A tool life prediction and maintenance method based on big data

Through big data analysis and three-dimensional reconstruction equipment, the problem of wear tools cannot be accurately predicted in the existing technology, and the production line prediction and regular maintenance are realized, production efficiency is improved and cost is reduced. .

CN114764231BActive Publication Date: 2024-11-22TSINGHTECH
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202210160323.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-22
Publication Date
2024-11-22
Estimated Expiration
2042-02-22

AI Technical Summary

Technical Problem

The prior art cannot accurately predict the wear degree of recycling tools and abnormal production line, resulting in production line paralysis and unqualified workpieces, making production efficiency and cost difficult to guarantee.

Method used

Using a big data-based method, data collection and reconstruction of wear tools is collected and rebuilt through three-dimensional reconstruction equipment, combined with database comparison, the wear position, degree and usage duration are determined, and the backtracking threshold is set for production line backtracking and life prediction, and maintenance is carried out in a timely manner.

Benefits of technology

Accurate judgment of tool wear and prediction of production line abnormalities is achieved, avoiding production line paralysis and workpiece failure, reducing production costs and improving production efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114764231B_ABST
    Figure CN114764231B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of recycling tool detection, and discloses a tool life prediction and maintenance method based on big data, including data collection of worn tools, determination of evaluation criteria for worn tools, backtracking of similar production lines where worn tools are located, life prediction of worn tools, and maintenance of similar production lines where worn tools are located, wherein the maintenance of similar production lines where worn tools are located: production line backtracking and life prediction of worn tools, judging whether the production line is in abnormal production, and timely regular maintenance of the production line. By comparing the total standard value and the single standard value with the backtracking threshold value respectively, if the total standard value is within the backtracking threshold range and the single standard value is not within the backtracking threshold range, it can be regarded as abnormal tool wear, and then check whether the production line is operating normally. If there is a slight abnormality, the production line is inspected and maintained in advance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of tool recovery detection, and in particular to a tool life prediction and maintenance method based on big data. Background Art

[0002] With the rapid development of economy and the improvement of people's living standards, the manufacturing industry plays an increasingly important role. At this stage, many manufacturing enterprises have optimized the production process from aspects such as cost saving, efficiency improvement and quality assurance through some digital and information means, among which the rational use of spare parts is one of the important links.

[0003] As the final executor of the machining process, the status of the tool directly affects the machining efficiency, cost, energy consumption and workpiece quality. Therefore, it is necessary to evaluate the service life of the tool, use the tool reasonably, eliminate production line abnormalities, fundamentally guarantee production efficiency and workpiece quality, and reduce production costs to a certain extent; Currently, there is no corresponding digital technology for judging the wear degree of recycled tools. It is mainly judged by staff based on past experience. Since there are certain differences in the judgment standards of different staff, the judgment results have greater uncertainty, and there are also certain differences in the judgment of production line abnormalities.

[0004] As for the recycled tools, they are replaced from the production line after being worn to different degrees. Generally, the staff will not observe them carefully unless the wear condition is significantly different from usual. Different staff members have different criteria for judging the wear condition of the tools, so there are also some differences in the judgment of abnormal conditions, and it is impossible to accurately predict whether the production line is abnormal.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the shortcomings of the prior art, the present invention provides a tool life prediction and maintenance method based on big data, which performs big data analysis on the wear status of tools recycled after use, determines whether the degree of tool wear is normal, traces back the production line for tools with abnormal wear, and finds out possible problems with the production line in advance, thereby avoiding the paralysis of the production line due to long-term accumulation of problems, and realizes the advantages of prediction and regular maintenance of abnormal parts of the production line, etc., and solves the problem that the tool life and production line abnormalities cannot be accurately predicted, resulting in the paralysis of the production line and the need to re-use materials for production, thereby reducing production efficiency.

[0008] (II) Technical solution

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions: a tool life prediction and maintenance method based on big data, comprising the following steps:

[0010] S1: Data collection of worn tools: Obtain the three-dimensional appearance of multiple groups of worn tools through video, reconstruct the three-dimensional model of the worn tools, and compare it with the database;

[0011] S2: Determine the evaluation criteria for the worn tool: Based on the image data of the six surfaces of the worn tool, output the standard values ​​of the worn position, wear degree and usage time of the worn tool;

[0012] S3: Backtracking of the same production line where the worn tool is located: set a backtracking threshold and compare the standard value for determination of judgment with the backtracking threshold;

[0013] According to the production line and location information registered when the worn tool is recovered, the production line where the worn tool is located can be traced back;

[0014] S4: Life prediction of worn tools: Based on the wear condition of the recovered worn tools, whether it is normal or not, and the backtracking of the production line, the life prediction of other tools at the same position on the same production line can be carried out;

[0015] S5: Maintenance of similar production lines where worn tools are located: By tracing back the production lines and predicting the life of worn tools, it is determined whether the production line is in abnormal production, and regular maintenance of the production line is carried out in a timely manner.

[0016] Preferably, the three-dimensional reconstruction device performs three-dimensional reconstruction on the worn tool to form a three-dimensional surface model of the real tool, and the database stores three-dimensional data of the factory standard model.

[0017] Preferably, the usage time is the actual usage time of the worn tool calculated based on the time the worn tool is put into use after being taken out of the warehouse and the time it is recovered after use; the wear position is the distance between each tool tip and the center position of the worn tool; and the wear degree is the average value of the distance between all tool tips and the center position of the worn tool.

[0018] Preferably, the evaluation criteria include an overall standard value and a single standard value, the overall standard value is the standard value of the time the worn tool is used and the degree of wear; the single standard value is the standard value of the time the worn tool is used and the minimum distance between the wear position.

[0019] Preferably, the production line backtracking compares the overall standard value with the backtracking threshold to determine whether the overall standard value is within the backtracking threshold, and compares the single standard value with the backtracking threshold to determine whether the single standard value is within the backtracking threshold.

[0020] Preferably, the life of worn tools is predicted based on the production line backtracking: when the overall standard value is within the backtracking threshold and the single standard value is also within the backtracking threshold, the service life of other tools at the same position on the same production line is further determined.

[0021] Preferably, the production line is inspected and maintained according to the production line backtracking: when the overall standard value is within the backtracking threshold and the single standard value is not within the backtracking threshold, it is determined that there is a problem in the operation of the production line where the tool is located.

[0022] Preferably, a 3D reconstruction device is used, which is used to obtain a 3D image of the worn tool and compare the 3D data with the factory standard model stored in the database; the 3D reconstruction device includes a 3D photography mechanism, a conveying mechanism, an imaging mechanism and a data analysis mechanism;

[0023] When executing the step S1, the worn tool is transported forward by the transport mechanism and transported to the three-dimensional photography mechanism to obtain multiple sets of three-dimensional images of the worn tool;

[0024] When executing the S2 step, the imaging mechanism performs three-dimensional reconstruction of the worn tool on the acquired multiple sets of three-dimensional images to determine the wear position and degree of wear of the tool; and cooperates with the data analysis mechanism to analyze and compare the three-dimensionally reconstructed worn tool with the database to form an overall standard value and a single standard value of the worn tool.

[0025] Preferably, the three-dimensional photography mechanism comprises a stepping track, a camera and a support frame, the stepping track is supported by the support frame, a stepping driving assembly is arranged outside the stepping track, the stepping driving assembly is used to drive the stepping track, and the cameras are respectively installed on the periphery of the stepping track and on the upper and lower sides of the support frame;

[0026] The conveying mechanism comprises a conveying plate, and the conveying plate is made of a hard transparent material.

[0027] Preferably, the imaging mechanism includes a multispectral imaging camera; the data analysis mechanism includes a computer, the computer combines multiple groups of three-dimensional images acquired by the camera; and distributes them to the multispectral imaging camera, thereby completing the three-dimensional reconstruction of the worn tool.

[0028] (III) Beneficial effects

[0029] Compared with the prior art, the present invention provides a tool life prediction and maintenance method based on big data, which has the following beneficial effects:

[0030] 1. This tool life prediction and maintenance method based on big data reconstructs the worn tool in three dimensions through three-dimensional reconstruction equipment, and compares it with the three-dimensional data of the factory standard model stored in the database to determine the normal wear of the tool, predict the service life of the tool under normal conditions, and trace the production line of tools with abnormal wear, or find out the possible problems of the production line in advance if the tool wear is abnormal, so as to avoid the paralysis of the production line due to the long-term accumulation of problems, and realize the prediction of the abnormal part of the production line and regular maintenance; predict the tool life and production line abnormalities to avoid the re-production of unqualified workpieces caused by the paralysis of the production line, thereby reducing production efficiency.

[0031] 2. This tool life prediction and maintenance method based on big data compares the total standard value and the single standard value with the backtracking threshold respectively. If the total standard value and the single standard value are both within the backtracking threshold range, they can be regarded as normal wear. Then, the tool life of other tools at the same position on the same production line can be predicted. When the tool at the same position on other tools on the same production line is close to the measured service life of the worn tool, the tool wear condition of tools at the same position on other tools on the same production line can be detected in advance, or new tools can be replaced in advance.

[0032] 3. This tool life prediction and maintenance method based on big data compares the total standard value and the single standard value with the backtracking threshold respectively. If the total standard value is within the backtracking threshold range and the single standard value is not within the backtracking threshold range, it can be regarded as abnormal tool wear. Then, check whether the production line is operating normally. If there is any abnormality, inspect and maintain the production line in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a flow chart of the method of the present invention;

[0034] Figure 2 The flowchart of the life detection and judgment of the worn tool of the present invention is as follows;

[0035] Figure 3 This is a maintenance judgment flow chart of the same production line where the worn tool of the present invention is located;

[0036] Figure 4 This is one of the overall structural schematic diagrams of the three-dimensional reconstruction device of the present invention;

[0037] Figure 5 This is the second schematic diagram of the overall structure of the three-dimensional reconstruction device of the present invention;

[0038] Figure 6 It is a schematic diagram of the three-dimensional structure of the three-dimensional photography mechanism of the present invention.

[0039] In the figure: 1. 3D photography mechanism; 11. stepping track; 12. camera; 13. support frame; 14. stepping drive assembly; 2. conveying mechanism; 21. conveying plate; 3. imaging mechanism; 31. multi-spectral imaging camera; 4. data analysis mechanism; 41. computer. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] As introduced in the background technology, there are deficiencies in the prior art. In order to solve the above technical problems, this application proposes a tool life prediction and maintenance method based on big data.

[0042] See also Figure 1-6 , a tool life prediction and maintenance method based on big data, comprising the following steps:

[0043] S1: Data collection of worn tools: Obtain the three-dimensional appearance of multiple groups of worn tools through video, reconstruct the three-dimensional model of the worn tools, and compare it with the database;

[0044] S2: Determine the evaluation criteria for the worn tool: Based on the image data of the six surfaces of the worn tool, output the standard values ​​of the worn position, wear degree and usage time of the worn tool;

[0045] S3: Backtracking of the same production line where the worn tool is located: set a backtracking threshold and compare the standard value for determination of judgment with the backtracking threshold;

[0046] According to the production line and location information registered when the worn tool is recovered, the production line where the worn tool is located can be traced back;

[0047] S4: Life prediction of worn tools: Based on the wear condition of the recovered worn tools, whether it is normal or not, and the backtracking of the production line, the life prediction of other tools at the same position on the same production line can be carried out;

[0048] S5: Maintenance of similar production lines where worn tools are located: By tracing back the production lines and predicting the life of worn tools, it is determined whether the production line is in abnormal production, and regular maintenance of the production line is carried out in a timely manner.

[0049] The worn tools are reconstructed in three dimensions through three-dimensional reconstruction equipment and compared with the three-dimensional data of the factory standard model stored in the database to determine the normal wear of the tools and predict the service life of the tools under normal conditions. The production line of tools with abnormal wear can be traced back, or if the tool wear is abnormal, possible problems with the production line can be found in advance, so as to avoid the paralysis of the production line due to the long-term accumulation of problems, and realize the prediction of abnormal parts of the production line and regular maintenance.

[0050] Furthermore, the 3D reconstruction equipment reconstructs the worn tool in 3D to form a 3D surface model of the real tool. The database stores the 3D data of the factory standard model. The worn tool is photographed from different viewpoints from multiple angles to obtain multiple groups of 3D images, and the tool is reconstructed in 3D to form a 3D surface model of the real tool. The 3D data is then compared with the factory standard model stored in the database, and the difference between the two is the wear condition.

[0051] Furthermore, the usage time is the actual usage time of the worn tool calculated based on the time the worn tool is put into use after being released from the warehouse and the time it is recovered after use; the wear position is the distance between each tool tip and the center position of the worn tool; the wear degree is the average value of the distance between all tool tips and the center position of the worn tool. By performing three-dimensional reconstruction on the collected worn tool data, the three-dimensional model of the worn tool is compared with the standard tool to determine the wear position and wear degree of the tool.

[0052] Furthermore, the evaluation criteria include overall standard values ​​and single standard values. The overall standard value is the standard value of the usage time and wear degree of the worn tool; the single standard value is the standard value of the usage time and the minimum distance between the wear position of the worn tool. A certain amount of data is collected, such as 10,000 groups, in which the images of six surfaces of a tool are a group; the usage time is compared with the wear position and the wear degree, all the data are analyzed and compared, and the data with large deviation are removed. The screened results are regressed and fitted. The fitted values ​​are used as the standard values ​​of the usage time, wear position and wear degree of each type of tool under normal circumstances, which are used as the evaluation criteria for whether the tool is normally worn.

[0053] Furthermore, the production line backtracking compares the overall standard value with the backtracking threshold to determine whether the overall standard value is within the backtracking threshold, and compares the single standard value with the backtracking threshold to determine whether the single standard value is within the backtracking threshold. After calculating the judgment standard for tool wear, it is compared with the backtracking threshold to determine whether the recovered tool is within the backtracking threshold range. Based on the production line and position information registered when the tool is recovered, the production line where the abnormal tool is located can be traced back to determine whether the production line is abnormal.

[0054] Furthermore, the life of worn tools is predicted based on production line backtracking: when the overall standard value is within the backtracking threshold and the single standard value is also within the backtracking threshold, the service life of tools at the same position on other same production lines is further judged. By comparing the total standard value and the single standard value with the backtracking threshold respectively, if both the total standard value and the single standard value are within the backtracking threshold range, they can be regarded as normal wear, and then the service life of tools at the same position on other same production lines can be predicted. When the tools at the same position on other same production lines are close to the measured service life of the worn tool, the wear conditions of tools at the same position on other same production lines can be detected in advance, or new tools can be replaced in advance.

[0055] Furthermore, the production line is inspected and maintained based on the production line backtracking: when the overall standard value is within the backtracking threshold and the single standard value is not within the backtracking threshold, it is judged that there is a problem with the operation of the production line where the tool is located. By comparing the overall standard value and the single standard value with the backtracking threshold respectively, if the overall standard value is within the backtracking threshold range and the single standard value is not within the backtracking threshold range, it can be regarded as abnormal tool wear. Then check whether the production line is operating normally. If there is a slight abnormality, the production line is inspected and maintained in advance.

[0056] When the total standard value is within the backtracking threshold, but a single standard value is not within the backtracking threshold, it means that at least one tool tip of the tool is more worn than other tool tips, indicating that the tool is operating abnormally in the production line and the production line should be inspected and maintained in time.

[0057] Furthermore, a 3D reconstruction device is used to obtain a 3D image of the worn tool and compare the 3D data with the factory standard model stored in the database; the 3D reconstruction device includes a 3D photography mechanism 1, a conveying mechanism 2, an imaging mechanism 3 and a data analysis mechanism 4;

[0058] When executing step S1, the worn tool is transported forward by the transport mechanism 2 and transported to the three-dimensional photography mechanism 1 to obtain multiple sets of three-dimensional images of the worn tool;

[0059] When executing step S2, the imaging mechanism 3 performs three-dimensional reconstruction of the worn tool on the acquired multiple sets of three-dimensional images to determine the wear position and degree of wear of the tool; and cooperates with the data analysis mechanism 4 to analyze and compare the three-dimensionally reconstructed worn tool with the database to form an overall standard value and a single standard value of the worn tool.

[0060] Furthermore, the three-dimensional photography mechanism 1 includes a stepping track 11, a camera 12 and a support frame 13. The stepping track 11 is supported by the support frame 13. A stepping driving assembly 14 is arranged outside the stepping track 11. The stepping driving assembly 14 is used to drive the stepping track 11. The camera 12 is respectively installed on the side of the stepping track 11 and on the upper and lower sides of the support frame 13.

[0061] The conveying mechanism 2 includes a conveying plate 21, and the conveying plate 21 is made of a hard transparent material;

[0062] The stepping track 11 is driven to rotate step by step by the stepping driving assembly 14, so that the camera 12 on the stepping track 11 cooperates with the cameras 12 on the upper and lower sides of the support frame 13 to shoot the worn tool at multiple angles to obtain multiple sets of three-dimensional images.

[0063] Furthermore, the imaging mechanism 3 includes a multispectral imaging camera 31, a multispectral imaging camera 31; the data analysis mechanism 4 includes a computer 41, the computer 41 combines multiple groups of three-dimensional images acquired by the camera 12; and distributes them to the multispectral imaging camera 31, thereby completing the three-dimensional reconstruction of the worn tool; a certain amount of data is collected by the computer 41, such as 10,000 groups, in which the images of six surfaces of a tool are one group; and then the imaging mechanism 3 is used to reconstruct each group of three-dimensional images, and the data analysis mechanism 4 analyzes and compares all the data, removes the data with large deviation, and then performs regression fitting on the screened results.

[0064] Working principle: First, the recovered worn tools are placed on the transparent conveying plate 21 of the conveying mechanism 2, and the conveying mechanism 2 conveys the recovered tools to the three-dimensional photography mechanism 1 for shooting to obtain multiple sets of three-dimensional images;

[0065] The stepping track 11 is driven to rotate step by step by the stepping driving assembly 14, so that the camera 12 on the stepping track 11 cooperates with the cameras 12 on the upper and lower sides of the support frame 13 to shoot the worn tool at multiple angles, obtain multiple sets of three-dimensional images, and process them by the computer 41;

[0066] A certain amount of data, such as 10,000 groups, is collected by a computer 41, where the images of the six surfaces of a tool are one group; the imaging mechanism 3 performs three-dimensional reconstruction on each group of three-dimensional images, and the data analysis mechanism 4 analyzes and compares all the data, removes the data with a large deviation, and then performs regression fitting on the screened results, performs three-dimensional reconstruction on the collected worn tool data, and compares the three-dimensional model of the worn tool with the standard tool to determine the wear position and wear degree of the tool. The fitted values ​​are used as the standard values ​​of the use time, wear position and wear degree of each type of tool under normal conditions, and are used as the criterion for judging whether the tool is normally worn;

[0067] After calculating the evaluation criteria for tool wear, the tool is compared with the backtracking threshold to determine whether the recovered tool is within the backtracking threshold range. Based on the production line and location information registered when the tool is recovered, the production line where the abnormal tool is located can be backtracked to determine whether the production line is abnormal.

[0068] Among them, first, the total standard value and the single standard value are compared with the backtracking threshold value respectively. If both the total standard value and the single standard value are within the backtracking threshold value range, they can be regarded as normal wear, and then the service life of the tools at the same position of other same production lines can be predicted. When the tools at the same position of other same production lines are close to the service life measured by the worn tool, the wear of the tools at the same position of other same production lines can be detected in advance, or new tools can be replaced in advance;

[0069] 2. The total standard value and the single standard value are compared with the backtracking threshold value respectively. If the total standard value is within the backtracking threshold range, and the single standard value is not within the backtracking threshold range, it can be regarded as abnormal tool wear. Then check whether the production line is operating normally. If there is any abnormality, inspect and maintain the production line in advance.

[0070] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A tool life prediction and maintenance method based on big data, characterized in that: The following steps are involved: S1: Data collection of worn tools: Obtain the three-dimensional appearance of multiple groups of worn tools through video, reconstruct the three-dimensional model of the worn tools, and compare it with the database; S2: Determine the evaluation criteria for the worn tool: Based on the image data of the six surfaces of the worn tool, output the standard values ​​of the worn position, wear degree and usage time of the worn tool; S3: Backtracking of the same production line where the worn tool is located: set a backtracking threshold and compare the standard value for determination of judgment with the backtracking threshold; According to the production line and location information registered when the worn tool is recovered, the production line where the worn tool is located can be traced back; S4: Life prediction of worn tools: Based on the wear condition of the recovered worn tools, whether it is normal or not, and the backtracking of the production line, the life prediction of other tools at the same position on the same production line can be carried out; S5: Maintenance of similar production lines where worn tools are located: By tracing back the production lines and predicting the life of worn tools, it is determined whether the production line is in abnormal production, and regular maintenance of the production line is carried out in a timely manner; The usage time is the actual usage time of the worn tool calculated based on the time when the worn tool was taken out of the warehouse and put into use and the time when it was recovered after use; the wear position is the distance between each tool tip and the center position of the worn tool; the wear degree is the average value of the distance between all tool tips and the center position of the worn tool; The evaluation criteria include an overall standard value and a single standard value, wherein the overall standard value is the standard value of the length of time the worn tool is used and the degree of wear; The single standard value is the standard value of the time the wear tool is used and the minimum distance of the wear position; The production line backtracking compares the overall standard value with the backtracking threshold to determine whether the overall standard value is within the backtracking threshold, and compares the single standard value with the backtracking threshold to determine whether the single standard value is within the backtracking threshold; The production line is inspected and maintained according to the production line backtracking: when the overall standard value is within the backtracking threshold and the single standard value is not within the backtracking threshold, it is determined that there is a problem in the operation of the production line where the tool is located; otherwise, no judgment is made.

2. The tool life prediction and maintenance method based on big data according to claim 1, characterized in that: The three-dimensional reconstruction device performs three-dimensional reconstruction on the worn tool to form a three-dimensional surface model of the real tool, and the database stores the three-dimensional data of the factory standard model.

3. The tool life prediction and maintenance method based on big data according to claim 1 is characterized in that: The life of worn tools is predicted based on the production line backtracking: when the overall standard value is within the backtracking threshold and the single standard value is also within the backtracking threshold, the service life of other tools at the same position on the same production line is judged; otherwise, no judgment is made.

4. The tool life prediction and maintenance method based on big data according to claim 1 is characterized in that: A three-dimensional reconstruction device is used, which is used to obtain a three-dimensional image of a worn tool and compare the three-dimensional data with a factory standard model stored in a database; the three-dimensional reconstruction device comprises a three-dimensional photography mechanism (1), a conveying mechanism (2), an imaging mechanism (3) and a data analysis mechanism (4); When executing step S1, the worn tool is transported forward by the transport mechanism (2) and transported to the three-dimensional photography mechanism (1) to obtain multiple sets of three-dimensional images of the worn tool; When executing the step S2, the imaging mechanism (3) performs three-dimensional reconstruction of the worn tool on the acquired multiple sets of three-dimensional images to determine the wear position and degree of wear of the tool; and cooperates with the data analysis mechanism (4) to analyze and compare the three-dimensionally reconstructed worn tool with the database to form an overall standard value and a single standard value of the worn tool.

5. The tool life prediction and maintenance method based on big data according to claim 4 is characterized in that: The three-dimensional photography mechanism (1) comprises a stepping track (11), a camera (12) and a support frame (13); the stepping track (11) is supported by the support frame (13); a stepping driving assembly (14) is arranged outside the stepping track (11); the stepping driving assembly (14) is used to drive the stepping track (11); the camera (12) is respectively mounted on the peripheral side of the stepping track (11) and on the upper and lower sides of the support frame (13); The conveying mechanism (2) comprises a conveying plate (21), and the conveying plate (21) is made of a hard transparent material.

6. The tool life prediction and maintenance method based on big data according to claim 5 is characterized in that: The imaging mechanism (3) includes a multispectral imaging camera (31); the multispectral imaging camera (31); the data analysis mechanism (4) includes a computer (41); the computer (41) combines multiple groups of three-dimensional images acquired by the camera (12); and distributes the images to the multispectral imaging camera (31), thereby completing the three-dimensional reconstruction of the worn tool.

Citation Information

Cited By

  • Cutter life prediction method based on fusion model

    CN117272803A