Automatic detection method and device for reinforcing steel bar semi-finished product

Abstract

The invention provides a reinforcing steel bar semi-finished product automatic detection method and device, and relates to the technical field of reinforcing steel bar construction.According to the reinforcing steel bar semi-finished product automatic detection method and device, bending angles are synchronously monitored through elastic rubber strips with indication marks, and changes of all bending sections in step-by-step bending can be reflected in real time; the angle of the bent steel bar can be accurately detected, and the detection precision and efficiency are improved; in addition, by collecting and analyzing surface abnormal change data of each bending section, a defect evaluation coefficient and an angle deviation evaluation coefficient can be accurately calculated; the parameters provide detailed quality evaluation and feedback for each bending section, so that the processing quality of the semi-finished reinforcing steel bar piece is improved; meanwhile, through comprehensive analysis of the evaluation coefficients, a bending compensation adjustment strategy can be formulated, and the dynamic control capability of the multi-step bending operation is remarkably enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of steel bar construction, and in particular to an automatic detection method and device for steel bar semi-finished products. Background Art

[0002] At present, there are many automatic detection methods on the market that have been applied to the production line of semi-finished steel bars, such as laser scanning, computer vision and ultrasonic detection, to achieve automatic detection of the geometric shape and physical properties of steel bars. However, these detection methods either focus on the measurement of overall geometric dimensions or on the detection of internal defects in the material, and often ignore the detailed monitoring of surface deformation and local defects generated during the steel bar bending process.

[0003] In the prior art, the publication number is CN116652066A, and the name is a method for automatically detecting the forming accuracy of semi-finished steel bars, including the processing accuracy detection of steel bar unit components and steel bar sheet bodies. The processing accuracy detection of steel bar unit components and steel bar sheet bodies is to set multiple high-definition cameras on the bending equipment and sheet body processing equipment, so that they are aimed at the bending area and the fabric area to shoot and collect videos, so as to judge whether the bent steel bar unit components and steel bar sheet body skeletons meet the accuracy requirements after analysis and comparison by the processing system. It solves the problems of high manual detection intensity, long detection cycle, and slow data feedback processing equipment, and improves the efficiency of precision detection and processing accuracy of semi-finished steel bars.

[0004] Although the existing technology has made significant progress in some aspects, it still has some shortcomings: first, the existing automatic inspection systems mostly rely on static scanning, and their ability to monitor dynamic changes in the process is relatively weak, especially in the large-angle bending process. It is impossible to accurately evaluate the relationship between the bending angle and the surface deformation in real time; second, when dealing with multi-step bending operations, traditional inspection methods cannot effectively conduct comprehensive analysis and feedback adjustments on the data of each stage, which affects the accuracy and stability of the final product.

[0005] The above information disclosed in the above Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a method and device for automatically detecting semi-finished steel bars to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for automatically detecting semi-finished steel bars, the specific steps comprising:

[0009] Step S1: On the basis that large-angle bending needs to be completed in steps, multiple bending sections of the semi-finished steel bar under the step-by-step bending method are determined, and the target bending angle under each bending section is obtained, and an elastic rubber strip with an indicator mark is set on the upper surface of the central axis of each bending section, and the elastic rubber strip can bend synchronously with the bending angle of the bending section, and the angle after bending is determined by the indicator mark;

[0010] Step S2: during the execution of the step-by-step bending method, determining the standard deformation data corresponding to the indicator mark of each bending segment when the corresponding target bending angle is reached;

[0011] Collect the surface abnormal change data of the semi-finished steel bar in the observation area corresponding to each bending section, and the actual deformation data corresponding to the indicator mark in the elastic strip on each bending section;

[0012] Step S3: Analyze the surface abnormal change data obtained for each bending section and calculate the corresponding defect evaluation coefficient, which is used to evaluate the degree of defects in each bending section;

[0013] Step S4: Compare and analyze the actual deformation data of the indicator mark corresponding to the elastic rubber strip on each bending section with the standard deformation data, and calculate the corresponding angle deviation evaluation coefficient, which is used to evaluate the degree of deviation of each bending section from the corresponding target bending angle;

[0014] Step S5: Comprehensively analyzing the defect evaluation coefficient and angle evaluation coefficient calculated for each bending section to generate an adjustment strategy for providing bending compensation for each bending section.

[0015] An automatic detection device for semi-finished steel bars, the device is used to execute the automatic detection method for semi-finished steel bars, specifically comprising:

[0016] Bending section setting module: It is used to determine the multiple bending sections of the semi-finished steel bar under the step-by-step bending method on the basis that large-angle bending needs to be completed in steps, and obtain the target bending angle under each bending section, and set an elastic rubber strip with an indicator mark on the upper surface of the central axis of each bending section. The elastic rubber strip can bend synchronously with the bending angle of the bending section, and the angle after bending is determined by the indicator mark;

[0017] Data acquisition module: used to determine the standard deformation data corresponding to the indicator mark of each bending section when it reaches the corresponding target bending angle during the execution of the step-by-step bending method;

[0018] Collect the surface abnormal change data of the semi-finished steel bar in the observation area corresponding to each bending section, and the actual deformation data corresponding to the indicator mark in the elastic strip on each bending section;

[0019] Defect evaluation coefficient generation module: used to analyze the surface abnormal change data obtained from each bending section and calculate the corresponding defect evaluation coefficient, which is used to evaluate the degree of defects in each bending section;

[0020] Angle deviation evaluation coefficient generation module: used to compare and analyze the actual deformation variable data of the indicator mark corresponding to the elastic rubber strip on each bending section with the standard deformation variable data, and calculate the corresponding angle deviation evaluation coefficient, which is used to evaluate the degree of deviation of each bending section from the corresponding target bending angle;

[0021] Adjustment strategy generation module: used to comprehensively analyze the defect evaluation coefficient and angle evaluation coefficient calculated under each bending section to generate an adjustment strategy for providing bending compensation for each bending section.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows: by using an elastic rubber strip with an indicator mark to synchronously monitor the bending angle, the changes of each bending section in the step-by-step bending can be reflected in real time; it is helpful to accurately detect the angle of the steel bar after bending, thereby improving the detection accuracy and efficiency; in addition, by collecting and analyzing the surface abnormal change data of each bending section, the defect evaluation coefficient and the angle deviation evaluation coefficient can be accurately calculated; these parameters provide detailed quality evaluation and feedback for each bending section, thereby improving the processing quality of the semi-finished steel bar parts; at the same time, through the comprehensive analysis of these evaluation coefficients, a bending compensation adjustment strategy can also be formulated, which significantly enhances the dynamic control capability of multi-step bending operations, and ultimately makes the production process more intelligent and automated. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0024] Figure 2 It is a module block diagram of the device of the present invention. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0026] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0027] Embodiment 1:

[0028] See also Figure 1 , the present invention provides a technical solution:

[0029] An automatic detection method for semi-finished steel bars is applied to semi-finished steel bars based on a step-by-step bending method, and the specific steps include:

[0030] Step S1: On the basis that large-angle bending needs to be completed in steps, multiple bending sections of the semi-finished steel bar under the step-by-step bending method are determined, and the target bending angle under each bending section is obtained, and an elastic rubber strip with an indicator mark is set on the upper surface of the central axis of each bending section, and the elastic rubber strip can bend synchronously with the bending angle of the bending section, and the angle after bending is determined by the indicator mark;

[0031] Step S2: during the execution of the step-by-step bending method, determining the standard deformation data corresponding to the indicator mark of each bending segment when the corresponding target bending angle is reached;

[0032] Collect the surface abnormal change data of the semi-finished steel bar in the observation area corresponding to each bending section, and the actual deformation data corresponding to the indicator mark in the elastic strip on each bending section;

[0033] Step S3: Analyze the surface abnormal change data obtained for each bending section and calculate the corresponding defect evaluation coefficient, which is used to evaluate the degree of defects in each bending section;

[0034] Step S4: Compare and analyze the actual deformation data of the indicator mark corresponding to the elastic rubber strip on each bending section with the standard deformation data, and calculate the corresponding angle deviation evaluation coefficient, which is used to evaluate the degree of deviation of each bending section from the corresponding target bending angle;

[0035] Step S5: Comprehensively analyzing the defect evaluation coefficient and angle evaluation coefficient calculated for each bending section to generate an adjustment strategy for providing bending compensation for each bending section.

[0036] Further explanation, based on the total bending angle requirement of large-angle bending, the total bending angle is decomposed into multiple bending segments with small angles, specifically:

[0037] Choose the appropriate thickness and width of the elastic strip to ensure it can withstand multiple bends without tearing or losing elasticity;

[0038] Multiple bending segments are represented as {1, 2, ..., i, ..., n}, where i represents the index of the i-th bending segment, and n represents the total number of bending segments that complete the large-angle bending.

[0039] Fix the selected elastic strip on the upper surface of the central axis of each bending section to ensure that the strip is smooth and firm; and check the indicator mark of the elastic strip to make it correspond to the angle indication that can be visually identified.

[0040] The upper surface of the central axis of each bending section is defined as: when the bending part of the steel bar is placed flat on a horizontal plane during the bending process, the bending part is observed from a top-down angle, and the outer surface visible directly above the bending area corresponding to the steel bar.

[0041] Further explanation: the standard deformation data, surface abnormal change data and actual deformation data specifically include:

[0042] Definition of standard shape variable data:

[0043] The standard deformation data is a set of theoretical reference data used to characterize the change of the "indicator mark" of the steel bar at the target bending angle. It not only expresses the bending angle information, but also includes whether the bending point is located in the middle of the "indicator mark" during the bending operation. This information is obtained through prior calculation or experimental calibration.

[0044] Standard deformation data, including: target angle variation and position deviation tolerance;

[0045] The target angle change is the angle change determined by the indicator mark when each bending segment reaches its target bending angle; the target angle change corresponding to the indicator mark on the i-th bending segment is defined as ; The calculation formula is as follows:

[0046]

[0047] in, is the target angle change of the i-th bending segment (unit: degree);

[0048] is the angle change of the i-th bending segment measured by the indicator mark;

[0049] During the bending process of the i-th bending section, the ideal middle position of the indicator mark is set; the position deviation tolerance indicates the allowed deviation range of the ideal middle position, which is used to evaluate whether the indicator mark is accurately located at the center position of the current bending section; when the center line formed by the bending part of the i-th bending section on the indicator mark coincides with the ideal middle position on the indicator mark, it indicates that the bending position is most accurate;

[0050] Collection method: Calibrate and test the characteristic data of different bending sections through high-precision tests in advance;

[0051] Define the position deviation tolerance of the ideal middle position corresponding to the indicator mark on the i-th bending segment as ;

[0052] In this embodiment, the position deviation tolerance It is determined according to the current forming accuracy requirements of the semi-finished steel bar parts. The specific value is set by the corresponding technical personnel and will not be elaborated here.

[0053] Definition of actual shape variable data:

[0054] The actual deformation data is based on the change profile of the "indicator mark" collected by the image monitoring equipment, and the actual bending angle information and specific bending position are extracted through image processing technology;

[0055] Actual deformation data, including: actual angle change and actual position change of the indicator marks on each bending segment extracted by image processing technology;

[0056] For the actual angle change: by analyzing the bending curvature of the steel bar frame by frame, the actual angle change of the "indicator mark" is extracted; the actual angle change corresponding to the indicator mark on the i-th bending segment is defined as ; The calculation formula is as follows:

[0057]

[0058] in, is the actual angle change of the indicator mark on the i-th bending segment (unit: degree);

[0059] is the actual angle (unit: degree) of the corresponding indicator mark after the i-th bending segment is bent through image recognition;

[0060] Acquisition method: Extract angle data from the real-time contour features of the indicator mark through image processing technology;

[0061] is the initial bending angle of the indicator mark on the i-th bending segment before bending (unit: degree);

[0062] For the actual position change: it is determined by calculating the distance difference between the center line formed by the bending part of the i-th bending segment on the indicator mark and the ideal middle position on the indicator mark;

[0063] Collection method: Use a high-definition image monitoring device installed on the equipment to track and analyze the "indicator mark" in real time during the bending process, and extract the contour change characteristics of the indicator mark in the image;

[0064] Definition of surface abnormal change data:

[0065] The surface abnormal change data is used to describe whether there are deformation, cracks, or pit defects on the surface of the semi-finished steel bar during the bending process;

[0066] The actual position change of the i-th bending segment is defined as ; The calculation formula is as follows:

[0067]

[0068] in, Characterization The vector displacement difference of

[0069] is the center point of the midline measurement position formed by the bent portion of the i-th bending segment on the indicator mark;

[0070] is the center point of the ideal middle position corresponding to the indicator mark on the i-th bending segment;

[0071] The observation area is set on the outer side of each bending section; the surface abnormal change data includes: crack characteristic index and concave-convex characteristic index;

[0072] Crack characteristic indicators: Through image monitoring equipment and image processing algorithms, the length, width and distribution range of cracks in each bending section of the surface are extracted; and the observation area of ​​image monitoring is the inner side or outer side of each bending section;

[0073] Crack characteristic indicators, including: total crack length, crack width and crack density;

[0074] Total crack length: total length of the crack (mm);

[0075] Crack width: the maximum width of the crack (mm);

[0076] Crack density: the number of cracks per unit area (number / area).

[0077] The total crack length of the i-th bending segment under the observation area is recorded as ;

[0078] Acquisition method: Statistics through the crack identification step of the image processing algorithm; crack pixel length multiplied by the camera pixel ratio converted to millimeters;

[0079] The crack width of the i-th bending segment under the observation area is recorded as ;and is the maximum width of all cracks in the i-th bending segment;

[0080] Acquisition method: Extract pixel distance through crack width profile and convert to millimeters;

[0081] The crack density of the i-th bending segment under the observation area is recorded as ; The calculation formula is as follows:

[0082]

[0083] in, is the number of cracks per unit area in the i-th bending segment; is the total number of cracks in the i-th bending segment; is the observation area of ​​the acquired image (unit: square millimeters);

[0084] Collection method: Determined by camera view angle calibration;

[0085] Concave-convex feature indicators: detect whether there are abnormal depressions or ridges on the surface through laser scanning or visual capture;

[0086] Concave-convex characteristic indicators include: maximum concave depth, total concave-convex area and surface flatness.

[0087] Depth of depression (mm): the maximum depth of the depression on the surface;

[0088] Concave and convex area (square millimeters): the area of ​​the significant concave or convex area;

[0089] Surface Flatness (Percent): The quantified percentage of surface relief compared to an ideal flat surface.

[0090] Collection method: The visual capture method uses high-definition image monitoring equipment and combines it with AI image processing algorithms (such as edge detection, crack detection, and surface texture analysis) to obtain data. The observation area is the inner or outer side of each bending section.

[0091] The maximum depression depth of the i-th bending segment under the observation area is recorded as ;

[0092] Collection method: Measure surface concavity and convexity by laser scanning or visual capture;

[0093] The total concave and convex area of ​​the i-th bending segment under the observation area is defined as ; It is obtained by calculating the total area of ​​all observed concave and convex regions;

[0094] Acquisition method: Calculate the area after extracting the region through image contour;

[0095] The surface flatness of the i-th bending segment under the observation area is defined as The calculation formula is as follows:

[0096]

[0097] in, is the deviation value of the actual surface height of the i-th bending segment under the observation area (unit: mm);

[0098] Acquisition method: Heave deviation calculated by laser scanning ranging;

[0099] Indicates from 0 and Select the maximum value among

[0100] It is the height difference of the ideal plane under the observation area of ​​the i-th bending section (unit: mm); the height difference of the ideal plane is determined according to the specifications in the design drawings.

[0101] Further explanation: the calculation of defect evaluation coefficient includes:

[0102] The crack characteristic index of the i-th bending segment is characterized as ; and the following calculation formula is obtained:

[0103]

[0104] The concave-convex characteristic index of the i-th bending segment is represented as ; and the following calculation formula is obtained:

[0105]

[0106] in, , and are the upper defect thresholds of the total crack length, crack width and crack density of the i-th bending segment;

[0107] and are the upper defect thresholds of the maximum concave depth and the total concave-convex area of ​​the i-th bending segment, respectively; is the lower defect threshold of surface flatness;

[0108] The above-mentioned upper and lower defect thresholds are determined according to the quality standard requirements of the current semi-finished steel bar parts. The specific values ​​are set by the corresponding technical personnel and will not be described in detail.

[0109] The "defect upper limit threshold" is used to represent the upper limit of the defect standard of the current semi-finished steel bar part regarding the total crack length, crack width, crack density, maximum depression depth and total concave-convex area. When any of the defect upper limit thresholds is exceeded, it means that the current semi-finished steel bar part does not meet the quality standard; the defect lower limit threshold is used to represent the lower limit of the defect standard of the current semi-finished steel bar part regarding the surface flatness. When the surface flatness is less than the defect lower limit threshold, it means that the current semi-finished steel bar part does not meet the quality standard;

[0110] is the crack defect evaluation coefficient of the i-th bending section; is the concave-convex defect evaluation coefficient of the i-th bending segment;

[0111] {a1, a2, a3} and {a4, a5, a6} are weight coefficients of each parameter, and a1+a2+a3=1, a4+a5+a6=1;

[0112] The values ​​of {a1, a2, a3} and {a4, a5, a6} are all within the interval (0, 1); {a1, a2, a3} and {a4, a5, a6} are determined by the entropy weight method and the fuzzy analytic hierarchy process (FAHP), which will not be described in detail;

[0113] when or or When the value exceeds 1, it means that the corresponding crack characteristic index exceeds the corresponding defect upper limit threshold; The value increases;

[0114] when or or If the value exceeds 1, it means that the corresponding concave-convex feature index exceeds the corresponding defect upper limit threshold; The value increases;

[0115] or The larger the value, the greater the defect degree of the corresponding bending section.

[0116] Further explanation: the acquisition of the angle deviation evaluation coefficient specifically includes:

[0117] The angle deviation evaluation coefficient of the i-th bending segment is defined as , the calculation formula is as follows:

[0118]

[0119] in, is the adjustment factor;

[0120] for : Indicates that the actual position change is below the position deviation tolerance, indicating that the corresponding indicator mark is located in the center area of ​​the current bending segment, and the bending position of the i-th bending segment is correct;

[0121] at this time ;and The closer the difference between is to 0, the smaller the deviation between the target angle change and the actual angle change is, which means that the deviation between the bending angle of the i-th bending segment and the target bending angle is smaller.

[0122] for : Indicates that the actual position change is above the position deviation tolerance, indicating that the corresponding indicator mark is outside the center position area of ​​the current bending segment, and the bending position of the i-th bending segment is incorrect;

[0123] at this time It is an abnormal output value greater than 180°, which is an output representation that the bending position of the i-th bending segment is incorrect.

[0124] Further explanation: the adjustment strategy of bending compensation is provided for each bending section, including:

[0125] Through multiple simulated bending experiments, the corresponding { , , The minimum value of each ratio and the minimum value of each ratio greater than 1 are used to determine the following warning thresholds:

[0126] set up , , In the case where only one ratio exceeds 1 and the other two ratios are minimum values, select Take the value and The minimum value is used as the warning threshold for defect evaluation of crack characteristics, denoted as ;

[0127] Through multiple simulated bending experiments, the corresponding { , , }The minimum value of each ratio, and the minimum value of each ratio greater than 1;

[0128] set up or or In the case where only one ratio exceeds 1 and the other two ratios are minimum values, select Take the value and The minimum value is used as the warning threshold for defect evaluation of concave and convex features, denoted as ;

[0129] During the bending process of the i-th bending section of the semi-finished steel bar, if there is In any of the following cases, the bending quality of the current i-th bending segment is judged to be unqualified;

[0130] Ruodang When controlling the bending parameters of the steel bar bending machine, The closer the difference is to 0;

[0131] Ruodang When the bending position is re-determined, the bending force point of the steel bar bending machine is adjusted to make .

[0132] Embodiment 2:

[0133] See also Figure 2 , a semi-finished steel bar automatic detection device, the device is used to perform the semi-finished steel bar automatic detection method, specifically comprising:

[0134] Bending section setting module: It is used to determine the multiple bending sections of the semi-finished steel bar under the step-by-step bending method on the basis that large-angle bending needs to be completed in steps, and obtain the target bending angle under each bending section, and set an elastic rubber strip with an indicator mark on the upper surface of the central axis of each bending section. The elastic rubber strip can bend synchronously with the bending angle of the bending section, and the angle after bending is determined by the indicator mark;

[0135] Data acquisition module: used to determine the standard deformation data corresponding to the indicator mark of each bending section when it reaches the corresponding target bending angle during the execution of the step-by-step bending method;

[0136] Collect the surface abnormal change data of the semi-finished steel bar in the observation area corresponding to each bending section, and the actual deformation data corresponding to the indicator mark in the elastic strip on each bending section;

[0137] Defect evaluation coefficient generation module: used to analyze the surface abnormal change data obtained from each bending section and calculate the corresponding defect evaluation coefficient, which is used to evaluate the degree of defects in each bending section;

[0138] Angle deviation evaluation coefficient generation module: used to compare and analyze the actual deformation variable data of the indicator mark corresponding to the elastic rubber strip on each bending section with the standard deformation variable data, and calculate the corresponding angle deviation evaluation coefficient, which is used to evaluate the degree of deviation of each bending section from the corresponding target bending angle;

[0139] Adjustment strategy generation module: used to comprehensively analyze the defect evaluation coefficient and angle evaluation coefficient calculated under each bending section to generate an adjustment strategy for providing bending compensation for each bending section.

[0140] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0141] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An automatic detection method for semi-finished steel bars, applied to semi-finished steel bars based on a step-by-step bending method, characterized in that: The specific steps include: Step S1: On the basis that large-angle bending needs to be completed in steps, multiple bending sections of the semi-finished steel bar under the step-by-step bending method are determined, and the target bending angle under each bending section is obtained, and an elastic rubber strip with an indicator mark is set on the upper surface of the central axis of each bending section, and the elastic rubber strip can bend synchronously with the bending angle of the bending section, and the angle after bending is determined by the indicator mark; Step S2: during the execution of the step-by-step bending method, determining the standard deformation data corresponding to the indicator mark of each bending segment when the corresponding target bending angle is reached; Collect the surface abnormal change data of the semi-finished steel bar in the observation area corresponding to each bending section, and the actual deformation data corresponding to the indicator mark in the elastic strip on each bending section; Step S3: Analyze the surface abnormal change data obtained for each bending section and calculate the corresponding defect evaluation coefficient, which is used to evaluate the defect degree of each bending section; Step S4: Compare and analyze the actual deformation data of the indicator mark corresponding to the elastic rubber strip on each bending section with the standard deformation data, and calculate the corresponding angle deviation evaluation coefficient, which is used to evaluate the degree of deviation of each bending section from the corresponding target bending angle; Step S5: Comprehensively analyzing the defect evaluation coefficient and angle evaluation coefficient calculated for each bending section to generate an adjustment strategy for providing bending compensation for each bending section.

2. The method for automatically detecting a semi-finished steel bar product according to claim 1, characterized in that: The standard deformation data, surface abnormal change data and actual deformation data specifically include: Standard deformation variable data, including: target angle variation and position deviation tolerance; i represents the index of the i-th bending segment; The target angle change is the angle change determined by the indicator mark when each bending segment reaches its target bending angle; the target angle change corresponding to the indicator mark on the i-th bending segment is defined as ; During the bending process of the i-th bending section, an ideal middle position of the indicator mark is set; the position deviation tolerance indicates the allowable deviation range of the ideal middle position, which is used to evaluate whether the indicator mark is accurately located at the center position of the current bending section; When the center line formed by the bent part of the i-th bending segment on the indicator mark coincides with the ideal middle position on the indicator mark, it indicates that the bending position is most accurate; Define the position deviation tolerance of the ideal middle position corresponding to the indicator mark on the i-th bending segment as ; Actual deformation data, including: actual angle change and actual position change of the indicator marks on each bending segment extracted by image processing technology; For the actual angle change: define the actual angle change corresponding to the indicator mark on the i-th bending segment as ; For the actual position change: it is determined by calculating the distance difference between the center line formed by the bending part of the i-th bending segment on the indicator mark and the ideal middle position on the indicator mark; The actual position change of the i-th bending segment is defined as .

3. The method for automatically detecting a semi-finished steel bar product according to claim 2, characterized in that: The observation area is set on the outer side of each bending section; Surface abnormal change data, including: crack characteristic index and concave-convex characteristic index; Crack characteristic indicators, including: total crack length, crack width and crack density; The total crack length of the i-th bending segment under the observation area is recorded as ; The crack width of the i-th bending segment under the observation area is recorded as ;and is the maximum width of all cracks in the i-th bending segment; The crack density of the i-th bending segment under the observation area is recorded as ; Concave-convex characteristic indicators, including: maximum concave depth, total concave-convex area and surface flatness; The maximum depression depth of the i-th bending segment under the observation area is recorded as ; The total concave and convex area of ​​the i-th bending segment under the observation area is defined as ; The surface flatness of the i-th bending segment under the observation area is defined as .

4. The method for automatically detecting a semi-finished steel bar product according to claim 3, characterized in that: The calculation of defect evaluation coefficient includes: The crack characteristic index of the i-th bending segment is characterized as ; and the following calculation formula is obtained: The concave-convex characteristic index of the i-th bending segment is represented as ; and the following calculation formula is obtained: in, , and are the upper defect thresholds of the total crack length, crack width and crack density of the i-th bending segment; and are the upper defect thresholds of the maximum concave depth and the total concave-convex area of ​​the i-th bending segment, respectively; is the lower defect threshold of surface flatness; is the crack defect evaluation coefficient of the i-th bending section; is the concave-convex defect evaluation coefficient of the i-th bending segment; {a1, a2, a3} and {a4, a5, a6} are weight coefficients of each parameter, and a1+a2+a3=1, a4+a5+a6=1; The values ​​of {a1, a2, a3} and {a4, a5, a6} are all in the interval (0, 1); when or or When the value exceeds 1, it means that the corresponding crack characteristic index exceeds the corresponding defect upper limit threshold; The value increases; when or or If the value exceeds 1, it means that the corresponding concave-convex feature index exceeds the corresponding defect upper limit threshold; The value increases; or The larger the value, the greater the defect degree of the corresponding bending section.

5. The method for automatically detecting a semi-finished steel bar product according to claim 4, characterized in that: The acquisition of the angle deviation evaluation coefficient specifically includes: The angle deviation evaluation coefficient of the i-th bending segment is defined as , the calculation formula is as follows: in, is the adjustment factor; for : Indicates that the actual position change is below the position deviation tolerance, indicating that the corresponding indicator mark is located in the center area of ​​the current bending segment, and the bending position of the i-th bending segment is correct; at this time ;and The closer the difference between is to 0, the smaller the deviation between the target angle change and the actual angle change is, which means that the deviation between the bending angle of the i-th bending segment and the target bending angle is smaller. for : Indicates that the actual position change is above the position deviation tolerance, indicating that the corresponding indicator mark is outside the center position area of ​​the current bending segment, and the bending position of the i-th bending segment is incorrect; at this time It is an abnormal output value greater than 180°, which is an output representation that the bending position of the i-th bending segment is incorrect.

6. The method for automatically detecting a semi-finished steel bar product according to claim 5, characterized in that: Provide bending compensation adjustment strategies for each bending section, including: Through multiple simulated bending experiments, the corresponding { , , The minimum value of each ratio and the minimum value of each ratio greater than 1 are used to determine the following warning thresholds: set up , , In the case where only one ratio exceeds 1 and the other two ratios are minimum values, select Take the value and The minimum value is used as the warning threshold for defect evaluation of crack characteristics, denoted as ; Through multiple simulated bending experiments, the corresponding { , , }The minimum value of each ratio, and the minimum value of each ratio greater than 1; set up or or In the case where only one ratio exceeds 1 and the other two ratios are minimum values, select Take the value and The minimum value is used as the warning threshold for defect evaluation of concave and convex features, denoted as ; During the bending process of the i-th bending section of the semi-finished steel bar, if there is In any of the following cases, the bending quality of the current i-th bending segment is judged to be unqualified; Ruodang When controlling the bending parameters of the steel bar bending machine, The closer the difference is to 0; Ruodang When the bending position is re-determined, the bending force point of the steel bar bending machine is adjusted to make .

7. An automatic detection device for semi-finished steel bars, characterized in that: The device is used to execute the automatic detection method of the semi-finished steel bar product according to any one of claims 1 to 6, specifically comprising: Bending section setting module: It is used to determine the multiple bending sections of the semi-finished steel bar under the step-by-step bending method on the basis that large-angle bending needs to be completed in steps, and obtain the target bending angle under each bending section, and set an elastic rubber strip with an indicator mark on the upper surface of the central axis of each bending section. The elastic rubber strip can bend synchronously with the bending angle of the bending section, and the angle after bending is determined by the indicator mark; Data acquisition module: used to determine the standard deformation data corresponding to the indicator mark when each bending section reaches the corresponding target bending angle during the execution of the step-by-step bending method; Collect the surface abnormal change data of the semi-finished steel bar in the observation area corresponding to each bending section, and the actual deformation data corresponding to the indicator mark in the elastic strip on each bending section; Defect evaluation coefficient generation module: used to analyze the surface abnormal change data obtained from each bending section and calculate the corresponding defect evaluation coefficient, which is used to evaluate the degree of defects in each bending section; Angle deviation evaluation coefficient generation module: used to compare and analyze the actual deformation variable data of the indicator mark corresponding to the elastic rubber strip on each bending section with the standard deformation variable data, and calculate the corresponding angle deviation evaluation coefficient, which is used to evaluate the degree of deviation of each bending section from the corresponding target bending angle; Adjustment strategy generation module: used to comprehensively analyze the defect evaluation coefficient and angle evaluation coefficient calculated under each bending section to generate an adjustment strategy for providing bending compensation for each bending section.

Images