An igwo-bp-pid-based cross-sieve screening parameter optimization method and system

Abstract

The application provides a cross screen screening parameter optimization method and system based on an improved grey wolf optimization algorithm (IGWO)-back-propagation neural network (BP)-proportional integral derivative (PID). The system comprises a cross screen, a control system, a communication unit, a monitoring system and an upper computer. The monitoring system monitors whether the screening parameters of the cross screen meet the optimal screening conditions. When the optimal screening conditions are not met, the upper computer optimizes the screening parameters through a preset IGWO-BP-PID algorithm and transmits the optimized screening parameters to the control system. The control system adjusts the mechanical system in the cross screen according to the optimized screening parameters to meet the optimal screening conditions. Through the above system, the mechanical system in the cross screen can be automatically and quantitatively adjusted under different working conditions to form different screen surface inclination angles, ensuring smooth screening. Moreover, the system can be automatically operated, further improving the screening efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of screening equipment, in particular to a cross screen screening parameter optimization method and system based on IGWO-BP-PID. BACKGROUND

[0002] The cross fine particle roller screen is a screening equipment suitable for wet fine raw coal dry deep screening, which has a wide application prospect in power plants, coal mines, coal preparation plants and other industries. Although the existing cross screen can provide basic screening function, it lacks intelligent automatic adjustment capability and cannot automatically optimize the screen angle according to the physical properties of different materials to make the material distribution uniform. Since the screen structure is fixed, it cannot be automatically adjusted when the working condition changes, resulting in low screening efficiency and uneven screen wear. In addition, the equipment lacks material monitoring and real-time adjustment mechanism, which cannot quickly respond when the material properties change, affecting the screening effect and equipment life. Therefore, improving the intelligent level of the equipment, especially introducing an automatic adjustment and real-time monitoring system, is the key to solving the current problems. SUMMARY

[0003] The purpose of the present application is to provide a cross screen screening parameter optimization method and system based on IGWO-BP-PID, which can automatically adjust the screen angle to different complex working conditions, thereby facilitating the smooth progress of the screening operation.

[0004] To solve the above technical problems, the embodiment of the present application provides a cross screen screening parameter optimization system based on IGWO-BP-PID, which comprises a cross fine particle roller screen, a control system, a communication unit, a monitoring system and an upper computer. The monitoring system is connected to the upper computer through the communication unit, and the monitoring system is used to monitor whether the screening parameters of the cross fine particle roller screen meet the best screening condition. When the best screening condition is not met, the monitoring system transmits the screening parameters to the upper computer through the communication unit. The upper computer is also connected to the control system. The upper computer reads the screening parameters and optimizes them through a preset IGWO-BP-PID algorithm to obtain optimized screening parameters, and transmits the optimized screening parameters to the control system. The control system is also connected to the cross fine particle roller screen, and the control system is used to adjust the mechanical system action of the cross fine particle roller screen according to the optimized screening parameters to meet the best screening condition.

[0005] The embodiment of the present application also provides a cross screen screening parameter optimization method based on IGWO-BP-PID, which is applied to the upper computer and comprises the following steps: receiving the screening parameters that do not meet the best screening condition sent by the monitoring system; optimizing the screening parameters through a preset IGWO-BP-PID algorithm to obtain optimized screening parameters; and transmitting the optimized screening parameters to the control system.

[0006] In addition, the optimized screening parameters are obtained by presetting the IGWO-BP-PID algorithm to optimize the screening parameters, including: establishing a corresponding motion model according to the motion analysis of the cross-type fine particle roller screen; designing a PID controller according to the system model; initializing the BP neural network, predicting the control output based on the historical data of the mechanical system of the cross-type fine particle roller screen; generating an initial PID parameter population using the IGWO algorithm, each group of parameters representing the Kp, Ki, and Kd of the PID controller, wherein Kp, Ki, and Kd are the proportional, integral, and differential coefficients of the PID controller, respectively; calculating the fitness value of each group of PID parameters in the initial PID parameter population using the initialized BP neural network; updating the population position based on the fitness value, and outputting the optimal PID parameter combination as the optimized screening parameter to control the mechanical system.

[0007] In addition, generating an initial PID parameter population using the IGWO algorithm includes: using chaotic mapping to generate an initial PID parameter population.

[0008] In addition, in the mechanical system, the PID parameter combination adjusts the extension amount of the hydraulic cylinder to achieve control of the mechanical system through the following formula:

[0009] Adjusting the extension amount x(t) of the hydraulic cylinder includes adjusting through the following formula:

[0010]

[0011] wherein u(t) represents the PID output, x(t) is the actual extension amount of the hydraulic cylinder, x setpoint represents the target extension amount of the hydraulic cylinder, e(t) represents the difference between the actual extension amount and the target extension amount, t is a time variable representing the length of the extension process, e(t) = x setpoint -x(t), K p , K i , and K d are the proportional, integral, and differential coefficients of the PID controller, respectively, and e(τ) represents the value of the cumulative extension error at different time points.

[0012] The fitness value is defined based on the performance indicators of the hydraulic cylinder:

[0013] Fitness = w1 x ITAE + w2 x MSE + w3 x Overshoot

[0014]

[0015] Wherein, the integral time absolute error ITAE is to measure the error and response time of the hydraulic cylinder, the mean square error MSE is the steady state error; the overshoot is the overshoot, which is used to represent the maximum deviation of the extension of the hydraulic cylinder before reaching the set value; w1, w2, w3 are weight coefficients, w1 corresponds to ITAE, w2 corresponds to MSE, and w3 corresponds to overshoot; T corresponds to the number of total time periods or the number of total sampling points for calculating the error.

[0016] In addition, the motion analysis of the cross-type fine particle roller screen includes establishing the following motion model:

[0017]

[0018] Wherein, θ1 is the initial pitch angle, θ2 is the angle size of the pitch adjustment, θ1+θ2 is the angle after the pitch control, β1 is the initial swing angle, β2 is the angle size of the swing adjustment, β1+β2 is the angle after the swing control, x is the extension length of the hydraulic cylinder in the swing control device, y is the extension length of the hydraulic cylinder in the pitch control device, A is the distance between the center of rotation of the inner and outer frame connecting device and the same plane between the pitch hydraulic cylinder and the top plate hinge point, B is the distance between the center of rotation of the inner and outer frame connecting device and the pitch hydraulic cylinder connecting seat and the inner frame hinge point, C is the initial length of the pitch hydraulic cylinder, a is the distance from the front support frame hinge point to the support swing hydraulic cylinder and the ground contact support frame hinge point, b is the distance from the front support frame hinge point to the swing hydraulic cylinder and the swing hydraulic cylinder connecting seat hinge point, and c is the initial height of the swing hydraulic cylinder.

[0019] In addition, monitoring whether the screening parameters of the cross-type fine particle roller screen meet the optimal screening condition includes: establishing a mathematical model of the material pile; obtaining the screening parameters of the cross-type fine particle roller screen from the mathematical model and determining whether the optimal screening condition is met.

[0020] In addition, the mathematical model of the material pile is established, including:

[0021] The point cloud data of the material pile is obtained by scanning the material pile through the linear array sensor;

[0022] Noise points are removed from the point cloud data and point cloud filtering processing is performed;

[0023] The filtering processing method is statistical filtering, including: judging whether a point is a noise point by calculating the distance of the neighborhood points of each point, and for any point p i =(x i ,y i ,z i ), the average distance d m of the neighborhood points is:

[0024]

[0025] where k is the number of neighborhood points, d(p i ,p j ) represents the distance between p i and neighborhood point p j ;

[0026] The morphology of the material pile is identified by fitting a surface model of the point cloud data using a least square method;

[0027] Specifically, when fitting the surface model using the least square method, a quadratic surface equation is used to approximate the point cloud data, and when scanning the material pile by the linear array sensor, three-dimensional point cloud data (x i ,y i ,z i ) is obtained, and a quadratic surface equation z=ax 2 +by 2 +cxy+dx+ey+f is obtained by fitting, where a, b, c, d, e, and f are fitting coefficients; the specific steps for determining the fitting coefficients are as follows:

[0028] Define an error function:

[0029] Construct the sum of squared errors: where N is the total number of points,

[0030] Construct a linear equation system: Z=Xβ, where,

[0031]

[0032] The fitting parameter β is obtained by solving the following normal equation:

[0033] β=(X T X) -1 X T Z, where X T is the transpose of matrix X, (X T X) -1 is the inverse matrix of X T X;

[0034] Extract the fitting coefficient to obtain the mathematical model of the surface model.

[0035] In addition, adjusting the mechanical system action in the cross-type fine particle roller screen includes:

[0036] Scanning the material pile by the linear array sensor to obtain point cloud data of the material pile for swing control;

[0037] The material thickness of the inlet is obtained by the ultrasonic ranging sensor to control the pitch; the material thickness is calculated by the time difference between the ultrasonic ranging sensor emitting a short ultrasonic pulse and the ultrasonic ranging sensor receiving the ultrasonic signal reflected from the material pile on the screen surface, and the specific calculation formula is:

[0038]

[0039] v = 331.4 + 0.6 x F

[0040] Wherein, S is the distance between the ultrasonic ranging sensor and the material pile, v is the sound velocity, the time difference is K, and the real-time temperature is F.

[0041] The system in the embodiment of the application comprises a cross-type fine particle roller screen, a control system, a communication unit, a monitoring system and an upper computer; the monitoring system is used to monitor whether the screening parameters of the cross-type fine particle roller screen meet the optimal screening condition; when the optimal screening condition is not met, the upper computer reads the screening parameters, optimizes the screening parameters by a preset IGWO-BP-PID algorithm to obtain optimized screening parameters, and transmits the optimized screening parameters to the control system; and the control system adjusts the mechanical system in the cross-type fine particle roller screen according to the optimized screening parameters to make the mechanical system meet the optimal screening condition. Through the above system, the mechanical system in the cross-type fine particle roller screen can be automatically and quantitatively adjusted under different complex working conditions, including different screening materials and different material piling conditions, so that different screen surface inclination angles are formed, which is beneficial to cope with different screening operation conditions and ensure smooth screening, and the system can be automatically operated, and the screening efficiency is further improved.

[0042] Compared with the prior art, the application has the following remarkable effects:

[0043] 1. Through the integration of the monitoring, control and optimization modules, the system can realize automatic operation of the screening process, thereby reducing manual intervention and improving the screening efficiency; the system can automatically adjust the screen surface inclination angle and the roller speed according to different working conditions, adapt to changes in the material piling mode and other conditions, realize efficient screening, and has a real-time monitoring and feedback mechanism, so that the operation parameters can be quickly adjusted when the screening conditions change, and the screening process can be continuously operated under the optimal conditions.

[0044] 2. Through the combination of IGWO and BP neural network, the system can realize parameter optimization under complex screening conditions, avoid the problem that the traditional optimization algorithm is easily trapped in local optimization in a multi-dimensional space, capture the complex and nonlinear relationships between many parameters in the screening process by the BP neural network, optimize the screening conditions, improve the screening quality, adjust the rapidly changing working conditions in time by the PID controller, prevent the problems of delayed adjustment or excessive adjustment, and thereby maintain the stability of the screening process. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the structure of a cross-screening parameter optimization system based on IGWO-BP-PID according to an embodiment of the present invention;

[0046] Figure 2 This is a flowchart of the process of a cross-screening parameter optimization system based on IGWO-BP-PID according to an embodiment of the present invention.

[0047] Figure 3 This is a front view of a cross-type fine particle roller screen according to an embodiment of the present invention;

[0048] Figure 4 for Figure 3 The right view. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the various embodiments of the present invention to facilitate a better understanding of this application. However, the technical solutions claimed in this application can be implemented even without these technical details and various changes and modifications based on the following embodiments. The division of the various embodiments below is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0050] One embodiment of the present invention relates to a method and system for optimizing screening parameters of a cross-type fine-particle roller screen based on Improved GreyWolf Optimization (IGWO) algorithm, Back-Propagation Neural Network, and Proportional Integral Derivative (PID) control. The system can be applied to integrated screening tools that include a cross-type fine-particle roller screen, such as... Figure 1As shown, the method can be applied in the host computer. The system in the embodiment of the present application comprises a cross-type fine particle roller screen, a control system, a communication unit, a monitoring system, a host computer; the monitoring system is connected with the host computer through the communication unit, and the monitoring system is used for monitoring whether the screening parameters of the cross-type fine particle roller screen meet the optimal screening condition; when the optimal screening condition is not met, the monitoring system transmits the screening parameters to the host computer through the communication unit; the host computer is also connected with the control system, and the host computer obtains the optimized screening parameters through the preset IGWO-BP-PID algorithm after reading the screening parameters, and transmits the optimized screening parameters to the control system; the control system is also connected with the cross-type fine particle roller screen, and the control system is used for adjusting the mechanical system in the cross-type fine particle roller screen according to the optimized screening parameters to make it meet the optimal screening condition. Through the above system, the mechanical system in the cross-type fine particle roller screen can be automatically adjusted quantitatively under different complex working conditions, including different types of screening materials and different stacking conditions, so that different screen surface inclination angles are formed, which can be beneficial to cope with different screening operation conditions and ensure smooth screening. The implementation details of the IGWO-BP-PID-based cross-type fine particle roller screen screening parameter optimization and system of an embodiment of the present application are described below, and the following content is only provided for the implementation details for easy understanding, and is not necessary for implementing the present solution.

[0051] Specifically, the mechanical system of the cross-type fine particle roller screen comprises a screen machine body, an outer frame, an inner frame, a pitch adjusting device and a swing adjusting device. The screen machine body is installed on the inner frame, the inner frame is arranged in the outer frame in a nested manner, the pitch adjusting device is connected to the inner frame and the outer frame, the screen machine body can be adjusted in pitch angle relative to the inner screen frame through the pitch adjusting device, and the swing adjusting device is connected to the ground and the outer frame. The inner frame and the outer frame are connected together, and the screen machine as a whole can swing through the pitch adjusting device.

[0052] The monitoring system comprises a linear array laser sensor, an ultrasonic ranging sensor, an inclination sensor, a displacement sensor and a rotary encoder. The linear array laser sensor is installed near the discharge port of the roller screen, so as to realize scanning of the material distribution on the whole screen surface. The ultrasonic ranging sensor is installed near the inlet of the roller screen, so as to better realize the monitoring effect. The inclination sensor is installed on the inner screen frame, and is used for detecting the pitch angle of the inner screen frame relative to the outer screen frame. There are four displacement sensors, which are respectively installed beside the hydraulic cylinders of the swing adjusting device and the pitch adjusting device, and are used for determining whether the adjustment is completed. The rotary encoder is installed at the end of the eccentric screen roller assembly away from the driving assembly, and is used for monitoring the real-time rotation speed of each eccentric screen roller assembly.

[0053] The communication unit includes industrial Ethernet, chip RS485, and chip RS232. Industrial Ethernet and a standard communication protocol are used as a communication interface, a control system is used as an intermediary, and an industrial standard communication protocol is used to complete cross fine particle roller screen screening parameter transmission and data interaction between units.

[0054] In one embodiment, when the IGWO-BP-PID-based cross fine particle roller screen screening parameter optimization system is in operation, the workflow is as shown in Figure 2 The first step is to obtain the roller screen action. The line array laser sensor collects the material load distribution on the reverse of the screen width, and the ultrasonic ranging sensor collects the material thickness distribution on the screen in the screen length direction, that is, the material flow information, to determine whether the roller screen is in an optimal screening condition. The line array laser sensor and the ultrasonic ranging sensor are used to determine whether the roller screen is in an optimal screening condition. When the line array laser sensor collects the material information on the screen, the sensor first scans the material pile. The laser reflection time and the laser propagation speed of the laser beam emitted by the line array laser sensor to the material pile are used to obtain a large amount of point cloud data. Then, the obtained point cloud data is processed, including removing noise points and point cloud filtering. Then, the least squares method is used to fit the surface model of the point cloud to complete the identification of the material form. Finally, the polynomial coefficients of the surface are extracted to obtain the mathematical model of the surface. When the ultrasonic ranging sensor collects the material thickness information on the screen, the principle is to calculate the material thickness by the time difference between the transmission of a short ultrasonic pulse by the sensor and the reception of the ultrasonic signal reflected from the screen coal particles. The collected data is first processed, and then the data is denoised, filtered, and averaged by multiple measurements. Finally, the host computer processes the data collected by the sensor. When the material flow distribution on the screen is uneven, the pitch control device and the swing control device drive the inner screen frame and the outer screen frame to adjust the angles in two directions, so that the roller screen is always in an optimal screening condition.

[0055] Specifically, monitoring whether the screening parameters of the cross fine particle roller screen meet the best screening condition includes: establishing a mathematical model of the material pile; obtaining the screening parameters of the cross fine particle roller screen from the mathematical model and determining whether the best screening condition is met. Establishing a mathematical model of the material pile includes: scanning the material pile by a line array sensor to obtain point cloud data of the material pile; removing noise points from the point cloud data and performing point cloud filtering; identifying the form of the material pile by fitting a surface model of the point cloud data using the least squares method; and extracting polynomial coefficients of the surface model to obtain a mathematical model of the surface model.

[0056] The filtering method is statistical filtering, which includes determining whether a point is a noise point by calculating the distance of the neighborhood points of each point, and denoising the data for any point p i = (x i ,yi ,z i ), the average distance d m of the neighborhood points of p

[0057]

[0058] wherein k is the number of neighborhood points, d(p i ,p j ) represents the distance between p i and the neighborhood point p j ; and then a surface model of the point cloud data is fitted by using a least square method to realize the form identification of the stockpile; specifically, when the least square method is used to fit the surface model, a quadratic surface equation is used to approximate the point cloud data, when the stockpile is scanned by a linear array sensor, three-dimensional point cloud data (x i ,y i ,z i ) is obtained, and a quadratic surface equation z=ax 2 +by 2 +cxy+dx+ey+f is obtained by fitting, wherein a, b, c, d, e, and f are fitting coefficients; the specific steps for determining the fitting coefficients are as follows:

[0059] an error function is defined as:

[0060] a sum of squared errors is constructed as: wherein N is the total number of points,

[0061] a linear equation system is constructed as: Z=Xβ, wherein,

[0062]

[0063] the fitting parameter β is obtained by solving the following normal equation:

[0064] β=(X T X) -1 X T Z, wherein X T is the transpose of the matrix X, (X T X) -1 is the inverse matrix of X T X; the fitting coefficient is extracted, and the mathematical model of the surface model is obtained.

[0065] The adjustment of the mechanical system action in the cross-type fine particle roller screen includes: the point cloud data of the stockpile is obtained by scanning the stockpile by a linear array sensor to realize swing control; the material thickness of the material inlet is obtained by an ultrasonic ranging sensor to realize pitch control; the material thickness is calculated by the time difference between the transmission of a short ultrasonic pulse by the sensor and the reflection of the ultrasonic signal from the coal particles on the screen surface by the sensor, and the specific calculation formula is:

[0066]

[0067] v = 331.4 + 0.6 x F

[0068] Wherein, S is the distance between the ultrasonic ranging sensor and the stockpile, v is the sound velocity, the time difference is K, and the real-time temperature is F.

[0069] When the data is processed, data filtering and optimization are performed, including data denoising and filtering and averaging of multiple groups of measurements, and finally the output data is the point cloud data of the stockpile. In addition, denoising includes: when processing the point cloud data, a large amount of dust and other interference scanning results will be generated during the operation of the cross screen, so noise points are removed to obtain initial screen surface points. Then the initial screen surface triangular mesh is constructed, the distance between the screen material particles and the screen surface triangular mesh is calculated, and it is judged whether the point cloud data is a noise point or a screen material point. The noise points are removed, and the screen material points are added to the screen point set.

[0070] Specifically, after the data is preprocessed, in order to ensure the accuracy of the screen point cloud data, the point cloud data needs to be denoised and filtered. First, the preliminary noise points are removed. When denoising the point cloud data, the preliminary collected point cloud data is first screened. This step can remove a large number of noise points that deviate significantly from the screen by counting the neighborhood density and distance. The neighborhood density of a certain range around each point is calculated, and the points with low density are noise points. For each point p i =(x i ,y i ,z i ), we calculate the number of neighborhood points M within a certain radius r, and if the number is less than a certain threshold 5, the point is determined to be a noise point. After preliminary denoising, the remaining point cloud data is triangulated to form a rough screen reference framework. The construction of the screen triangular mesh can be realized by the Delaunay triangulation algorithm, and then the distance between the screen material particles and the screen triangular mesh is calculated to determine whether the point cloud data is a noise point or a screen material point. The noise points are removed, and the screen material points are added to the screen point set. Finally, when the point cloud data denoising and screening are completed, the obtained screen material points are further optimized. The point cloud data after multiple denoising, screening and optimization is the screen surface morphology information of the stockpile, which is used for subsequent screen adjustment and control.

[0071] Specifically, the optimized screening parameters obtained through the preset IGWO-BP-PID algorithm include: establishing a corresponding system model based on the motion analysis of the cross-type fine-particle roller screen; designing a PID controller based on the system model; initializing a BP neural network and predicting the control output based on historical data of the mechanical system of the cross-type fine-particle roller screen; and generating an initial PID parameter population using the IGWO algorithm, where each set of parameters represents the K-value of the PID controller. p K i K d , where K p K i K d These are the proportional, integral, and derivative coefficients of the PID controller. The fitness value of each PID parameter group in the initial PID parameter population is calculated using an initialized BP neural network. The population position is updated based on the fitness values, and the optimal PID parameter combination is output as the optimized selection parameters to control the mechanical system. Furthermore, to avoid the initial population distribution being too concentrated or trapped in local optima, chaotic mapping is used instead of traditional random initialization to generate the initial PID parameter population.

[0072] Specifically, the motion analysis of the cross-type fine-particle roller screen includes establishing the following motion model:

[0073]

[0074] Where θ1 is the initial pitch angle; θ2 is the pitch adjustment angle, i.e., the angle changed by the pitch hydraulic cylinder after the pitch control device is activated (the pitch hydraulic cylinder extends or retracts); θ1+θ2 is the angle after pitch adjustment; β1 is the initial swing angle; β2 is the swing adjustment angle, i.e., the angle changed by the swing hydraulic cylinder after the swing control device is activated (the swing hydraulic cylinder extends or retracts); β1+β2 is the angle after swing adjustment; and x is the extension length of the hydraulic cylinder in the swing control device. y is the extension length of the hydraulic cylinder in the pitch control device; A is the distance between the rotation center of the inner and outer frame connecting device and the plane of the pitch hydraulic cylinder hinge point with the top plate; B is the distance between the rotation center of the inner and outer frame connecting device and the hinge point between the pitch hydraulic cylinder connecting seat and the inner frame; C is the initial length of the pitch hydraulic cylinder; a is the distance between the hinge point of the front support frame and the hinge point of the support swing hydraulic cylinder in contact with the ground support frame; b is the distance between the hinge point of the front support frame and the hinge point between the swing hydraulic cylinder and the swing hydraulic cylinder connecting seat; c is the initial height of the swing hydraulic cylinder. In this embodiment, A, B, C, a, b, and c can be respectively derived from… Figure 3 and Figure 4 The measurements were obtained using the cross-type fine-particle roller sieve shown.

[0075] Specifically, in a mechanical system, a PID parameter combination is used to adjust the extension of a hydraulic cylinder to achieve control of the mechanical system.

[0076] Adjusting the extension of the hydraulic cylinder x(t) includes adjusting by the following formula:

[0077]

[0078] where e(t) = x setpoint -x(t), K p , K i , K d are the proportional, integral, and derivative coefficients of the PID controller, respectively, u(t) represents the PID output, x(t) is the actual extension of the hydraulic cylinder, x setpoint represents the target extension of the hydraulic cylinder, e(t) represents the difference between the actual extension and the target extension, t is a time variable representing the length of the extension process, e(t) = x setpoint -x(t), K p , K i , K d are the proportional, integral, and derivative coefficients of the PID controller, respectively, e(τ) represents the value of the cumulative extension error at different time points. By integrating the error over the entire time period (i.e., calculating the cumulative error), the PID controller can effectively adjust the system response to make the actual output closer to the set value.

[0079] The fitness value is defined based on the performance indicators of the hydraulic cylinder:

[0080] Fitness = w1 x ITAE + w2 x MSE + w3 x Overshoot

[0081]

[0082] Wherein, the integral time absolute error ITAE is to measure the error and response time of the hydraulic cylinder, the mean square error MSE is the steady-state error, and the overshoot is the maximum deviation of the extension of the hydraulic cylinder before reaching the set value; w1, w2 and w3 are weight coefficients, w1 corresponds to ITAE, ITAE measures the response performance of the system in time, and reflects the tracking performance of the system to the set value; this weight is usually used to emphasize the importance of reducing the error in time in the control process; w2 corresponds to MSE, MSE measures the average error between the system output and the expected output, and reflects the steady-state accuracy of the system; w3 corresponds to the overshoot, the overshoot refers to the degree of the system output exceeding the steady-state value, and reflects the dynamic characteristics of the system; this weight is used to control the response speed and stability of the system, and ensures that the system does not fluctuate excessively; T corresponds to the total time period or the total number of sampling points for calculating the error. After the PID parameter combination is adjusted by the optimization processing, the extension of the hydraulic cylinder is adjusted to realize the control of the mechanical system, and the adjustment of the screen surface inclination angle can be realized, which is beneficial to the smooth operation of the screening operation. In the system, the adjustment process can be automatically operated, and the efficiency is further improved.

[0083] The embodiments of the present application are described in detail above with reference to the drawings, but the present application is not limited thereto, and various changes can be made within the knowledge of those skilled in the art without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and equivalent technologies thereof, the present application is also intended to include these modifications and variations.

[0084] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and equivalent technologies thereof, the present application is also intended to include these modifications and variations.

Claims

1. An IGWO-BP-PID based cross-sieve screening parameter optimization system, characterized in that, The cross fine particle roller screen, the control system, the communication unit, the monitoring system and the host computer are included. The monitoring system is connected with the host computer through the communication unit, and is used for monitoring whether the screening parameters of the cross fine particle roller screen meet the optimal screening condition. When the optimal screening condition is not met, the monitoring system transmits the screening parameters to the host computer through the communication unit. The host computer is also connected with the control system, and the host computer reads the screening parameters and obtains the optimized screening parameters through the preset IGWO-BP-PID algorithm, and transmits the optimized screening parameters to the control system. The control system is also connected with the cross fine particle roller screen, and the control system is used for adjusting the mechanical system in the cross fine particle roller screen according to the optimized screening parameters to meet the optimal screening condition. The monitoring whether the screening parameters of the cross fine particle roller screen meet the optimal screening condition comprises: establishing a mathematical model of the material pile; obtaining the screening parameters of the cross fine particle roller screen from the mathematical model and judging whether the optimal screening condition is met; the mathematical model of the material pile comprises: scanning the material pile through a linear array sensor to obtain point cloud data of the material pile; removing noise points in the point cloud data and performing point cloud filtering processing; The filtering processing method is statistical filtering, comprising: judging whether a point is a noise point by calculating the distance of the neighborhood points of each point The average distance of the neighborhood points of the point is ​ wherein, is the number of neighborhood points, denotes the distance to a neighborhood point . then fitting a curved surface model of the point cloud data by using a least square method to realize form recognition of the material pile; In the use of least square method fitting curved surface model, through a quadratic surface equation to approach point cloud data, in through linear array sensor scanning stockpile, obtain three-dimensional point cloud data , through fitting to obtain quadratic surface equation , Wherein is fitting coefficient; the specific steps for determining fitting coefficient are: Define the error function: , Construct the sum of squared errors: where, N is the total number of points, Constructing the linear equations: wherein, Fitting parameters By solving the following normal equations: wherein is the transpose of the matrix , is the inverse matrix of ; extracting the fitting coefficients to obtain a mathematical model of the curved surface model.

2. An IGWO-BP-PID-based cross-sieve screening parameter optimization method applied to an upper computer, characterized in that, comprises: receiving the screening parameters which do not meet the optimal screening condition sent by the monitoring system; optimizing the screening parameters through the preset IGWO-BP-PID algorithm to obtain the optimized screening parameters; transmitting the optimized screening parameters to the control system; the optimization of the screening parameters to obtain the optimized screening parameters comprises: establishing a corresponding motion model according to the motion analysis of the cross fine particle roller screen; designing a PID controller according to the system model; initializing a BP neural network, and predicting control output based on historical data of the mechanical system of the cross fine particle roller screen; The IGWO algorithm is used to generate an initial PID parameter population, and each group of parameters represents the PID controller 、 、 wherein, 、 、 are proportional, integral, and derivative coefficients of the PID controller, respectively. calculating the fitness value of each group of PID parameters in the initial PID parameter population by using the initialized BP neural network; updating the population position based on the fitness value, and outputting the optimal PID parameter combination as the optimized screening parameters to control the mechanical system.

3. The method of claim 2, wherein the IGWO-BP-PID based cross-sieve screening parameter optimization method is characterized by, the initial PID parameter population generated by the IGWO algorithm comprises: using a chaotic mapping to generate the initial PID parameter population.

4. The method of claim 2, wherein the method is an IGWO-BP-PID based cross-sieve screening parameter optimization method. In the mechanical system, the PID parameter combination adjusts the elongation of the hydraulic cylinder to control the mechanical system through the following formula: Adjusting the extension of a hydraulic cylinder including adjustment by the equation: wherein, represents a PID output, is an actual extension amount of the hydraulic cylinder, represents a target extension amount of the hydraulic cylinder, represents a difference between the actual extension amount and the target extension amount, is a time variable representing a length of the extension process, , , , are a proportional, integral, and derivative coefficient of the PID controller, respectively, represents a value of the cumulative extension amount error at different time points; the fitness value is defined based on the performance indicators of the hydraulic cylinder: Among them, the integral time absolute error ITAE is to measure the error and response time of the hydraulic cylinder, and the mean square error MSE is to represent the square average of the error; overshoot is the overshoot, which is used to represent the maximum deviation of the extension of the hydraulic cylinder before reaching the set value; 、 、 is a weight coefficient, corresponds to ITAE , corresponds to MSE , corresponds to overshoot ; T corresponds to the number of total time periods or the number of total sampling points for calculating the error.

5. The method of claim 2, wherein the IGWO-BP-PID based cross-sieve screening parameter optimization method is characterized by, The motion analysis of the cross fine particle roller screen comprises establishing the following motion model: wherein, is the initial tilt angle, is the angle size of the tilt adjustment, is the angle after the tilt adjustment, is the initial swing angle, is the angle size of the swing adjustment, is the angle after the swing adjustment, is the extension length of the swing cylinder in the swing adjustment device, is the extension length of the tilt cylinder in the tilt adjustment device, A is the distance between the rotation center of the inner and outer frame connecting device and the same plane of the tilt hydraulic cylinder and the top plate hinge point, B is the distance between the rotation center of the inner and outer frame connecting device and the hinge point between the tilt hydraulic cylinder connecting seat and the inner frame, C is the initial length of the tilt hydraulic cylinder, a is the distance between the front support frame hinge point and the support swing hydraulic cylinder and the ground contact support frame hinge point, b is the distance between the front support frame hinge point and the swing hydraulic cylinder and the swing hydraulic cylinder connecting seat hinge point, c is the initial height of the swing hydraulic cylinder.

6. The IGWO-BP-PID based cross-sieve screening parameter optimization system as claimed in claim 1, wherein, adjusting the mechanical system in the cross fine particle roller screen comprises: scanning the material pile through a linear array sensor to obtain point cloud data of the material pile for swing control; The material thickness at the feeding inlet is obtained by the ultrasonic ranging sensor to control the pitch; the material thickness is calculated by the time difference between the ultrasonic ranging sensor emitting a short ultrasonic pulse and the ultrasonic ranging sensor receiving the ultrasonic signal reflected from the material pile on the screen surface, and the specific calculation formula is: wherein, S is the distance between the ultrasonic ranging sensor and the material pile, v is the speed of sound, the time difference is K is the real-time temperature, F .

Images