A method for defect recognition in steel pipe manufacturing

Abstract

The present application relates to the technical field of steel pipe defect detection, and particularly relates to a defect identification method for steel pipe manufacturing, comprising: acquiring steel pipe surface weld image data and determining a weld appearance index according to the image data, wherein the image data comprises a weld width, a weld excess height and a undercut depth; determining the weldability of the steel pipe according to the weld appearance index, determining the reason for unqualified welding according to the average undercut depth of the weld under the condition of unqualified welding; determining an ultrasonic detection strategy according to the defect corresponding rate of the weld width and the weld excess height under the condition of qualified welding, and acquiring a defect characteristic value inside the weld through ultrasonic detection; determining the weldability of the steel pipe manufacturing according to the defect characteristic value, and determining whether the steel pipe meets the preset standard according to the defect area proportion under the condition of unqualified steel pipe manufacturing. The present application improves the accuracy and efficiency of steel pipe defect identification.

Description

Technical Field

[0001] This invention relates to the field of steel pipe defect detection technology, and in particular to a defect identification method for steel pipe manufacturing. Background Technology

[0002] Welding is a critical process in steel pipe manufacturing, but it is prone to defects such as porosity, cracks, lack of fusion, and slag inclusions. These defects significantly reduce the mechanical properties and service safety of the steel pipe. Especially in applications such as oil and gas pipelines and high-pressure boiler tubes, weld quality directly affects the reliability and safety of the overall structure; therefore, high-precision detection of weld defects is essential. Thus, efficient and accurate defect detection during steel pipe production is a key step in ensuring product quality. Traditional defect identification methods mainly rely on manual visual inspection or offline sampling, which suffers from low efficiency, high subjectivity, and high false negative rates.

[0003] Chinese Patent Application Publication No. CN118396974A discloses a method and system for identifying surface weld defects in pressure steel pipes in the field of surface defect detection technology. The system aims to solve problems such as the existence of a series of defects in steel pipe surface welds when manually inspected in existing technologies. The method includes: a wall-climbing robot moving to photograph the steel pipe surface weld to obtain an image; constructing a first improved YOLOv5 algorithm model and pre-training it to obtain a pre-trained first improved YOLOv5 algorithm model; obtaining the model parameters from the pre-trained first improved YOLOv5 algorithm model and loading them into a second improved YOLOv5 algorithm model to obtain a pre-trained second improved YOLOv5 algorithm model; and processing the steel pipe surface weld image based on the pre-trained second improved YOLOv5 algorithm model to obtain the steel pipe surface weld defect category and weld defect location, etc.

[0004] However, the existing technology has the following problems: the existing technology only analyzes the surface image and does not take into account the problem of inaccurate defect identification caused by internal defects in the weld. Summary of the Invention

[0005] Therefore, the present invention provides a defect identification method for steel pipe manufacturing, which overcomes the problem of inaccurate defect identification caused by the failure to consider internal defects in the weld in the prior art.

[0006] To achieve the above objectives, the present invention provides a defect identification method for steel pipe manufacturing, comprising:

[0007] Acquire image data of weld seams on the surface of steel pipes and determine weld seam morphology indices based on the image data, wherein the image data includes weld seam width, weld seam reinforcement height, and undercut depth;

[0008] The weld morphology index is used to determine the qualification of steel pipe welding. Under the condition of unqualified welding, the reason for the unqualified welding is determined by the average undercut depth of the weld.

[0009] Under the condition that the welding is qualified, the ultrasonic testing strategy is determined according to the defect correspondence rate between the weld width and the weld reinforcement, and the defect characteristic value inside the weld is obtained by ultrasonic testing.

[0010] The qualification of steel pipe manufacturing is determined based on the defect characteristic value. If the steel pipe manufacturing is unqualified, the steel pipe is judged to meet the preset standard based on the defect area ratio.

[0011] Furthermore, the process of determining the qualification of steel pipe welding based on weld morphology index includes:

[0012] The weld morphology index is compared with the preset morphology index;

[0013] Based on the comparison results of the weld morphology index being less than the preset morphology index, the steel pipe welding is determined to be qualified, and the qualification of steel pipe manufacturing is determined according to the defect characteristic value.

[0014] Based on the comparison results of the weld morphology index being greater than or equal to the preset morphology index, the steel pipe welding is determined to be unqualified, and the reason for the welding failure is determined according to the average undercut depth of the weld.

[0015] Furthermore, the weld morphology index is determined jointly by the weld width excess rate and the weld reinforcement uniformity index.

[0016] Furthermore, the reasons for welding defects are determined based on the average undercut depth of the weld, among which,

[0017] If the average undercut depth of the weld is less than the preset depth, the reason for the weld failure is determined to be that the welding speed is not up to standard, and the welding speed is reduced according to the difference between the weld width over-limit rate and the preset over-limit rate.

[0018] If the average undercut depth of the weld is greater than or equal to the preset depth, the reason for the weld failure is determined to be that the welding voltage is not up to standard, and the welding voltage is reduced according to the difference between the preset uniformity index and the weld reinforcement uniformity index.

[0019] Furthermore, the welding rate is negatively correlated with the difference in the over-limit rate, which is the difference between the weld width over-limit rate and the preset over-limit rate.

[0020] Furthermore, the ultrasonic testing strategy is determined based on the defect correspondence rate between weld width and weld reinforcement height, wherein...

[0021] If the defect correspondence rate is less than the first preset correspondence rate, then the ultrasonic testing strategy is determined to be full weld inspection;

[0022] If the defect correspondence rate is greater than or equal to the first preset correspondence rate and less than the second preset correspondence rate, then the ultrasonic testing strategy is determined to be equal-spaced point detection combined with local point detection.

[0023] If the defect correspondence rate is greater than or equal to the second preset correspondence rate, then the ultrasonic testing strategy is determined to be local point detection, where local point is a point where both weld width defect and weld reinforcement defect exist simultaneously.

[0024] Furthermore, the qualification of steel pipe manufacturing is determined based on defect characteristic values, among which,

[0025] If the defect characteristic value is less than the preset characteristic value, the steel pipe is deemed to be manufactured as qualified.

[0026] If the defect feature value is greater than or equal to the preset feature value, the steel pipe is determined to be unqualified, and whether the steel pipe meets the preset standard is determined according to the defect area ratio.

[0027] Furthermore, the defect characteristic value is determined by both the defect size and the defect distribution density.

[0028] Furthermore, several adjustment methods are provided for the welding voltage, and each adjustment method has a different adjustment range for the welding voltage.

[0029] Furthermore, if the defect area ratio is less than the preset area ratio, the steel pipe is determined to meet the preset standard.

[0030] Compared with existing technologies, the advantages of this invention are that it acquires weld image data on the surface of the steel pipe, determines the weld morphology index, and then judges the weld qualification based on the index. Under qualified conditions, it further obtains the characteristic values ​​of internal defects in the weld through ultrasonic testing, and judges the qualification of steel pipe manufacturing accordingly. By comprehensively considering both surface and internal defects of the weld, this method can effectively improve the accuracy of defect identification, reduce quality problems caused by inaccurate defect identification, and ensure the quality of steel pipe manufacturing.

[0031] Furthermore, when determining that a steel pipe weld is unqualified, this invention accurately determines the cause of the unqualification based on the average undercut depth of the weld. If the average undercut depth is less than a preset depth, it is determined that the welding speed is not up to standard, and the welding speed is reasonably reduced based on the difference between the weld width over-limit rate and the preset over-limit rate. If the average undercut depth is greater than or equal to the preset depth, it is determined that the welding voltage is not up to standard, and the welding voltage is reduced based on the difference between the preset uniformity index and the weld reinforcement uniformity index. By accurately locating the cause and making targeted adjustments, welding problems can be solved quickly, improving welding efficiency and quality.

[0032] Furthermore, when the defect correspondence rate is less than a first preset correspondence rate, the present invention employs full weld inspection to ensure that no potential defects are missed. When the defect correspondence rate is greater than or equal to the first preset correspondence rate but less than a second preset correspondence rate, it employs a combination of equidistant point inspection and local point inspection to improve inspection efficiency while ensuring inspection effectiveness. When the defect correspondence rate is greater than or equal to the second preset correspondence rate, it only inspects local points where both weld width defects and weld reinforcement defects coexist, precisely focusing on areas where defects may exist. By flexibly adjusting the inspection strategy according to different situations, the present invention can improve inspection efficiency and reduce inspection costs.

[0033] Furthermore, this invention determines the qualification of steel pipe manufacturing based on defect characteristic values. If the defect characteristic value is less than a preset characteristic value, the steel pipe is deemed qualified; if it is greater than or equal to the preset characteristic value, it is deemed unqualified. The invention further determines whether the steel pipe meets preset standards based on the defect area ratio. This layered judgment method not only strictly controls the quality of steel pipe manufacturing but also provides reasonable handling suggestions based on the defect area ratio when steel pipe manufacturing is unqualified. This avoids resource waste caused by a one-size-fits-all approach and provides a scientific basis for quality control and subsequent processing in steel pipe manufacturing. Attached Figure Description

[0034] Figure 1 This is a flowchart of a defect identification method for steel pipe manufacturing according to an embodiment of the present invention;

[0035] Figure 2 This is a flowchart illustrating the process of determining the weld qualification of steel pipe welding based on weld morphology index according to an embodiment of the present invention.

[0036] Figure 3 This is a flowchart illustrating how the causes of welding defects are determined based on the average undercut depth of the weld, according to an embodiment of the present invention.

[0037] Figure 4 This is a flowchart illustrating how an ultrasonic testing strategy is determined based on the defect correspondence rate between weld width and weld reinforcement in an embodiment of the present invention. Detailed Implementation

[0038] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0039] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0040] It should be noted that the data in this embodiment are all derived from a comprehensive analysis and evaluation of historical test data and corresponding historical test results from the three months prior to this test. Those skilled in the art will understand that the determination of the above-mentioned parameters for any single item in this invention can be achieved by selecting the value with the highest percentage based on the data distribution as the preset standard parameter, using weighted summation to obtain the value as the preset standard parameter, substituting each historical data point into a specific formula and using the value obtained from that formula as the preset standard parameter, or other selection methods, as long as the invention can clearly define different specific situations in the single-item judgment process through the obtained values.

[0041] Please see Figures 1 to 4 The flowcharts shown are respectively: a flowchart of a defect identification method for steel pipe manufacturing according to an embodiment of the present invention; a flowchart of determining the qualification of steel pipe welding based on weld morphology index according to an embodiment of the present invention; a flowchart of determining the cause of welding failure based on the average undercut depth of the weld according to an embodiment of the present invention; and a flowchart of determining an ultrasonic testing strategy based on the defect correspondence rate between weld width and weld reinforcement height according to an embodiment of the present invention.

[0042] The defect identification method for steel pipe manufacturing according to embodiments of the present invention includes:

[0043] Step S1: Obtain weld image data on the surface of the steel pipe and determine the weld morphology index based on the image data. The image data includes weld width, weld reinforcement height, and undercut depth.

[0044] Step S2: Determine the qualification of steel pipe welding based on weld morphology index; under the condition of unqualified welding, determine the reason for unqualified welding based on the average undercut depth of weld.

[0045] Step S3: Under the condition that the welding is qualified, determine the ultrasonic testing strategy based on the defect correspondence rate between the weld width and the weld reinforcement, and obtain the defect characteristic value inside the weld through ultrasonic testing.

[0046] Step S4: Determine the qualification of steel pipe manufacturing based on defect characteristic values. If the steel pipe manufacturing is unqualified, determine whether the steel pipe meets the preset standard based on the defect area ratio.

[0047] Specifically, a CCD camera combined with a laser scanner is used to scan and capture images of the weld seam along the steel pipe to obtain images of the weld seam on the steel pipe surface.

[0048] Specifically, the process of determining the qualification of steel pipe welding based on weld morphology index includes:

[0049] The weld morphology index is compared with the preset morphology index;

[0050] Based on the comparison results of the weld morphology index being less than the preset morphology index, the steel pipe welding is determined to be qualified, and the qualification of steel pipe manufacturing is determined according to the defect characteristic value.

[0051] Based on the comparison results of the weld morphology index being greater than or equal to the preset morphology index, the steel pipe welding is determined to be unqualified, and the reason for the welding failure is determined according to the average undercut depth of the weld.

[0052] In this embodiment of the invention, the preset morphology index is 0.8, but the above value is not limited to this. Those skilled in the art can adjust the above value according to actual needs.

[0053] Specifically, the weld morphology index is determined by the weld width excess rate and the weld reinforcement uniformity index. The weld morphology index = first weighting coefficient × weld width excess rate / excess rate threshold + second weighting coefficient × weld reinforcement uniformity index / uniformity index threshold.

[0054] In this embodiment of the invention, the first weighting coefficient is 0.55, the weld width excess rate is the ratio of the weld length exceeding the preset width range to the weld length of a single steel pipe, the preset width range is 18mm to 24mm, the excess rate threshold is 5%, the second weighting coefficient is 0.45, the weld reinforcement uniformity index is the standard deviation of the weld reinforcement, and the uniformity index threshold is 0.3mm. However, the above values ​​are not limited to these, and those skilled in the art can adjust the above values ​​according to actual needs.

[0055] Specifically, the cause of welding defects is determined based on the average undercut depth of the weld.

[0056] If the average undercut depth of the weld is less than the preset depth, the reason for the weld failure is determined to be that the welding speed is not up to standard, and the welding speed is reduced according to the difference between the weld width over-limit rate and the preset over-limit rate.

[0057] If the average undercut depth of the weld is greater than or equal to the preset depth, the reason for the weld failure is determined to be that the welding voltage is not up to standard, and the welding voltage is reduced according to the difference between the preset uniformity index and the weld reinforcement uniformity index.

[0058] In this embodiment of the invention, the preset depth is 0.4 mm, but the above value is not limited to this. Those skilled in the art can adjust the above value according to actual needs.

[0059] Specifically, the welding rate is negatively correlated with the difference in the over-limit rate. If the difference in the over-limit rate is less than the first preset difference in the over-limit rate, the welding rate is reduced to the corresponding value using the first rate adjustment coefficient of 0.90.

[0060] If the difference in the over-limit rate is greater than or equal to the first preset over-limit rate difference and less than the second preset over-limit rate difference, then the welding rate is reduced to the corresponding value using the second rate adjustment coefficient of 0.83.

[0061] If the difference in the over-limit rate is greater than or equal to the second preset difference in the over-limit rate, the welding rate is reduced to the corresponding value using the third rate adjustment coefficient of 0.75.

[0062] The over-limit rate difference is the difference between the weld width over-limit rate and the preset over-limit rate.

[0063] In this embodiment of the invention, the first preset over-limit rate difference is 1%, the second preset over-limit rate difference is 3%, the initial welding rate is 1.2 m / min, and the preset over-limit rate is 5%. However, the above values ​​are not limited to these values, and those skilled in the art can adjust the above values ​​according to actual needs.

[0064] Specifically, the ultrasonic testing strategy is determined based on the defect correspondence rate between weld width and weld reinforcement height.

[0065] If the defect correspondence rate is less than the first preset correspondence rate, then the ultrasonic testing strategy is determined to be full weld inspection;

[0066] If the defect correspondence rate is greater than or equal to the first preset correspondence rate and less than the second preset correspondence rate, then the ultrasonic testing strategy is determined to be equal-spaced point detection combined with local point detection.

[0067] If the defect correspondence rate is greater than or equal to the second preset correspondence rate, then the ultrasonic testing strategy is determined to be local point detection, where local point is a point where both weld width defect and weld reinforcement defect exist simultaneously.

[0068] In this embodiment of the invention, the first preset correspondence rate is 20%, and the second preset correspondence rate is 50%. However, the above values ​​are not limited to these values, and those skilled in the art can adjust the above values ​​according to actual needs.

[0069] Specifically, equidistant point inspection involves selecting several points on the weld of a single steel pipe for testing. For example, 10 points may be selected at equal intervals on the steel pipe, including both ends. The specific number of points is not limited and can be adjusted according to the actual length of the steel pipe. When the points selected for equidistant point inspection do not include weld morphology defects, local point inspection must be combined.

[0070] Specifically, the process of obtaining the defect correspondence rate between weld width and weld reinforcement includes:

[0071] Complete weld width and weld reinforcement curves are obtained through image acquisition.

[0072] Identify the areas where the weld width and weld reinforcement exceed the limits, with the acceptable range for weld reinforcement being 0–3 mm.

[0073] The ratio of the overlap length of each weld width excess area and weld height excess area to the total defect area is recorded as the defect correspondence rate. The total defect area is the length of the union of the weld width excess area and the weld height excess area.

[0074] Specifically, the qualification of steel pipe manufacturing is determined based on defect characteristic values, among which,

[0075] If the defect characteristic value is less than the preset characteristic value, the steel pipe is deemed to be manufactured as qualified.

[0076] If the defect feature value is greater than or equal to the preset feature value, the steel pipe is determined to be unqualified, and whether the steel pipe meets the preset standard is determined according to the defect area ratio.

[0077] In this embodiment of the invention, the preset feature value is 0.90, but the above value is not limited to this. Those skilled in the art can adjust the above value according to actual needs.

[0078] Specifically, the defect feature value is determined by the defect size and the defect distribution density. The defect feature value = third weighting coefficient × defect length / defect length threshold + fourth weighting coefficient × defect distribution density / distribution density threshold.

[0079] In this embodiment of the invention, the third weighting coefficient is 0.5, the defect length threshold is 10mm, the fourth weighting coefficient is 0.5, the defect distribution density is the number of defects per unit length, and the distribution density threshold is 4 defects / m. However, the above values ​​are not limited to these values, and those skilled in the art can adjust the above values ​​according to actual needs.

[0080] Specifically, there are several adjustment methods for the welding voltage, and each adjustment method has a different adjustment range for the welding voltage. If the uniformity index difference is less than the first preset index difference, the welding voltage is reduced to the corresponding value using the first voltage adjustment coefficient.

[0081] If the uniformity index difference is greater than or equal to the first preset index difference and less than the second preset index difference, then the welding voltage is reduced to the corresponding value using the second voltage adjustment coefficient.

[0082] If the uniformity index difference is greater than or equal to the second preset index difference, the welding voltage is reduced to the corresponding value using the third voltage adjustment coefficient.

[0083] The uniformity index difference is the difference between the preset uniformity index and the weld reinforcement uniformity index.

[0084] In this embodiment of the invention, the first preset index difference is 0.05, the second preset index difference is 0.1, the initial welding voltage is 25V, and the preset uniformity index is 0.3mm. However, the above values ​​are not limited to these values, and those skilled in the art can adjust the above values ​​according to actual needs.

[0085] Specifically, the steel pipe is deemed to meet the preset standard if the defect area ratio is less than the preset area ratio.

[0086] In this embodiment of the invention, the preset area ratio is 5%, but the above value is not limited to this. Those skilled in the art can adjust the above value according to actual needs.

[0087] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0088] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for defect identification in steel pipe manufacturing, characterized in that, include: Acquire image data of weld seams on the surface of steel pipes and determine weld seam morphology indices based on the image data, wherein the image data includes weld seam width, weld seam reinforcement height, and undercut depth; The weld morphology index is used to determine the qualification of steel pipe welding. Under the condition of unqualified welding, the reason for the unqualified welding is determined by the average undercut depth of the weld. Under the condition that the welding is qualified, the ultrasonic testing strategy is determined based on the defect correspondence rate between the weld width and the weld reinforcement height. If the defect correspondence rate is less than the first preset correspondence rate, then the ultrasonic testing strategy is determined to be full weld inspection; If the defect correspondence rate is greater than or equal to the first preset correspondence rate and less than the second preset correspondence rate, then the ultrasonic testing strategy is determined to be equal-spaced point detection combined with local point detection. If the defect correspondence rate is greater than or equal to the second preset correspondence rate, then the ultrasonic testing strategy is determined to be local point detection, and the local point is the point where both weld width defect and weld reinforcement defect exist simultaneously. The defect correspondence rate is determined by comparing the ratio of the overlap length of each weld width exceeding the limit area and the weld height exceeding the limit area to the length of the total defect area; the length of the total defect area is the length of the union area of ​​the weld width exceeding the limit area and the weld height exceeding the limit area. Defect characteristics inside the weld are obtained through ultrasonic testing; The qualification of steel pipe manufacturing is determined based on the defect characteristic value. If the steel pipe manufacturing is unqualified, the steel pipe is judged to meet the preset standard based on the defect area ratio.

2. The defect identification method for steel pipe manufacturing according to claim 1, characterized in that, The process of determining the qualification of steel pipe welding based on weld morphology index includes: The weld morphology index is compared with the preset morphology index; Based on the comparison results of the weld morphology index being less than the preset morphology index, the steel pipe welding is determined to be qualified, and the qualification of steel pipe manufacturing is determined according to the defect characteristic value. Based on the comparison results of the weld morphology index being greater than or equal to the preset morphology index, the steel pipe welding is determined to be unqualified, and the reason for the welding failure is determined according to the average undercut depth of the weld.

3. The defect identification method for steel pipe manufacturing according to claim 2, characterized in that, The weld morphology index is determined by the weld width excess rate and the weld reinforcement uniformity index.

4. The defect identification method for steel pipe manufacturing according to claim 3, characterized in that, The cause of welding defects is determined based on the average undercut depth of the weld. If the average undercut depth of the weld is less than the preset depth, the reason for the weld failure is determined to be that the welding speed is not up to standard, and the welding speed is reduced according to the difference between the weld width over-limit rate and the preset over-limit rate. If the average undercut depth of the weld is greater than or equal to the preset depth, the reason for the weld failure is determined to be that the welding voltage is not up to standard, and the welding voltage is reduced according to the difference between the preset uniformity index and the weld reinforcement uniformity index.

5. The defect identification method for steel pipe manufacturing according to claim 4, characterized in that, The welding rate is negatively correlated with the difference in the over-limit rate, which is the difference between the weld width over-limit rate and the preset over-limit rate.

6. The defect identification method for steel pipe manufacturing according to claim 5, characterized in that, The qualification of steel pipe manufacturing is determined based on defect characteristic values, among which, If the defect characteristic value is less than the preset characteristic value, the steel pipe is deemed to be manufactured as qualified. If the defect feature value is greater than or equal to the preset feature value, the steel pipe is determined to be unqualified, and whether the steel pipe meets the preset standard is determined according to the defect area ratio.

7. The defect identification method for steel pipe manufacturing according to claim 6, characterized in that, The defect characteristic value is determined by both the defect size and the defect distribution density.

8. The defect identification method for steel pipe manufacturing according to claim 7, characterized in that, There are several adjustment methods for the welding voltage, and each adjustment method has a different adjustment range for the welding voltage.

9. The defect identification method for steel pipe manufacturing according to claim 8, characterized in that, The steel pipe is deemed to meet the preset standard if the defect area ratio is less than the preset area ratio.

Images