Coal quality detection method and system based on combination of machine vision and multispectrum

Abstract

The invention provides a coal quality detection method and system based on combination of machine vision and multispectrum, and belongs to the technical field of coal mine automatic online detection. Pretreating the coal sample; accurately positioning the coal sample by using machine vision auxiliary image analysis equipment and multispectral analysis equipment; detecting the coal sample by using image analysis equipment and multispectral analysis equipment to obtain various detection data; importing the detection data of the multiple spectral analysis devices into a pre-established comprehensive multi-spectral detection model; and outputting an image analysis detection result and a multispectral analysis detection result. According to the method, more elements in coal can be quantitatively detected, fusion processing of various coal detection data is realized, coal components and non-coal components in a coal sample can be detected at the same time, the detection precision is further improved, the limitation of a single coal quality detection technology is avoided, the advantages of various coal quality detection technologies are fully played, and the method is suitable for popularization and application. More comprehensive, quicker and more accurate coal quality detection is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic online detection of coal, and in particular relates to a coal quality detection method and system based on the combination of machine vision and multi-spectrum. Background Art

[0002] In the coal industry, coal quality testing is a key link in ensuring coal quality and optimizing coal utilization efficiency. Traditional coal quality testing methods mainly rely on chemical analysis. Although these methods can provide accurate results, they have many limitations, such as long testing time, complex operation, high cost, and certain pollution to the environment. Therefore, finding more efficient and environmentally friendly coal quality testing technology has become an important demand of the coal industry.

[0003] In recent years, spectral analysis technology has gradually attracted attention in the field of coal quality testing due to its characteristics of rapid, non-destructive and multi-element analysis. For example, X-ray fluorescence spectroscopy (XRF) technology can detect multiple elements in coal with high precision, and is particularly suitable for detecting key indicators such as ash and sulfur. Laser induced breakdown spectroscopy (LIBS) technology is widely used in the rapid screening of coal components due to its rapid detection and full element analysis capabilities. In addition, near-infrared spectroscopy (NIRS) technology also performs well in detecting moisture and volatile matter in coal. However, these single spectral technologies still have some shortcomings in practical applications, such as the relatively slow detection speed of XRF and the need to improve the quantitative analysis accuracy of LIBS.

[0004] At the same time, the application of machine vision technology in coal quality testing is also gradually emerging. Through image analysis, machine vision can provide information such as coal's appearance characteristics and particle size distribution. For example, by using the difference in surface texture between coal and rock, machine vision technology can realize coal-rock identification. Combined with image processing and artificial intelligence algorithms, machine vision technology can also predict coal quality parameters with a small error in the test results. However, machine vision technology mainly focuses on the appearance characteristics of coal, and its ability to detect internal chemical composition is limited.

[0005] The existing single coal quality detection technology is difficult to meet the requirements of fast, multi-element and high precision at the same time, while the combination of machine vision and multi-spectrum can make up for their respective shortcomings. Summary of the invention

[0006] In order to solve the problems existing in the existing technology, the present invention proposes a coal quality detection method and system combining machine vision and multi-spectrum. The present invention can avoid the limitations of a single coal quality detection technology, give full play to the advantages of various coal quality detection technologies, and achieve more comprehensive, faster and more accurate coal quality detection.

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

[0008] A coal quality detection method using machine vision and multi-spectrum, comprising the following steps:

[0009] Pre-treatment of coal samples;

[0010] Use machine vision-assisted image analysis equipment and multi-spectral analysis equipment to accurately locate coal samples;

[0011] Use image analysis equipment and multi-spectral analysis equipment to test coal samples and obtain a variety of test data;

[0012] Import the detection data of various spectral analysis equipment into the pre-established comprehensive multi-spectral detection model;

[0013] Output image analysis test results and multispectral analysis test results.

[0014] As an optional implementation, the step of pre-processing the coal sample includes:

[0015] Collect sample coal lumps on the coal conveyor belt;

[0016] The sample coal blocks are further broken down into a size suitable for testing;

[0017] The crushed sample coal blocks are evenly spread and conveyed to the detection belt.

[0018] As an optional implementation, a machine vision-assisted image analysis device and a multi-spectral analysis device are used to accurately locate the sample coal block to be tested.

[0019] As an optional implementation, an image analysis device and a multi-spectral analysis device are used to detect the coal sample to obtain a variety of detection data;

[0020] Furthermore, image analysis equipment is used to detect non-coal components such as impurities and rocks in coal samples.

[0021] Further, the steps of image analysis include:

[0022] Acquire coal particle images;

[0023] De-noise the coal particle image and adjust the image contrast;

[0024] Extract surface texture features, RGB features, and HSV features of coal particle images;

[0025] Identify non-coal components such as impurities and rocks in coal.

[0026] Furthermore, the multi-spectral analysis equipment includes a laser induced breakdown spectroscopy (LIBS) detection equipment, an X-ray fluorescence spectroscopy (XRF) detection equipment and a near infrared spectroscopy (NIRS) detection equipment.

[0027] Furthermore, the detection process of the multi-spectral analysis equipment follows industry standards, and specific operating details can be found in relevant literature.

[0028] Furthermore, the various detection data obtained include analysis data of coal samples by image analysis equipment and spectral data of coal samples detected by three types of spectral analysis detection equipment, namely LIBS detection, XRF detection, and NIRS detection.

[0029] Furthermore, the detection order of the multi-spectral analysis is near infrared spectroscopy (NIRS) detection, X-ray fluorescence spectroscopy (XRF) detection, and laser induced breakdown spectroscopy (LIBS) detection.

[0030] As an optional implementation, the steps of establishing a comprehensive multispectral detection model include:

[0031] Pre-select an appropriate amount of coal samples, use multi-spectral analysis methods and traditional chemical methods to test coal quality, and obtain spectral test data and chemical method test data;

[0032] Obtain LIBS data, XRF data, NIRS data, and chemical method data;

[0033] Extract the common components of multi-spectral data and chemical data, and select the spectral data that best matches the chemical results as the final test data of the component based on the least squares comparison. The test data selection method for other coal components is the same as above.

[0034] Extract the data other than the data that can test the same coal component from the three types of test data as the test data of other coal components;

[0035] Extract the final determined test data of various coal components as final test data;

[0036] Furthermore, the comprehensive multispectral detection model does not need to be frequently adjusted after being established and finalized once.

[0037] As an optional implementation, the final output result includes the detection result of the image analysis and the detection result of the multi-spectral analysis.

[0038] A coal quality detection system based on machine vision and multi-spectrum, comprising:

[0039] A sample pre-processing module is configured to collect sample coal blocks on the coal conveyor belt, further crush the sample coal blocks into a size suitable for detection, and then convey the crushed sample coal blocks to the detection belt;

[0040] A positioning and guiding module is configured to use a machine vision method to assist an image analysis device and a multi-spectral analysis device in accurately positioning a sample coal block to be tested;

[0041] The sample detection module is configured to detect the coal sample using an image analysis device and a near infrared spectroscopy (NIRS) detection device, an X-ray fluorescence spectroscopy (XRF) detection device, and a laser induced breakdown spectroscopy (LIBS) detection device to obtain image analysis data and a variety of spectral data;

[0042] A data processing module is configured to determine final detection data of various coal components using a pre-established comprehensive multi-spectral detection model;

[0043] The result output module is configured to ultimately output the image analysis test results and the multi-spectral analysis test results for the coal samples.

[0044] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention can quantitatively test more elements in coal. The present invention can realize the fusion processing of multiple coal detection data, and can simultaneously detect the coal components and non-coal components in the coal sample, further improving the detection accuracy. The present invention can avoid the limitations of a single coal quality detection technology, give full play to the advantages of various coal quality detection technologies, and realize more comprehensive, faster and more accurate coal quality detection.

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0049] Figure 1 The present invention is a flow chart of coal quality detection based on the combination of machine vision and multi-spectrum in one embodiment;

[0050] Figure 2 The present invention is a flowchart of coal sample preprocessing in the coal quality detection process based on the combination of machine vision and multi-spectrum in one embodiment;

[0051] Figure 3The present invention is a flowchart of an image analysis process in a coal quality detection process based on the combination of machine vision and multi-spectrum in an embodiment;

[0052] Figure 4 The present invention is a flowchart of an embodiment of establishing a comprehensive multi-spectral detection model in the coal quality detection process based on the combination of machine vision and multi-spectrum. DETAILED DESCRIPTION

[0053] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0054] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. 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 invention belongs.

[0055] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0056] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0057] Embodiment 1

[0058] A coal quality detection method using machine vision and multi-spectrum can quantitatively test more elements in coal, realize the fusion processing of multiple coal detection data, and detect coal components and non-coal components in coal samples at the same time, further improve the detection accuracy, avoid the limitations of a single coal quality detection technology, give full play to the advantages of various coal quality detection technologies, and realize more comprehensive, faster and more accurate coal quality detection. The specific steps are as follows: Figure 1 As shown:

[0059] S100: pre-processing of coal samples;

[0060] In this embodiment, the step of pre-processing the coal sample is as follows: Figure 2 As shown, including:

[0061] S110: Collecting sample coal blocks on the coal conveyor belt;

[0062] S120: further crushing the sample coal block into a size suitable for testing;

[0063] S130: evenly spread the crushed sample coal blocks and convey them to the detection belt;

[0064] S200: Machine vision-assisted image analysis equipment and multi-spectral analysis equipment to accurately locate coal samples;

[0065] S300: Use image analysis equipment and multi-spectral analysis equipment to test coal samples and obtain various test data;

[0066] In this embodiment, the image analysis device is used to detect non-coal components such as impurities and rocks in the coal sample;

[0067] In this embodiment, the image analysis step is as follows: Figure 3 As shown, including:

[0068] S311: Acquire coal particle images through a camera;

[0069] S312: using Gaussian filtering to remove noise from the coal particle image and adjust the image contrast to make the coal features more obvious;

[0070] S313: extracting surface texture features, RGB features, and HSV features of coal particle images;

[0071] S314: Identify impurities, rocks and other non-coal components in coal;

[0072] In this embodiment, the spectral analysis equipment includes a laser induced breakdown spectroscopy (LIBS) detection equipment, an X-ray fluorescence spectroscopy (XRF) detection equipment, and a near infrared spectroscopy (NIRS) detection equipment;

[0073] In this embodiment, the detection process of the spectrum analysis equipment follows the industry standard, and the specific operation details can be referred to the relevant literature;

[0074] In this embodiment, the various detection data obtained include analysis data of coal samples by image analysis equipment and spectral data of coal samples detected by three types of spectral analysis detection equipment, namely LIBS detection, XRF detection, and NIRS detection;

[0075] In this embodiment, the detection order of the multispectral analysis is near infrared spectroscopy (NIRS) detection, X-ray fluorescence spectroscopy (XRF) detection, and laser induced breakdown spectroscopy (LIBS) detection;

[0076] S400: importing the detection data of various spectral analysis equipment into a pre-established comprehensive multi-spectral detection model;

[0077] In this embodiment, the steps of establishing the pre-established comprehensive multi-spectral detection model are as follows: Figure 4 As shown, including:

[0078] S410: Preselect an appropriate amount of coal samples, use multi-spectral analysis methods and traditional chemical methods to test coal quality, and obtain spectral test data and chemical method test data;

[0079] S420: Obtain LIBS data, XRF data, NIRS data, and chemical method data;

[0080] S430: extracting the common components of the multi-spectral data and the chemical data, and selecting the spectral data that best matches the chemical result as the final detection data of the component based on the least squares comparison. The detection data selection method for other coal components is the same as above;

[0081] S440: extracting data other than the data that can test the same coal component from the three types of test data as test data of other coal components;

[0082] S450: extracting the finally determined test data of various coal components as final test data;

[0083] In this embodiment, the comprehensive multi-spectral detection model will not be changed after it is established once and finally determined.

[0084] S500: Outputting image analysis detection results and multi-spectral analysis detection results.

[0085] Embodiment 2:

[0086] A coal quality detection system based on machine vision and multi-spectrum, comprising:

[0087] A sample pre-processing module is configured to collect sample coal blocks on the coal conveyor belt, further crush the sample coal blocks into a size suitable for detection, and then convey the crushed sample coal blocks to the detection belt;

[0088] A positioning and guiding module is configured to use a machine vision method to assist an image analysis device and a multi-spectral analysis device in accurately positioning a sample coal block to be tested;

[0089] The sample detection module is configured to detect the coal sample using an image analysis device and a near infrared spectroscopy (NIRS) detection device, an X-ray fluorescence spectroscopy (XRF) detection device, and a laser induced breakdown spectroscopy (LIBS) detection device to obtain image analysis data and a variety of spectral data;

[0090] A data processing module is configured to determine final detection data of various coal components using a pre-established comprehensive multi-spectral detection model;

[0091] The result output module is configured to ultimately output the image analysis test results and the multi-spectral analysis test results for the coal samples.

[0092] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of 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 produce 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.

[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] 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 1 The steps for the functions specified in one or more boxes.

[0096] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A coal quality detection method based on machine vision and multi-spectrum, characterized in that: The following steps are involved: Pre-treatment of coal samples; Use machine vision-assisted image analysis equipment and multi-spectral analysis equipment to accurately locate coal samples; Use image analysis equipment and multi-spectral analysis equipment to test coal samples and obtain a variety of test data; Import the detection data of various spectral analysis equipment into the pre-established comprehensive multi-spectral detection model; Output image analysis test results and multispectral analysis test results.

2. The coal quality detection method based on machine vision and multi-spectrum according to claim 1 is characterized in that: The steps for pre-processing coal samples include: Collect sample coal lumps on the coal conveyor belt; The sample coal blocks are further broken down into a size suitable for testing; The crushed sample coal blocks are evenly spread and conveyed to the detection belt.

3. The coal quality detection method based on machine vision and multi-spectrum according to claim 1 is characterized in that: Image analysis equipment is used to detect impurities, rocks and other non-coal components in coal samples. The steps of image analysis include: Acquire coal particle images; De-noise the coal particle image and adjust the image contrast; Extract surface texture features, RGB features, and HSV features of coal particle images; Identify non-coal components such as impurities and rocks in coal.

4. The coal quality detection method based on machine vision and multi-spectrum according to claim 1 is characterized in that: Spectral analysis equipment includes laser induced breakdown spectroscopy (LIBS) detection equipment, X-ray fluorescence spectroscopy (XRF) detection equipment and near infrared spectroscopy (NIRS) detection equipment.

5. The coal quality detection method based on machine vision and multi-spectrum according to claim 1 is characterized in that: The various test data obtained include analysis data of coal samples by image analysis equipment and spectral data of coal samples by three types of spectral analysis and testing equipment: LIBS testing, XRF testing, and NIRS testing.

6. The coal quality detection method based on machine vision and multi-spectrum according to claim 1 is characterized in that: The detection order of multi-spectral analysis is near infrared spectroscopy (NIRS), X-ray fluorescence spectroscopy (XRF), and laser induced breakdown spectroscopy (LIBS).

7. The coal quality detection method based on machine vision and multi-spectrum according to claim 1 is characterized in that: The steps to build a comprehensive multispectral detection model include: Pre-select an appropriate amount of coal samples, use multi-spectral analysis methods and traditional chemical methods to test coal quality, and obtain spectral test data and chemical method test data; Obtain LIBS data, XRF data, NIRS data, and chemical method data; Extract the common components of multi-spectral data and chemical data, and select the spectral data that best matches the chemical results as the final test data of the component based on the least squares comparison. The test data selection method for other coal components is the same as above. Extract the data other than the data that can test the same coal component from the three types of test data as the test data of other coal components; Extract the final determined test data of various coal components as final test data; Once the model is finalized, it does not need to be adjusted frequently.

8. The coal quality detection method based on machine vision and multi-spectrum according to claim 1 is characterized in that: The final output results include the detection results of image analysis and multi-spectral analysis.

9. A coal quality detection system based on machine vision and multi-spectrum, characterized in that: include: A sample pre-processing module is configured to collect sample coal blocks on the coal conveyor belt, further crush the sample coal blocks into a size suitable for detection, and then convey the crushed sample coal blocks to the detection belt; A positioning and guiding module is configured to use a machine vision method to assist an image analysis device and a multi-spectral analysis device in accurately positioning a sample coal block to be tested; The sample detection module is configured to detect the coal sample using an image analysis device and a near infrared spectroscopy (NIRS) detection device, an X-ray fluorescence spectroscopy (XRF) detection device, and a laser induced breakdown spectroscopy (LIBS) detection device to obtain image analysis data and a variety of spectral data; A data processing module is configured to determine final detection data of various coal components using a pre-established comprehensive multi-spectral detection model; The result output module is configured to ultimately output the image analysis test results and the multi-spectral analysis test results for the coal samples.

10. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps of any one of claims 1 to 8 are completed.

Images