A polysilicon silicon charge sorting apparatus
By combining a visual recognition unit and a rejection actuator, the problem of particle size deviation in polysilicon sorting equipment is solved, realizing automated sorting, improving the size qualification rate and product consistency of silicon material, and reducing the reliance on manual intervention.
Patent Information
- Application Number
- CN202521788853.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-21
- Publication Date
- 2026-08-25
- Estimated Expiration
- 2035-08-21
AI Technical Summary
Existing polysilicon material sorting equipment suffers from particle size deviation, leading to the mixing of substandard materials, which affects product quality. Furthermore, relying on manual sorting results in low efficiency and lack of control.
The system uses a visual recognition unit to detect the size of silicon material in real time, and sorts out the oversized material to the corresponding bin through a rejection actuator. Combined with a vibrating feeder and a grading collection unit, it achieves automated sorting.
It improves the size qualification rate of silicon material after sorting, enhances product consistency and customer satisfaction, eliminates the manual re-inspection process, avoids quality fluctuations, and improves sorting efficiency.
Smart Images

Figure CN224673231U_ABST
Abstract
Description
Technical Field
[0001] This utility model relates to the field of polycrystalline silicon production technology, and in particular to a polycrystalline silicon material sorting device. Background Technology
[0002] Currently, the sorting of polysilicon raw materials in the polysilicon industry mostly uses a combination of crushers and screening machines for particle size separation. However, due to the irregularity of the particle size after crushing, and limitations imposed by factors such as screen aperture diameter, screen density, and screen blockage, a certain percentage of the screened polysilicon exhibits a diameter deviation. Taking reprocessed feedstock as an example, the linear dimension requirement is 5-50mm, with a requirement that silicon particles larger than 50mm be less than 5%. However, in actual production, this occasionally exceeds 7%. Even if the percentage doesn't exceed the standard, some silicon particles still exhibit severely excessive linear dimensions on their longest diagonal. During actual crushing, silicon particles with a linear dimension of 80mm (long strips) may leak into the reprocessed feedstock, leading to size deviations and affecting product quality. To ensure product quality, additional personnel are required for sorting, which is not only labor-intensive and inefficient but also results in unpredictable outcomes (whether qualified samples are selected depends on the operator's level of responsibility). Summary of the Invention
[0003] In view of the above situation and to overcome the defects of the prior art, the purpose of this utility model is to provide a polycrystalline silicon material sorting device, which solves the technical problem that the silicon material after sorting by the existing sorting device still has a certain degree of particle size deviation.
[0004] To achieve the above objectives, this utility model provides the following technical solution:
[0005] A polycrystalline silicon material sorting device includes: a conveying mechanism; a vision recognition unit disposed above the conveying mechanism for real-time detection of the size of the silicon material on the conveying mechanism; a rejection execution mechanism disposed on one side of the discharge end of the conveying mechanism; a grading collection unit disposed below the conveying mechanism and the rejection execution mechanism; and a controller electrically connected to the vision recognition unit and the rejection execution mechanism for controlling the action of the rejection execution mechanism based on the detection result of the vision recognition unit.
[0006] This invention can detect the maximum diagonal size and volume characteristics of silicon material in real time, and sort it into the corresponding bins through a rejection mechanism. This completely solves the problems of missed screening and incorrect screening caused by the irregular shape of silicon material in traditional screening processes. It effectively improves the size qualification rate of the sorted silicon material, avoids the mixing of materials exceeding 80mm in size, and significantly improves product consistency and customer satisfaction. Moreover, the entire process requires no manual supervision and eliminates the need for manual re-inspection, avoiding quality fluctuations caused by human factors and resulting in high sorting efficiency.
[0007] Optionally, the sorting equipment further includes: a vibrating feeder, disposed at the feed end of the conveying mechanism; the vibrating feeder includes: a hopper, disposed above the feed end of the conveying mechanism; and a vibrator, mounted on the hopper, for vibratingly conveying the silicon material in the hopper to the conveying mechanism.
[0008] Optionally, the rejection mechanism includes: an actuator disposed on one side of the discharge end of the conveying mechanism; and a pusher plate disposed on the movable end of the actuator; wherein the input end of the actuator is electrically connected to the controller, and the controller controls the extension and retraction of the actuator according to the silicon material size detected by the visual recognition unit.
[0009] Optionally, the rejection mechanism includes: multiple actuators arranged along the width direction of the conveying mechanism; each actuator has a push plate at its movable end; wherein the input end of each actuator is electrically connected to a controller, and the controller controls the actuator at the corresponding position to move according to the silicon material size and position information detected by the visual recognition unit.
[0010] Optionally, the pusher plate has an inclined surface on the side facing the conveying mechanism.
[0011] Optionally, the actuator is an electric cylinder or a pneumatic cylinder.
[0012] Optionally, the graded collection unit comprises: a first hopper located below one side of the rejection actuator; and a second hopper located next to the first hopper; wherein, when the size of the silicon material detected by the visual recognition unit is greater than a preset value, the controller controls the rejection actuator to push the silicon material into the second hopper.
[0013] Optionally, the graded collection unit includes a first hopper, a second hopper, and a third hopper arranged sequentially along the pushing direction of the rejection actuator; wherein, when the size of the silicon material detected by the visual recognition unit is greater than a first preset value, the rejection actuator extends to a first stroke to push the silicon material into the second hopper; when the size of the silicon material detected by the visual recognition unit is greater than a second preset value, the rejection actuator extends to a second stroke to push the silicon material into the third hopper.
[0014] Optionally, each silo has an open top and a discharge port at the bottom, with a corresponding conveying device below each discharge port.
[0015] Optionally, the visual recognition unit includes a high-definition CCD camera.
[0016] Optionally, the output of the visual recognition unit is connected to the input of the computer, the output of the computer is connected to the input of the controller, the output of the controller is connected to the input of the rejection actuator, the visual recognition unit acquires silicon material image data, the computer processes the image data and identifies the silicon material size, and the controller controls the rejection actuator according to the recognition result.
[0017] Compared with the prior art, the beneficial effects of this utility model are as follows:
[0018] This invention utilizes AI visual recognition technology to detect the maximum diagonal size and volume characteristics of silicon material in real time. By using a rejection mechanism to sort the material into corresponding bins, it completely solves the problems of missed or incorrect screening caused by the irregular shape of silicon material in traditional screening processes. This effectively improves the size qualification rate of the sorted silicon material, preventing the mixing of materials exceeding 80mm in size. Simultaneously, it enables the identification and sorting of silicon material conditions, significantly improving product consistency and customer satisfaction. Furthermore, the entire process requires no manual supervision and eliminates the need for manual re-inspection, avoiding quality fluctuations caused by human factors and resulting in high sorting efficiency. Attached Figure Description
[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 This is a schematic diagram of the structure of this utility model.
[0021] Figure 2 This is a schematic diagram of the structure of the present invention without the actuator.
[0022] Reference numerals: 1. Vibrating feeder; 11. Feed hopper; 12. Vibrator; 2. Conveying mechanism; 3. Vision recognition unit; 4. Rejection actuator; 41. Actuator; 42. Push plate; 421. Inclined surface; 5. Grading and collection unit; 51. First hopper; 52. Second hopper; 53. Third hopper; 6. Controller; 7. Conveying device; 8. Computer. Detailed Implementation
[0023] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the embodiments of this utility model application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.
[0024] In the description of the embodiments of this utility model application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", "end", "side" etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, are only for the convenience of describing the embodiments of this utility model application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the embodiments of this utility model application.
[0025] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of this utility model application, "multiple" means two or more, unless otherwise explicitly specified.
[0026] In the embodiments of this utility model application, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a communication connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this utility model application according to the specific circumstances.
[0027] In the embodiments of this utility model application, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature being directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.
[0028] The following disclosure provides many different implementations or examples for carrying out different structures of the embodiments of this utility model application. To simplify the disclosure of the embodiments of this utility model application, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the embodiments of this utility model application. Furthermore, reference numerals and / or reference letters may be repeated in different examples of the embodiments of this utility model application; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various implementations and / or arrangements discussed.
[0029] The embodiments of this utility model will now be described in detail with reference to the accompanying drawings.
[0030] Example 1
[0031] like Figure 1 and Figure 2 As shown in the figure, this utility model application provides a polycrystalline silicon material sorting device, including a vibrating feeding mechanism 1, a conveying mechanism 2, a vision recognition unit 3, a rejection execution mechanism 4, a grading collection unit 5, and a controller 6.
[0032] Vibrating feeder 1 is located at the feed end of conveying mechanism 2, rejection actuator 4 is located on one side of the discharge end of conveying mechanism 2, vision recognition unit 3 is located above conveying mechanism 2 for real-time detection of silicon material size entering the detection area, grading collection unit 5 is located below conveying mechanism 2 and rejection actuator 4, and controller 6 is electrically connected to vision recognition unit 3 and rejection actuator 4 respectively. Controller 6 receives detection signals from vision recognition unit 3 and controls the opening and closing of rejection actuator 4 according to the detection signals.
[0033] In use, the AI intelligent recognition system is first used to model the size of the silicon material and set the size to be rejected. Then, the vibrating feeding mechanism 1 feeds the silicon material to be sorted onto the conveying mechanism 2. The conveying mechanism 2 drives the silicon material into the detection area of the vision recognition unit 3. The vision recognition unit 3 identifies the silicon material in the detection area. When the size of the silicon material exceeds the preset value, the rejection execution mechanism 4 is activated to reject the silicon material that exceeds the standard.
[0034] Optionally, the vibrating feeding mechanism 1 includes a material box 11 and a vibrator 12. The material box 11 is located above the feeding end of the conveying mechanism 2. Under the action of the vibrator 12, the silicon material inside the material box 11 is fed onto the conveying mechanism 2. Under the action of vibration, the silicon material can be dispersed and arranged on the conveying mechanism 2, which is conducive to the visual recognition unit 3 to perform detection and the rejection execution mechanism 4 to reject.
[0035] Optionally, conveyor 2 may be a belt conveyor.
[0036] Optionally, the graded collection unit 5 includes at least two hoppers.
[0037] Optionally, each silo has an open top and a discharge port at the bottom. Each discharge port is equipped with a conveying device 7, which is used to transport the sorted silicon material to a designated location.
[0038] Example 2
[0039] like Figure 2 As shown, this utility model application provides a rejection execution mechanism 4, which includes an actuator 41 and a push plate 42 disposed at the movable end of the actuator 41. The input end of each actuator 41 is electrically connected to a controller 6. The controller 6 adjusts the action of the corresponding actuator 41 according to the size of the silicon material, so that the actuator 41 drives the push plate 42 to push the corresponding silicon material into the corresponding hopper.
[0040] Preferably, the rejection mechanism 4 includes multiple actuators 41, which are arranged along the width direction of the conveying mechanism 2. Each actuator 41 has a push plate 42 at its movable end. The input end of each actuator 41 is electrically connected to the controller 6. The controller 6 precisely controls the action of the actuators 41 in the corresponding area according to the silicon material size and position information detected by the vision recognition unit 3, so that the push plate 42 acts only on the target silicon material in front and pushes it into the designated hopper.
[0041] In operation, when the vision recognition unit 3 detects excessive silicon material at a certain location, the controller 6 activates the corresponding actuator 41, and the pusher plate 42 pushes the silicon material to the target bin. Through multiple independently controlled actuators and pushers, each actuator 41 only sorts the silicon material directly in front of it, avoiding erroneous actions that could interfere with adjacent silicon materials. The coordinated operation of multiple actuators allows for the simultaneous removal of excessive material from different areas of the conveying mechanism 2, resulting in high sorting efficiency. The specific number of actuators 41 can be flexibly increased or decreased according to production capacity requirements.
[0042] Optionally, actuator 41 can be an electric cylinder or a pneumatic cylinder.
[0043] Optionally, the pusher plate 42 has an inclined surface 421 on the side facing the conveying mechanism 2. In use, in the initial state (when the actuator is not activated), the pusher plate 42 is located above and to the left of the first hopper 51. In this way, when the silicon material is thrown out in a parabolic trajectory under the action of inertia, the pusher plate 42 can block some of the silicon material that meets the standard. That is, some of the thrown silicon material can fall into the first hopper below after passing through the slope formed by multiple inclined surfaces. At the same time, the inclined surface 421 also facilitates the rejection of silicon material.
[0044] Optionally, the push plate 42 has a right-angled triangular structure, with its inclined surface 421 facing the direction of the conveying mechanism 2.
[0045] Example 3
[0046] Based on Embodiment 1 or Embodiment 2, in this embodiment, the graded collection unit 5 uses two hoppers. Specifically, the graded collection unit 5 includes a first hopper 51 and a second hopper 52. The first hopper 51 is located below one side of the rejection actuator 4, and the second hopper 52 is located next to the first hopper 51. The tops of both the first hopper 51 and the second hopper 52 are open.
[0047] In use, the size of the silicon material is first modeled and a preset value for rejection is set. When the size of the silicon material is smaller than the preset value, the silicon material falls directly into the first hopper 51 due to inertia under the operation of the belt conveyor mechanism 2. When the size of the silicon material is larger than the preset value, the rejection actuator 4 is activated to push the silicon material into the second hopper 52.
[0048] As an implementation scenario, in this scenario, when the actuator 41 is not activated, the pusher plate 42 is located above the left side of the first material bin 51. After the actuator 41 is activated, the pusher plate 42 can extend to the middle or the top right side of the first material bin 51. That is, after the actuator 4 is activated, the silicon material located above the first material bin 51 and in the process of falling enters the second material bin 52 under the action of the pusher plate 42.
[0049] Example 4
[0050] Based on Embodiment 1 or Embodiment 2, in this embodiment, the graded collection unit 5 uses three hoppers. Specifically, the graded collection unit 5 includes a first hopper 51, a second hopper 52, and a third hopper 53. The three hoppers are arranged sequentially from one end of the rejection actuator 4, that is: the first hopper 51 is located close to the rejection actuator 4, the second hopper 52 is located between the first hopper 51 and the third hopper 53, and the third hopper 53 is located below the outlet end of the conveying mechanism 2.
[0051] Optionally, the second hopper 52 may overlap with the conveying mechanism 2.
[0052] In use, the size of the silicon material is first modeled, and a first preset value and a second preset value for rejection are set. When the size of the silicon material is smaller than the first preset value, the rejection actuator 4 does not move, and the silicon material falls directly into the first hopper 51 due to inertia under the operation of the belt conveyor 2. When the size of the silicon material is larger than the first preset value, the rejection actuator 4 extends to the first stroke (short stroke) to push the silicon material into the second hopper 52. When the size of the silicon material is larger than the second preset value, the rejection actuator 4 extends to the second stroke (long stroke) to push the silicon material into the third hopper 53.
[0053] As an implementation scenario, in this scenario, when the actuator 41 is not activated, the pusher plate 42 can be located above the left side of the first hopper 51. When the actuator 41 performs the first stroke, the pusher plate 42 can extend to the middle or the top right side of the first hopper 51. When the actuator 41 performs the second stroke, the pusher plate 42 can extend to the top right side or the top right side of the first hopper 51. Thus, the silicon material located above the first hopper 51 and in the process of falling enters the second hopper 52 or the third hopper 53 under the action of the pusher plate 42.
[0054] In practical applications, polycrystalline silicon is classified into dense silicon (with a dense surface and cross-sectional structure, a smooth silicon rod surface, and surface unevenness less than 5mm), porous silicon (with surface unevenness of 5-20mm, internal gaps less than 20mm, or internal pores), and coral silicon (with internal gaps >20mm, a loose structure, needle-like or internally porous and crevice-like silicon). As an implementation scenario, in this scenario, the first hopper 51 can be set as the coral silicon hopper, the second hopper 52 as the porous silicon hopper, and the third hopper 53 as the dense silicon hopper. That is, when using an AI intelligent recognition system to model and set the size to be discarded for silicon material size, the first preset value is set as porous silicon, and the second preset value is set as dense silicon. During operation, the coral material, driven by the high-speed operation of the belt conveyor 2, falls directly into the first hopper 51 due to inertia. When the silicon material is identified as loose, the rejection mechanism 4 pushes it into the second hopper 52. When it is identified as dense, the rejection mechanism 4 pushes it into the third hopper 53. The silicon material in each hopper is then discharged to the next process through the outlet at the bottom of the hopper via the corresponding conveyor 7. Specifically, the outlets at the bottom of the first hopper 51, second hopper 52, and third hopper 53 are each connected to a corresponding conveyor 7, and the inlet ends of each conveyor 7 are arranged in a stepped structure. This equipment can identify and sort the silicon material, separating silicon materials of different conditions into their respective hoppers, thus controlling the proportion of silicon material conditions and ensuring that the final appearance quality deviation of each bag of product is controllable.
[0055] Example 5
[0056] Based on any of the above embodiments, in this embodiment, the visual recognition unit 3 includes a high-definition CCD camera. The surface of the middle part or near the exit end of the conveying mechanism 2 is designed as a detection area, and the high-definition CCD camera is set above the detection area, with its output end electrically connected to the input end of the controller 6. In use, the size of the silicon material is first modeled, and the size to be rejected is set. When the silicon material enters the detection area, the high-definition CCD camera takes a picture to obtain an image of the silicon material. The controller 6 receives the data collected by the high-definition CCD camera and makes a judgment based on the set rejection size. When the size deviates from the set value, the rejection execution mechanism 4 is activated. Specifically, under the rapid operation of the belt conveyor mechanism 2, the silicon material will be thrown out at the exit end in a parabolic trajectory due to inertia. Normal silicon material falls directly into the hopper below, while silicon material exceeding the set value is rejected by the rejection execution mechanism 4.
[0057] Example 6
[0058] Based on any of the above embodiments, in this embodiment, the visual recognition unit 3 and the controller 6 are electrically connected via a computer 8.
[0059] Specifically, the visual recognition unit 3 includes a high-definition CCD camera. The output of the high-definition CCD camera is electrically connected to the input of the computer. The output of the computer is electrically connected to the input of the controller 6. The output of the controller 6 is electrically connected to the input of the rejection actuator 4.
[0060] In use, the computer 8 first models the size of the silicon material and sets the size to be rejected. When the silicon material enters the detection area, the high-definition CCD camera takes a picture of the silicon material. The computer 8 receives the data collected by the camera, judges it according to the set rejection size, and transmits the data to the controller 6. The controller controls the action of the rejection execution mechanism 4. Under the rapid operation of the belt conveyor mechanism 2, the silicon material will be thrown out at the outlet end in a parabolic trajectory due to inertia. Normal silicon material falls directly into the designated hopper, while silicon material exceeding the set size is rejected by the rejection execution mechanism 4.
[0061] The silicon material size modeling algorithm utilizes existing technology and can automatically optimize sorting parameters based on the crushing characteristics of different batches of silicon material (such as long strips, flakes, and irregularly shaped materials). Furthermore, it integrates production data recording functions, storing key parameters such as the size distribution and sorting pass rate of each batch of silicon material in real time, enabling data traceability.
[0062] Any aspects not described in detail in this embodiment are techniques known in the art.
[0063] The above description is merely a specific embodiment of this utility model, but the protection scope of this utility model is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this utility model, and these should all be included within the protection scope of this utility model. Therefore, the protection scope of this utility model should be determined by the protection scope of the claims.
Claims
1. A polycrystalline silicon material sorting device, characterized in that, include: Conveying mechanism; A visual recognition unit is disposed above the conveying mechanism and is used to detect the size of the silicon material on the conveying mechanism in real time. The actuator is removed and is located on one side of the discharge end of the conveying mechanism; A graded collection unit is disposed below the conveying mechanism and the rejection execution mechanism; The controller is electrically connected to the visual recognition unit and the rejection execution mechanism, and is used to control the action of the rejection execution mechanism according to the detection result of the visual recognition unit.
2. The sorting equipment according to claim 1, characterized in that, The sorting equipment also includes: A vibrating feeder is installed at the feed end of the conveying mechanism; The vibrating feeder mechanism includes: The material bin is positioned above the feed end of the conveying mechanism; A vibrator, installed on the hopper, is used to vibrate and convey the silicon material in the hopper to the conveying mechanism.
3. The sorting equipment according to claim 1, characterized in that, The removal execution mechanism includes: An actuator is located on one side of the discharge end of the conveying mechanism; A push plate is disposed at the movable end of the actuator; The actuator's input terminal is electrically connected to the controller, which controls the actuator's extension and retraction based on the silicon material size detected by the visual recognition unit.
4. The sorting equipment according to claim 1, characterized in that, The removal execution mechanism includes: Multiple actuators are arranged along the width direction of the conveying mechanism; Each actuator has a push plate on its movable end; Each actuator's input terminal is electrically connected to the controller, which controls the actuator's movement at the corresponding position based on the silicon material size and position information detected by the visual recognition unit.
5. The sorting equipment according to claim 3 or 4, characterized in that, The pusher plate has an inclined surface on the side facing the conveying mechanism.
6. The sorting equipment according to claim 3 or 4, characterized in that, The actuator is an electric cylinder or a pneumatic cylinder.
7. The sorting equipment according to claim 1, characterized in that, The hierarchical collection unit: The first hopper is located below one side of the rejection actuator; The second hopper is located next to the first hopper; When the size of the silicon material detected by the visual recognition unit is greater than a preset value, the controller controls the rejection mechanism to push the silicon material into the second hopper.
8. The sorting equipment according to claim 1, characterized in that, The hierarchical collection unit includes: The first hopper, the second hopper, and the third hopper are arranged sequentially along the pushing direction of the rejection actuator; Specifically, when the size of the silicon material detected by the visual recognition unit is greater than the first preset value, the rejection actuator extends to the first stroke to push the silicon material into the second hopper; when the size of the silicon material detected by the visual recognition unit is greater than the second preset value, the rejection actuator extends to the second stroke to push the silicon material into the third hopper.
9. The sorting equipment according to claim 7 or 8, characterized in that, Each silo has an open top and a discharge port at the bottom, with a corresponding conveying device below each discharge port.
10. The sorting device according to claim 1, characterized in that: The visual recognition unit includes a high-definition CCD camera; And / or, the output of the visual recognition unit is connected to the input of the computer, the output of the computer is connected to the input of the controller, the output of the controller is connected to the input of the rejection actuator, the visual recognition unit acquires silicon material image data, the computer processes the image data and identifies the silicon material size, and the controller controls the rejection actuator according to the recognition result.