A retired photovoltaic module silicon wafer glass physical separation control system

Abstract

The application discloses a retired photovoltaic module silicon wafer glass physical separation control system, comprising: a feeding assembly, a sorting assembly, a sensing assembly and a control assembly; the sorting assembly and the sensing assembly are in communication with the control assembly; the feeding assembly is used for conveying mixed materials to the sorting assembly for sorting; the sensing assembly is used for collecting real-time images of the mixed materials during sorting on the sorting assembly, and judging whether the silicon wafer and the glass in the mixed materials are successfully sorted according to the real-time images; the control assembly is used for controlling the sorting assembly to adjust sorting parameters when the sensing assembly judges that the silicon wafer and the glass in the mixed materials fail to be sorted, and controlling the sorted silicon wafer and glass materials to be quickly intercepted and discharged when the sensing assembly judges that the silicon wafer and the glass materials in the mixed materials are successfully sorted. The application combines machine vision technology with an automatic control system, and can realize rapid physical separation and treatment of the retired photovoltaic module silicon wafer and glass, and further realize automation of a production process.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of recycling of decommissioned photovoltaic modules, and in particular to a decommissioned photovoltaic module silicon wafer and glass physical separation control system. BACKGROUND

[0002] With the rapid development of the field of solar photovoltaic power generation, a large number of decommissioned photovoltaic modules will need to be recycled. In the recycling process of decommissioned photovoltaic modules, efficient separation and recovery of silicon wafers and glass materials is an important step in realizing the recycling of photovoltaic modules. The traditional decommissioned photovoltaic module silicon wafer and glass physical separation equipment has low automation during operation, often relies on manual operation, has low separation efficiency and cannot guarantee the consistency of the quality of the separated products. Therefore, it is necessary to develop an intelligent control system for decommissioned photovoltaic module silicon wafer and glass physical separation equipment to achieve efficient separation of silicon wafers and glass materials in decommissioned photovoltaic modules. SUMMARY

[0003] The present application provides a decommissioned photovoltaic module silicon wafer and glass physical separation control system to solve the technical problem of low separation efficiency of decommissioned photovoltaic module silicon wafer and glass physical separation equipment relying on manual operation.

[0004] To solve the above technical problems, the technical solution proposed by the present application is:

[0005] A decommissioned photovoltaic module silicon wafer and glass physical separation control system, comprising:

[0006] a feeding assembly, a separation assembly, a sensing assembly, and a control assembly; the separation assembly and the sensing assembly are in communication with the control assembly;

[0007] The feeding assembly is used to transport mixed materials to the separation assembly for separation;

[0008] The sensing assembly is used to collect real-time images of the separation of mixed materials on the separation assembly, and to determine whether the separation of silicon wafers and glass in the mixed materials is successful according to the real-time images;

[0009] The control assembly is used to control the separation assembly to adjust the separation parameters when the sensing assembly determines that the separation of silicon wafers and glass in the mixed materials fails.

[0010] Preferably, the sensing assembly comprises an image acquisition assembly and an image processing module, the image acquisition assembly is used to acquire the real-time images and send them to the image processing module;

[0011] The image processing module is configured to input the real-time image into a pre-trained sorting recognition model to obtain position information of a segmentation boundary of a region where a wafer is located at an end of material conveying of a sorting platform and a segmentation boundary of a region where glass is located.

[0012] Preferably, the sorting recognition model comprises an encoder, a decoder, and a boundary extraction module.

[0013] The encoder comprises a residual backbone network, a dilated convolution network, a spatial pyramid pooling module, and an attention mechanism; the dilated convolution network is configured to extract a plurality of global feature maps of different scales on the input image in parallel through the residual backbone network; the spatial pyramid pooling module is configured to enhance local semantic information corresponding to the plurality of global feature maps of different scales; and the attention mechanism is configured to calculate correlations between the plurality of global feature maps to generate an attention weight map.

[0014] The decoder comprises a feature fusion module, an up-sampling module and a prediction module, and a batch normalization module; the feature fusion module is configured to fuse the plurality of global feature maps of different scales according to the attention weight map to obtain a fused feature map; the up-sampling module and the prediction module are configured to perform linear interpolation up-sampling on the fused feature map, and perform channel adjustment to obtain a segmentation image and a segmentation mask of wafer material and glass material; and the batch normalization module is configured to perform a batch normalization operation on a convolution layer in the decoder.

[0015] The boundary extraction module is configured to extract a boundary according to the segmentation image and the segmentation mask of the wafer material and the glass material, and calculate coordinates of a separation boundary based on the extracted boundary.

[0016] Preferably, the sorting assembly comprises a material platform, a vibration voltage frequency adjustment assembly, a height adjustment assembly, a first sorting plate, and a second sorting plate; the vibration voltage frequency adjustment assembly and the height adjustment assembly both establish communication with the control assembly.

[0017] The material platform is configured to receive and sort mixed material transported by the feeding assembly.

[0018] The vibration voltage frequency adjustment assembly is configured to control vibration of the material platform.

[0019] The height adjustment assembly is configured to adjust a pose of the material platform.

[0020] The first sorting plate is configured to intercept wafer material sorted by the material platform.

[0021] The second sorting plate is configured to intercept glass material sorted by the material platform.

[0022] The control component is configured to control the vibration voltage frequency adjusting component and / or the height adjusting component to adjust the vibration voltage, vibration frequency and / or pose of the material platform when the perception component determines that the separation of the silicon wafer and the glass in the mixed material fails, so as to make the separation of the mixed material successful, and control the first separation plate and the second separation plate to quickly intercept the material when the separation of the mixed material is successful.

[0023] Preferably, the vibration voltage frequency adjusting component comprises a plurality of separation vibrators arranged at the bottom of the material platform, and the plurality of separation vibrators are distributed along the material transportation direction of the material platform.

[0024] and / or

[0025] The height adjusting device comprises a first three-phase motor and a second three-phase motor.

[0026] The first three-phase motor is configured to adjust the front-rear longitudinal height of the material platform in a first direction, and the first direction is the material transportation direction of the material platform.

[0027] The second three-phase motor is configured to adjust the left-right longitudinal height of the material platform in a second direction, and the second direction is perpendicular to the first direction.

[0028] Preferably, the perception component comprises an illumination module and an image display module, the image display module is connected with an image processing module, the image acquisition component comprises a plurality of industrial cameras configured to acquire real-time photos at the end of the material transportation, and the illumination module is configured to provide light for the industrial cameras.

[0029] Preferably, the separation component further comprises a first position adjusting component and a second position adjusting component, and the first position adjusting component and the second position adjusting component are connected with the control component.

[0030] The first position adjusting component is configured to adjust the position of the first separation plate.

[0031] The second position adjusting component is configured to adjust the position of the second separation plate.

[0032] Preferably, the separation identification model is further configured to determine the segmentation position of the silicon wafer and the glass in the real-time image and the falling position of the silicon wafer and the glass at the end of the material platform.

[0033] The control component is further configured to compare the first falling position of the silicon wafer with a first real-time position of the first sorting plate, and when a deviation between the first falling position and the first real-time position is greater than a preset threshold, control a first position adjusting component to adjust the position of the first sorting plate so that the deviation between the first falling position and the first real-time position is within the preset threshold.

[0034] and / or

[0035] The control component is further configured to compare the second falling position of the glass with a second real-time position of the second sorting plate, and when a deviation between the second falling position and the second real-time position is greater than a preset threshold, control a second position adjusting component to adjust the position of the second sorting plate so that the deviation between the second falling position and the second real-time position is within the preset threshold.

[0036] Preferably, the feeding assembly comprises a feeding hopper and a feeding vibrator.

[0037] The feeding hopper is configured to deliver the input material to the material platform.

[0038] The feeding vibrator is configured to vibrate the feeding hopper.

[0039] Preferably, the first position adjusting component and the second position adjusting component are both stepper motors.

[0040] The control component comprises a stepper motor driver, a stepper motor controller, a feeding vibration controller, a sorting vibration controller, a three-phase motor controller, and a PLC controller. The PLC controller is in communication with the stepper motor controller, the feeding vibration controller, the sorting vibration controller, and the three-phase motor controller. The stepper motor controller is connected to the stepper motor through the stepper motor driver. The feeding vibration controller is connected to the feeding vibrator. The sorting vibration controller is connected to the sorting vibrator. The three-phase motor controller is connected to the first three-phase motor and the second three-phase motor.

[0041] The present application has the following beneficial effects:

[0042] The present application combines machine vision technology with an automatic control system, which can achieve rapid physical separation and processing of retired photovoltaic component silicon wafers and glass, and further realize the automation of the production process. This not only improves production efficiency, but also helps to improve product quality and reduce production cycle.

[0043] In addition to the purposes, features, and advantages described above, the present application has other purposes, features, and advantages. The present application will be described in further detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0044] The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application and are incorporated in and constitute a part of this application. The illustrations, together with their description, serve to explain the application without unduly limiting it.

[0045] Figure 1 Workflow diagram of a physical separation system for silicon wafer and glass of decommissioned photovoltaic modules based on automatic control and machine vision in a preferred embodiment of the present application;

[0046] Figure 2 Image processing flow diagram of a physical separation system for silicon wafer and glass of decommissioned photovoltaic modules based on automatic control and machine vision in a preferred embodiment of the present application;

[0047] Figure 3 IO distribution diagram of a physical separation system for silicon wafer and glass of decommissioned photovoltaic modules based on automatic control and machine vision in a preferred embodiment of the present application;

[0048] Figure 4 Schematic diagram of the vibration of the sorting platform vibrator along the material transport direction in a preferred embodiment of the present application;

[0049] Figure 5 Schematic diagram of the first three-phase motor adjusting the height difference between the front and back of the sorting platform in a preferred embodiment of the present application;

[0050] Figure 6 Schematic diagram of the second three-phase motor adjusting the height difference between the left and right of the sorting platform in a preferred embodiment of the present application;

[0051] Figure 7 Structure diagram of the sorting and identification model in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0052] The embodiments of the present application will be described in detail below with reference to the accompanying drawings, but the present application can be implemented in various different ways as limited and covered by the claims.

[0053] Embodiments:

[0054] The present application aims to provide a physical separation control system and method for silicon wafer and glass of decommissioned photovoltaic modules to solve the technical problems that the existing technology cannot monitor the whole process in real time, cannot identify the operation errors in the separation process, and cannot effectively separate the silicon wafer particles and glass particles.

[0055] To achieve the above-mentioned purpose, the present application provides a physical separation control system for silicon wafer and glass of decommissioned photovoltaic modules, which comprises five parts of feeding control, sorting control, visual acquisition control, distribution control, and control center, and realizes the functions of automatic vibration feeding, silicon wafer and glass oscillation separation, product visual image feature extraction, automatic interception and collection of silicon wafer and glass products, centralized control and management, etc.

[0056] The feeding control section includes a feeding hopper, a feeding vibrator, and a feeding vibration controller. The feeding vibrator is located above and behind the device's support frame and is connected to the feeding vibration controller inside the control cabinet. Its main function is to feed materials.

[0057] like Figures 4-6 As shown, the sorting control section includes three identical sorting vibrators connected in parallel to a single sorting vibration controller. The sorting vibrators are positioned below the material platform, and the sorting vibration controller is located inside the control cabinet. The sorting section also includes two three-phase motors, namely a first three-phase motor and a second three-phase motor. Each of the two three-phase motors is connected to a reducer at its end. The two three-phase motors with reducers at their ends adjust the front-to-back longitudinal height and the left-to-right longitudinal height of the material platform, respectively. The material platform is surrounded by bent metal to form a material separation passage. Its main function is to convey and sort materials. Adjusting the front-to-back longitudinal height of the material platform is mainly to adjust the front-to-back height difference of the material platform, thereby adjusting the longitudinal tilt angle of the material platform. Adjusting the left-to-right longitudinal height of the material platform is mainly to adjust the left-to-right height difference of the material platform, thereby adjusting the horizontal tilt angle of the material platform.

[0058] The vision acquisition and control unit mainly consists of four parts: a lighting module, an image acquisition component, an image display module, and an image processing module. The lighting module includes an industrial camera light source; the image acquisition component includes two industrial cameras, positioned directly above the entire material sorting platform; the image processing module uses a microcontroller as its control core and communicates with the controller for data interaction, forming a feedback path.

[0059] The material sorting control section includes two sorting plates, namely the first sorting plate and the second sorting plate, two stepper motors and stepper motor drivers; the sorting plates are located above the material passage and are welded to the stepper motor shafts for coaxial rotation; the stepper motors are connected to the stepper motor drivers; the stepper motor drivers are connected to the PLC controllers in the control cabinet; material recycling containers are placed at the outlets below the sorting plates; their function is to hold the sorted recycled materials.

[0060] The control center is a control cabinet. The cabinet contains a PLC controller, HMI, feeding vibration controller, sorting vibration controller, stepper motor driver, stepper motor controller, AC contactor, thermal relay, intermediate relay, air switch, sockets, switching power supply, buttons, knobs, etc. It is responsible for data acquisition and processing, intelligent decision-making and control, automated control processes, system monitoring and management, security, network communication, and optimization and upgrades, ensuring the efficient, stable, and safe operation of the entire system.

[0061] In the preferred embodiment, the control cabinet is installed above the device support frame; the electric control elements are arranged inside the control cabinet; the display device is communicatively connected to the surface of the control cabinet.

[0062] Further preferably, the vibrator control of the feeding part and the conveying part is realized by the PLC controller digital output signal to control the power switch of the vibrator, to start and stop the vibrator; the controller analog output signal is used to control the voltage signal and frequency signal of the vibrator, to control the output voltage and vibration frequency of the vibrator.

[0063] In the preferred embodiment, the three-phase motor control of the material platform of the conveying part is realized by using the controller output signal to control the normally open contact of the AC contactor, by designing a self-locking interlocking circuit to control the on-off of the three-phase power supply and to control the running and stopping of the motor, to realize the start and stop of the material platform; the controller output signal is used to control the forward and reverse interlocking contactor of the three-phase motor, to realize the forward and reverse rotation of the motor, to adjust the horizontal angle of the material platform; a knob switch is connected in the three-phase motor control circuit, to switch between the local control and remote control at any time.

[0064] In the preferred embodiment, the step motor control of the sorting plate part is realized by using the controller IO interface to control the pulse signal of the step motor driver, by the frequency and pulse number of the pulse signal to control the rotating speed and moving steps of the step motor; the controller can set the motion direction, acceleration, starting position and target position and other parameters according to the requirement, and realize the precise positioning and action control of the step motor by the logic control, to realize the precise adjustment of the angle of the sorting plate.

[0065] In the preferred embodiment, as Figure 3As shown, the C2 port of the feeding vibration controller sdvc31 of the vibrating feeding part accesses the DQa.0 of the controller to realize the controller control start-stop; the D1 and D2 ports of the feeding vibration controller sdvc31 of the vibrating feeding part are connected in series into an intermediate relay, and the normally open contact of the intermediate relay is connected in series into the common terminal of the controller and the DIa.0 to realize the real-time monitoring of the controller on the running parameters such as the voltage and frequency of the vibrator of the vibrating feeding part; the C2 port of the sorting vibration controller sdvc34-ur of the vibrating conveying part accesses the DQa.1 of the controller to realize the controller control start-stop; the D1 and D2 ports of the sorting vibration controller sdvc31 of the vibrating conveying part are connected in series into an intermediate relay, and the normally open contact of the intermediate relay is connected in series into the common terminal of the controller and the DIa.1 to realize the real-time monitoring of the controller on the running parameters such as the voltage and frequency of the vibrator of the vibrating conveying part; the lifting motor 1 (i.e. the first three-phase motor) of the material platform part occupies the DIa.6, DIa.7, DIb.0 and DIb.1 of the controller respectively to realize the remote switching, forward rotation start-stop, reverse rotation start-stop and fault alarm; the lifting motor 2 (i.e. the second three-phase motor) of the material platform part occupies the DIb.2, DIb.3, DIb.4 and DIb.5 of the controller respectively to realize the remote switching, forward rotation start-stop, reverse rotation start-stop and fault alarm; the Pend+ and ALM+ of the two stepper motor drivers of the sorting plate part access the DIa.2, DIa.3, DIa.4 and DIa.5 of the controller respectively to realize the fault alarm of the stepper motor and the angle in-place prompt of the sorting plate.

[0066] In the preferred solution, the image processing module of the vision part has two main functions. One is to identify the current separation effect of the product and predict the separation position of the silicon wafer and the glass, which is used to adjust the voltage and frequency value; the other is to identify the actual falling position of the product at the end of the material platform to adjust the position of the sorting plate.

[0067] In the preferred solution, as shown in Figure 2 , Figure 7 The first function of the image processing module is based on a pre-trained deep learning model, which is improved based on the Residual Network (ResNet) and Dilation Convolutions (Dilated Convolutions) to the DeepLabV3+ algorithm; thereby obtaining a fast, lightweight and accurate sorting identification algorithm. The improved DeepLabV3+ model not only utilizes the powerful feature extraction capability of ResNet, but also increases the receptive field through Dilation Convolutions, while maintaining the resolution of the feature map;

[0068] Among them, the improved DeepLabV3+ algorithm framework still adopts the Encoder-Decoder structure. The encoder part is responsible for extracting the high-level semantic information of the image, while the decoder part is responsible for recovering the spatial information to obtain more accurate segmentation results.

[0069] The encoder includes five parts of a residual backbone network, a dilated convolution network, an ASPP module (a spatial pyramid pooling module), and an attention mechanism. The backbone network adopts an improved ResNet residual network to extract basic features of an image. By introducing a residual block, the gradient vanishing problem in a deep neural network is effectively alleviated, and the training efficiency and performance of the network are improved. On the basis of the backbone network, a dilated convolution is introduced to expand the receptive field while maintaining the resolution of the feature map. The dilated convolution inserts holes (i.e., skips some pixels) between the convolution kernels, so that the convolution kernel can capture more extensive context information without increasing the amount of calculation. The ASPP module includes multiple parallel dilated convolutions, each having a different dilation rate. These dilated convolutions act on the input feature map in a parallel manner and can capture features at different scales. The ASPP module also includes a global average pooling operation and a standard 1x1 convolution for capturing the most basic local information. Through the ASPP module, the encoder can generate a feature map with rich multi-scale context information. The attention mechanism is introduced to enhance the network's attention to important features. The attention mechanism can generate an attention weight map by calculating the correlation between feature maps, thereby highlighting important features and suppressing irrelevant features, and improving the segmentation accuracy of silicon-oscillation separation visual images.

[0070] The decoder mainly includes three parts of a feature fusion module, an up-sampling module and a prediction module, and a batch normalization module. The decoder receives high-level semantic feature maps from the encoder and low-level feature maps in the backbone network. First, the low-level feature maps are subjected to 1x1 convolution for channel dimension reduction, and then the high-level semantic feature maps from the ASPP are subjected to interpolation up-sampling to make their size the same as that of the low-level feature maps. Next, the two are concatenated and sent to a group of 3x3 convolution blocks for processing to fuse feature information at different scales. After feature fusion, the decoder performs linear interpolation up-sampling again to restore the resolution of the feature map to the same as that of the original image. Finally, a 1x1 convolution is used for channel adjustment to obtain the final segmentation result. In addition, a batch normalization operation is introduced after each convolution layer of the network to accelerate model convergence and prevent gradient vanishing. By normalizing each small batch of data, the output of the network is more stable, and the generalization ability of the network is improved.

[0071] In the preferred embodiment, an attention mechanism is also incorporated into the model to further enhance the ability to capture key information. To accelerate model training and enhance the generalization ability of the model, the batch normalization method is used, and the network structure is optimized to improve the convergence speed and segmentation accuracy of the model, thereby generating accurate segmentation lines;

[0072] According to the image segmentation result, the separation position of the silicon wafer and the glass in the subsequent separation is predicted, and the voltage and frequency values are adaptively adjusted based on the predicted separation position and the current position of the sorting plate.

[0073] In the preferred embodiment, the image processing module uses an improved DeepLabV3+ algorithm for image segmentation. By accurately segmenting the image at the end of the material platform, we can accurately identify the actual falling position of the product.

[0074] In the preferred embodiment, the controller is selected from the Siemens 1200 series; the DI interface of the controller is connected in series with the normally open contact of the thermal relay to collect device operating indicators and send command signals, ensuring the safe and stable operation of the motor and fault alarm; the display device is selected from the Siemens series as a human-machine interface to view the device operating status in real time and control the start and stop of the device;

[0075] The core of the operating indicators is the voltage and frequency setting of the sorting vibrator, where the specific values of voltage and frequency have a known and explicit correlation with the motion state of the silicon wafer and glass during the separation process.

[0076] In addition, to achieve the above-mentioned purposes, as shown in Figure 1 The working process of the retired photovoltaic module silicon glass physical separation system of the present application is as follows:

[0077] Step 1: System startup, material arrives at the inlet of the vibrating feeder;

[0078] Step 2: The vibrating feeder starts according to the initial default value, and the control center obtains and displays the current frequency and voltage of the feeding vibrator in real time;

[0079] Step 3: The material reaches the material platform, and the sorting vibrator operates according to the default initial value, and the material platform is at the default initial inclination angle;

[0080] Step 4: The material is conveyed to the vision acquisition area to achieve preliminary separation of the silicon wafer and the glass;

[0081] Step 5: The image acquisition component captures images of the material platform in real-time through an industrial camera, which are then processed and analyzed by the image processing module to obtain predicted separation position coordinate values. The controller compares the predicted coordinates with the current sorting plate coordinates to check the position deviation and determine whether it is within the allowed range. If it is, step 7 is executed; if not, step 6 is executed.

[0082] Step 6: When the system detects that the position deviation of the silicon wafer or glass on the material platform exceeds the pre-set allowed range, it will immediately trigger the start of the Model Predictive Control (MPC) algorithm. The core of this MPC algorithm lies in the use of its built-in system dynamic model, which deeply simulates the physical behavior characteristics of the sorting vibrator, material platform, and silicon wafer or glass separation, ensuring the high accuracy of the model. During the algorithm's operation, the current system state is comprehensively considered, specifically including the actual position of the silicon wafer or glass on the material platform, as well as the key control variables - voltage and frequency. At the same time, the MPC algorithm also explicitly sets the prediction time domain and control time domain: the prediction time domain is used to define the time span for the algorithm to predict the future state of the system, while the control time domain limits the time range considered by the algorithm when optimizing control inputs. Based on the above information, the MPC algorithm carefully constructs an optimization problem, aiming to find a series of optimal control input sequences to minimize future position deviations or meet other pre-set cost function requirements. Through advanced optimization algorithms, MPC can output a series of optimal control input sequences that can guide the system to operate in an optimal state within a specific time period in the future. Subsequently, the system intelligently selects the required control input at the current time from the optimal control input sequence, i.e., the accurate voltage and frequency values, and converts them into adjustment instructions. These instructions are then sent to the sorting vibrator controller, which immediately executes the corresponding adjustment actions upon receiving the instructions. To ensure the accuracy and effectiveness of the adjustment, the system continuously monitors the controller's feedback until it confirms that the voltage and frequency values have been correctly set. Once the adjustment is completed and verified, the system automatically returns to step 5, restarting the position prediction and deviation checking process to ensure the accurate separation of silicon wafers or glass is continuously achieved;

[0083] Step 7: The image processing module identifies the product drop position;

[0084] Step 8: The obtained product actual drop position is converted into a machine coordinate system that can be understood by the PLC, obtaining the product drop coordinates;

[0085] Step 9: The controller converts the product drop coordinates into control signals through the I / O module and transmits them to the stepper motor driver;

[0086] Step 10: The stepper motor driver adjusts the pulse frequency and pulse number of the stepper motor according to the signals, thereby accurately controlling the placement angle of the sorting plate;

[0087] Step 11: Use the position sensor to detect the current position of the sorting plate;

[0088] Step 12: The PLC receives data from the sensor and processes it according to a predetermined algorithm or logic to obtain the coordinates of the sorting plate.

[0089] Step 13: The controller compares the current sorting plate coordinates with the product drop coordinates to form a closed-loop control system to ensure positioning accuracy. If they are the same, proceed to Step 14.

[0090] Step 14: The separated silicon wafer glass material falls into the material recovery vessel below due to the automatic interception of the sorting plate, completing the collection.

[0091] Further preferably, the control center monitors the running state of the entire system in real time, including the vibration voltage and frequency of the vibrator, the inclination angle of the sorting plate, the horizontal inclination angle and longitudinal inclination angle of the sorting platform, and displays them in real time to the HMI.

[0092] Further preferably, the initial position coordinates of the sorting plate are the origin of the controller's coordinate system.

[0093] Further preferably, in the physical separation control method for retired photovoltaic module silicon wafer glass, the initial values of the vibration voltage and frequency of the vibrator, the horizontal inclination angle of the platform, etc. are the better values summarized through experiments, which can achieve better separation effect.

[0094] In summary, the present application aims to provide a physical separation control system and method for retired photovoltaic module silicon wafer glass. By providing a physical separation control system and method for retired photovoltaic module silicon wafer glass, efficient separation of the oscillation separation process of the silicon wafer and glass is realized, the separation boundary between the silicon wafer and the glass product is accurately identified, the oscillation separation equipment is controlled to automatically intercept and separate the silicon wafer and glass particles stably, and the automation and intelligent control of the entire physical separation process of the silicon wafer and glass are realized.

[0095] The present application has the following advantages:

[0096] (1) High separation efficiency: Traditional separation of retired photovoltaic module silicon wafer glass usually requires manual operation, which is slow and prone to errors. Machine vision technology can realize fast and accurate image recognition and analysis, thereby improving separation efficiency.

[0097] (2) Reduce labor costs: Using machine vision technology can reduce the demand for manual labor, thereby reducing labor costs. Since the machine vision system can automatically perform the separation process without direct human involvement, it can reduce related training and management costs.

[0098] (3) Improve safety: In the traditional process of separating silicon wafers from glass, operators may face certain safety risks, such as being cut by glass fragments. The physical separation control system and method based on machine vision can avoid these potential dangers and protect the safety of operators.

[0099] (4) Realize automated production: Machine vision technology combined with an automatic control system can achieve rapid physical separation and processing of retired photovoltaic module silicon wafers and glass, thereby realizing automation of the production process. This not only improves production efficiency but also helps to improve product quality and reduce production cycle.

[0100] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A physical separation control system for silicon wafer glass in decommissioned photovoltaic modules, characterized in that, include: The system includes a feeding component, a sorting component, a sensing component, and a control component; the sorting component and the sensing component communicate with the control component. The feeding assembly is used to convey the mixture to the sorting assembly for sorting; The sensing component is used to collect real-time images of the mixture being sorted on the sorting component, and to determine whether the silicon wafers and glass in the mixture have been successfully sorted based on the real-time images. The control component is used to control the sorting component to adjust the sorting parameters when the sensing component determines that the silicon wafers and glass in the mixture have failed to be sorted. The sensing component includes an image acquisition component and an image processing module. The image acquisition component is used to acquire the real-time image and send the real-time image to the image processing module. The image processing module is used to input the real-time image into a pre-trained sorting and recognition model to obtain the position information of the segmentation boundary between the silicon wafer area and the glass area at the end of the material conveying platform. The control component predicts the subsequent separation position of the silicon wafer and glass based on the image segmentation results, and compares the predicted separation position with the current optimal sorting plate position to calculate the position deviation. When the position deviation exceeds the preset allowable range, the instantaneous trigger model predictive control algorithm is used to adaptively adjust the voltage and frequency values. The instantaneous trigger model predictive control algorithm outputs the optimal control input sequence with the requirement of minimizing future unknown deviations and satisfying the preset cost function. The control component selects the control input required at the current moment, i.e., the precise voltage and frequency values, from the optimal control input sequence and converts them into adjustment commands. The adjustment commands are then sent to the vibration voltage and frequency adjustment component. After receiving the command, the vibration voltage and frequency adjustment component will immediately execute the corresponding adjustment action. The sorting assembly includes a material platform, a vibration voltage and frequency adjustment assembly, a height adjustment assembly, a first sorting plate, and a second sorting plate; the vibration voltage and frequency adjustment assembly and the height adjustment assembly both communicate with the control assembly. The material platform is used to receive and sort the mixed materials transported by the feeding assembly; The vibration voltage frequency adjustment component is used to control the vibration of the material platform; it includes multiple sorting vibrators disposed at the bottom of the material platform, the multiple sorting vibrators being distributed at intervals along the transport direction of the material platform; all multiple sorting vibrators establish communication with the control component; The height adjustment component is used to adjust the position and orientation of the material platform, and includes a first three-phase motor and a second three-phase motor. The first three-phase motor is used to adjust the longitudinal height of the material platform in a first direction, where the first direction is the material transport direction of the material platform. The second three-phase motor is used to adjust the longitudinal height of the material platform in a second direction, where the second direction is on the same horizontal plane as the first direction and perpendicular to it. The first sorting plate is used to intercept the silicon wafers sorted out by the material platform; The second sorting plate is used to intercept the glass material sorted by the material platform; The control component is used to control the vibration voltage frequency adjustment component and the height adjustment component to adjust the vibration voltage, vibration frequency and posture of the material platform when the sensing component determines that the silicon wafers and glass in the mixture have failed to be sorted, so as to make the mixture sorted successfully. When the mixture is sorted successfully, the control component controls the first sorting plate and the second sorting plate to quickly cut out the material.

2. The physical separation control system for silicon wafer glass of decommissioned photovoltaic modules according to claim 1, characterized in that, The sorting and recognition model includes an encoder, a decoder, and a boundary extraction module; The encoder includes a residual backbone network, a dilated convolutional network, a spatial pyramid pooling module, and an attention mechanism; the dilated convolutional network is used to extract multiple global feature maps of different scales on the input image in parallel through the residual backbone network; The spatial pyramid pooling module is used to enhance the local semantic information corresponding to the multiple global feature maps of different scales; the attention mechanism is used to calculate the correlation between multiple global feature maps and generate an attention weight map. The decoder includes a feature fusion module, an upsampling module, a prediction module, and a batch regularization module. The feature fusion module is used to fuse multiple global feature maps of different scales according to the attention weight map to obtain a fused feature map. The upsampling module and the prediction module are used to perform linear interpolation upsampling on the fused feature map and perform channel adjustment to obtain segmented images and segmentation masks of silicon wafer materials and glass materials. The batch regularization module is used to perform batch regularization operations on the convolutional layers in the decoder. The boundary extraction module is used to extract boundaries based on the segmented images and segmentation masks of the silicon wafer material and glass material, and to calculate the coordinates of the separation boundary based on the extracted boundaries.

3. The physical separation control system for silicon wafer glass of decommissioned photovoltaic modules according to claim 2, characterized in that, The sensing component includes a lighting module and an image display module; the image display module is connected to the image processing module; the image acquisition component includes multiple industrial cameras for acquiring real-time photos of the material transport end; and the lighting module is used to provide supplementary lighting for the industrial cameras.

4. The physical separation control system for silicon wafer glass of decommissioned photovoltaic modules according to claim 3, characterized in that, The sorting component further includes a first position adjustment component and a second position adjustment component; both the first position adjustment component and the second position adjustment component are connected to the control component. The first position adjustment component is used to adjust the position of the first sorting plate; The second position adjustment component is used to adjust the position of the second sorting plate.

5. The physical separation control system for silicon wafer glass of decommissioned photovoltaic modules according to claim 4, characterized in that, The sorting and recognition model is also used to determine the segmentation position of silicon wafers and glass on the real-time image, as well as the predicted drop position of silicon wafers and glass at the end of the material platform. The control component is also used to compare the first falling position of the silicon wafer with the first real-time position of the first sorting plate. When the deviation between the first falling position and the first real-time position is greater than a preset threshold, the control component is used to adjust the position of the first sorting plate so that the deviation between the first falling position and the first real-time position is within the preset threshold. and / or The control component is also used to compare the second falling position of the glass with the second real-time position of the second sorting plate. When the deviation between the second falling position and the second real-time position is greater than a preset threshold, the control component is used to adjust the position of the second sorting plate so that the deviation between the second falling position and the second real-time position is within the preset threshold.

6. The physical separation control system for silicon wafer glass of decommissioned photovoltaic modules according to claim 5, characterized in that, The feeding assembly includes: a feeding funnel and a feeding vibrator; The feeding funnel is used to transfer the input material to the material platform; The feed vibrator is used to vibrate the feed funnel.

7. The physical separation control system for silicon wafer glass of decommissioned photovoltaic modules according to claim 6, characterized in that, Both the first position adjustment component and the second position adjustment component are stepper motors; The control components include a stepper motor driver, a stepper motor controller, a feeding vibration controller, a sorting vibration controller, a three-phase motor controller, and a PLC controller. Each PLC controller communicates with the stepper motor controller, feeding vibration controller, sorting vibration controller, and three-phase motor controller. The stepper motor controller is connected to the stepper motor via the stepper motor driver. The feeding vibration controller is connected to the feeding vibrator. The sorting vibration controller is connected to the sorting vibrator. The three-phase motor controller is connected to a first three-phase motor and a second three-phase motor.

Images