A method for improving screening efficiency of vibrating screen

Abstract

The present invention discloses a method for improving the screening efficiency of a vibrating screen, which relates to the technical field of improving the efficiency of a vibrating screen, and includes the following steps: dynamically analyzing the vibration system of the vibrating screen, calculating its vibration frequency range, and determining the natural frequency of each component in combination with the structural parameters of the screen and the frame. Through dynamic frequency analysis, real-time vibration monitoring and intelligent adjustment mechanism, the vibrating screen can accurately identify the natural frequency and resonance risk, avoid dangerous frequency areas, fundamentally avoid resonance, protect key components, reduce failure rates and maintenance costs, and significantly improve screening efficiency and operational stability. Combined with machine learning and data-driven optimization, the equipment operating parameters can adapt to different materials and working conditions, achieve efficient screening and intelligent operation, reduce manual intervention, extend equipment life, and improve production efficiency and economic benefits.

Description

Technical Field

[0001] The present invention relates to the technical field of improving the efficiency of a vibrating screen, and in particular to a method for improving the screening efficiency of a vibrating screen. Background Art

[0002] Improving the screening efficiency of the vibrating screen means improving the degree of effective separation of materials during the screening process by optimizing the design, operating parameters or process flow of the vibrating screen, that is, accurately separating the target particles from the non-target particles in the shortest time. Improving the screening efficiency can be achieved in many ways, such as adjusting the aperture and shape of the screen, optimizing the amplitude, frequency and screen angle of the vibrating screen, improving the material feeding method, or dynamically monitoring and adjusting the screening process through intelligent control technology, thereby reducing the omission and misclassification of particles during the screening process, improving production efficiency and resource utilization, and reducing energy consumption and operating costs.

[0003] The prior art has the following deficiencies:

[0004] In the process of optimizing the vibration parameters (such as amplitude and frequency) of the vibrating screen to improve screening efficiency, if the natural frequency of the screening equipment structure is not accurately predicted and effectively avoided, resonance with it may cause a sharp increase in the system vibration amplitude. This uncontrolled resonance will significantly increase the operating load of the equipment, causing structural damage such as deformation, cracks, or even fractures of key components such as the screen frame, screen or supporting structure. In addition, resonance may also cause mechanical coupling between equipment, causing operating noise and vibration amplitude to propagate throughout the production line, further weakening the stability and safety of the production line. Once this problem occurs, it will not only cause unplanned equipment downtime, directly affecting production efficiency, but may also increase maintenance time and costs, and even threaten personnel safety.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method for improving the screening efficiency of a vibrating screen. Through dynamic frequency analysis, real-time vibration monitoring and intelligent adjustment mechanism, the vibrating screen can accurately identify the natural frequency and resonance risk, avoid dangerous frequency areas, fundamentally avoid resonance, protect key components, reduce failure rate and maintenance costs, and significantly improve screening efficiency and operational stability. Combined with machine learning and data-driven optimization, the equipment operating parameters can adapt to different materials and working conditions, achieve efficient screening and intelligent operation, reduce manual intervention, extend equipment life, and improve production efficiency and economic benefits to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for improving the screening efficiency of a vibrating screen, comprising the following steps:

[0008] Dynamically analyze the vibration system of the vibrating screen, calculate its vibration frequency range, and determine the natural frequency of each component based on the structural parameters of the screen and frame;

[0009] When setting the operating parameters of the vibrating screen, adjust the installation position of the vibrator and the magnitude of the exciting force to keep the vibration frequency out of the natural frequency range;

[0010] Configure a real-time vibration monitoring system to collect frequency data during the operation of the vibrating screen through sensors and compare it with the system set value;

[0011] Based on the frequency monitoring data, the anti-resonance algorithm is run to identify the resonance risk characteristics in the vibration signal through fast Fourier transform analysis, and the vibration frequency is dynamically adjusted;

[0012] Using machine learning optimization algorithms, we analyzed multiple batches of vibrating screen operation data, summarized the key parameters affecting resonance, and further optimized the vibrating screen operation model and parameter configuration.

[0013] Preferably, the vibration system of the vibrating screen is dynamically analyzed to calculate its vibration frequency range, and the natural frequency of each component is determined in combination with the structural parameters of the screen and the frame. The specific steps are as follows:

[0014] First, the dynamic model of the vibrating screen is constructed;

[0015] According to the dynamic model, the vibration frequency range of the vibrating screen is calculated using modal analysis;

[0016] Finite element analysis tools are used to calculate the natural frequencies of the vibrating screen mesh, frame and supporting components;

[0017] The frequency coupling between the vibration system and each component is analyzed by combining the overall vibration frequency range and local natural frequency results.

[0018] Preferably, the installation position of the vibrator and the magnitude of the exciting force are adjusted so that the vibration frequency is out of the natural frequency range. The specific steps are as follows:

[0019] Determine the installation position of the vibrator based on the dynamic analysis of the vibrating screen vibration system and the calculation results of the natural frequency;

[0020] Using the calculated natural frequency range of the vibrating screen, adjust the exciting force of the vibrator so that its operating frequency avoids the overlapping area with the dangerous frequency band. ;

[0021] Finite element simulation tools are used to simulate the effects of different vibrator installation positions and exciting force combinations on the dynamic performance of the system;

[0022] Vibration sensors are installed to monitor the frequency response characteristics of the vibrating screen in real time, and the position and exciting force of the vibrator are adjusted in combination with on-site tests.

[0023] Preferably, the specific steps of collecting the frequency data of the vibrating screen during operation by the sensor and comparing it with the system setting value are as follows:

[0024] According to the vibrator installation position and exciting force adjustment results in the vibrating screen operation parameter setting, determine the key parts for real-time monitoring and the vibration signal collection targets;

[0025] Connect the installed sensors to the central control system via wired or wireless means to build a real-time data collection network;

[0026] When the vibrating screen is running, the sensor continuously collects frequency signals and transmits the data to the central system for real-time processing;

[0027] When the monitoring system detects a dangerous frequency, the automatic control module adjusts the exciting force of the vibrator according to the preset logic.

[0028] Preferably, the specific steps of identifying the resonance risk characteristics in the vibration signal through fast Fourier transform analysis and dynamically adjusting the vibration frequency are as follows:

[0029] The sensor collects the vibration signal x(t) during the operation of the vibrating screen. Since the signal contains noise and interference, the data needs to be preprocessed before analysis, including denoising and normalization. A high-pass filter is used to remove low-frequency noise, and a sliding mean filter is used to eliminate high-frequency interference to obtain a net signal x′(t). The net signal x′(t) is then normalized to ensure that all measured values ​​are within a uniform amplitude range. The calculation expression is as follows:

[0030]

[0031] , where μ is the signal mean, σ is the signal standard deviation, quantifies the fluctuation range of x′(t), and represents the amplitude strength of the vibration signal, x norm (t) is the normalized signal;

[0032] For the normalized signal x norm (t) is transformed into a frequency domain signal by fast Fourier transform. The calculation expression is as follows:

[0033]

[0034] , where X(f) is the frequency domain signal and x is the standardized signal normThe frequency component of (t) reflects the amplitude and phase of the signal at different frequencies f, e is the natural base, t is the time variable, j is the complex unit, e -j2πft It is a complex exponential basis function, a basis function of Fourier transform, representing a composite form of a sine wave and a cosine wave with a frequency of f;

[0035] Using the mathematical model of the resonance risk characteristics, the dangerous frequency band in the spectrum is analyzed and the resonance risk function is defined. The calculation expression is as follows:

[0036]

[0037] , where R(f) is the resonance risk function, |X(f)| is the amplitude of the frequency domain signal X(f), indicating the energy of the vibration signal at frequency f, and max(|X(f)|) is the maximum amplitude of the spectrum;

[0038] After the resonance risk is detected, the operating frequency of the vibrator is adjusted to avoid the dangerous frequency band. The calculation expression is as follows:

[0039] f new =f current +k·R(f current )·(f safe -f current )

[0040] , where f new is the new frequency after adjustment, f current is the current operating frequency, f safe represents the safety target frequency, k is the adjustment rate coefficient, R(f current ) is the resonance risk quantification value of the current frequency, which is a quantitative indicator calculated based on the resonance risk function and represents the current operating frequency f current The risk level is calculated as follows:

[0041]

[0042] , where |X(f current )| is the amplitude of the current frequency signal, R(f current ) value, the higher the resonance risk of the current frequency.

[0043] Preferably, the machine learning optimization algorithm is used to analyze the operation data of multiple batches of vibrating screens, summarize the key parameters affecting resonance, and further optimize the operation model and parameter configuration of the vibrating screen. The specific steps are as follows:

[0044] Collect the parameters recorded during the operation of the vibrating screen, vibration frequency f run , amplitude A, acceleration a, screening efficiency E, noise level N, and operating parameters: material distribution uniformity Um , material particle size D and load L, all data are normalized and the calculation expression is as follows:

[0045] X∈{f run ,A,a,E,n,U m ,D,L}

[0046] , where X norm,i is the normalized data value, X i is the original value of the ith data point, min(X) is the minimum value of the parameter data set, and ma(X) is the maximum value of the parameter data set;

[0047] All normalized data values ​​X norm,i Form the normalized data matrix X norm , and use principal component analysis from the data matrix X norm Extract key features, define the covariance matrix, and calculate the expression as follows:

[0048]

[0049] , where C is the covariance matrix, n is the number of data samples, indicating the total number of collected data points, that is, the number of samples contained in the data set; X norm is the normalized data matrix, is the transpose of the normalized data matrix;

[0050] Obtain eigenvalues ​​and eigenvectors through eigendecomposition, and select the first k features to form the matrix V k , calculate the key features after dimensionality reduction, the expression is as follows:

[0051] Y=X norm ·V k , Y={y i}={y1, y2, y3,...,y k}

[0052] , where Y is the data matrix after dimensionality reduction, V k is the eigenvector matrix of the first k principal components selected after principal component analysis, with a dimension of m×k, y i is the i-th principal component in the data matrix Y after dimensionality reduction, k is the number of principal components, that is, the number of features retained after dimensionality reduction;

[0053] Based on the reduced-dimensional data matrix Y, a regression model is established to predict the screening efficiency and resonance risk. The optimization goal is to find the excitation parameters to maximize the screening efficiency and minimize the resonance risk. The calculation expression is as follows:

[0054] E=w1y1+w2y2+…+wk y k ,

[0055] , where E is the screening efficiency, w1, w2, w3, ..., w k is the weight coefficient, which indicates that each principal component y i Contribution to screening efficiency E, R is the resonance risk, is the mean of the principal components, that is, the mean of the i-th principal component;

[0056] By adjusting the excitation parameters to maximize the screening efficiency and minimize the resonance risk, the optimal parameter configuration is output. The calculation expression is as follows:

[0057] max(E)-α·R

[0058] , where α is a factor that weighs efficiency and risk.

[0059] R opt ={f run,opt ,A opt ,a opt ,L opt}

[0060] , where P opt is the optimal parameter configuration, f run,opt is the optimal vibration frequency when the vibrating screen is running, A opt is the optimal amplitude of the vibrating screen during operation, a opt is the optimal acceleration when the vibrating screen is running, L opt It is the optimal load when the vibrating screen is running;

[0061] The optimal parameter configuration P opt Applied to actual operation, real-time monitoring of vibrating screen data, update parameter configuration, and adjust parameters according to new operating data. The calculation expression is as follows:

[0062]

[0063] , where P new is the updated parameter configuration, η is the learning rate, is the gradient of resonance risk.

[0064] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0065] The present invention can effectively identify the natural frequency range and potential resonant frequency band of the vibrating screen through the application of dynamic frequency analysis and real-time vibration monitoring system. During operation, by using real-time monitoring data and intelligent adjustment mechanism, dangerous frequency areas can be quickly avoided, fundamentally avoiding the occurrence of resonance. This not only protects key components such as the screen and frame, reduces premature wear or structural damage caused by resonance, but also significantly reduces equipment failure rate and maintenance costs. In addition, after avoiding resonance, the vibration of the screen is more uniform, the amplitude is controlled within a reasonable range, and the screening efficiency is significantly improved. After the operating stability of the equipment is enhanced, not only production interruptions are reduced, but also a strong guarantee is provided for the reliability of the production plan.

[0066] The present invention combines machine learning optimization with long-term operation data analysis, and the operating parameters of the vibrating screen can be continuously adjusted and optimized to meet the screening requirements of different materials and complex working conditions. By automatically adjusting the exciting force, screen surface inclination or vibration frequency, the equipment can flexibly adapt to lightweight, highly adhesive or high-density materials to achieve higher screening accuracy and efficiency. At the same time, intelligent operation reduces dependence on manual intervention and improves the convenience and safety of operation. Thanks to the data-driven optimization mechanism, the long-term performance of the vibrating screen is better, the service life is extended, and the overall productivity and economic benefits of the equipment are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0068] Figure 1 The present invention is a method flow chart of a method for improving the screening efficiency of a vibrating screen. DETAILED DESCRIPTION

[0069] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0070] The present invention provides Figure 1 A method for improving the screening efficiency of a vibrating screen is shown, comprising the following steps:

[0071] Dynamically analyze the vibration system of the vibrating screen, calculate its vibration frequency range, and determine the natural frequency of each component based on the structural parameters of the screen and frame;

[0072] Dynamically analyze the vibration system of the vibrating screen, calculate its vibration frequency range, and determine the natural frequency of each component in combination with the structural parameters of the screen and frame. The specific steps are as follows:

[0073] First, the dynamic model of the vibrating screen is constructed;

[0074] By analyzing the mass distribution and rigid structure of the vibrating screen, the mathematical expression of the system is established, and the Lagrange equation or modal analysis method is usually used to describe its motion characteristics. This step requires determining the mass, elastic modulus, damping coefficient and connection method of each part, which directly affects the dynamic behavior of the system. The construction of the model is the basis for analyzing the vibration characteristics of the vibrating screen and ensuring the accuracy of the calculation results.

[0075] According to the dynamic model, the vibration frequency range of the vibrating screen is calculated using modal analysis;

[0076] The specific operation includes free vibration analysis of the vibrating screen and solving the eigenvalues ​​of the vibration equation, which correspond to the natural frequency of the system. In order to more accurately reflect the actual working conditions, it is also necessary to combine the frequency range of the vibrator excitation force and the operating environment of the vibrating screen to simulate the vibration characteristics under different working conditions. Through this step, the normal operating frequency range of the vibrating screen is clarified to provide guidance for subsequent optimization.

[0077] Use finite element analysis tools (such as ANSYS or ABAQUS) to calculate the natural frequencies of the vibrating screen, frame and supporting components;

[0078] By refining the mesh, the vibration modes of each part under different constraints are simulated. Focus on the local frequency characteristics of the connection between the screen and the frame, because these areas are often high-risk points for resonance. The results of finite element analysis can intuitively display the vibration mode distribution of the component and its corresponding frequency, providing a more specific basis for avoiding the resonant frequency band.

[0079] Combine the overall vibration frequency range and local natural frequency results to analyze the frequency coupling between the vibration system and each component;

[0080] By comparing the vibrator's operating frequency with each natural frequency, the dangerous frequency band that may cause resonance can be identified. If overlapping areas are found, the design can be optimized by adjusting the exciting force, changing the frame rigidity or increasing damping. The focus of this step is to comprehensively evaluate the system's dynamic performance to ensure that the vibrating screen avoids dangerous frequency bands in actual operation, thereby improving screening efficiency and equipment stability.

[0081] When setting the operating parameters of the vibrating screen, adjust the installation position of the vibrator and the magnitude of the exciting force to keep the vibration frequency out of the natural frequency range;

[0082] Adjust the installation position of the vibrator and the magnitude of the exciting force to make the vibration frequency avoid the natural frequency range. The specific steps are as follows:

[0083] Determine the installation position of the vibrator based on the dynamic analysis of the vibrating screen vibration system and the calculation results of the natural frequency;

[0084] The vibrator is usually installed on the side or bottom of the screen frame to provide sufficient exciting force to drive the screen. The selection of the installation position needs to balance the range of the exciting force and the transmission efficiency of the vibration energy to ensure that the screen achieves a uniform vibration mode on the screen surface. If the installation position is improper, it may cause local stress concentration or uneven overall amplitude of the screen, increasing the risk of resonance. By comprehensively considering the center of gravity, support point position and vibration mode of the screen frame, the optimal initial installation point of the vibrator is determined to provide a basis for subsequent adjustments.

[0085] Using the calculated natural frequency range of the vibrating screen, adjust the exciting force of the vibrator so that its operating frequency avoids the overlapping area with the dangerous frequency band. ;

[0086] The adjustment of the exciting force can be achieved by changing the angle and weight of the eccentric block inside the vibrator. Specifically, appropriately reducing the exciting force can reduce the operating frequency, but may affect the screening effect; conversely, increasing the exciting force requires ensuring that the amplitude does not exceed the bearing capacity of the screen and frame. The magnitude of the exciting force not only affects the vibration frequency, but is also directly related to the stratification and passing efficiency of the material on the screen surface, so it is necessary to combine experimental verification and simulation optimization for dynamic adjustment.

[0087] Finite element simulation tools are used to simulate the effects of different vibrator installation positions and exciting force combinations on the dynamic performance of the system;

[0088] The simulation content includes the vibration mode, amplitude distribution and frequency response characteristics of the screen. Special attention should be paid to the stress concentration area and the maximum amplitude point of the screen to ensure that there is sufficient safety margin between the operating frequency and the natural frequency. The simulation results can intuitively show the comprehensive impact of the vibrator position and the adjustment of the exciting force on the screening efficiency and resonance risk, providing a quantitative basis for further optimization.

[0089] Vibration sensors are installed to monitor the frequency response characteristics of the vibrating screen in real time, and the position and exciting force of the vibrator are adjusted in combination with on-site tests;

[0090] If the operating frequency of the vibrating screen is found to be close to the dangerous frequency band, further optimization measures can be taken, such as slightly changing the installation angle of the vibrator or the weight distribution of the eccentric block to improve the frequency separation. At the same time, the operating data under different working conditions are recorded to optimize the dynamic parameter model of the vibrating screen. This process needs to be repeatedly verified many times until the system can be stably operated within the safe and efficient frequency band, fundamentally avoiding the occurrence of resonance problems.

[0091] Configure a real-time vibration monitoring system to collect frequency data during the operation of the vibrating screen through sensors and compare it with the system set value;

[0092] The specific steps of collecting frequency data during the operation of the vibrating screen through sensors and comparing it with the system setting value are as follows:

[0093] According to the vibrator installation position and exciting force adjustment results in the vibrating screen operation parameter setting, determine the key parts for real-time monitoring and the vibration signal collection targets;

[0094] The sensor should be installed mainly at the connection between the screen and the frame, the support point of the screen frame, and near the vibrator. The vibration characteristics of these locations are most significant and can reflect the dynamic operation status of the system. The sensor type can be an accelerometer or a vibration frequency sensor, and its sensitivity must match the frequency range of the vibrating screen. During installation, ensure that the sensor is firmly connected and does not affect the normal operation of the screen or frame to avoid signal distortion or data deviation due to installation problems.

[0095] Connect the installed sensors to the central control system via wired or wireless means to build a real-time data collection network;

[0096] The vibration frequency, amplitude, acceleration and other signals collected by the sensor need to be converted into digital signals by the data collector and transmitted to the control system for real-time processing. The safe frequency range and warning value of the vibrating screen are configured in the system to trigger the alarm mechanism when the signal exceeds the set range. This communication network needs to ensure the real-time and stability of the transmission, and redundant channels need to be set to prevent the impact of signal interruption on the monitoring process.

[0097] When the vibrating screen is running, the sensor continuously collects frequency signals and transmits the data to the central system for real-time processing;

[0098] The system's built-in algorithm performs spectrum analysis on the collected signals and compares the current frequency with the safe frequency band. Once the vibration frequency is detected to be close to the dangerous range of the natural frequency, the system will immediately issue an early warning and record the data for subsequent analysis. During this process, the system also needs to monitor whether the frequency response of the vibrator after the excitation force is adjusted is within the expected range, providing feedback information for further optimization of parameters.

[0099] When the monitoring system detects a dangerous frequency, the automatic control module adjusts the exciting force of the vibrator according to the preset logic;

[0100] The frequency can be reduced by changing the angle of the eccentric block of the vibrator, or the amplitude can be adjusted to quickly move away from the resonance range. At the same time, the system will continuously record all operating data, including sensor signals, frequency adjustment process and effect. Through multiple operation records, the operation model of the vibrating screen can be further optimized to ensure long-term stability and efficient screening effect. The accumulation of data can also be used to train machine learning models to provide data support for the intelligent operation of vibrating screens in the future.

[0101] Based on the frequency monitoring data, the anti-resonance algorithm is run to identify the resonance risk characteristics in the vibration signal through fast Fourier transform analysis, and the vibration frequency is dynamically adjusted;

[0102] The specific steps to identify the resonance risk characteristics in the vibration signal through fast Fourier transform analysis and dynamically adjust the vibration frequency are as follows:

[0103] The sensor collects the vibration signal x(t) during the operation of the vibrating screen. The vibration signal x(t) is a time domain signal that changes with time. Since the signal contains noise and interference, the data needs to be preprocessed before analysis, including denoising and normalization. A high-pass filter is used to remove low-frequency noise, and a sliding mean filter is used to eliminate high-frequency interference to obtain a net signal x′(t). The net signal x′(t) is then normalized to ensure that all measured values ​​are within a uniform amplitude range. The calculation expression is as follows:

[0104]

[0105] , where σ is the signal mean, which is the net signal x′(t) is the average value, which represents the DC component or long-term deviation trend of the signal, σ is the signal standard deviation, which quantifies the fluctuation range of x′(t) and represents the amplitude strength of the vibration signal, xn orm (t) is the standardized signal, which is the normalized vibration signal, eliminating the mean shift and amplitude difference, and focusing on reflecting the dynamic characteristics of the signal;

[0106] For the normalized signal x norm (t) is transformed into a frequency domain signal by fast Fourier transform. The calculation expression is as follows:

[0107]

[0108] , where X(f) is the frequency domain signal and X is the standardized signal norm The frequency component of (t) reflects the amplitude and phase of the signal at different frequencies f. e is the natural base, t is the time variable, indicating the value of the vibration signal at a certain moment, j is the complex unit, and e is the natural base. -j2πft It is a complex exponential basis function, a basis function of Fourier transform, representing a composite form of a sine wave and a cosine wave with a frequency of f;

[0109] Using the mathematical model of the resonance risk characteristics, the dangerous frequency band in the spectrum is analyzed and the resonance risk function is defined. The calculation expression is as follows:

[0110]

[0111] , where R(f) is the resonance risk function, |X(f)| is the amplitude of the frequency domain signal X(f), which indicates the energy of the vibration signal at frequency f, and max(|X(f)|) is the maximum amplitude of the spectrum, which is the maximum value of all frequency amplitudes in the spectrum, indicating the intensity of the frequency component with the most concentrated energy in the signal;

[0112] The resonance risk function is a mathematical expression used to quantify whether the vibrating screen has a resonance risk at a certain frequency. It determines whether the frequency is close to the natural frequency or dangerous frequency band of the system by calculating the relative strength of the vibration signal at that frequency (i.e., the ratio of the current frequency signal amplitude to the maximum amplitude of the spectrum), thereby evaluating the possibility and severity of resonance. Its role is to provide a dimensionless risk indicator to help quickly identify potential dangerous frequency areas in the spectrum and provide a quantitative basis for dynamically adjusting the operating frequency of the vibrator. By using the resonance risk function, the system can monitor the operating status in real time and trigger adjustments when the risk exceeds the threshold, thereby effectively avoiding equipment damage and reduced efficiency.

[0113] The mathematical model of resonance risk characteristics is a quantitative method to describe the resonance risk in the operation of the vibrating screen, which is expressed in the form of functions (such as the resonance risk function Characterizes the relative strength of the vibration signal amplitude at different frequencies and its proximity to the natural frequency. Using this model, frequency points with significantly increased amplitude can be identified from the spectrum. These points usually overlap or are close to the natural frequency of the system, indicating the risk of resonance. Its role is to quantitatively analyze the frequency components through mathematical models and accurately locate dangerous frequency segments, thereby providing a scientific basis for adjusting the operating parameters of the vibrating screen (such as avoiding dangerous frequencies), ensuring the stability and screening efficiency of the equipment, and avoiding damage or performance degradation caused by resonance.

[0114] After the resonance risk is detected, the operating frequency of the vibrator is adjusted to avoid the dangerous frequency band. The calculation expression is as follows:

[0115] f new =f current +k·R(f current )·(f safe -f current )

[0116] , where f new is the new frequency after adjustment, f current is the current operating frequency, the operating frequency of the vibrating screen before adjustment, fsafe represents the safe target frequency, which is the target frequency set based on spectrum analysis and natural frequency calculation, and is located in the safe frequency band outside the resonance danger zone. k is the adjustment rate coefficient, R(f current ) is the resonance risk quantification value of the current frequency, which is a quantitative indicator calculated based on the resonance risk function and represents the current operating frequency f current The risk level is calculated as follows:

[0117]

[0118] , where |X(f current )| is the amplitude of the current frequency signal, R(f current ) value, the higher the resonance risk of the current frequency;

[0119] The adjustment rate coefficient k is a proportional factor used to control the adjustment speed of the vibration screen's operating frequency. It determines the size of the adjustment step and the sensitivity of the adjustment process. In the dynamic adjustment formula, k directly affects the system's response speed to resonance risks: the larger the k value, the faster the frequency adjustment, but it may introduce the risk of instability or over-adjustment; the smaller the k value, the smoother the adjustment, which helps the system stability, but may delay the adjustment effect. Its role is to achieve a balance between adjustment speed and system stability, ensuring that the equipment can quickly avoid risks when the resonance risk is high, and avoiding frequent adjustments that interfere with the operating status when the risk is low, thereby ensuring the efficient and stable operation of the vibration screen.

[0120] Using machine learning optimization algorithms, we analyzed multiple batches of vibrating screen operation data, summarized the key parameters that affect resonance, and further optimized the vibrating screen operation model and parameter configuration;

[0121] Using machine learning optimization algorithms, we analyzed multiple batches of vibrating screen operation data, summarized the key parameters that affect resonance, and further optimized the vibrating screen operation model and parameter configuration. The specific steps are as follows:

[0122] Collect the parameters recorded during the operation of the vibrating screen, vibration frequency f run , amplitude A, acceleration a, screening efficiency E, noise level N, and operating parameters: material distribution uniformity U m , material particle size D and load L, all data are normalized and the calculation expression is as follows:

[0123] X∈{f run ,A,a,E,N,U m ,D,L}

[0124] , where X norm,i is the normalized data value, X iis the original value of the ith data point, min(X) is the minimum value of the parameter data set, and max(X) is the maximum value of the parameter data set;

[0125] All normalized data values ​​X norm,i Form the normalized data matrix X norm , and use principal component analysis from the data matrix X norm Extract key features, define the covariance matrix, and calculate the expression as follows:

[0126]

[0127] , where C is the covariance matrix, n is the number of data samples, indicating the total number of collected data points, that is, the number of samples contained in the data set; X norm is the normalized data matrix, is the transpose of the normalized data matrix;

[0128] The covariance matrix is ​​a statistical tool used to measure the linear correlation between multiple variables. The role of the covariance matrix is ​​to quantify the correlation between different parameters, thereby identifying key variables that may affect screening efficiency or resonance risk. For example, if the covariance matrix shows a high correlation between amplitude A and screening efficiency E, it means that adjusting the amplitude may be an important means to optimize screening efficiency.

[0129] Normalized data matrix X norm Transpose The rows and columns of the matrix are swapped, so that each row represents a data sample and each column represents a variable, and each row represents a variable and each column represents a sample. Transposition is particularly important when calculating the covariance matrix, because the covariance matrix needs to analyze the interaction between variables at the same time. Through matrix transposition and matrix multiplication It can efficiently calculate the covariance between all variables, simplify the statistical analysis process, and provide the basic data structure for dimensionality reduction algorithms such as principal component analysis (PCA).

[0130] Obtain eigenvalues ​​and eigenvectors through eigendecomposition, and select the first k features to form the matrix V k , calculate the key features after dimensionality reduction, the expression is as follows:

[0131] Y=X norm ·V k , Y={y i}={y1, y2, y3,...,y k}

[0132] , where Y is the data matrix after dimensionality reduction, V kis the eigenvector matrix of the first k principal components selected after principal component analysis (PCA), with a dimension of m×k, y i is the i-th principal component in the data matrix Y after dimensionality reduction. The principal component is a linear combination of the original variables, representing a new "dimension" or feature that describes the most important information in the data. k is the number of principal components, that is, the number of features retained after dimensionality reduction.

[0133] Based on the reduced-dimensional data matrix Y, a regression model is established to predict the screening efficiency and resonance risk. The optimization goal is to find the excitation parameters to maximize the screening efficiency and minimize the resonance risk. The calculation expression is as follows:

[0134] E=w1y1+w2y2+…+w k y k ,

[0135] , where E is the screening efficiency, w1, w2, w3, ..., w k is the weight coefficient, which indicates that each principal component y i The contribution to the screening efficiency E, R is the resonance risk, which is an indicator that describes the possibility of resonance during the operation of the vibrating screen, indicating the degree to which the system deviates from the normal working state. is the mean of the principal components, that is, the mean of the i-th principal component;

[0136] By adjusting the excitation parameters to maximize the screening efficiency and minimize the resonance risk, the optimal parameter configuration is output. The calculation expression is as follows:

[0137] max(E)-α·R

[0138] , where α is a factor that weighs efficiency and risk.

[0139] p opt ={f run,opt ,A opt ,a opt ,L opt}

[0140] , where P opt is the optimal parameter configuration, f run,opt is the optimal vibration frequency when the vibrating screen is running, A opt is the optimal amplitude of the vibrating screen during operation, a opt is the optimal acceleration when the vibrating screen is running, L opt It is the optimal load when the vibrating screen is running;

[0141] Screening efficiency is an important indicator to measure the performance of the vibrating screen. It indicates the ability of the screen to correctly classify the material, usually expressed as a percentage. For example, a screening efficiency of 90% means that qualified materials passing through the screen account for 90% of the input material. Screening efficiency is affected by many factors, including vibration frequency, amplitude, screen surface inclination, material particle size distribution and material flow characteristics. High screening efficiency indicates that the vibrating screen can accurately separate the material into the target particle size range during operation, thereby improving the accuracy and efficiency of production. The role of screening efficiency is to directly affect the processing quality and economic benefits of the production line. An efficient vibrating screen can minimize the mixing of unqualified materials, thereby reducing the waste of raw materials and subsequent processing costs. At the same time, high screening efficiency can also improve the production capacity of the entire production process and ensure the reliable operation of the equipment under high load.

[0142] Resonance risk describes the possibility of resonance when the vibration frequency of the vibrating screen is close to or equal to the natural frequency during operation. Resonance can cause drastic amplitude fluctuations in the screen, frame or other components, resulting in reduced screening accuracy, increased equipment wear and even structural damage. Resonance risk is usually expressed as a quantitative indicator, which is based on a comparative analysis of the equipment's operating data (such as vibration frequency and acceleration) and the normal operating range of the system. The role of resonance risk is to ensure the safety and stability of equipment operation. An effective resonance risk assessment can help engineers identify high-risk working conditions and adjust equipment parameters (such as amplitude, frequency or exciting force) to avoid resonance. By controlling the resonance risk, the vibrating screen can not only extend its service life, but also avoid downtime, maintenance costs and production losses caused by failures, ensuring that the system operates stably at high efficiency.

[0143] The optimal parameter configuration P opt Applied to actual operation, real-time monitoring of vibrating screen data, update parameter configuration, and adjust parameters according to new operating data. The calculation expression is as follows:

[0144]

[0145] , where P new is the updated parameter configuration, η is the learning rate, that is, the learning rate used to control the parameter adjustment amplitude during the optimization process, usually a small positive number, is the gradient of the resonance risk, which is the resonance risk R relative to each operating parameter (vibration frequency f run , amplitude A, acceleration a, load L) weighted sum of partial derivatives;

[0146] Implementation method 1: Anti-resonance solution based on dynamic frequency analysis and vibrator optimization

[0147] The core of this implementation method is to ensure that the vibrating screen is away from the dangerous frequency band of resonance during operation through preliminary dynamic frequency analysis and optimization of vibrator parameters, thereby fundamentally reducing the risk of resonance. First, the dynamic behavior of the vibrating screen system is comprehensively modeled to analyze the natural frequency distribution of the screen, frame and vibrator. The vibration mode and characteristic frequency of the vibrating screen under different excitation forces are calculated using modal analysis or finite element analysis tools (such as ANSYS). This process requires precise measurement of the material parameters, geometric dimensions and connection methods of the screen frame, screen and supporting structure, which directly determine the range and distribution of the natural frequency. In addition, it is also necessary to combine the working characteristics of the vibrating screen, such as material weight, conveying speed and inclination, to simulate the actual force conditions during the screening process to ensure the accuracy of the analysis results.

[0148] After determining the natural frequency of the vibrating screen system, optimize the installation position and exciting force parameters of the vibrator for the frequency band where resonance may occur. The vibrator is usually installed on the side or bottom of the screen frame, and its position determines the distribution of vibration energy. If the installation position deviates too far from the center of gravity of the screen frame, it may cause uneven vibration of the screen and even aggravate local stress concentration, causing damage or deformation of the screen. By combining experiments with simulations, adjust the installation position of the vibrator so that the point of action of the exciting force is as close to the center of gravity of the screen frame as possible to ensure uniform vibration of the entire screen. In addition, optimize the exciting force parameters of the vibrator, including adjusting the angle, weight and distribution of the eccentric block. Reducing the exciting force can reduce the vibration frequency, but may affect the screening efficiency; increasing the exciting force requires ensuring that the screen and frame can withstand greater dynamic loads.

[0149] In order to verify the effectiveness of the adjustment results, the finite element simulation tool is further used to analyze the dynamic performance of the adjusted vibrating screen system. The simulation content includes the amplitude distribution, stress concentration area and frequency response characteristics of the screen. Focus on checking whether the adjusted working frequency completely avoids the dangerous area of ​​the natural frequency, and at the same time evaluate the impact of the adjustment on the screening efficiency. If the simulation results show that the screen vibrates evenly and the amplitude and stress distribution are within the design range, it can be considered that the parameter adjustment has achieved the optimization goal. Finally, the actual operation test is used to verify whether the performance of the adjusted vibrating screen is stable and efficient.

[0150] The advantage of this implementation is that through sufficient analysis and optimization in the early stage, the sudden risk caused by resonance problems in the operation of the equipment can be avoided. The whole process focuses on optimizing the early parameter configuration so that the vibrating screen always remains within the safe frequency band from startup to operation. In addition, this method relies on dynamic models and simulation technology, and the debugging process is accurate and efficient, which can significantly improve the screening efficiency and equipment service life.

[0151] Implementation method 2: Intelligent monitoring solution with real-time vibration monitoring and dynamic adjustment

[0152] This implementation method achieves rapid response and adaptive optimization of resonance problems during the operation of the vibrating screen through real-time vibration monitoring and dynamic adjustment technology. First, high-precision vibration sensors are installed at key locations of the vibrating screen, such as the support points of the screen frame, the connection between the screen and the frame, and near the vibrator. The sensor should be an accelerometer or a vibration frequency sensor, and its sensitivity should cover the operating frequency range of the vibrating screen and have high anti-interference capabilities. The sensor is connected to the central control system via wired or wireless means to build a real-time data acquisition network. The data acquisition module needs to support multi-channel input in order to monitor multiple sensor signals simultaneously.

[0153] During the operation of the vibrating screen, the sensor continuously collects dynamic data such as vibration frequency, amplitude and acceleration, and transmits it to the central control system. The control system uses the fast Fourier transform (FFT) algorithm to perform spectral analysis on the signal, extract the vibration frequency components and the corresponding energy distribution, and compare the current frequency with the safe frequency band in real time. When the operating frequency is detected to be close to the dangerous area of ​​the natural frequency, the system will trigger an early warning and record the relevant data for subsequent analysis. In addition, the control system also needs to monitor the frequency response of the vibrator after the excitation force is adjusted to verify whether it is within the expected range and provide feedback for further optimization.

[0154] Once the system detects a dangerous frequency, the control module can automatically adjust the operating parameters of the vibrator according to the preset logic. For example, by changing the angle of the eccentric block or the weight distribution, the vibration frequency can be reduced to a safe range. If the dangerous frequency is caused by uneven material distribution, the system can also improve the movement of the material on the screen by adjusting the screen surface inclination or the feeding speed, thereby indirectly reducing the risk of resonance. This intelligent adjustment mechanism can complete frequency adjustment in a short time, minimizing the impact of resonance on screening efficiency and equipment safety.

[0155] This implementation method ensures the stable operation of the vibrating screen under complex working conditions through real-time monitoring and dynamic adjustment. Compared with traditional manual monitoring, this solution has a fast response speed and precise adjustment, effectively avoiding sudden equipment damage caused by resonance. In addition, the large amount of operating data recorded by the monitoring system provides valuable reference for subsequent system optimization and intelligent upgrades.

[0156] Implementation method 3: Data-driven machine learning optimization and long-term performance improvement solution

[0157] This implementation method is based on a large amount of data collected during the long-term operation of the vibrating screen, and analyzes key parameters through machine learning models to continuously optimize the system's operating performance. After the vibrating screen is installed with a real-time monitoring system, dynamic data such as vibration frequency, amplitude, screening efficiency, and material characteristics are recorded during each operation. These data cover the operating status of the vibrating screen under different working conditions and can reflect the potential laws of resonance. The data is uploaded to a central database, and a feature set for training is generated through preprocessing steps such as denoising, standardization, and normalization.

[0158] Based on the processed data, a machine learning model (such as support vector machine, random forest or deep learning network) is constructed to explore the key parameters that affect resonance and their interrelationships. For example, the model can identify the weight of the vibrator installation position, the magnitude of the exciting force and the tightness of the screen on the occurrence of resonance. Through model prediction, the resonance risk under different operating conditions can be identified in advance, and parameter optimization suggestions can be provided. For example, for certain high-risk frequency bands, the model may recommend reducing the exciting force, changing the vibrator installation position or adjusting the screen tension to avoid resonance.

[0159] In addition, the machine learning model can also provide personalized optimization solutions for complex working conditions. For example, when processing light or easily sticky materials, the vibration frequency can be automatically adjusted to improve screening efficiency; for high-volume requirements, the excitation force and screen surface inclination angle are optimized to achieve higher conveying speeds. Through continuous data accumulation and model updates, the system's predictive capabilities and optimization accuracy will continue to improve, allowing the vibrating screen to adapt to a wider variety of materials and operating environments.

[0160] The advantage of this implementation is that it combines machine learning technology with the operation of the vibrating screen, giving the system the ability to self-learn and self-optimize. Compared with the traditional experience-based adjustment method, data-driven optimization is more scientific and reliable, which can significantly improve the long-term stability and screening efficiency of the equipment, while reducing the risk of resonance and extending the service life of the equipment.

[0161] The present invention can effectively identify the natural frequency range and potential resonant frequency band of the vibrating screen through the application of dynamic frequency analysis and real-time vibration monitoring system. During operation, by using real-time monitoring data and intelligent adjustment mechanism, dangerous frequency areas can be quickly avoided, fundamentally avoiding the occurrence of resonance. This not only protects key components such as the screen and frame, reduces premature wear or structural damage caused by resonance, but also significantly reduces equipment failure rate and maintenance costs. In addition, after avoiding resonance, the vibration of the screen is more uniform, the amplitude is controlled within a reasonable range, and the screening efficiency is significantly improved. After the operating stability of the equipment is enhanced, not only production interruptions are reduced, but also a strong guarantee is provided for the reliability of the production plan.

[0162] The present invention combines machine learning optimization with long-term operation data analysis, and the operating parameters of the vibrating screen can be continuously adjusted and optimized to meet the screening requirements of different materials and complex working conditions. By automatically adjusting the exciting force, screen surface inclination or vibration frequency, the equipment can flexibly adapt to lightweight, highly adhesive or high-density materials to achieve higher screening accuracy and efficiency. At the same time, intelligent operation reduces dependence on manual intervention and improves the convenience and safety of operation. Thanks to the data-driven optimization mechanism, the long-term performance of the vibrating screen is better, the service life is extended, and the overall productivity and economic benefits of the equipment are significantly improved.

[0163] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for improving the screening efficiency of a vibrating screen, characterized in that: The following steps are involved: Dynamically analyze the vibration system of the vibrating screen, calculate its vibration frequency range, and determine the natural frequency of each component based on the structural parameters of the screen and frame; When setting the operating parameters of the vibrating screen, adjust the installation position of the vibrator and the magnitude of the exciting force to keep the vibration frequency out of the natural frequency range; Configure a real-time vibration monitoring system to collect frequency data during the operation of the vibrating screen through sensors and compare it with the system set value; Based on the frequency monitoring data, the anti-resonance algorithm is run to identify the resonance risk characteristics in the vibration signal through fast Fourier transform analysis, and the vibration frequency is dynamically adjusted; Using machine learning optimization algorithms, we analyzed multiple batches of vibrating screen operation data, summarized the key parameters affecting resonance, and further optimized the vibrating screen operation model and parameter configuration.

2. The method for improving the screening efficiency of a vibrating screen according to claim 1, characterized in that: Dynamically analyze the vibration system of the vibrating screen, calculate its vibration frequency range, and determine the natural frequency of each component in combination with the structural parameters of the screen and frame. The specific steps are as follows: First, the dynamic model of the vibrating screen is constructed; According to the dynamic model, the vibration frequency range of the vibrating screen is calculated using modal analysis; Finite element analysis tools are used to calculate the natural frequencies of the vibrating screen mesh, frame and supporting components; The frequency coupling between the vibration system and each component is analyzed by combining the overall vibration frequency range and local natural frequency results.

3. The method for improving the screening efficiency of a vibrating screen according to claim 1, characterized in that: Adjust the installation position of the vibrator and the magnitude of the exciting force to make the vibration frequency avoid the natural frequency range. The specific steps are as follows: Determine the installation position of the vibrator based on the dynamic analysis of the vibrating screen vibration system and the calculation results of the natural frequency; Using the calculated natural frequency range of the vibrating screen, adjust the exciting force of the vibrator so that its operating frequency avoids the overlapping area with the dangerous frequency band. ; Finite element simulation tools are used to simulate the effects of different vibrator installation positions and exciting force combinations on the dynamic performance of the system; Vibration sensors are installed to monitor the frequency response characteristics of the vibrating screen in real time, and the position and exciting force of the vibrator are adjusted in combination with on-site tests.

4. The method for improving the screening efficiency of a vibrating screen according to claim 1, characterized in that: The specific steps of collecting frequency data during the operation of the vibrating screen through sensors and comparing it with the system setting value are as follows: According to the vibrator installation position and exciting force adjustment results in the vibrating screen operation parameter setting, determine the key parts for real-time monitoring and the vibration signal collection targets; Connect the installed sensors to the central control system via wired or wireless means to build a real-time data collection network; When the vibrating screen is running, the sensor continuously collects frequency signals and transmits the data to the central system for real-time processing; When the monitoring system detects a dangerous frequency, the automatic control module adjusts the exciting force of the vibrator according to the preset logic.

5. The method for improving the screening efficiency of a vibrating screen according to claim 1, characterized in that: The specific steps to identify the resonance risk characteristics in the vibration signal through fast Fourier transform analysis and dynamically adjust the vibration frequency are as follows: The sensor collects the vibration signal x(t) during the operation of the vibrating screen. Since the signal contains noise and interference, the data needs to be preprocessed before analysis, including denoising and normalization. A high-pass filter is used to remove low-frequency noise, and a sliding mean filter is used to eliminate high-frequency interference to obtain a net signal x ′ (t), then the net signal x ′ (t) Perform normalization to ensure that all measured values ​​are within a uniform amplitude range. The calculation expression is as follows: ， Where μ is the signal mean and σ is the signal standard deviation, which quantifies x ′ The fluctuation range of (t) indicates the amplitude strength of the vibration signal, x norm (t) is the normalized signal; For the normalized signal x norm (t) is transformed into a frequency domain signal by fast Fourier transform. The calculation expression is as follows: ， Where X(f) is the frequency domain signal and is the standardized signal x norm The frequency component of (t) reflects the amplitude and phase of the signal at different frequencies f, e is the natural base, t is the time variable, j is the complex unit, e -j2πft It is a complex exponential basis function, a basis function of Fourier transform, representing a composite form of a sine wave and a cosine wave with a frequency of f; Using the mathematical model of the resonance risk characteristics, the dangerous frequency band in the spectrum is analyzed and the resonance risk function is defined. The calculation expression is as follows: ， Where R(f) is the resonance risk function, |X(f)| is the amplitude of the frequency domain signal X(f), which indicates the energy of the vibration signal at frequency f, and max(|X(f)|) is the maximum amplitude of the spectrum; After the resonance risk is detected, the operating frequency of the vibrator is adjusted to avoid the dangerous frequency band. The calculation expression is as follows: f new =f current +k·R(f current )·(f safe -f current ), In the formula, f new is the new frequency after adjustment, f current is the current operating frequency, f safe represents the safety target frequency, k is the adjustment rate coefficient, R(f current ) is the resonance risk quantification value of the current frequency, which is a quantitative indicator calculated based on the resonance risk function and represents the current operating frequency f current The risk level is calculated as follows: ， In the formula, |X(f current )| is the amplitude of the current frequency signal, R(f current ) value, the higher the resonance risk of the current frequency.

6. The method for improving the screening efficiency of a vibrating screen according to claim 1, characterized in that: Using machine learning optimization algorithms, we analyzed multiple batches of vibrating screen operation data, summarized the key parameters that affect resonance, and further optimized the vibrating screen operation model and parameter configuration. The specific steps are as follows: Collect the parameters recorded during the operation of the vibrating screen, vibration frequency f run , amplitude A, acceleration a, screening efficiency E, noise level N, and operating parameters: material distribution uniformity U m , material particle size D and load L, all data are normalized and the calculation expression is as follows: ， Where, X norm,i is the normalized data value, X i is the original value of the ith data point, min(X) is the minimum value of the parameter data set, and max(X) is the maximum value of the parameter data set; All normalized data values ​​X norm,i Form the normalized data matrix X norm , and use principal component analysis from the data matrix X norm Extract key features, define the covariance matrix, and calculate the expression as follows: ， Where C is the covariance matrix, n is the number of data samples, which means the total number of data points collected, that is, the number of samples contained in the data set; X norm is the normalized data matrix, is the transpose of the normalized data matrix; Obtain eigenvalues ​​and eigenvectors through eigendecomposition, and select the first k features to form the matrix V k , calculate the key features after dimensionality reduction, the expression is as follows: Y=X norm ·V k ,Y={y i }={y1、y2、y3、……、y k }, Where Y is the data matrix after dimensionality reduction, V k is the eigenvector matrix of the first k principal components selected after principal component analysis, with a dimension of m×k, y i is the i-th principal component in the data matrix Y after dimensionality reduction, k is the number of principal components, that is, the number of features retained after dimensionality reduction; Based on the reduced-dimensional data matrix Y, a regression model is established to predict the screening efficiency and resonance risk. The optimization goal is to find the excitation parameters to maximize the screening efficiency and minimize the resonance risk. The calculation expression is as follows: ， Where E is the screening efficiency, w1, w2, w3, ..., w k is the weight coefficient, which indicates that each principal component y i Contribution to screening efficiency E, R is the resonance risk, is the mean of the principal components, that is, the mean of the i-th principal component; By adjusting the excitation parameters to maximize the screening efficiency and minimize the resonance risk, the optimal parameter configuration is output. The calculation expression is as follows: max(E)-α·R, In the formula, α is a factor that weighs efficiency and risk. P opt ={f run,opt ,A opt ,a opt ,L opt }, Where P opt is the optimal parameter configuration, f run,opt is the optimal vibration frequency when the vibrating screen is running, A opt is the optimal amplitude of the vibrating screen during operation, a opt is the optimal acceleration when the vibrating screen is running, L opt It is the optimal load when the vibrating screen is running; The optimal parameter configuration P opt Applied to actual operation, real-time monitoring of vibrating screen data, update parameter configuration, and adjust parameters according to new operating data. The calculation expression is as follows: ， Where P new is the updated parameter configuration, η is the learning rate, is the gradient of resonance risk.

Images