Coal gangue identification method based on polarization defogging technology

Abstract

The invention discloses a coal gangue identification method based on a polarization defogging technology, and the method comprises the following steps: building a cuboid model with a hollow interior, and enabling the cuboid model to serve as a scene for achieving the whole polarization defogging; coal and gangue with different lumpiness are placed on the rear scraper conveyor model which is scaled in equal proportion, and the moving coal flow state is obtained; acquiring a coal flow image on the rear scraper model by using a multi-view polarization imaging system; based on a polarization defogging technology, defogging processing is carried out on an obtained coal flow image, and a clear coal flow image is obtained; and processing the defogged coal flow image by using a related image segmentation algorithm to obtain images and data after coal and gangue in the coal flow are identified, thereby realizing coal and gangue identification. According to the method, technologies in other fields can be introduced to the technical field of coal mines, a new method is provided for the coal gangue identification technology of the fully mechanized caving face, and fusion development of multiple fields is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine engineering, and in particular to a coal gangue identification method based on polarization defogging technology. Background Art

[0002] Traditional coal caving methods have many limitations in mining thick and extra-thick coal seams. These methods rely primarily on manual observation and control, with workers distinguishing between coal and gangue by observing the color and shape of the discharged coal and listening to the sound of top coal falling into the caving window. This method is labor-intensive, inefficient, and has unstable identification accuracy, susceptible to changes in worker condition and experience. With the development of intelligent technology, the coal mining industry is also facing the need for intelligent transformation. Intelligent coal caving technology enables real-time monitoring and control of the caving process, improving production efficiency and safety. Therefore, the use of intelligent coal caving technology is an inevitable trend.

[0003] During top coal caving, the mixture of coal and gangue is complex, and the rapidly moving gangue is difficult to accurately identify on scraper conveyors. Environmental factors such as high dust levels, low illumination, and overlapping coal and gangue also complicate gangue identification. Therefore, appropriate methods are needed to identify coal and gangue. For example, image recognition technology utilizes image recognition algorithms to identify coal and gangue. By calculating the mixed gangue ratio (coal-gangue mixture ratio), precise control of the caving process is achieved. Image recognition technology can overcome the recognition errors and subjectivity inherent in traditional methods, improving recognition accuracy and stability. Furthermore, based on image recognition technology, polarization dehazing technology, combined with and incorporating technologies from other fields, is being used to achieve gangue identification. This not only provides a new approach to gangue identification in fully-mechanized caving working faces but also promotes the integrated development of multiple fields. Summary of the Invention

[0004] The present invention provides a coal gangue identification method based on polarization defogging technology to solve the problems raised in the above background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A coal gangue identification method based on polarization defogging technology comprises the following steps: constructing a hollow rectangular parallelepiped model as a scene for realizing the entire polarization defogging; placing coal and gangue of different sizes on a scaled rear scraper conveyor model to obtain a moving coal flow state; using a multi-eye polarization imaging system to obtain a coal flow image on the rear scraper model; defogging the acquired coal flow image based on polarization defogging technology to obtain a clearer coal flow image; and processing the defogging coal flow image using a related image segmentation algorithm to obtain an image and data after coal and gangue in the coal flow are identified, thereby realizing coal gangue identification.

[0006] As a further improvement of the present technical solution: Step S1 described in right 2 further includes: the hollow rectangular model is used to simulate the scene with dust in the production process of the comprehensive mining working face, and a hole for releasing dust is set on the top, a circular hole for air intake is set on the left side, and a blower is placed on the left side for air intake, a circular hole for air exhaust is set on the right side, and a dust bag is tied to the circular hole on the right side to collect the dust blown out.

[0007] As a further improvement to this technical solution, step S2 described in claim 3 further includes: The scaled rear scraper conveyor model comprises an external conveyor frame, a belt, and a motor. Coal and gangue of varying sizes are placed on the belt to simulate the flow of coal along with the rear scraper in a fully mechanized caving face after caving. The scaled rear scraper conveyor model is then placed at the bottom of the hollow rectangular parallelepiped model described in step S1.

[0008] As a further improvement to this technical solution, step S3 described in claim 4 further includes: the multi-eye polarization imaging system is composed of multiple polarization imaging cameras. A polarization imaging camera is a high-speed camera with an angled linear polarizer added in front of its lens. Polarizers with different angles are installed in multiple high-speed cameras to analyze the effects of different polarization angles. Several polarization imaging cameras constitute a multi-eye polarization imaging system. The multi-eye polarization imaging system is placed in front of the hollow rectangular model described in step S1 to capture real-time images of the coal flow in motion.

[0009] As a further improvement of the present technical solution: Step S4 described in right 5 further includes: the polarization defogging technology uses an improved polarization defogging algorithm in a computer to perform defogging on the collected coal flow image, highlight the desired image features, and finally obtain a clearer coal flow image after defogging.

[0010] As a further improvement of the present technical solution: in step S5 described in right 6, it further includes: the algorithm for the relevant image segmentation refers to the algorithm for semantic segmentation and instance segmentation, and the dehazed image is segmented by using different image segmentation algorithms based on deep learning to obtain different coal flow images after segmenting and identifying coal and gangue, and the coal flow images segmented by different algorithms are compared to obtain and use the most suitable image segmentation algorithm, which is then used for subsequent coal gangue identification.

[0011] Compared with the prior art, the present invention has the following beneficial effects: Applying technologies from other fields to the field of coal mining technology provides a new method for coal gangue identification technology in fully mechanized caving working faces and promotes the integrated development of multiple fields.

[0012] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and to implement it according to the contents of the description, the following preferred embodiments of the present invention are described in detail with reference to the accompanying drawings. The specific implementation methods of the present invention are given in detail by the following embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 This is a flow chart of a coal gangue identification method based on polarization defogging technology proposed in the present invention. DETAILED DESCRIPTION

[0014] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples provided are intended only to illustrate the present invention and are not intended to limit the scope of the present invention. The following paragraphs describe the present invention in more detail by way of example with reference to the accompanying drawings. It should be noted that the drawings are all in a very simplified form and are not to exact scale, and are only used for the purpose of conveniently and clearly illustrating the embodiments of the present invention.

[0015] It should be noted that when a component is referred to as being "fixed to" another component, it may be directly on the other component or there may also be a central component. When a component is considered to be "connected to" another component, it may be directly connected to the other component or there may also be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may also be a central component. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0016] See also Figure 1 In an embodiment of the present invention, a coal gangue identification method based on polarization defogging technology includes the following steps: S1. Build a hollow rectangular model to realize the entire polarization defogging scene.

[0017] Specifically, the hollow rectangular model is used to simulate the dusty conditions encountered during the fully mechanized caving face production process. It can be constructed using acrylic panels. A dust release hole is located at the top, which must continue to release dust after pre-ventilation. A circular hole is placed on the left side to allow air in. A blower is placed on the left side, with a set wind speed for 20 minutes of pre-ventilation to expel the polluted air from the model. A circular hole is located on the right side to allow air out, and a dust bag is attached to the hole to collect the dust that is blown out.

[0018] S2. The coal flow state of motion is obtained by placing coal and gangue of different sizes on the scaled rear scraper conveyor model.

[0019] Specifically, a scaled rear scraper conveyor model consists of an external conveyor frame, a belt, and a motor. This scaled rear scraper conveyor model is placed at the bottom of the hollow rectangular model from step S1. The motor is powered on, allowing the belt to move continuously. Coal and gangue of varying sizes are placed on the belt to simulate the flow of coal following the rear scraper in a fully mechanized caving face.

[0020] S3. Obtain coal flow images on the rear scraper model by using a multi-eye polarization imaging system.

[0021] Specifically, the multi-lens polarization imaging system consists of multiple polarization imaging cameras. Polarization imaging cameras are essentially high-speed cameras with an angled linear polarizer installed in front of their lenses. Polarizers with different angles are installed in multiple high-speed cameras to analyze the effects of different polarization angles. Several polarization imaging cameras together form a multi-lens polarization imaging system. The multi-lens polarization imaging system is placed in front of the hollow rectangular model from step S1. The frequency of simultaneous capture is set to capture real-time images of the coal flow in motion.

[0022] S4. By using polarization defogging technology, the acquired coal flow image is defogged to obtain a clearer coal flow image.

[0023] Specifically, polarization defogging technology uses an improved polarization defogging algorithm in a computer to defog the collected coal flow image, highlight the desired image features, and finally obtain a clearer coal flow image after defogging.

[0024] S5. By using the algorithm of related image segmentation, the coal flow image after defogging is processed to obtain the image and data after the coal and gangue in the coal flow are identified, thereby realizing coal gangue identification.

[0025] Specifically, the algorithms for relevant image segmentation refer to semantic segmentation and instance segmentation algorithms. By using different image segmentation algorithms based on deep learning to segment the dehazed image, different coal flow images are obtained after the coal and gangue are separated and identified. The coal flow images segmented by different algorithms are compared to obtain and use the most suitable image segmentation algorithm for subsequent coal gangue identification.

[0026] The working principle of the present invention is: Polarization defogging technology is used to perform image recognition of coal and gangue in the coal flow moving on the rear scraper conveyor.

[0027] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any ordinary technician in this industry can smoothly implement the present invention as shown in the drawings and described above. However, any equivalent changes, modifications and evolutions made by technicians familiar with this profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the scope of protection of the technical solution of the present invention.

Claims

1. A coal gangue identification method based on polarization defogging technology, characterized in that: The method comprises the following steps: S1. Build a hollow rectangular model to realize the entire polarization defogging scene; S2. Obtain the coal flow state by placing coal and gangue of different sizes on the scaled rear scraper conveyor model; S3, obtaining coal flow images on the rear scraper model by using a multi-eye polarization imaging system; S4. Defogging the acquired coal flow image by using polarization-based defogging technology to obtain a clearer coal flow image; S5. By using the algorithm of related image segmentation, the coal flow image after defogging is processed to obtain the image and data after the coal and gangue in the coal flow are identified, thereby realizing coal gangue identification.

2. The coal gangue identification method based on polarization defogging technology according to claim 1 is characterized in that: The step S1 further includes: The hollow rectangular model is used to simulate the dusty scene during the production process of the fully mechanized caving working face. It is necessary to set a hole on the top to release dust, set a circular hole on the left side to let in air, and place a blower on the left side for letting in air. A circular hole on the right side to let out air is set, and a dust bag is tied to the circular hole on the right side to collect the dust blown out.

3. The coal gangue identification method based on polarization defogging technology according to claim 1 is characterized in that: The step S2 further includes: The scaled rear scraper conveyor model consists of a conveyor frame, belt, and motor. Coal and gangue of varying sizes are placed on the belt to simulate the flow of coal along with the rear scraper in a fully mechanized caving face after caving. The scaled rear scraper conveyor model is placed at the bottom of the hollow rectangular parallelepiped model from step S1.

4. The coal gangue identification method based on polarization defogging technology according to claim 1 is characterized in that: The step S3 further includes: The multi-lens polarization imaging system is composed of multiple polarization imaging cameras. Polarization imaging cameras are designed to add an angled linear polarizer in front of the lens of a high-speed camera. Polarizers of different angles are installed in multiple high-speed cameras to analyze the effects of different polarization angles. Several polarization imaging cameras together form a multi-lens polarization imaging system. The multi-lens polarization imaging system is placed in front of the hollow rectangular parallelepiped model in step S1 to capture real-time images of the coal flow in motion.

5. The coal gangue identification method based on polarization defogging technology according to claim 1 is characterized in that: The step S4 further includes: The polarization defogging technology uses an improved polarization defogging algorithm in a computer to perform defogging on the collected coal flow image, highlight the desired image features, and finally obtain a clearer coal flow image after defogging.

6. The coal gangue identification method based on polarization defogging technology according to claim 1 is characterized in that: The step S5 further includes: The related image segmentation algorithms refer to semantic segmentation and instance segmentation algorithms. By using different image segmentation algorithms based on deep learning to segment the dehazed image, different coal flow images are obtained after segmenting and identifying coal and gangue. The coal flow images segmented by different algorithms are compared to obtain and use the most suitable image segmentation algorithm for subsequent coal gangue identification.

Images