Screen penetration rate optimization method for drum screen

Abstract

The invention relates to a drum screen penetration rate optimization method, belongs to the technical field of penetration rate optimization, and solves the problems that in the prior art, a penetration rate prediction method is low in accuracy and high in calculation cost, and it is difficult to obtain the optimal penetration rate by adjusting working condition parameters. Constructing a sieve penetration rate sample data set based on the drum sieve discrete element model and the particle factory space model; training a target machine learning model based on the through screening rate sample data set to obtain a through screening rate prediction model; obtaining a to-be-tested parameter sample, and inputting the to-be-tested parameter sample into the through screening rate prediction model to obtain through screening rates of different particle sizes corresponding to the to-be-tested parameter sample; and if the sieve penetration rate accords with an expected target, taking the to-be-tested parameter sample as a control parameter of the drum screen, and if the sieve penetration rate does not accord with the expected target, optimizing the to-be-tested parameter sample by adopting a particle swarm algorithm, and taking the optimized parameter as the control parameter of the drum screen, thereby improving the sieve penetration rate of the to-be-tested vibrating screen. The accurate and efficient sieve penetration rate prediction and optimization method is realized.

Description

Technical Field

[0001] The invention relates to the technical field of screening rate optimization, and in particular to a method for optimizing the screening rate of a drum screen. Background Art

[0002] The screening rate (i.e. the rate at which particles smaller than the sieve holes are screened out) is an important indicator for evaluating the effectiveness of the drum screen in separating particulate materials. The screening rate is affected by many factors, including the drum speed, the drum installation angle, the time the screened material stays inside the drum screen, the ratio of the drum length to the drum diameter, the nature of the feed, etc., and there is a nonlinear relationship between the various factors.

[0003] In the prior art, the prediction research on the screening behavior of drum screens mainly includes: traditional probabilistic screening model, dynamic screening model and discrete element numerical simulation. However, the traditional probabilistic screening model is based on idealized assumptions, ignoring complex behaviors such as collision, stacking and rolling between particles, unable to capture the movement trajectory of particles, and does not consider the influence of particle shape and particle size distribution, making it difficult to describe the dynamic evolution of the screening process; although the dynamic screening model analyzes the force and movement of particles based on the principles of physical mechanics, the description of the interaction between particles is relatively simplified, and the calculation complexity is high, making it difficult to simulate large-scale particle systems, resulting in insufficient description of the nonlinear dynamic characteristics of particles; discrete element numerical simulation (DEM), as a refined modeling method, can better describe the movement behavior of particles in the drum screen, but the calculation cost is huge, and the universality and accuracy of the simulation results still need to be further verified and improved.

[0004] The neural network model has powerful nonlinear mapping and self-learning capabilities, can extract useful features from a large amount of data, and establish a complex relationship between input and output. Therefore, it is necessary to combine the advantages of the neural network model and DEM simulation to provide an accurate and efficient method for predicting and optimizing the screening rate, so as to more comprehensively reveal the screening mechanism of the drum screen. Summary of the invention

[0005] In view of the above analysis, an embodiment of the present invention aims to provide a method for optimizing the screening rate of a drum screen, so as to solve the problems of low accuracy, high calculation cost and difficulty in obtaining the optimal screening rate by adjusting the operating parameters of the existing screening rate prediction method.

[0006] An embodiment of the present invention provides a method for optimizing the screening rate of a drum screen, comprising:

[0007] Construct a discrete element model of the drum screen and a spatial model of the pellet plant;

[0008] Constructing a screening rate sample data set based on the drum screen discrete element model and the particle factory spatial model, the screening rate sample data set includes: particle size, feeding rate of each particle, drum screen inclination angle, drum screen mesh speed, drum screen internal component speed, and screening rate;

[0009] Training a target machine learning model based on the screening rate sample data set to obtain a screening rate prediction model;

[0010] Acquire a parameter sample to be measured, and input the parameter sample to be measured into the screening rate prediction model to obtain the screening rate of different particle sizes corresponding to the parameter sample to be measured;

[0011] If the screening rate meets the expected target, the parameter sample to be tested is used as the control parameter of the drum screen; if it does not meet the expected target, the particle swarm algorithm is used to optimize the parameter sample to be tested, and the optimized parameter is used as the control parameter of the drum screen, thereby improving the screening rate of the vibrating screen to be tested;

[0012] During the optimization process, the input parameters represented by each particle are input into the screening rate prediction model to obtain the screening rate corresponding to the particle, and the fitness function is calculated based on the screening rate of the particle and the corresponding drum screen inclination angle, drum screen mesh speed, and drum screen built-in component speed.

[0013] Based on the further improvement of the above method, the construction of the drum screen discrete element model and the particle factory space model includes: constructing the drum screen discrete element model, the drum screen discrete element model includes: a cylindrical screen and built-in components, and dividing the cylindrical screen discrete element model to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length; constructing the particle factory space model, the particle factory space model is placed at the feed end of the drum screen discrete element model and is located inside the cylindrical screen discrete element model, and the particle generation method and particle parameters of the particle factory space model are set based on business needs.

[0014] Based on the further improvement of the above method, the cylindrical screen discrete element model is divided to obtain multiple sub-cylindrical screen discrete element models with the same screen length, including: obtaining the drum screen length of the cylindrical screen discrete element model, and the particle factory space model length of the particle factory space model along the length direction of the drum screen, and obtaining the available drum screen length based on the drum screen length and the particle factory space model length along the length direction of the drum screen; dividing the cylindrical screen discrete element model based on the available drum screen length and the preset length, thereby obtaining multiple sub-cylindrical screen discrete element models with the same screen length.

[0015] Based on the further improvement of the above method, the cylindrical screen discrete element model is divided based on the available drum screen length and the preset length, so as to obtain multiple sub-cylindrical screen discrete element models with the same screen length, including:

[0016] A1: setting a segmentation starting point, the segmentation starting point is located on the axis of the cylindrical screen discrete element model, and the shortest distance from the segmentation starting point to the discharge end of the cylindrical screen discrete element model is equal to the available drum screen length;

[0017] A2: Taking the segmentation starting point as the division starting point and the preset length as the step length, a plurality of segmentation points are obtained on the axis, and the cylindrical screen discrete element model is divided by a plane passing through the segmentation points and perpendicular to the axis to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length;

[0018] A3: offset the segmentation starting point by a preset distance toward the discharge end, and use the offset point as a new segmentation starting point, and determine whether the current offset times exceed the preset movement times. If not, return to A2; if exceeded, use the result of each division in step A2 as a sub-cylindrical screen discrete element model.

[0019] Based on the further improvement of the above method, the method of constructing a screening rate sample data set based on the drum screen discrete element model and the particle factory space model includes:

[0020] B 1: Based on the drum screen discrete element model and the particle factory spatial model, the drum screen screening process is simulated, and the simulation results are obtained, wherein the simulation results include the feeding rate of various particles corresponding to each time step in the simulation process, the spatial position of each particle, the drum screen inclination angle, the drum screen mesh speed, and the drum screen internal component speed;

[0021] B2: calculating the screening rate of different particle sizes corresponding to each sub-cylindrical screen discrete element model based on the spatial position of each particle;

[0022] B3: The feeding rate of various particles, the inclination angle of the drum screen, the rotation speed of the drum screen mesh, the rotation speed of the drum screen internal components and the screening rate of various particles at each time step corresponding to each sub-cylindrical screen discrete element model are taken as a sample in the screening rate sample data set corresponding to the screen length;

[0023] B4: Determine whether the amount of sample data currently generated meets the preset quantity requirement. If so, stop generating. If not, adjust the current particle generation method and particle parameters based on business needs and return to B1.

[0024] Based on the further improvement of the above method, the screening rate prediction model is a neural network model, and the Harris Eagle optimization algorithm is used to optimize the number of neurons, Dropout coefficient and batch size of the neural network model, and the optimization results are used as the initial parameters of the neural network model.

[0025] Based on the further improvement of the above method, the particle swarm algorithm is used to optimize the parameter sample to be measured, and the optimized parameters are used as the control parameters of the drum screen, including:

[0026] C1: Initialize the particle group, select sample data that meets the expected target from the screening rate sample data set as the first sample data set, take the feed rate of various particles, the drum screen inclination angle, the drum screen mesh speed, and the drum screen built-in component speed of each data in the first sample data set as a particle, take the feed rate of various particles in the parameter sample to be measured, the drum screen inclination angle, the drum screen mesh speed, and the drum screen built-in component speed as a particle, and judge whether the total number of current particles meets the preset number. If yes, execute C3, if not, execute C2;

[0027] C2: Counting the range of each parameter in the first sample data set, and randomly taking values ​​within the range of each parameter based on a random generation algorithm, thereby generating multiple particles, so that the total number of particles meets the preset number requirement;

[0028] C3: Calculate the fitness function of each particle to update the individual optimal and global optimal values, and determine whether the end condition is met. If so, execute C5; if not, execute C4.

[0029] C4: Update the speed and position of each particle and return to C3;

[0030] C5: Output the optimal position, and the particle group parameters corresponding to the optimal position are the control parameters of the drum screen.

[0031] Based on the further improvement of the above method, the fitness function is calculated based on the particle penetration rate and the drum screen inclination angle, drum screen mesh speed, and drum screen built-in component speed corresponding to the particle, including:

[0032]

[0033] Among them, y′ is the predicted screening rate corresponding to the current particle, is the expected target, α′, ω 1 ′ω 2 ′ is the drum screen inclination angle, drum screen mesh speed, and drum screen internal component speed corresponding to the current particle, α, ω 1 ,ω2 are the drum screen inclination angle, the drum screen mesh speed, and the drum screen internal component speed of the parameter sample to be measured, and a, b, c, and d are constants.

[0034] Based on the further improvement of the above method, the screening rate of different particle sizes corresponding to each sub-cylindrical screen discrete element model is calculated based on the spatial position of each particle, including: for the first sub-cylindrical screen discrete element model close to the feed end, the screening rate of various particle sizes is calculated based on the feed rate of various particles generated in the particle factory spatial model, the inclination angle of the drum screen, the rotation speed of the drum screen mesh, the rotation speed of the built-in components of the drum screen, and the mass of various sizes of particles below the first sub-cylindrical screen discrete element model; for other sub-cylindrical screen discrete element models, the particle size at the discharge end of the previous sub-cylindrical screen discrete element model, the feed rate of various particles, the inclination angle of the drum screen, the rotation speed of the drum screen mesh, and the rotation speed of the built-in components of the drum screen are used as the feed parameters of the current sub-cylindrical screen discrete element model, and the screening rate of various particle sizes is calculated based on the feed parameters of the sub-cylindrical screen discrete element model and the mass of various sizes of particles below the sub-cylindrical screen discrete element model.

[0035] Based on the further improvement of the above method, the simulation result refers to the particle size corresponding to each sub-cylindrical screen discrete element model in each time step, the feeding rate of various particles, the spatial position of each particle, the inclination angle of the drum screen, the screen speed of the drum screen, and the speed of the built-in components of the drum screen after the screening process reaches a steady state; the steady state means that the sum of the mass of particles passing through the discrete element model of the sub-cylindrical screen and the particle discharge rate at the discharge end per unit time is equal to the particle feeding rate.

[0036] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0037] 1. The present invention provides a method for optimizing the screening rate of a drum screen. After obtaining the screening rates of particles of different particle sizes according to the current operating parameters, a judgment is made based on the expected target. If the target requirements are not met, the current operating parameters are further optimized through the particle swarm algorithm to obtain operating parameters that meet the expected target, thereby guiding users to design operating parameters that meet the expected screening rate, saving process costs and improving design efficiency.

[0038] 2. The present invention provides a method for optimizing the screening rate of a drum screen. A screening efficiency prediction model is constructed based on a machine learning model, which can more flexibly meet business needs. Compared with the traditional probabilistic screening model, dynamic screening model and discrete element numerical simulation in the prior art, the method proposed in the present invention has higher prediction accuracy and calculation efficiency, strong real-time performance and can adapt to various complex working conditions.

[0039] 3. The present invention provides a method for optimizing the screening rate of a drum screen. The drum screen discrete element model is divided based on a preset length to obtain multiple sub-sieve discrete element models of the same length. For each operating condition simulation of the particle factory space model, after steady state, each time step can generate multiple sets of simulation data corresponding to the operating condition and the preset length of the screen. Compared with the prior art that each time step can only generate a set of simulation data corresponding to the operating condition and the preset length, the present invention is more efficient in constructing a screening efficiency sample data set; in addition, the sub-sieve discrete element models are arranged continuously, and the output of the previous sub-sieve discrete element model is used as the input of the next sub-sieve discrete element model. Compared with the prior art that only obtains sample data for a fixed length of screen model, the screening sample data obtained by simulating each sub-sieve discrete element model in the present invention is closer to the actual vibrating screen screening process.

[0040] In the present invention, the above-mentioned technical solutions can also be combined with each other to achieve more preferred combination solutions. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can become obvious from the description, or can be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are only used for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. In the entire drawings, the same reference symbols represent the same components;

[0042] Figure 1 This is an example diagram of a method for optimizing the screening rate of a drum screen in an embodiment of the present invention;

[0043] Figure 2 This is an example diagram of a discrete element model of a drum screen in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0045] A specific embodiment of the present invention discloses a method for optimizing the screening rate of a drum screen, such as Figure 1 As shown, including:

[0046] S1: Construct the discrete element model of the drum screen and the spatial model of the pellet plant, including:

[0047] S11: constructing a drum screen discrete element model, the drum screen discrete element model comprising: a cylindrical screen and built-in components, and dividing the cylindrical screen discrete element model to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length.

[0048] For example, any modeling software can be used to establish the drum screen discrete element model. Furthermore, considering factors such as computational efficiency and resource consumption, the present invention will remove unnecessary details and complex structures in the drum screen discrete element model, and finally simplify the drum screen discrete element model based on business needs. Figure 2 The model shown is composed of a drum screen discrete element model and a built-in component discrete element model. Exemplarily, the drum screen discrete element model established in the present invention has a length and a diameter of 600 mm and 200 mm respectively, and the cylindrical screen has a 6 mm circular hole.

[0049] It is defined in the present invention that the left side of the drum screen discrete element model is the feed end.

[0050] After obtaining the drum screen discrete element model, the screen discrete element model can be divided based on the preset screen length specified by business needs to obtain multiple sub-screen discrete element models with the same screen length. The present invention does not limit the preset screen length, and the value of the preset screen length can be set according to business needs or actual needs. For example, the preset screen length can be set to 100 mm.

[0051] The step of dividing the cylindrical screen discrete element model to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length includes:

[0052] Obtaining the drum screen length of the cylindrical screen discrete element model and the particle factory space model length of the particle factory space model along the length direction of the drum screen, and obtaining the available drum screen length based on the drum screen length and the particle factory space model length along the length direction of the drum screen;

[0053] The cylindrical screen discrete element model is divided based on the available drum screen length and the preset length, thereby obtaining a plurality of sub-cylindrical screen discrete element models with the same screen length, including:

[0054] A1: setting a segmentation starting point, the segmentation starting point is located on the axis of the cylindrical screen discrete element model, and the shortest distance from the segmentation starting point to the discharge end of the cylindrical screen discrete element model is equal to the available drum screen length;

[0055] A2: Taking the segmentation starting point as the division starting point and the preset length as the step length, a plurality of segmentation points are obtained on the axis, and the cylindrical screen discrete element model is divided by a plane passing through the segmentation points and perpendicular to the axis to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length;

[0056] A3: offset the segmentation starting point by a preset distance toward the discharge end, and use the offset point as a new segmentation starting point, and determine whether the current offset times exceed the preset movement times. If not, return to A2; if exceeded, use the result of each division in step A2 as a sub-cylindrical screen discrete element model.

[0057] Initially, the segmentation starting point should be set on the right side of the particle factory space model. Therefore, a certain distance should be reserved between the initial segmentation starting point and the particle factory space model. Then, the segmentation point is determined according to the segmentation starting point and the preset length. Multiple sub-cylindrical screen discrete element models with the same screen length are obtained through section division. Then, the segmentation starting point is moved based on the preset distance, and the process of dividing the sub-cylindrical screen discrete element model is repeated to obtain multiple sub-cylindrical screen discrete element models. Finally, multiple cylindrical screen discrete element models are obtained, and each cylindrical screen discrete element model is divided into a different number of sub-cylindrical screen discrete element models.

[0058] It is worth noting that the preset distance should be set according to the length of the actual screen discrete element model and the preset length. If the preset distance is too close, the difference between the two sample data obtained by simulation may be too small, making the obtained training data closer, resulting in the sample having less training effect on the screening efficiency prediction model.

[0059] Exemplarily, the present invention sets the preset distance to 50 mm. The preset number of moves can be set according to actual needs, or it can be calculated based on the segmentation starting point, the available drum screen length, the preset number of moves and the preset distance. Assuming that the length of the drum screen discrete element model is 600 mm, the length of the particle factory space model is 15 mm, the preset screen length is 100 mm, and the preset number of moves is 1, the available drum screen length is 585 mm, and the segmentation starting point is set at 15 mm to the right of the feed end face. After division, a total of 5 sub-cylindrical screen discrete element models are obtained, and the remaining 85 mm is not considered. Then the segmentation starting point is offset by 50 mm toward the discharge end, and the segmentation starting point is located at 65 mm to the right of the feed end face. After division, a total of 5 sub-cylindrical screen discrete element models are obtained, and the remaining 35 mm is not considered.

[0060] S12: Construct a particle factory space model, which is placed at the feed end of the drum screen discrete element model and inside the cylindrical screen discrete element model, and sets the particle generation method and particle parameters of the particle factory space model based on business needs.

[0061] Figure 2 The location of the particle plant space model is not shown in the figure, but it is generally placed on the left side of the drum screen discrete element model so that the particles it produces can fall into the screen area.

[0062] The present invention does not limit the software for constructing the discrete element model, and discrete element software such as EDEM, YADE, LIGGGHTS, DEMms, SDEM, etc. can be used. For example, EDEM can be used to define the particle factory space, including:

[0063] Particle definition: Users can define the physical properties of particles, such as shape (spherical, blocky, fibrous, etc.), size, mass, density, etc.

[0064] Particle generation: Through the API source code, the particle generation process in the simulation space can be realized, including the position, speed, rotation angle, etc. of particle generation and the particle generation method. Users can write code to generate a single particle, or batch generate particle groups with different properties (for example, generate particle groups with different particle sizes according to the different particle sizes defined in the particle definition step);

[0065] Particle behavior control: The particle factory API provides methods to control the movement and interaction of particles. Users can specify collisions, friction, and bonding between particles, as well as interactions between particles and simulation devices.

[0066] Customized simulation: By modifying and extending the API source files, users can create customized simulation scenarios to achieve specific particle flow patterns, particle loading and unloading processes, particle-device interactions, etc.

[0067] Integration of external data: API supports importing initial conditions and property parameters of particles from external data sources, such as importing particle shapes from CAD models or obtaining physical properties of particles from experimental data;

[0068] Performance optimization: By writing API code, users can optimize simulation performance, such as reducing simulation calculation time through algorithm optimization, or adjusting the particle management strategy during the simulation process;

[0069] Visualization: During the simulation, the API also provides a visualization output of the particle state. Users can programmatically control the output of particle position, velocity and other information for result analysis and display.

[0070] User interaction and automation: The API allows users to interactively control the simulation process, such as starting, pausing, and stopping the simulation, as well as dynamically adjusting particle parameters during the simulation. At the same time, users can automate a series of simulation tasks through the API to improve work efficiency.

[0071] The above contents are common operations of the particle factory space. The purpose of the particle factory space used in the present invention is to generate particles that meet business needs. The present invention does not specifically limit the specific operations of generating particles, such as the generation method of particles and the particle size of particles, which shall be based on the ability to meet business needs. Exemplarily, the particle generation method can be dynamic, and the particle size can be 3mm, 3mm to 4.5mm, 4.5mm to 6mm, 6mm to 9mm, 9mm to 13mm, 13mm to 25mm.

[0072] It can be understood that in the simulation experiment, the proportion of each particle needs to be set. In the process of generating particles in the present invention, the proportion of each particle remains unchanged. For example, for particles in the range of 3 to 4.5 mm, the proportion of 3.5 mm, 4 mm, and 4.4 mm particles can be set to 30%, 35%, and 35%.

[0073] S2: constructing a screening rate sample data set based on the drum screen discrete element model and the particle factory spatial model, wherein the screening rate sample data set includes: particle size, feed rate of each particle, drum screen inclination angle, drum screen mesh speed, drum screen internal component speed, and screening rate.

[0074] The method of constructing a screening rate sample data set based on the drum screen discrete element model and the particle factory spatial model includes:

[0075] B1: Based on the drum screen discrete element model and the particle factory spatial model, the drum screen screening process simulation is implemented, and the simulation results are obtained. The simulation results include the feeding rate of various particles corresponding to each time step in the simulation process, the spatial position of each particle, the drum screen inclination angle, the drum screen mesh speed, and the speed of the built-in components of the drum screen.

[0076] Understandably, before the simulation process is carried out, simulation parameters need to be set, including: screen body simulation material (mass, density, Young's modulus, sliding friction coefficient, rolling friction coefficient, etc.), setting the movement mode of the cylindrical screen and the built-in rotating component, adding a particle model (taking perfect spherical particles as an example: setting the radius), setting the particle factory (the location, size, shape, and feeding rate of the particle factory), setting the time step and simulation time, setting the simulation parameter group (here the rotation rate of the cylindrical screen, the rotation rate of the built-in component, the feeding rate of each particle, and the inclination angle of the drum screen), each simulation parameter can be set according to business needs, and finally discrete element simulation is carried out. Exemplarily, the movement mode of the screen surface can be simple harmonic vibration.

[0077] The simulation result refers to the result after the screening process reaches a steady state. Steady state means that the sum of the mass of particles passing through the sub-cylindrical screen discrete element model per unit time and the particle discharge rate at the discharge end is equal to the particle input rate.

[0078] After setting the simulation parameters, iterative simulation can be performed until the screening process enters a steady state, and discrete element iterative solution can be continued. The steady state should be simulated for at least 10 seconds, and the discrete element simulation data can be saved.

[0079] The discrete element simulation data mainly includes the position information (3D coordinates), motion information (force, velocity, acceleration, angular velocity, torque, etc.) and attribute information (mass, density, Young's modulus, sliding friction coefficient, rolling friction coefficient, etc.) of particles and geometric bodies (screens). Taking EDEM as an example, the information of particles and geometric models at each time step is stored in h5 format files, and the naming method is "time step + .h5".

[0080] In the present invention, according to business needs, the data required by the present invention are the feed rate of various particles corresponding to each time step, the spatial position of each particle, the inclination angle of the drum screen, the screen speed of the drum screen, and the speed of the built-in components of the drum screen.

[0081] The present invention divides the vibration screen discrete element model based on a preset length to obtain multiple sub-screen discrete element models of the same length. The sub-screen discrete element models are arranged continuously, and the output of the previous sub-screen discrete element model is used as the input of the next sub-screen discrete element model. It can be seen from step A3 that by continuously shifting the segmentation starting point, multiple cylindrical screen discrete element models are actually obtained. These cylindrical screen discrete element models are controlled by a program to achieve simulation of the same operating parameters. The input parameters of each cylindrical screen discrete element model are the same operating parameters. Because the number of sub-cylindrical screen discrete element models corresponding to each cylindrical screen discrete element model is different, it is achieved to obtain multiple groups of training sample data for sub-cylindrical screen discrete element models of the same screen length based on one operating parameter.

[0082] B2: Calculate the screening rate of different particle sizes corresponding to each sub-cylindrical screen discrete element model based on the spatial position of each particle.

[0083] For the first sub-cylindrical screen discrete element model near the feed end, the screening rate of each particle size is calculated based on the particle size generated in the particle factory spatial model, the feed rate of various particles, the inclination angle of the drum screen, the rotation speed of the drum screen, the rotation speed of the built-in components of the drum screen, and the mass of particles of various sizes below the first sub-cylindrical screen discrete element model.

[0084] For other sub-cylindrical screen discrete element models, the particle size at the discharge end, the feeding rate of various particles, the inclination angle of the drum screen, the screen speed of the drum screen, and the speed of the built-in components of the drum screen of the previous sub-cylindrical screen discrete element model are used as the particle size, the feeding rate of various particles, the inclination angle of the drum screen, the screen speed of the drum screen, and the speed of the built-in components of the drum screen of the sub-cylindrical screen discrete element model, and the screening rate of each particle size is calculated based on the particle size, the feeding rate of various particles, the inclination angle of the drum screen, the screen speed of the drum screen, the speed of the built-in components of the drum screen and the mass of particles of various sizes below the sub-cylindrical screen discrete element model.

[0085] The screening rate of each particle size in each sub-cylindrical screen discrete element model is calculated as follows:

[0086] B1: Count the number Q of particles of this size located below the sieve;

[0087] B2: Calculate the feed rate L of this particle size;

[0088] B3: Screen penetration rate S = Q*M / L, where M is the mass of the particles.

[0089] The feeding rate of various particles, the inclination angle of the drum screen, the rotation speed of the drum screen, the rotation speed of the built-in components of the drum screen and the screening rate of various particles at each time step corresponding to each sub-cylindrical screen discrete element model are taken as a sample in the screening rate sample data set corresponding to the screen length.

[0090] For each working condition simulation of the particle factory space model of the present invention, after steady state, each time step can generate multiple sets of simulation data corresponding to the working condition and the preset length screen. Exemplarily, assuming that the length of the drum screen discrete element model is 600 mm, the length of the particle factory space model is 15 mm, the preset screen length is 100 mm, and the preset number of moves is 1, the segmentation starting point can be set to be 20 mm to the right of the feed end face, and a total of 5 sub-cylindrical screen discrete element models are obtained. Then the segmentation starting point is offset 50 mm toward the discharge end, and a total of 5 sub-cylindrical screen discrete element models are obtained. Then, a total of 10 sub-cylindrical screen discrete element models are obtained. Therefore, a working condition simulation is performed, and 10 samples can be obtained at each time step. After the working condition simulation is completed, 10*N samples can be obtained, where N is the number of time steps.

[0091] B4: Determine whether the amount of sample data currently generated meets the preset quantity requirement. If so, stop generating. If not, adjust the current particle generation method and particle parameters based on business needs and return to B1.

[0092] The present invention adopts a machine learning model as a screening rate prediction model, and the number of training samples is an important indicator affecting the prediction accuracy of the machine learning model. Therefore, it is necessary to set the number of training sample data here so that the prediction effect of the machine learning model meets the requirements.

[0093] For example, the sample data volume may be set to 5000. If the currently generated sample data volume does not meet the requirement, the sample may be further generated by adjusting the particle generation method and particle parameters.

[0094] S3: Training a target machine learning model based on the screening rate sample data set to obtain a screening rate prediction model.

[0095] Understandably, the data set of the sample data of the screening rate should be preprocessed first so that it can meet the input requirements of the machine learning model. Data preprocessing operations include: missing value processing: you can choose to delete samples or features with missing values, or use interpolation, mean, median, mode and other methods to fill missing values; outlier processing: you can use statistical methods (such as Z-Score) or model-based methods (such as IQR) to handle outliers; data standardization: scale the data to a specific range (such as [0, 1]) so that different features have the same scale; data normalization: convert the data to values ​​between 0 and 1 to eliminate the dimensional effects between features. Feature selection: select features based on importance and relevance to improve the performance of the model.

[0096] Exemplarily, the machine learning model can be a support vector machine, a random forest, a Gaussian process regression, a BP neural network regression, a gradient enhancement regression, etc., which is not limited in the present invention. A BP neural network model with a Dropout layer can be used as a screening rate prediction model, and the input sample data includes the feed rate of each particle, the inclination angle of the drum screen, the rotation speed of the drum screen mesh, and the rotation speed of the built-in components of the drum screen. The output data is the screening rate of various particles. For example, the screening rate of 3mm, the screening rate of 3mm to 4.5mm, the screening rate of 4.5mm to 6mm, etc. It can be understood that the training process of the machine learning model determines the output result of the screening rate prediction model. When using the method proposed in the present invention, the input and output parameters of the machine learning model can be set as needed, so as to achieve the screening rate of different particles corresponding to the working condition based on a set of working condition parameters.

[0097] Preferably, the Harris Eagle optimization algorithm is used to optimize the number of neurons, Dropout coefficient and batch size of the neural network model, and the optimization result is used as the initial parameter of the neural network model. The specific implementation method of the Harris Eagle optimization algorithm to optimize the BP neural network model is not limited in the present invention.

[0098] S4: Obtain a sample of the parameter to be measured, and input the sample of the parameter to be measured into the screening rate prediction model to obtain the screening rate of different particle sizes corresponding to the sample of the parameter to be measured.

[0099] The parameter samples to be tested include: the feed rate of each particle, the inclination angle of the drum screen, the rotation speed of the drum screen mesh, and the rotation speed of the built-in components of the drum screen. By inputting them into the trained screening rate prediction model, the screening rates of particles of different sizes can be obtained.

[0100] S5: If the screening rate meets the expected target, the parameter sample to be tested is used as the control parameter of the drum screen; if it does not meet the expected target, the particle swarm algorithm is used to optimize the parameter sample to be tested, and the optimized parameter is used as the control parameter of the drum screen, thereby improving the screening rate of the vibrating screen to be tested;

[0101] During the optimization process, the input parameters represented by each particle are input into the screening rate prediction model to obtain the screening rate corresponding to the particle, and the fitness function is calculated based on the screening rate of the particle and the corresponding drum screen inclination angle, drum screen mesh speed, and drum screen built-in component speed.

[0102] After obtaining the screening rates of different particle sizes corresponding to the parameter sample to be tested in step S4, there may be a certain particle size whose screening rate does not meet the expected target (i.e., the expected value of the screening rate of a certain particle). Therefore, it is necessary to adjust each parameter in the parameter sample to be tested so that its corresponding screening rate meets the expected target.

[0103] The fitness function is calculated based on the particle penetration rate and the corresponding drum screen inclination angle, drum screen mesh speed, and drum screen internal component speed of the particle, including:

[0104]

[0105] Among them, y′ is the predicted screening rate corresponding to the current particle, is the expected target, α′, ω 1 ′ω 2 ′ is the drum screen inclination angle, drum screen mesh speed, and drum screen internal component speed corresponding to the current particle, α, ω 1 ,ω 2 are the drum screen inclination angle, drum screen mesh speed, and drum screen internal component speed of the parameter sample to be measured, and a, b, c, and d are constants that can be set according to trial and error or experience.

[0106] In the fitness function, the effects of the screening rate and the working parameters such as the drum screen inclination angle, the drum screen mesh speed, and the drum screen internal component speed are comprehensively considered. For example, for the current application scenario, the placement of the drum screen is fixed in advance, and the range of change of the drum screen inclination angle is limited. The inclination angle needs to be adjusted within the limited range of change to make the screening rate meet the requirements. Therefore, when screening particles in a particle group, the present invention can use the change of inclination angle as a consideration standard for the optimal parameter.

[0107] The method of optimizing the parameter sample to be tested by using a particle swarm algorithm and using the optimized parameters as control parameters of the drum screen includes:

[0108] C1: Initialize the particle group, select sample data that meets the expected target from the screening rate sample data set as the first sample data set, take the feeding rate of various particles, the drum screen inclination angle, the drum screen mesh speed, and the drum screen built-in component speed of each data in the first sample data set as a particle, take the feeding rate of various particles in the parameter sample to be measured, the drum screen inclination angle, the drum screen mesh speed, and the drum screen built-in component speed as a particle, and judge whether the total number of current particles meets the preset number. If yes, execute C3, if not, execute C2.

[0109] Exemplarily, the preset number may be 30.

[0110] C2: Counting the range of each parameter in the first sample data set, and randomly taking values ​​within the range of each parameter based on a random generation algorithm, thereby generating multiple particles, so that the total number of particles meets the preset number requirement.

[0111] C3: Calculate the fitness function of each particle to update the individual optimal and global optimal values, and determine whether the end condition is met. If so, execute C5; if not, execute C4.

[0112] C4: Update the speed and position of each particle and return to C3.

[0113] C5: Output the optimal position, and the particle group parameters corresponding to the optimal position are the control parameters of the drum screen.

[0114] It can be understood that the updating methods of position and speed, the updating methods of individual optimal and global optimal values, the adjustment of inertia weight, the adjustment of acceleration constant, etc. in the particle swarm algorithm are all common knowledge in the art and are not limited in the present invention.

[0115] Compared with the prior art, the present embodiment provides a method for optimizing the screening rate of a drum screen. After obtaining the screening rates of particles of different particle sizes according to the current operating parameters, a judgment is made based on the expected target. If the target requirements are not met, the current operating parameters are further optimized through the particle swarm algorithm to obtain operating parameters that meet the expected target, thereby guiding users to design operating parameters that meet the expected screening rate, saving process costs and improving design efficiency. A screening efficiency prediction model is constructed based on a machine learning model, which can more flexibly meet business needs. Compared with the traditional probabilistic screening model, dynamic screening model and discrete element numerical simulation in the prior art, the method proposed in the present invention has higher prediction accuracy and calculation efficiency, stronger real-time performance and can adapt to various complex working conditions. Based on a preset length The drum screen discrete element model is divided to obtain multiple sub-sieve discrete element models of the same length. For each operating condition simulation of the particle factory space model, after steady state, each time step can generate multiple sets of simulation data corresponding to the operating condition and the preset length of the sieve. Compared with the prior art that each time step can only generate one set of simulation data corresponding to the operating condition and the preset length, the present invention is more efficient in constructing a screening efficiency sample data set; in addition, the sub-sieve discrete element models are arranged continuously, and the output of the previous sub-sieve discrete element model is used as the input of the next sub-sieve discrete element model. Compared with the prior art that only obtains sample data for a fixed length of sieve model, the screening sample data obtained by simulating each sub-sieve discrete element model in the present invention is closer to the actual vibrating screen screening process.

[0116] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0117] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for optimizing the screening rate of a drum screen, characterized in that: include: Construct a discrete element model of the drum screen and a spatial model of the pellet plant; Constructing a screening rate sample data set based on the drum screen discrete element model and the particle factory spatial model, the screening rate sample data set includes: particle size, feeding rate of each particle, drum screen inclination angle, drum screen mesh speed, drum screen internal component speed, and screening rate; Training a target machine learning model based on the screening rate sample data set to obtain a screening rate prediction model; Acquire a parameter sample to be measured, and input the parameter sample to be measured into the screening rate prediction model to obtain the screening rate of different particle sizes corresponding to the parameter sample to be measured; If the screening rate meets the expected target, the parameter sample to be tested is used as the control parameter of the drum screen; if it does not meet the expected target, the particle swarm algorithm is used to optimize the parameter sample to be tested, and the optimized parameter is used as the control parameter of the drum screen, thereby improving the screening rate of the vibrating screen to be tested; During the optimization process, the input parameters represented by each particle are input into the screening rate prediction model to obtain the screening rate corresponding to the particle, and the fitness function is calculated based on the screening rate of the particle and the corresponding drum screen inclination angle, drum screen mesh speed, and drum screen built-in component speed.

2. A method for optimizing the screening rate of a drum screen according to claim 1, characterized in that: The construction of the drum screen discrete element model and the particle plant space model includes: Constructing a drum screen discrete element model, the drum screen discrete element model comprising: a cylindrical screen and an internal component, and dividing the cylindrical screen discrete element model to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length; A particle factory space model is constructed. The particle factory space model is placed at the feed end of the drum screen discrete element model and inside the cylindrical screen discrete element model. The particle generation method and particle parameters of the particle factory space model are set based on business needs.

3. A method for optimizing the screening rate of a drum screen according to claim 2, characterized in that: The step of dividing the cylindrical screen discrete element model to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length includes: Obtaining the drum screen length of the cylindrical screen discrete element model and the particle factory space model length of the particle factory space model along the length direction of the drum screen, and obtaining the available drum screen length based on the drum screen length and the particle factory space model length along the length direction of the drum screen; The cylindrical screen discrete element model is divided based on the available drum screen length and the preset length, thereby obtaining a plurality of sub-cylindrical screen discrete element models with the same screen length.

4. A method for optimizing the screening rate of a drum screen according to claim 3, characterized in that: The cylindrical screen discrete element model is divided based on the available drum screen length and the preset length to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length, including: A1: setting a segmentation starting point, the segmentation starting point is located on the axis of the cylindrical screen discrete element model, and the shortest distance from the segmentation starting point to the discharge end of the cylindrical screen discrete element model is equal to the available drum screen length; A2: Taking the segmentation starting point as the division starting point and the preset length as the step length, a plurality of segmentation points are obtained on the axis, and the cylindrical screen discrete element model is divided by a plane passing through the segmentation points and perpendicular to the axis to obtain a plurality of sub-cylindrical screen discrete element models with the same screen length; A3: offset the segmentation starting point by a preset distance toward the discharge end, and use the offset point as a new segmentation starting point, and determine whether the current offset times exceed the preset movement times. If not, return to A2; if exceeded, use the result of each division in step A2 as a sub-cylindrical screen discrete element model.

5. A method for optimizing the screening rate of a drum screen according to claim 4, characterized in that: The method of constructing a screening rate sample data set based on the drum screen discrete element model and the particle factory spatial model includes: B 1: Based on the drum screen discrete element model and the particle factory spatial model, the drum screen screening process is simulated, and the simulation results are obtained, wherein the simulation results include the feeding rate of various particles corresponding to each time step in the simulation process, the spatial position of each particle, the drum screen inclination angle, the drum screen mesh speed, and the drum screen internal component speed; B2: calculating the screening rate of different particle sizes corresponding to each sub-cylindrical screen discrete element model based on the spatial position of each particle; B3: The feeding rate of various particles, the inclination angle of the drum screen, the rotation speed of the drum screen mesh, the rotation speed of the drum screen internal components and the screening rate of various particles at each time step corresponding to each sub-cylindrical screen discrete element model are taken as a sample in the screening rate sample data set corresponding to the screen length; B4: Determine whether the amount of sample data currently generated meets the preset quantity requirement. If so, stop generating. If not, adjust the current particle generation method and particle parameters based on business needs and return to B1.

6. A method for optimizing the screening rate of a drum screen according to claim 5, characterized in that: include: The screening rate prediction model is a neural network model, and the Harris Eagle optimization algorithm is used to optimize the number of neurons, Dropout coefficient and batch size of the neural network model, and the optimization result is used as the initial parameter of the neural network model.

7. A method for optimizing the screening rate of a drum screen according to claim 6, characterized in that: The method of optimizing the parameter sample to be tested by using a particle swarm algorithm and using the optimized parameters as control parameters of the drum screen includes: C1: Initialize the particle group, select sample data that meets the expected target from the screening rate sample data set as the first sample data set, take the feed rate of various particles, the drum screen inclination angle, the drum screen mesh speed, and the drum screen built-in component speed of each data in the first sample data set as a particle, take the feed rate of various particles in the parameter sample to be measured, the drum screen inclination angle, the drum screen mesh speed, and the drum screen built-in component speed as a particle, and judge whether the total number of current particles meets the preset number. If yes, execute C3, if not, execute C2; C2: Counting the range of each parameter in the first sample data set, and randomly taking values ​​within the range of each parameter based on a random generation algorithm, thereby generating multiple particles, so that the total number of particles meets the preset number requirement; C3: Calculate the fitness function of each particle to update the individual optimal and global optimal values, and determine whether the end condition is met. If so, execute C5; if not, execute C4. C4: Update the speed and position of each particle and return to C3; C5: Output the optimal position, and the particle group parameters corresponding to the optimal position are the control parameters of the drum screen.

8. A method for optimizing the screening rate of a drum screen according to claim 7, characterized in that: The fitness function is calculated based on the particle penetration rate and the drum screen inclination angle, drum screen mesh speed, and drum screen internal component speed corresponding to the particle, including: Among them, y′ is the predicted screening rate corresponding to the current particle, is the expected target, α′, ω1′ω2′ are the drum screen inclination angle, drum screen mesh speed, and drum screen built-in component speed corresponding to the current particle, α, ω1, ω2 are the drum screen inclination angle, drum screen mesh speed, and drum screen built-in component speed of the parameter sample to be measured, and a, b, c, d are constants.

9. A method for optimizing the screening rate of a drum screen according to claim 8, characterized in that: The calculating, based on the spatial position of each particle, the screening rate of different particle sizes corresponding to each sub-cylindrical screen discrete element model comprises: For the first sub-cylindrical screen discrete element model near the feed end, the screening rates of various particle sizes are calculated based on the feed rates of various particles generated in the particle factory space model, the drum screen inclination angle, the drum screen mesh speed, the drum screen built-in component speed, and the masses of particles of various sizes below the first sub-cylindrical screen discrete element model; For other sub-cylindrical screen discrete element models, the particle size at the discharge end of the previous sub-cylindrical screen discrete element model, the feeding rate of various particles, the drum screen inclination angle, the drum screen mesh speed, and the speed of the drum screen built-in components are used as the feeding parameters of the current sub-cylindrical screen discrete element model. Based on the feeding parameters of the sub-cylindrical screen discrete element model and the mass of particles of various sizes below the sub-cylindrical screen discrete element model, the screening rates of various particle sizes are calculated.

10. A method for optimizing the screening rate of a drum screen according to claim 9, characterized in that: include: The simulation results refer to the particle size, feed rate of various particles, spatial position of each particle, drum screen inclination, drum screen mesh speed, and drum screen built-in component speed of each sub-cylindrical screen discrete element model in each time step after the screening process reaches a steady state; The steady state means that the sum of the mass of particles passing through the sub-cylindrical screen discrete element model per unit time and the particle discharge rate at the discharge end is equal to the particle input rate.

Images