An online detection and metering method applied to a coal washing system

Abstract

The application discloses an online detection and metering method applied to a coal washing system, and comprises the following steps: conveying raw coal in a coal receiving machine to a sizing screen, detecting the particle size of the oversize and undersize of the sizing screen, and sending an alarm information of sizing screen abnormality when the particle size of the undersize is uneven; carrying out crushing detection on the oversize, selecting large raw coal after crushing for secondary crushing, and sending an alarm information of crusher abnormality when the raw coal needing secondary crushing exceeds a preset range; conveying the raw coal after secondary crushing and the undersize to a coal washer for classification to obtain gangue and medium coal; carrying out secondary screening on the medium coal through a jig to obtain fine coal with a smaller particle size, and when the particle size of the fine coal after secondary screening does not meet a preset requirement, the coal after secondary screening is put into the jig for tertiary screening, and when the fine coal after tertiary screening still does not meet the preset requirement, an alarm information of jig abnormality is sent; and metering the fine coal meeting the preset requirement.

Description

Technical Field

[0001] This invention relates to the field of coal washing and testing and measurement technology, specifically to an online detection and measurement method applied to a coal washing and testing system. Background Technology

[0002] Coal washing is a process that uses physical and other methods to refine raw coal, improving the quality of the refined coal product and reducing its ash, sulfur, and volatile matter content to meet customer requirements. This coal processing method can separate and reduce undesirable components in coal, such as ash and sulfur, improving the energy utilization rate and economic value of coal, and reducing pollutants generated during combustion. Coal washing has become an important technology in the modern coal industry, not only improving fuel performance and reducing environmental pollution, but also promoting the diversification of energy mix and ensuring energy security.

[0003] However, in the coal washing process, how to cut the coal to achieve a uniform size of coal blocks fed into the jig, avoid damage to the jig, and extend the working life of the jig has become a major problem. In addition, different coal qualities have different requirements for washing processes. Existing technologies may not be able to achieve ideal coal washing efficiency and clean coal quality when processing certain complex coal qualities. High-efficiency coal washing equipment has a high initial investment, and daily operation and maintenance also require high costs. Summary of the Invention

[0004] To address the above technical problems, this invention provides an online detection and measurement method for a coal washing and preparation system, the method comprising:

[0005] The raw coal in the coal receiving machine is conveyed to the grading screen. The particle size of the oversize and undersize material of the grading screen is detected. When the particle size of the undersize material is uneven, an alarm message of abnormality of the grading screen is sent.

[0006] The material on the screen is crushed. Large pieces of raw coal after crushing are selected for secondary crushing. When the amount of raw coal that needs to be crushed for secondary crushing exceeds the preset range, an alarm message for crusher abnormality is sent.

[0007] The raw coal and undersize material from the secondary crushing are conveyed to a coal washing machine for classification to obtain gangue and middlings.

[0008] The middlings are screened twice by the jig to obtain finer coal with smaller particle size. If the particle size of the finer coal after the second screening does not meet the preset requirements, the coal after the second screening is put into the jig for a third screening. If the third screening still does not meet the preset requirements, an alarm message for jig abnormality is sent.

[0009] Measuring of clean coal that meets preset requirements.

[0010] Optionally, the step of conveying raw coal from the coal receiving machine to a grading screen, and performing particle size detection on the oversize and undersize materials of the grading screen, and sending an alarm message indicating an abnormality in the grading screen when the particle size of the undersize material is uneven, specifically includes:

[0011] Extract the contour features of the raw coal to generate a cutting scheme;

[0012] Raw coal is conveyed to a grading screen via a coal receiving machine;

[0013] The coal under the grading screen is subjected to lifting wavelet and LBF model for coal particle size detection. When the detected particle size does not meet the requirements, an abnormal alarm for the grading screen is sent.

[0014] Optionally, the methods for automatically generating cutting schemes include:

[0015] Superpixel blocks are generated by segmenting coal mine images using a superpixel algorithm.

[0016] The superpixel blocks are merged using a merging strategy, and the coal block image to be processed is obtained by region segmentation.

[0017] The data of the coal block images to be processed are labeled, and a segmentation model based on semi-supervised learning and self-training is constructed based on the labeled data and the data of the remaining coal block images to be processed.

[0018] The segmentation model based on semi-supervised learning and self-training is used to segment coal mine images, thereby achieving coal mine segmentation.

[0019] Optionally, lifting wavelet and LBF model are used to detect the coal particle size under the grading screen. When the detected particle size does not meet the requirements, the content of the grading screen abnormality alarm sent includes:

[0020] The cubic B-spline function is used as the prediction operator for lifting wavelets to filter, denoise, and detect edges in the acquired coal block image to be processed.

[0021] Morphological operations are performed on the wavelet-transformed image to eliminate holes in the coal mine image.

[0022] The image after wavelet processing is segmented using the LBF model. Connected component operations are performed on the segmented image to obtain the number of coal mines. The number of pixels in the image is converted into the actual ore area. The horizontal projection of the ore is equivalent to a circle, and the approximate ore particle size is obtained through the area of ​​the circle.

[0023] The average value of the approximate ore particle size is obtained. If the average value of the approximate ore particle size exceeds the preset ore particle size threshold range, an abnormal alarm for the grading screen is triggered.

[0024] Optionally, the step of performing crushing detection on the oversize material, selecting large pieces of raw coal after crushing for secondary crushing, and sending an alarm message indicating a crusher malfunction when the amount of raw coal requiring secondary crushing exceeds a preset range specifically includes:

[0025] The U-NET network was used to extract the contour features of the large pieces of material on the sieve, and the first contour image was obtained.

[0026] The Canny algorithm is used to perform edge enhancement processing on the first contour image to obtain the second contour image;

[0027] Large pieces of raw coal with an area greater than a preset threshold are calculated in the second contour map and fed into a crusher for secondary crushing.

[0028] If the area of ​​a large piece of raw coal in the second contour image is larger than the preset threshold range, an alarm message indicating an abnormality in the crusher will be sent.

[0029] Optionally, the U-NET network is used to extract the contour features of the large pieces of material on the screen, and the content of the first contour image specifically includes:

[0030] When using U-NET, add an attention mechanism at the skip connections in the U-Net model to extract features;

[0031] The loss function is used to optimize the extracted features to obtain the first contour image.

[0032] Optionally, the process of conveying the secondary crushed raw coal and undersize material to a coal washing machine for classification to obtain gangue and middlings specifically includes:

[0033] The gangue comprises pure gangue and first-grade coal, with a density greater than 1.6 g / cm³. 3 ;

[0034] The middlings coal includes second middlings coal and refined coal, with a density of less than 1.6 g / cm³. 3 .

[0035] Optionally, the middlings are subjected to a second screening using a jig to obtain finer coal with a smaller particle size. If the particle size of the fine coal after the second screening does not meet the preset requirements, the coal after the second screening is fed into the jig for a third screening. If the third screening still does not meet the preset requirements, an alarm message for jig abnormality is sent. The specific content of the alarm message includes:

[0036] The size of the clean coal is tested. If the size meets the preset requirements, it is determined that there is no abnormality. If the size of the clean coal exceeds the preset requirements, a second screening is performed. If the size of the clean coal after the second screening still does not meet the preset requirements, the tool is determined to be abnormal, the jig operation is stopped, and a fault signal is issued.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0038] This invention employs a two-stage cutting method. First, a semi-supervised method is used to plan and cut the raw coal. Then, contour cutting is performed based on the image of the cut raw coal after conveying, resulting in a clearer image and more uniform coal block size. This invention monitors the working status of each component in real time, enabling timely detection and maintenance when component malfunctions cause problems in the coal washing system. Finally, the metering method of this invention can predict future clean coal yield and monitor the overall operation of the coal washing system based on the output. Attached Figure Description

[0039] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating the steps of an online detection and measurement method applied to a coal washing and preparation system according to an embodiment of the present invention. Detailed Implementation

[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0042] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] The raw coal in the coal receiving machine is conveyed to the grading screen. Particle size is measured on both the oversize and undersize materials. If the undersize material has an uneven particle size, an alarm message indicating a grading screen anomaly is sent. Optionally, the specific steps of conveying the raw coal in the coal receiving machine to the grading screen, measuring the particle size of the oversize and undersize materials, and sending an alarm message indicating a grading screen anomaly when the undersize material has an uneven particle size include: extracting the contour features of the raw coal and generating a cutting scheme; conveying the raw coal to the grading screen via the coal receiving machine; and performing coal particle size measurement on the undersize coal using lifting wavelet and LBF models. If the measured particle size does not meet the requirements, an alarm message indicating a grading screen anomaly is sent. In this invention, the particle size requirement range is 8-13 mm.

[0044] The method for automatically generating a cutting scheme specifically includes: using a superpixel algorithm to segment a coal mine image to generate superpixel blocks; using a merging strategy to merge the superpixel blocks and cutting them according to regions to obtain coal block images to be processed; labeling the data of some coal block images to be processed, and constructing a segmentation model based on semi-supervised learning and self-training based on the labeled data and the data of the remaining coal block images to be processed; and using the segmentation model based on semi-supervised learning and self-training to cut the coal mine image to achieve the cutting of raw coal.

[0045] The coal under the grading screen is subjected to lifting wavelet and LBF model for particle size detection. When the detected particle size does not meet the requirements, a grading screen anomaly alarm is sent. Specifically, this includes: using a cubic B-spline function as the prediction operator for the lifting wavelet to filter, denoise, and detect edges on the acquired coal block image; performing morphological operations on the wavelet-transformed image to eliminate holes in the coal block image; performing LBF model image segmentation on the wavelet-processed image, performing connected component operations on the segmented image to obtain the number of coal blocks, converting the number of pixels in the image into the actual ore area, equating the horizontal projection of the ore to a circle, and obtaining the approximate ore particle size through the area of ​​the circle; calculating the mean of the approximate ore particle size, and if the mean of the approximate ore particle size exceeds a preset ore particle size threshold range, a grading screen anomaly alarm is issued. That is, when the mean ore particle size is greater than the preset range of 8-13mm, the grading screen is considered damaged or abnormal, and a grading screen anomaly alarm is issued.

[0046] The process involves: detecting the crushing of the material on the screen; selecting large pieces of raw coal after crushing for secondary crushing; and sending an alarm message indicating a crusher malfunction if the amount of raw coal requiring secondary crushing exceeds a preset range. Specifically, this process includes: extracting contour features from the large pieces of raw coal on the screen using a U-NET network to obtain a first contour image; performing edge enhancement processing on the first contour image using the Canny algorithm to obtain a second contour image; calculating the area of ​​large pieces of raw coal in the second contour image that exceeds a preset threshold, and feeding them into the crusher for secondary crushing; and sending an alarm message indicating a crusher malfunction if the area of ​​large pieces of raw coal in the second contour image exceeds the preset threshold range. The extraction of contour features from the large pieces of raw coal using a U-NET network to obtain the first contour image specifically includes: adding an attention mechanism at the skip connections in the U-Net model to extract features; and optimizing the feature extraction using a loss function to obtain the first contour image.

[0047] The raw coal from secondary crushing and the undersize material are conveyed to a coal washing machine for classification, yielding gangue and middlings. Specifically, the gangue includes pure gangue and first-stage middlings, with a density greater than 1.6 g / cm³. 3 The middlings coal includes second middlings and refined coal, with a density of less than 1.6 g / cm³. 3 .

[0048] The middlings are screened a second time by a jig to obtain finer coal with smaller particle sizes. If the particle size of the fine coal after the second screening does not meet the preset requirements, the coal after the second screening is put back into the jig for a third screening. If the third screening still does not meet the preset requirements, a jig anomaly alarm is sent. The specific content of the jig anomaly alarm includes: checking the size of the fine coal; if the size meets the preset requirements, it is determined that there is no abnormality; if the size of the fine coal exceeds the preset requirements, a second screening is performed; if the size of the fine coal after the second screening still does not meet the preset requirements, the tool is determined to be abnormal, the jig operation is stopped, and a fault signal is issued.

[0049] In this embodiment, the density of the clean coal is required to be 1.5 g / cm³. 3 .

[0050] Measuring of clean coal that meets preset requirements.

[0051] During measurement, it is necessary to calculate the weight of raw coal input within a certain time period and the weight of clean coal obtained after the raw coal has passed through the coal washing and beneficiation system.

[0052] In this embodiment, the time period for raw coal input is recorded. Based on the time required for the coal washing and beneficiation system to process the coal and the conveyor belt speed, the time it takes for the clean coal to fall after the raw coal passes through the system is obtained. Weight is calculated starting from the moment the clean coal falls, and the quantity of clean coal converted from the input raw coal is calculated to obtain the clean coal yield. When the conversion rate is lower than the normal quantity, the system checks whether each component of the coal washing and beneficiation system is functioning properly. If any component malfunctions, an alarm is sent.

[0053] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. An online detection and measurement method applied to a coal preparation system, characterized in that, The method comprises: The raw coal in the receiving machine is conveyed to the sizing screen, and the particle size of the oversize and undersize of the sizing screen is detected, and when the particle size of the undersize is uneven, an alarm information of sizing screen abnormality is sent; The broken detection is performed on the oversize, and the large raw coal after breaking is selected for secondary breaking, and when the raw coal needing secondary breaking exceeds the preset range, an alarm information of breaker abnormality is sent; The secondary broken raw coal and the undersize are conveyed to the coal washer for classification to obtain gangue and medium coal; The medium coal is subjected to secondary screening by the jig, to obtain fine coal with smaller particle size, and when the particle size of the secondary screened fine coal does not meet the preset requirement, the coal after secondary screening is put into the jig for tertiary screening, and when the tertiary screening still does not meet the preset requirement, an alarm information of jig abnormality is sent; The fine coal meeting the preset requirement is metered; The raw coal in the receiving machine is conveyed to the sizing screen, and the particle size of the oversize and undersize of the sizing screen is detected, and when the particle size of the undersize is uneven, an alarm information of sizing screen abnormality is sent; The profile feature of the raw coal is extracted to generate a cutting scheme; The raw coal is conveyed to the sizing screen through the receiving machine; The coal under the sizing screen is subjected to coal mine particle size detection using lifting wavelet and LBF model, and when the detection does not meet the particle size requirement, an alarm of sizing screen abnormality is sent; The method for automatically generating the cutting scheme comprises: The coal mine image is segmented using a superpixel algorithm to generate a superpixel block; The superpixel blocks are merged using a merging strategy to obtain a to-be-processed coal block image according to region cutting; Part of the to-be-processed coal block image is labeled, and a segmentation model based on semi-supervised learning self-training is constructed according to the labeled data and the data of the remaining to-be-processed coal block image; The coal mine image is cut using the segmentation model based on semi-supervised learning self-training, to realize cutting of the coal mine.

2. The online detection and metering method for use in a coal preparation system according to claim 1, characterized in that, The coal under the sizing screen is subjected to coal mine particle size detection using lifting wavelet and LBF model, and when the detection does not meet the particle size requirement, an alarm of sizing screen abnormality is sent; A cubic B-spline function is used as a prediction operator of the lifting wavelet to filter and denoise the obtained to-be-processed coal block image and perform edge detection; Morphological operation is performed on the image after wavelet transform to eliminate the hole part existing in the coal mine image; LBF model is used for image cutting on the image after wavelet processing, connected domain operation is performed on the cut image, the number of coal mines is obtained, the pixel number in the image is converted into the actual ore area, the horizontal projection of the ore is equivalent to a circle, and the approximate ore particle size is obtained through the area of the circle; The mean value of the approximate ore particle size is calculated, and if the mean value of the approximate ore particle size exceeds the preset ore particle size threshold range, an alarm of sizing screen abnormality is sent.

3. The online detection and metering method for use in a coal preparation system according to claim 1, characterized in that, The broken detection is performed on the oversize, and the large raw coal after breaking is selected for secondary breaking, and when the raw coal needing secondary breaking exceeds the preset range, an alarm information of breaker abnormality is sent; The profile feature of the large oversize is extracted using a U-NET network to obtain a first profile image; Edge enhancement processing is performed on the first profile image using a Canny algorithm to obtain a second profile image; The large lump of raw coal in the second profile map whose area is greater than a preset threshold is put into a crusher for secondary crushing. If the area of the large lump of raw coal in the second profile image is greater than a preset threshold range, an alarm information of the crusher exception is sent.

4. The online detection and metering method for use in a coal preparation system according to claim 3, characterized in that, The U-NET network is used to extract the profile features of the large lump of sieve residue, and the content of the first profile image includes: When the U-NET is used, an attention mechanism is added to the U-Net model to extract features. The loss function is used to optimize the feature extraction content, and the first profile image is obtained.

5. The online detection and metering method for use in a coal preparation system according to claim 1, characterized in that, The content of the secondary crushed raw coal and the sieve residue is sent to the coal washer for classification to obtain the gangue and the medium coal includes: The gangue includes pure gangue and first middlings, the density of which is greater than 1.6 g / cm 3 ; The middlings include second middlings and clean coal, and the density of the second middlings and the clean coal is less than 1.6 g / cm 3 .

6. The online detection and measurement method for use in a coal preparation system according to claim 1, characterized in that, The medium coal is subjected to secondary screening by the jig, and the fine coal with smaller particle size is obtained. When the particle size of the secondary screened coal does not meet the preset requirement, the coal after the secondary screening is put into the jig for tertiary screening. When the tertiary screening still does not meet the preset requirement, an alarm information of the jig exception is sent. The size of the fine coal is detected. If the size meets the preset requirement, it is determined that there is no exception. If the size of the fine coal exceeds the preset requirement, secondary jig screening is performed. If the size of the fine coal after the secondary jig screening still does not meet the preset requirement, it is determined that the tool is abnormal, the jig operation is stopped, and a fault signal is sent.

Images