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

Abstract

The invention relates to the technical field of powder concentrator monitoring, in particular to an unpowered powder concentrator air volume fluctuation monitoring method and system, which comprehensively considers environmental factors, quantifies environmental fluctuation influence, intelligently evaluates air volume fluctuation, eliminates external cause influence correction, and has the characteristics of real-time performance, automation and the like. The accuracy and the reliability of air volume monitoring as well as the grading effect and the overall production efficiency of the unpowered powder concentrator are improved; the method comprises the following steps: acquiring an environmental parameter fluctuation vector corresponding to a set time window; inputting the environmental parameter fluctuation vector into a pre-constructed environmental fluctuation influence analysis model to obtain an environmental fluctuation influence factor; the environmental fluctuation influence factor is used for representing the influence degree of environmental parameter change on the air volume fluctuation of the powder concentrator; a powder concentrator air volume characteristic matrix in a preset time window is obtained; the powder concentrator air volume characteristic matrix comprises powder concentrator multi-dimensional operation parameters collected at different time nodes.

Description

Technical Field

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

[0002] As an important material grading equipment, the unpowered powder classifier is widely used in industrial production for the grading of various materials such as ore, coal, and chemical raw materials. During the operation of the unpowered powder classifier, the stability of the air volume is directly related to the grading effect and the quality of the product. 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 powder classifier, and thus affect the grading effect.

[0003] Existing air volume monitoring methods often only focus on the operating parameters of the powder classifier itself, such as air volume at the tuyere, vibration, etc., while ignoring the impact of external environmental factors on air volume fluctuations; existing methods may be effective to a certain extent when environmental parameters are relatively stable, but when environmental parameters fluctuate greatly, the accuracy and reliability of the monitoring results will be greatly reduced. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for monitoring air volume fluctuations of an unpowered powder classifier, which improves the accuracy and reliability of air volume monitoring as well as the grading effect and overall production efficiency of the unpowered powder classifier by comprehensively considering environmental factors, quantifying the impact of environmental fluctuations, intelligently evaluating air volume fluctuations, eliminating external influence correction, and real-time and automation.

[0005] In a first aspect, the present invention provides a method for monitoring air volume fluctuation of an unpowered powder selector, the method comprising:

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

[0007] The environmental parameter fluctuation vector is input into a pre-built environmental fluctuation impact analysis model to obtain an 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 powder selector;

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

[0009] Inputting the air volume characteristic matrix of the powder separator into the pre-built air volume fluctuation evaluation model to obtain the air volume fluctuation index of the powder separator; the air volume fluctuation index of the powder separator is used to characterize the air volume stability of the powder separator within a set time window;

[0010] Based on the environmental fluctuation influencing factors, the air volume fluctuation index of the powder selector is corrected to remove external factors and obtain the air volume fluctuation index of the powder selector itself;

[0011] The air volume fluctuation index of the powder selector itself is compared with the preset air volume fluctuation threshold, and whether the air volume fluctuation of the powder selector is normal is determined based on the comparison result.

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

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

[0014] Collect historical data of environmental parameter fluctuation vector V and corresponding powder selector air volume fluctuation data;

[0015] Perform missing value processing, outlier detection and data standardization on the collected historical data;

[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 data set 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 degree of fit of the environmental fluctuation impact analysis model is measured by the mean square error or determination coefficient;

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

[0020] The currently acquired 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 the environmental parameters and the air volume fluctuation of the powder selector, the mathematical formula of the environmental fluctuation influence factor α is:

[0022] α=ω 1 f+ω 2 g+ω 3 h;

[0023] Among them, the coefficients in α represent the weight coefficients of the first-order environmental parameter impact results, the second-order environmental parameter impact results, and the environmental parameter interaction term impact results;

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

[0025]

[0026] Where ΔH, ΔT, ΔP, ΔW represent the environmental humidity difference, environmental temperature difference, atmospheric pressure difference and environmental wind speed difference respectively, and the coefficients in f represent the first-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;

[0027] g represents the impact result of the second-order environmental parameters, and the calculation method is 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;

[0030] h represents the effect of the environmental parameter interaction term, and the calculation method is as follows:

[0031]

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

[0033] Furthermore, the method for obtaining the air volume characteristic matrix of the powder selector within a preset time window includes:

[0034] The set time window is divided into time equidistant divisions to obtain multiple time nodes for collecting the operating parameters of the powder selector;

[0035] Based on the obtained time nodes, a multi-dimensional operating parameter set of the powder selector is collected in sequence, wherein the multi-dimensional operating parameter set of the powder selector includes an air volume at an air outlet, an air volume at an air inlet, a feed speed, and a material humidity;

[0036] The multi-dimensional operating parameter sets of the powder selector corresponding to the collected multiple time nodes are aligned with the time series parameters to obtain the powder selector air volume characteristic matrix.

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

[0038]

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

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

[0041] Collect the historical data of the air volume characteristic matrix of the powder selector and the corresponding air volume fluctuation;

[0042] Perform missing value processing, outlier detection and elimination, data standardization and normalization on the collected historical data;

[0043] According to the degree of air volume fluctuation of the quantified powder concentrator, a regression analysis model is selected according to the actual situation, such as linear regression, ridge regression or LASSO regression to construct an air volume fluctuation evaluation model;

[0044] The preprocessed data set 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 according to the performance on the validation set to optimize the performance of the air volume fluctuation evaluation model.

[0045] The obtained powder separator air volume characteristic matrix is ​​input into the trained air volume fluctuation evaluation model to obtain the powder separator air volume fluctuation index;

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

[0047] IVF = γ 0 +γ 1 Qo+γ 2 Qi+γ 3 v+γ 4 H;

[0048] Among them, γ 0 represents the intercept term, γ 1 , γ 2 , γ 3 , γ 4 They represent the weight coefficients of the outlet air volume, inlet air volume, feed speed and material humidity respectively. The above weight coefficients are determined during the training process of the air volume fluctuation evaluation model. o , Q i ,v,H represent the outlet air volume, inlet air volume, feed speed and material humidity respectively.

[0049] On the other hand, the present application also provides an air volume fluctuation monitoring system for an unpowered powder classifier, the system comprising:

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

[0051] An environmental parameter fluctuation calculation module is used to obtain data from the environmental parameter monitoring module and calculate the fluctuation vector of the environmental parameter 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 the pre-trained model, and the environmental fluctuation impact factor is used to evaluate the specific impact of environmental changes on the air volume fluctuation of the powder selector;

[0053] The powder selector operation parameter monitoring module is used to monitor and collect the multi-dimensional operation parameters of the powder selector within the set time window to form the powder selector air volume characteristic matrix;

[0054] The air volume fluctuation evaluation model is used to receive the air volume characteristic matrix of the powder selector as input, and calculate the air volume fluctuation index of the powder selector through the pre-trained model, reflecting the air volume stability of the powder selector within a specific time window;

[0055] The external influence correction module is used to correct the air volume fluctuation index based on the environmental fluctuation influence factor, so as to remove the influence of environmental factors and obtain a more accurate air volume fluctuation index of the powder selector itself;

[0056] The air volume fluctuation state judgment module is used to compare the corrected air volume fluctuation index of the powder selector itself with the preset air volume fluctuation threshold to determine whether the air volume fluctuation state of the powder selector is normal.

[0057] 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.

[0058] 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.

[0059] Compared with the prior art, the beneficial effects of the present invention are as follows: by considering the operating parameters of the powder classifier itself and introducing the environmental parameter fluctuation vector, the influence of environmental conditions on the air volume fluctuation of the powder classifier can be comprehensively evaluated; the degree of influence of environmental parameter changes on the air volume fluctuation of the powder classifier can be quantified through the environmental fluctuation impact analysis model, so as to accurately identify which environmental factors have a significant impact on the air volume fluctuation, so as to take targeted measures; by applying the environmental fluctuation influencing factor to the calculation of the air volume fluctuation index, the actual fluctuation of the air volume of the powder classifier can be accurately evaluated, and the accuracy of the monitoring results can be improved; when the environmental parameters fluctuate greatly, the influence of environmental factors on the air volume fluctuation monitoring results can be reduced by correcting the environmental fluctuation influencing factor, thereby improving the adaptability in complex environments; by removing the influence of external factors Correction, to obtain an air volume fluctuation index that is closer to the actual working state of the powder classifier, and to improve the reliability and stability of the monitoring results; by comparing the air volume fluctuation index of the powder classifier itself with the preset air volume fluctuation threshold, it is accurately determined whether the air volume fluctuation of the powder classifier is within the normal range, and decision support is provided to the operator to ensure the classification effect and product quality; through accurate monitoring and evaluation of air volume fluctuations, the working parameters of the powder classifier can be better adjusted, the production process can be optimized, and the classification effect and production efficiency can be improved; the air volume fluctuation monitoring method of the power powder classifier improves the accuracy and reliability of air volume monitoring as well as the classification effect and overall production efficiency of the unpowered powder classifier by comprehensively considering environmental factors, quantifying the impact of environmental fluctuations, intelligent air volume fluctuation evaluation, eliminating external factors and correction, as well as real-time and automation. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a flow chart of the present invention;

[0061] Figure 2 It is a flow chart of a method for obtaining an air volume fluctuation evaluation model;

[0062] Figure 3 It is the structural diagram of the air volume fluctuation monitoring system of the unpowered powder classifier. DETAILED DESCRIPTION

[0063] 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.

[0064] 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.

[0065] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0066] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0067] 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.

[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 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.

[0069] 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.

[0070] The present application is described below in conjunction with the drawings in the present application.

[0071] Embodiment 1: Figure 1 to Figure 2 As shown, the method for monitoring air volume fluctuation of an unpowered powder selector of the present invention specifically comprises the following steps:

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

[0073] Step S1 is to obtain the environmental parameter fluctuation vector corresponding to the set time window, which is directly related to the accuracy and reliability of the 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 environmental parameter fluctuation analysis. At the same time, the length of the time window should be determined according to environmental changes and monitoring needs, such as 1 hour, one day or one week. It should be able to capture significant changes in environmental parameters, but avoid being too long to cause data redundancy or increase 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 the atmospheric pressure; ambient wind speed, using an anemometer to monitor the wind speed;

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

[0077] Calculate the environmental parameter changes between the starting time points of the set time window, including: environmental humidity difference, which indicates the difference between the current humidity and the humidity at the starting time; environmental temperature difference, which indicates the difference between the current temperature and the temperature at the starting time; atmospheric pressure difference, which indicates the difference between the current atmospheric pressure and the atmospheric pressure at the starting time; environmental wind speed difference, which indicates the difference between the current wind speed and the wind speed at the starting time;

[0078] The environmental parameter changes are organized into a vector form as an environmental parameter fluctuation vector; the environmental parameter fluctuation vector is as follows:

[0079]

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

[0081] By continuously monitoring the changes in environmental parameters within the set time window and calculating the changes in these parameters, the impact of environmental changes on the fluctuation of the air volume of the powder selector can be accurately evaluated; at the same time, multiple parameters such as environmental humidity, temperature, atmospheric pressure and wind speed can be monitored to fully capture changes in environmental conditions; the set time window can be flexibly adjusted according to actual conditions, and the time window can be shortened to capture more subtle changes when the environment changes rapidly, or the window can be extended to reduce the complexity of data processing when the environment is relatively stable; the choice of time window is determined according to monitoring needs and the frequency of environmental changes, so that it can adapt to different industrial scenarios; by calculating the changes in environmental parameters rather than absolute values, the interference caused by the inherent fluctuations of the environment itself is reduced, and the reliability of monitoring results is improved; standard humidity sensors, temperature sensors, and air flow sensors are used. The pressure gauge and anemometer are used for monitoring, and the above equipment is easily available in the market and easy to integrate into the monitoring system; by continuously recording data within a set time window, it is ensured that the acquired data is representative and better reflects the changing trend of environmental conditions; the environmental parameter changes are organized into vector form, which is convenient for the subsequent processing of the environmental fluctuation impact analysis model and simplifies the data processing process; by pre-setting the time window, automatic data collection is realized, manual intervention is reduced, and monitoring efficiency is improved; even in the case of large fluctuations in environmental parameters, these changes can be effectively captured to enhance adaptability; by obtaining the environmental parameter fluctuation vector within the set time window, the accuracy, comprehensiveness and flexibility of wind volume fluctuation monitoring are improved, which is convenient for subsequent environmental fluctuation impact analysis and improves the performance of the entire monitoring system.

[0082] S2. Inputting the environmental parameter fluctuation vector into a pre-built environmental fluctuation impact analysis model to obtain an environmental fluctuation impact factor; the environmental fluctuation impact factor is used to characterize the degree of influence of environmental parameter changes on the fluctuation of the air volume of the powder selector;

[0083] Step S2 is a process of inputting the environmental parameter fluctuation vector into a pre-built environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factor, which is one of the links in the whole unpowered powder selection machine air volume fluctuation monitoring method; the details are as follows:

[0084] First, we build an environmental fluctuation impact analysis model, including:

[0085] Collect historical data, including environmental parameter fluctuation vector V and corresponding powder selector air volume fluctuation data;

[0086] Preprocess the collected historical data, including missing value processing, outlier detection and elimination, and data standardization to ensure data quality;

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

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

[0089] Use validation set data to evaluate the performance of the environmental fluctuation impact analysis model, and measure the degree of fit of the environmental fluctuation impact analysis model through mean square error or determination coefficient; if the performance of the environmental fluctuation impact analysis model is poor, 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] Input the currently acquired environmental parameter fluctuation vector V into the trained environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factor α, which reflects the degree of influence of environmental parameter changes on the air volume fluctuation of the powder selector;

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

[0093] α=ω 1 f+ω 2 g+ω 3 h;

[0094] Among them, the coefficients in α represent the weight coefficients of the first-order environmental parameter impact results, the second-order environmental parameter impact results, and the environmental parameter interaction term impact results;

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

[0096]

[0097] Where ΔH, ΔT, ΔP, ΔW represent the difference 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 difference in ambient humidity, ambient temperature, atmospheric pressure and ambient wind speed on the environmental fluctuation influencing factors respectively; reflecting the degree of influence of each environmental parameter on the environmental fluctuation influencing factor when it changes alone;

[0098] g represents the impact result of the second-order environmental parameters, and the calculation method is as follows:

[0099]

[0100] 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 influencing factors; they reflect the nonlinear influence of each environmental parameter on the environmental fluctuation influencing factors when it changes alone;

[0101] h represents the effect of the environmental parameter interaction term, and the calculation method is as follows:

[0102]

[0103] The coefficients in h represent the interaction coefficients between any two environmental parameters, reflecting the interactive effect of the factors affecting environmental fluctuations when two environmental parameters change at the same time.

[0104] By preprocessing the collected historical data, including missing value processing, outlier detection and elimination, and data standardization, the data quality is ensured and the prediction accuracy of the environmental fluctuation impact analysis model is improved; the appropriate model type is selected to quantify the impact of environmental parameter changes on air volume fluctuations, including linear regression, machine learning algorithms (random forest or neural network, etc., which can be flexibly selected according to actual conditions; the performance of the environmental fluctuation impact analysis model is evaluated using validation set data, and the degree of model fitting is measured by indicators such as mean square error or determination coefficient to ensure the reliability and generalization ability of the environmental fluctuation impact analysis model; the hyperparameters of the environmental fluctuation impact analysis model, such as regularization parameters and the number of trees, are adjusted according to the performance on the validation set to optimize the performance of the environmental fluctuation impact analysis model; the environmental fluctuation impact analysis model takes into account the operating parameters of the powder selector itself, as well as multiple environmental parameters such as environmental humidity, temperature, atmospheric pressure and wind speed, so as to facilitate a comprehensive assessment of the impact of environmental changes on air volume fluctuations; even when the environmental parameters fluctuate greatly, the environmental fluctuation impact analysis model can capture them through training data to enhance adaptability; when using a linear regression model, the parameters of the environmental fluctuation impact analysis model directly reflect the influence of each environmental parameter The environmental fluctuation impact factor can be used to measure the degree of influence of environmental parameter changes on air volume fluctuation, and increase the interpretability of the environmental fluctuation impact analysis model; the environmental fluctuation impact analysis model can be regularly updated to reflect the latest environmental conditions and powder classifier operating characteristics, and maintain the effectiveness of the environmental fluctuation impact analysis model; by accurately evaluating the impact of environmental parameter changes on air volume fluctuation, effective decision support can be provided to operators, and the working parameters of the powder classifier can be better adjusted; the formula for obtaining environmental fluctuation impact factors provides a method for quantifying the degree of influence of environmental parameter changes on the air volume fluctuation of the powder classifier, making the results comparable; and the formula is concise and clear, easy to understand and explain, and helps technical personnel and managers to quickly grasp key information; by adjusting the parameters of the environmental fluctuation impact analysis model, the performance of the environmental fluctuation impact analysis model is optimized, making the environmental fluctuation impact analysis model more in line with the needs of actual applications; using formulas to help realize the automation of the monitoring system, reduce manual intervention and improve efficiency; the formula is adjusted according to the needs of different scenarios to adapt to different data characteristics and application scenarios; by constructing an environmental fluctuation impact analysis model and obtaining environmental fluctuation impact factors, the accuracy, comprehensiveness and reliability of air volume fluctuation monitoring are improved, and it is also convenient for subsequent air volume fluctuation index correction and improves monitoring performance.

[0105] S3, obtaining a powder selector air volume characteristic matrix within a preset time window; the powder selector air volume characteristic matrix includes multi-dimensional operating parameters of the powder selector collected at different time nodes;

[0106] Acquiring the powder selector air volume characteristic matrix within the preset time window in step S3 is one of the links in the process of monitoring the air volume fluctuation of the unpowered powder selector. The powder selector air volume characteristic matrix can comprehensively and accurately capture the operating status of the powder selector within a specific time period, so as to subsequently analyze the internal causes and external influences of the air volume fluctuation; the details are as follows:

[0107] First, determine the preset time window. The time window should be long enough to contain enough data for analysis, but short enough to reflect the air volume fluctuation of the unpowered powder classifier in a short period of time. According to the monitoring requirements and data collection frequency, the set time window is equally divided into multiple time periods. The equally divided time window helps to ensure the uniformity and consistency of data collection. The length of each time period depends on the required monitoring accuracy and data availability. Through the equally divided time window, it is ensured that there is an opportunity to collect the operating parameters of the unpowered powder classifier at each time node, so as to construct a continuous and uniform air volume feature matrix.

[0108] Based on the determined time nodes, the multi-dimensional operating parameters of the unpowered powder classifier are collected in sequence; the multi-dimensional operating parameters can fully reflect the operating status and air volume of the unpowered powder classifier. In the field of unpowered powder classifier monitoring, common multi-dimensional operating parameters include: outlet air volume, using an air volume meter to measure the air volume discharged from the outlet of the powder classifier; inlet air volume, also using an air volume meter to measure the air volume entering the powder classifier; feed speed, using a flow meter to measure the material flow rate entering the powder classifier; material humidity, using a humidity sensor to measure the material humidity entering the powder classifier;

[0109] The multi-dimensional operating parameters collected at each time node are arranged in time sequence to form a powder selector air volume characteristic matrix. The purpose of time sequence parameter alignment is to adjust the multi-dimensional operating parameters collected at different time nodes to a unified time base. Through time sequence parameter alignment, a complete and time-continuous powder selector air volume characteristic matrix is ​​obtained. The powder selector air volume characteristic matrix contains the powder selector multi-dimensional operating parameter information at all time nodes within the preset time window;

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

[0111]

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

[0113] By collecting multi-dimensional operating parameters including outlet air volume, inlet air volume, feed speed and material humidity, the operating status and air volume of the powder classifier can be fully reflected; by equally dividing the time window and aligning the time sequence parameters, the uniformity and consistency of data collection can be ensured, and the accuracy of the air volume characteristic matrix of the powder classifier can be improved; the length of the time window can be flexibly adjusted according to the monitoring needs and data collection frequency, which can not only capture the air volume fluctuation in a short time, but also include a long enough time period to reflect the long-term trend; the time interval of data collection can be adjusted according to actual needs to balance the resolution and processing complexity of the data; by arranging the multi-dimensional operating parameters in chronological order to form a matrix, it is convenient for the subsequent air volume fluctuation evaluation model to process and analyze; by ensuring the completeness of data collection Improve the integrity and accuracy of the air volume characteristic matrix and the accuracy of subsequent analysis; reduce the false alarm rate caused by discontinuous or inconsistent data by constructing a continuous and uniform air volume characteristic matrix; provide more effective decision support for operators by more accurately capturing the operating status of the classifier in a specific time period, and facilitate the adjustment of the working parameters of the classifier; ensure the accuracy of data collection by regularly checking and calibrating sensors, and upgrade the monitoring system according to actual needs; the accurate air volume characteristic matrix helps adjust process parameters, improve production efficiency, and ensure the consistency of product quality; by obtaining the air volume characteristic matrix of the classifier within the preset time window, the comprehensiveness and accuracy of air volume fluctuation monitoring can be improved, and it is also convenient for the subsequent calculation of the air volume fluctuation index and improves the monitoring performance.

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

[0115] In step S4, the powder separator air volume characteristic matrix is ​​input into the pre-built air volume fluctuation evaluation model to obtain the powder separator air volume fluctuation index; specifically, as follows:

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

[0117] Collect historical data, including the air volume characteristic matrix of the classifier and the corresponding air volume fluctuations; the above data covers a variety of operating conditions so that the air volume fluctuation evaluation model can adapt to a wide range of operating scenarios;

[0118] Preprocess the collected historical data, including missing value processing, outlier detection and elimination, data standardization and normalization, to ensure data quality;

[0119] The goal of the air volume fluctuation evaluation model is to quantify the degree of air volume fluctuation in the classifier, and to select a regression analysis model, such as linear regression, ridge regression, or LASSO regression;

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

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

[0122] The obtained air volume characteristic matrix of the powder separator is input into the trained air volume fluctuation evaluation model to obtain the air volume fluctuation index of the powder separator, which reflects the air volume stability of the powder separator within the 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 = γ 0 +γ 1 Qo+γ 2 Qi+γ 3 v+γ 4 H;

[0125] Among them, IVF represents the air volume fluctuation index of the powder concentrator, γ 0 represents the intercept term, γ 1 , γ 2 , γ 3 , γ 4 They represent the weight coefficients of the outlet air volume, inlet air volume, feed speed and material humidity respectively. The above weight coefficients are determined during the training process of the air volume fluctuation evaluation model. o , Q i ,v,H represent the outlet air volume, inlet air volume, feed speed and material humidity respectively.

[0126] By training the air volume fluctuation evaluation model, the degree of air volume fluctuation of the classifier can be accurately quantified, and the accuracy of air volume fluctuation monitoring can be improved; the air volume fluctuation evaluation model takes into account the operating parameters of the classifier itself, as well as multiple key parameters, including outlet air volume, inlet air volume, feed speed and material humidity, so as to comprehensively evaluate the air volume stability of the classifier; the data used in the training of the air volume fluctuation evaluation model covers a variety of different operating conditions, so that the air volume fluctuation evaluation model can adapt to a wide range of operating scenarios; different model types are selected according to actual needs, such as linear regression, ridge regression or LASSO regression, etc., to adapt to different data characteristics and application scenarios; the performance of the air volume fluctuation evaluation model is evaluated by using the validation set data to ensure the reliability and generalization ability of the air volume fluctuation evaluation model; when using the linear regression model, the air volume fluctuation evaluation model parameters directly reflect the various The degree of influence of parameters on air volume fluctuation increases the interpretability of the air volume fluctuation evaluation model; the parameters of the air volume fluctuation evaluation model are adjusted according to the performance on the validation set to optimize the performance of the air volume fluctuation evaluation model, and fine-tuned according to the actual application situation; the air volume fluctuation evaluation model is regularly updated to reflect the latest operating characteristics, which helps to maintain the effectiveness of the air volume fluctuation evaluation model; by more accurately evaluating the degree of air volume fluctuation of the classifier, the false alarm rate caused by the error of the air volume fluctuation evaluation model is reduced; by more accurately evaluating the air volume stability of the classifier within the set time window, effective decision support is provided to the operator to better adjust the working parameters of the classifier; by constructing an air volume fluctuation evaluation model and obtaining the air volume fluctuation index of the classifier, the accuracy, comprehensiveness and reliability of air volume fluctuation monitoring can be improved, and it is also convenient for subsequent air volume fluctuation index correction to improve monitoring performance.

[0127] S5. Based on the environmental fluctuation influencing factors, the air volume fluctuation index of the powder selector is corrected to remove external influences, and the air volume fluctuation index of the powder selector itself is obtained;

[0128] In step S5, the air volume fluctuation index of the powder selector is corrected to remove external influences based on the environmental fluctuation influencing factors to ensure that the evaluation result can truly reflect the air volume stability of the powder selector itself; the details are as follows:

[0129] According to the environmental fluctuation impact factor α obtained by inputting the environmental parameter fluctuation vector into the pre-built environmental fluctuation impact analysis model in step S2, the environmental fluctuation impact factor reflects the influence of the environmental parameter change on the air volume fluctuation of the powder selector;

[0130] According to the powder separator air volume fluctuation index IVF obtained by inputting the powder separator air volume characteristic matrix into the air volume fluctuation evaluation model in step S4, the powder separator air volume fluctuation index is used to characterize the air volume stability of the powder separator within a set time window;

[0131] According to the environmental fluctuation factor α, the powder selector air volume fluctuation index IVF is corrected to remove the influence of external environmental factors; the correction formula is as follows:

[0132] IVF c =IVF-α;

[0133] Among them, IVF c represents the corrected air volume fluctuation index of the classifier itself, IVF represents the air volume fluctuation index of the classifier, and α represents the environmental fluctuation influencing factor;

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

[0135] By correcting the air volume fluctuation index IVF of the classifier based on the environmental fluctuation influence factor α, the air volume fluctuation of the classifier itself can be accurately reflected, thereby improving the accuracy of air volume fluctuation monitoring; the correction process removes the influence of external environmental factors on the air volume fluctuation index of the classifier, ensuring that the evaluation results can truly reflect the air volume stability of the classifier itself; by removing the external influence of correction, the uncertainty of the monitoring results caused by changes in environmental factors is reduced, thereby improving the reliability of the monitoring results; by accurately reflecting the air volume stability of the classifier itself, more effective decision-making support is provided to operators, and the working parameters of the classifier can be better adjusted; the correction formula is simple, intuitive, and easy to understand It can be mastered and implemented without complex mathematical background; it can improve monitoring efficiency by reducing the impact of external environmental factors on air volume fluctuation monitoring results, and more quickly identify the air volume fluctuation of the powder selector itself; it can reduce the false alarm rate caused by external environmental factors by accurately reflecting the air volume stability of the powder selector itself; accurate air volume fluctuation monitoring can help adjust process parameters, improve production efficiency, and ensure the consistency of product quality; the method of correcting the air volume fluctuation index of the powder selector based on the environmental fluctuation influencing factors can improve the accuracy, reliability and applicability of air volume fluctuation monitoring, and at the same time facilitate the subsequent judgment of the air volume fluctuation status and improve monitoring efficiency.

[0136] S6, comparing the air volume fluctuation index of the powder selector with the preset air volume fluctuation threshold, and judging whether the air volume fluctuation of the powder selector is normal according to the comparison result;

[0137] Step S6 evaluates the air volume fluctuation index of the powder selector itself and determines whether it is normal; the details are as follows:

[0138] S61. According to the design requirements and operating experience of the powder selector, set a reasonable air volume fluctuation threshold, the threshold is IVF t; The threshold is based on the air volume fluctuation range when the powder classifier is operating normally, ensuring that in most cases it can be correctly judged whether the air volume fluctuation is normal;

[0139] S62, the corrected air volume fluctuation index IVF of the powder concentrator obtained in step S5 c Preset air volume fluctuation threshold IVF t Make comparisons;

[0140] S63, when IVF c <IVF t When the air volume fluctuation of the powder selector is within the normal range, c ≥ IVF t When , it is considered that the air volume fluctuation of the powder selector exceeds the normal range and there is an abnormal situation;

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

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

[0143] Through the corrected IVF of the powder selector's own air volume fluctuation index c With the preset air volume fluctuation threshold IVF t Compare and accurately judge whether the air volume fluctuation of the powder selector is normal; monitor the air volume fluctuation of the powder selector in real time, discover and deal with abnormal situations in time, and improve production efficiency and product quality; preset air volume fluctuation threshold IVF t Based on the design requirements and operating experience of the powder classifier, correctly judge whether the air volume fluctuation is normal and improve the reliability of the monitoring results; by accurately judging whether the air volume fluctuation of the powder classifier is normal, provide more effective decision support for operators and better adjust the working parameters of the powder classifier; accurate air volume fluctuation monitoring can help adjust process parameters, improve production efficiency, and ensure the consistency of product quality; through the judgment method based on the air volume fluctuation index of the powder classifier itself, reduce the false alarm rate caused by environmental factors; with the accumulation of time and experience, adjust and optimize the preset air volume fluctuation threshold according to the actual operating conditions to adapt to different production environments and needs; by timely discovering and handling abnormal situations, reduce unplanned downtime and improve equipment availability and production efficiency; by comparing the air volume fluctuation index of the powder classifier itself with the preset air volume fluctuation threshold, the accuracy, reliability and applicability of air volume fluctuation monitoring can be improved, and it is also convenient to timely discover and handle abnormal situations and improve monitoring performance.

[0144] Embodiment 2: Figure 3As shown, the air volume fluctuation monitoring system of the unpowered powder classifier of the present invention specifically includes the following modules:

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

[0146] An environmental parameter fluctuation calculation module is used to obtain data from the environmental parameter monitoring module and calculate the fluctuation vector of the environmental parameter 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 the pre-trained model, and the environmental fluctuation impact factor is used to evaluate the specific impact of environmental changes on the air volume fluctuation of the powder selector;

[0148] The powder selector operation parameter monitoring module is used to monitor and collect the multi-dimensional operation parameters of the powder selector within the set time window to form the powder selector air volume characteristic matrix;

[0149] The air volume fluctuation evaluation model is used to receive the air volume characteristic matrix of the powder selector as input, and calculate the air volume fluctuation index of the powder selector through the pre-trained model, reflecting the air volume stability of the powder selector within a specific time window;

[0150] The external influence correction module is used to correct the air volume fluctuation index based on the environmental fluctuation influence factor, so as to remove the influence of environmental factors and obtain a more accurate air volume fluctuation index of the powder selector itself;

[0151] The air volume fluctuation state judgment module is used to compare the corrected air volume fluctuation index of the powder selector itself with the preset air volume fluctuation threshold to determine whether the air volume fluctuation state of the powder selector is normal.

[0152] The system monitors the operating parameters of the powder selector itself and the environmental parameters, including ambient humidity, temperature, atmospheric pressure and wind speed, to comprehensively evaluate the impact of these factors on air volume fluctuations. The environmental fluctuation impact factor calculated by the environmental fluctuation impact analysis model can quantify the specific impact of environmental changes on air volume fluctuations and improve the accuracy of air volume fluctuation monitoring. When the environmental parameters fluctuate greatly, the environmental fluctuation impact analysis model and the external factor impact correction module are used to reduce the impact of environmental factors on the air volume fluctuation monitoring results and enhance the adaptability of the system. The external factor impact correction module adjusts the powder selector air volume fluctuation index to remove the impact of external environmental factors and improve the accuracy of monitoring results. The well-trained environmental fluctuation impact analysis model and air volume fluctuation evaluation model can improve the system's automation level and reduce the need for human intervention; the air volume fluctuation status judgment module can timely provide the judgment result of whether the air volume fluctuation of the powder selector is normal, which is convenient for operators to respond quickly and improve 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 degradation; accurate air volume fluctuation monitoring can help adjust process parameters, improve production efficiency and ensure product quality consistency; by introducing considerations of environmental factors, the accuracy and reliability of air volume fluctuation monitoring as well as the grading effect and overall production efficiency of the unpowered powder selector can be improved.

[0153] The various variations and specific embodiments of the method for monitoring air volume fluctuations of an unpowered powder classifier in the aforementioned embodiment 1 are also applicable to the system for monitoring air volume fluctuations of an unpowered powder classifier in the present embodiment. Through the aforementioned detailed description of the method for monitoring air volume fluctuations of an unpowered powder classifier, those skilled in the art can clearly know the implementation method of the system for monitoring air volume fluctuations of an unpowered powder classifier in the present embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0154] 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.

[0155] 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 monitoring air volume fluctuation of an unpowered powder selector, characterized in that: The method comprises: Obtaining the environmental parameter fluctuation vector corresponding to the set time window; The environmental parameter fluctuation vector is input into a pre-built environmental fluctuation impact analysis model to obtain an 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 powder selector; Obtaining a powder selector air volume characteristic matrix within a preset time window; the powder selector air volume characteristic matrix includes multi-dimensional operating parameters of the powder selector collected at different time nodes; Inputting the air volume characteristic matrix of the powder separator into the pre-built air volume fluctuation evaluation model to obtain the air volume fluctuation index of the powder separator; the air volume fluctuation index of the powder separator is used to characterize the air volume stability of the powder separator within a set time window; Based on the environmental fluctuation influencing factors, the air volume fluctuation index of the powder selector is corrected to remove external factors and obtain the air volume fluctuation index of the powder selector itself; The air volume fluctuation index of the powder selector itself is compared with the preset air volume fluctuation threshold, and whether the air volume fluctuation of the powder selector is normal is determined based on the comparison result.

2. The method for monitoring air volume fluctuation of an unpowered powder selector according to claim 1, characterized in that: The environmental parameter fluctuation vector includes the environmental humidity difference, environmental temperature difference, atmospheric pressure difference and environmental wind speed difference between the starting time points of the set time window.

3. The method for monitoring air volume fluctuation of an unpowered powder concentrator according to claim 1, characterized in that: The method for obtaining the environmental fluctuation influencing factor comprises: Collect historical data of environmental parameter fluctuation vector V and corresponding powder selector air volume fluctuation data; Perform missing value processing, outlier detection and data standardization on the collected historical data; Choose linear regression, machine learning algorithms, random forests, or neural networks to build models for analyzing the impact of environmental fluctuations; The preprocessed data set 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. The degree of fit of the environmental fluctuation impact analysis model is measured by the mean square error or determination coefficient; Adjust the hyperparameters of the environmental fluctuation impact analysis model based on the performance on the validation set; The currently acquired environmental parameter fluctuation vector V is input into the trained environmental fluctuation impact analysis model to obtain the environmental fluctuation impact factor α.

4. The method for monitoring air volume fluctuation of an unpowered powder selector according to claim 3, characterized in that: When there is a linear relationship between the environmental parameters and the air volume fluctuation of the powder selector, the mathematical formula of the environmental fluctuation influence factor α is: α=ω1f+ω2g+ω3h; Among them, the coefficients in α represent the weight coefficients of the first-order environmental parameter impact results, the second-order environmental parameter impact results, and the environmental parameter interaction term impact results; f represents the first-order environmental parameter impact result, and the calculation method is as follows: Where ΔH, ΔT, ΔP, ΔW represent the environmental humidity difference, environmental temperature difference, atmospheric pressure difference and environmental wind speed difference respectively, and the coefficients in f represent the first-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; g represents the impact result of the second-order environmental parameters, and the calculation method is as follows: 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; h represents the effect of the environmental parameter interaction term, and the calculation method is as follows: The coefficients in h represent the interaction coefficients between any two environmental parameters.

5. The method for monitoring air volume fluctuation of an unpowered powder concentrator according to claim 1, characterized in that: The method for obtaining the air volume characteristic matrix of the powder selector within a preset time window includes: The set time window is divided into time equidistant divisions to obtain multiple time nodes for collecting the operating parameters of the powder selector; Based on the obtained time nodes, a multi-dimensional operating parameter set of the powder selector is collected in sequence, wherein the multi-dimensional operating parameter set of the powder selector includes an air volume at an air outlet, an air volume at an air inlet, a feed speed, and a material humidity; The multi-dimensional operating parameter sets of the powder selector corresponding to the collected multiple time nodes are aligned with the time series parameters to obtain the powder selector air volume characteristic matrix.

6. The method for monitoring air volume fluctuation of an unpowered powder selector according to claim 5, characterized in that: The air volume characteristic matrix of the powder selector is as follows: The time window is divided into n time periods, and the parameters collected in each time period include the outlet air volume Q o And the air volume Q i , feed rate v and material humidity H.

7. The method for monitoring air volume fluctuation of an unpowered powder concentrator according to claim 1, characterized in that: The method for obtaining the wind volume fluctuation evaluation model comprises: Collect the historical data of the air volume characteristic matrix of the powder selector and the corresponding air volume fluctuation; Perform missing value processing, outlier detection and elimination, data standardization and normalization on the collected historical data; According to the degree of air volume fluctuation of the quantified powder concentrator, a regression analysis model is selected according to the actual situation, such as linear regression, ridge regression or LASSO regression to construct an air volume fluctuation evaluation model; The preprocessed data set 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 according to the performance on the validation set to optimize the performance of the air volume fluctuation evaluation model. The obtained powder separator air volume characteristic matrix is ​​input into the trained air volume fluctuation evaluation model to obtain the powder separator air volume fluctuation index; If the air volume fluctuation evaluation model uses a linear regression model, the air volume fluctuation index IVF is as follows: IVF=γ0+γ1Qo+γ2Qi+γ3v+γ4H; Among them, γ0 represents the intercept term, γ1, γ2, γ3, and γ4 represent the weight coefficients of the outlet air volume, inlet air volume, feed speed, and material humidity, respectively. The above weight coefficients are determined during the training process of the air volume fluctuation evaluation model. o , Q i ,v,H represent the outlet air volume, inlet air volume, feed speed and material humidity respectively.

8. A non-powered powder selector air volume fluctuation monitoring system, characterized in that: The system comprises: Environmental parameter monitoring module, used to monitor and record environmental parameters in real time, including ambient humidity, ambient temperature, atmospheric pressure and ambient wind speed; An environmental parameter fluctuation calculation module is used to obtain data from the environmental parameter monitoring module and calculate the fluctuation vector of the environmental parameter within a set time window; 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 the pre-trained model, and the environmental fluctuation impact factor is used to evaluate the specific impact of environmental changes on the air volume fluctuation of the powder selector; The powder selector operation parameter monitoring module is used to monitor and collect the multi-dimensional operation parameters of the powder selector within the set time window to form the powder selector air volume characteristic matrix; The air volume fluctuation evaluation model is used to receive the air volume characteristic matrix of the powder selector as input, and calculate the air volume fluctuation index of the powder selector through the pre-trained model, reflecting the air volume stability of the powder selector within a specific time window; The external influence correction module is used to correct the air volume fluctuation index based on the environmental fluctuation influence factor, so as to remove the influence of environmental factors and obtain a more accurate air volume fluctuation index of the powder selector itself; The air volume fluctuation state judgment module is used to compare the corrected air volume fluctuation index of the powder selector itself with the preset air volume fluctuation threshold to determine whether the air volume fluctuation state of the powder selector is normal.

9. An electronic device for monitoring air volume fluctuation 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