Coal gangue identification method and system based on thermal imaging and multivariate spectrum

Abstract

The present disclosure provides a coal gangue identification method and system based on thermal imaging and multivariate spectroscopy, which relates to the technical field of coal gangue qualitative and quantitative identification, including obtaining infrared radiation data of coal gangue to be identified and spectral reflectance data of multiple bands; preprocessing the infrared radiation data and spectral reflectance data; extracting edge morphological features and temperature features from the infrared radiation data, and extracting spectral reflectance features in different bands from the spectral reflectance data; fusing temperature features, edge morphological features and spectral features through multimodal feature fusion; inputting the fused features into a coal gangue identification model to obtain classification results of coal and gangue. The present disclosure utilizes the differences between coal and gangue in spectral characteristics and temperature distribution to construct more comprehensive and accurate features, improve the accuracy and stability of identification, and utilizes the complementarity of multi-source information to greatly improve the accuracy and reliability of coal gangue identification.

Description

Technical Field

[0001] The present disclosure relates to the technical field of qualitative and quantitative identification of coal gangue, and in particular to a coal gangue identification method and system based on the combination of thermal imaging and multivariate spectroscopy. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] When mining thick coal seams, the top coal caving method is often used for mining, especially for gently inclined and steeply inclined extra-thick coal seams. This method arranges a long wall working face with a mining height of 2-3 meters along the bottom of the thick coal seam, uses a comprehensive mechanized coal mining process for mining, and uses mining pressure or artificial loosening to break the coal seam above the support into loose bodies, which are then released from the coal caving window behind or above the support to the scraper conveyor. This method can greatly increase the thickness of one-time mining, simplify the layout of the tunnel, reduce the workload of excavation, improve the efficiency of coal mining, and reduce the production cost per ton of coal.

[0004] However, when dropping coal fragments through the coal discharge window, the staff needs to judge the coal and gangue on the scraper conveyor and close the coal discharge window in time to avoid the mixing of gangue fragments above after the coal is dropped. Otherwise, the mixed gangue will reduce the coal recovery rate and is not conducive to the coal preparation work of the coal washing plant. The environment of the coal working face has the characteristics of low brightness, small space, high dust and high noise. The harsh environment of the working face greatly affects the correct judgment of the staff and is not conducive to the personal safety of the staff.

[0005] Infrared imaging technology can capture the thermal radiation on the surface of an object, and multivariate spectroscopy technology can collect multi-band spectral data of coal gangue samples. Both technologies can realize non-contact detection of rock samples, and have the characteristics of rapid and large-area monitoring. Therefore, these two technologies have been widely used in geological detection in coal mining and tunnel engineering, but infrared imaging technology and multivariate spectroscopy technology have problems such as low accuracy and poor environmental adaptability when used alone, and the integrated application of the two is not yet mature. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a coal gangue identification method and system based on the combination of thermal imaging and multivariate spectroscopy, which utilizes the complementarity of thermal imaging technology and multivariate spectroscopy and realizes high-precision and real-time identification of coal and gangue through multi-source information fusion, which is of great significance for improving the coal recovery rate of top coal caving.

[0007] According to some embodiments, the present disclosure adopts the following technical solutions:

[0008] The coal gangue identification method based on thermal imaging and multivariate spectroscopy includes:

[0009] Obtain infrared radiation data of the coal gangue to be identified and spectral reflectance data of multiple bands;

[0010] Preprocess infrared radiation data and spectral reflectance data;

[0011] Extract edge morphology features and temperature features from the infrared radiation data, and extract spectral reflectance features in different bands from the spectral reflectance data;

[0012] Through multi-modal feature fusion, the temperature feature, edge morphology feature and spectral reflectance feature are fused to obtain the fusion feature;

[0013] The fusion features are input into the coal gangue recognition model to obtain the automatic classification results of coal and gangue.

[0014] According to some embodiments, the present disclosure adopts the following technical solutions:

[0015] The coal gangue identification system based on thermal imaging and multivariate spectroscopy includes:

[0016] A data acquisition module is used to acquire infrared radiation data of the coal gangue to be identified and spectral reflectance data of multiple bands;

[0017] A data preprocessing module, used for preprocessing infrared radiation data and spectral reflectance data;

[0018] A feature extraction module, used to extract edge morphological features and temperature features from the infrared radiation data, and to extract spectral reflectance features in different bands from the spectral reflectance data;

[0019] A feature fusion module is used to fuse temperature features, edge morphology features, and spectral reflectance features through multi-modal feature fusion to obtain fusion features;

[0020] The classification module is used to input the fusion features into the coal gangue recognition model to obtain the automatic classification results of coal and gangue.

[0021] According to some embodiments, the present disclosure adopts the following technical solutions:

[0022] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the coal gangue identification method based on the combination of thermal imaging and multivariate spectrum is implemented.

[0023] According to some embodiments, the present disclosure adopts the following technical solutions:

[0024] A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy is implemented.

[0025] According to some embodiments, the present disclosure adopts the following technical solutions:

[0026] An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device implements the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The disclosed coal gangue identification method based on thermal imaging and multivariate spectroscopy can comprehensively utilize the differences in spectral characteristics and temperature distribution between coal and gangue by integrating thermal imaging and multivariate spectroscopy technology to construct more comprehensive and accurate identification features. The comprehensive features are trained and classified using advanced machine learning or deep learning algorithms, which can automatically learn the complex feature patterns of coal and gangue, further improving the accuracy and stability of identification. The complementarity of this multi-source information greatly improves the accuracy and reliability of coal gangue identification.

[0029] The disclosed coal gangue identification method based on thermal imaging and multivariate spectroscopy can adapt to the complex environment of underground top coal caving working face, which is complex and changeable, including illumination changes, dust interference, noise influence, etc. The image is processed by denoising and contrast enhancement in the preprocessing step, which effectively reduces the interference of environmental factors and enables the system to work stably in various complex environments.

[0030] The disclosed coal gangue identification method based on thermal imaging and multivariate spectroscopy can identify coal and gangue in real time, and immediately feedback the identification results of coal and gangue. According to the coal gangue identification results, the system can automatically adjust the mining parameters of the top coal caving equipment, such as coal mining height, propulsion speed, etc., which not only reduces the mixing of gangue, but also reduces the downtime of the coal mining system, improves the quality of coal and ensures mining efficiency. When the system recognizes that a large amount of gangue has fallen in, it can also issue an alarm in time to remind the staff to take corresponding measures to avoid the occurrence of safety accidents. According to the coal gangue identification results, the staff can make more scientific and reasonable mining decisions to ensure the safety and controllability of the mining process.

[0031] The coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy disclosed in the present invention has shown significant beneficial effects in many aspects such as identification accuracy, environmental adaptability, mining efficiency, coal quality, and operation safety, and has important application value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0033] Figure 1 It is a flow chart of the coal gangue identification method of top coal caving working face according to the embodiment of the present disclosure;

[0034] Figure 2 is a workflow diagram of the coal gangue identification model of the embodiment of the present disclosure;

[0035] Figure 3 It is a schematic diagram of a coal gangue collecting device according to an embodiment of the present disclosure.

[0036] Among them: 1. Thermal imaging camera; 2. Multi-spectral sensor. DETAILED DESCRIPTION

[0037] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0038] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0039] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0040] Example 1

[0041] In one embodiment of the present disclosure, a coal gangue identification method based on thermal imaging and multivariate spectroscopy is provided, comprising:

[0042] Step 1: Obtain infrared radiation data of the coal gangue to be identified and spectral reflectance data of multiple bands;

[0043] Step 2: Preprocess the infrared radiation data and spectral reflectance data;

[0044] Step 3: extracting edge morphological features and temperature features from the infrared radiation data, and extracting spectral reflectance features in different bands from the spectral reflectance data;

[0045] Step 4: Fuse the temperature features, edge morphology features and spectral reflectance features to obtain fusion features;

[0046] Step 5: Input the fusion features into the coal gangue recognition model to obtain the automatic classification results of coal and gangue.

[0047] As an embodiment, the specific implementation process of a coal gangue identification method based on thermal imaging and multivariate spectroscopy disclosed in the present invention is as follows:

[0048] Step 1: Obtain infrared radiation data of the coal gangue to be identified and spectral reflectance data of multiple bands;

[0049] Specifically, conduct preliminary on-site investigation to fully understand the caving conditions of coal and gangue fragments at the "coal caving window" and collect coal and gangue samples at the top coal caving working face. Figure 3 As shown, a thermal imaging camera 1 and a multi-spectral sensor 2 are installed on the hydraulic support to ensure that the equipment is firmly installed to avoid data collection being affected by mechanical vibration. The infrared camera is used to capture the infrared radiation data of coal and gangue respectively, and the multi-spectral sensor is used to collect the spectral reflectance data of coal and gangue in multiple bands;

[0050] Among them, the "coal discharge window" is the area formed by the contraction of the baffle behind the top coal discharge support, and the top coal and gangue fall onto the scraper conveyor from this area.

[0051] Step 2: Preprocess the infrared radiation data and spectral reflectance data;

[0052] Specifically, the thermal imaging information is subjected to noise removal processing, and the multivariate spectral information is subjected to normalization processing.

[0053] Step 3: extracting edge morphological features and temperature features from the infrared radiation data, extracting spectral reflectances in different bands from the spectral reflectance data, and constructing multi-band spectral features;

[0054] Specifically, the eccentricity, circularity and average temperature are extracted from the preprocessed thermal imaging data, and the multivariate spectral peak features of each band are extracted from the preprocessed multivariate spectral data;

[0055] Among them, 1) obtaining edge morphological features includes:

[0056] The thermal image is converted from color to grayscale using the following formula:

[0057]

[0058] Where: w is the weight of the red, green and blue color channels, usually w r Take 0.299, w g Take 0.587, w b Take 0.114; M It is a matrix of different color channels of red, green and blue.

[0059] The Prewitt edge detection algorithm is used to identify the contours of objects in grayscale images. The algorithm includes two kernel functions, one for the horizontal direction x and the other for the vertical direction y:

[0060]

[0061] After preprocessing, the image I Convolution is performed to obtain the horizontal and vertical gradients. I x and I y ：

[0062]

[0063] The gradient magnitude and direction of each pixel can be obtained by the following formula:

[0064]

[0065] in, I x and I y are the gradients in the horizontal and vertical directions respectively; G and are the gradient magnitude and direction of each pixel respectively.

[0066] The final edge is determined by double threshold processing. First, a high threshold is used to determine the strong edge, and then a low threshold is used to determine the possible weak edge (the high threshold takes the maximum value of the gradient amplitude G max The low threshold is 60% of the high threshold, and the low threshold is 40% of the high threshold). Then the object edge is determined by the hysteresis threshold method. For each weak edge pixel, if its gradient amplitude is greater than the low threshold and the gradient amplitude of its adjacent strong edge pixel is greater than the high threshold, the weak edge pixel is retained, and the strong edge and the retained weak edge are connected to form a complete edge.

[0067] After edge detection, the contour information of the object can be obtained, including the area, major semi-axis length, minor semi-axis length, etc. On this basis, the eccentricity and circularity of the object can be calculated to describe the edge morphological characteristics of the object.

[0068] Eccentricity:

[0069]

[0070] Where: E is the eccentricity, a measure of the flatness of an object’s shape; a is the length of the major semiaxis; b is the length of the minor semiaxis.

[0071] Roundness:

[0072]

[0073] Where: C is the circularity, ( x i , y i ) is the coordinate of the i-th edge pixel, and N is the total number of edge pixels.

[0074] 2) Obtaining average temperature features includes:

[0075] The temperature information of the surface of coal or gangue can be directly obtained from the infrared thermal image obtained by the infrared thermal imager. Each pixel in the infrared thermal image has a corresponding temperature. In order to avoid the influence of the surrounding environment on the thermal imaging, a median filter can be used to denoise the temperature information, and then the average temperature is calculated within the object contour.

[0076] The average temperature characteristic can be obtained by the following formula:

[0077]

[0078] Where: T is the average temperature; T i Pixel i The temperature value at n is the total number of pixels within the object outline.

[0079] 3) Obtaining multivariate spectral reflectance features includes:

[0080] The multivariate spectral reflectance data of each band are normalized by the following formula:

[0081]

[0082] Where: λ i is the i-th band, R norm ( λ i ) is the band λi Department Multivariate spectral data of R ( λ i )for λ i Department The original data; R max for λ i Department The maximum value of the data; R min for λ i Department The minimum value of the data.

[0083] After normalization, the multi-band spectral feature vector can be constructed:

[0084]

[0085] Step 4: Through multimodal feature fusion, the temperature feature, edge morphology feature and spectral reflectance feature are fused to obtain the fusion feature;

[0086] Specifically, the coal gangue identification feature vector is formed by multi-feature fusion M , the temperature features, edge morphology features and spectral reflectance are processed jointly:

[0087]

[0088] Step 5: Perform infrared and multivariate spectrum detection on multiple coal gangue samples, obtain the fusion features of each sample, and mark the sample type, build a coal gangue recognition module training set, obtain the fusion features of unknown samples, and automatically identify them through the coal gangue recognition model;

[0089] Specifically, the eccentricity E Take the following example to get the eccentricity of multiple samples: E , and marked the sample as coal or gangue, and the k-nearest neighbor algorithm (k-NN) was used to compare the distance between the eccentricity of the unknown sample and the eccentricity of the known sample to obtain the probability that the unknown sample is coal. PE c The probability that the sum is gangue PE g Similarly, the circularity of the unknown sample can be calculated by inputting C , average temperature T , reflectivity in different bands R norm (λ i )Calculate the distance with the corresponding features of the known samples and obtain the probability that the sample is coal PC c , PT c , PR norm (λ 1 ) c … PR norm (λ m ) c The probability that the sum is gangue PC g PT g , PR norm (λ 1 ) g … PR norm (λ m ) g .

[0090] The probability that the unknown sample is coal can then be calculated using Bayesian decision theory:

[0091]

[0092] The probability that the unknown sample is gangue:

[0093]

[0094] By inputting the fusion features of the unknown sample, the probability that the sample is coal can be obtained. P c and the probability of gangue P g By comparing the sizes of the two, we can determine whether the unknown sample is gangue or coal.

[0095] As an embodiment, the actual working process of the method disclosed herein is as follows:

[0096] Install thermal imaging cameras and multi-spectral sensors at the "coal placement window" of the hydraulic support to ensure that the equipment is firmly installed to avoid data collection affected by mechanical vibration;

[0097] After the coal caving work begins, the system is turned on to collect thermal imaging and spectral data during the top coal caving process, and the real-time collected thermal imaging data and multivariate spectral data are input into the trained coal gangue recognition model for coal gangue recognition;

[0098] Taking one minute as a time period, according to the gangue identification results, calculate the gangue content in the coal on the scraper conveyor in each time period. When the gangue content reaches 3%, narrow the "coal discharge window" and reduce the coal discharge rate. When the gangue content reaches 5%, close the "coal discharge window" and issue an early warning to the staff.

[0099] Conduct system tests during actual top coal caving to evaluate recognition accuracy and real-time performance;

[0100] Regularly perform maintenance and care on thermal imaging cameras and multivariate spectrometers to ensure their long-term stable operation.

[0101] Furthermore, an intuitive user interface is provided to allow staff to monitor the gangue identification process, adjust system parameters, view identification results, and perform manual intervention when necessary; and store the results.

[0102] Example 2

[0103] In one embodiment of the present disclosure, a coal gangue identification system based on thermal imaging and multivariate spectroscopy is provided, comprising:

[0104] A data acquisition module is used to acquire infrared radiation data of the coal gangue to be identified and spectral reflectance data of multiple bands;

[0105] A data preprocessing module, used for preprocessing infrared radiation data and spectral reflectance data;

[0106] A feature extraction module, used to extract edge morphological features and temperature features from the infrared radiation data, and to extract spectral reflectance features in different bands from the spectral reflectance data;

[0107] A fusion module is used to fuse temperature features, edge morphology features and spectral features through multi-modal feature fusion to obtain fusion features;

[0108] The classification module is used to input the fusion features into the coal gangue recognition model to obtain the automatic classification results of coal and gangue.

[0109] It also includes a coal discharge control module, which is used to calculate the gangue content in the coal within a certain period of time according to the coal gangue identification module, and to reduce or close the "coal discharge window" when the gangue content reaches a certain value;

[0110] User interface, which provides an intuitive user interface that allows personnel to monitor the gangue identification process, adjust system parameters, view identification results, and perform manual intervention when necessary;

[0111] System integration and communication system, used to integrate various modules into a complete system and ensure effective communication and data synchronization between modules;

[0112] Data storage and analysis system, used to store historical data and conduct in-depth data analysis;

[0113] System monitoring and maintenance system is used to ensure stable operation and timely maintenance of the system.

[0114] Example 3

[0115] In one embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy is implemented.

[0116] Example 4

[0117] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy is implemented.

[0118] Example 5

[0119] In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy.

[0120] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0122] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A coal gangue identification method based on thermal imaging and multivariate spectroscopy is characterized by: include: Obtain infrared radiation data of the coal gangue to be identified and spectral reflectance data of multiple bands; Preprocess infrared radiation data and spectral reflectance data; Extract edge morphology features and temperature features from the infrared radiation data, and extract spectral reflectance features in different bands from the spectral reflectance data; Through multimodal feature fusion, the temperature feature, edge morphology feature and spectral feature are fused to obtain the fusion feature; Inputting the fusion features into a coal gangue recognition model to obtain automatic classification results of coal and gangue; It includes: performing infrared and multivariate spectrum detection on multiple coal gangue samples, obtaining the fusion features of each sample, and marking the sample type, constructing a coal gangue recognition module training set, obtaining the fusion features of unknown samples, and automatically identifying them through the coal gangue recognition model; Specifically, obtain the eccentricity of multiple samples E , and mark the sample as coal or gangue, and use the k nearest neighbor algorithm to compare the distance between the eccentricity of the unknown sample and the eccentricity of the known sample to obtain the probability that the unknown sample is coal PE c The probability that the sum is gangue PE g ; By entering the circularity of the unknown sample C , average temperature T , reflectivity in different bands R norm (λ i ) Calculate the distance with the corresponding features of the known samples and obtain the probability that the sample is coal PC c , PT c , PR norm (λ 1 ) c … PR norm (λ m ) c The probability that the sum is gangue PC g PT g , PR norm (λ 1 ) g …PR norm (λ m ) g ; Then, the probability that the unknown sample is coal is calculated by Bayesian decision theory: The probability that the unknown sample is gangue: By inputting the fusion features of the unknown sample, the probability that the sample is coal is obtained P c and the probability of gangue P g By comparing the sizes of the two, it can be determined whether the unknown sample is gangue or coal.

2. The coal gangue identification method based on thermal imaging and multivariate spectroscopy as claimed in claim 1, characterized in that: The preprocessing process includes: compensating and correcting the acquired infrared radiation data and spectral reflection data, standardizing the infrared radiation data, and suppressing noise on the spectral reflection data.

3. The coal gangue identification method based on thermal imaging and multivariate spectroscopy as claimed in claim 1, characterized in that: The edge morphology feature is extracted from the infrared radiation data. The edge morphology feature extraction uses the Prewitt edge detection algorithm to identify the object contour in the grayscale image, including two kernel functions, which are used to calculate the horizontal direction and the horizontal direction, respectively. x and vertical direction y , and then double threshold processing is used to determine the final edge.

4. The coal gangue identification method based on thermal imaging and multivariate spectroscopy as claimed in claim 1, characterized in that: The temperature feature is extracted from the infrared radiation data. The temperature information of the coal or gangue surface is directly obtained from the infrared thermal image obtained by the infrared thermal imager. Each pixel point of the infrared thermal image has its corresponding temperature. The temperature information is denoised by using a median filter. After denoising, the average temperature feature can be obtained as follows: Where: T is the average temperature; T i Pixel i The temperature value at n is the total number of pixels in the infrared thermal image.

5. The coal gangue identification method based on thermal imaging and multivariate spectroscopy as claimed in claim 1, characterized in that: The spectral reflectance characteristics in different bands are extracted from the spectral reflectance data, and the multivariate spectral reflectance data of each band is normalized by the following formula: Where: λ i is the i-th band, R norm ( λ i ) is the band λ i Department Multivariate spectral data of R ( λ i )for λ i Department The original data; R max for λ i Department The maximum value of the data; R min for λ i Department The minimum value of the data; After normalization, the multi-band spectral reflectance feature vector can be constructed: 。 6. A coal gangue identification system based on thermal imaging and multivariate spectroscopy, which implements a coal gangue identification method based on thermal imaging and multivariate spectroscopy as described in any one of claims 1 to 5, characterized in that: include: A data acquisition module is used to acquire infrared radiation data of the coal gangue to be identified and spectral reflectance data of multiple bands; A data preprocessing module, used for preprocessing infrared radiation data and spectral reflectance data; A feature extraction module, used to extract edge morphological features and temperature features from the infrared radiation data, and to extract spectral reflectance features in different bands from the spectral reflectance data; A feature fusion module is used to fuse temperature features, edge morphology features and spectral features through multi-modal feature fusion to obtain fusion features; The classification module is used to input the fusion features into the coal gangue recognition model to obtain the automatic classification results of coal and gangue.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy described in any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy as described in any one of claims 1 to 5 is implemented.

9. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the coal gangue identification method based on the combination of thermal imaging and multivariate spectroscopy as described in any one of claims 1 to 5.

Images