Phosphorite sorting method, electronic equipment and medium

Abstract

The invention provides a phosphorite sorting method, electronic equipment and a medium, in a preprocessing stage, an obtained raw ore high-energy diagram is registered with a low-energy diagram as a reference, a difference diagram representing gray difference is obtained through the registered high-energy diagram and the low-energy diagram, then three-channel fusion is carried out on the low-energy diagram, the registered high-energy diagram and the difference diagram, a pseudo-color diagram is obtained, and the high-energy diagram, the low-energy diagram, the high-energy diagram and the difference diagram are subjected to three-channel fusion; and in the intelligent identification stage, the pseudo-color image is used as input, and the target detection model based on deep learning is used for processing, so that the phosphorite in the raw ore is accurately and efficiently identified.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mineral separation, in particular to a phosphate rock separation method, an electronic device and a medium. BACKGROUND

[0002] With the increasing demand for global food security and sustainable agricultural development, phosphate rock, as an important resource for producing phosphate fertilizer and fine chemical products, has an irreplaceable strategic position in the fields of agriculture, chemical industry, food, medicine and new energy materials.

[0003] In the pre-selection and waste-throwing process of phosphate rock, a large amount of gangue minerals such as dolomite and calcite are often mixed in the raw ore, which has a wide particle size distribution, similar color and blurred boundary, and seriously restricts the separation accuracy and efficiency of phosphate rock. SUMMARY

[0004] The present application provides a phosphate rock separation method, an electronic device and a medium, which can solve one of the problems in the background art.

[0005] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0006] In a first aspect, a phosphate rock separation method is provided, comprising:

[0007] In the preprocessing stage, an original high-energy image and an original low-energy image of a raw ore are obtained, the original high-energy image and the original low-energy image are obtained by dual-energy X-ray projection imaging of the raw ore; using an enhanced correlation coefficient registration algorithm, the original low-energy image is used as a reference, and the original high-energy image is registered to obtain a secondary high-energy image; from the secondary high-energy image and the original low-energy image, a difference image representing the gray difference between the secondary high-energy image and the original low-energy image is obtained; and the secondary high-energy image, the original low-energy image and the difference image are fused according to three channels to obtain a pseudo-color image; and

[0008] In the intelligent identification stage, the pseudo-color image is used as the input of a target detection model based on deep learning, and the separation result of the phosphate rock in the raw ore is obtained by processing of the target detection model.

[0009] Based on the above technical solutions, in the preprocessing stage, the obtained high-energy image of the raw ore is registered with the low-energy image as a reference, the difference image representing the gray difference is obtained from the registered high-energy image and low-energy image, and then the low-energy image, the registered high-energy image and the difference image are fused in three channels to obtain a pseudo-color image. In the intelligent identification stage, the pseudo-color image is used as the input, and the target detection model based on deep learning is used for processing, so as to realize the accurate and efficient identification of phosphate rock in the raw ore.

[0010] In a possible design of the first aspect, the target detection model adopts a YOLO model, and the YOLO model includes a feature extraction network, a feature fusion network, and a detection head.

[0011] In a possible design of the first aspect, a lightweight convolution block attention module is integrated in a path aggregation based feature pyramid network of the feature fusion network, and the lightweight convolution block attention module is configured to perform attention guidance on a channel and a spatial dimension of an intermediate feature map.

[0012] In a possible design of the first aspect, in the YOLO model, a convolution layer adopts a HardSwish activation function.

[0013] wherein x represents an input of the HardSwish activation function, and ReLU6() represents a truncated form of a ReLU activation function in a range of 0 to 6.

[0014] In a possible design of the first aspect, the YOLO model adopts an Optuna hyperparameter automatic search framework.

[0015] In a possible design of the first aspect, the preprocessing stage further includes: performing gray scale enhancement processing and image normalization processing on the secondary high-energy image and the original low-energy image.

[0016] In a possible design of the first aspect, the gray scale enhancement processing adopts a contrast limited adaptive histogram equalization processing that divides an image into 12*12 grid regions.

[0017] In a possible design of the first aspect, the preprocessing stage further includes: performing background color replacement on the pseudo-color image to remove background noise interference.

[0018] In a second aspect, an electronic device is provided, including a processor and a memory coupled to the processor, the memory being configured to store a computer program, and the processor being configured to execute the computer program stored in the memory, so that the electronic device performs the phosphate ore sorting method according to any possible implementation manner of the first aspect.

[0019] In a third aspect, a computer readable storage medium is provided, including a computer program or instructions, when the computer program or instructions are executed on a computer, the computer program or instructions cause the computer to perform the phosphate ore sorting method according to any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or related description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is an X-ray diffraction analysis result schematic diagram of a phosphate rock sample provided by the present application;

[0022] Figure 2 is a collophane microstructure feature diagram provided by the present application;

[0023] Figure 3 is a main mineral particle size distribution diagram of a phosphate rock provided by the present application;

[0024] Figure 4 is a dual-energy XRT gray scale diagram of a sample provided by the present application, wherein, Figure 4 (a) is a high-energy phosphate rock XRT gray scale diagram, Figure 4 (b) is a low-energy phosphate rock XRT gray scale diagram;

[0025] Figure 5 is a gray scale histogram of a dual-energy XRT image of a phosphate rock provided by the present application;

[0026] Figure 6 is a high-energy phosphate rock image obtained after ECC registration change provided by the present application;

[0027] Figure 7 is a schematic diagram of the result of CLAHE processing of the gray scale diagram of the phosphate rock after ECC registration provided by the present application;

[0028] Figure 8 is an original three-channel pseudo-color diagram provided by the present application;

[0029] Figure 9 is a three-channel pseudo-color diagram processed provided by the present application;

[0030] Figure 10 is a YOLO model structure schematic diagram provided by the present application;

[0031] Figure 11 is a CBAM structure schematic diagram provided by the present application;

[0032] Figure 12 is a HardSwish and SiLU activation function schematic diagram provided by the present application;

[0033] Figure 13This is a flowchart of the phosphate rock identification algorithm implementation scheme provided in the embodiments of this application;

[0034] Figure 14 This is a schematic diagram illustrating the results of identifying XRT false-color images of phosphate rock provided in an embodiment of this application. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0038] Before introducing the embodiments of this application, a brief description of the current stage of technical research of this application will be given:

[0039] The elemental chemical composition of the phosphate rock samples collected in the study is shown in Table 1. Overall, the chemical composition of the samples is dominated by oxygen-containing compounds, exhibiting obvious multi-element symbiosis and complex compositional characteristics, providing a data foundation for subsequent process mineralogical research and optimization of intelligent mineral processing algorithms.

[0040] Table 1. Elemental chemical composition of mineral samples

[0041] The X-ray diffraction (XRD) analysis results of the sample are shown in the figure. Figure 1 .

[0042] The phase composition of the samples was determined using an automated mineralogy image analysis system (AMICS), as shown in Table 2.

[0043] Table 2 Phase composition of phosphate rock samples

[0044] Depend on Figure 1As can be seen from Table 2, the main minerals in the ore sample are dolomite and collophanite, with mass fractions of 48.84% and 30.19% respectively, and also containing a small amount of quartz, calcite, kaolinite and pyrite, with mass fractions of 8.02%, 3.98%, 1.62% and 1.09% respectively. Collophanite is the main useful mineral, and dolomite is a triclinic carbonate mineral, with a crystal structure similar to calcite, and is the main gangue mineral.

[0045] The microstructure characteristics of the collophanite sample are shown in Figure 2 The figure reveals that the collophanite sample has various microstructures, which reflect the typical genetic characteristics of the phosphorite in the sedimentary environment, and shows that there is a close cementation between the phosphorite and the carbonate minerals such as dolomite. These characteristics have important reference value for judging the genesis of the phosphorite, the sedimentary environment and the processing and utilization mode of the ore.

[0046] The embedded particle size characteristics are important properties of the phosphorite, and the particle size distribution of the main component minerals in the phosphorite is shown in Figure 3 As can be seen from Figure 3

[0047] (1) The particle size distribution of the overall minerals is relatively uniform, and the proportion of the particle size greater than 150 μm and the particle size less than 75 μm is close.

[0048] (2) The particle size distribution of the main minerals dolomite and collophanite is basically the same, mainly less than 75 μm, and secondly greater than 150 μm. The particle size of the minerals such as calcite, quartz and pyrite is relatively fine, and the proportion of the particle size less than 75 μm is 70%~80%.

[0049] (3) The particle size of the suzorite is mainly 75~150 μm, accounting for nearly 50%, and secondly less than 75 μm.

[0050] The particle size of the libbyite is relatively small, and the proportion of the particle size less than 75 μm is 63.30%.

[0051] According to the analysis of the process mineralogy of the sample, it is known that the sample is a phosphatic rock type ore, with a P2O5 grade of only 12.05%, belonging to a low grade phosphorite. The main non-metallic minerals in the sample are dolomite and collophanite, with mass fractions of 48.84% and 30.19% respectively, followed by quartz and calcite, and the main metallic mineral is pyrite.

[0052] The apatite is in microcrystalline form, the collophanite is in amorphous structure or microcryptocrystalline structure, the intergrowth relationship is complex, and the collophanite is mainly in the form of fine particles and irregularly embedded, with a particle size mainly less than 75 μm. At the same time, the collophanite is associated with fine-grained dolomite, and most of them are in oolitic structure, so it is difficult to remove the dolomite by flotation.

[0053] ​According to the process mineralogy information of the phosphate ore sample, the main minerals are dolomite, collophanite and quartz, and the densities of the three are relatively close. Dolomite and quartz have strong X-ray penetration and high gray value; and collophanite has strong X-ray attenuation and low gray value. Therefore, the image enhancement strategy should focus on improving the gray scale contrast, and the low gray scale area in the pseudo-color map mapping can be mapped to blue to enhance the visual features of the target mineral. The dual-energy XRT gray scale image of the sample is as shown in Figure 4 .

[0054] As can be seen from Figure 4 , the dual-energy XRT image of the phosphate ore sample clearly shows the different responses of high-energy and low-energy rays to different minerals, and the low-energy highlights the composition difference, and the high-energy ensures the penetration and shape fidelity. Figure 4 (a) and Figure 4 (b) have little difference in visual observation, which is due to the close densities of the main minerals dolomite, collophanite and quartz in the sample, so machine methods are needed for phosphate separation. The combination of the two can provide image data basis for subsequent differential operation, pseudo-color map construction and AI recognition algorithm based on deep learning.

[0055] Based on this, the embodiment introduces a difference fusion strategy in the construction of the pseudo-color map, and fuses the dual-energy features in the model training, so as to fully exploit the density response information under different energy spectrums and improve the intelligent differentiation ability of the algorithm for the phosphate ore area and the non-target mineral area.

[0056] The preprocessing scheme based on the dual-energy XRT gray scale image of the phosphate ore constructed in the embodiment fuses physical modeling and visual mapping, greatly improves the visualization features of the XRT image of the phosphate ore, provides a high-quality data set input basis for the accurate recognition of the deep learning AI algorithm, and has significant engineering practical value and innovation. The gray scale histogram of the dual-energy XRT image of the phosphate ore is as shown in Figure 5 .

[0057] As can be seen from the analysis of Figure 5 , the phosphate ore and waste rock have different responses under low-energy and high-energy, and the histogram distribution intervals are different, which has the potential to enhance the contrast by using the dual-energy ratio or difference. At the same time, the background pixel ratio is large, and noise reduction processing is needed.

[0058] During the dual-energy X-ray transmission imaging process of the phosphate ore, there is often a slight visual angle deviation or mechanical disturbance between the high-energy image and the low-energy image during the imaging process, resulting in a sub-pixel level spatial displacement error between the images. In order to realize accurate fusion and pseudo-color map mapping, the image pair needs to be accurately aligned.

[0059] The enhanced correlation coefficient registration algorithm (ECC) is a registration strategy based on maximizing the enhanced correlation coefficient in the image gray space, which can effectively overcome the micro-displacement error caused by material vibration and belt movement, thereby improving the accuracy and stability of subsequent image fusion and pseudo-color map generation. Given a reference image and a to-be-registered image , the main goal of the ECC algorithm is to transform into ) through an affine transformation , so that the enhanced correlation coefficient between the two images is maximized. The ECC optimization objective function is as follows:

[0060] In the above formula, denotes the image coordinates; denotes the reference image pixel value; denotes the to-be-registered image transformed through the affine transformation parameter ; and and denote the mean values of the two images, respectively, denotes the enhanced correlation coefficient. The ECC registration takes the low-energy image as the reference and performs registration on the high-energy image, and through iterative optimization of the affine transformation parameter , the two images are made most similar in the gray statistical sense. This step is the key basis for subsequent pseudo-color map generation and mineral identification. In this embodiment, the low-energy image is selected as the reference because the low-energy image has weaker penetration ability, higher sensitivity to internal details of the ore, and clearer and more stable texture and edge information, and therefore, as a reference, it is more conducive to the registration of the high-energy image and the subsequent pseudo-color map generation. The high-energy phosphorite image obtained after ECC registration is shown in Figure 6 .

[0061] To further improve the gray contrast between the ore and the background in the registered image and enhance the expression of local detail information, this embodiment performs gray enhancement processing on the registered result image by introducing the contrast limited adaptive histogram equalization (CLAHE) data enhancement method after completing the image registration based on the ECC algorithm.

[0062] Unlike the traditional histogram equalization, which only operates in the full image range, CLAHE divides the image into a plurality of small grids, respectively performs local histogram equalization, and through bilinear interpolation fusion of the edge region, effectively enhances the image details while suppressing the noise caused by excessive enhancement. By setting the contrast enhancement threshold to the maximum value, the gray difference of the ore region edge can be effectively amplified. CLAHE divides the image into 8x8 grid regions by default, and in this embodiment, in order to balance the local details and overall uniformity of the image, the image is divided into 12x12 grid regions. The result of the phosphorite gray image after ECC registration and CLAHE processing is as shown inFigure 7 as shown.

[0063] To fully exploit the response difference characteristics of phosphate ore under high-energy and low-energy X-ray images, a reasonable image preprocessing and fusion strategy is designed in this embodiment to construct a pseudo-color difference map as the input of the AI recognition algorithm, thereby enhancing the density contrast between ore and waste rock and improving the recognition accuracy. The specific processing flow is as follows:

[0064] (1) Image normalization processing: In order to eliminate the influence of image brightness difference on subsequent analysis, the gray values of the high-energy image after ECC registration and CLAHE enhancement and the original low-energy image are uniformly compressed to the [0, 1] interval, enhancing the contrast consistency between different images.

[0065] (2) Difference map generation: Based on the normalization result, the gray difference between the high-energy image and the low-energy image is calculated pixel by pixel to obtain a single-channel difference map. This map can effectively reflect the change in the penetration characteristics of the ore under different energy X-rays, highlighting the difference in gray response between the target ore and waste rock. The specific mathematical formula is shown as follows:

[0066] In the above formula, represents the result of the gray value of the high-energy XRT image at pixel after maximum normalization, represents the result of the gray value of the low-energy XRT image after maximum normalization; are the gray values of the high-energy and low-energy XRT images at pixel , respectively, is a very small constant to prevent taking 0, nonlinear control can be achieved. represents the power difference feature map calculated according to the above normalization result and at pixel .

[0067] (3) Pseudo-color map construction: To further enhance the image level and feature sensitivity, the high-energy image, the low-energy image, and the difference image are fused in a three-channel manner to construct a pseudo-color image. The specific way is: the power difference feature map is input to the R channel, the normalized low-energy image is input to the G channel, and the normalized high-energy image is input to the B channel. The pseudo-color image generated in this way not only visually presents the contrast difference between ore and waste rock, but also provides multi-dimensional input information for subsequent deep learning algorithm training and optimization.

[0068] ​Through the above steps, the neural network can make full use of the complementarity of dual-energy images, capture the intensity gradient information of mineral response in the initial stage of feature extraction, and finally obtain a three-channel pseudo-color map as shown in Figure 8

[0069] In addition, in order to effectively remove background interference, a BGR color mask is constructed and the redundant red background is replaced with pure white, thereby improving the target ore saliency, as shown in Figure 9 Figure 9 Not only does it have good mineral differentiation in vision, but it also provides more discriminative image input for AI recognition algorithms, verifying the effectiveness of the overall preprocessing strategy.

[0070] In this embodiment, dual-energy X-ray image data sets of phosphate ore are collected and processed, and the gray-scale image is converted into a three-channel color image with high differentiation through the preprocessing strategy of fusing ECC and CLAHE and the pseudo-color mapping algorithm. The sufficiency of the training process and the generalization ability of the performance are ensured, and the image resolution and channel standard are unified, which is beneficial to the subsequent input adaptation of YOLO algorithm.

[0071] For the optimization design of the phosphate ore recognition algorithm, this embodiment focuses on the following three deep fusion strategies to achieve high robustness and high-precision target detection effect under complex background and fuzzy boundary conditions. These three methods are closely related to the characteristics of dual-energy XRT images, and combined with the structural flexibility of the YOLO model, the pseudo-color map driven recognition optimization is realized, as shown in Figure 10

[0072] In order to further improve the perception ability of YOLO to the characteristics of phosphate ore and enhance the key information expression effect in the multi-scale feature fusion process, this embodiment introduces a lightweight convolution block attention module (CBAM) as shown in Figure 11 CBAM is composed of channel attention and spatial attention in series: first, generate channel description through global average pooling and maximum pooling, then calculate the channel attention weight through the shared weight full connection layer, and weight the input features in the channel dimension; then, the weighted feature map is averaged and maximized in the spatial dimension, and the spatial attention map is generated after convolution operation, which weights the input features in the spatial position, thereby enhancing the expression ability of the network to key regions and channel features while keeping lightweight.

[0073] Integrating CBAM into the feature fusion network (Neck) part of YOLO based on the path aggregation feature pyramid network (PAN-FPN). Under the premise of keeping the overall structure of the original algorithm framework unchanged, through attention guidance of the channel and spatial dimension of the intermediate feature map, the recognition ability and region selectivity of the neural network to the mineral density response region are effectively improved, and the background noise interference is reduced.​​​

[0074] Specifically, this embodiment introduces a CBAM module in the PAN-FPN feature fusion structure of YOLOv8, and performs attention enhancement on the multi-scale features from the backbone network in the fusion process after upsampling and downsampling. In this way, YOLOv8 can adaptively identify and highlight key regions when interacting with multi-level features, thereby improving the recognition ability of the algorithm for boundary fuzzy ores, density gradient transition regions, and noise background interference.

[0075] In summary, the introduction of CBAM not only improves the recognition accuracy of YOLOv8 in complex working conditions, but also maintains the simplicity of the network structure and the efficiency of deployment, making it suitable for application in industrial online intelligent ore dressing scenarios.

[0076] In YOLO, the default activation function used is the Sigmoid linear unit (SiLU), which performs well in regular tasks. However, in the specific task of phosphor ore pseudo-color image recognition, replacing the activation function is an effective strategy to further improve the algorithm's nonlinear expression ability for small targets.

[0077] This embodiment replaces the SiLU activation function with the HardSwish activation function, which is a computationally efficient and high-performance activation function widely used in lightweight deep learning models. While maintaining the model's nonlinear ability, HardSwish effectively reduces inference delay, making it very suitable for deployment on resource-constrained ore dressing edge platforms. Its mathematical formula is as follows:

[0078] In the above formula, x represents the input of the activation function, and ReLU6() represents the truncated form of the ReLU activation function within the range of 0 to 6.

[0079] This function has the following advantages: first, it is computationally efficient, as it consists entirely of linear and ReLU functions, unlike SiLU which involves exponential calculations, resulting in shorter inference times; second, it has stronger response capabilities to small amplitude perturbations, improving ore boundary detection accuracy; third, it has good deployment compatibility, supporting fast inference and deployment on edge platforms such as Ascend Atlas, with a more concise computational graph; finally, after inputting the pseudo-color image feature channels, HardSwish can enhance the algorithm's nonlinear response ability to weak contrast and strong noise regions. The images of HardSwish and SiLU activation functions are shown in Figure 12 .

[0080] In the YOLOv8 structure optimization process of the present embodiment, HardSwish is preferentially selected as the activation function to construct a lightweight high-performance neural network structure more suitable for the phosphate rock XRT false color image recognition scenario. The replacement mode specifically includes replacing all SiLU activation units in the Backbone and Neck parts one by one, while keeping the detection head (Head) detection structure unchanged, so as to retain the original recognition accuracy structure optimization path. From the curve shape, HardSwish and SiLU are both close to linear in the positive interval, and both show a smooth saturation trend in the negative interval, so the output curve difference between the two is indeed not large. But HardSwish is an approximate piecewise linear function, which is simpler to calculate, faster to infer, and smaller in memory overhead than SiLU function, and is very suitable for lightweight high-performance network deployment scenarios; while maintaining similar nonlinear characteristics, HardSwish can significantly reduce inference time. This is the reason why HardSwish is selected to replace SiLU in the YOLOv8 optimization of the present embodiment.

[0081] To further improve the accuracy and inference efficiency of the phosphate rock false color image recognition AI recognition algorithm, the present embodiment introduces the Optuna hyperparameter automatic search framework based on the YOLO improved structure, and performs Bayesian optimization again for the learning rate, momentum coefficient, weight decay and other key training parameters. Compared with the traditional manual parameter tuning method, Optuna can quickly approach the optimal hyperparameter combination within a limited time, effectively accelerating the model convergence process. This optimization strategy realizes the dual improvement of the phosphate rock recognition algorithm in accuracy and speed under the premise of keeping the inference time basically unchanged, provides more efficient and robust parameter configuration for the deployment of phosphate rock intelligent beneficiation algorithm, and the best result is shown in Table 3.

[0082] Table 3 Optimal hyperparameter configuration for training of phosphate rock XRT false color image

[0083] Compared with the prior art, the present embodiment has the following beneficial effects:

[0084] In the preprocessing stage of the dual-energy XRT image, ECC image registration, CLAHE data enhancement, and false color mapping and denoising techniques are used to enhance the feature expression of the target ore in the image. In the algorithm optimization stage, a lightweight convolution attention module (CBAM) is further introduced, the HardSwish activation function is replaced, and the Optuna hyperparameter optimization framework is called to improve the accuracy and speed of the YOLO-based phosphate rock AI recognition algorithm. Through these optimizations, the recognition accuracy of the model is improved to 95.8%. The final YOLO algorithm network result is shown in Figure 10 .

[0085] The embodiment obtains a YOLO lightweight AI recognition algorithm for phosphate ore by first performing multi-stage optimization preprocessing on the dual-energy XRT image of the phosphate ore and then optimizing the recognition algorithm. The algorithm has good universality and scalability and can be widely applied to the industrial fields of photoelectric intelligent sorting and preselection of phosphate ore and waste.

[0086] As shown in Figure 13 , the specific implementation details of the phosphate ore recognition algorithm implementation scheme of the embodiment are as follows:

[0087] Data acquisition and set division: obtain a dual-energy XRT image dataset of a phosphate ore sample, wherein the image contains a high-energy channel and a low-energy channel. The acquired raw data is reasonably divided to form a training set, a validation set and a test set to ensure the scientificity and reliability of algorithm training and performance evaluation.

[0088] Dual-energy XRT image preprocessing: registration and enhancement processing are performed on the high-energy and low-energy images. First, the ECC registration algorithm is used to ensure the consistency of the high-energy and low-energy images in spatial position and avoid offset errors in subsequent processing. Then, the CLAHE method is used to enhance the contrast of the image and highlight the subtle features of the target ore and waste rock in the gray difference.

[0089] Feature pseudo-color map mapping and denoising: after the preprocessing is completed, the dual-energy image difference is calculated to obtain a single-channel feature map that reflects the density difference of the ore. Further, the high-energy image, the low-energy image and the difference image are combined to construct a three-channel pseudo-color image, and noise suppression processing is performed to improve the discrimination and stability of the model input data.

[0090] Optimized YOLO algorithm: first, the CBAM attention mechanism is added in the Neck feature pyramid structure to enhance the focusing ability of the algorithm on key areas and improve the recognition performance of the ore boundaries and small targets in complex backgrounds. Then, the HardSwish activation function is replaced to improve the nonlinear representation ability of the network and improve the convergence speed. Finally, the Optuna hyperparameter search framework is combined to automatically optimize the learning rate, batch size, optimizer and other training hyperparameters to ensure the global optimal balance of the model in accuracy and speed.

[0091] Algorithm training and verification: the constructed three-channel pseudo-color image is input into the optimized YOLO model for training and reasoning to realize the automatic recognition and classification of phosphate ore and waste rock.

[0092] Result display and analysis: the AI algorithm recognition result is displayed and evaluated through a visualization software, and the rectangular recognition box, class label and confidence information are intuitively presented as shown in Figure 14 to verify the applicability and reliability of the method in the industrial scene.

[0093] The results of the identification of the pseudo-color image of the phosphate ore XRT are shown in FIG. 14. In the figure, "ore" represents the ore target category identified by the model, and "waste" represents the waste target category identified by the model; the numbers above them are the confidence values output by the model, indicating the reliability of the model's judgment of the category of the detection box. The closer the value is to 1.0, the higher the model's confidence that the target belongs to the category. It can be seen that the YOLO optimization algorithm proposed in this embodiment can accurately distinguish between ore and waste, the rectangular box coverage is accurate, and the confidence is mostly above 0.7. At the same time, the background noise is not misdetected, proving that this embodiment has good robustness and practical application value under complex working conditions. In actual industrial applications, the pseudo-color image can be used as an auxiliary feature and combined with the gray-scale image for multi-modal fusion to improve the performance of existing models.

[0094] The electronic device provided in the embodiments of the present application includes a processor and a memory coupled to the processor, the memory being configured to store a computer program, and the processor being configured to execute the computer program stored in the memory to enable the electronic device to perform the method according to any one of the embodiments described above.

[0095] The electronic device can be a desktop computer, a notebook computer, a palm computer, a cloud server, or other computing devices. The electronic device can include, but is not limited to, a processor and a memory.

[0096] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The processor is the control center of the electronic device, and is connected to various parts of the electronic device through various interfaces and lines.

[0097] The memory can be configured to store the computer program, and the processor can be configured to run or execute the computer program stored in the memory, and to call data stored in the memory, to realize various functions of the electronic device.

[0098] The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, application programs required by at least one function, and the like. The data storage area can store data created according to the use of the mobile phone, and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory device.

[0099] The embodiment of the present application further provides a storage medium, which is a computer readable storage medium, and a computer program is stored in the computer readable storage medium. The computer program can implement the steps of the above-mentioned various method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, etc.

[0100] The embodiment of the present application further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions run on a computer, the computer program or instructions make the computer execute the method of any possible implementation manner.

[0101] The above is the preferred embodiment of the present application. It should be noted that, for those skilled in the art, without departing from the principle of the present application, a number of improvements and refinements can be made, which are also considered to be within the protection scope of the present application.

Claims

1. A method for separating phosphate rock, characterized in that, include: In the preprocessing stage, the original high-energy image and the original low-energy image of the raw ore are obtained. The original high-energy image and the original low-energy image are obtained by dual-energy X-ray projection imaging of the raw ore. Using the enhanced correlation coefficient registration algorithm, the original high-energy image is registered with the original low-energy image as a reference to obtain the secondary high-energy image. From the secondary high-energy image and the original low-energy image, a difference image is obtained that characterizes the grayscale difference between the secondary high-energy image and the original low-energy image; and the secondary high-energy image, the original low-energy image and the difference image are fused according to three channels to obtain a pseudo-color image; as well as, In the intelligent recognition stage, the pseudo-color image is used as the input to a deep learning-based target detection model. Through the processing of the target detection model, the sorting results of phosphate ore in the raw ore are obtained.

2. The phosphate rock beneficiation method as described in claim 1, characterized in that, The target detection model adopts the YOLO model, which includes a feature extraction network, a feature fusion network, and a detection head.

3. The phosphate rock beneficiation method as described in claim 2, characterized in that, A lightweight convolutional block attention module is integrated into the path-aggregation-based feature pyramid network of the feature fusion network. The lightweight convolutional block attention module is used to guide the attention of intermediate feature maps in terms of channel and spatial dimensions.

4. The phosphate rock beneficiation method as described in claim 2, characterized in that, In the YOLO model, the convolutional layers use the HardSwish activation function: Where x represents the input to the HardSwish activation function, and ReLU6() represents the truncated form of the ReLU activation function in the range of 0 to 6.

5. The phosphate rock beneficiation method as described in claim 2, characterized in that, The YOLO model uses the Optuna hyperparameter automatic search framework.

6. The phosphate rock beneficiation method as described in claim 1, characterized in that, The preprocessing stage further includes: performing grayscale enhancement processing and image normalization processing on the secondary high-energy image and the original low-energy image.

7. The phosphate rock beneficiation method as described in claim 6, characterized in that, The grayscale enhancement process employs contrast-limited adaptive histogram equalization, which divides the image into 12×12 grid regions.

8. The phosphate rock beneficiation method as described in claim 1, characterized in that, The preprocessing stage also includes: replacing the background color of the pseudo-color image to remove background noise interference.

9. An electronic device, characterized in that, The electronic device includes: a processor, and a memory coupled to the processor. The memory is used to store computer programs; and The processor is configured to execute the computer program stored in the memory, so that the electronic device performs the phosphate rock sorting method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program or instructions that, when executed on a computer, cause the computer to perform the phosphate rock sorting method as described in any one of claims 1-8.

Images