An intelligent shaking table diversion and ore sorting system, sorting method and software hub platform

Abstract

The present invention relates to an intelligent shaking table diversion and ore sorting system, a sorting method, and a software hub platform, comprising a high-performance server, a touch display screen, a data switch, a central control cabinet, a gigabit Ethernet line, a shaking table group, a diversion and ore sorting device, a shaking table water supply control group, and a shaking table ore supply control group. The shaking table group includes multiple shaking tables, and the shaking table group includes an upstream shaking table group, a midstream shaking table group, and a downstream shaking table group. Each shaking table is used for mineral sorting and is equipped with a diversion and ore sorting device. The diversion and ore sorting device is connected to the data switch via a first gigabit Ethernet line to transmit image data to the high-performance server, and transmits control instructions to the high-performance server via a second gigabit Ethernet line. The present invention controls multiple shaking tables simultaneously through a single-control multi-intelligent control center, realizes the precise identification of ore zone demarcation points and the dynamic adjustment of the diversion and ore receiving plate function, thereby reducing labor intensity and improving sorting accuracy and efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of mineral processing, and in particular relates to an intelligent shaking table diversion and ore sorting system, a sorting method and a software hub platform. Background Art

[0002] Gravity separation plays a crucial role in the mineral processing process of non-coal mines, particularly in the separation of rare and precious metal ores such as tungsten, tin, tantalum, niobium, and gold. As the core equipment in this process, the ore-dressing table, through its unique water flow and asymmetric reciprocating motion, loosens and stratifies the minerals on the bed surface, forming fan-shaped ore zones, including concentrated concentrate zones, intermediate zones, and tailings zones. However, despite the irreplaceable role of ore-dressing tables in mineral processing, their operation remains largely manual, particularly for the dynamic positioning, diversion, separation, and collection of the concentrate zone. Ore-dressing plants are typically equipped with dozens or even hundreds of ore-dressing tables. Workers must continuously monitor the ore zones and manually adjust the diversion plates based on their experience to adapt to real-time changes in the ore zone position. This manual operation is not only labor-intensive but also difficult to ensure consistent separation accuracy and efficiency due to variations in worker judgment and experience. It also makes it difficult to avoid concentrate losses due to delayed adjustments.

[0003] Although some automation technologies have emerged on the market, attempting to replace or assist manual operations, they exhibit significant limitations in practical applications. Existing automation technologies often suffer from several issues: First, automatic control equipment is often limited to single control or only controls a single process segment, making it difficult to achieve centralized control of shakers across multiple process segments. This not only results in high investment costs but also makes overall management and control inconvenient. Second, these devices lack accuracy in receiving position, adjustment frequency, and response speed, resulting in processing performance that cannot meet production requirements. Finally, existing automation systems are significantly affected by the operating environment and are highly sensitive to the shaker's feed, water supply, vibration parameters, and ambient light. Furthermore, they lack closed-loop feedback control, making it difficult for the system to achieve stable operation. These drawbacks not only fail to effectively reduce workers' labor intensity, but can also lead to concentrate losses due to technical errors, increase production costs, and reduce mineral processing efficiency. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides an intelligent shaking table diversion and ore sorting system, a sorting method and a software hub platform to achieve the precise identification of ore zone boundary points and the dynamic adjustment of the diversion and ore receiving plates, thereby reducing labor intensity, improving sorting accuracy and efficiency, and overcoming the limitations of existing automation equipment in terms of accuracy, response speed and environmental adaptability.

[0005] To achieve the above object, the technical solution of the present invention is as follows:

[0006] An intelligent shaking table diversion and ore sorting system includes a high-performance server, a touch screen, a data switch, a central control cabinet, a first gigabit Ethernet line, a second gigabit Ethernet line, a shaking table group, a diversion and ore sorting device, a shaking table water supply control group and a shaking table ore supply control group. The high-performance server is used to process the collected image data and generate control commands. The touch screen is directly connected to the high-performance server to provide a user operation and monitoring interface. The data switch is connected to the high-performance server to aggregate image data from multiple shaking tables. The central control cabinet is used to integrate and install high-performance servers, touch screens and data switches. The shaking table group includes multiple shaking tables, and the shaking table group includes an upstream shaking table group, a midstream shaking table group, and a shaking table group. The downstream of the group, the midstream of the shaking table group is the next mineral processing stage upstream of the shaking table group, and the downstream of the shaking table group is the next mineral processing stage upstream of the shaking table group, wherein each shaking table is used to handle mineral sorting, and each shaking table is equipped with a diversion and ore sorting device, which is connected to the data switch through the first Gigabit Ethernet line to transmit image data to the high-performance server, and transmits control instructions to the high-performance server through the second Gigabit Ethernet line. The high-performance server controls the shaking table water supply control group and the shaking table ore feeding control group respectively through the signal bus according to the sorting situation of the diversion and ore sorting device, so as to realize closed-loop automatic control of automatic ore receiving, automatic water supply and automatic ore feeding of the shaking tables in each mineral processing section.

[0007] Preferably, each shaking table in the shaking table group includes a shaking table surface at the top, a shaking table chute at the edge of the shaking table surface, and a shaking table fence at the edge of the shaking table chute.

[0008] Preferably, the diversion and ore sorting device is installed on the shaking table fence, including a network camera located directly above the shaking table surface, connected to the device support frame through an extendable camera bracket, for collecting image data; the drive and controller are located inside the diversion and ore sorting device, and are connected to the stepper motor to receive control instructions from the high-performance server and drive the stepper motor to rotate; the control button panel is connected to the drive and controller for manually controlling the rotation of the stepper motor; the stepper motor is connected to the linear belt module to drive the linear module slider to move; the front end of the calibration plate is connected to the linear module slider, and the rear end is connected to the diversion and ore plate, so as to realize the left and right linear movement of the diversion and ore plate under the control of the control button panel or the high-performance server.

[0009] On the other hand, the present invention also discloses an intelligent shaking table diversion and ore sorting method based on the above-mentioned intelligent shaking table diversion and ore sorting system, comprising:

[0010] Step S1: Image preprocessing: compressing the image of the shaking table collected by the network camera to maintain the same aspect ratio of the image, and filling the edge area to form a standardized image size;

[0011] Step S2: building a deep learning algorithm model, including image sample collection and labeling, model design, and model training;

[0012] Step S3: Model prediction and recognition: input the image data of non-training samples into the trained model, use the model weight parameters to identify the mineral belt boundary points, generate a segmentation mask to distinguish the different areas of the mineral belt, and the prediction output includes the category label, bounding box and pixel-level mask;

[0013] Step S4: Post-processing of ore zone position identification: By analyzing the segmentation mask output by the model, the boundary point between the concentrate zone and the intermediate ore zone is accurately identified, and the boundary point is determined as the target position of the diversion and ore receiving plate;

[0014] Step S5: Dynamically adjust the diversion and ore receiving plate. Generate a control command based on the real-time identified ore zone boundary point information, and dynamically adjust the position of the diversion and ore receiving plate to align it with the boundary point to ensure accurate diversion and sorting of the minerals.

[0015] Preferably, step S1 includes:

[0016] S11, input original image;

[0017] S12, determining the target size;

[0018] S13, calculating the proportional scaling factor and comparing the sizes;

[0019] S14, applying the scaling factor to scale the source image proportionally;

[0020] S15, calculating the size of the scaled image;

[0021] S16, copying the scaled image to the center of the target image array to form a new image;

[0022] S17, filling the edge of the new image array;

[0023] S18. Output the filled image.

[0024] Preferably, step S2 is completed using a high-performance server, including:

[0025] S21. Image sample collection and labeling: For a single shaker, image sample data is collected periodically, with a sample quantity of no less than 1,000. Regional labeling is performed based on the distribution of ore zones in the sample. Labeled regions are defined as background, concentrate, intermediate, and tailings areas to form a labeled image dataset.

[0026] S22. Model design uses an improved YOLOv7-Segmentation model based on multi-scale feature fusion, path aggregation network, and fast spatial pyramid pooling technology, combined with the EIoU loss function, to improve the detection and segmentation speed and accuracy of large targets in mining belts and small targets at the marking position of moving devices;

[0027] S23. Model training: input the labeled image sample dataset into the designed algorithm model to enable the model to learn the classification and segmentation features of each area. The trained model can generate the final prediction results with category labels, bounding boxes and pixel-level masks, thereby realizing the accurate identification of the mineral belt boundary points.

[0028] Preferably, in step S22, the improved YOLOv7-Segmentation model is that the input stage is used to receive an image of size 512x512x3, and includes a backbone network C3 module, the C3 module includes: a first convolution layer, configured with 32 filters, a convolution kernel size of 3x3, a step size of 1, a padding of 1, and after batch normalization and ReLU activation function processing, the output size is 512x512x32; a second convolution layer, configured with 64 filters, a convolution kernel size of 3x3, a step size of 1, a padding of 1, and an output size of 512x512x64 after batch normalization and ReLU activation function processing; and setting the c3k parameter to False in the shallow network to form a C2f structure similar to that in YOLOv8.

[0029] Preferably, in step S22, the improved YOLOv7-Segmentation model includes a feature fusion part, wherein the C3 module outputs and generates feature maps of four different scales, with sizes of 512x512x64, 256x256x128, 128x128x256 and 64x64x512 respectively, and further fuses feature maps of different scales through the feature pyramid network FPN and the path aggregation network PAN, and keeps the output size consistent; a multi-head attention mechanism C2PSA is embedded in the C2 mechanism to enhance the spatial perception ability of the feature map; the multi-scale feature map is detected in the P2 detection layer, The 1x1 convolution dimensionality reduction is achieved through the fast spatial pyramid pooling SPPF module, and multiple pooling is performed using MaxPool2d with different convolution kernel sizes. After connecting the results, the output feature map sizes are 512x512x64, 256x256x128, 128x128x256 and 64x64x512; the detection head includes depthwise separable convolution DWConv, an adaptive anchor box mechanism is configured to optimize the anchor box configuration, and an EIoU loss function is introduced to improve the prediction accuracy by considering the overlapping area, aspect ratio and center point offset between the predicted box and the true box, and finally outputs the prediction results of category labels, bounding boxes and pixel-level masks.

[0030] On the other hand, the present invention also discloses a software central platform for executing the above-mentioned intelligent shaking table diversion and ore sorting method. The tasks of the software central platform are divided into a main thread, an image acquisition thread, a real-time display thread and a logic control thread. The main thread runs the main interface of the software central platform. The main interface includes a parameter setting module, a monitoring module, a user operation module and a communication module. The main thread starts the other three threads through the user operation module; the image acquisition thread is set to read the image data collected by the network camera at a fixed frequency, and transmits the read image to the data queue; the real-time display thread reads the image data from the data queue at a fixed frequency, on the one hand, displays the image in the main interface in the form of video, and on the other hand, sends the latest image data to the logic control thread; the logic control thread includes a mineral belt boundary point identification module, a logic control algorithm core and a command generation module. The logic control thread generates control commands based on the boundary point information in the mineral belt image, and continuously monitors the changes in the mineral belt boundary point to dynamically adjust the system control parameters.

[0031] Preferably, the software central platform also includes configuration and monitoring functions, which supports the operator to complete the target offset value setting of the diversion plate position in the parameter setting window, and stop the operation of the diversion and ore sorting device at any time through the emergency stop button in the control button panel. After operation, the diversion plate position is automatically adjusted to align with the ore belt boundary point, and the changes in the boundary point are continuously monitored. The operator can monitor the system status in real time and view the operation log.

[0032] Compared with the prior art, the advantages of the present invention are:

[0033] The present invention realizes the automation and intelligence of mineral processing operations by providing an intelligent shaking table diversion and ore sorting system, a sorting method, and a software hub platform, significantly improving sorting accuracy and efficiency. The system utilizes a deep learning algorithm and, through an improved YOLOv7-segmentation model, significantly improves the detection and segmentation speed and accuracy of large targets such as ore belts and small targets such as motion device markers while maintaining high segmentation accuracy, and has important practical application value. In addition, by setting a "one control multiple" mode, the system can simultaneously control the operation of multiple shaking tables, simplifying the operating process, reducing labor intensity, and enabling the system to maintain stable operation in different operating environments, unaffected by environmental factors such as light, achieving a higher level of automation. The software hub platform integrates modules such as parameter setting, real-time monitoring, and user operation, and realizes dynamic monitoring and real-time adjustment of ore belt demarcation points through logical control threads, further optimizing the sorting process. The overall design of the system helps to improve the accuracy of ore belt identification, ensure the continuity and accuracy of the sorting process, thereby improving the stability and efficiency of mineral sorting operations and providing reliable technical support for mineral processing operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a structural diagram of the multiple intelligent shaking table diversion and ore sorting system of the present invention;

[0035] Figure 2 A top view of the intelligent shaking table diversion and ore separation system of the present invention;

[0036] Figure 3 This is a structural schematic diagram of the diversion and ore separation device of the present invention;

[0037] Figure 4 This is a design framework diagram of the single intelligent shaking table diversion and ore sorting system of the present invention;

[0038] Figure 5 This is a design framework diagram of the multi-intelligent shaking table diversion and ore sorting system of the present invention;

[0039] Figure 6 This is a schematic flow chart of the intelligent shaking table diversion and ore separation method of the present invention;

[0040] Figure 7 This is a diagram showing the prediction effect of the deep learning algorithm model of the present invention;

[0041] Figure 8 This is a schematic diagram of the positioning of the mineral belt boundary points of the deep learning algorithm model of the present invention;

[0042] Figure 9 This is a flow chart of the image preprocessing method of the present invention;

[0043] Figure 10 A flowchart of constructing a deep learning algorithm model for the present invention;

[0044] Figure 11 The original image collected as the image sample of the present invention;

[0045] Figure 12 is a labeling diagram of an image sample of the present invention;

[0046] Figure 13 It is the overall framework diagram of the software process of the present invention;

[0047] Figure 14 This is a diagram of the overall system architecture of the present invention;

[0048] Figure markings: 1-high-performance server; 2-touch screen; 3-data switch; 4-central control cabinet; 5-first Gigabit Ethernet line; 6-second Gigabit Ethernet line; 7-shaking table group; 8-diversion and ore sorting device; 9-shaking table water supply control group; 10-shaking table ore feeding control group; 701-upstream of shaking table group; 702-midstream of shaking table group; 703-downstream of shaking table group; 71-shaking table surface; 72-shaking table chute; 73-shaking table fence; 81-network camera; 82-extendable camera bracket; 83-device support frame; 84-drive and controller; 85-control button panel; 86-stepping motor; 87-linear belt module; 88-linear module slider; 89-calibration plate; 810-diversion and ore receiving plate. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the present invention.

[0050] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0051] like Figure 1-3 As shown, this embodiment discloses an intelligent shaking table diversion and ore sorting system, including a high-performance server 1, a touch screen 2, a data switch 3, a central control cabinet 4, a first Gigabit Ethernet line 5, a second Gigabit Ethernet line 6, a shaking table group 7, a diversion and ore sorting device 8, a shaking table water supply control group 9 and a shaking table ore supply control group 10. The high-performance server 1 is used to process the collected image data and generate control commands. The touch screen 2 is directly connected to the high-performance server 1, providing a user operation and monitoring interface, which is convenient for operators to monitor the ore sorting situation in real time. The data switch 3 is connected to the high-performance server 1, aggregating image data from multiple shaking tables, optimizing the transmission speed of image data, and ensuring the rapid response of the sorting system as a whole. The central control cabinet 4 is used to integrate and install the high-performance server 1, the touch screen 2 and the data switch 3, thereby providing centralized control and security protection of the system.

[0052] The shaking table group 7 comprises multiple shaking tables, used to perform mineral sorting tasks. Specifically, the shaking table group 7 includes an upstream shaking table group 701, a midstream shaking table group 702, and a downstream shaking table group 703, forming a segmented process flow. The midstream shaking table group 702 is the next stage of the mineral processing process after the upstream shaking table group 701, and the downstream shaking table group 703 is the next stage of the mineral processing process after the midstream shaking table group 702. This structural design divides the mineral processing process into different stages, facilitating more precise segmented control and sorting. Each shaking table is equipped with a diversion and ore sorting device 8 for diverting and receiving minerals. The diversion and ore sorting device 8 is connected to the data switch 3 via a first Gigabit Ethernet line 5, enabling real-time transmission of image data to the high-performance server 1. It also transmits control commands to the high-performance server 1 via a second Gigabit Ethernet line 6. Based on this architecture, a master-slave communication model is established between the high-performance server 1 and the diversion and ore sorting device 8, ensuring rapid transmission and execution of control commands.

[0053] Furthermore, based on the sorting results of the diversion and ore sorting device 8, the high-performance server 1 controls the shaking table water supply control group 9 and the shaking table ore feeding control group 10 via a signal bus. This enables closed-loop automated control of the shaking tables in each beneficiation process stage, including automatic ore receiving, automatic water supply, and automatic ore feeding. This closed-loop control mode not only ensures sorting accuracy, but also effectively improves overall sorting efficiency and reduces manual intervention, thus achieving intelligent automated beneficiation management.

[0054] Each shaker in the shaker group 7 comprises a shaker table 71 at the top, a shaker chute 72 at the edge of the table 71, and a shaker fence 73 at the edge of the chute 72. The table 71 serves as the working surface for mineral separation, separating the minerals through water flow and reciprocating motion. The shaker chute 72 guides the flow of separated minerals, while the shaker fence 73 ensures that the mineral flow is confined and prevents spillage.

[0055] The diversion and ore sorting device 8 is installed on the shaking table fence 73, and its structural design facilitates its precise control and flexible position adjustment. The diversion and ore sorting device 8 includes a network camera 81 located directly above the shaking table 71, which is connected to the device support frame 83 via an extendable camera bracket 82 and is used to collect image data of the ore belt. The real-time image transmission of the network camera 81 can provide the high-performance server 1 with a basis for identifying the ore belt demarcation point, ensuring that the position adjustment of the ore receiving plate can accurately align with the ore belt demarcation point. The drive and controller 84 is located inside the diversion and ore sorting device 8 and is connected to the stepper motor 86 to receive control instructions from the high-performance server 1 and drive the stepper motor 86 to rotate. The control button panel 85 is connected to the drive and controller 84 for manually controlling the rotation of the stepper motor 86 so that manual operation can be performed when necessary. The rotation of the stepper motor 86 drives the linear belt module 87, which drives the linear module slider 88 to move. The front end of the calibration plate 89 is connected to the linear module slider 88, and the rear end is connected to the diversion receiving plate 810. The left and right linear movement of the diversion receiving plate 810 is achieved through the movement of the linear module slider 88, so that the left and right linear movement of the diversion receiving plate 810 is achieved under the control of the control button panel 85 or the high-performance server 1, ensuring that the diversion receiving plate 810 can be accurately aligned with the boundary point of the ore belt to achieve accurate mineral diversion reception.

[0056] The first Gigabit Ethernet line 5 uses the TCP / IP protocol to transmit image data collected by the diversion, receiving, and sorting device 8 to the high-performance server 1. The TCP / IP protocol ensures high compatibility and reliability of data transmission, ensuring that image data from multiple shaking tables can be stably aggregated to the high-performance server 1 for centralized processing, thereby supporting real-time data input from multiple diversion, receiving, and sorting devices 8.

[0057] The second Gigabit Ethernet line 6 utilizes the Ethercat protocol to transmit control commands between the high-performance server 1 and each diversion, receiving, and sorting device 8. The Ethercat protocol offers fast and precise communication, significantly reducing command transmission latency. This enables the high-performance server 1 to achieve real-time control and rapid response to the actions of the diversion, receiving, and sorting devices 8, ensuring accurate position adjustment of the diversion, receiving, and sorting plates 810. This network configuration, combining TCP / IP and Ethercat protocols, ensures both data transmission compatibility and real-time responsiveness, ensuring efficient and stable operation of the intelligent shaking table diversion, receiving, and sorting system.

[0058] like Figure 4As shown in the figure, the design framework of a single intelligent shaking table diversion and ore sorting system consists of three main components: a camera-based image acquisition module, a motion control and drive module that controls the movement of the diversion and receiving plate, and a high-performance server (computer) responsible for image data processing and system control. The system uses the image acquisition module to capture real-time images of the shaking table's operating status and transmits them to the main control unit via Ethernet. The main control unit uses a preprocessing algorithm and a deep learning model to process the acquired image data, generate control instructions, and transmits them to the motion controller and drive module to drive the diversion and receiving plate to the target position, completing the mineral diversion and sorting operation. This constitutes a closed-loop intelligent automatic control system consisting of image acquisition, main control unit, and receiving plate control, effectively realizing intelligent sorting for a single shaking table.

[0059] like Figure 5 As shown, the design framework for the multi-shaker intelligent diversion, receiving, and sorting system is based on the design of the single-shaker system described above. Through a distributed layout, image data from multiple shakers is aggregated and transmitted to a high-performance server 1 via a data switch, achieving "one-to-many" processing. The processor transmits the processing results and instructions to the corresponding slave stations (drive and control modules) via the Ethercat communication protocol, which in turn drives the diversion and receiving plates of each shaker to the target position, achieving precise mineral diversion and sorting. This forms a multi-shaker intelligent automatic control system consisting of image acquisition, data switch, main control unit, drive and controller, and receiving plate control.

[0060] like Figure 6 As shown, based on a system for diverting and connecting ore and separating multiple intelligent shaking tables, the embodiment of the present application also discloses an intelligent shaking table diverting and connecting ore and separating method, including:

[0061] Step S1, image preprocessing, compresses the image captured by network camera 81 to maintain a consistent aspect ratio and pads the edges to a standardized image size. By compressing and padding the edges, consistency is ensured for images of varying sizes during subsequent processing, improving the algorithm model's adaptability to the input image.

[0062] Step S2 builds a deep learning algorithm model, which includes image sample collection and labeling, model design, and model training. This step collects and labels sample data to form a clearly classified training set. The model design utilizes the YOLOv7-Segmentation model integrated with the Convolutional Block Attention Module (CBAM) to improve recognition accuracy. Ultimately, model training enables the system to learn the characteristics of each area and accurately distinguish between concentrate, middling, and tailings zones.

[0063] Step S3, model prediction and recognition, input the image data of non-training samples into the trained model, use the model weight parameters to identify the boundary points of the ore belt, generate a segmentation mask to distinguish the various areas of the ore belt, and the predicted output includes category labels, bounding boxes and pixel-level masks. By using the trained model parameters, the system can quickly analyze and segment new images to achieve accurate recognition of various areas of the ore belt. After learning a large amount of labeled sample data, the model will eventually output a model file with new weight parameters. By loading this file and reading the image data in the non-training sample, the model can be predicted and recognized, and the effect is as follows: Figure 7 shown.

[0064] Step S4, post-processing of the ore belt position identification, by analyzing the segmentation mask output by the model, accurately identify the boundary point between the concentrate belt and the medium ore belt, and determine the boundary point as the target position of the diversion receiving plate 810. After the model algorithm is processed, it can be seen that the ore belt has been clearly segmented. As long as the boundary point adjacent to the bottom concentrate belt (yellow area) and the medium ore belt (green area) is found, it can be used as the target position of the diversion receiving plate. This solution obtains the boundary point through the image processing algorithm. Figure 8 Shown in the blue circle.

[0065] Step S5 dynamically adjusts the diversion receiving plate. Based on the real-time identification of the ore zone demarcation point, control commands are generated to dynamically adjust the position of the diversion receiving plate 810 to align it with the demarcation point, ensuring accurate diversion and sorting of the minerals. Dynamic adjustment automates the movement of the diversion receiving plate 810 to align it with the ore zone demarcation point, ensuring accurate diversion and sorting of the minerals and improving the utilization efficiency of mineral resources.

[0066] like Figure 9 As shown, the image preprocessing in step S1 includes:

[0067] S11, input original image;

[0068] S12, determining the target size;

[0069] S13, calculating the proportional scaling factor and comparing the sizes;

[0070] S14, applying the scaling factor to scale the source image proportionally;

[0071] S15, calculating the size of the scaled image;

[0072] S16, copying the scaled image to the center of the target image array to form a new image;

[0073] S17, filling the edge of the new image array;

[0074] S18. Output the filled image.

[0075] The original image size is 2560×1920, and the compressed target size (algorithm model input size) is 512×512. The calculation formula involved in the process is as follows:

[0076] 1) Target and original image size:

[0077]

[0078]

[0079]

[0080]

[0081] 2) Calculate the scaling factor:

[0082]

[0083]

[0084] 3) Choose the minimum scaling factor to preserve the aspect ratio:

[0085]

[0086] 4) Calculate the scaled image size:

[0087]

[0088]

[0089] 5) Calculate the size of the padding required:

[0090]

[0091]

[0092] 6) Scaling the image: For each pixel In the source image, the new position = , perform zero padding:

[0093]

[0094]

[0095] 7) Output preprocessed image: The output padded image size is .

[0096] like Figure 10 As shown, step S2 is completed using the high-performance server 1, and specifically includes:

[0097] S21, Image Sample Collection and Labeling: Image sample data is collected periodically for a single shaker, with a sample size of at least 1,000. Regions are labeled based on the distribution of ore zones within the samples. Labeled regions are defined as background, concentrate, intermediate, and tailings areas, forming a labeled image dataset. Collecting a large number of image samples ensures sufficient model training and generalization capabilities. Region labeling enables the model to learn the characteristics of different ore zones, laying the foundation for subsequent accurate identification. Figure 11 is the original image from which the image samples were collected. Figure 12 is the label map of the image sample.

[0098] S22, model design, adopts the improved YOLOv7-Segmentation model, based on multi-scale feature fusion, path aggregation network and fast spatial pyramid pooling technology, combined with the EIoU loss function, to improve the detection and segmentation speed and accuracy of large targets in mining belts and small targets in the marking position of moving devices.

[0099] S23, model training, involves inputting the labeled image sample dataset into the designed algorithm model, enabling it to learn the classification and segmentation characteristics of each region. The trained model generates final predictions with category labels, bounding boxes, and pixel-level masks, enabling accurate identification of mineral zone demarcation points. Through model training, the algorithm adjusts its internal parameters to adapt to the data characteristics. Ultimately, the model is able to accurately interpret newly input shaking table images, providing reliable data support for the system's automated control.

[0100] In this example, an improved YOLOv7-Segmentation model is proposed. By integrating the CBAM attention mechanism, it significantly improves object detection and instance segmentation performance. The model leverages CBAM's channel and spatial attention capabilities to dynamically enhance key information in feature maps while suppressing irrelevant features. This improvement enables the model to more accurately identify and locate objects and generate high-quality segmentation masks when processing high-resolution 512x512 pixel input images. Through a carefully designed loss function and optimization strategy, the model further improves detection accuracy and segmentation quality while maintaining the original fast detection advantage of YOLOv7.

[0101] In this embodiment, the model's input stage accepts images of size 512x512x3, formatted as width x height x number of channels, to accommodate the computational requirements of the subsequent network. The model's backbone network uses the C3 module as its foundational architecture. The first convolutional layer uses 32 filters with a kernel size of 3x3, a stride of 1, and padding of 1. After this layer, the output feature map has a size of 512x512x32. The feature map then undergoes BatchNorm and ReLU activation to further enhance network training stability, maintaining the output size at 512x512x32.

[0102] In the second convolutional layer of the backbone network, the number of filters increases to 64, and the convolution kernel size remains 3x3, with a stride of 1 and padding of 1. After the same batch normalization and ReLU activation, the output size is updated to 512x512x64. To optimize shallow feature learning, the C3 module uses the C3k2 mechanism. In shallow networks, the c3k parameter is set to False, forming a structure similar to the C2f in YOLOv8, which enhances the model's performance in processing small object features.

[0103] In the feature fusion phase, the C3 module outputs feature maps of four different scales: 512x512x64, 256x256x128, 128x128x256, and 64x64x512. These feature maps are further fused using a Feature Pyramid Network (FPN) to extract rich feature information from different scales and ensure consistent output sizes. Simultaneously, a Path Aggregation Network (PAN) is used to further optimize the feature fusion process, resulting in final output feature map sizes of 512x512x64, 256x256x128, 128x128x256, and 64x64x512, improving detection of both large and small objects.

[0104] The C2 mechanism incorporates a C2PSA multi-head attention mechanism, which uses pyramid spatial attention (PSA) to enhance the spatial perception of feature maps, thereby strengthening the network's ability to capture and identify objects. A P2 detection layer is added after the first output of the C3 module to increase feature output and facilitate multi-scale feature map detection. The output feature map sizes are 512x512x64, 256x256x128, 128x128x256, and 64x64x512.

[0105] The fast spatial pyramid pooling module (SPPF) achieves dimensionality reduction through 1x1 convolution and performs multiple pooling using MaxPool2d with different convolution kernel sizes to obtain a fusion output of features at different scales. The output feature map sizes are 512x512x64, 256x256x128, 128x128x256, and 64x64x512, providing rich multi-scale information for the model detection stage.

[0106] The detection head uses a depthwise separable convolution (DWConv) structure. By adding two DWConv convolution kernels, the model's computational complexity and parameter count are reduced, improving overall efficiency. The output size of the detection head is determined by the specific parameters and settings of DWConv.

[0107] Furthermore, to adapt to the characteristics of different datasets, the model introduces an adaptive anchor box mechanism, automatically optimizing the anchor box configuration across different datasets to improve object detection accuracy. Furthermore, the model incorporates the Extended IoU (EIoU) loss function, which takes into account the overlap area, aspect ratio, and center point offset between the predicted and ground-truth boxes when calculating the loss, further improving the model's prediction accuracy. The model ultimately generates predictions including category labels, bounding boxes, and pixel-level masks, enabling high-precision object detection and segmentation.

[0108] like Figure 13 As shown, an embodiment of the present application also discloses a software hub platform for executing the above-mentioned intelligent shaking table diversion and ore sorting method. The tasks of the software hub platform are divided into a main thread, an image acquisition thread, a real-time display thread and a logic control thread. The main thread runs the main interface of the software hub platform, and the main interface includes a parameter setting module, a monitoring module, a user operation module and a communication module. Through the user operation module, the main thread can start the other three threads, so that the entire system has good interactivity and flexibility in operation. The image acquisition thread is set to read the image data collected by the network camera 81 at a fixed frequency, and transmits the read image to the data queue to ensure that the image data can be stably collected and transmitted for subsequent processing. The real-time display thread reads the image data from the data queue at a fixed frequency. On the one hand, it displays the image in the main interface in the form of video, providing a visual interface for real-time monitoring; on the other hand, it sends the latest image data to the logic control thread to ensure that the control decision is based on the latest image information. The logic control thread includes a mineral belt demarcation point identification module, a logic control algorithm core, and a command generation module. The logic control thread generates control commands based on the demarcation point information in the mineral belt image, and continuously monitors the changes in the mineral belt demarcation point to dynamically adjust the system control parameters, thereby ensuring the precise positioning and real-time response of the diversion and ore receiving plate.

[0109] Furthermore, the software hub platform also includes configuration and monitoring functions, which support operators to complete the target offset value setting of the diversion receiving plate 810 position in the parameter setting window, so that operators can flexibly adjust the position of the receiving plate to adapt to different ore belt demarcation point requirements. Through the emergency stop button in the control button panel 85, the operator can stop the operation of the diversion receiving and sorting device 8 at any time, so as to quickly control the equipment status in an emergency and ensure safety. After restarting, the system automatically adjusts the position of the diversion receiving plate 810 to align with the ore belt demarcation point, ensuring that the diversion receiving plate 810 is always in the correct position to achieve efficient mineral diversion and sorting. In addition, the system also continuously monitors the changes in the ore belt demarcation point, so that the diversion receiving plate 810 can dynamically adapt to the fluctuation of the ore belt position, further improving the sorting accuracy. Through the software hub platform, operators can monitor the system status in real time, view the operation log, track and analyze the historical operation of the system, and provide important reference data for subsequent operation and maintenance.

[0110] This application constructs a software process framework based on the functional requirements of an intelligent shaking table diversion, ore receiving, and sorting system. This software process framework integrates the functions required by the intelligent shaking table diversion, ore receiving, and sorting system, covering the system's control, monitoring, and operation functions. In practical applications, the hardware infrastructure is first fully installed to ensure that each component is in normal working order. Next, a debugging tool is used to debug the communication function with the motion control system to verify that data transmission and response between devices are normal. The diversion and ore receiving plate 810 is also calibrated to ensure that it accurately aligns with the ore zone demarcation point upon system startup. After hardware debugging is completed, the intelligent shaking table diversion, ore receiving, and sorting system is fully debugged. An appropriate target offset value is set and confirmed. This offset value influences the final position of the diversion and ore receiving plate 810, thereby adjusting the shaker's ore receiving grade. This offset value is set in the parameter settings window to ensure that all system configurations meet the sorting requirements. After configuration is complete, the operator starts the intelligent shaking table diversion, ore receiving, and sorting system through the software hub platform, and the system enters automatic operation. An emergency stop button is also provided on the platform interface, which allows operators to stop the operation of the automatic ore receiving system at any time in an emergency, thereby improving the safety and reliability of the system. After the system is started, the diversion receiving plate 810 automatically moves to the ore belt demarcation point position and begins normal mineral diversion and sorting work. During operation, the system continuously monitors the changes in the ore belt demarcation point. The diversion receiving plate 810 will automatically adjust according to the latest identified demarcation point position to maintain sorting accuracy and stability. In addition, operators can monitor the operating status of the system in real time through the software hub platform, view the dynamic performance of the system at any time, and access and view the operation log after the system is turned on, providing detailed data support for daily operations and subsequent maintenance.

[0111] like Figure 14As shown in the figure, the operation process of the intelligent shaking table diversion and ore sorting system is as follows: First, the system enters from "Start" and performs system initialization operations. The initialization process includes checking the connection status of the equipment camera, driver and ore / water flow valve to ensure that all equipment is connected normally before entering the next step of the operation process. When the camera is connected, the system executes the data acquisition module to collect shaking table image data from the camera and perform data annotation. Through deep learning model training and evaluation of the annotated data, the system generates a deep learning model suitable for the current operation. Next, the system reads the image information of each shaking table group and uses the deep learning model to determine the ore sorting position of each shaking table to ensure that the diversion and ore sorting device is positioned in the optimal sorting area.

[0112] During the operation of each shaking table receiving and sorting device, the system continuously monitors the device status and ore belt range. If it detects that the sorting device's position exceeds the set receiving range (i.e., an abnormality occurs), the system immediately adjusts the feed and water flow rates to adjust the ore and water flows to ensure the stability of the ore belt distribution, thereby maintaining sorting accuracy and efficiency. If the receiving and sorting device is within the range, the system operates normally and continues to move the sorting device to achieve dynamic sorting. Finally, when the system determines that the exit conditions have been met or receives an exit command, the program terminates and exits the process. Through this closed-loop automated control, the system effectively improves the intelligence level of mineral processing operations and reduces the burden of manual operation.

[0113] In summary, this application discloses an intelligent shaking table diversion and ore sorting system, sorting method, and software hub platform. The system, consisting of a high-performance server 1, a touchscreen display 2, a data switch 3, a central control cabinet 4, a network camera 81, and a diversion and ore receiving plate 810, forms a highly integrated intelligent sorting control system. The system divides the operation of the intelligent shaking table into a preparation layer, a control layer, and an application layer. The software hub platform implements full-process control, from image acquisition, data processing, dynamic recognition, to ore receiving plate position adjustment. The entire system utilizes a deep learning model to identify ore zone demarcation points and automatically adjust the diversion and ore receiving plate 810, improving the system's sorting accuracy and automation level. The system utilizes an improved YOLOv7-Segmentation model and CBAM attention mechanism to enhance the accuracy of ore zone image recognition and ensure sorting precision. Through a "one-control-many" intelligent control center, the system can simultaneously control the operation of multiple shaking tables, achieving efficient operational management and improving response speed. The designed image preprocessing and compression algorithms significantly improve the algorithm's inference speed while maintaining recognition accuracy. The real-time ore belt demarcation point identification algorithm based on deep learning can dynamically identify and adjust the ore belt demarcation point to achieve accurate mineral diversion and sorting effects. The system adopts a distributed architecture to centralize the image data of multiple shaking tables to the high-performance server 1 through the data switch 3 for processing, thereby achieving efficient data integration and processing. The automated diversion receiving plate 810 automatically adjusts its position according to the instructions of the control layer, making the diversion and sorting of the ore belt more accurate. The software hub platform provides a comprehensive software process framework, integrates all necessary functions, and provides an intuitive user interface and real-time monitoring function. Operators can check the system status and record operation logs at any time to facilitate troubleshooting and system optimization. The present invention effectively improves the efficiency and accuracy of mineral sorting, while reducing dependence on manual operation, and provides an innovative solution for the intelligence and automation of mine sorting technology.

[0114] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of the different aspects of the present invention as described above. For the sake of simplicity, they are not provided in detail. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions described in the above embodiments, or to make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent shaking table diversion and ore sorting system, characterized in that: The invention comprises a high-performance server (1), a touch screen (2), a data switch (3), a central control cabinet (4), a first gigabit Ethernet line (5), a second gigabit Ethernet line (6), a shaking table group (7), a diversion and ore sorting device (8), a shaking table water supply control group (9) and a shaking table ore supply control group (10), wherein the high-performance server (1) is used to process the collected image data and generate control commands, the touch screen (2) is directly connected to the high-performance server (1) to provide a user operation and monitoring interface, the data switch (3) is connected to the high-performance server (1) to aggregate image data from multiple shaking tables, and the central control cabinet (4) is used to integrate and install the high-performance server (1), the touch screen (2) and the data switch (3). The display screen (2) and the data switch (3) are provided, wherein the shaking table group (7) includes a plurality of shaking tables, and the shaking table group (7) includes an upstream shaking table group (701), a midstream shaking table group (702), and a downstream shaking table group (703). The midstream shaking table group (702) is the next beneficiation process stage of the upstream shaking table group (701), and the downstream shaking table group (703) is the next beneficiation process stage of the midstream shaking table group (702). Each shaking table is used for processing mineral sorting, and a flow guide and ore sorting device (8) is installed on each shaking table. The flow guide and ore sorting device (8) is connected to the data switch (3) via a first gigabit Ethernet line (5) to transmit image data to the high-performance server (1), and is connected to the data switch (3) via a second gigabit Ethernet line (5) to transmit image data to the high-performance server (1). The Gigabit Ethernet line (6) transmits control instructions to the high-performance server (1). The high-performance server (1) controls the shaking table water supply control group (9) and the shaking table ore feeding control group (10) respectively through the signal bus according to the sorting situation of the diversion ore sorting device (8), so as to realize the closed-loop automatic control of automatic ore receiving, automatic water supply and automatic ore feeding of the shaking tables in each ore dressing process section; the first Gigabit Ethernet line (5) adopts the TCP / IP protocol, and the second Gigabit Ethernet line (6) adopts the Ethercat protocol; each shaking table in the shaking table group (7) includes a shaking table surface at the top, a shaking table chute (72) at the edge of the shaking table surface (71) and a shaking table at the edge of the shaking table chute (72). Fence (73); wherein the diversion and ore separation device (8) is installed on the shaking table fence (73), including a network camera (81) located directly above the shaking table surface (71), connected to the device support frame (83) through an extendable camera bracket (82), for collecting image data; a drive and controller (84) is located inside the diversion and ore separation device (8), and is connected to a stepper motor (86) to receive control instructions from a high-performance server (1) and drive the stepper motor (86) to rotate; a control button panel (85) is connected to the drive and controller (84) for manually controlling the rotation of the stepper motor (86); the stepper motor (86) is connected to a linear belt module (87) to drive the linear module slider (88) to move;The front end of the calibration plate (89) is connected to the linear module slider (88), and the rear end is connected to the guide plate (810) to achieve left and right linear movement of the guide plate (810) under the control of the control button panel (85) or the high-performance server (1).

2. An intelligent shaking table diversion and ore sorting method based on the intelligent shaking table diversion and ore sorting system according to claim 1, characterized in that: include: Step S1, image preprocessing, compressing the image of the shaking table collected by the network camera (81) to keep the image aspect ratio consistent, and filling the edge area to form a standardized image size; Step S2: building a deep learning algorithm model, including image sample collection and labeling, model design, and model training; Step S3: Model prediction and recognition: input the image data of non-training samples into the trained model, use the model weight parameters to identify the mineral belt boundary points, generate a segmentation mask to distinguish the different areas of the mineral belt, and the prediction output includes the category label, bounding box and pixel-level mask; Step S4, post-processing of ore zone position identification, accurately identifying the boundary point between the concentrate zone and the medium ore zone by analyzing the segmentation mask output by the model, and determining the boundary point as the target position of the diversion and ore receiving plate (810); Step S5, dynamically adjust the guide receiving plate (810), generate a control command based on the real-time identified ore zone boundary point information, and dynamically adjust the position of the guide receiving plate (810) to align it with the boundary point to ensure accurate guide separation of the minerals.

3. The intelligent shaking table diversion and ore separation method according to claim 2 is characterized in that: Step S1 includes: S11, input original image; S12, determining the target size; S13, calculating the proportional scaling factor and comparing the sizes; S14, applying the scaling factor to scale the source image proportionally; S15, calculating the size of the scaled image; S16, copying the scaled image to the center of the target image array to form a new image; S17, filling the edge of the new image array; S18. Output the filled image.

4. The intelligent shaking table diversion and ore separation method according to claim 3 is characterized in that: Step S2 is completed using a high-performance server (1), including: S21. Image sample collection and labeling: For a single shaker, image sample data is collected periodically, with a sample quantity of no less than 1,000. Regional labeling is performed based on the distribution of ore zones in the sample. Labeled regions are defined as background, concentrate, intermediate, and tailings areas to form a labeled image dataset. S22. Model design uses an improved YOLOv7-Segmentation model based on multi-scale feature fusion, path aggregation network, and fast spatial pyramid pooling technology, combined with the EIoU loss function, to improve the detection and segmentation speed and accuracy of large targets in mining belts and small targets at the marking position of moving devices; S23. Model training: input the labeled image sample dataset into the designed algorithm model to enable the model to learn the classification and segmentation features of each area. The trained model can generate the final prediction results with category labels, bounding boxes and pixel-level masks, thereby realizing the accurate identification of the mineral belt boundary points.

5. The intelligent shaking table diversion and ore separation method according to claim 4 is characterized in that: In step S22, the improved YOLOv7-Segmentation model is that the input stage is used to receive an image of size 512x512x3, and includes a backbone network C3 module, which includes: a first convolution layer, configured with 32 filters, a convolution kernel size of 3x3, a step size of 1, a padding of 1, and after batch normalization and ReLU activation function processing, the output size is 512x512x32; a second convolution layer, configured with 64 filters, a convolution kernel size of 3x3, a step size of 1, a padding of 1, and an output size of 512x512x64 after batch normalization and ReLU activation function processing; and setting the c3k parameter to False in the shallow network to form a C2f structure similar to that in YOLOv8.

6. The intelligent shaking table diversion and ore separation method according to claim 5 is characterized in that: In step S22, the improved YOLOv7-Segmentation model includes a feature fusion part, wherein the C3 module outputs four feature maps of different scales, with sizes of 512x512x64, 256x256x128, 128x128x256 and 64x64x512 respectively, and further fuses the feature maps of different scales through the feature pyramid network FPN and the path aggregation network PAN, and keeps the output size consistent; the multi-head attention mechanism C2PSA is embedded in the C2 mechanism to enhance the spatial perception ability of the feature map; the multi-scale feature map is detected in the P2 detection layer, and the feature map is detected by the P2 detection layer. The 1x1 convolution dimensionality reduction is achieved through the fast spatial pyramid pooling SPPF module, and multiple pooling is performed using MaxPool2d with different convolution kernel sizes. The results are concatenated and the output feature map sizes are 512x512x64, 256x256x128, 128x128x256, and 64x64x512. The detection head includes depthwise separable convolution DWConv, an adaptive anchor box mechanism is configured to optimize the anchor box configuration, and an EIoU loss function is introduced to improve the prediction accuracy by considering the overlapping area, aspect ratio, and center point offset between the predicted box and the true box. Finally, the prediction results of the category label, bounding box, and pixel-level mask are output.

7. A software hub platform for executing the intelligent shaking table diversion and ore separation method according to any one of claims 2 to 6, characterized in that: The tasks of the software central platform are divided into a main thread, an image acquisition thread, a real-time display thread and a logic control thread, wherein the main thread runs the main interface of the software central platform, and the main interface includes a parameter setting module, a monitoring module, a user operation module and a communication module. The main thread starts the other three threads through the user operation module; the image acquisition thread is set to read the image data collected by the network camera (81) at a fixed frequency and transmit the read image to the data queue; The real-time display thread reads image data from the data queue at a fixed frequency, and on the one hand displays the image in the form of video in the main interface, and on the other hand sends the latest image data to the logic control thread; the logic control thread includes a mineral belt boundary point identification module, a logic control algorithm core and a command generation module. The logic control thread generates control commands based on the boundary point information in the mineral belt image, and continuously monitors the changes in the mineral belt boundary point to dynamically adjust the system control parameters.

8. The software hub platform according to claim 7, characterized in that: The software central platform also includes configuration and monitoring functions, which support the operator to complete the target offset value setting of the diversion receiving plate (810) position in the parameter setting window, and to stop the operation of the diversion receiving and sorting device (8) at any time through the emergency stop button in the control button panel (85). After operation, the position of the diversion receiving plate (810) is automatically adjusted to align with the ore belt boundary point, and the changes of the boundary point are continuously monitored. The operator can monitor the system status in real time and view the operation log.

Images