Intelligent sorting system and method for soft and hard gangue in coal gangue

Abstract

The invention provides an intelligent sorting system and method for soft and hard gangue in coal gangue, and belongs to the field of coal gangue sorting. The problems that current coal gangue quality and classification utilization and disposal are low in intelligent degree and highly depend on manpower are solved. The system comprises an image acquisition and processing module which is used for acquiring dual-energy X-ray images of coal gangue and converting the images into data features; the soft and hard coal gangue evaluation label establishing module is used for establishing a coal gangue classification standard and an evaluation label according to the point load test data of the soft and hard coal gangue; and the intelligent identification and classification algorithm module is used for extracting key features from the data features to form feature vectors, fusing the feature vectors and the point load test data to form comprehensive feature vectors, taking the comprehensive feature vectors as input features of a classification algorithm model, taking coal gangue evaluation tags as classification tags, and carrying out classification on the coal gangue evaluation tags. Training the classification algorithm model, and outputting a classification recognition result; a control and sorting execution module; the method is applied to soft and hard coal gangue separation.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent separation of coal gangue, and particularly relates to a system and method for intelligent separation of hard and soft gangue in coal gangue. Background Art

[0002] Coal gangue is a solid waste generated during coal mining and washing. Coal gangue has a high output, large property differences, and significant environmental hazards, and its treatment is a major problem in the national coal industry. However, in fact, coal gangue has great potential utilization value, and it is very necessary to carry out cascade utilization and disposal of coal gangue by classifying and grading its quality.

[0003] Currently, the research on intelligent separation technology mainly focuses on the identification and separation of coal and coal gangue, and there are large technical gaps in the field of fine classification and identification of coal gangue. The traditional classification and separation methods of coal gangue mainly rely on manual labor and simple mechanical equipment, and have problems such as low efficiency, poor separation accuracy, resource waste, and high dependence on manual experience. With the development of artificial intelligence and automation technology, there is an urgent need for an intelligent method for fine classification and identification of coal gangue to improve the separation efficiency and accuracy. Summary of the Invention

[0004] In order to solve the problems of low intelligence level and high dependence on manual labor in the current classification and utilization of coal gangue by quality, the present application proposes a system and method for intelligent separation of hard and soft gangue in coal gangue, which uses advanced artificial intelligence technology and automation equipment to achieve efficient and accurate separation of hard and soft gangue.

[0005] The technical solution adopted by the present application is: an intelligent separation system for hard and soft gangue in coal gangue, including:

[0006] An image acquisition and processing module: used to acquire dual-energy X-ray images of coal gangue and convert the images into data features;

[0007] A hard and soft coal gangue evaluation label establishment module: used to establish a classification standard and evaluation label for coal gangue according to the point load test data of hard and soft coal gangue;

[0008] An intelligent recognition and classification algorithm module: used to extract key features from the data features to form feature vectors, fuse the feature vectors with the point load test data to form a comprehensive feature vector, use the comprehensive feature vector as input features to input into a classification algorithm model, use the coal gangue evaluation label as a classification label, train the classification algorithm model, and output a classification recognition result;

[0009] A control and separation execution module: used to generate a separation instruction according to the classification recognition result and separate the hard and soft coal gangue through a separation execution device.

[0010] Further, the image acquisition and processing module includes a dual-energy X-ray source, a ray signal detector, and an image processing unit. The dual-energy X-ray source is used to generate high- and low-energy rays to perform penetrating scanning on coal gangue to obtain its internal structure information and material properties. The ray signal detector is used to receive and record the X-ray signals passing through the coal gangue to generate a digital image. The image processing unit performs denoising, enhancement, and feature extraction on the acquired image, and obtains the data characteristics of the high-energy area and low-energy area X-ray images through theoretical calculations.

[0011] Further, the hard and soft gangue evaluation label establishment module includes a strength testing device and a label database. The strength testing device is used to test the point load strength of the coal gangue, convert the point load test data of the coal gangue into the uniaxial compressive strength of the rock, and establish a label database based on the uniaxial compressive strength of the coal gangue.

[0012] Further, the intelligent recognition and classification algorithm module includes a feature data extraction unit and a classification model training unit. The feature data extraction unit extracts key features from the image to form a feature vector. The classification model training unit uses a machine learning algorithm, uses a pre-trained deep transfer learning model ResNet, fuses the data characteristics of the dual-energy X-ray image and the point load test data to form a comprehensive feature vector as the input feature, uses the hard and soft coal gangue evaluation label as the classification label, establishes a classification algorithm model for recognition and sorting, and then performs model training through machine learning to output the classification recognition result.

[0013] Further, the classification algorithm model adopts a random forest classification model based on the PSO particle swarm optimization algorithm.

[0014] Further, the control and sorting execution module includes a control system and a sorting execution device. The control system generates a sorting instruction according to the classification recognition result and sends it to the sorting execution device.

[0015] Further, the sorting execution device includes a gas ejection device and a high-pressure air pump. The gas ejection device controls the gas ejection intensity to separate the hard and soft coal gangue.

[0016] Further, the calculation principle of the classification algorithm model for recognition and classification is as follows:

[0017] X d =f R (I m ; θ R );

[0018] X c =[X h ,X d ;

[0019] X f =[Xc , P];

[0020]

[0021] Where: X d is the high-level feature output by the ResNet learning model, f R is the ResNet learning model, I m is the image obtained by the coal gangue through dual-energy X-ray, θ R is the model parameter of the ResNet deep transfer learning, X c is the feature after splicing two features, X h is the feature of the dual-energy X-ray image calculated and extracted, X f is the comprehensive feature vector, P is the point load test data, is the classification result, f s is the random forest model, θ s is the model parameter of the random forest model, y is the true label, L is the loss function, is the hyperparameter obtained after the PSO particle swarm optimization algorithm.

[0022] Furthermore, the calculation formula of the data feature is as follows:

[0023]

[0024]

[0025] T = μρh;

[0026]

[0027] Where: I l0 is the average gray value of the image of the empty conveyor belt before the low-energy X-ray penetrates the coal gangue, I l is the average gray value of the image after the low-energy X-ray penetrates the coal gangue; I h0 is the average gray value of the image of the empty conveyor belt before the high-energy X-ray penetrates the coal gangue, I h is the average gray value of the image after the high-energy X-ray penetrates the coal gangue, μ l is the mass attenuation coefficient of the coal gangue in the low-energy area; μ h is the mass attenuation coefficient of the coal gangue in the high-energy area, h is the effective thickness of the penetrated coal gangue, ρ is the density of the penetrated coal gangue, R is the material property value, and T is the feature data including the thickness and density attributes of the coal gangue.

[0028] An intelligent sorting method for hard and soft gangues in coal gangue, using the intelligent sorting system for hard and soft gangues in coal gangue, includes the following steps:

[0029] Step 1: Collect and load dual-energy X-ray image data and point load test data;

[0030] Step 2: Select the pre-trained deep transfer learning model ResNet, fuse the feature items of the dual-energy X-ray image data and the point load test data to form a comprehensive feature vector, and use this comprehensive feature vector as the input feature;

[0031] Step 3: Establish an evaluation criterion through point load strength testing and calculation, and obtain the classification labels of the classification algorithm model;

[0032] Step 4: Train the classification algorithm model: Use the dual-energy X-ray image data and the point load test data to train the classification algorithm model;

[0033] Step 5: Input the newly collected dual-energy X-ray image data into the trained classification algorithm model, output the classification result, the control system generates a sorting instruction according to the classification result, and the sorting execution device realizes the precise sorting of hard and soft gangue according to the sorting instruction.

[0034] The beneficial effects of this application compared with the prior art are as follows: Starting from the compressive strength gradient difference and utilization methods of coal gangue, this application proposes a method for intelligent identification and sorting of hard and soft gangue in coal gangue by combining dual-energy X-ray technology and machine learning artificial intelligence algorithms. The advantages are:

[0035] (1) High sorting efficiency, automatically distinguish hard and soft coal gangue through intelligent recognition algorithms, reduce manual intervention, and improve sorting speed.

[0036] (2) High sorting accuracy, use dual-energy X-ray technology combined with advanced machine learning algorithms to improve the accuracy of identification and classification.

[0037] (3) High resource utilization rate, accurately separate hard and soft coal gangue, and maximize the utilization efficiency of coal gangue resources.

[0038] (4) High degree of automation, reduce dependence on manual operations, and reduce labor costs and labor intensity.

[0039] (5) Strong adaptability, the system can operate stably under different working conditions, and establish a sample database to train the model for different coal mines / coal preparation plants, which is applicable to various types of coal gangue and mine environments. Brief Description of the Drawings

[0040] The following further describes this application with reference to the drawings:

[0041] Figure 1 It is a schematic diagram of the system structure provided by the embodiment of this application;

[0042] Figure 2A flow chart of the method provided in the embodiment of the present application;

[0043] Figure 3 A three-dimensional schematic diagram of a system provided in an embodiment of the present application;

[0044] In the figure: 1 is the gangue feeding port, 2 is the belt, 3 is the point load tester, 4 is the dual-energy X-ray source, 5 is the ray signal detector, 6 is the junction box, 7 is the computer workstation, 8 is the gas pushing device, 9 is the first gangue bin, 10 is the second gangue bin, and 11 is the high-pressure air pump. DETAILED DESCRIPTION

[0045] like Figures 1 to 3 As shown, the present application provides an intelligent sorting system for soft and hard gangue in coal gangue, establishes a coal gangue quality classification system based on compressive strength differences; establishes a classification algorithm model by combining dual-energy X-ray technology with machine learning algorithms; applies artificial intelligence technology and automation equipment to the field of coal gangue classification and sorting, solving the problems existing in traditional manual sorting.

[0046] like Figure 1 As shown, the sorting system provided in the embodiment of the present application includes an image acquisition and processing module, a soft and hard coal gangue evaluation label establishment module, an intelligent recognition and classification algorithm module, and a control and sorting execution module, wherein the image acquisition and processing module includes hardware devices such as a dual-energy X-ray source and a ray signal detector and software modules such as an image processing unit. The dual-energy X-ray source is used to generate high and low energy rays to perform penetrating scanning on the coal gangue to obtain its internal structure information and material properties; the ray signal detector is used to receive and record the X-ray signal passing through the coal gangue to generate a digital image; the image processing unit performs denoising, enhancement and feature extraction on the collected image, and obtains I through theoretical calculation. l ,I h , R, T l 、T h The above dual-energy X-ray image features serve as important input features for the subsequent classification algorithm model.

[0047] The calculation formula of data features is as follows:

[0048]

[0049]

[0050] T = μρh;

[0051]

[0052] Where: I l0 is the grayscale mean of the empty conveyor belt image in the low-energy region where X-rays do not transmit coal gangue, Il is the average gray value of the image after the X-ray in the low-energy region penetrates the coal gangue; I h0 is the average gray value of the image of the empty conveyor belt before the X-ray in the high-energy region penetrates the coal gangue, I h is the average gray value of the image after the X-ray in the high-energy region penetrates the coal gangue. Substitute I l0 and I l and I h0 and I h into the Lambert-Beer formula for these two groups of quantities respectively to obtain μ l is the mass attenuation coefficient of the coal gangue in the low-energy region; μ h is the mass attenuation coefficient of the coal gangue in the high-energy region, h is the effective thickness of the penetrated coal gangue, ρ is the density of the penetrated coal gangue, R is the value of the material property, T is the characteristic data including the thickness and density attributes of the coal gangue, and the T value retains the influence of the thickness h and density ρ of the coal gangue. Taking the T value as the classification feature can take into account the influence of the thickness and density of the coal gangue and reduce the influence brought by the thickness effect.

[0053] The evaluation label establishment module for hard and soft coal gangue includes hardware devices such as a strength testing device and software modules such as a label database for hard and soft coal gangue. Among them, the strength testing device is used to conduct strength tests on coal gangue as an important classification basis for hard and soft coal gangue. By measuring the point load strength of coal gangue samples in coal mines / coal preparation plants and performing the conversion of the uniaxial compressive strength of rock, the classification standard for hard and soft coal gangue is established with reference to GB / T50218-2014 "Standard for Classification of Engineering Rock Masses". By statistically analyzing the sample data and establishing a label database for storing the characteristic data of different types of coal gangue, it serves as a reference standard for training and identifying hard and soft coal gangue.

[0054] The process of calculating and converting the uniaxial compressive strength of rock is as follows:

[0055]

[0056] I s(50) = FI s ;

[0057]

[0058] In the formula: I s is the uncorrected point load strength index, with the unit of MPa; P is the failure load, with the unit of N; D e is the equivalent core diameter, with the unit of mm; w is the width of the minimum cross-section passing through the two loading points, with the unit of mm; D is the loading point spacing, with the unit of mm; F is the correction coefficient; m is the correction exponent, determined by the empirical values of the same type of rock, and generally can be taken as 0.45; Rc is the uniaxial compressive strength of the rock, and the measured rock point load strength index Is(50) The conversion value, in MPa.

[0059] The intelligent recognition and classification algorithm module includes a feature data extraction unit and a classification model training unit. The feature data extraction unit extracts key features from the digital image to form a feature vector. The classification model training unit uses a machine learning algorithm and the pre-trained deep transfer learning model ResNet to use the features I l 、I h 、R、T l 、T h of the dual-energy X-ray image after preprocessing and the feature vector of the point load test data fused to form a comprehensive feature vector as the input feature, and uses the hard and soft coal gangue evaluation label Rc as the classification label to establish a classification algorithm model for identification and sorting, and then conducts model training through machine learning to output the classification recognition result.

[0060] The classification algorithm model is a random forest classification model based on the PSO particle swarm optimization algorithm, trained by combining dual-energy X-ray image data and point load test data. The trained model can be used to analyze real-time images to identify and classify hard and soft coal gangue.

[0061] The principle of the classification algorithm model for identification and classification is as follows:

[0062] X d =f R (I m ;θ R );

[0063] X c =[X h ,X d ;

[0064] X f =[X c ,P];

[0065]

[0066] In the formula: X d is the high-level feature of the image extracted by the ResNet learning model through the convolutional layer when processing the picture, including the edges, textures of the picture, and the shapes and structures of objects. The purpose of extracting these high-level features is to more accurately identify and classify hard and soft coal gangue. f R is the ResNet learning model, I m is the image of the coal gangue obtained by dual-energy X-ray, θ R is the model parameter of the ResNet deep transfer learning, X c is the feature after splicing two features, X hAt the beginning, the image processing unit denoises, enhances, and extracts features from the acquired digital image. By calculating the extracted I l 、I h 、R、T l 、T h These dual-energy X-ray image features, X f is the comprehensive feature vector, P is the point load test data, is the classification result, f s is the random forest model, θ s is the model parameter of the random forest model, y is the true label, L is the loss function, is the hyperparameter obtained after the PSO particle swarm optimization algorithm.

[0067] The control and sorting execution module includes a control system and a sorting execution device. The control system generates a sorting instruction according to the classification and recognition result and sends it to the sorting execution device. The sorting execution device accurately separates the identified hard and soft coal gangue.

[0068] As Figure 2 shown, the embodiment of the present application also proposes an intelligent sorting method for hard and soft gangue in coal gangue. Based on the above sorting system, the main implementation steps are as follows:

[0069] Step 1: Collect and load dual-energy X-ray image data and point load test data;

[0070] Step 2: Select the pre-trained deep transfer learning model ResNet, fuse the feature items of the dual-energy X-ray image data and the point load test data to form a comprehensive feature vector, and use this comprehensive feature vector as the input feature;

[0071] Step 3: Establish an evaluation criterion through point load strength test and calculation, and obtain the classification label of the classification algorithm model;

[0072] Step 4: Train the classification algorithm model: Use the dual-energy X-ray image data and the point load test data to train the classification algorithm model;

[0073] Step 5: Input the newly collected dual-energy X-ray image data into the trained classification algorithm model, output the classification result, the control system generates a sorting instruction according to the classification result, and the sorting execution device realizes the accurate sorting of hard and soft coal gangue according to the sorting instruction.

[0074] As Figure 3As shown, the present embodiment specifically provides a structure of a realizable sorting system, including a gangue conveying device using a belt 2 for conveying, a dual-energy X-ray source 4 is installed above the belt 2 of the gangue conveying device, and a radiation signal detector 5 is arranged below the belt 2 at a position corresponding to the dual-energy X-ray source 4, a sorting execution device and a first gangue bin 9 and a second gangue bin 10 are arranged at the discharge port of the gangue conveying device, the sorting execution device includes a high-pressure air pump 11 and a gas pushing device 8, the gas pushing device 8 is located at the discharge port of the gangue conveying device, and the gas pushing device 8 is connected to the high-pressure air pump 11; a computer workstation 7 and a point load tester 3 are also arranged next to the gangue conveying device, and the computer workstation 7 is respectively connected to the dual-energy X-ray source 4, the radiation signal detector 5, the point load tester 3 and the gas pushing device 8 through a junction box 6. When in use, the system is set at the gangue discharge port of the gangue sorting device. The gangue coming out of the gangue sorting device directly falls into the gangue inlet 1 of the gangue conveying device. After being transported by the belt 2, X-ray images of the gangue in batches are collected in real time. The gangue is classified according to the trained classification algorithm model. Finally, the soft and hard gangue are blown into the first gangue bin 9 and the second gangue bin 10 respectively according to the gas pushing device 8, thereby realizing the accurate distinction between soft and hard gangue.

[0075] The high-pressure air pump 11 and the gas push device 8, according to the instructions of the control system, accurately separate the identified soft and hard coal gangue through the difference in gas push strength, and drop them into the corresponding coal gangue bin. For example, for soft coal gangue with a classification label of 0, the gas push strength is controlled to be weak (the specific gas pressure can be given according to the measured point load test data of soft and hard coal gangue), and it is pushed into the coal gangue bin of about 1 meter. For hard coal gangue with a classification label of 1, the gas push strength is controlled to be strong, and it is pushed into the coal gangue bin of about 5 meters, thereby realizing the accurate sorting of soft and hard coal gangue.

[0076] This application also has the following advantages or innovations:

[0077] (1) Based on dual-energy X-ray technology, combined with density indicators and machine learning algorithms, it is applied to the classification and sorting of coal gangue, achieving high-precision identification and sorting of soft and hard coal gangue.

[0078] (2) Based on the differences in the compressive strength of coal gangue, a reliable coal gangue classification standard and evaluation label system is established based on point load strength testing.

[0079] (3) Multi-source data fusion innovation - Previous sorting methods only relied on a single type of data and could not comprehensively and accurately distinguish between hard and soft coal gangue. This application realizes multi-dimensional analysis of coal gangue characteristics by fusing two different types of data, namely dual-energy X-ray image data and point load test data, significantly improving the accuracy and reliability of sorting. This multi-source data fusion method provides a new technical idea for the field of coal gangue sorting and effectively solves the limitations of traditional methods in the face of complex coal gangue characteristics.

[0080] (4) Precision innovation of the sorting execution device - Highlight the innovation point of accurately separating hard and soft coal gangue through the difference in gas ejection intensity in the control and sorting execution module. This module can not only accurately classify hard and soft coal gangue according to the recognition result, but also accurately push different hardness coal gangue by precisely controlling the gas ejection intensity of the high-pressure air pump and the gas ejection device. This gas ejection mechanism based on different intensities ensures that hard and soft coal gangue can be accurately separated and fall into the corresponding coal gangue bins, effectively avoiding the problem of coal gangue misloading caused by inaccurate sorting execution and improving the purity and quality of sorting.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent sorting system for soft and hard gangue in coal gangue, characterized by: include: Image acquisition and processing module: used to acquire dual-energy X-ray images of coal gangue and convert the images into data features; Soft and hard coal gangue evaluation label establishment module: used to establish coal gangue classification standards and evaluation labels based on the point load test data of soft and hard coal gangue; Intelligent recognition and classification algorithm module: used to extract key features from data features to form feature vectors, and fuse the feature vectors with point load test data to form comprehensive feature vectors, input the comprehensive feature vectors as input features into the classification algorithm model, use the gangue evaluation labels as classification labels, train the classification algorithm model, and output classification recognition results; control and sorting execution module: used to generate sorting instructions based on the classification recognition results, and separate soft and hard gangue through the sorting execution device.

2. The intelligent separation system for soft and hard gangue in coal gangue according to claim 1 is characterized by: The image acquisition and processing module includes a dual-energy X-ray source, a radiation signal detector and an image processing unit. The dual-energy X-ray source is used to generate high- and low-energy rays to perform penetrating scanning on coal gangue to obtain its internal structure information and material properties. The X-ray signal detector is used to receive and record X-ray signals passing through coal gangue and generate digital images; the image processing unit denoises, enhances and extracts features from the collected images, and obtains the data features of X-ray images in high-energy and low-energy areas through theoretical calculations.

3. The intelligent separation system for soft and hard gangue in coal gangue according to claim 2 is characterized by: The soft and hard gangue evaluation label establishment module includes a strength testing device and a label database. The strength testing device is used to test the point load strength of the gangue and convert the point load test data of the gangue into the uniaxial compressive strength of the rock. The label database is established according to the uniaxial compressive strength of the gangue.

4. The intelligent sorting system for soft and hard gangue in coal gangue according to claim 3 is characterized by: The intelligent recognition and classification algorithm module includes a feature data extraction unit and a classification model training unit. The feature data extraction unit extracts key features from the image to form a feature vector. The classification model training unit adopts a machine learning algorithm and uses the pre-trained deep transfer learning model ResNet to integrate the data features of the dual-energy X-ray image and the point load test data to form a comprehensive feature vector as the input feature. The soft and hard coal gangue evaluation labels are used as classification labels, and a classification algorithm model is established for recognition and sorting. The model is then trained through machine learning to output the classification recognition results.

5. The intelligent sorting system for soft and hard gangue in coal gangue according to claim 4 is characterized by: The classification algorithm model adopts a random forest classification model based on the PSO particle swarm optimization algorithm.

6. The intelligent sorting system for soft and hard gangue in coal gangue according to claim 1 is characterized by: The control and sorting execution module includes a control system and a sorting execution device. The control system generates a sorting instruction according to the classification and recognition result and sends it to the sorting execution device.

7. The intelligent sorting system for soft and hard gangue in coal gangue according to claim 6 is characterized by: The sorting execution device includes a gas pushing device and a high-pressure air pump. The gas pushing device controls the gas pushing intensity to separate the soft and hard coal gangue.

8. The intelligent sorting system for soft and hard gangue in coal gangue according to claim 4 is characterized by: The calculation principle of the classification algorithm model for identification and classification is as follows: X d =f R (I m ;θ R ); X c =[X h ,X d ]; X f =[X c ,P]; Where: X d The high-level features output by the ResNet learning model, f R Learning model for ResNet, I m is the image of coal gangue obtained by dual-energy X-ray, θ R is the model parameter of ResNet deep transfer learning, X c X is the feature after concatenating two features. h To calculate the extracted dual-energy X-ray image features, X f is the comprehensive characteristic vector, P is the point load test data, is the classification result, f s is the random forest model, θ s is the model parameter of the random forest model, y is the true label, L is the loss function, is the hyperparameter obtained after PSO particle swarm optimization algorithm.

9. The intelligent separation system for soft and hard gangue in coal gangue according to claim 4 is characterized by: The calculation formula of data features is as follows: T = μρh; Where: I l0 is the grayscale mean of the empty conveyor belt image in the low-energy region where X-rays do not transmit coal gangue, I l I is the grayscale mean of the image after low-energy X-ray transmission through coal gangue; h0 is the grayscale mean of the image of the empty conveyor belt in the high-energy region where X-rays do not transmit the gangue, I h is the grayscale mean of the image after high-energy X-ray transmission through coal gangue, μ l is the mass attenuation coefficient of coal gangue in low energy zone; μ h is the mass attenuation coefficient of the gangue in the high energy zone, h is the effective thickness of the transmitted gangue, ρ is the density of the transmitted gangue, R is the material property value, and T is the characteristic data including the thickness and density properties of the gangue.

10. A method for intelligently separating soft and hard gangue from coal gangue, characterized in that: The intelligent separation system for soft and hard gangue in coal gangue according to any one of claims 1 to 9 comprises the following steps: Step 1: Collect and load dual-energy X-ray image data and point load test data; Step 2: Select the pre-trained deep transfer learning model ResNet, fuse the feature items of dual-energy X-ray image data and point load test data to form a comprehensive feature vector, and use the comprehensive feature vector as the input feature; Step 3: Establish evaluation criteria through point load strength testing and calculation to obtain classification labels for the classification algorithm model; Step 4: Training the classification algorithm model: using dual-energy X-ray image data and point load test data to train the classification algorithm model; Step 5: Input the newly acquired dual-energy X-ray image data into the trained classification algorithm model, output the classification results, the control system generates sorting instructions according to the classification results, and the sorting execution device realizes the accurate sorting of soft and hard gangue according to the sorting instructions.

Images