A method for online repair of grinding parts in a medium-speed coal mill

Abstract

This application discloses an online repair method for grinding components of a medium-speed coal mill, relating to the field of coal mill repair technology. The method includes: S100, acquiring image information of the damaged area and determining the location and coverage of the damaged area; S200, determining whether the damaged area is related to surrounding components within its coverage area; if the current damaged area is related to surrounding components, determining the edge portion of the damaged area and assessing the damage amount of the edge portion; determining the required repair area based on the damage amount of the edge portion; S300, selecting repair schemes based on the location of the damaged area and the damage amount of the edge portion; S400, if the current damaged area is not related to surrounding components, determining the repair area based on the damage amount of the damaged area; this method can improve the accuracy and efficiency of the repair.

Description

Technical Field

[0001] This invention relates to the field of coal mill repair technology, and in particular to an online repair method for grinding components of a medium-speed coal mill. Background Technology

[0002] As a core auxiliary machine in the boiler system of thermal power units, the coal mill's operating status has a crucial impact on the overall performance of the unit. However, because coal mills typically operate continuously for extended periods and the internal environment is harsh, the wear of the grinding components is severe, becoming one of the key factors affecting the operational stability of the coal mill.

[0003] Traditional methods for repairing coal mill grinding components mainly include offline welding and online welding. Offline welding requires disassembling and transporting the grinding components to the manufacturer for repair, which not only consumes a lot of time and labor costs but also poses certain construction risks. While online welding can be performed inside the mill, it has strict requirements on the size of the mill and is not universally applicable. Summary of the Invention

[0004] This application provides an online repair method for grinding parts of a medium-speed coal mill, which solves the problem that existing repair techniques are not applicable and improves the accuracy and efficiency of repair.

[0005] This application provides an online repair method for grinding parts of a medium-speed coal mill, including:

[0006] S100: Acquire image information of the damaged area to determine the location and coverage of the damaged area;

[0007] S200, determine whether the damaged area is related to surrounding components within the coverage area of ​​the damaged area. If the current damaged area is related to surrounding components, determine the edge portion of the damaged area and assess the amount of damage to the edge portion; based on the amount of damage to the edge portion, determine the required repair area.

[0008] S300, based on the location of the damaged area and the amount of damage to the edge parts, selects repair solutions;

[0009] S400, if the currently damaged area is not related to surrounding components, the area to be repaired is determined based on the amount of damage to the damaged area;

[0010] S500 verifies the repair area and location for each repair and determines the overlap rate between the weld bead and the actual repair area; based on the overlap rate between the weld bead and the actual repair area, evaluates the repair plan and determines the evaluated repair plan.

[0011] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0012] By acquiring image information of the damaged area, the location and coverage of the damaged area can be accurately determined, providing an accurate basis for subsequent repairs. Based on the correlation between the damaged area and surrounding components, as well as the magnitude of the damage, a suitable repair plan can be selected to ensure the repair effect. By determining parameters such as the movement trajectory of the welding torch and the number of weld layers, the repair process can be optimized to improve repair efficiency and quality. Attached Figure Description

[0013] Figure 1 This is a schematic flowchart of an online repair method for grinding parts of a medium-speed coal mill according to the present invention. Detailed Implementation

[0014] To facilitate understanding of the present invention, a more complete description of this application will be given below with reference to the accompanying drawings, which illustrate preferred embodiments of the invention. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to enable a more thorough and complete understanding of the disclosure of the present invention.

[0015] It should be noted that the terms "vertical," "horizontal," "up," "down," "left," "right," and similar expressions used in this article are for illustrative purposes only and do not represent the only possible implementation.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention; the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0017] Example 1

[0018] like Figure 1 As shown, this application discloses an online repair method for grinding parts of a medium-speed coal mill, including...

[0019] S100: Acquire image information of the damaged area to determine the location and coverage of the damaged area;

[0020] S200, determine the correlation between the damaged area and surrounding components within the coverage area of ​​the damaged area; if the current damaged area is related to surrounding components, determine the edge portion of the damaged area and assess the damage amount of the edge portion; based on the damage amount of the edge portion, determine the required repair area.

[0021] S300, based on the location of the damaged area and the amount of damage to the edge parts, selects repair solutions;

[0022] S400, if the currently damaged area is not related to surrounding components, the repair area is determined based on the amount of damage to the damaged area;

[0023] S500 verifies the repair area and location for each repair and determines the overlap rate between the weld bead and the actual repair area; based on the overlap rate between the weld bead and the actual repair area, evaluates the repair plan and determines the evaluated repair plan.

[0024] First, the damaged area is identified using laser scanning and image recognition to determine its location and coverage. It also checks if the damaged area is related to surrounding components. If so, the edge of the corresponding area on the surrounding components is identified, and the extent of damage to that edge is determined. Based on the damage amount, the area requiring repair is determined, and a repair plan is selected. When selecting a repair plan, the welding torch's movement trajectory and the number of weld layers are determined based on the wear and location during repair. If the damaged area is not related to surrounding components, the repair area is determined based on the extent of damage.

[0025] In step S100, by identifying the image information of the damaged area, the location, coverage and shape of the damaged area are identified from the image information. At this time, the identified location needs to represent the coordinate position of the repair area relative to the machine, and the coverage is used to identify whether there is a correlation within the current damaged area.

[0026] Preferably, in step S200, the correlation between the damaged area and the surrounding components is expressed as follows: by identifying the number of grinding parts set in the damaged area, if the number of identified grinding parts is not unique, it indicates that there are associated surrounding components in the damaged area. At the same time, it is necessary to quantify the degree of damage, determine the characteristic values ​​of the damaged area and the surrounding components, and determine the correlation between the damaged area and the surrounding components based on the Pearson correlation coefficient of the characteristic values ​​of the damaged area and the surrounding components.

[0027] For the calculation of the Pearson correlation coefficient, the relationship between the damaged area and the surrounding components is quantified by calculating the distance between the pixels at the edge of the damaged area and the surrounding components. A set of pixels located in the damaged area and the surrounding components with the obtained distance values ​​are used as variables. The mean, covariance and standard deviation of the variables are calculated. Based on the mean, covariance and standard deviation, the Pearson correlation coefficient of the feature values ​​of the damaged area and the surrounding components is calculated. According to the calculated value, if the value is greater than 0, it indicates that there is a correlation between the damaged area and the surrounding components. If it is less than 0, it is considered that there is no correlation between the two.

[0028] The damage amount of the edge part is calculated by taking the minimum area of ​​the entire region that can be repaired as the current damage amount of the edge part. The damage amount is obtained by comparing the image of the original part with the image of the current wear, comparing the pixels in the image, and taking the area of ​​the image points after comparison as the current identified damage amount.

[0029] The total area that needs to be repaired can be obtained by summing the total amount of damage.

[0030] The implementation of the corresponding repair scheme in step S300 includes: based on the repair scheme, determining the moving trajectory and number of weld layers of the welding torch, determining the forward and backward distances of the welding torch, and the maximum distance that can be moved each time; setting the number of weld layers to ensure that the weld shape meets the process requirements.

[0031] When setting the movement trajectory of the welding torch, it is necessary to determine the forward and backward distance of the welding torch, as well as the maximum distance that can be moved each time. The shape, width and height of the weld bead, and the number of weld layers corresponding to each welding operation are determined through image recognition and laser scanning.

[0032] Setting the number of weld overlay layers also includes selecting the starting position for weld overlay repair, setting the forward or backward distance of the welding torch for each round of welding to be 3-4.8mm and the maximum distance to be 4.8mm, setting the number of weld overlay layers, and according to the weld overlay process requirements, the weld bead shape should be a narrow weld bead with a width of 10-12mm and a height of 2-3mm, and the subsequent weld bead of the same weld layer should cover 30%-40% of the previous weld bead.

[0033] The step S300 of determining the screening scheme includes: after determining the damaged area, determining the welding parameters during the overlay welding, using the current damage amount and location as input, screening out the repair schemes corresponding to the damage amount and location, and determining the overlay welding parameters in the repair scheme, including determining the wire extension length, wire feeding speed, deposited metal amount, and welding line speed.

[0034] Preferably, the welding parameters are set according to the welding process requirements, including a wire extension length of 20-35mm, a wire feeding speed of 3.5-6.0m / min, a deposited metal of 5-8KG / hour, and a welding line speed of 1000-1600mm / min, with the optimal control at 1200mm / min.

[0035] Wire feeding speed V f The calculation can be derived based on the amount of deposited metal and the welding line speed:

[0036]

[0037] Where M is the amount of metal deposited per unit time, η is the deposition efficiency, B is the cross-sectional area of ​​the welding wire, and w is the welding line speed.

[0038] The screening of repair solutions also includes searching for repair solutions based on the wire extension length and wire feeding speed, and determining the first similarity between the wire extension length, wire feeding speed and the repair solution.

[0039] Based on the amount of deposited metal and the welding line speed, the repair schemes are searched to determine the second similarity in terms of the amount of deposited metal, the welding line speed and the repair scheme.

[0040] Based on the first and second similarity scores, the final repair scheme is determined.

[0041] The first similarity is:

[0042]

[0043] Where d(l,v) is the first similarity, l i It is the extension length of the i-th welding wire, v i It is the i-th wire feeding speed. This is the standard value for the extension length of the welding wire. It is the standard value for wire feeding speed.

[0044] The scheme with the closest historical data points in terms of wire extension length and wire feed speed is selected as the scheme with the highest similarity.

[0045] The second similarity is represented as:

[0046]

[0047] Where d(M,w) is the second similarity, M i It is the amount of the i-th deposited metal, w i It is the i-th welding line speed. This is the standard value for the amount of deposited metal. This is the standard value for wiring speed.

[0048] The second similarity is the same as the first similarity. The second similarity is the scheme that is closest to the standard values ​​of the wire extension length and the wire feeding speed.

[0049] The final repair solution is determined based on the average of the first similarity and the second similarity. The average of the first similarity and the second similarity is weighted and averaged. The repair solution corresponding to the weighted average is taken as the repair solution to be implemented.

[0050] In step S500, based on the actual repair area and location determined for each repair, the repair amount at the corresponding location is obtained, and the overlap rate between the weld and the actual repair area is determined according to the repair amount at the corresponding location; based on the overlap rate between the weld and the actual repair area, the location and overlapping area between the overlapping boundaries are identified, and the current repair location and repair amount are determined to be correct.

[0051] Using a laser scanner, the actual repair area can be calculated through image processing algorithms, which typically involves pixel counting or contour detection, and then converted into physical dimensions.

[0052] The repair area for each repair is represented as follows:

[0053]

[0054] Where, ΔA i A is the physical area corresponding to each damaged region in the image, and A is the actual repaired area.

[0055] The overlap rate O between the weld bead and the actual repair area is calculated based on the width of the weld bead and the distance between adjacent weld beads:

[0056]

[0057] Where W is the weld width and d is the distance between adjacent welds.

[0058] The location and overlapping area between overlapping boundaries are used to assess the accuracy of the current repair location by obtaining the weld overlap rate. Simultaneously, the weld overlap rate (CR) can be used to assess the fit between the weld and the intended repair area.

[0059]

[0060] Among them, A overlap It is the overlapping area of ​​the weld and the repair area, A total It is the total area of ​​the repaired area.

[0061] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for online repair of grinding parts in a medium-speed coal mill, characterized in that, include: S100: Acquire image information of the damaged area to determine the location and coverage of the damaged area; S200, determine whether the damaged area is related to surrounding components within the coverage area of ​​the damaged area. If the current damaged area is related to surrounding components, determine the edge portion of the damaged area and assess the amount of damage to the edge portion. Determine the required repair area based on the amount of damage at the edges; S300, based on the location of the damaged area and the amount of damage to the edge parts, selects repair solutions; S400, if the currently damaged area is not related to surrounding components, the area to be repaired is determined based on the amount of damage to the damaged area; S500 verifies the repair area and location for each repair and determines the overlap rate between the weld bead and the actual repair area; based on the overlap rate between the weld bead and the actual repair area, evaluates the repair plan and determines the evaluated repair plan. In step S200, the correlation between the damaged area and the surrounding components is represented by identifying the number of grinding parts set in the damaged area. If the number of grinding parts identified is not unique, it indicates that there are associated surrounding components in the damaged area. At the same time, it is necessary to quantify the degree of damage, determine the characteristic values ​​of the damaged area and the surrounding components, and determine the correlation between the damaged area and the surrounding components based on the Pearson correlation coefficient of the characteristic values ​​of the damaged area and the surrounding components. For the calculation of the Pearson correlation coefficient, the relationship between the damaged area and the surrounding components is quantified by calculating the distance between the pixels at the edge of the damaged area and the surrounding components. A set of pixels located in the damaged area and the surrounding components with the obtained distance values ​​are used as variables. The mean, covariance and standard deviation of the variables are calculated. Based on the mean, covariance and standard deviation, the Pearson correlation coefficient of the feature values ​​of the damaged area and the surrounding components is calculated. According to the calculated value, if the value is greater than 0, it indicates that there is a correlation between the damaged area and the surrounding components. If it is less than 0, it is considered that there is no correlation between the two.

2. The online repair method for grinding parts of a medium-speed coal mill as described in claim 1, characterized in that, The implementation of the corresponding repair scheme in step S300 includes: based on the repair scheme, determining the moving trajectory and number of weld layers of the welding torch, determining the forward and backward distances of the welding torch, and the maximum distance that can be moved each time; setting the number of weld layers to ensure that the weld shape meets the process requirements.

3. The online repair method for grinding parts of a medium-speed coal mill as described in claim 2, characterized in that, Determining the movement trajectory of the welding torch includes determining the forward and backward distances of the welding torch, the maximum distance that can be moved each time, the shape, width and height of the weld bead, and the number of weld layers corresponding to each welding operation.

4. The online repair method for grinding parts of a medium-speed coal mill as described in claim 3, characterized in that, Setting the number of weld overlay layers also includes selecting the starting position of the weld overlay repair, setting the forward or backward distance of the welding torch for each round of welding to be 3-4.8mm and the maximum distance to be 4.8mm, and the weld shape should be a narrow weld bead with a width of 10-12mm and a height of 2-3mm. The subsequent weld bead of the same weld layer should cover 30%-40% of the previous weld bead.

5. The online repair method for grinding parts of a medium-speed coal mill as described in claim 1, characterized in that, Using the current damage amount and location as input, the system filters out the repair solutions corresponding to the damage amount and location, and determines the welding parameters in the repair solution, including the wire extension length, wire feed speed, amount of deposited metal, and welding line speed.

6. The online repair method for grinding parts of a medium-speed coal mill as described in claim 5, characterized in that, The welding parameters include a wire extension length of 20-35mm, a wire feed speed of 3.5-6.0m / min, a deposited metal of 5-8KG / hour, and a welding line speed of 1000-1600mm / min, with the optimal control at 1200mm / min.

7. The online repair method for grinding parts of a medium-speed coal mill as described in claim 5, characterized in that, The screening of repair solutions also includes searching for repair solutions based on the wire extension length and wire feeding speed, and determining the first similarity between the wire extension length, wire feeding speed and the repair solution; Based on the amount of deposited metal and the welding line speed, the repair schemes are searched to determine the second similarity regarding the amount of deposited metal, the welding line speed and the repair scheme; Based on the first and second similarity scores, the final repair scheme is determined.

8. The online repair method for grinding parts of a medium-speed coal mill as described in claim 1, characterized in that, The repair area for each repair is represented as follows: ； in, It is the physical area corresponding to each damaged region in the image. This is the actual area repaired.

9. The online repair method for grinding parts of a medium-speed coal mill as described in claim 1, characterized in that, Overlap rate between weld bead and actual repair area The calculation is based on the width of the weld bead and the distance between adjacent weld beads: ； in, It is the weld width. It is the distance between adjacent weld beads.

10. The online repair method for grinding parts of a medium-speed coal mill as described in claim 1, characterized in that, Step S500 also includes identifying the position and overlapping area between the overlapping boundaries based on the overlap rate between the weld and the actual repair area, and determining that the current repair position and repair amount are correct. The location and overlapping area between the overlapping boundaries are used to assess the accuracy of the current repair location by obtaining the weld overlap rate. Represented as: ; in, It is the overlapping area of ​​the weld and the repair area. It is the total area of ​​the repaired area.

Images