Multi-degree-of-freedom vibrating screen control method and system based on the distribution state of undersize materials

Abstract

The present invention provides a multi-degree-of-freedom vibrating screen control method and system based on the distribution state of the sieved material. A plurality of rows of grain counting sensors are arranged below the vibrating screen to monitor the number of grains passing through the vibrating screen. The controller inputs the output signals of α, β and the grain counting sensors into the BP neural network prediction model to obtain the radial distribution coefficient V of the screen surface, substitutes V into the horizontal attitude angle fuzzy control model to obtain the horizontal attitude angle rotation amount Δβ, substitutes the amount d of the grains passing through the screen tail into the inclination angle fuzzy control model to obtain the inclination angle rotation amount Δα, and the controller controls the inclination angle and attitude angle of the vibrating screen according to the horizontal attitude angle rotation amount Δβ and the inclination angle rotation amount Δα. The present invention monitors the sieved grain flow rate in a certain area below the screen, predicts the distribution state of the material on the vibrating screen surface through a model, and proposes a quantitative description index, respectively constructs fuzzy control strategies for the horizontal attitude angle and the inclination angle of the screen surface, realizes the automatic control of the attitude of the vibrating screen surface, and improves the real-time performance and stability of the control system.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent control of sieve surface attitude, and particularly relates to a control method and system for a multi-degree-of-freedom vibrating screen based on the distribution state of sifted materials. Background Art

[0002] Sieving and cleaning is a key operation link in combine harvesting of grains. It can separate the grains and impurities in the mixture after threshing operation. The clean grains are collected into the grain tank, and the impurities are scattered back to the field.

[0003] The distribution state of the mixed materials on the sieve surface is the main factor affecting the performance of the sieving operation. The more uniform the material distribution is, the higher the utilization efficiency of the sieve surface will be, thus improving the performance of the sieving operation. The distribution of materials on the sieve surface will be affected by comprehensive factors such as the feeding distribution of materials, the vibration parameters of the sieve surface, and the sieve surface attitude. Affected by the ground undulation and the threshing working principle, when the threshed mixture is fed onto the sieve surface, it is impossible to be uniform along the radial direction of the sieve surface. The sieve surface adopts the traditional single reciprocating vibration form, which is difficult to achieve uniform dispersion and sifting of materials on the sieve surface, and it is difficult to effectively reduce the loss rate. To improve the rationality of the sieve surface attitude control, it is necessary to obtain the distribution state of materials on the vibrating sieve surface in real time. However, the sieving and cleaning device is a closed structure, and the materials on the vibrating sieve surface are always in a moving state, which is difficult to directly measure. Currently, widely used is to install a grain loss sensor at the sieve tail, and feedback control is carried out by measuring the distribution of lost grains. It cannot provide an accurate control basis and there is a long feedback time lag, resulting in unstable control performance. Summary of the Invention

[0004] Aiming at the above technical problems, one of the purposes of one aspect of the present invention is to provide a control method and system for a multi-degree-of-freedom vibrating screen based on the distribution state of sifted materials. By monitoring the sifted grain flow rate in a certain area below the sieve, predicting the distribution state of materials on the vibrating sieve surface through a model, and proposing quantitative description indexes, respectively constructing fuzzy control strategies for the horizontal attitude angle and the inclination angle of the sieve surface, and integrally developing a control system to realize the automatic control of the sieve surface attitude, improve the real-time performance and stability of the control system, and have important theoretical research significance and practical value for improving the sieving efficiency of grains and the operation performance of the whole machine.

[0005] One of the purposes of one aspect of the present invention is to provide a multi-degree-of-freedom vibrating screen, which can adjust the horizontal attitude angle and the inclination angle of the sieve surface through a parallel mechanism on the basis of traditional reciprocating vibration.

[0006] One of the objectives of one embodiment of the present invention is to achieve automatic control of the attitude of a vibrating screen surface with multiple degrees of freedom during the combined harvesting operation of grains. Through correlation analysis, the correlation coefficients of the material above the screen surface and the material passing through the screen are obtained. Multiple groups of grain counting sensors are installed below the axial position of the screen surface with a relatively large correlation coefficient to monitor the state of grains passing through the screen in different regions. A calculation method for the radial distribution coefficient of the material on the screen surface is proposed, and a neural network is used to construct a mathematical model between the radial distribution coefficient of the grains and the monitoring results of the sensors to obtain the distribution state of the material above the screen surface in real time. Based on the radial distribution coefficient, a fuzzy control method for the horizontal attitude angle of the screen surface is constructed, and a fuzzy control method for the inclination angle of the screen surface is constructed according to the number of grains passing through the screen monitored by the sensors at the screen tail. Using an ARM as the controller, a control system for the attitude of a vibrating screen surface with multiple degrees of freedom is established to automatically control the horizontal attitude angle and inclination angle of the vibrating screen surface, so that the material is evenly and discretely distributed on the screen surface, improving the screening efficiency and reducing the loss rate.

[0007] Note that the description of these objectives does not preclude the existence of other objectives. One embodiment of the present invention does not need to achieve all of the above objectives. Other objectives than the above can be extracted from the description of the specification, drawings, and claims.

[0008] The present invention achieves the above technical objectives through the following technical means.

[0009] A control method for a vibrating screen with multiple degrees of freedom based on the distribution state of the material passing through the screen includes the following steps:

[0010] Arrange multiple rows of grain counting sensors below the vibrating screen, monitor the number of grains passing through the vibrating screen through the grain counting sensors, and transmit the signals to the controller;

[0011] Establish a BP neural network prediction model, a horizontal attitude angle fuzzy control model, and an inclination angle fuzzy control model inside the controller;

[0012] The controller calculates the inclination angle α, the horizontal attitude angle β, and the amount of grains passing through the screen at the screen tail d of the vibrating screen, inputs α, β, and the output signals of the grain counting sensors into the BP neural network prediction model to obtain the radial distribution coefficient V of the screen surface; substitute the obtained radial distribution coefficient V into the horizontal attitude angle fuzzy control model to obtain the rotation amount Δβ of the horizontal attitude angle; substitute the amount of grains passing through the screen at the screen tail d into the inclination angle fuzzy control model to obtain the rotation amount Δα of the inclination angle, and the controller controls the inclination angle and the attitude angle of the vibrating screen according to the rotation amount Δβ of the horizontal attitude angle and the rotation amount Δα of the inclination angle.

[0013] In the above solution, arrange multiple rows of grain counting sensors in the correlation region below the vibrating screen.

[0014] Furthermore, the lower associated area of the vibrating screen is determined by the mean value of the correlation coefficients obtained by analyzing the correlation between the grains above the screen surface of the vibrating screen and the grains passing through the vibrating screen using the discrete element DEM simulation method;

[0015] The mean value of the correlation coefficient is:

[0016]

[0017] where m is the number of groups of simulation experiments, and ρ is is the correlation coefficient of the i-th row in the s-th group of experiments.

[0018] In the above solution, the radial distribution coefficient V is:

[0019]

[0020]

[0021]

[0022] where k is the number of rows divided by the vibrating screen in the simulation, r is the number of columns divided by the vibrating screen in the simulation, P j is the radial position number, P j is symmetric about 0, j = 1, 2, 3... r, x i is the amount of grains in the i-th row area on the screen surface, i = 1, 2, 3... k, x ij is the amount of grains in the i-th row and j-th column area on the screen surface, V i is the radial distribution coefficient of the grains in the i-th row of the screen surface, w i is the weight coefficient of the i-th row, and W i is the normalized weight coefficient of the i-th row.

[0023] Furthermore, the radial distribution coefficient V is between [-1, 1], and its absolute value represents the degree of difference in the distribution of materials along the screen surface. The positive and negative signs represent the left and right sides of the center of the screen surface. The closer V is to 0, the more uniform the distribution.

[0024] In the above solution, the amount of grains passing through the screen at the screen tail d is:

[0025] The sum of the products of the correlation coefficients of the screen tail and each associated area and the monitoring values of the grain counting sensors in the corresponding areas.

[0026] A system for implementing the multi-degree-of-freedom vibrating screen surface attitude control method described above, including a vibrating screen, a grain counting sensor, a displacement sensor, and a controller;

[0027] The vibrating screen is provided with a parallel drive mechanism, a series drive mechanism and a constraint connecting rod, and can realize two translations and two rotations. Among them, the parallel drive mechanism realizes the three-degree-of-freedom motion of the screen surface rotating around the X-axis, Y-axis and translating along the Z-axis, and the series mechanism realizes the one-degree-of-freedom reciprocating motion of the screen surface; one end of the constraint connecting rod is connected to the frame, and the other end is connected to the side surface of the vibrating screen;

[0028] A plurality of rows of grain counting sensors are arranged below the vibrating screen. The grain counting sensors are used to monitor the number of grains passing through the vibrating screen and transmit signals to the controller;

[0029] The controller internally establishes a BP neural network prediction model, a horizontal attitude angle fuzzy control model and an inclination angle fuzzy control model;

[0030] The controller calculates the inclination angle α, the horizontal attitude angle β and the amount d of grains passing through the screen at the tail of the vibrating screen, and inputs α, β and the output signal of the grain counting sensor into the BP neural network prediction model to obtain the radial distribution coefficient V of the screen surface; substituting the obtained radial distribution coefficient V into the horizontal attitude angle fuzzy control model to obtain the horizontal attitude angle rotation amount Δβ; substituting the amount d of grains passing through the screen at the tail into the inclination angle fuzzy control model to obtain the inclination angle rotation amount Δα. The controller controls the inclination angle and the attitude angle of the vibrating screen according to the horizontal attitude angle rotation amount Δβ and the inclination angle rotation amount Δα.

[0031] In the above solution, the parallel drive mechanism includes four groups of parallel adjustment components, namely the first adjustment component, the second adjustment component, the third adjustment component and the fourth adjustment component;

[0032] Each group of adjustments includes a stepping motor, a lead screw, a slider, a slide base and a displacement sensor; the lead screw is installed on the slide base, and the slider and the lead screw are in threaded transmission fit. Driven by the stepping motor, the slider can move linearly along the lead screw;

[0033] The slide base of each group of drive components is installed on the frame. The slider is connected to one end of the connecting rod through a fourth spherical bearing, and the other end of the connecting rod is connected to the vibrating screen through a third spherical bearing; the transmitting end of the displacement sensor is installed vertically downward on the slider, and the displacement ranging plate is installed on the lower end face of the slide base.

[0034] In the above solution, the series drive mechanism includes a DC motor, an eccentric rotating disk and a drive connecting rod;

[0035] One end of the drive connecting rod is connected to the vibrating screen through a second spherical bearing, and the other end of the drive connecting rod is connected to the eccentric rotating disk through a first spherical bearing; the eccentric rotating disk is installed on the output shaft of the DC motor, and the DC motor is installed on the frame cross beam;

[0036] In the above solution, the inclination angle α and the horizontal attitude angle β of the vibrating screen are calculated by the following formula:

[0037]

[0038]

[0039] Among them, H 1 、H 2 、H 3 are the distances from the transmitting ends of three displacement sensors to the displacement ranging plate respectively; L X and L Y are the center distances of the parallel drive components along the X-axis and Y-axis directions respectively.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] The present invention proposes to use the radial distribution coefficient and the amount of sifted grains at the sieve tail to describe the distribution state of materials on the sieve surface. By setting grain counting sensors in the area below the vibrating screen with relatively high correlation, the distribution state of grains passing through the sieve is monitored, and a model is established to predict the distribution state of materials on the sieve surface; taking the radial distribution coefficient as an evaluation index, a control model for the horizontal attitude angle of the sieve surface is constructed, and taking the amount of sifted grains at the sieve tail as an evaluation index, a control model for the inclination angle of the sieve surface is constructed, which can real-time control the attitude of the vibrating screen sieve surface, effectively promote the rapid and uniform distribution of materials on the sieve surface, thereby improving the screening performance and the real-time and stability of the control system.

[0042] Note that the description of these effects does not prevent the existence of other effects. A mode of the present invention does not necessarily have all the above effects. Effects other than the above can be obviously seen and extracted from the descriptions in the specification, drawings, claims, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a schematic structural diagram of a multi-degree-of-freedom vibrating screen screening mechanism according to an embodiment of the present invention Figure 1 ;

[0044] Figure 2 is a schematic structural diagram of a multi-degree-of-freedom vibrating screen screening mechanism according to an embodiment of the present invention Figure 2 ;

[0045] Figure 3 is a schematic structural diagram of an adjusting component according to an embodiment of the present invention;

[0046] Figure 4 is a simulation test diagram according to an embodiment of the present invention;

[0047] Figure 5 is a schematic diagram of the sifting monitoring area according to an embodiment of the present invention;

[0048] Figure 6is the BP neural network model of an embodiment of the present invention;

[0049] Figure 7 is the fuzzy rule control table of the horizontal attitude angle of an embodiment of the present invention;

[0050] Figure 8 is the fuzzy rule control table of the inclination angle of an embodiment of the present invention;

[0051] Figure 9 is the electrical connection diagram of the control system of an embodiment of the present invention;

[0052] Figure 10 is the working principle diagram of the control system of an embodiment of the present invention.

[0053] Among them, 1. frame; 2. vibrating screen; 311. first adjusting component; 312. second adjusting component; 313. third adjusting component; 314. fourth adjusting component; 4. displacement sensor; 401. first displacement sensor; 402. second displacement sensor; 403. third displacement sensor; 404. fourth displacement sensor; 5. first constraint link; 6. first grain counting sensor group; 7. DC motor; 8. eccentric rotating disc; 9. first spherical bearing; 10. driving link; 11. second constraint link; 12. second spherical bearing; 13. second grain counting sensor group; 14. third grain counting sensor group; 301. third spherical bearing; 302. link; 303. fourth spherical bearing; 304. stepper motor; 305. lead screw; 306. slider; 307. slide base; 308. displacement ranging plate; 15. controller; 16. DC motor driver; 17. stepper motor driver. Specific embodiments

[0054] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0055] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "front", "rear", "left", "right", "upper", "lower", "axial", "radial", "vertical", "horizontal", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise specifically defined.

[0056] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "joined", "fixed", etc. shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] Combined with Figure 1 and Figure 2 As shown, in an embodiment of the present invention, a system for a multi-degree-of-freedom vibrating screen control method based on the distribution state of the material passing through the screen includes a vibrating screen 2, a grain counting sensor, a displacement sensor 4, and a controller 15;

[0058] The vibrating screen 2 is provided with a parallel drive mechanism, a series drive mechanism, and a constraint link, and can achieve two translations and two rotations. Among them, the parallel drive mechanism realizes the three-degree-of-freedom movement of the screen surface rotating around the X-axis and Y-axis and translating along the Z-axis, and the series mechanism realizes the one-degree-of-freedom reciprocating movement of the screen surface; one end of the constraint link is connected to the frame, and the other end is connected to the side surface of the vibrating screen 2; a plurality of rows of grain counting sensors are arranged below the vibrating screen 2, and the grain counting sensors are used to monitor the number of grains passing through the vibrating screen 2 and transmit the signals to the controller 15;

[0059] The controller 15 internally establishes a BP neural network prediction model, a horizontal attitude angle fuzzy control model, and an inclination angle fuzzy control model;

[0060] The controller 15 inputs the inclination angle α, the horizontal attitude angle β, and the amount d of the grains passing through the sieve tail of the vibrating screen 2 obtained by calculation, as well as the output signals of the α, β, and the grain counting sensor, into the BP neural network prediction model to obtain the radial distribution coefficient V of the sieve surface; substitutes the obtained radial distribution coefficient V into the horizontal attitude angle fuzzy control model to obtain the rotation amount Δβ of the horizontal attitude angle; substitutes the amount d of the grains passing through the sieve tail into the inclination angle fuzzy control model to obtain the rotation amount Δα of the inclination angle. The controller 15 controls the inclination angle and the attitude angle of the vibrating screen 2 according to the rotation amount Δβ of the horizontal attitude angle and the rotation amount Δα of the inclination angle.

[0061] In an embodiment of the present invention, the parallel drive mechanism includes four groups of parallel adjustment components 3, namely a first adjustment component 311, a second adjustment component 312, a third adjustment component 313, and a fourth adjustment component 314;

[0062] Each group of adjustments includes a stepping motor 304, a lead screw 305, a slider 306, a slide base 307, and a displacement sensor 4; the lead screw 305 is installed on the slide base 307, and the slider 306 is in threaded transmission cooperation with the lead screw 305. Driven by the stepping motor 304, the slider 306 can move linearly along the lead screw 305;

[0063] The slide base 307 of each group of drive components is installed on the frame, and the slider 306 is connected to one end of the connecting rod 302 through a fourth spherical bearing 303. The other end of the connecting rod 302 is connected to the vibrating screen 2 through a third spherical bearing 301; the transmitting end of the displacement sensor 4 is installed vertically downward on the slider 306, and the displacement ranging plate 308 is installed on the lower end surface of the slide base 307.

[0064] In an embodiment of the present invention, the first adjustment component 311, the second adjustment component 312, the third adjustment component 313, and the fourth adjustment component 314 are respectively fixedly installed on the four vertical columns of the frame 1 and are arranged in a rectangular shape with each other.

[0065] One end of the connecting rod 302 of the first adjustment component 311, the second adjustment component 312, the third adjustment component 313, and the fourth adjustment component 314 is fixedly connected to the four ends of the vibrating screen 2 respectively through a third spherical bearing 301, and the other end of the connecting rod 302 of the first adjustment component 311, the second adjustment component 312, the third adjustment component 313, and the fourth adjustment component 314 is fixedly connected to the sliders 306 of the respective adjustment components through a fourth spherical bearing 303.

[0066] The displacement sensor 4 includes a first displacement sensor 401, a second displacement sensor 402, a third displacement sensor 403, and a fourth displacement sensor 404; the first displacement sensor 401, the second displacement sensor 402, the third displacement sensor 403, and the fourth displacement sensor 404 are respectively installed and fixed on the frame crossbeam beside the first adjusting member 311, the second adjusting member 312, the third adjusting member 313, and the fourth adjusting member 314, and their measuring rods are respectively connected to the sliders 306 of the first adjusting member 311, the second adjusting member 312, the third adjusting member 313, and the fourth adjusting member 314, and it is ensured that the measuring rods and the sliders 306 move synchronously and vertically.

[0067] After the installation is completed, it should be ensured that the connecting rods 302 of the first adjusting member 311, the second adjusting member 312, the third adjusting member 313, and the fourth adjusting member 314 are respectively perpendicular to the ground and parallel to each other, the center line of the slide base 307 is kept vertical, and the screen surface of the vibrating screen 2 is horizontal.

[0068] In an embodiment of the present invention, the series drive mechanism includes a DC motor 7, an eccentric rotating disk 8, and a drive connecting rod 10;

[0069] One end of the drive connecting rod 10 is connected to the vibrating screen 1 through a second spherical bearing 6, and the other end of the drive connecting rod 10 is connected to the eccentric rotating disk 8 through a first spherical bearing 9; the eccentric rotating disk 8 is installed on the output shaft of the DC motor 7, and the DC motor 7 is installed on the frame.

[0070] The side of the vibrating screen 2 is connected to the crossbeam of the frame 1 through a first restraint connecting rod 5 and a second restraint connecting rod 11.

[0071] After the installation is completed, it should be ensured that the first restraint connecting rod 5 and the second restraint connecting rod 11 are parallel to each other, forming a parallelogram structure, and the lengths of the first restraint connecting rod 5 and the second restraint connecting rod 11 are much larger than the eccentricity of the eccentric rotating disk 8 to ensure the motion stability of the vibrating screen 2.

[0072] The driving method of the screen surface movement:

[0073] The reciprocating motion of the vibrating screen 2 is realized by driving the DC motor 7, and the input voltage of the DC motor 7 can be controlled to control the rotation speed ω of the DC motor 7 0 , to realize the adjustment of the vibration frequency f = ω 0 / 2π.

[0074] Define the horizontal attitude angle β as the angle of the vibrating screen 2 rotating around the X-axis, with the clockwise direction along the X-axis being positive and the counterclockwise direction being negative; define the inclination angle α as the angle of the vibrating screen 2 rotating around the Y-axis, with the clockwise direction along the Y-axis being positive and the counterclockwise direction being negative.

[0075] In an embodiment of the present invention, the current inclination angle α and the horizontal attitude angle β can be calculated through three groups of displacement sensors 4 therein, and the calculation formulas are as follows:

[0076]

[0077]

[0078] Wherein, H 1 、H 2 and H 3 are the monitoring values of the first displacement sensor 401, the second displacement sensor 402, and the third displacement sensor 403 respectively; L X is the length of the vibrating screen 2, and L Y is the width of the vibrating screen 2.

[0079] When the motors of the first adjusting member 311 and the second adjusting member 312 rotate forward, and the motors of the third adjusting member 313 and the fourth adjusting member 314 rotate in reverse, the vibrating screen 2 tilts backward and the inclination angle α becomes larger; conversely, the vibrating screen 2 tilts forward and the inclination angle α becomes smaller; according to the relative speed v 1 between the slider 306 of the first adjusting member 311 and the slider 306 of the fourth adjusting member 314, the relationship between the rotation inclination angle and the motor rotation time can be calculated

[0080] When the motors of the first adjusting member 311 and the fourth adjusting member 314 rotate forward, and the motors of the second adjusting member 312 and the third adjusting member 313 rotate in reverse, the vibrating screen 2 tilts to the left and the horizontal attitude angle β becomes larger; conversely, the vibrating screen 2 tilts to the right and the horizontal attitude angle β becomes smaller; according to the relative speed v 2 between the slider 306 of the first adjusting member 311 and the slider 306 of the second adjusting member 312, the relationship between the rotation attitude angle and the motor rotation time can be calculated

[0081] By decoupling calculation, the stepping motors 304 of the first adjusting member 311, the second adjusting member 312, the third adjusting member 313, and the fourth adjusting member 314 are driven in parallel to realize the adjustment of the horizontal attitude angle β and the inclination angle α of the vibrating screen 2.

[0082] A multi-degree-of-freedom vibrating screen control method based on the distribution state of the material passing through the screen includes the following steps:

[0083] Arrange multiple rows of grain counting sensors below the vibrating screen 2, monitor the number of grains passing through the vibrating screen 2 through the grain counting sensors, and transmit the signals to the controller 15;

[0084] The controller 15 internally establishes a BP neural network prediction model, a horizontal attitude angle fuzzy control model, and an inclination angle fuzzy control model;

[0085] The controller 15 calculates the inclination angle α, the horizontal attitude angle β, and the amount d of the grains passing through the screen tail of the vibrating screen 2, inputs α, β, and the output signal of the grain counting sensor into the BP neural network prediction model to obtain the radial distribution coefficient V of the screen surface; substitutes the obtained radial distribution coefficient V into the horizontal attitude angle fuzzy control model to obtain the rotation amount Δβ of the horizontal attitude angle; substitutes the amount d of the grains passing through the screen tail into the inclination angle fuzzy control model to obtain the rotation amount Δα of the inclination angle, and the controller 15 controls the inclination angle and the attitude angle of the vibrating screen 2 according to the rotation amount Δβ of the horizontal attitude angle and the rotation amount Δα of the inclination angle.

[0086] In an embodiment of the present invention, multiple rows of grain counting sensors are arranged in the associated area below the vibrating screen 2.

[0087] In an embodiment of the present invention, the associated area below the vibrating screen 2 is determined by the mean value of the correlation coefficients obtained by analyzing the correlation between the grains above the screen surface of the vibrating screen 2 and the grains passing through the vibrating screen 2 by using the discrete element DEM simulation method;

[0088] The mean value of the correlation coefficients is:

[0089]

[0090] where m is the number of groups of simulation experiments, and ρ is is the correlation coefficient of the i-th row in the s-th group of experiments.

[0091] In an embodiment of the present invention, the radial distribution coefficient V is:

[0092]

[0093]

[0094]

[0095] where k is the number of rows divided by the vibrating screen in the simulation, r is the number of columns divided by the vibrating screen in the simulation, P j is the radial position number, P j is symmetric about 0, j = 1, 2, 3... r, x i is the amount of grains in the i-th row area on the screen surface, i = 1, 2, 3... k, x ij is the amount of grains in the i-th row and j-th column area on the screen surface, V i is the radial distribution coefficient of the grains in the i-th row of the screen surface, w i is the weight coefficient of the i-th row, and W i is the normalized weight coefficient of the i-th row.

[0096] In an embodiment of the present invention, the radial distribution coefficient V is between [-1, 1], and its absolute value represents the degree of difference in the distribution of materials along the sieve surface. The positive and negative signs represent the left and right sides of the center of the sieve surface. The closer V is to 0, the more uniform the distribution is.

[0097] In an embodiment of the present invention, the amount of sieve-through grains at the sieve tail d is:

[0098] The sum of the products of the correlation coefficients of the determined sieve tail and each associated region and the monitoring values of the grain counting sensors in the corresponding regions. In an embodiment of the present invention, specifically, the correlation analysis of the materials above the sieve surface and the sieve-through materials is combined with Figure 4 as shown. The selection of the position of the sieve-through monitoring area is combined with Figure 5 as shown. During the screening operation, the materials above the sieve surface and the sieve-through materials are both in motion, and it is difficult to accurately obtain their motion states through experimental methods. Therefore, the discrete element (DEM) simulation method is used to analyze the correlation between the materials above the sieve surface and the sieve-through materials.

[0099] In an embodiment of the present invention, the simulation process of DEM mainly includes three parts: model selection and setting, simulation parameter setting, and post-processing.

[0100] The first step: Model selection and setting

[0101] A vibrating screen solid model was constructed using Solidworks and imported into the EDEM simulation software. The center of the sieve surface coincides with the coordinate origin of the simulation environment, and rotational amounts along the X-axis and Y-axis are added to achieve changes in the inclination angle and horizontal attitude angle. A reciprocating motion along the X-axis is added to achieve the vibration of the sieve surface; a three-dimensional model of agricultural materials is constructed, and a contact mechanics model is selected.

[0102] Four rectangular particle factories arranged in sequence along the Y-axis are added directly above the sieve surface feeding area. By separately setting the particle generation rate of each particle factory, non-uniform feeding of materials during the screening process can be achieved.

[0103] The second step: Simulation parameter setting

[0104] The total particle generation rate of the four rectangular particle factories is set to N, the angle of rotation of the sieve surface around the Y-axis is the inclination angle α, with clockwise being positive and counterclockwise being negative. According to the actual screening operation parameter range, α is set to be adjustable within 2° to 8°; the angle of rotation of the sieve surface around the X-axis is the horizontal attitude angle β, with clockwise being positive and counterclockwise being negative, and β is adjustable within -4° to 4°; the vibration frequency is set to 5 Hz, and the amplitude is 16 mm for simulation tests.

[0105] The third step: Post-processing

[0106] After the simulation is completed, a grid is added to the simulation space to record and analyze information such as the number, position, and velocity of the grains in the grid at each time step.

[0107] The sieve surface is divided into 7 rows and 4 columns along the axial and radial directions, that is, 28 regions. 28 grids are added above and below the 28 regions. The number of grains in the grid space above the sieve surface is denoted as x ij , and the number of grains in the grid space below the sieve surface is denoted as y ij , where i = 1, 2... 7 and j = 1, 2... 4.

[0108] The number of grains in the i-th row along the axial direction of the sieve surface is respectively:

[0109]

[0110] The Person correlation coefficient is selected to describe the correlation between the distribution of the material and the material passing through the sieve. The correlation coefficient is denoted as ρ i

[0111] When the material screening enters the steady state, the number of grains x at n moments is statistically counted i and y i , and the sample data {X i1 , X i2 , …, X in} and {Y i1 , Y i2 , …, Y in} are obtained. The respective means are calculated as

[0112]

[0113] The covariance is

[0114]

[0115] Then the correlation coefficient ρ i can be obtained through the following formula

[0116]

[0117] The particle feeding rate and sieve surface inclination parameters in the EDEM simulation are changed, and m groups of simulation experiments are carried out to obtain m ρ i , and the mean value of the correlation coefficients of each axial region is calculated:

[0118]

[0119] The correlation analysis results show that when there is a large accumulation of grains above the sieve surface, the flow rate of the grains passing through the sieve reaches the maximum, and the phenomenon of sieve saturation is likely to occur, that is, the change in the amount of grains on the sieve surface no longer affects the change in the amount of grains passing through the sieve, and the correlation coefficient is relatively low. This mainly occurs in the material feeding area; as the amount of grains above the sieve surface decreases, the correlation coefficient gradually increases; when there are only a small amount of grains above the sieve surface, due to the randomness of the grains passing through the sieve, the stability of the correlation coefficient will decrease accordingly, that is, the correlation coefficient will show large fluctuations. Obtained through simulation Sorted from largest to smallest as:

[0120] Select The three largest regions for monitoring the grains passing through the sieve, that is, select the area below the first row in the axial direction of the sieve as monitoring area one to install the first grain counting sensor group 6, select the area below the fifth row in the axial direction of the sieve as monitoring area two to install the second grain counting sensor group 13, and select the area below the sixth row in the axial direction of the sieve as monitoring area three to install the third grain counting sensor group 14.

[0121] In an embodiment of the present invention, a monitoring model for the distribution state of grains above the sieve surface is established, and the established BP neural network structure is combined with Figure 5 as shown.

[0122] According to the discrete element (DEM) simulation results of material vibration screening and combined with the monitoring areas of the grain counting sensors, a monitoring model for the distribution state of grains above the sieve surface is constructed using a BP neural network.

[0123] Definition of radial distribution coefficient:

[0124] In order to describe the distribution state of the material above the sieve surface along the radial direction of the sieve, the radial distribution coefficient V is defined as:

[0125]

[0126]

[0127]

[0128] where k = 7, r = 4, the radial position number P j = 2, 1, -1, -2, j = 1, 2, 3, 4, x i is the amount of grains in the i-th row area on the sieve surface, i = 1, 2, 3... k, x ij is the amount of grains in the i-th row and j-th column area on the sieve surface, V i is the radial distribution coefficient of the grains in the i-th row of the sieve surface, w i is the weight coefficient of the i-th row, W i is the normalized weight coefficient of the i-th row.

[0129] The calculated radial distribution coefficient V ranges from -1 to 1. Its absolute value represents the degree of difference in the distribution of materials along the sieve surface. The positive and negative signs represent the left and right sides of the center of the sieve surface. Obviously, the closer V is to 0, the more uniform the distribution is.

[0130] In one embodiment of the present invention, a BP neural network is constructed, combined with Figure 6 as shown:

[0131] A three-layer BP neural network consisting of an input layer, a hidden layer, and an output layer is established. The number of grains in the monitoring areas of 12 grain counting sensors after normalization, the horizontal attitude angle of the sieve surface, and the inclination angle of the sieve surface are used as input parameters, and the radial distribution coefficient of the materials on the sieve surface is used as the output. A BP neural network with 14 inputs and 1 output is constructed.

[0132] The range y of the number of grains monitored by the grain counting sensor ij is between [0, y max , the adjustment range of the inclination angle α of the sieve surface is between [2°, 8°], and the adjustment range of the horizontal attitude angle β is between [-4°, 4°]. The linear normalization method is used to normalize the three input variables, and the calculation formula is as follows:

[0133]

[0134]

[0135]

[0136] The number of neurons in the hidden layer is determined comprehensively according to the empirical formula and multiple test methods. The empirical formula is as follows:

[0137]

[0138] Among them, M is the number of input neurons, M = 14, L is the number of neurons in the hidden layer, L = 10, N is the number of neurons in the output layer, N = 1, and a is generally taken as an integer between 1 and 10, a = 3.

[0139] Select the S-type function as the transfer function of the neurons in the hidden layer, and calculate the output h of neuron q through the following formula q :

[0140]

[0141] Among them, ω pq is the connection weight between the input layer neuron p and the hidden layer neuron q, t p is the p-th input variable. Select the pureline function as the transfer function of the output neuron, and the output O is:

[0142]

[0143] Among them, ω q is the connection weight between the hidden layer neuron q and the output layer neuron, and O is the output V p , taking V as the target output, the error function is defined as:

[0144] E = e 2 = (V - V P ) 2

[0145] Train the network using the LMS algorithm to calculate the weights ω pq and ω q to reduce the overall error. The calculation formula for the connection weight is:

[0146]

[0147]

[0148] Among them, η represents the learning rate.

[0149] BP neural network training method:

[0150] In the EDEM simulation experiment, within a moment after the screening reaches a steady state, y ij (i = 1, 5, 6, j = 1, 2, 3, 4), the radial distribution coefficient V, the inclination angle α of the vibrating screen, and the horizontal attitude angle β are used as inputs, and the radial distribution coefficient V is used as the output, and a set of simulation data can be obtained.

[0151] Within the set range of simulation parameters, by changing the particle generation rate N, the inclination angle α of the vibrating screen, and the horizontal attitude angle β, sm sets of simulation data can be obtained.

[0152] Using m sets of simulation data as training samples and substituting them into the established BP neural network for training until the error meets the set range, the monitoring model for the distribution state of the grains above the sieve surface is obtained. During the actual operation process, only the monitoring results of 12 grain counting sensors, the horizontal attitude angle β of the sieve surface, and the inclination angle α of the sieve surface need to be used as inputs, and the real-time radial distribution coefficient V can be calculated.

[0153] In an embodiment of the present invention, the control method for the horizontal attitude angle of the sieve surface:

[0154] The fuzzy control rule table for the horizontal attitude angle is combined with Figure 7 as shown:

[0155] The control model of the sieve surface horizontal attitude angle is a dual-input fuzzy control model, with the radial distribution coefficient V and the change rate of the radial distribution coefficient ΔV as inputs, and the rotation amount of the horizontal attitude angle Δβ as the output.

[0156] Among them, the change range of the input radial distribution coefficient V is [-1, 1], which is divided into seven levels: -1 to -0.7, -0.7 to -0.4, -0.4 to -0.1, -0.1 to 0.1, 0.1 to 0.4, 0.4 to 0.7, 0.7 to 1; the change range of the change rate of the input radial distribution coefficient ΔV is [-0.2, 0.2], which is divided into seven levels: -0.2 to -0.14, -0.14 to -0.08, -0.08 to -0.02, -0.02 to 0.02, 0.02 to 0.08, 0.08 to 0.14, 0.14 to 0.2; the fuzzy language variables corresponding to V and ΔV are: NB (negative big), NM (negative medium), NS (negative small), ZE (zero), PS (positive small), PM (positive medium), PB (positive big).

[0157] The change range of the output attitude angle rotation amount Δβ is [-3, 3], which is divided into seven levels: -3, -2, -1, 0, 1, 2, 3; the fuzzy language variables corresponding to Δβ are: NB (negative big), NM (negative medium), NS (negative small), ZE (zero), PS (positive small), PM (positive medium), PB (positive big).

[0158] The attitude angle fuzzy control rule is: if the radial distribution coefficient is less than the target interval, the attitude angle should rotate forward, and when the non-uniformity change rate is smaller, the forward rotation angle is larger; if the radial distribution coefficient is greater than the target interval, the attitude angle should rotate backward, and the greater the non-uniformity change rate, the larger the backward rotation angle; if the radial distribution coefficient is in the target interval, the attitude angle state remains unchanged.

[0159] In an embodiment of the present invention, the control method of the inclination angle:

[0160] The fuzzy control rule table of the inclination angle is combined with Figure 8 as shown:

[0161] During the screening operation process, the number of grains above the sieve surface in the material feeding area is the largest. Under the vibration of the sieve surface, the material moves towards the sieve tail, and along with the penetration of the grains through the sieve, therefore, the amount of grains approximately presents a decreasing exponential distribution along the axial direction of the sieve surface.

[0162] There is a certain proportional relationship between the number of grains passing through the sieve at the tail of the sieve and the number of lost grains. If the number of grains passing through the sieve at the tail of the sieve is large, the amount of lost grains will also increase correspondingly; if the number of grains passing through the sieve at the tail of the sieve is very small, it means that the material has completed sieving before being transported to the tail of the sieve, and the material has not been in full contact with the sieve surface, which will cause impurities and grains to pass through the sieve holes together, affecting the cleanliness of the sieved grains. Therefore, the ideal screening state is to be able to control the number of grains passing through the sieve at the tail of the sieve within a certain range, so as to control the amount of lost grains within a certain range, comprehensively improve the utilization efficiency of the sieve surface, and improve the screening efficiency and performance.

[0163] To describe the number of grains passing through the sieve at the tail of the sieve, the amount of grains passing through the sieve at the tail is defined as d:

[0164]

[0165] where y 5 is the number of grains in the grid space of the fifth row under the sieve, is the correlation coefficient of the fifth row, and y 6 is the number of grains in the grid space of the sixth row under the sieve, is the correlation coefficient of the sixth row.

[0166] The particles that fail to pass through the sieve per unit time are recorded as the cleaning loss rate μ, and the calculation formula of μ is:

[0167]

[0168] where is the total amount of grains under the sieve surface per unit time.

[0169] In the EDEM simulation, according to the actual feeding rate of the working material, the total particle generation rate N is set within a suitable range, the sieve surface inclination angle α is changed, and the amount of grains passing through the sieve at the tail d and the cleaning loss rate μ are statistically analyzed at a moment after the screening reaches a steady state.

[0170] The cleaning loss rate μ is between 0% and 10%, and the amount of grains passing through the sieve at the tail d is between 0 and N d During actual operation, the screening performance is better when the cleaning loss rate μ is about 2%, and the corresponding average value of the amount of grains passing through the sieve at the tail d is N 0 , and the inclination control model is designed based on this range.

[0171] The inclination control model is a two-input fuzzy control model, with the amount of grains passing through the sieve at the tail d and the change rate of the amount of grains passing through the sieve at the tail Δd as inputs, and the inclination rotation amount Δα as the output.

[0172] Among them, the change range of the input amount of the amount of grains passing through the sieve at the tail d is [0, N d , so it is divided into 0 - 0.4N0 , 0.4N 0 ~0.9N 0 , 0.9N 0 ~1.1N 0 , 1.1N 0 ~1.5N 0 , 1.5N 0 ~N d Five levels; the change range of the change rate Δd of the amount of sieved grains passing through the sieve tail of the input amount is [-dN d , dN d , and it is divided into -dN d ~-0.6dN d , -0.6dN d ~-0.2dN d , -0.2dN d ~0.2dN d , 0.2dN d ~0.6dN d , 0.6dN d ~dN d Five levels; the fuzzy language variables corresponding to d and Δd are: NB (Negative Big), NS (Negative Small), ZE (Zero), PS (Positive Small), PB (Positive Big).

[0173] The change range of the output attitude angle rotation amount Δα is [-2, 2], and it is divided into five levels: -2, -1, 0, 1, 2; the fuzzy language variable corresponding to Δα is: NB (Negative Big), NS (Negative Small), ZE (Zero), PS (Positive Small), PB (Positive Big).

[0174] The fuzzy control rule of the inclination angle is: if the amount of sieved grains passing through the sieve tail d is less than the appropriate range, the inclination angle should rotate forward, and when the change rate Δd of the amount of sieved grains passing through the sieve tail is smaller, the forward rotation angle is larger; if the amount of sieved grains passing through the sieve tail d is greater than the appropriate range, the inclination angle should rotate backward, and when the change rate Δd of the amount of sieved grains passing through the sieve tail is larger, the backward rotation angle is larger; if the amount of sieved grains passing through the sieve tail d is within the appropriate range, the inclination angle remains unchanged.

[0175] In an embodiment of the present invention, the three-degree-of-freedom hybrid vibration sieve 2 is controlled and electrically connected as shown in Figure 9 shown.

[0176] Use ARM as the controller 15.

[0177] The first displacement sensor 401, the second displacement sensor 402, the third displacement sensor 403, and the fourth displacement sensor 404 are connected to the input end of the controller 15.

[0178] The output ends of the first grain counting sensor group 6, the second grain counting sensor group 13, and the third grain counting sensor group 14 are connected to the input end of the controller 15.

[0179] The output end of the controller 15 is connected to the input end of the DC motor driver 16, and the output end of the DC motor driver 16 is connected to the DC motor 7.

[0180] The output end of the controller 15 is connected to the input ends of four stepper motor drivers 17, and the output ends of the four stepper motor drivers 17 are respectively connected to four stepper motors 304.

[0181] In a specific embodiment of the present invention, in combination with Figure 10 describe the operation process of the multi-degree-of-freedom vibrating screen control system based on the distribution state of the material passing through the screen:

[0182] The controller 15 takes ARM as the core, and a BP neural network prediction model, a horizontal attitude angle fuzzy control model, and an inclination angle fuzzy control model are established inside the controller 15.

[0183] During the working process, the controller 15 collects 12 output signals y of the first grain counting sensor group 6, the second grain counting sensor group 13, and the third grain counting sensor group 14 in real time 11 、y 12 …y 64 ; The controller 15 collects the output signals H of the first displacement sensor 401, the second displacement sensor 402, the third displacement sensor 403, and the fourth displacement sensor 404 in real time 1 、H 2 、H 3 、H 4 ; According to the formulas and calculate to obtain the inclination angle α and the horizontal attitude angle β of the vibrating screen 2; According to the formula calculate to obtain the amount of grains passing through the screen at the screen tail d.

[0184] Substitute the obtained α, β, y 11 、y 12 …y 64 into the established BP neural network prediction model to obtain the radial distribution coefficient V of the screen surface.

[0185] Substitute the obtained radial distribution coefficient V into the attitude angle fuzzy control rule table for fuzzy inference to obtain the horizontal attitude angle rotation amount Δβ.

[0186] Substitute the obtained amount of grains passing through the screen at the screen tail d into the inclination angle fuzzy control rule table for fuzzy inference to obtain the inclination angle rotation amount Δα.

[0187] According to the formula and the formula Obtain the rotation time of each motor.

[0188] The controller 15 controls the rotation time and rotation direction of the four stepper motors 304 to adjust the inclination angle and attitude angle of the vibrating screen 2.

[0189] In the present invention, by monitoring the flow rate of the sifted grains in a certain area below the sieve, the distribution state of the material on the vibrating screen surface is predicted through a model, and quantitative description indexes are proposed. Fuzzy control strategies for the horizontal attitude angle and inclination angle of the sieve surface are respectively constructed, and a control system is integrally developed to realize the automatic control of the attitude of the vibrating screen surface, improve the real-time performance and stability of the control system, and have important theoretical research significance and practical value for improving the screening efficiency of grains and the operating performance of the whole machine.

[0190] When the present invention is used for the operation of a combine harvester for grains, it realizes the automatic control of the attitude of the vibrating screen surface with multiple degrees of freedom. Through correlation analysis, the correlation coefficient of the distribution of the material above the sieve surface and the sifted material is obtained. Multiple groups of grain counting sensors are installed below the axial position of the sieve surface with a relatively large correlation coefficient to monitor the sifting state of the grains in different areas; a calculation method for the radial distribution coefficient of the material on the sieve surface is proposed, and a mathematical model of the radial distribution coefficient of the grains and the monitoring results of the sensors is constructed by using a neural network to obtain the distribution state of the material above the sieve surface in real time; based on the radial distribution coefficient, a fuzzy control method for the horizontal attitude angle of the sieve surface is constructed, and a fuzzy control method for the inclination angle of the sieve surface is constructed according to the number of sifted grains monitored by the sensor at the sieve tail; with an ARM as the controller, a control system for the attitude of the vibrating screen surface with multiple degrees of freedom is established to automatically control the horizontal attitude angle and inclination angle of the vibrating screen surface, so that the material is evenly and discretely distributed on the sieve surface, improving the screening efficiency and reducing the loss rate.

[0191] It should be understood that although this specification is described according to each embodiment, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0192] The series of detailed descriptions listed above are only specific descriptions of the feasible embodiments of the present invention, and they are not used to limit the protection scope of the present invention. Any equivalent embodiments or changes made without departing from the technical spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. Multi-degree-of-freedom vibrating screen control method based on the distribution state of sifted materials, characterized in that, it includes the following steps: Arrange multiple rows of grain counting sensors below the vibrating screen (2), monitor the number of grains passing through the vibrating screen (2) through the grain counting sensors, and transmit the signals to the controller (15); Establish a BP neural network prediction model, a horizontal attitude angle fuzzy control model and an inclination angle fuzzy control model inside the controller (15); The controller (15) calculates the inclination angle α, the horizontal attitude angle β and the sifted grain quantity d at the screen tail of the vibrating screen (2), inputs α, β and the output signals of the grain counting sensors into the BP neural network prediction model to obtain the radial distribution coefficient V of the screen surface; substitute the obtained radial distribution coefficient V into the horizontal attitude angle fuzzy control model to obtain the horizontal attitude angle rotation amount Δβ; substitute the sifted grain quantity d at the screen tail into the inclination angle fuzzy control model to obtain the inclination angle rotation amount Δα, and the controller (15) controls the inclination angle and the attitude angle of the vibrating screen (2) according to the horizontal attitude angle rotation amount Δβ and the inclination angle rotation amount Δα; The sifted grain quantity d at the screen tail is: The sum of the products of the correlation coefficients of the determined screen tail and each correlation region and the monitoring values of the grain counting sensors in the corresponding regions; The inclination angle α and the horizontal attitude angle β of the vibrating screen (2) are calculated by the following formula: Among them, H 1 , H 2 , H 3 are respectively the distances from the emission ends of three displacement sensors (4) to the displacement ranging plate (308); L X and L Y are respectively the center distances of the parallel drive components along the X-axis and Y-axis directions.

2. The multi-degree-of-freedom vibrating screen control method based on the distribution state of sifted materials according to claim 1, characterized in that, Arrange multiple rows of grain counting sensors in the correlation regions below the vibrating screen (2).

3. The multi-degree-of-freedom vibrating screen control method based on the distribution state of sifted materials according to claim 2, characterized in that, The correlation regions below the vibrating screen (2) are determined by the mean value of the correlation coefficients obtained by analyzing the correlation between the grains above the screen surface of the vibrating screen (2) and the distribution of the grains passing through the vibrating screen (2) using the discrete element DEM simulation method; The mean value of the correlation coefficients is: where m is the number of groups of simulation experiments, and ρ is is the correlation coefficient of the i-th row in the s-th group of experiments.

4. The multi-degree-of-freedom vibrating screen control method based on the distribution state of sifted materials according to claim 1, characterized in that, The radial distribution coefficient V is: where k is the number of rows into which the vibrating screen is divided in the simulation, r is the number of columns into which the vibrating screen is divided in the simulation, P j is the radial position number, P j is symmetric about 0, j = 1, 2, 3... r, x i is the amount of grains in the i-th row area on the sieve surface, i = 1, 2, 3... k, x ij is the amount of grains in the area of the i-th row and j-th column on the sieve surface, V i is the radial distribution coefficient of the grains in the i-th row of the sieve surface, w i is the weight coefficient of the i-th row, W i is the normalized weight coefficient of the i-th row.

5. The multi-degree-of-freedom vibrating screen control method based on the distribution state of sifted materials according to claim 4, characterized in that, The radial distribution coefficient V is between [-1, 1], and its absolute value represents the degree of difference in the distribution of materials along the screen surface. The positive and negative signs represent the left and right sides of the center of the screen surface. The closer V is to 0, the more uniform the distribution.

6. A system for implementing the multi-degree-of-freedom vibrating screen control method based on the distribution state of sifted materials according to any one of claims 1-5, characterized in that, it includes a vibrating screen (2), grain counting sensors, displacement sensors and a controller (15); The vibrating screen (2) is provided with a parallel drive mechanism, a series drive mechanism and a constraint link, and can realize two translations and two rotations. Among them, the parallel drive mechanism realizes the three-degree-of-freedom motion of the screen surface rotating around the X-axis, Y-axis and translating along the Z-axis, and the series mechanism realizes the one-degree-of-freedom reciprocating motion of the screen surface; one end of the constraint link is connected to the frame, and the other end is connected to the side surface of the vibrating screen (2); a plurality of rows of grain counting sensors are arranged below the vibrating screen (2), and the grain counting sensors are used to monitor the number of grains passing through the vibrating screen (2) and transmit signals to the controller (15); The controller (15) internally establishes a BP neural network prediction model, a horizontal attitude angle fuzzy control model and an inclination angle fuzzy control model; The controller (15) calculates the inclination angle α, the horizontal attitude angle β and the amount of sifted grains d at the screen tail of the vibrating screen (2), inputs α, β and the output signal of the grain counting sensor into the BP neural network prediction model to obtain the radial distribution coefficient V of the screen surface; substitutes the obtained radial distribution coefficient V into the horizontal attitude angle fuzzy control model to obtain the horizontal attitude angle rotation amount Δβ; substitutes the amount of sifted grains d at the screen tail into the inclination angle fuzzy control model to obtain the inclination angle rotation amount Δα, and the controller (15) controls the inclination angle and attitude angle of the vibrating screen (2) according to the horizontal attitude angle rotation amount Δβ and the inclination angle rotation amount Δα.

7. The system of the multi-degree-of-freedom vibrating screen control method based on the distribution state of the sifted material according to claim 6, Characterized in that, The parallel drive mechanism includes four groups of parallel adjustment components (3), namely a first adjustment component (311), a second adjustment component (312), a third adjustment component (313) and a fourth adjustment component (314); Each group of adjustments includes a stepping motor (304), a lead screw (305), a slider (306), a slide base (307) and a displacement sensor (4); the lead screw (305) is installed on the slide base (307), and the slider (306) is in threaded transmission cooperation with the lead screw (305). Driven by the stepping motor (304), the slider (306) can move linearly along the lead screw (305); The slide base (307) of each group of drive components is installed on the frame, the slider (306) is connected to one end of the connecting rod (302) through a fourth spherical eye bearing (303), and the other end of the connecting rod (302) is connected to the vibrating screen (2) through a third spherical eye bearing (301); the transmitting end of the displacement sensor (4) is vertically downward installed on the slider (306), and the displacement ranging plate (308) is installed on the lower end surface of the slide base (307).

8. The system of the multi-degree-of-freedom vibrating screen control method based on the distribution state of the sifted material according to claim 6, Characterized in that, The series drive mechanism includes a DC motor (7), an eccentric rotating disk (8) and a drive connecting rod (10); One end of the driving connecting rod (10) is connected to the vibrating screen (2) through a second spherical bearing (12), and the other end of the driving connecting rod (10) is connected to the eccentric rotating disc (8) through a first spherical bearing (9); the eccentric rotating disc (8) is installed on the output shaft of the DC motor (7), and the DC motor (7) is installed on the frame.

Images