CN114733640A - Method and device for adjusting processing parameters of pulverizer and computer equipment - Google Patents
Method and device for adjusting processing parameters of pulverizer and computer equipment Download PDFInfo
- Publication number
- CN114733640A CN114733640A CN202210210313.4A CN202210210313A CN114733640A CN 114733640 A CN114733640 A CN 114733640A CN 202210210313 A CN202210210313 A CN 202210210313A CN 114733640 A CN114733640 A CN 114733640A
- Authority
- CN
- China
- Prior art keywords
- prediction
- fineness
- yield
- processing parameters
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
- B02C25/00—Control arrangements specially adapted for crushing or disintegrating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Neurology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Food Science & Technology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Disintegrating Or Milling (AREA)
Abstract
The present disclosure relates to a method, an apparatus, a computer device, a storage medium and a computer program product for adjusting mill processing parameters. The method comprises the following steps: acquiring processing parameters of a crusher and target fineness of material processing; inputting the processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material through the prediction model; determining optimized processing parameters according to a preset optimization algorithm under the conditions that the prediction fineness is within a first preset range of the target fineness and the prediction yield is outside a preset range of yield; and inputting the optimized processing parameters into the prediction model until the prediction fineness output by the prediction model is within the first preset range and the output predicted yield is within the preset range of the yield corresponding to the optimized processing parameters. By adopting the method, the fineness of the material can be accurately and efficiently adjusted, and the productivity is kept stable at a higher level.
Description
Technical Field
The disclosure relates to the technical field of material crushing, in particular to a method and a device for adjusting processing parameters of a crusher and computer equipment.
Background
The existing pulverizer system mainly comprises a pulverizing mechanism, a grading mechanism and a pneumatic conveying system. The grading mechanism is used for separating small particle materials meeting the fineness requirement out of the crushing chamber, and meanwhile, large particle materials are forced to return to the crushing chamber to continue to be hit by the crushing mechanism. Among them, the structure generally adopted by the classification mechanism is a classification wheel.
In the existing crushing technology, the initial rotating speed of a classifying wheel is manually set according to experience for production, a crushed material sample is obtained in the production process, the fineness of the crushed material is checked, and the rotating speed of the classifying wheel is adjusted according to the fineness. However, in the actual production process, the system air volume of the pulverizer also affects the fineness of the pulverized material, and the system air volume and the rotational speed of the classifying wheel also affect the capacity of the pulverizer system, so that when the processing parameters are adjusted manually according to experience, the accuracy is low, the capacity is unstable, and the pulverizing efficiency is low.
Disclosure of Invention
In view of the above, there is a need to provide a method, an apparatus, a computer device and a storage medium for adjusting processing parameters of a pulverizer, which can accurately and efficiently adjust the fineness of a material while maintaining stable production performance.
In a first aspect, embodiments of the present disclosure provide a method for adjusting processing parameters of a pulverizer. The method is applied to a pulverizer, and comprises the following steps:
acquiring processing parameters of a crusher and target fineness of material processing;
inputting the processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material through the prediction model, wherein the prediction model is set to be obtained by utilizing the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield through training;
determining optimized processing parameters according to a preset optimization algorithm under the conditions that the prediction fineness is within a first preset range of the target fineness and the prediction yield is outside a preset range of yield;
and inputting the optimized processing parameters into the prediction model until the prediction fineness output by the prediction model is within the first preset range and the output predicted yield is within the preset range of the yield corresponding to the optimized processing parameters.
In one embodiment, the preset range of the yield is set in a manner that:
acquiring a partial derivative of the predicted yield to the processing parameter;
and determining a preset range of the yield corresponding to the processing parameter according to the partial derivative.
In one embodiment, after the outputting the predicted fineness and the predicted yield of the material through the prediction model, the method further comprises:
determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is out of a first preset range of the target fineness;
and inputting the optimized processing parameters into the prediction model until the prediction fineness of the material output by the prediction model is within the first preset range.
In one embodiment, the determining the optimized processing parameter according to a preset optimization algorithm includes:
obtaining the product of the partial derivative of the prediction fineness on the processing parameter and a preset value;
and determining the sum of the product and the machining parameter as the optimized machining parameter.
In one embodiment, the determining the optimized machining parameters according to a preset optimization algorithm includes:
obtaining the product of the partial derivative of the predicted yield to the processing parameter and a preset value;
and determining the sum of the product and the machining parameter as the optimized machining parameter.
In one embodiment, the prediction model is set to be obtained by training using the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield, and comprises the following steps:
acquiring a set of sample processing parameters, wherein the set comprises a plurality of sample processing parameters marked with fineness labels and yield labels;
constructing a prediction model, wherein training parameters are set in the prediction model;
inputting the sample processing parameters into the fineness and yield prediction model to generate a prediction result;
and iteratively adjusting the prediction model based on the difference between the prediction result and the labeled fineness label and the labeled yield label until the difference meets the preset requirement to obtain the prediction model.
In one embodiment, the inputting the processing parameters into a prediction model, and outputting the predicted fineness and the predicted yield of the material through the prediction model comprises:
carrying out standardization processing on the processing parameters to obtain processed processing parameters;
and inputting the processed processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material through the prediction model.
In one embodiment, after the step of outputting the predicted fineness within the first preset range and the predicted yield within the preset range of the yield corresponding to the optimized processing parameter by the prediction model, the method further includes:
obtaining optimized processing parameters, wherein the prediction fineness corresponding to the processing parameters is within the first preset range, and the corresponding prediction yield is within the preset range of the yield corresponding to the processing parameters;
and processing the material according to the optimized processing parameters.
In a second aspect, the disclosed embodiment further provides a device for adjusting processing parameters of the pulverizer. The device is applied to a pulverizer comprising a classifying wheel, comprising:
the acquisition module is used for acquiring the processing parameters of the crusher and the target fineness of material processing;
the prediction module is used for inputting the processing parameters into a prediction model and outputting the prediction fineness and the prediction yield of the material through the prediction model, wherein the prediction model is set to be obtained by utilizing the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield in a training mode;
the optimization module is used for determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is within a first preset range of the target fineness and the prediction yield is outside a preset range of yield;
and the adjusting module is used for inputting the optimized processing parameters into the prediction model until the prediction fineness output by the prediction model is within the first preset range and the output predicted yield is within the preset range of the yield corresponding to the optimized processing parameters.
In a third aspect, an embodiment of the present disclosure further provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method according to any of the embodiments of the present disclosure when executing the computer program.
In a fourth aspect, the disclosed embodiments also provide a computer-readable storage medium. The computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of the embodiments of the disclosure.
In a fifth aspect, the disclosed embodiments also provide a computer program product. The computer program product comprising a computer program that when executed by a processor implements the steps of the method of any of the embodiments of the present disclosure.
According to the method and the device, the prediction fineness and the prediction yield corresponding to the processing parameters are obtained through the prediction model, the preset range of the yield can be obtained according to the obtained prediction yield, when the fineness meets the requirement and the yield is not in the preset range, the processing parameters are optimized through the preset optimization algorithm to obtain the optimized processing parameters, the optimized processing parameters are input into the prediction model to obtain the prediction fineness and the prediction yield, judgment is carried out again until the prediction fineness and the prediction yield are both in the preset range, so that the processing parameters can be adjusted through the prediction module and parameter optimization, the adjusted fineness reaches the standard and the yield is higher, the full-automatic adjustment of the processing parameters is realized, the efficiency and the accuracy are improved, and the stability of the yield is guaranteed.
Drawings
FIG. 1 is a schematic view showing the structure of a pulverizer according to an embodiment;
FIG. 2 is a schematic flow diagram of a method for adjusting mill processing parameters in one embodiment;
FIG. 3 is a flow diagram illustrating a method for predictive model generation in one embodiment;
FIG. 4 is a schematic flow diagram of a method for adjusting mill process parameters according to one embodiment;
FIG. 5 is a block diagram showing the structure of a processing parameter adjusting apparatus of the pulverizer according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clearly understood, the embodiments of the present disclosure are described in further detail below with reference to the accompanying drawings and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the disclosure and that they are not intended to limit the embodiments of the disclosure.
In order to facilitate those skilled in the art to understand the technical solutions provided by the embodiments of the present disclosure, a technical environment for implementing the technical solutions is described below.
Fig. 1 is a system configuration diagram of a pulverizer shown according to an exemplary embodiment, and referring to fig. 1, the ultrafine pulverizer system includes a bin to be pulverized, an ultrafine pulverizing main machine, a shakelong (i.e., a cyclone), a pulse dust collector, and a fan, an online particle size/fineness detection system may be further added to the pulverizer system for detecting the fineness of the material after production, and the online particle size/fineness detection system may be installed at a, i.e., behind the classification system in the pulverizer, or at B, i.e., behind a subsequent screening device.
In one embodiment, illustrated in FIG. 2, a method of adjusting a mill process parameter is provided and is exemplified in the context of its application to a mill that includes a classifier wheel. In this embodiment, the method includes the steps of:
step S210, obtaining processing parameters of a pulverizer and target fineness of material processing;
in the embodiment of the disclosure, when the pulverizer performs pulverizing processing, due to the difference of processing parameters such as the rotating speed of the grading wheel and the air volume of the system, the fineness of the obtained pulverized material is different. The fineness of the crushed material is different according to the purpose, the type and the like of the crushed material, namely the target fineness. Before the pulverizer performs material pulverizing processing, firstly, acquiring initial processing parameters of the pulverizer and target fineness of processing. In one example, the initial processing parameter may be a suitable processing parameter determined by a human or a computer device according to the current material type and the target fineness, or may be a parameter value set arbitrarily.
Step S220, inputting the processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material through the prediction model, wherein the prediction model is set to be obtained by utilizing the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield through training;
in the embodiment of the disclosure, after the processing parameters of the pulverizer are acquired, the processing parameters are input into the prediction model, and the prediction model outputs the prediction fineness and the prediction yield corresponding to the processing parameters according to the input processing parameters. The prediction model is obtained by training in advance, and the model is trained according to the corresponding relation between the processing parameters in the sample and the prediction fineness and the prediction yield to obtain the final prediction model. In one example, the processing parameters may be the rotational speed of the classifier wheel and the system air volume. The fineness prediction model may include, but is not limited to, a deep neural network model, an M5P model, and the like.
Step S230, determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is within a first preset range of the target fineness and the prediction yield is outside a preset range of yield;
in the embodiment of the disclosure, after obtaining the predicted fineness and the predicted yield output by the prediction model, first, it is determined whether the predicted fineness is within a first preset range of a target fineness, where the first preset range is an error allowable range of the preset target fineness, in one example, when a certain feed product is crushed, the fineness requirement of the crushed material is represented by an 80-mesh sieving rate, and when the target fineness requirement is an 80-mesh passing rate of 95%, the preset range of the target fineness may be set to an 80-mesh passing rate of 95% ± 0.5%. When the predicted fineness is within the first preset range, the predicted fineness at this time satisfies the requirement of the pulverization processing. Then, it is determined whether the predicted yield is within a preset range of yield, where the yield generally refers to the yield of material crushing processing within a preset fixed time period, and the preset range of yield generally refers to a range determined according to the current processing parameters and the predicted yield. When the yield is within the preset range, the predicted yield at this time can be considered to be locally optimal, and when the yield is outside the preset range, the predicted yield at this time is low and not locally optimal, and the processing parameters need to be optimized and adjusted. And when the processing parameters are optimized and adjusted, obtaining optimized processing parameters through a preset optimization algorithm according to the processing parameters and the predicted yield corresponding to the processing parameters. The optimization algorithm may include, but is not limited to, a gradient descent method, a newton method, a quasi-newton method, a conjugate gradient method, a genetic algorithm, and the like.
Step S240, inputting the optimized processing parameter into the prediction model until the prediction fineness output by the prediction model is within the first preset range, and the output predicted yield is within the preset range of the yield corresponding to the optimized processing parameter.
In the embodiment of the disclosure, after the optimized processing parameters are obtained, the optimized processing parameters are input into the prediction model to obtain the corresponding prediction fineness and the prediction yield. Judging the obtained prediction fineness and the prediction yield, continuing optimizing the processing parameters when the prediction fineness and/or the prediction yield do not reach the preset range until the prediction fineness and the prediction yield obtained by inputting the processing parameters into the prediction model are both in the preset range,
according to the method and the device, the prediction fineness and the prediction yield corresponding to the processing parameters are obtained through the prediction model, the preset range of the yield can be obtained according to the obtained prediction yield, when the fineness meets the requirement and the yield is not in the preset range, the processing parameters are optimized through the preset optimization algorithm to obtain the optimized processing parameters, the optimized processing parameters are input into the prediction model to obtain the prediction fineness and the prediction yield, judgment is carried out again until the prediction fineness and the prediction yield are both in the preset range, so that the processing parameters can be adjusted through the prediction module and parameter optimization, the adjusted fineness reaches the standard and the yield is higher, the full-automatic adjustment of the processing parameters is realized, the efficiency and the accuracy are improved, and the stability of the yield is guaranteed.
In one embodiment, the preset range of the yield is set in a manner that:
acquiring a partial derivative of the predicted yield to the processing parameter;
and determining a preset range of the yield corresponding to the processing parameter according to the partial derivative.
In the embodiment of the present disclosure, the preset range of the yield is generally an allowable range of a locally optimal solution of the yield obtained by calculation. The preset range may be set by obtaining a preset range of yield according to the processing parameters and the obtained predicted yield. Acquiring partial derivative of predicted yield to processing parameter due to correlation between processing parameter and yieldAdding the squares of the partial derivatives, and judging whether the obtained value is within a range, in one example, the range can be a more appropriate range selected according to an actual scene, when the sum of the squares of the partial derivatives is within the range, the predicted yield at the moment can be considered to be locally optimal, and the production according to the processing parameters at the moment can ensure that the yield is maintained at a higher level; when the sum of the squares of the partial derivatives is not within this range, it is considered that the predicted yield at this time is not locally optimal, and the production yield is low according to the processing parameters at this time, and therefore, the processing parameters need to be optimally adjusted. In one example, the processing parameters may include the rotation speed of the classifying wheel and the system air volume, and the preset range of the output is calculated according to the formula (1), where ω is*For the rotation speed of the classifier wheel, Q*The air quantity of the system is the air quantity,to predict yield.
According to the embodiment of the disclosure, by acquiring the partial derivative of the predicted yield to the processing parameter and judging the predicted yield according to the partial derivative, whether the predicted yield is within the preset range at the moment is determined, so that a judgment condition is provided for adjustment and optimization of the subsequent processing parameter, and the adjustment accuracy and the stability of the capacity of the subsequent production can be improved.
In one embodiment, after the outputting the predicted fineness and the predicted yield of the material through the prediction model, the method further comprises:
determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is out of a first preset range of the target fineness;
and inputting the optimized processing parameters into the prediction model until the prediction fineness of the material output by the prediction model is within the first preset range.
In the embodiment of the disclosure, after the prediction fineness and the prediction yield output by the prediction model are obtained, it is first determined whether the prediction fineness is within a first preset range of the target fineness, where the first preset range is an error allowable range of the preset target fineness, and the fineness can be considered to reach the standard within the range. When the prediction fineness is beyond a first preset range of the target fineness, the prediction fineness does not meet the requirement, and the processing parameters need to be optimized and adjusted. Calculating and optimizing the processing parameters by using a preset optimization algorithm, inputting the obtained optimized processing parameters into a prediction model to obtain prediction fineness, judging whether the prediction fineness is within a first preset range at the moment, if so, continuously optimizing the processing parameters by using the optimization algorithm until the prediction fineness corresponding to the optimized processing parameters is within the first preset range, and at the moment, considering that the prediction fineness reaches the production requirement. And after the prediction fineness meets the requirement, the prediction yield can be continuously judged. In one example, a difference between the prediction fineness and the target fineness is calculatedJudging whether the production requirement is met, if | delta f | is less than or equal to epsilon2(0<ε2< 1), the requirement is met, otherwise, the requirement is not met.
According to the method and the device, after the result output by the prediction model is obtained, the prediction fineness is judged firstly, and the processing parameters are optimized under the condition that the prediction fineness does not meet the requirement until the prediction fineness corresponding to the optimized processing parameters meets the requirement, so that the fineness of the material processed by the grinder can reach the standard, the fineness adjustment efficiency and accuracy are improved, and the dependence on manpower is reduced.
In one embodiment, the determining the optimized machining parameters according to a preset optimization algorithm includes:
obtaining the product of the partial derivative of the prediction fineness on the processing parameter and a preset value;
and determining the sum of the product and the machining parameter as the optimized machining parameter.
In this disclosure, the method for determining the optimized processing parameter according to the preset optimization algorithm may include obtaining a partial derivative of the prediction fineness to the processing parameter, and multiplying the obtained partial derivative by a preset value to obtain a product, where a sum of the product and the processing parameter is the optimized processing parameter, where preset values corresponding to different processing parameters may also be different, and the preset value is usually a more appropriate adjustment parameter value preset according to an actual scene.
According to the method and the device, the optimized adjustment parameter can be obtained by predicting the product of the fineness and the partial derivative of the processing parameter and the preset value, the optimized parameter obtained through the algorithm can enable the processing parameter to be adjusted more accurately, the adjusting efficiency and accuracy are improved, and the processed fineness can meet the requirement.
In one embodiment, the determining the optimized processing parameters according to a preset optimization algorithm includes:
obtaining the product of the partial derivative of the predicted yield to the processing parameter and a preset value;
and determining the sum of the product and the machining parameter as the optimized machining parameter.
In this disclosure, the method for determining the optimized processing parameter according to the preset optimization algorithm may include first obtaining a partial derivative of the predicted yield with respect to the processing parameter, and multiplying the obtained partial derivative by a preset value to obtain a product, where a sum of the product and the processing parameter is the optimized processing parameter, where preset values corresponding to different processing parameters may also be different, and the preset value is usually a more appropriate adjustment parameter value preset according to an actual scene. In one example, when the processing parameters are the rotating speed of the grading wheel and the air volume of the system, the rotating speed of the grading wheel after optimization isThe optimized system air quantity isWherein α is a constant and 0<α<1; beta is a constant and 0<β<1; omega' is the rotation speed of the optimized rear fan wheel; and Q' is the optimized air volume.
According to the method and the device, the optimized adjustment parameters can be obtained by predicting the product of the yield and the partial derivative of the processing parameters and the preset value, the optimized parameters obtained through the algorithm can enable the processing parameters to be adjusted more accurately, the adjusting efficiency and accuracy are improved, and the yield after processing can be maintained at a higher level.
In one embodiment, as shown in fig. 3, the prediction model is configured to be obtained by training using the correspondence between the sample processing parameters and the prediction fineness and the prediction yield, and includes:
step S310, acquiring a set of sample processing parameters, wherein the set comprises a plurality of sample processing parameters marked with fineness labels and yield labels;
step S320, constructing a prediction model, wherein training parameters are set in the prediction model;
step S330, inputting the sample processing parameters into the fineness and yield prediction model to generate a prediction result;
and step S340, performing iterative adjustment on the prediction model based on the difference between the prediction result and the marked fineness label and yield label until the difference meets the preset requirement to obtain the prediction model.
In the embodiment of the present disclosure, a set of sample processing parameters is obtained, that is, a set containing processing parameters is prepared in advance, the processing parameters are labeled with corresponding fineness tags and yield tags, the fineness tags are generally the processed fineness corresponding to the processing parameters in actual production, and the yield tags are generally the processed yield corresponding to the processing parameters in actual processing. And constructing an initial model, wherein initial training parameters are set in the initial model. After the sample processing parameters are input into the initial model, an initial prediction result is output, the initial prediction result is compared with fineness labels and yield labels corresponding to the sample processing parameters, and initial training parameters between the initial models are adjusted according to the difference between the initial prediction fineness result and the fineness labels and the result between the initial prediction yield result and the yield labels. And performing iterative adjustment for multiple times according to the steps until the difference between the fineness output by the adjusted prediction model and the fineness label meets the preset requirement, and the difference between the output yield and the yield meets the preset requirement, and determining the prediction model at the moment as a final prediction model, wherein the preset requirement can be a smaller range around the label set according to the actual scene, and when the prediction result is in the smaller range of the label, the prediction result at the moment can be considered to be more accurate. The fineness and the yield of the processed materials of the crusher are influenced by the types of the materials, so that the corresponding fineness label and yield label on the sample processing parameter input by the same prediction model are generally the fineness and the yield obtained when the same crusher processes the same material according to the processing parameter when the prediction model is trained. In one example, the sample processing parameters are normalized and then input into the prediction model for training, which enables more efficient model training.
In one example, taking a deep neural network with 2 hidden layers as an example, the number of neurons in the first hidden layer is N1The number of neurons in the hidden layer in the second layer is N1. For convenience of description, let the input layer input data be [ x ]1,x2]=[ω*,Q*]. Wherein, ω is*For standardizing the rotational speed and Q of the fan wheel after treatment*The air volume after the standardized treatment.
The output value of each neuron of the layer 1 hidden layer is:
y1i=tanh(∑j=1...2W1ijxj+W1i0) (2)
where tanh () is the activation function,W1ijweights for input layer jth neuron to layer 1 hidden layer ith neuron; w1i0For inputting layer constant parameters to layer 1Hiding the weight of the ith neuron of the layer; y is1iAnd hiding the output value of the ith neuron of the layer 1. The activation function here may be various, and is not limited to tanh ().
Similarly, the output values of the neurons of the hidden layer 2 are as follows:
wherein ReLU () is an activation function, ReLU (x) max (0, x); w2ijWeighting jth neuron of a layer 1 hidden layer to ith neuron of a layer 2 hidden layer; w2i0Weights of the jth neuron from the layer 1 hidden layer constant parameter to the layer 2 hidden layer constant parameter; y is2iAnd hiding the output value of the ith neuron of the layer 2. The activation function here may be various, and is not limited to the ReLU ().
The predicted values of the productivity and the grain fineness number of the output layer are as follows:
wherein ReLU () is an activation function, ReLU (x) max (0, x); wO1jWeighting the jth neuron of the layer 2 shadow layer to the 1 st neuron of the output layer; wO2jThe weight from the jth neuron of the shadow layer 2 to the 2 nd neuron of the output layer is calculated; wO10Weights from layer 2 occlusion layer normal parameters to output layer 1 st neurons; wO20Weights from layer 2 occlusion layer normal parameters to output layer 2 neurons;is a predicted yield value;is prepared byAnd measuring the particle fineness value. The activation function here may be various, and is not limited to the ReLU ().
According to the embodiment of the disclosure, an initial prediction model is constructed, and the initial prediction model is trained through sample processing parameters, fineness labels and yield labels to obtain the prediction model. The prediction model obtained by the embodiment of the disclosure can accurately predict the fineness and the yield of the article, and ensure the accuracy of subsequent parameter adjustment.
In one embodiment, the inputting the processing parameters into a prediction model, and outputting the predicted fineness and the predicted yield of the material through the prediction model comprises:
carrying out standardization processing on the processing parameters to obtain processed processing parameters;
and inputting the processed processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material through the prediction model.
In the embodiment of the disclosure, after the processing parameters of the pulverizer are obtained, the processing parameters are subjected to standardization processing to obtain the processed processing parameters. And inputting the standardized processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material by the prediction model. In one example, the data preprocessing module normalizes the classification wheel speed and the system air volume. The normalization processing function is:
wherein x is*For the data after normalization, x is the raw data, μ is the mean of the historical data used for model training, and σ is the standard deviation of the historical data used for model training. Taking the rotation speed ω of the motor of the grading wheel as an example, assuming that there are N groups of data used for training the model, the converted data is:
wherein:
after processing, the data preprocessing module is used for processing the standardized rotating speed omega of the fan wheel*Sum air quantity Q*And inputting the data into a prediction model to obtain the prediction fineness and the prediction yield of the output material.
According to the embodiment of the disclosure, through carrying out standardization processing on the processing parameters of the crusher, the input parameters of different units or orders of magnitude can be subjected to weighting and adaptive to the prediction model, the accuracy of the output result of the prediction model is improved, and the efficiency of searching the optimal parameters is improved.
In one embodiment, after the step of outputting the predicted fineness until the predicted model output is within the first preset range and the output predicted yield is within a preset range of the yield corresponding to the optimized processing parameter, the method further comprises:
obtaining optimized processing parameters, wherein the prediction fineness corresponding to the processing parameters is within the first preset range and the corresponding prediction yield is within the preset range of the yield corresponding to the processing parameters;
and processing the material according to the optimized processing parameters.
In the embodiment of the disclosure, the optimized processing parameters are obtained, the prediction fineness corresponding to the optimized processing parameters at this time is within a first preset range of the target fineness, and the prediction yield is within a preset range of the yield corresponding to the processing parameters at this time, that is, the processing parameters at this time meet the requirement of the crushing task, and the yield can be maintained at a higher level. And controlling the pulverizer to process the material according to the optimized processing parameters to obtain the processed material. In one example, whether the fineness of the processed material is within a preset range is judged, if so, production is continued according to the current parameters, and if not, the processing parameters are adjusted according to the steps of the processing parameter adjusting method. Wherein, whether the fineness of the processed material is in place or not is judgedWithin a predetermined range, the sampling detection may be performed periodically. In one example, the fineness of the processed material is typically obtained by an on-line particle size monitoring system, which may be based on a variety of principles, such as on a laser particle size distribution instrument, on machine vision principles, and the like. According to actual production needs, the particle size online monitoring system can be installed behind a grading system in the pulverizer, and can also be installed behind subsequent screening equipment. In one example, the results given by a particle size distribution instrument tend to be a probability density distribution over the full size range; in different industries, fineness is characterized in different ways, and a conversion is needed among the different industries. Taking the ultramicro crushing operation in the feed processing industry as an example, the requirement of a certain feed product on the fineness of the crushed material is generally represented by a 80-mesh sieve ratio, such as: the 80-mesh passing rate is 95% +/-0.5%. A pore size of 0.18mm for 80 mesh, then:the granularity on-line monitoring system can feed back the granularity distribution of the crushed material to the fineness control system according to the set sampling frequency; the control system converts the particle size distribution to an 80 mesh screen size and then compares it to a fineness standard.
According to the embodiment of the disclosure, the material is processed according to the optimized processing parameters, so that the processed fineness is within the preset range of the target fineness and the yield reaches the local optimum, and the yield is guaranteed to be stable while accurate crushing processing is realized.
FIG. 4 is a flow diagram illustrating a method for adjusting mill process parameters according to an exemplary embodiment, and referring to FIG. 4, after the program is initiated, the model selection module selects a predictive model matching the material type based on the material type currently being produced; the data preprocessing module is used for carrying out standardization processing on the current rotating speed of the grading wheel and the system air volume; inputting the rotational speed of the treated grading wheel and the system air volume into a prediction model, and outputting prediction fineness and prediction yield by the model; and judging whether the prediction fineness is within a preset range, optimizing the processing parameters under the condition that the prediction fineness is outside the preset range, inputting the optimized processing parameters into the prediction model again, and judging whether the output prediction fineness is within the preset range. When the output prediction fineness is within a preset range of the target fineness, judging whether the prediction yield is within a preset range of the yield corresponding to the processing parameter, and when the prediction yield is outside the preset range, optimizing the processing parameter of the crusher until the prediction fineness is within the preset range of the target fineness and the prediction yield is within the preset range of the yield corresponding to the processing parameter; and producing according to the optimized processing parameters, judging whether the fineness of the optimized processed product is within a preset range, if so, continuing processing according to the current parameters, and if not, repeating the steps of the processing parameter adjusting method until the pulverizer stops producing.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in the figures may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or at least partially in sequence with other steps or other steps.
Based on the same inventive concept, the embodiment of the disclosure also provides a device for adjusting the processing parameters of the crusher, which is used for realizing the method for adjusting the processing parameters of the crusher. The solution of the problem provided by the device is similar to the solution described in the above method, so the specific limitations in the embodiment of the adjusting device for one or more parameters of the crusher provided below can be referred to the limitations on the adjusting method for the parameters of the crusher, and are not described herein again.
In one embodiment, as shown in fig. 5, there is provided a device for adjusting processing parameters of a pulverizer, the device being applied to a pulverizer including a classification wheel, comprising:
the acquisition module is used for acquiring processing parameters of the crusher and target fineness of material processing;
the prediction module is used for inputting the processing parameters into a prediction model and outputting the prediction fineness and the prediction yield of the material through the prediction model, wherein the prediction model is set to be obtained by utilizing the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield in a training mode;
the optimization module is used for determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is within a first preset range of the target fineness and the prediction yield is outside a preset range of yield;
and the adjusting module is used for inputting the optimized processing parameters into the prediction model until the prediction fineness output by the prediction model is within the first preset range and the output predicted yield is within the preset range of the yield corresponding to the optimized processing parameters.
In one embodiment, the module for setting the preset range of the yield comprises:
the acquisition module is used for acquiring the partial derivative of the predicted yield to the processing parameter;
and the determining module is used for determining the preset range of the yield corresponding to the processing parameter according to the partial derivative.
In one embodiment, the prediction module is followed by:
the determining module is used for determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is out of a first preset range of the target fineness;
and the input module is used for inputting the optimized processing parameters into the prediction model until the prediction fineness of the material output by the prediction model is within the first preset range.
In one embodiment, the optimization module includes:
the obtaining module is used for obtaining the product of the partial derivative of the prediction fineness on the processing parameter and a preset value;
and the determining module is used for determining that the sum of the product and the machining parameter is the optimized machining parameter.
In one embodiment, the optimization module includes:
the acquisition module is used for acquiring the product of the partial derivative of the predicted yield to the processing parameter and a preset value;
and the determining module is used for determining that the sum of the product and the machining parameter is the optimized machining parameter.
In one embodiment, the prediction model is set to be obtained by training using the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield, and comprises the following steps:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a set of sample processing parameters, and the set comprises a plurality of sample processing parameters marked with fineness labels and yield labels;
the construction module is used for constructing a prediction model, and training parameters are set in the prediction model;
the generating module is used for inputting the sample processing parameters to the fineness and yield prediction model to generate a prediction result;
and the iteration module is used for iteratively adjusting the prediction model based on the difference between the prediction result and the marked fineness label and the marked yield label until the difference meets the preset requirement to obtain the prediction model.
In one embodiment, the prediction module comprises:
the processing module is used for carrying out standardized processing on the processing parameters to obtain processed processing parameters;
and the input module is used for inputting the processed processing parameters into a prediction model and outputting the prediction fineness and the prediction yield of the material through the prediction model.
In one embodiment, the adjusting module is followed by:
an obtaining module, configured to obtain the optimized processing parameter, where a prediction fineness corresponding to the processing parameter is within the first preset range and a corresponding predicted yield is within a preset range of a yield corresponding to the processing parameter;
and the processing module is used for processing the material according to the optimized processing parameters.
The modules in the adjusting device for the processing parameters of the pulverizer can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as the processing parameters of the crusher. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of adjusting a shredder processing parameter.
Those skilled in the art will appreciate that the configuration shown in fig. 6 is a block diagram of only a portion of the configuration associated with embodiments of the present disclosure, and does not constitute a limitation of the computing devices to which embodiments of the present disclosure may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, carries out the steps in the method embodiments described above.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) related to the embodiments of the present disclosure are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, databases, or other media used in the embodiments provided by the embodiments of the disclosure may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the various embodiments provided by the embodiments of the present disclosure may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided in the disclosure may be general processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., without being limited thereto.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The embodiments described above only represent several implementation manners of the embodiments of the present disclosure, and the descriptions are specific and detailed, but should not be construed as limiting the scope of the claims of the embodiments of the present disclosure. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the embodiments of the disclosure, and these changes and modifications are all within the scope of the embodiments of the disclosure. Therefore, the protection scope of the embodiments of the present disclosure should be subject to the appended claims.
Claims (12)
1. A method for adjusting processing parameters of a pulverizer, said method being applied to a pulverizer, said pulverizer including a classification wheel, comprising:
acquiring processing parameters of a crusher and target fineness of material processing;
inputting the processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material through the prediction model, wherein the prediction model is set to be obtained by utilizing the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield through training;
determining optimized processing parameters according to a preset optimization algorithm under the conditions that the prediction fineness is within a first preset range of the target fineness and the prediction yield is outside a preset range of yield;
and inputting the optimized processing parameters into the prediction model until the prediction fineness output by the prediction model is within the first preset range and the output predicted yield is within the preset range of the yield corresponding to the optimized processing parameters.
2. The method of claim 1, wherein the predetermined range of production rates is set by:
acquiring a partial derivative of the predicted yield to the processing parameter;
and determining a preset range of the yield corresponding to the processing parameter according to the partial derivative.
3. The method of claim 1, wherein after said outputting the predicted fineness and predicted yield of the material via the predictive model, further comprising:
determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is out of a first preset range of the target fineness;
and inputting the optimized processing parameters into the prediction model until the prediction fineness of the material output by the prediction model is within the first preset range.
4. The method of claim 3, wherein determining the optimized machining parameters according to a predetermined optimization algorithm comprises:
obtaining the product of the partial derivative of the prediction fineness on the processing parameter and a preset value;
and determining the sum of the product and the machining parameter as the optimized machining parameter.
5. The method of claim 1, wherein determining the optimized machining parameters according to a predetermined optimization algorithm comprises:
obtaining the product of the partial derivative of the predicted yield to the processing parameter and a preset value;
and determining the sum of the product and the machining parameter as the optimized machining parameter.
6. The method according to claim 1, wherein the prediction model is configured to be obtained by training using a corresponding relationship between sample processing parameters and prediction fineness and prediction yield, and comprises:
acquiring a set of sample processing parameters, wherein the set comprises a plurality of sample processing parameters marked with fineness labels and yield labels;
constructing a prediction model, wherein training parameters are set in the prediction model;
inputting the sample processing parameters into the fineness and yield prediction model to generate a prediction result;
and iteratively adjusting the prediction model based on the difference between the prediction result and the labeled fineness label and the labeled yield label until the difference meets the preset requirement to obtain the prediction model.
7. The method of claim 1, wherein the inputting the processing parameters into a predictive model, outputting the predicted fineness and predicted yield of the material via the predictive model, comprises:
carrying out standardization processing on the processing parameters to obtain processed processing parameters;
and inputting the processed processing parameters into a prediction model, and outputting the prediction fineness and the prediction yield of the material through the prediction model.
8. The method as claimed in claim 1, wherein after the step of outputting the predicted yield within the first predetermined range and the predicted yield corresponding to the optimized processing parameter, the method further comprises:
obtaining optimized processing parameters, wherein the prediction fineness corresponding to the processing parameters is within the first preset range and the corresponding prediction yield is within the preset range of the yield corresponding to the processing parameters;
and processing the material according to the optimized processing parameters.
9. A device for regulating the processing parameters of a pulverizer, said device being applied to a pulverizer comprising a classifying wheel, comprising:
the acquisition module is used for acquiring the processing parameters of the crusher and the target fineness of material processing;
the prediction module is used for inputting the processing parameters into a prediction model and outputting the prediction fineness and the prediction yield of the material through the prediction model, wherein the prediction model is set to be obtained by utilizing the corresponding relation between the sample processing parameters and the prediction fineness and the prediction yield through training;
the optimization module is used for determining optimized processing parameters according to a preset optimization algorithm under the condition that the prediction fineness is within a first preset range of the target fineness and the prediction yield is outside a preset range of yield;
and the adjusting module is used for inputting the optimized processing parameters into the prediction model until the prediction fineness output by the prediction model is within the first preset range and the output predicted yield is within the preset range of the yield corresponding to the optimized processing parameters.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of adjusting a shredder processing parameter of any of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for adjusting a milling parameter according to any one of claims 1 to 8.
12. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of adjusting the processing parameters of a pulverizer as defined in any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210210313.4A CN114733640B (en) | 2022-03-03 | 2022-03-03 | Method and device for adjusting processing parameters of pulverizer and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210210313.4A CN114733640B (en) | 2022-03-03 | 2022-03-03 | Method and device for adjusting processing parameters of pulverizer and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114733640A true CN114733640A (en) | 2022-07-12 |
CN114733640B CN114733640B (en) | 2023-09-12 |
Family
ID=82275296
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210210313.4A Active CN114733640B (en) | 2022-03-03 | 2022-03-03 | Method and device for adjusting processing parameters of pulverizer and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114733640B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102151605A (en) * | 2011-03-17 | 2011-08-17 | 浙江大学 | Advanced control method and system for vertical mill based on model identification and predictive control |
CN106391286A (en) * | 2016-08-31 | 2017-02-15 | 珠海市华远自动化科技有限公司 | System and method for controlling fineness of pulverized coal |
DE102015114891A1 (en) * | 2015-09-04 | 2017-03-09 | Turbocut Jopp Gmbh | Meat grinder with housing, at least one conveyor and at least one cutting attachment and cutting attachment for such a meat grinder |
WO2019114421A1 (en) * | 2017-12-15 | 2019-06-20 | 阿里巴巴集团控股有限公司 | Model integration method and device |
CN110689176A (en) * | 2019-09-17 | 2020-01-14 | 国网湖南省电力有限公司 | Method, system and medium for optimizing output measurement of double-inlet and double-outlet coal mill |
JP2020025915A (en) * | 2018-08-10 | 2020-02-20 | 日立金属株式会社 | Pulverization control method |
CN110918244A (en) * | 2019-12-23 | 2020-03-27 | 杭州和利时自动化有限公司 | Control method and device of cement grinding mill system and related equipment |
CN111617876A (en) * | 2020-04-10 | 2020-09-04 | 杭州电子科技大学 | Method for optimizing online comprehensive operation of coal mill |
CN112163350A (en) * | 2020-11-02 | 2021-01-01 | 国能黄金埠发电有限公司 | Double-model real-time online soft measurement system and method for coal powder fineness of powder making system |
CN112275439A (en) * | 2020-10-14 | 2021-01-29 | 济南大学 | Cement raw material vertical mill differential pressure soft measurement modeling method, storage medium and system |
WO2021143067A1 (en) * | 2020-05-28 | 2021-07-22 | 平安科技(深圳)有限公司 | Method and apparatus for predicting workpiece quality, and computer device |
CN113457832A (en) * | 2021-07-02 | 2021-10-01 | 湖南杉杉能源科技有限公司 | Material crushing granularity control system and control method and application thereof |
-
2022
- 2022-03-03 CN CN202210210313.4A patent/CN114733640B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102151605A (en) * | 2011-03-17 | 2011-08-17 | 浙江大学 | Advanced control method and system for vertical mill based on model identification and predictive control |
DE102015114891A1 (en) * | 2015-09-04 | 2017-03-09 | Turbocut Jopp Gmbh | Meat grinder with housing, at least one conveyor and at least one cutting attachment and cutting attachment for such a meat grinder |
CN106391286A (en) * | 2016-08-31 | 2017-02-15 | 珠海市华远自动化科技有限公司 | System and method for controlling fineness of pulverized coal |
WO2019114421A1 (en) * | 2017-12-15 | 2019-06-20 | 阿里巴巴集团控股有限公司 | Model integration method and device |
JP2020025915A (en) * | 2018-08-10 | 2020-02-20 | 日立金属株式会社 | Pulverization control method |
CN110689176A (en) * | 2019-09-17 | 2020-01-14 | 国网湖南省电力有限公司 | Method, system and medium for optimizing output measurement of double-inlet and double-outlet coal mill |
CN110918244A (en) * | 2019-12-23 | 2020-03-27 | 杭州和利时自动化有限公司 | Control method and device of cement grinding mill system and related equipment |
CN111617876A (en) * | 2020-04-10 | 2020-09-04 | 杭州电子科技大学 | Method for optimizing online comprehensive operation of coal mill |
WO2021143067A1 (en) * | 2020-05-28 | 2021-07-22 | 平安科技(深圳)有限公司 | Method and apparatus for predicting workpiece quality, and computer device |
CN112275439A (en) * | 2020-10-14 | 2021-01-29 | 济南大学 | Cement raw material vertical mill differential pressure soft measurement modeling method, storage medium and system |
CN112163350A (en) * | 2020-11-02 | 2021-01-01 | 国能黄金埠发电有限公司 | Double-model real-time online soft measurement system and method for coal powder fineness of powder making system |
CN113457832A (en) * | 2021-07-02 | 2021-10-01 | 湖南杉杉能源科技有限公司 | Material crushing granularity control system and control method and application thereof |
Also Published As
Publication number | Publication date |
---|---|
CN114733640B (en) | 2023-09-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110472817B (en) | XGboost integrated credit evaluation system and method combined with deep neural network | |
Binsaeid et al. | Machine ensemble approach for simultaneous detection of transient and gradual abnormalities in end milling using multisensor fusion | |
Khatri et al. | Wheat seed classification: utilizing ensemble machine learning approach | |
Shastri et al. | Stock price prediction using artificial neural model: an application of big data | |
Kishore et al. | Computer‐aided multiclass classification of corn from corn images integrating deep feature extraction | |
CN112053223A (en) | Internet financial fraud behavior detection method based on GA-SVM algorithm | |
Popordanoska et al. | A consistent and differentiable lp canonical calibration error estimator | |
Pandey et al. | Gold and diamond price prediction using enhanced ensemble learning | |
Hadju et al. | Sentiment analysis of indonesian e-commerce product reviews using support vector machine based term frequency inverse document frequency | |
Asha et al. | An efficient hybrid machine learning classifier for rainfall prediction | |
CN114733640B (en) | Method and device for adjusting processing parameters of pulverizer and computer equipment | |
Rahajoe | Forecasting feature selection based on single exponential smoothing using Wrapper method | |
CN114377842B (en) | Material fineness adjusting method and device, computer equipment and storage medium | |
Verianto et al. | Artificial Neural Network Model with PSO as a Learning Method to Predict Movement of the Rupiah Exchange Rate against the US Dollar | |
Tan et al. | Using Classification with K-means Clustering to Investigate Transaction Anomaly | |
Nurhasanah et al. | Backpropagation neural network for predict sugarcane stock availability | |
Razdan et al. | A multi-layer feed forward network intrusion detection system using individual component optimization methodology for cloud computing | |
Elfar et al. | Accelerating Logical Analysis of Data Using an Ensemble-Based Technique. | |
Shikalgar et al. | Optimized auto encoder on high dimensional big data reduction: an analytical approach | |
He et al. | PRAM: A novel approach for predicting riskless state of commodity future arbitrages with machine learning techniques | |
Dutta et al. | Outlier detection in additive manufacturing using novel machine learning algorithm | |
Harahap et al. | Using support vector machines for classification datamining on international trade price index data | |
CN115128950B (en) | Crushing and screening control method and device, electronic equipment and storage medium | |
Bazzana et al. | Machine learning techniques for default prediction: an application to small Italian companies | |
CN114308367B (en) | Material fineness adjusting method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |