Steel bar machining control system based on digital production

Abstract

The invention relates to the technical field of reinforcing steel bar cutting, and particularly discloses a reinforcing steel bar processing control system based on digital production, comprising: an initial module for setting a time node; setting an initial speed, and obtaining an initial sequence; the calibration module is used for cutting the reinforcing steel bars at the initial speed V1; after cutting is completed, cutting scores are calculated, and coordinate points are generated; obtaining a new initial sequence, generating new coordinate points, and fitting the coordinate points to obtain a fitted curve; substituting the cutting score threshold into the fitted curve to obtain first speeds, and recording the maximum first speed as a theoretical speed; and the control module is used for acquiring the actual time length, calculating a time difference value and determining a theoretical speed VDY based on the time difference value. The cutting efficiency can be prevented from being reduced while the steel bar notch quality can be ensured.

Description

Technical Field

[0001] The invention relates to the technical field of steel bar cutting, and in particular to a steel bar processing control system based on digital production. Background Art

[0002] In the field of construction, steel bars are one of the key materials to ensure the strength and stability of building structures, and play a vital role in the safety and durability of buildings. During the construction process, steel bars need to be processed, such as cutting them into appropriate lengths to meet specific construction design and construction requirements.

[0003] Mechanical cutting is efficient and accurate. It can quickly and accurately cut steel bars according to the predetermined length through professional cutting equipment. Specifically, after starting the cutting equipment, the cutter starts to rotate under the drive of the power, and then the steel bar is fed into the cutting port and cut by the rotating cutter. In this process, the cutting speed of the steel bar needs to be controlled. A faster cutting speed may cause the steel bar cut to be uneven and have burrs, while a slower cutting speed will result in a slower steel bar processing speed. Therefore, how to determine a reasonable cutting speed has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide a steel bar processing control system based on digital production to solve the following technical problems:

[0005] Mechanical cutting is efficient and accurate. It can cut steel bars quickly and accurately according to the predetermined length through professional cutting equipment. Specifically, after starting the cutting equipment, the cutter starts to rotate under the drive of the power, and then the steel bars are fed into the cutting port and cut by the rotating cutter. In this process, the cutting speed of the steel bars needs to be controlled. A faster cutting speed may cause the steel bar cut to be uneven and have burrs, while a slower cutting speed will result in a slower steel bar processing speed.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A steel bar processing control system based on digital production, comprising:

[0008] Initial module: setting a tool usage time interval [0, t], where t represents the design life of the tool, and setting a number of time nodes within the usage time interval at preset usage time intervals;

[0009] Setting a steel bar cutting speed interval [v1, v2], selecting a number of cutting speeds as initial speeds within the cutting speed interval at a preset cutting speed interval, and sorting the initial speeds in descending order to obtain an initial sort;

[0010] Calibration module: obtaining the usage time Ta corresponding to the time node a, obtaining a tool with a usage time Ta, recorded as tool DTa, obtaining the initial speed V1 at the first position in the initial sorting, maintaining the cutting speed at the initial speed V1, and cutting the steel bar by the tool DTa;

[0011] After the steel bar cutting is completed, an image of the front of the steel bar cut is collected, and the density p of the burrs at the steel bar cut is obtained based on the image, then the cutting score P=η / p, and a coordinate point (V1, P) is generated in the coordinate system, where η is a preset correction coefficient;

[0012] Remove the first initial speed V1 from the initial sorting to obtain a new initial sorting, repeat the above steps to generate new coordinate points until the number of coordinate points reaches a preset number, fit the coordinate points to obtain a fitting curve f(x), where x represents the cutting speed;

[0013] Substituting the preset cutting score threshold value Pys into the fitting curve f(x) to obtain the first speed, and recording the maximum first speed as the theoretical speed VTa of the tool DTa;

[0014] Control module: obtain the usage time of the current tool, record it as the actual time T, calculate the time difference ΔTi=|T-Ti|, obtain the theoretical speed VDY corresponding to the minimum time difference, maintain the cutting speed at the theoretical speed VDY, and cut the steel bar with the current tool.

[0015] As a further solution of the present invention: in the calibration module, when the theoretical speed VTa<v1, an early warning message is sent for reporting.

[0016] As a further solution of the present invention: in the control module, in the process of obtaining the theoretical speed VDY, when there are two time differences that are the same and the minimum time difference, the average of the corresponding theoretical speeds is calculated as the theoretical speed VDY.

[0017] As a further solution of the present invention: in the calibration module, during the process of cutting the steel bars, the rotation speed of the cutter is kept constant.

[0018] As a further solution of the present invention: in the calibration module, the process of obtaining the density p of the burrs at the steel bar cut based on the image specifically includes:

[0019] Establishing a database, wherein the database stores images with marked burr density levels;

[0020] A burr density recognition model is established based on the deep learning model, the burr density recognition model is trained and verified through the database, the image is input into the verified burr density recognition model, and the density p of the burrs at the steel bar cut is output.

[0021] As a further solution of the present invention: in the calibration module, the images with the burr density annotated and stored in the database are based on manual acquisition.

[0022] As a further solution of the present invention: in the calibration module, the process of obtaining the theoretical speed VTa also includes the following steps:

[0023] Obtain n tools with a usage time of Ta, and obtain the corresponding theoretical speeds respectively, calculate the average VPJ of the theoretical speeds corresponding to the n tools with a usage time of Ta as the theoretical speed VTa, where n represents the preset number of tools.

[0024] As a further solution of the present invention: in the process of calculating the mean VPJ, when there is a difference between a certain theoretical speed and the mean VPJ that is greater than or equal to a preset difference threshold, the theoretical speed is removed and the mean VPJ is calculated again.

[0025] Beneficial effects of the present invention: In this scheme, firstly, the use time interval of the tool and the cutting speed interval of the steel bar are set and several nodes and speeds are selected, thereby providing an organized and planned data basis for subsequent experiments. By clarifying the use time interval of the tool [0, t] and subdividing it into multiple time nodes, the entire process of the tool from brand new to gradually worn can be fully covered, so that the characteristics of the tool at different wear stages can be carefully studied; for the steel bar cutting speed interval [v1, v2], several speeds are selected and sorted in descending order at preset intervals as initial speeds, which enables the subsequent systematic exploration of the influence of different speeds on the incision quality, because the cutting speed is a key factor affecting the incision quality, and this orderly speed selection method helps to establish a clear relationship between speed and incision quality, laying the foundation for the final establishment of an accurate model; then, the relevant information of the tool after cutting the steel bar at a specific speed under a specific use time is obtained, thereby establishing a direct connection between the use time of the tool, the cutting speed and the incision quality, and quantifying the abstract cutting effect; it is worth noting that as the use time of the tool increases, its wear degree will change, and when cutting at different speeds , the change in the quality of the cut will also be reflected in the density of the burrs due to the wear of the tool. By converting these data into a coordinate point fitting curve, we can clearly see the relationship between the cutting speed and the cut quality at different stages of tool wear, which provides a basis for determining the appropriate cutting speed according to the actual tool usage time; finally, the current tool usage time is obtained and the time difference with the ideal time is calculated, and then the theoretical speed is determined and the cutting speed is maintained, thereby realizing the dynamic optimization of the cutting process. In actual production, the tool usage time is in dynamic change. By obtaining the current tool usage time in real time and calculating the time difference with the ideal time, the corresponding theoretical speed VDY can be found. Since the relationship model between tool usage time, cutting speed and cut quality has been established before, the cutting speed determined in this way can adapt to the current wear state of the tool, which not only ensures that the cut quality will not decrease due to tool wear, but also avoids the unreasonable reduction of the cutting speed due to excessive pursuit of quality, thereby ensuring the quality of the steel bar cut while avoiding the decrease in cutting efficiency, so that the entire steel bar cutting process achieves a better balance between quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention will be further described below in conjunction with the accompanying drawings.

[0027] Figure 1 It is a flow chart of a steel bar processing control system based on digital production according to the present invention. DETAILED DESCRIPTION

[0028] 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.

[0029] See also Figure 1 As shown, the present invention is a steel bar processing control system based on digital production, comprising:

[0030] Initial module: setting a tool usage time interval [0, t], where t represents the design life of the tool, and setting a number of time nodes within the usage time interval at preset usage time intervals;

[0031] Setting a steel bar cutting speed interval [v1, v2], selecting a number of cutting speeds as initial speeds within the cutting speed interval at a preset cutting speed interval, and sorting the initial speeds in descending order to obtain an initial sort;

[0032] Calibration module: obtaining the usage time Ta corresponding to the time node a, obtaining a tool with a usage time Ta, recorded as tool DTa, obtaining the initial speed V1 at the first position in the initial sorting, maintaining the cutting speed at the initial speed V1, and cutting the steel bar by the tool DTa;

[0033] After the steel bar cutting is completed, an image of the front of the steel bar cut is collected, and the density p of the burrs at the steel bar cut is obtained based on the image, then the cutting score P=η / p, and a coordinate point (V1, P) is generated in the coordinate system, where η is a preset correction coefficient;

[0034] Remove the first initial speed V1 from the initial sorting to obtain a new initial sorting, repeat the above steps to generate new coordinate points until the number of coordinate points reaches a preset number, fit the coordinate points to obtain a fitting curve f(x), where x represents the cutting speed;

[0035] Substituting the preset cutting score threshold value Pys into the fitting curve f(x) to obtain the first speed, and recording the maximum first speed as the theoretical speed VTa of the tool DTa;

[0036] Control module: obtain the usage time of the current tool, record it as the actual time T, calculate the time difference ΔTi=|T-Ti|, obtain the theoretical speed VDY corresponding to the minimum time difference, maintain the cutting speed at the theoretical speed VDY, and cut the steel bar with the current tool.

[0037] It should be noted that, firstly, the tool usage time interval and the steel bar cutting speed interval are set and several nodes and speeds are selected, so as to provide an organized and planned data basis for subsequent experiments. By clarifying the tool usage time interval [0, t] and subdividing it into multiple time nodes, the entire process of the tool from brand new to gradually worn can be fully covered, so that the characteristics of the tool at different wear stages can be carefully studied; for the steel bar cutting speed interval [v1, v2], several speeds are selected and sorted in descending order at preset intervals as the initial speeds, which enables the subsequent systematic exploration of the influence of different speeds on the incision quality, because the cutting speed is a key factor affecting the incision quality. This orderly speed selection method helps to establish a clear relationship between speed and incision quality, laying the foundation for the final establishment of an accurate model; then, the relevant information of the tool after cutting the steel bar at a specific speed under a specific usage time is obtained, so as to establish a direct connection between the tool usage time, cutting speed and incision quality, and quantify the abstract cutting effect; it is worth noting that as the tool usage time increases, its wear degree will change. When cutting at different speeds, the incision quality will change. The change in the amount of burrs caused by tool wear will also be reflected in the density of burrs. By converting these data into coordinate point fitting curves, we can clearly see the relationship between cutting speed and incision quality at different tool wear stages, which provides a basis for determining the appropriate cutting speed according to the actual tool usage time; finally, the current tool usage time is obtained and the time difference with the ideal time is calculated, and then the theoretical speed is determined and the cutting speed is maintained, thereby realizing the dynamic optimization of the cutting process. In actual production, the tool usage time is in dynamic change. By obtaining the current tool usage time in real time and calculating the time difference with the ideal time, the corresponding theoretical speed VDY can be found. Since the relationship model between tool usage time, cutting speed and incision quality has been established before, the cutting speed determined in this way can adapt to the current wear state of the tool, which not only ensures that the incision quality will not decrease due to tool wear, but also avoids the unreasonable reduction of cutting speed due to excessive pursuit of quality, thereby ensuring the quality of steel bar incision while avoiding the decrease of cutting efficiency, so that the whole steel bar cutting process achieves a better balance between quality and efficiency.

[0038] In another preferred embodiment of the present invention, in the calibration module, when the theoretical speed VTa<v1, an early warning message is sent for reporting.

[0039] In another preferred embodiment of the present invention, in the control module, in the process of obtaining the theoretical speed VDY, when there are two time differences that are the same and the minimum time difference, the average of the corresponding theoretical speeds is calculated as the theoretical speed VDY.

[0040] In another preferred embodiment of the present invention, in the calibration module, the rotation speed of the cutter is kept constant during the process of cutting the steel bars.

[0041] It should be noted that different rotation speeds will also affect the cutting quality, so in the actual calibration process, the rotation speed of the tool needs to be kept constant.

[0042] In another preferred embodiment of the present invention, in the calibration module, the process of obtaining the density p of burrs at the steel bar cut based on the image specifically includes:

[0043] Establishing a database, wherein the database stores images with marked burr density levels;

[0044] A burr density recognition model is established based on the deep learning model, the burr density recognition model is trained and verified through the database, the image is input into the verified burr density recognition model, and the density p of the burrs at the steel bar cut is output.

[0045] It is worth noting that the powerful feature extraction and pattern recognition capabilities of deep learning can be used to more accurately and efficiently evaluate the burr density. Traditional manual evaluation of burr density may be affected by subjective factors and is inefficient. By establishing a special database to store images with annotated burr density, rich learning materials are provided for deep learning models. The burr density recognition model trained and verified based on these data can quickly and accurately identify the burr density in new images;

[0046] It is worth noting that in the process of collecting images of the front side of the steel bar incision, the position of the collected images should be kept consistent to reduce the impact of changes in image information caused by position differences on the assessment of burr density; if the collection position is not fixed, images at different positions may show large differences in burr shape and distribution due to factors such as the steel bar shape and stress distribution around the incision, which will increase the difficulty of assessing the burr density and easily introduce errors.

[0047] In another preferred embodiment of the present invention, in the calibration module, the images with labeled burr density levels stored in the database are manually acquired.

[0048] In another preferred embodiment of the present invention, in the calibration module, the process of obtaining the theoretical speed VTa further includes the following steps:

[0049] Obtain n tools with a usage time of Ta, and obtain the corresponding theoretical speeds respectively, calculate the average VPJ of the theoretical speeds corresponding to the n tools with a usage time of Ta as the theoretical speed VTa, where n represents the preset number of tools.

[0050] It is understandable that taking the average of the data of multiple tools can effectively reduce the error caused by the characteristics of a single tool. Even if different tools are used for the same length of time, their actual performance may be different due to factors such as manufacturing process and slight differences in materials. For example, there may be differences in the sharpness of the blade and the balance of the tool. By obtaining the theoretical speeds of n tools and calculating the average, the impact of these individual differences on the results can be weakened, so that the obtained theoretical speed VTa can more accurately reflect the general performance level of the tool under this length of use.

[0051] In another preferred embodiment of the present invention, during the calculation of the mean VPJ, when the difference between a certain theoretical speed and the mean VPJ is greater than or equal to a preset difference threshold, the theoretical speed is removed and the mean VPJ is calculated again.

[0052] It should be noted that in the actual production process, due to various accidental factors, some theoretical speed data that are obviously deviated from the normal range may be generated. For example, the tool may encounter a sudden external force impact during the cutting process, or the material itself may have local abnormal hardness unevenness, which may cause the theoretical speed of the tool to be far from normal expectations. By setting a difference threshold and removing other data with excessive differences, it is possible to avoid these abnormal data from interfering with the overall mean calculation, so that the final mean VPJ can more accurately reflect the theoretical speed level of the tool under normal circumstances.

[0053] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A steel bar processing control system based on digital production, characterized in that: include: Initial module: setting a tool usage time interval [0, t], where t represents the design life of the tool, and setting a number of time nodes within the usage time interval at preset usage time intervals; Setting a steel bar cutting speed interval [v1, v2], selecting a number of cutting speeds as initial speeds within the cutting speed interval at a preset cutting speed interval, and sorting the initial speeds in descending order to obtain an initial sort; Calibration module: obtaining the usage time Ta corresponding to the time node a, obtaining a tool with a usage time Ta, recorded as tool DTa, obtaining the initial speed V1 at the first position in the initial sorting, maintaining the cutting speed at the initial speed V1, and cutting the steel bar by the tool DTa; After the steel bar cutting is completed, an image of the front of the steel bar cut is collected, and the density p of the burrs at the steel bar cut is obtained based on the image, then the cutting score P=η / p, and a coordinate point (V1, P) is generated in the coordinate system, where η is a preset correction coefficient; Remove the first initial speed V1 from the initial sorting to obtain a new initial sorting, repeat the above steps to generate new coordinate points until the number of coordinate points reaches a preset number, fit the coordinate points to obtain a fitting curve f(x), where x represents the cutting speed; Substituting the preset cutting score threshold value Pys into the fitting curve f(x) to obtain the first speed, and recording the maximum first speed as the theoretical speed VTa of the tool DTa; Control module: obtain the usage time of the current tool, record it as the actual time T, calculate the time difference ΔTi=|T-Ti|, obtain the theoretical speed VDY corresponding to the minimum time difference, maintain the cutting speed at the theoretical speed VDY, and cut the steel bar with the current tool.

2. According to the steel bar processing control system based on digital production according to claim 1, it is characterized in that: In the calibration module, when the theoretical speed VTa<v1, an early warning message is sent for reporting.

3. The steel bar processing control system based on digital production according to claim 1 is characterized in that: In the control module, in the process of obtaining the theoretical speed VDY, when there are two time differences that are the same and the minimum time difference, the average of the corresponding theoretical speeds is calculated as the theoretical speed VDY.

4. The steel bar processing control system based on digital production according to claim 1 is characterized in that: In the calibration module, the rotation speed of the cutter is kept constant during the process of cutting the steel bars.

5. The steel bar processing control system based on digital production according to claim 1 is characterized in that: In the calibration module, the process of obtaining the density p of the burrs at the steel bar cut based on the image specifically includes: Establishing a database, wherein the database stores images with marked burr density levels; A burr density recognition model is established based on the deep learning model, the burr density recognition model is trained and verified through the database, the image is input into the verified burr density recognition model, and the density p of the burrs at the steel bar cut is output.

6. A steel bar processing control system based on digital production according to claim 5, characterized in that: In the calibration module, the images with the burr density annotated and stored in the database are manually acquired.

7. The steel bar processing control system based on digital production according to claim 1 is characterized in that: In the calibration module, the process of obtaining the theoretical speed VTa also includes the following steps: Obtain n tools with a usage time of Ta, and obtain the corresponding theoretical speeds respectively, calculate the average VPJ of the theoretical speeds corresponding to the n tools with a usage time of Ta as the theoretical speed VTa, where n represents the preset number of tools.

8. A steel bar processing control system based on digital production according to claim 7, characterized in that: In the process of calculating the average VPJ, when the difference between a certain theoretical speed and the average VPJ is greater than or equal to a preset difference threshold, the theoretical speed is removed and the average VPJ is calculated again.

Images