect.

[0003] Existing airflow monitoring methods often only focus on the air classifier's own operating parameters, such as airflow at the air outlet and vibration, while ignoring the impact of external environmental factors on airflow fluctuations. Existing methods may be effective when environmental parameters are relatively stable, but when environmental parameters fluctuate significantly, the accuracy and reliability of the monitoring results will be greatly reduced. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method and system for monitoring airflow fluctuations in a non-powered air classifier. This system improves the accuracy and reliability of airflow monitoring, as well as the grading effect and overall production efficiency of the non-powered air classifier by comprehensively considering environmental factors, quantifying the impact of environmental fluctuations, intelligently evaluating airflow fluctuations, correcting for external factors, and featuring real-time performance and automation.

[0005] In a first aspect, the present invention provides a method for monitoring airflow fluctuations in a non-powered air classifier, the method comprising:

[0006] Obtain the environmental parameter fluctuation vector corresponding to the set time window;

[0007] The environmental parameter fluctuation vector is input into a pre-constructed environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factor; the environmental fluctuation impact factor is used to characterize the degree of influence of environmental parameter changes on the air volume fluctuation of the classifier.

[0008] Obtain the air volume characteristic matrix of the air classifier within a preset time window; the air volume characteristic matrix of the air classifier includes multi-dimensional operating parameters of the air classifier collected at different time nodes;

[0009] The air volume characteristic matrix of the air classifier is input into the pre-constructed air volume fluctuation evaluation model to obtain the air volume fluctuation index of the air classifier; the air volume fluctuation index of the air classifier is used to characterize the air volume stability of the air classifier within a set time window;

[0010] Based on the environmental fluctuation influencing factors, the air volume fluctuation index of the air classifier is corrected to remove the external factors, and the air volume fluctuation index of the air classifier itself is obtained.

[0011] The airflow fluctuation index of the air classifier itself is compared with the preset airflow fluctuation threshold, and the airflow fluctuation of the air classifier is judged to be normal based on the comparison results.

[0012] Furthermore, the environmental parameter fluctuation vector includes the difference in environmental humidity, environmental temperature, atmospheric pressure, and environmental wind speed between the start and end times of the set time window.

[0013] Furthermore, the method for obtaining the environmental fluctuation influencing factors includes:

[0014] Collect historical data on environmental parameter fluctuation vector V and corresponding airflow fluctuation data of the classifier;

[0015] The collected historical data is processed for missing values, outlier detection, and data standardization.

[0016] Choose linear regression, machine learning algorithms, random forests, or neural networks to build models for analyzing the impact of environmental fluctuations;

[0017] The preprocessed dataset is divided into a training set and a validation set. The training set data is used to train the environmental fluctuation impact analysis model, and the validation set data is used to evaluate the performance of the environmental fluctuation impact analysis model.

[0018] The mean squared error or coefficient of determination is used to measure the fit of the environmental fluctuation impact analysis model.

[0019] Adjust the hyperparameters of the environmental fluctuation impact analysis model based on the performance on the validation set;

[0020] The environmental parameter fluctuation vector V is input into the trained environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factor α.

[0021] Furthermore, when there is a linear relationship between environmental parameters and the airflow fluctuation of the air classifier, the mathematical formula for the environmental fluctuation influence factor α is:

[0022] α=ω1f+ω2g+ω3h;

[0023] Wherein, the coefficients in α represent the weight coefficients of the influence results of the first-order environmental parameters, the second-order environmental parameters, and the environmental parameter interaction terms, respectively.

[0024] f represents the influence of the first-order environmental parameter, and the calculation method is as follows:

[0025]

[0026] Where ΔH, ΔT, ΔP, and ΔW represent the differences in ambient humidity, ambient temperature, atmospheric pressure, and ambient wind speed, respectively, and the coefficients in f represent the first-order effect coefficients of the differences in ambient humidity, ambient temperature, atmospheric pressure, and ambient wind speed on the factors affecting environmental fluctuations.

[0027] g represents the influence of second-order environmental parameters, which are calculated as follows:

[0028]

[0029] The coefficients in g represent the second-order effect coefficients of the environmental humidity difference, environmental temperature difference, atmospheric pressure difference, and environmental wind speed difference on the environmental fluctuation factors, respectively.

[0030] h represents the impact of the interaction terms of environmental parameters on the result, and is calculated as follows:

[0031]

[0032] The coefficients in h represent the interaction coefficients between any two environmental parameters.

[0033] Furthermore, the method for obtaining the airflow characteristic matrix of the classifier within a preset time window includes:

[0034] The set time window is divided into equal time intervals to obtain multiple time nodes for collecting the air classifier's operating parameters;

[0035] Based on the obtained time points, the multi-dimensional operating parameters of the air classifier are collected sequentially. The multi-dimensional operating parameters of the air classifier include the air volume at the outlet, the air volume at the inlet, the feeding speed, and the material moisture content.

[0036] The time-series parameters of the air classifier at multiple time points are aligned to obtain the air volume characteristic matrix of the air classifier.

[0037] Furthermore, the air volume characteristic matrix of the air classifier is as follows:

[0038]

[0039] The time window is divided into n time periods, and the parameters collected in each time period include the air volume Q at the air outlet. o and air inlet air volume Q i , feed rate v and material moisture content H.

[0040] Furthermore, the method for obtaining the airflow fluctuation evaluation model includes:

[0041] Collect historical data on the air volume characteristic matrix of the air classifier and the corresponding air volume fluctuations;

[0042] The collected historical data undergoes missing value processing, outlier detection and removal, and data standardization and normalization.

[0043] Based on the degree of airflow fluctuation in the quantified air classifier, a regression analysis model, such as linear regression, ridge regression, or LASSO regression, is selected according to the actual situation to construct an airflow fluctuation evaluation model.

[0044] The preprocessed dataset is divided into a training set and a validation set. The air volume fluctuation evaluation model is trained using the training set data. The hyperparameters of the air volume fluctuation evaluation model are adjusted based on the performance on the validation set to optimize the performance of the air volume fluctuation evaluation model.

[0045] The obtained air volume feature matrix of the air classifier is input into the trained air volume fluctuation evaluation model to obtain the air volume fluctuation index of the air classifier.

[0046] If the airflow fluctuation evaluation model uses a linear regression model, the airflow fluctuation index IVF is as follows:

[0047] IVF=γ0+γ1Qo+γ2Qi+γ3v+γ4H;

[0048] Where γ0 represents the intercept term, and γ1, γ2, γ3, and γ4 represent the weighting coefficients of the outlet air volume, inlet air volume, feed rate, and material moisture content, respectively. These weighting coefficients are determined during the training of the air volume fluctuation evaluation model. o Q i v and H represent the air volume at the outlet, the air volume at the inlet, the feeding speed, and the material humidity, respectively.

[0049] On the other hand, this application also provides a system for monitoring airflow fluctuations in a non-powered air classifier, the system comprising:

[0050] The environmental parameter monitoring module is used to monitor and record environmental parameters in real time, including ambient humidity, ambient temperature, atmospheric pressure, and ambient wind speed.

[0051] The environmental parameter fluctuation calculation module is used to obtain data from the environmental parameter monitoring module and calculate the fluctuation vector of environmental parameters within a set time window;

[0052] The environmental fluctuation impact analysis model is used to receive data input from the environmental parameter fluctuation calculation module, analyze and calculate the environmental fluctuation impact factor through a pre-trained model, and the environmental fluctuation impact factor is used to assess the specific impact of environmental changes on the air volume fluctuation of the air classifier.

[0053] The air classifier operation parameter monitoring module is used to monitor and collect multi-dimensional operation parameters of the air classifier within a set time window, forming an air volume characteristic matrix of the air classifier;

[0054] The air volume fluctuation evaluation model is used to receive the air volume feature matrix of the air classifier as input, and calculate the air volume fluctuation index of the air classifier through the pre-trained model to reflect the air volume stability of the air classifier within a specific time window.

[0055] The external influence correction module is used to correct the air volume fluctuation index based on environmental fluctuation influence factors, in order to remove the influence of environmental factors and obtain a more accurate air volume fluctuation index of the classifier itself.

[0056] The airflow fluctuation status judgment module is used to compare the corrected airflow fluctuation index of the air classifier with the preset airflow fluctuation threshold to determine whether the airflow fluctuation status of the air classifier is normal.

[0057] Thirdly, this 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. 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 of the methods described above.

[0058] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0059] Compared with existing technologies, the beneficial effects of this invention are as follows: By considering the operating parameters of the air classifier itself and introducing an environmental parameter fluctuation vector, the impact of environmental conditions on the airflow fluctuation of the air classifier can be comprehensively assessed; by using an environmental fluctuation impact analysis model to quantify the degree of influence of environmental parameter changes on the airflow fluctuation of the air classifier, it is easier to accurately identify which environmental factors have a significant impact on the airflow fluctuation, thereby enabling targeted measures to be taken; by applying the environmental fluctuation impact factor to the calculation of the airflow fluctuation index, the actual fluctuation of the airflow of the air classifier can be accurately assessed, improving the accuracy of monitoring results; when there are large fluctuations in environmental parameters, the impact of environmental factors on the airflow fluctuation monitoring results can be reduced through the correction of the environmental fluctuation impact factor, improving adaptability in complex environments; and by removing external factors... The method corrects and obtains an airflow fluctuation index that more closely approximates the actual working state of the air classifier, improving the reliability and stability of monitoring results. By comparing the airflow fluctuation index of the air classifier itself with the preset airflow fluctuation threshold, it accurately determines whether the airflow fluctuation of the air classifier is within the normal range, providing decision support for operators and ensuring grading effect and product quality. Through precise monitoring and evaluation of airflow fluctuations, the working parameters of the air classifier can be better adjusted, the production process can be optimized, and the grading effect and production efficiency can be improved. The airflow fluctuation monitoring method for powered air classifiers improves the accuracy and reliability of airflow monitoring and the grading effect and overall production efficiency of unpowered air classifiers by comprehensively considering environmental factors, quantifying the impact of environmental fluctuations, intelligently evaluating airflow fluctuations, correcting for external factors, and featuring real-time and automation characteristics. Attached Figure Description

[0060] Figure 1 This is a flowchart of the present invention;

[0061] Figure 2 This is a flowchart of the method for obtaining the air volume fluctuation evaluation model;

[0062] Figure 3 This is a structural diagram of the airflow fluctuation monitoring system for a non-powered air classifier. Detailed Implementation

[0063] As will be apparent to those skilled in the art from the description of this application, this application can be implemented as a method, apparatus, electronic device, and computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software. Furthermore, in some embodiments, this application can also be implemented as a computer program product contained in one or more computer-readable storage media, which includes computer program code.

[0064] The aforementioned computer-readable storage medium may be any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, flash memory, optical fiber, optical disc read-only memory, optical storage devices, magnetic storage devices, or any combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0065] The acquisition, storage, use, and processing of data in this application all comply with relevant national laws and regulations.

[0066] This application describes the provided methods, apparatus, and electronic devices using flowcharts and / or block diagrams.

[0067] It should be understood that each block of a flowchart and / or block diagram, as well as combinations of blocks in a 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 apparatus to produce a machine that, when executed by a computer or other programmable data processing apparatus, creates means for implementing the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0068] 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 function in a particular manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction apparatus product that includes the functions / operations specified in the blocks of a flowchart and / or block diagram.

[0069] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable data processing apparatus provide a process for implementing the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0070] This application will now be described with reference to the accompanying drawings.

[0071] Example 1: As Figures 1 to 2 As shown, the method for monitoring airflow fluctuations in a non-powered air classifier according to the present invention specifically includes the following steps:

[0072] S1. Obtain the environmental parameter fluctuation vector corresponding to the set time window; the environmental parameter fluctuation vector includes the difference in environmental humidity, the difference in environmental temperature, the difference in atmospheric pressure, and the difference in environmental wind speed between the start time points of the set time window;

[0073] Step S1 involves obtaining the environmental parameter fluctuation vector corresponding to the set time window, which directly affects the accuracy and reliability of subsequent environmental fluctuation impact analysis; the details are as follows:

[0074] First, determine the detection cycle and clearly set the time window. The time window is the basis for analyzing the fluctuation of environmental parameters. At the same time, the length of the time window should be determined according to environmental changes and monitoring needs, such as 1 hour, 1 day, or 1 week. It should be able to capture significant changes in environmental parameters, but should also avoid being too long, which would lead to data redundancy or increased processing complexity.

[0075] Use appropriate sensors to monitor environmental parameters, including: ambient humidity (using a humidity sensor to monitor the moisture content in the air); ambient temperature (using a temperature sensor to monitor the ambient temperature); atmospheric pressure (using a barometer to monitor atmospheric pressure); and ambient wind speed (using an anemometer to monitor wind speed).

[0076] Within the set time window, record the changes of the above environmental parameters over time;

[0077] Calculate the changes in environmental parameters between the start and end times of the set time window, including: ambient humidity difference, which represents the difference between the current humidity and the humidity at the start time; ambient temperature difference, which represents the difference between the current temperature and the temperature at the start time; atmospheric pressure difference, which represents the difference between the current atmospheric pressure and the atmospheric pressure at the start time; and ambient wind speed difference, which represents the difference between the current wind speed and the wind speed at the start time.

[0078] The changes in environmental parameters are organized into a vector form, which is called the environmental parameter fluctuation vector; the environmental parameter fluctuation vector is as follows:

[0079]

[0080] Where V represents the environmental parameter fluctuation vector, H c T c P c W c H represents the ambient humidity, ambient temperature, atmospheric pressure, and ambient wind speed at the end of the time window. s T s P s W s These represent the initial values ​​of these parameters at the start of the time window.

[0081] By continuously monitoring changes in environmental parameters within a set time window and calculating the magnitude of these changes, the system accurately assesses the impact of environmental changes on the airflow fluctuations of the air classifier. It simultaneously monitors multiple parameters, including humidity, temperature, atmospheric pressure, and wind speed, comprehensively capturing changes in environmental conditions. The system flexibly adjusts the set time window based on actual conditions, shortening it when environmental changes are rapid to capture more subtle changes, and extending it when the environment is relatively stable to reduce data processing complexity. The time window selection is determined based on monitoring needs and the frequency of environmental changes, enabling adaptation to different industrial scenarios. By calculating the magnitude of environmental parameter changes rather than their absolute values, it reduces interference from inherent environmental fluctuations, improving the reliability of monitoring results. It utilizes standard humidity sensors, temperature sensors, and air... Monitoring is performed using pressure gauges and anemometers, which are readily available on the market and easily integrated into the monitoring system. Continuous data recording within a defined time window ensures the representativeness of the acquired data and better reflects changing environmental conditions. Organizing environmental parameter changes into vector form facilitates subsequent processing in environmental fluctuation impact analysis models, simplifying the data processing workflow. Pre-setting time windows enables automated data acquisition, reducing manual intervention and improving monitoring efficiency. Even under conditions of significant environmental parameter fluctuations, these changes can be effectively captured, enhancing adaptability. The method of acquiring environmental parameter fluctuation vectors within a defined time window improves the accuracy, comprehensiveness, and flexibility of airflow fluctuation monitoring, facilitating subsequent environmental fluctuation impact analysis and enhancing the overall performance of the monitoring system.

[0082] S2. Input the environmental parameter fluctuation vector into the pre-constructed environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factor; the environmental fluctuation impact factor is used to characterize the degree of influence of environmental parameter changes on the air volume fluctuation of the classifier.

[0083] Step S2, which involves inputting the environmental parameter fluctuation vector into a pre-built environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factors, is one of the steps in the entire method for monitoring the airflow fluctuation of a non-powered air classifier; the details are as follows:

[0084] First, an environmental fluctuation impact analysis model is constructed, including:

[0085] Collect historical data, including the environmental parameter fluctuation vector V and the corresponding airflow fluctuation data of the classifier;

[0086] The collected historical data is preprocessed, including missing value handling, outlier detection and removal, and data standardization, to ensure data quality;

[0087] Choose an appropriate model type to quantify the impact of environmental parameter changes on air volume fluctuations, including linear regression, machine learning algorithms, random forests, or neural networks;

[0088] The preprocessed dataset is divided into a training set and a validation set. The training set data is used to train the environmental fluctuation impact analysis model and find the parameters of the environmental fluctuation impact analysis model that describe the relationship between changes in environmental parameters and fluctuations in the air volume of the classifier.

[0089] Use validation set data to evaluate the performance of the environmental fluctuation impact analysis model, and use mean squared error or coefficient of determination to measure the goodness of fit of the environmental fluctuation impact analysis model; if the performance of the environmental fluctuation impact analysis model is not good, adjust the parameters of the environmental fluctuation impact analysis model or try other types of environmental fluctuation impact analysis models;

[0090] Adjust the hyperparameters of the environmental fluctuation impact analysis model, such as regularization parameters and the number of trees, based on the performance on the validation set to optimize the performance of the environmental fluctuation impact analysis model;

[0091] The environmental parameter fluctuation vector V is input into the trained environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factor α, which reflects the degree of impact of environmental parameter changes on the air volume fluctuation of the classifier.

[0092] When there is a linear relationship between environmental parameters and the airflow fluctuation of the air classifier, the environmental fluctuation influence factor α is as follows:

[0093] α=ω1f+ω2g+ω3h;

[0094] Wherein, the coefficients in α represent the weight coefficients of the influence results of the first-order environmental parameters, the second-order environmental parameters, and the environmental parameter interaction terms, respectively.

[0095] f represents the influence of the first-order environmental parameter, and the calculation method is as follows:

[0096]

[0097] Where ΔH, ΔT, ΔP, and ΔW represent the differences in environmental humidity, temperature, atmospheric pressure, and wind speed, respectively, and the coefficients in f represent the first-order effect coefficients of the differences in environmental humidity, temperature, atmospheric pressure, and wind speed on the environmental fluctuation factors; reflecting the degree of influence of each environmental parameter changing individually on the environmental fluctuation factors.

[0098] g represents the influence of second-order environmental parameters, which are calculated as follows:

[0099]

[0100] The coefficients in g represent the second-order effect coefficients of environmental humidity difference, environmental temperature difference, atmospheric pressure difference, and environmental wind speed difference on environmental fluctuation factors, respectively; they reflect the degree of nonlinear influence of individual changes of each environmental parameter on environmental fluctuation factors.

[0101] h represents the impact of the interaction terms of environmental parameters on the result, and is calculated as follows:

[0102]

[0103] The coefficients in h represent the interaction coefficients between any two environmental parameters, reflecting the interaction effect on environmental fluctuation factors when two environmental parameters change simultaneously.

[0104] By preprocessing the collected historical data, including missing value handling, outlier detection and removal, and data standardization, data quality was ensured, improving the predictive accuracy of the environmental fluctuation impact analysis model. Appropriate model types were selected to quantify the impact of environmental parameter changes on airflow fluctuations, including linear regression and machine learning algorithms (random forests or neural networks, etc., chosen flexibly according to actual conditions). Validation set data was used to evaluate the performance of the environmental fluctuation impact analysis model, using metrics such as mean squared error or coefficient of determination to measure the model's fit and ensure its reliability and generalization ability. Hyperparameters of the environmental fluctuation impact analysis model, such as regularization parameters and the number of trees, were adjusted based on the validation set performance to optimize its performance. The environmental fluctuation impact analysis model considers not only the classifier's own operating parameters but also multiple environmental parameters such as humidity, temperature, atmospheric pressure, and wind speed, facilitating a comprehensive assessment of the impact of environmental changes on airflow fluctuations. Even under conditions of large environmental parameter fluctuations, the environmental fluctuation impact analysis model can capture these fluctuations through training data, enhancing its adaptability. When using a linear regression model, the parameters of the environmental fluctuation impact analysis model directly reflect the various environmental parameters. This study assesses the degree of impact of environmental parameters on airflow fluctuations, increasing the interpretability of the environmental fluctuation impact analysis model. Regular updates to the model reflect the latest environmental conditions and air classifier operating characteristics maintain its effectiveness. Accurate assessment of the impact of environmental parameter changes on airflow fluctuations provides effective decision support for operators, enabling better adjustment of air classifier operating parameters. The formula for obtaining environmental fluctuation impact factors provides a method for quantifying the impact of environmental parameter changes on airflow fluctuations, making the results comparable. The formula is concise and easy to understand and interpret, helping technicians and managers quickly grasp key information. Adjusting the parameters of the environmental fluctuation impact analysis model optimizes its performance, making it more suitable for practical applications. The formula facilitates automation of the monitoring system, reducing manual intervention and improving efficiency. The formula is adjusted according to the needs of different scenarios to adapt to different data characteristics and application scenarios. Constructing an environmental fluctuation impact analysis model and obtaining environmental fluctuation impact factors improves the accuracy, comprehensiveness, and reliability of airflow fluctuation monitoring, while also facilitating subsequent airflow fluctuation index correction and enhancing monitoring performance.

[0105] S3. Obtain the air volume characteristic matrix of the air classifier within a preset time window; the air volume characteristic matrix of the air classifier includes multi-dimensional operating parameters of the air classifier collected at different time nodes;

[0106] Step S3, obtaining the airflow characteristic matrix of the air classifier within a preset time window, is one of the steps in the airflow fluctuation monitoring process of the non-powered air classifier. The airflow characteristic matrix allows for a comprehensive and accurate capture of the air classifier's operating status within a specific time period, facilitating subsequent analysis of the internal causes and external influences of airflow fluctuations. Specifically:

[0107] First, determine the preset time window. The time window should be long enough to include enough data for analysis, but short enough to reflect the airflow fluctuation of the non-powered air classifier in a short period of time. According to the monitoring requirements and data acquisition frequency, the set time window is divided into multiple time periods at equal intervals. The equal interval division of the time window helps to ensure the uniformity and consistency of data acquisition. The length of each time period depends on the required monitoring accuracy and data availability. By dividing the time window at equal intervals, it is ensured that the operating parameters of the non-powered air classifier can be collected at each time point, thereby constructing a continuous and uniform airflow characteristic matrix.

[0108] Based on defined time points, multi-dimensional operating parameters of the non-powered air classifier are collected sequentially. These multi-dimensional operating parameters comprehensively reflect the operating status and airflow of the non-powered air classifier. In the field of non-powered air classifier monitoring, common multi-dimensional operating parameters include: outlet airflow, measured using an airflow meter; inlet airflow, measured using an airflow meter; feed velocity, measured using a flow meter; and material moisture content, measured using a moisture sensor.

[0109] The multi-dimensional operating parameters collected at each time point are arranged in chronological order to form the air volume feature matrix of the air classifier. The purpose of aligning the time sequence parameters is to adjust the multi-dimensional operating parameters collected at different time points to a unified time reference. Through the alignment of the time sequence parameters, a complete and temporally continuous air volume feature matrix of the air classifier is obtained. The air volume feature matrix of the air classifier contains the multi-dimensional operating parameter information of the air classifier at all time points within the preset time window.

[0110] The air volume characteristic matrix of the air classifier is as follows:

[0111]

[0112] The time window is divided into n time periods, and the parameters collected in each time period include the air volume Q at the air outlet. o and air inlet air volume Q i , feed rate v and material moisture content H.

[0113] By collecting multi-dimensional operating parameters, including outlet airflow, inlet airflow, feed rate, and material moisture, the system comprehensively reflects the airflow status and performance of the air classifier. By dividing the time window into equal intervals and aligning time-sequence parameters, the system ensures the uniformity and consistency of data collection, improving the accuracy of the airflow characteristic matrix. The length of the time window is flexibly adjusted according to monitoring needs and data collection frequency, capturing both short-term airflow fluctuations and sufficiently long periods to reflect long-term trends. The data collection interval is adjusted according to actual needs to balance data resolution and processing complexity. Arranging the multi-dimensional operating parameters into a matrix according to time sequence facilitates subsequent processing and analysis by the airflow fluctuation evaluation model. Ensuring the completeness of data collection... Integrity and accuracy are improved, enhancing the reliability of the airflow characteristic matrix and the accuracy of subsequent analysis; by constructing a continuous and uniform airflow characteristic matrix, the false alarm rate caused by discontinuous or inconsistent data is reduced; by more accurately capturing the operating status of the air classifier within a specific time period, more effective decision support is provided to operators, facilitating the adjustment of the air classifier's operating parameters; by regularly checking and calibrating sensors, the accuracy of data acquisition is ensured, and the monitoring system is upgraded according to actual needs; a precise airflow characteristic matrix helps adjust process parameters, improving production efficiency while ensuring product quality consistency; by obtaining the airflow characteristic matrix of the air classifier within a preset time window, the comprehensiveness and accuracy of airflow fluctuation monitoring can be improved, while also facilitating subsequent calculation of the airflow fluctuation index and improving monitoring performance.

[0114] S4. Input the air volume characteristic matrix of the air classifier into the pre-constructed air volume fluctuation evaluation model to obtain the air volume fluctuation index of the air classifier; the air volume fluctuation index of the air classifier is used to characterize the air volume stability of the air classifier within a set time window.

[0115] In step S4, the airflow characteristic matrix of the air classifier is input into the pre-constructed airflow fluctuation evaluation model to obtain the airflow fluctuation index of the air classifier; specifically as follows:

[0116] First, a wind volume fluctuation evaluation model is constructed, including:

[0117] Historical data was collected, including the air volume characteristic matrix of the air classifier and the corresponding air volume fluctuations. The above data covers a variety of different operating conditions so that the air volume fluctuation evaluation model can adapt to a wide range of operating scenarios.

[0118] The collected historical data is preprocessed, including missing value handling, outlier detection and removal, data standardization and normalization, to ensure data quality;

[0119] The goal of the airflow fluctuation evaluation model is to quantify the degree of airflow fluctuation in the air classifier. A regression analysis model, such as linear regression, ridge regression, or LASSO regression, is selected.

[0120] The preprocessed dataset is divided into a training set and a validation set. The training set data is used to train the wind volume fluctuation evaluation model. After training, the validation set data is used to evaluate the performance of the wind volume fluctuation evaluation model.

[0121] Adjust the hyperparameters of the airflow fluctuation evaluation model based on the performance on the validation set to optimize the performance of the airflow fluctuation evaluation model;

[0122] The obtained air volume feature matrix of the air classifier is input into the trained air volume fluctuation evaluation model to obtain the air volume fluctuation index of the air classifier. The air volume fluctuation index of the air classifier reflects the air volume stability of the air classifier within a set time window.

[0123] If the air volume fluctuation evaluation model uses a linear regression model, the air volume fluctuation index is as follows:

[0124] IVF=γ0+γ1Qo+γ2Qi+γ3v+γ4H;

[0125] Where IVF represents the airflow fluctuation index of the air classifier, γ0 represents the intercept term, and γ1, γ2, γ3, and γ4 represent the weighting coefficients of the outlet airflow, inlet airflow, feed velocity, and material moisture content, respectively. These weighting coefficients are determined during the training of the airflow fluctuation evaluation model. o Q i v and H represent the air volume at the outlet, the air volume at the inlet, the feeding speed, and the material humidity, respectively.

[0126] By training an airflow fluctuation evaluation model, the degree of airflow fluctuation in the air classifier is accurately quantified, improving the accuracy of airflow fluctuation monitoring. The model considers the air classifier's own operating parameters, as well as several key parameters, including outlet airflow, inlet airflow, feed rate, and material moisture content, facilitating a comprehensive assessment of the airflow stability. The training data for the airflow fluctuation evaluation model covers various operating conditions, enabling it to adapt to a wide range of operating scenarios. Different model types, such as linear regression, ridge regression, or LASSO regression, can be selected based on actual needs to adapt to different data characteristics and application scenarios. The performance of the airflow fluctuation evaluation model is evaluated using validation set data to ensure its reliability and generalization ability. When using a linear regression model, the airflow fluctuation evaluation model parameters directly reflect various... The degree to which parameters affect airflow fluctuations increases the interpretability of the airflow fluctuation evaluation model; the parameters of the airflow fluctuation evaluation model are adjusted based on the performance on the validation set to optimize the performance of the airflow fluctuation evaluation model, and fine-tuned according to actual application conditions; regularly updating the airflow fluctuation evaluation model to reflect the latest operating characteristics helps maintain the effectiveness of the airflow fluctuation evaluation model; by more accurately assessing the degree of airflow fluctuation in the air classifier, the false alarm rate caused by errors in the airflow fluctuation evaluation model is reduced; by more accurately assessing the airflow stability of the air classifier within a set time window, effective decision support is provided for operators to better adjust the operating parameters of the air classifier; by constructing an airflow fluctuation evaluation model and obtaining the airflow fluctuation index of the air classifier, the accuracy, comprehensiveness and reliability of airflow fluctuation monitoring can be improved, and subsequent airflow fluctuation index correction can be facilitated, thereby improving monitoring performance.

[0127] S5. Based on the environmental fluctuation impact factor, the air volume fluctuation index of the air classifier is corrected to remove the external factors and obtain the air volume fluctuation index of the air classifier itself.

[0128] In step S5, the airflow fluctuation index of the air classifier is corrected for external factors based on environmental fluctuation influencing factors to ensure that the evaluation results can truly reflect the airflow stability of the air classifier itself; the details are as follows:

[0129] Based on step S2, the environmental fluctuation impact factor α is obtained by inputting the environmental parameter fluctuation vector into the pre-built environmental fluctuation impact analysis model. The environmental fluctuation impact factor reflects the degree of influence of environmental parameter changes on the air volume fluctuation of the classifier.

[0130] Based on the air volume fluctuation index (IVF) of the air volume classifier obtained by inputting the air volume characteristic matrix of the air volume classifier into the air volume fluctuation evaluation model in step S4, the air volume fluctuation index of the air volume classifier is used to characterize the air volume stability of the air volume classifier within a set time window.

[0131] The airflow fluctuation index (IVF) of the air classifier is corrected based on the environmental fluctuation impact factor α to remove the influence of external environmental factors; the correction formula is as follows:

[0132] IVF c =IVF-α;

[0133] IVF c The corrected airflow fluctuation index of the air classifier is represented by IVF, which represents the airflow fluctuation index of the air classifier, and α represents the environmental fluctuation influence factor.

[0134] After correction, the airflow fluctuation index of the air classifier itself is obtained, which accurately reflects the stability of the airflow of the air classifier. The airflow fluctuation index of the air classifier itself is used as the basis for subsequent judgment on whether the airflow fluctuation of the air classifier is normal.

[0135] By correcting the airflow fluctuation index (IVF) of the air classifier based on the environmental fluctuation influence factor α, the airflow fluctuation of the air classifier is accurately reflected, improving the accuracy of airflow fluctuation monitoring. The correction process removes the influence of external environmental factors on the airflow fluctuation index, ensuring that the evaluation results truly reflect the airflow stability of the air classifier. By removing external factors, the uncertainty of monitoring results caused by changes in environmental factors is reduced, improving the reliability of the monitoring results. By accurately reflecting the airflow stability of the air classifier, more effective decision support is provided for operators, allowing for better adjustment of the air classifier's operating parameters. The correction formula is simple, intuitive, and easy to understand. The method can be implemented without requiring a complex mathematical background; by reducing the impact of external environmental factors on airflow fluctuation monitoring results, it improves monitoring efficiency and more quickly identifies the airflow fluctuations of the air classifier itself; by accurately reflecting the airflow stability of the air classifier itself, it reduces the false alarm rate caused by external environmental factors; precise airflow fluctuation monitoring can help adjust process parameters, improve production efficiency, and ensure product quality consistency; by correcting the airflow fluctuation index of the air classifier based on environmental fluctuation influencing factors, it improves the accuracy, reliability, and applicability of airflow fluctuation monitoring, and also facilitates subsequent airflow fluctuation status judgment, thereby improving monitoring efficiency.

[0136] S6. Compare the air volume fluctuation index of the air classifier itself with the preset air volume fluctuation threshold, and determine whether the air volume fluctuation of the air classifier is normal based on the comparison result.

[0137] Step S6 assesses the airflow fluctuation index of the air classifier itself and determines whether it is normal; the details are as follows:

[0138] S61. Based on the design requirements and operating experience of the air classifier, set a reasonable airflow fluctuation threshold, the threshold being IVF. tThe threshold is based on the airflow fluctuation range during normal operation of the air classifier, ensuring that the airflow fluctuation can be correctly judged as normal in most cases.

[0139] S62. The corrected airflow fluctuation index (IVF) of the classifier obtained in step S5. c Preset airflow fluctuation threshold IVF t Compare;

[0140] S63, When IVF c <IVF t At that time, it was considered that the air volume fluctuation of the air classifier was within the normal range; when IVF c ≥IVF t If this occurs, it is considered that the air volume fluctuation of the air classifier exceeds the normal range, indicating an abnormal situation.

[0141] S64. When the air volume fluctuates beyond the normal range, it is necessary to further analyze the cause and take necessary adjustment measures to restore the normal operation of the air classifier.

[0142] S65. As time goes by and experience accumulates, the preset air volume fluctuation threshold needs to be adjusted and optimized according to the actual operating conditions.

[0143] By analyzing the corrected airflow fluctuation index (IVF) of the air classifier. c Compared with the preset airflow fluctuation threshold IVF t By comparing and accurately determining whether the airflow fluctuation of the air classifier is normal; by monitoring the airflow fluctuation of the air classifier in real time, abnormalities can be detected and handled in a timely manner, thereby improving production efficiency and product quality; and a preset airflow fluctuation threshold (IVF) is used. t Based on the design requirements and operational experience of the air classifier, this system accurately determines whether airflow fluctuations are normal, improving the reliability of monitoring results. Accurate judgment of airflow fluctuations provides operators with more effective decision support, enabling better adjustment of the air classifier's operating parameters. Precise airflow fluctuation monitoring helps adjust process parameters, improving production efficiency while ensuring product quality consistency. A method based on the airflow fluctuation index of the air classifier itself reduces false alarms caused by environmental factors. With time and experience accumulation, the preset airflow fluctuation threshold can be adjusted and optimized according to actual operating conditions to adapt to different production environments and needs. Timely detection and handling of abnormal situations reduces unplanned downtime, improving equipment availability and production efficiency. Comparing the airflow fluctuation index of the air classifier itself with the preset airflow fluctuation threshold improves the accuracy, reliability, and applicability of airflow fluctuation monitoring, while also facilitating timely detection and handling of abnormal situations, thus enhancing monitoring performance.

[0144] Example 2: Figure 3As shown, the airflow fluctuation monitoring system for the non-powered air classifier of the present invention specifically includes the following modules;

[0145] The environmental parameter monitoring module is used to monitor and record environmental parameters in real time, including ambient humidity, ambient temperature, atmospheric pressure, and ambient wind speed.

[0146] The environmental parameter fluctuation calculation module is used to obtain data from the environmental parameter monitoring module and calculate the fluctuation vector of environmental parameters within a set time window;

[0147] The environmental fluctuation impact analysis model is used to receive data input from the environmental parameter fluctuation calculation module, analyze and calculate the environmental fluctuation impact factor through a pre-trained model, and the environmental fluctuation impact factor is used to assess the specific impact of environmental changes on the air volume fluctuation of the air classifier.

[0148] The air classifier operation parameter monitoring module is used to monitor and collect multi-dimensional operation parameters of the air classifier within a set time window, forming an air volume characteristic matrix of the air classifier;

[0149] The air volume fluctuation evaluation model is used to receive the air volume feature matrix of the air classifier as input, and calculate the air volume fluctuation index of the air classifier through the pre-trained model to reflect the air volume stability of the air classifier within a specific time window.

[0150] The external influence correction module is used to correct the air volume fluctuation index based on environmental fluctuation influence factors, in order to remove the influence of environmental factors and obtain a more accurate air volume fluctuation index of the classifier itself.

[0151] The airflow fluctuation status judgment module is used to compare the corrected airflow fluctuation index of the air classifier with the preset airflow fluctuation threshold to determine whether the airflow fluctuation status of the air classifier is normal.

[0152] The system monitors both the air classifier's operating parameters and environmental parameters, including humidity, temperature, atmospheric pressure, and wind speed, to comprehensively assess the impact of these factors on airflow fluctuations. The environmental fluctuation impact factor calculated by the environmental fluctuation impact analysis model quantifies the specific degree of environmental change's influence on airflow fluctuations, improving the accuracy of airflow fluctuation monitoring. When environmental parameters fluctuate significantly, the environmental fluctuation impact analysis model and external factor correction module reduce the impact of environmental factors on airflow fluctuation monitoring results, enhancing the system's adaptability. The external factor correction module adjusts the airflow fluctuation index of the air classifier to remove the influence of external environmental factors, improving the accuracy of monitoring results. Furthermore, by using pre-trained... A well-developed environmental fluctuation impact analysis model and airflow fluctuation evaluation model improve the system's automation level and reduce the need for human intervention. The airflow fluctuation status judgment module can provide timely results on whether the airflow fluctuation of the classifier is normal, facilitating rapid response by operators and improving the stability of the production process and product quality. Through continuous monitoring and data analysis, potential problems can be predicted, and measures can be taken in advance to avoid production interruptions or product quality decline. Precise airflow fluctuation monitoring can help adjust process parameters, improve production efficiency, and ensure product quality consistency. By incorporating environmental factors, the accuracy and reliability of airflow fluctuation monitoring, as well as the grading effect and overall production efficiency of the non-powered classifier, are improved.

[0153] The various variations and specific embodiments of the non-powered air classifier airflow fluctuation monitoring method in the aforementioned Embodiment 1 are also applicable to the non-powered air classifier airflow fluctuation monitoring system of this embodiment. Through the foregoing detailed description of the non-powered air classifier airflow fluctuation monitoring method, those skilled in the art can clearly understand the implementation method of the non-powered air classifier airflow fluctuation monitoring system of this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0154] In addition, this 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 the bus. When the computer program is executed by the processor, it implements the various processes of the above-described method embodiment for controlling output data and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0155] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method of monitoring air volume fluctuation of an unpowered classifier, characterized by, The method comprises: acquiring an environment parameter fluctuation vector corresponding to a set time window; inputting the environment parameter fluctuation vector into a pre-constructed environment fluctuation influence analysis model to obtain an environment fluctuation influence factor; the environment fluctuation influence factor is used to represent the influence degree of environment parameter change on the air volume fluctuation of the powder concentrator; acquiring a powder concentrator air volume feature matrix in a preset time window; the powder concentrator air volume feature matrix comprises multi-dimensional operation parameters of the powder concentrator collected at different time nodes; inputting the powder concentrator air volume feature matrix into a pre-constructed air volume fluctuation evaluation model to obtain a powder concentrator air volume fluctuation index; the powder concentrator air volume fluctuation index is used to represent the air volume stability of the powder concentrator in the set time window; based on the environment fluctuation influence factor, correcting the powder concentrator air volume fluctuation index from external influence to obtain a self air volume fluctuation index of the powder concentrator; comparing the self air volume fluctuation index of the powder concentrator with a preset air volume fluctuation threshold, and judging whether the air volume fluctuation of the powder concentrator is normal according to the comparison result; the method for obtaining the air volume fluctuation evaluation model comprises: collecting historical data of the powder concentrator air volume feature matrix and the corresponding air volume fluctuation; performing missing value processing, abnormal value detection and elimination, data standardization and normalization processing on the collected historical data; according to the degree of quantifying the air volume fluctuation of the powder concentrator, selecting a regression analysis model according to the actual situation, and using linear regression, ridge regression or LASSO regression to construct the air volume fluctuation evaluation model; dividing the preprocessed data set into a training set and a validation set, training the air volume fluctuation evaluation model using the training set data, adjusting the air volume fluctuation evaluation model hyperparameters according to the performance on the validation set, and optimizing the performance of the air volume fluctuation evaluation model; inputting the obtained powder concentrator air volume feature matrix into the trained air volume fluctuation evaluation model to obtain the powder concentrator air volume fluctuation index; if the air volume fluctuation evaluation model uses a linear regression model, the air volume fluctuation index is as follows: ； wherein, represents an intercept term, respectively represent the weight coefficients of the air volume of the air outlet, the air volume of the air inlet, the feeding speed and the material humidity, and the weight coefficients are determined in the training process of the air volume fluctuation evaluation model, respectively represent the air volume of the air outlet, the air volume of the air inlet, the feeding speed and the material humidity; the external influence correction formula is: ； wherein, represents the corrected classifier itself air volume fluctuation index, represents the classifier air volume fluctuation index, represents the environmental fluctuation influence factor.

2. The method of claim 1, wherein, the environment parameter fluctuation vector comprises environment humidity difference, environment temperature difference, atmospheric pressure difference and environment wind speed difference between the starting time points of the set time window.

3. The method of claim 1, wherein the air flow fluctuation monitoring method of the unpowered classifier is characterized by, the method for obtaining the environment fluctuation influence factor comprises: Collecting environmental parameter fluctuation vectors and corresponding historical data of air volume fluctuation data of the classifier performing missing value processing, abnormal value detection and data standardization processing on the collected historical data; selecting linear regression, machine learning algorithm, random forest or neural network to construct the environment fluctuation influence analysis model; dividing the preprocessed data set into a training set and a validation set, training the environment fluctuation influence analysis model using the training set data, and evaluating the performance of the environment fluctuation influence analysis model using the validation set data; measuring the fitting degree of the environment fluctuation influence analysis model by mean square error or decision coefficient; adjusting the environment fluctuation influence analysis model hyperparameters according to the performance on the validation set; the current acquired environmental parameter fluctuation vector is input into the trained environmental fluctuation influence analysis model to obtain an environmental fluctuation influence factor .

4. The unpowered classifier air flow fluctuation monitoring method of claim 3, wherein, When there is a linear relationship between the environmental parameter and the air volume fluctuation of the powder classifier, the environmental fluctuation influence factor The mathematical formula is: ； wherein, respectively represent the weight coefficients of the first-order environmental parameter influence result, the second-order environmental parameter influence result, and the environmental parameter interaction term influence result. represents the result of the first-order environmental parameter impact, and the calculation method is as follows: ； wherein respectively represent the environmental humidity difference, the environmental temperature difference, the atmospheric pressure difference and the environmental wind speed difference, respectively represent the first order effect coefficient of the environmental humidity difference, the environmental temperature difference, the atmospheric pressure difference and the environmental wind speed difference on the environmental fluctuation influence factor; represents the result of the second order ambient parameter influence and is calculated as follows: ； respectively represent the second order effect coefficients of the environmental humidity difference, the environmental temperature difference, the atmospheric pressure difference and the environmental wind speed difference on the environmental fluctuation influence factor; The environmental parameter interaction item represents the influence result of the environmental parameter interaction item, and the calculation method is as follows: ； represents an interaction term coefficient between the ambient humidity difference and the ambient temperature difference; represents an interaction term coefficient between the ambient humidity difference and the atmospheric pressure difference; represents an interaction term coefficient between the ambient humidity difference and the ambient wind speed difference; represents an interaction term coefficient between the ambient temperature difference and the atmospheric pressure difference; represents an interaction term coefficient between the ambient temperature difference and the ambient wind speed difference; represents an interaction term coefficient between the atmospheric pressure difference and the ambient wind speed difference.

5. The unpowered classifier air flow fluctuation monitoring method of claim 1, wherein, the method for acquiring the powder concentrator air volume feature matrix in the preset time window comprises: equidistantly dividing the set time window to obtain a plurality of time nodes for collecting operation parameters of the powder concentrator; based on the obtained time nodes, sequentially collecting a set of multi-dimensional operation parameters of the powder concentrator, the set of multi-dimensional operation parameters of the powder concentrator comprising air volume of an air outlet, air volume of an air inlet, feeding speed and material humidity; The multi-dimensional operation parameter set of the powder concentrator corresponding to the plurality of time nodes is time-series parameter aligned to obtain a wind volume feature matrix of the powder concentrator.

6. The unpowered classifier air flow fluctuation monitoring method of claim 5, wherein, The wind volume feature matrix of the powder concentrator is as follows: ； The time window is divided into time periods, and the parameters collected in each time period include the air volume at the air outlet and the air volume at the air inlet, the feeding speed and the material humidity .

7. An unpowered classifier air flow fluctuation monitoring system, characterized by, The system is applied to the unpowered powder concentrator wind volume fluctuation monitoring method of claim 1, and the system comprises: An environmental parameter monitoring module is configured to monitor and record environmental parameters in real time, including environmental humidity, environmental temperature, atmospheric pressure, and environmental wind speed. An environmental parameter fluctuation calculation module is configured to obtain data from the environmental parameter monitoring module and calculate a fluctuation vector of the environmental parameters within a set time window. An environmental fluctuation influence analysis model is configured to receive data input from the environmental parameter fluctuation calculation module, analyze and calculate an environmental fluctuation influence factor through a pre-trained model, and use the environmental fluctuation influence factor to evaluate the specific influence degree of environmental changes on the wind volume fluctuation of the powder concentrator. A powder concentrator operation parameter monitoring module is configured to monitor and collect multi-dimensional operation parameters of the powder concentrator within a set time window to form a wind volume feature matrix of the powder concentrator. A wind volume fluctuation evaluation model is configured to receive the wind volume feature matrix of the powder concentrator as input, calculate a wind volume fluctuation index of the powder concentrator through a pre-trained model, and reflect the wind volume stability of the powder concentrator within a specific time window. An external influence correction module is configured to correct the wind volume fluctuation index based on the environmental fluctuation influence factor to remove the influence of environmental factors and obtain a more accurate wind volume fluctuation index of the powder concentrator itself. A wind volume fluctuation state judgment module is configured to compare the corrected wind volume fluctuation index of the powder concentrator itself with a preset wind volume fluctuation threshold to determine whether the wind volume fluctuation state of the powder concentrator is normal.

8. An unpowered classifier air flow fluctuation monitoring electronics device comprising a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and capable of running on the processor, the transceiver, the memory, and the processor connected by the bus, characterized in that, The computer program is executed by the processor to implement the steps in the method of any one of claims 1-6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps in the method of any one of claims 1-6.

Images