A decommissioned photovoltaic module disassembly and feeding device and method based on intelligent visual recognition

Abstract

The application discloses a kind of based on intelligent visual identification's decommissioned photovoltaic module disassembly feeding device and method, belong to decommissioned photovoltaic module resource processing technical field.The device includes feeding overall frame, movable cross bar, double mechanical arm and visual identification system.Two mechanical arms and a set of visual identification system are installed on movable cross bar, and visual identification system is composed of three-dimensional snapshot camera and polarization two-dimensional camera combination.Three-dimensional snapshot camera is used to obtain the overall space pose of decommissioned photovoltaic module aluminum frame, and polarization two-dimensional camera is used to eliminate reflection interference and accurately detect frame edge.Double mechanical arm front end is provided with telescopic cylinder and rotary calipers, can be according to visual identification result clamping aluminum frame, and photovoltaic module is handled to disassembly conveying belt.The design shows strong adaptability to complex working conditions such as high dust and component glass defect, and improves the automation level of decommissioned photovoltaic module recycling process.

Description

Technical Field

[0001] This invention belongs to the field of resource utilization technology for decommissioned photovoltaic modules, specifically relating to a device and method for dismantling and loading decommissioned photovoltaic modules based on intelligent visual recognition. Background Technology

[0002] With the rapid development of the photovoltaic industry, a large number of early-installed photovoltaic modules are gradually entering the retirement stage. The sheer number of retired photovoltaic modules makes their recycling and harmless disposal a core issue for the industry's sustainable development. Generally, photovoltaic modules have a lifespan of about 25 years and are mainly composed of glass, backsheets, solar cells, aluminum alloy frames, EVA, copper solder strips, and junction boxes. Most of the materials (such as glass, copper, aluminum, silicon, silver, gallium, and indium) have high recycling value. If these scrapped modules are not properly recycled and disposed of, it will not only waste rare metal resources but may also cause serious pollution to the ecological environment.

[0003] In the recycling and processing of retired photovoltaic modules, loading is the first step in the dismantling line, and its stability and reliability directly determine the efficiency and safety of subsequent processes. Currently, the industry's commonly used manual handling method is not only labor-intensive and inefficient but also poses safety hazards and is unsuitable for large-scale processing needs. Even highly automated vacuum suction cup loading devices face significant challenges in practical applications: retired modules operate outdoors for extended periods, often accumulating large amounts of dust on their surfaces, which severely weakens the suction cup's adsorption force, causing modules to accidentally detach during handling; more problematic is that many retired modules have cracked or partially damaged glass panels, preventing the vacuum suction cup from forming an effective sealing surface, thus rendering it completely ineffective. Furthermore, potential warping or deformation of the modules further increases the difficulty of stable gripping. These issues collectively result in unsatisfactory reliability and efficiency when dealing with the complex operating conditions of actual retired modules. Therefore, existing loading methods cannot effectively meet the stable and reliable loading requirements of retired photovoltaic modules under complex operating conditions. Summary of the Invention

[0004] The purpose of this invention is to overcome the above-mentioned problems and provide a device and method for dismantling and loading retired photovoltaic modules based on intelligent visual recognition, which can solve the technical problem that retired photovoltaic modules fall off or cannot be picked up due to insufficient adsorption force in traditional vacuum suction cup loading mechanisms.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a dismantling and loading device for decommissioned photovoltaic modules based on intelligent visual recognition, comprising a loading frame, a movable crossbar on the loading frame, two robotic arms symmetrically arranged on the movable crossbar, a visual recognition system between the two robotic arms, the visual recognition system comprising a first polarization two-dimensional camera, a three-dimensional fast camera and a second polarization two-dimensional camera; a telescopic cylinder is provided at the front end of the robotic arm, and a rotating clamp is connected to the telescopic cylinder.

[0006] A further improvement of the present invention is that each robotic arm is connected to a movable crossbar via a robotic arm sliding cylinder, wherein the robotic arm sliding cylinder includes a first robotic arm sliding cylinder and a second robotic arm sliding cylinder.

[0007] A further improvement of the present invention is that the three-dimensional fast camera is located between the first polarization two-dimensional camera and the second polarization two-dimensional camera.

[0008] A further improvement of the present invention is that the movable crossbar is slidably connected to the overall feeding frame via a first movable crossbar sliding cylinder and a second movable crossbar sliding cylinder.

[0009] A further improvement of the present invention is that the robotic arm is a six-degree-of-freedom robotic arm with a rated load of 10-12.5 kg.

[0010] A further improvement of the present invention is that the opening stroke of the rotary caliper is 40-60mm and the clamping force is 150-300N.

[0011] A further improvement of the present invention is that the retractable cylinder is connected to the rotary caliper via a caliper rotation mechanism; the inner surface of the rotary caliper is provided with wear-resistant rubber and is provided with a torque or current threshold sensing protection device.

[0012] Secondly, the present invention also provides a method for dismantling and loading decommissioned photovoltaic modules based on intelligent visual recognition, comprising the following steps: Step 1: Collect point cloud data of retired photovoltaic modules using a 3D fast camera, and obtain the overall spatial position of the aluminum frame through plane fitting and frame detection algorithms. Step 2: Based on the obtained overall spatial position of the aluminum frame, control the movable crossbar and the robotic arm to move above the target area, acquire images of the aluminum frame through the first polarization 2D camera and the second polarization 2D camera, and use edge detection and sub-pixel line fitting algorithms to accurately locate the clamping point position. Step 3: Control the retractable cylinder to drive the rotating caliper to clamp the aluminum frame; Step 4: The robotic arm lifts and transports the decommissioned photovoltaic modules and places them on the dismantling conveyor belt to complete the loading process.

[0013] A further improvement of the present invention is that, in step 3, when the rotating caliper clamps the aluminum frame, the clamping force stops after reaching a set threshold; when the clamping force or current exceeds a safe value, the clamping is automatically stopped.

[0014] A further improvement of the present invention is that the single feeding cycle time is controlled within 6-10 seconds.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a dismantling and loading device for decommissioned photovoltaic (PV) modules based on intelligent visual recognition. By symmetrically arranging two robotic arms on the movable crossbar of the overall loading frame and integrating a visual recognition system composed of a first polarized 2D camera, a 3D fast camera, and a second polarized 2D camera, the device replaces traditional vacuum suction cups with a physical contact method of clamping from the aluminum frame. This effectively avoids insufficient or failed suction due to dust accumulation on the PV module surface or glass panel breakage, significantly improving the reliability of the loading operation. The device uses a 3D fast camera for rapid coarse spatial positioning, combined with a polarized 2D camera to suppress glare interference from the aluminum frame and glass surface, achieving sub-pixel-level precise positioning of the aluminum frame edge. This guides the retractable cylinder and rotating clamp at the front end of the robotic arm for precise clamping. This design demonstrates strong adaptability to complex working conditions such as high dust levels and damaged module glass, reducing the intensity and safety risks of manual operation, and significantly improving the automation level and economic benefits of the entire process of decommissioned PV module recycling.

[0016] Furthermore, the 3D fast camera is located between the first polarization 2D camera and the second polarization 2D camera. The 3D fast camera, located in the middle, can acquire the 3D point cloud data of the entire component at once, providing the robotic arm with the initial spatial coordinates and attitude reference. Then, the polarization 2D cameras on both sides use their properties to suppress reflections from metal and glass surfaces to finely correct the edges of the aluminum frame, which not only ensures recognition efficiency but also greatly improves the accuracy and robustness of clamping and positioning.

[0017] Furthermore, the robotic arm is a six-degree-of-freedom robotic arm, which can achieve precise control of any position and posture in three-dimensional space, thereby efficiently completing complex and high-precision operation tasks.

[0018] Furthermore, the inner surface of the rotary caliper is equipped with wear-resistant rubber and a torque or current threshold sensing protection device. Through flexible contact, it effectively absorbs impacts to prevent scratching the aluminum frame or crushing the glass. At the same time, the sensing system monitors the clamping force in real time and automatically stops the action in case of overload, thereby achieving dual protection for vulnerable components while ensuring clamping stability.

[0019] Furthermore, this device is highly adaptable and can be used in complex environments such as high dust levels and glass breakage, reducing the intensity of manual operation and safety risks, and improving the automation level of the recycling and processing of retired photovoltaic modules.

[0020] This invention also provides a method for dismantling and loading retired photovoltaic modules based on intelligent visual recognition. First, a 3D camera quickly scans and roughly locates the position of the aluminum frame, ensuring a reliable initial position even if the module is warped or dusty. Next, a polarized 2D camera effectively filters out reflections from the aluminum frame and glass, finely correcting the clamping points and significantly improving positioning accuracy. Unlike vacuum suction cups, which are easily affected by surface conditions, this method uses rotating clamps to directly grip the aluminum frame, fundamentally avoiding suction failure caused by glass breakage or dust. Simultaneously, the built-in force sensor ensures the clamping force is just right, preventing damage to the module. Finally, two robotic arms work together to complete the transport, effectively distributing the weight of the module and ensuring dynamic stability during transport, thus enabling the retired photovoltaic modules to be quickly and smoothly placed onto the dismantling conveyor belt. This method demonstrates high adaptability and robustness in handling complex conditions such as glass breakage and dust accumulation, effectively solving the technical bottlenecks of traditional loading methods and well adapting to the needs of various complex conditions in actual dismantling production.

[0021] Furthermore, this method can complete the loading of a single module in a cycle time of 6-10 seconds, meeting the efficiency requirements for large-scale dismantling and processing of retired photovoltaic modules. Attached Figure Description

[0022] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the invention in any way. Furthermore, the shapes and proportions of the components in the drawings are merely illustrative to aid in understanding the invention and do not specifically limit the shapes and proportions of the components of the invention.

[0023] Figure 1 This is a schematic diagram of the overall structure of the disassembly and feeding device of the present invention; Figure 2 This is a top view of the disassembly and feeding device of the present invention; Figure 3 This is a front view of the disassembly and feeding device of the present invention; Figure 4 This is a left view of the disassembly and feeding device of the present invention.

[0024] The components include: 1. Overall feeding frame; 11. First polarization 2D camera; 12. 3D fast camera; 13. Second polarization 2D camera; 14. First robotic arm sliding cylinder; 15. Second robotic arm sliding cylinder; 16. Movable crossbar; 17. First movable crossbar sliding cylinder; 18. Second movable crossbar sliding cylinder; 2. Robotic arm; 21. Rotary caliper; 22. Caliper rotation mechanism; 23. Telescopic cylinder. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0027] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0028] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not 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 of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0030] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0031] The present invention will now be described in further detail with reference to the accompanying drawings: like Figures 1 to 4 As shown, this invention provides a decommissioned photovoltaic module dismantling and loading device based on intelligent visual recognition, including a loading frame 1. A movable crossbar 16 driven by a motor is mounted on the loading frame 1. Two robotic arms 2 are symmetrically arranged on the movable crossbar 16, with a visual recognition system positioned between the two robotic arms 2. Each robotic arm 2 has a telescopic cylinder 23 at its front end, which is connected to a rotating clamp 21 via a clamp rotation mechanism 22. The visual recognition system identifies the position of the aluminum frame around the decommissioned photovoltaic module. The motor-driven movable crossbar 16 moves above the aluminum frame, and the visual recognition system re-identifies and confirms the position of the aluminum frame. The robotic arms 2 and the rotating clamp 21 are then activated, using the rotating clamp 21 to grip the aluminum frame of the decommissioned photovoltaic panel and place the photovoltaic panel onto a subsequent dismantling conveyor belt.

[0032] The robotic arm 2 used in this invention is a dual-arm collaborative clamping frame design. Each robotic arm 2 is a six-degree-of-freedom robotic arm with a maximum load of not less than 10kg, a working radius of not less than 1300mm, a repeatability accuracy better than ±0.05mm, and a protection level of IP54 or higher. Considering that the overall weight of retired photovoltaic modules is usually between 18-28kg, the dual-arm collaborative clamping method can ensure stable handling. The end of the robotic arm 2 is equipped with a telescopic cylinder 23 and a rotary clamp 21 structure. The opening stroke of the rotary clamp 21 is 40-60mm, providing an adjustable clamping force of 150-300N. It is protected by adding wear-resistant rubber and setting torque or current threshold sensors to avoid damage to the aluminum frame or breakage of the glass due to over-clamping. The overall robotic arm 2 takes into account stability, accuracy, and flexibility, and can meet the clamping requirements of retired photovoltaic modules of different specifications.

[0033] This invention employs a combination of a 3D fast camera 12 and a polarized 2D camera to improve positioning accuracy and robustness. The visual recognition system includes a first polarized 2D camera 11, a 3D fast camera 12, and a second polarized 2D camera 13. The 3D fast camera 12 is located at the center of a movable crossbar 16, with a working distance of 1.0-1.6m and a field of view covering the entire surface of the decommissioned photovoltaic module (≥700mm × 600mm), achieving a spatial resolution within 0.5mm. It is used to acquire the overall spatial pose of the aluminum frame in a single operation. The first polarized 2D camera 11 and the second polarized 2D camera 13 are respectively mounted on either side of the 3D fast camera 12. Utilizing a micro-polarization array or external polarizer in conjunction with a strip light source, interference caused by reflections from the aluminum frame and glass can be effectively suppressed, thereby achieving accurate detection of the frame edges. The 2D polarized visual resolution is approximately 5 million pixels, with a frame rate of no less than 24fps, a global shutter structure, and reflective suppression capabilities. To adapt to dust and complex environments, the camera body can be equipped with a protective cover and air curtain; some models can directly achieve an IP67 protection rating, ensuring long-term stable operation.

[0034] In some embodiments, each robotic arm 2 is connected to a movable crossbar 16 via a robotic arm sliding cylinder, which includes a first robotic arm sliding cylinder 14 and a second robotic arm sliding cylinder 15. This dual-sliding-cylinder design significantly enhances the rigidity and stability of the robotic arm 2 when moving on the movable crossbar 16. The coordinated operation of the dual sliding cylinders effectively withstands the off-center load torque generated during the handling of photovoltaic modules, preventing the robotic arm 2 from jamming or wobbling during movement. This provides a stable motion reference for the vision recognition system and precise clamping, ensuring the smoothness and accuracy of the loading process.

[0035] In some embodiments, the movable crossbar 16 is slidably connected to the overall loading frame 1 via the first movable crossbar sliding cylinder 17 and the second movable crossbar sliding cylinder 18, which effectively suppresses the off-center torque and sway that may be generated by single-point drive, and provides a smooth and high-precision motion reference for the robotic arm 2 mounted above and the vision recognition system. This design ensures the rigidity and reliability of the entire loading device in repeated positioning and high-speed operation.

[0036] This invention also provides a method for dismantling and loading decommissioned photovoltaic modules based on intelligent visual recognition, comprising the following steps: Step 1, coarse positioning: The point cloud data of the retired photovoltaic modules is collected by the 3D fast camera 12, and the overall spatial position of the aluminum frame is obtained by plane fitting and frame detection algorithm. Step 2, Precise Positioning: Based on the obtained overall spatial position of the aluminum frame, control the movable crossbar 16 and the robotic arm 2 to move above the target area, and acquire images of the aluminum frame through the first polarization two-dimensional camera 11 and the second polarization two-dimensional camera 13. Use edge detection and sub-pixel line fitting algorithms to accurately position the clamping point. Step 3, Clamping and Protection: Control the retractable cylinder 23 to drive the rotating caliper 21 to clamp the aluminum frame. Stop when the clamping force reaches the set threshold; if the clamping force or current exceeds the safety value, clamping will automatically stop. Step 4, Handling and Placement: Robotic arm 2 lifts and moves the decommissioned photovoltaic modules and places them on the dismantling conveyor belt to complete the loading.

[0037] In some embodiments, controlling the single feeding cycle time to between 6 and 10 seconds can meet the cycle time requirements of the decommissioned photovoltaic module dismantling line.

[0038] This invention addresses the common problems encountered in the dismantling and loading of decommissioned photovoltaic (PV) modules using traditional vacuum suction cup mechanisms. These problems stem from reduced suction power due to dust accumulation on the module surface, broken or warped glass panels, leading to accidental drops or complete failure to hold the modules during transport. A novel solution is proposed. This invention employs a mechanical clamping method based on intelligent vision guidance, integrating the coarse spatial positioning capabilities of a 3D fast camera with the fine edge positioning advantages of a polarized 2D camera, enabling sub-pixel-level precision correction of the clamping point. Based on this, the device drives a rotating caliper at the end of a robotic arm to precisely clamp the aluminum frame of the module. This physical contact gripping method fundamentally overcomes the impact of poor surface conditions. The collaborative design of the dual robotic arms not only effectively distributes the weight of the module but also ensures dynamic stability during transport. Ultimately, this decommissioned PV module dismantling and loading method enables the equipment to reliably and stably complete the loading task of decommissioned PV modules within a cycle time of 6 to 10 seconds, even under harsh conditions such as high dust levels, broken glass, and warped frames. This significantly improves the automation level, operational safety, and overall processing efficiency of the dismantling production line. Many embodiments and applications beyond the examples provided will be apparent to those skilled in the art upon reading the foregoing description. Therefore, the scope of this teaching should not be determined by reference to the foregoing description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be construed as an indication that the applicant has not considered that subject matter as part of the disclosed inventive subject matter.

[0039] The above content provides a further detailed description of the present invention. It should not be construed that the specific embodiments of the present invention are limited to this. For those skilled in the art, several simple deductions or substitutions can be made without departing from the concept of the present invention, and all such deductions or substitutions should be considered to fall within the scope of protection of the present invention as defined by the submitted claims.

Claims

1. A dismantling and loading device for decommissioned photovoltaic modules based on intelligent visual recognition, characterized in that, The system includes a loading frame (1), on which a movable crossbar (16) is provided. Two robotic arms (2) are symmetrically arranged on the movable crossbar (16). A vision recognition system is provided between the two robotic arms (2). The vision recognition system includes a first polarization two-dimensional camera (11), a three-dimensional fast camera (12), and a second polarization two-dimensional camera (13). A telescopic cylinder (23) is provided at the front end of the robotic arm (2). The telescopic cylinder (23) is connected to a rotating caliper (21).

2. The decommissioned photovoltaic module dismantling and loading device based on intelligent visual recognition according to claim 1, characterized in that, Each robotic arm (2) is connected to a movable crossbar (16) via a robotic arm sliding cylinder, the robotic arm sliding cylinder including a first robotic arm sliding cylinder (14) and a second robotic arm sliding cylinder (15).

3. The decommissioned photovoltaic module dismantling and loading device based on intelligent visual recognition according to claim 1, characterized in that, The three-dimensional fast camera (12) is located between the first polarization two-dimensional camera (11) and the second polarization two-dimensional camera (13).

4. The decommissioned photovoltaic module dismantling and loading device based on intelligent visual recognition according to claim 1, characterized in that, The movable crossbar (16) is slidably connected to the overall loading frame (1) via the first movable crossbar sliding cylinder (17) and the second movable crossbar sliding cylinder (18).

5. The decommissioned photovoltaic module dismantling and loading device based on intelligent visual recognition according to claim 1, characterized in that, The robotic arm (2) is a six-degree-of-freedom robotic arm with a rated load of 10-12.5 kg.

6. The decommissioned photovoltaic module dismantling and loading device based on intelligent visual recognition according to claim 1, characterized in that, The opening stroke of the rotary caliper (21) is 40-60mm, and the clamping force is 150-300N.

7. The decommissioned photovoltaic module dismantling and loading device based on intelligent visual recognition according to claim 1, characterized in that, The retractable cylinder (23) is connected to the rotating caliper (21) via the caliper rotating mechanism (22); the inner surface of the rotating caliper (21) is provided with wear-resistant rubber and is provided with a torque or current threshold sensing protection device.

8. A method for dismantling and loading decommissioned photovoltaic modules using the apparatus described in any one of claims 1-7, characterized in that, Includes the following steps: Step 1: Collect point cloud data of retired photovoltaic modules using a 3D fast camera (12), and obtain the overall spatial position of the aluminum frame by plane fitting and frame detection algorithm; Step 2: Based on the obtained overall spatial position of the aluminum frame, control the movable crossbar (16) and the robotic arm (2) to move above the target area, and collect images of the aluminum frame through the first polarization two-dimensional camera (11) and the second polarization two-dimensional camera (13). Use edge detection and sub-pixel line fitting algorithm to accurately locate the clamping point position. Step 3: Control the telescopic cylinder (23) to drive the rotary caliper (21) to clamp the aluminum frame; Step 4: The robotic arm (2) lifts and transports the retired photovoltaic modules and places them on the dismantling conveyor belt to complete the loading.

9. A method for dismantling and loading decommissioned photovoltaic modules based on intelligent visual recognition according to claim 8, characterized in that, In step (3), when the rotating caliper (21) clamps the aluminum frame, it stops after the clamping force reaches the set threshold; when the clamping force or current exceeds the safety value, the clamping is automatically stopped.

10. A method for dismantling and loading decommissioned photovoltaic modules based on intelligent visual recognition according to claim 8, characterized in that, The time for a single feeding cycle is controlled to be 6-10 seconds.

Images