CN117434083A - Non-contact type steel pipe surface defect detection method - Google Patents
Non-contact type steel pipe surface defect detection method Download PDFInfo
- Publication number
- CN117434083A CN117434083A CN202311361573.2A CN202311361573A CN117434083A CN 117434083 A CN117434083 A CN 117434083A CN 202311361573 A CN202311361573 A CN 202311361573A CN 117434083 A CN117434083 A CN 117434083A
- Authority
- CN
- China
- Prior art keywords
- steel pipe
- cloud data
- point cloud
- data
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 79
- 239000010959 steel Substances 0.000 title claims abstract description 79
- 230000007547 defect Effects 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000004907 flux Effects 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/952—Inspecting the exterior surface of cylindrical bodies or wires
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
The invention relates to a non-contact steel pipe surface defect detection method, which comprises the following steps: s1, acquiring cloud data of the positions of contour points of the surface of a steel pipe by using a sensor; s2, eliminating noise points by using a limiting amplitude noise reduction filter; s3, establishing a best curve fitting model of the surface profile of the steel pipe; s4, judging the surface defect of the steel pipe through the model of the S3 and the data acquired in the S1; the invention determines the surface defects of the steel pipe through the optimal curve fitting model of the surface profile of the steel pipe, accurately determines the positions, the sizes, the center coordinates and the radiuses of the surface defects of the steel pipe, solves the problem of missing detection of equipment such as ultrasonic detection, magnetic flux missing detection and eddy current detection at present through the non-contact detection method, realizes the accurate detection of the surface defects of the steel pipe, and improves the detection precision and efficiency.
Description
Technical Field
The invention relates to the technical field of automatic detection, in particular to a non-contact type steel pipe surface defect detection method.
Background
The common quality detection modes of the steel pipe such as ultrasonic detection, magnetic leakage detection, eddy current detection and the like are mainly used for detecting cracks and folds, certain leakage detection conditions exist for pits, the ultrasonic detection and the magnetic leakage detection are both contact type detection, a probe is directly contacted with the surface of the steel pipe, the requirement on the straightness of the steel pipe is high, and misjudgment or leakage judgment is easily caused by poor contact; in addition, the ultrasonic detection equipment and the magnetic leakage detection equipment are limited by the size of the probe, the possibility of leakage detection exists for small pits, the sensitivity of eddy current detection to the pits is higher, but no corresponding method exists for large-diameter steel pipes with the diameter of more than 180mm at present, therefore, in actual production, a plurality of detection technologies are often adopted and are combined with manual visual detection to judge, and because the manual surface detection is time-consuming and labor-consuming, the reliability of the detection process is greatly influenced by human factors, and the leakage report is easy to occur, so that the non-contact steel pipe surface defect detection method is provided for the problems.
Disclosure of Invention
The invention provides a non-contact steel pipe surface defect detection method, which solves the problem of missing detection of the existing ultrasonic detection, magnetic flux leakage detection, eddy current detection and other equipment, is suitable for online detection of the steel pipe surface, has low algorithm calculation amount, high defect detection speed and high accuracy, and improves the working efficiency.
In order to achieve the above purpose, the invention is realized by adopting the following technical scheme:
a non-contact steel pipe surface defect detection method comprises the following steps:
s1, acquiring three-dimensional point cloud data of a steel pipe surface profile by using a laser sensor;
s2, eliminating noise points by using a limiting amplitude noise reduction filter;
s3, establishing a best curve fitting model of the surface profile of the steel pipe;
s4, judging the surface defect of the steel pipe through the model of S3 and the data acquired in S1.
Further, the laser sensors are symmetrically arranged around the steel pipe, the laser lines of the sensors are kept perpendicular to the moving direction of the steel pipe, and the measuring range of the laser sensors covers the surface profile of the steel pipe.
Further, the step of removing noise points by using the limiting amplitude noise reduction filter is as follows:
s21, determining the maximum allowable deviation value of the cloud data of two adjacent points;
s22, performing difference calculation on the front point and the rear point of the acquired point cloud data, and recording the current point cloud data with the difference larger than the maximum allowable deviation value as noise points;
s23, repeating the step S22, detecting the data one by one, and eliminating noise points.
Further, in the step S3, the distance from each data point to the center of the outline of the point is calculated through a circular curve equation, and then the center coordinates and the radius of the outline of the point of the steel pipe are determined through a least square method and an extremum principle.
Further, the step of S4 for judging the surface defect of the steel pipe is as follows:
s41, selecting data points at equal intervals according to the sequence of index values of the point cloud data for one frame of the point cloud data;
s42, bringing the selected data points into a best curve fitting model of the surface profile of the steel pipe, and calculating the circle center coordinates and the radius of a circular curve in the fitting model by adopting a least square method;
s43, calculating the distance between the rest data points and the fitted curve, calculating the average distance, and judging the data points as suspicious defect points if the distance between the data points and the fitted curve is larger than a given threshold value;
s44, repeating the steps S41 to S43, and reselecting the data point in the frame of point cloud data to judge the suspicious defect point;
s45, selecting a fitting curve parameter circle center coordinate and radius corresponding to the minimum average distance in the point cloud data of the frame, and recording a defect suspicious point cloud data index value in an array;
s46, carrying out continuous frame point cloud data calculation, repeating S41 to S45,
s47, after detecting continuous frame point cloud data, calculating the occurrence times of each index value in the array, and if the occurrence times of each index value in the array/the number of frames of the point cloud data are greater than or equal to a given probability threshold, judging that the suspicious point cloud data corresponding to the index value are defect data, and judging that the continuous frame point cloud data have defects;
s48, positioning the defect and calculating the size of the defect;
s49, calculating out-of-roundness of the steel pipe.
S50, calculating the minimum average distance of continuous multi-frame point cloud data of the steel pipe, and selecting the center coordinates and the radius of the best fitting curve parameters corresponding to the minimum average distance.
Compared with the prior art, the invention has the beneficial effects that:
1) The established limiting amplitude noise reduction filter eliminates environmental noise points, meanwhile, the defect information is reserved, and the defect detection accuracy is ensured;
2) The position, the size, the circle center and the radius of the surface defect of the steel pipe are precisely determined by a curve fitting model with the optimal profile of the surface of the steel pipe and a method for judging the surface defect of the steel pipe, a probability threshold method is introduced in the defect detection process, the anti-interference capability is improved, and instability is avoided;
3) The non-contact detection method solves the problem of missing detection of the existing ultrasonic detection, magnetic flux leakage detection, eddy current detection and other equipment, realizes the accurate detection of the surface defects of the steel pipe, and improves the detection precision and efficiency.
Drawings
Fig. 1 is a flowchart of the steel pipe surface defect detection according to the embodiment of the invention.
FIG. 2 is a schematic diagram of a sensor position according to an embodiment of the invention.
Fig. 3 is an original graph of point cloud data of a steel pipe simulation object acquired by a single sensor according to an embodiment of the invention.
Fig. 4 is a flow chart of cloud data processing of the limiting amplitude noise reduction filter according to the embodiment of the present invention.
Fig. 5 is a simulated physical point cloud of the steel pipe after noise reduction according to the embodiment of the invention.
Fig. 6 is a graph of the fitting effect of a cloud image of the contour points on the surface of a frame of steel pipe according to the embodiment of the invention.
Fig. 7 is a schematic view of a cloud image defect of a profile point on the surface of a frame of steel pipe according to an embodiment of the invention.
In the figure: 1. laser sensor 2. Steel pipe
Detailed Description
The following is a further description of embodiments of the invention, taken in conjunction with the accompanying drawings:
fig. 1 is a flowchart of the detection according to an embodiment of the present invention. The invention discloses a non-contact steel pipe surface defect detection method, which comprises the following steps:
s1, acquiring cloud data of the positions of profile points on the surface of a steel pipe by using a laser sensor: referring to fig. 2, the sensors adopt 4 three-dimensional laser sensors, the laser lines of each laser sensor are ensured to be perpendicular to the motion direction of the steel pipe, the included angle between every two adjacent laser sensors is 90 degrees, the measuring range of each 4-path laser sensor completely covers the surface profile of the steel pipe, the laser sensors collect multi-frame steel pipe point cloud data, each point cloud data consists of three coordinate points, wherein x coordinates reflect length information, y coordinates reflect the number of frames of data of the point cloud data, and z coordinates reflect depth information on the surface profile of the steel pipe, therefore, each point in each frame of data of each sensor can be expressed as a group of two-dimensional coordinates (x, z), fig. 3 is a steel pipe simulated object point cloud diagram collected by a single sensor, and points in circles in the figure are noise points.
S2, eliminating noise points by using a limiting amplitude noise reduction filter, see fig. 4, wherein the specific steps are as follows:
s21, determining a maximum allowable deviation value delta z of two adjacent points according to the defect judgment standard of the surface profile of the steel pipe for each frame of point cloud data acquired by each sensor;
s22, respectively calculating the |z for the nth point cloud data n -z n-1 |and |z n+1 -z n |, when |z n -z n-1 |<Δz or |z n+1 -z n |<At Δz, the nth is markedThe point cloud data is a non-noise point, otherwise, the point cloud is marked as a noise point;
s23, repeating the step S22 in sequence, detecting noise points from the point cloud data one by one, removing the noise points, and referring to FIG. 5, simulating an object point cloud image for the steel pipe after removing the noise.
S3, establishing a best curve fitting model of the surface profile of the steel pipe: because the profile of the outer surface of the steel pipe is composed of arc lines, the profile of the steel pipe is fitted by adopting a circular curve model, and the profile of the surface of the steel pipe is fitted by adopting a best curve fitting model:
R 2 ＝(x-A) 2 +(z-B) 2 (1)
let a= -2a, b= -2b, c=a 2 +B 2 -R 2 Wherein (A, B) is the position coordinate of the circle center of the outline of the point of the steel pipe, and R is the radius of the outline of the point of the steel pipe;
thus another expression of the circular curve equation is: x is x 2 +y 2 +ax+bz+c＝0(2)
Existing sample set (x) i ,z i ) I e (1, 2,3,., N), point-to-center distance d i According to the least squares method, the objective function formula is as follows:
converting the formula (3) into a linear equation set by utilizing the extremum principle, solving parameters a, b and c, wherein the formula is as follows:
the circle centers (A, B) and the radius R are respectively:
the coefficient matrix of the equation set (4) is a positive symmetric matrix, the linear equation set is solved, and the coefficients a, B and c of the equation can be uniquely determined, so that the circle center (A, B) and the radius R of a certain profile of the pipe are determined;
fig. 6 is a graph of a fitting effect of a frame of a steel pipe surface contour point cloud image, 31 in the graph is simulated object point cloud data of the steel pipe after noise reduction, 32 in the graph is a fitted circle curve of the point cloud data, and it can be seen from the graph that the circle curve fitting model can better recover original data and can be applied to defect detection.
S4, when the fitted curve contains defect points, the fitted curve deviates from an actual steel pipe contour line, so that the defect points are prevented from being brought into a fitted model when the fitted curve is fitted, multiple times of curve fitting are needed, and curve fitting is carried out by different point cloud data each time, and the specific detection steps are as follows:
s41, selecting 3 data points of one frame of point cloud data at equal intervals according to the sequence of the data index values. For example, one frame of steel pipe surface contour point cloud data set is q= { (x) i ,z i ) I=0, 1,2, N, n=n/3, select p 1 ＝(x 0 ,z 0 ),p 2 ＝(x n ,z n ),p 3 ＝(x 2n ,z 2n ) Fitting the data points as a model;
s42, according to the best curve fitting model of the surface profile of the steel pipe established in the step S3, p is calculated 1 ，p 2 ，p 3 Carrying out model loading, and calculating circular curve parameters A, B and R in the fitting model by adopting a least square method;
s43, calculating the distance between the rest data points and the fitted curve, calculating the average distance, and judging the data points as suspicious defect points if the distance between the data points and the fitted curve is larger than a given threshold epsilon;
s44, repeating SS41 to SS43, and then reselecting p 1 ，p 2 ，p 3 The next set of points is p, compared to the three points in S41 1 ＝(x 10 ,z 10 ),p 2 ＝(x n+10 ,z n+10 ),p 3 ＝(x 2n+10 ,z 2n+10 ) And 2n+10<N；
S45, calculating the circle center and the radius of the steel pipe, selecting the circle center and the radius of a fitting curve parameter corresponding to the minimum average distance in the point cloud data of the frame and the cloud index value of the defect suspicious point cloud data, and recording the circle center and the radius in an Array;
s46, repeating S41 to S45 for the next frame of point cloud data;
s47, after detecting continuous k frames of point cloud data, calculating the occurrence number of each index value in the Array, marking as m, calculating the value of m/k, and giving a probability threshold epsilon p If m/k is greater than or equal to epsilon p The defect suspicious point cloud data corresponding to the index value is defect data;
s48, positioning the defect and calculating the size of the defect: calculating each continuous index value segment, finding out the corresponding coordinates of the defect points according to the index values, obtaining the defect length in the x-axis direction and the maximum defect depth in the z-axis direction, positioning the position of the defect, and determining the number n of occurrences of the same continuous index segments in the Array and the resolution in the Y-direction as Y res Calculating the width n x Y of the defect res The area of the defect is calculated based on the length and width of the defect, see fig. 7, where 41 is the localized defect.
S49, calculating out-of-roundness NR of the steel pipe:
wherein R is max Fitting a maximum value of curve radius in units of m and R for continuous k-frame point cloud data min And fitting a minimum value of the radius of the curve to the continuous k-frame point cloud data, wherein the minimum value is expressed as a unit m.
S50, obtaining the minimum average distance and the center coordinates (A, B) and R of the best fit curve parameters from S45 for each frame of point cloud data, comparing the minimum average distance in the continuous k frames of point cloud data, and selecting the center coordinates (A, B) and R of the best fit curve parameters corresponding to the minimum average distance from the minimum average distance, namely the center coordinates (A, B) and the radius R of the steel pipe.
The above examples are implemented on the premise of the technical scheme of the present invention, and detailed implementation manners and specific operation processes are given, but the protection scope of the present invention is not limited to the above examples. The methods used in the above examples are conventional methods unless otherwise specified.
Claims (5)
1. The non-contact steel pipe surface defect detection method is characterized by comprising the following steps of:
s1, acquiring three-dimensional point cloud data of a steel pipe surface profile by using a laser sensor;
s2, eliminating noise points by using a limiting amplitude noise reduction filter;
s3, establishing a best curve fitting model of the surface profile of the steel pipe;
s4, judging the surface defect of the steel pipe through the model of S3 and the data acquired in S1.
2. The non-contact steel pipe surface defect detection method according to claim 1, wherein the laser sensors are symmetrically arranged around the steel pipe, the laser lines of the sensors are kept perpendicular to the moving direction of the steel pipe, and the measuring range of the laser sensors covers the surface profile of the steel pipe.
3. The method for detecting the surface defects of the steel pipe according to claim 1, wherein the step of eliminating noise points by using the limiting amplitude noise reduction filter comprises the following steps:
s21, determining the maximum allowable deviation value of the cloud data of two adjacent points;
s22, performing difference calculation on the front point and the rear point of the acquired point cloud data, and recording the current point cloud data with the difference larger than the maximum allowable deviation value as noise points;
s23, repeating the step S22, detecting the data one by one, and eliminating noise points.
4. The method for detecting the surface defects of the steel pipe according to claim 1, wherein in the step S3, the distance from each data point to the center of the outline of the point is calculated through a circular curve equation, and then the center coordinates and the radius of the outline of the point of the steel pipe are determined through a least square method and an extremum principle.
5. The method for detecting surface defects of a steel pipe according to claim 1, wherein the step of S4 determining the surface defects of the steel pipe comprises the steps of:
s41, selecting data points at equal intervals according to the sequence of index values of the point cloud data for one frame of the point cloud data;
s42, bringing the selected data points into a best curve fitting model of the surface profile of the steel pipe, and calculating the circle center coordinates and the radius of a circular curve in the fitting model by adopting a least square method;
s43, calculating the distance between the rest data points and the fitted curve, calculating the average distance, and judging the data points as suspicious defect points if the distance between the data points and the fitted curve is larger than a given threshold value;
s44, repeating the steps S41 to S43, and reselecting the data point in the frame of point cloud data to judge the suspicious defect point;
s45, selecting a fitting curve parameter circle center coordinate and radius corresponding to the minimum average distance in the point cloud data of the frame, and recording a defect suspicious point cloud data index value in an array;
s46, carrying out continuous frame point cloud data calculation, repeating S41 to S45,
s47, after detecting continuous frame point cloud data, calculating the occurrence times of each index value in the array, and if the occurrence times of each index value in the array/the number of frames of the point cloud data are greater than or equal to a given probability threshold, judging that the suspicious point cloud data corresponding to the index value are defect data, and judging that the continuous frame point cloud data have defects;
s48, positioning the defect and calculating the size of the defect;
s49, calculating out-of-roundness of the steel pipe.
S50, calculating the minimum average distance of continuous multi-frame point cloud data of the steel pipe, and selecting the center coordinates and the radius of the best fitting curve parameters corresponding to the minimum average distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311361573.2A CN117434083A (en) | 2023-10-20 | 2023-10-20 | Non-contact type steel pipe surface defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311361573.2A CN117434083A (en) | 2023-10-20 | 2023-10-20 | Non-contact type steel pipe surface defect detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117434083A true CN117434083A (en) | 2024-01-23 |
Family
ID=89556253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311361573.2A Pending CN117434083A (en) | 2023-10-20 | 2023-10-20 | Non-contact type steel pipe surface defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117434083A (en) |
-
2023
- 2023-10-20 CN CN202311361573.2A patent/CN117434083A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751604B (en) | Online detection method for weld defects of steel pipe based on machine vision | |
| CN107341802B (en) | Corner sub-pixel positioning method based on curvature and gray scale compounding | |
| CN113465511B (en) | Steel coil size online measurement and omnibearing end surface defect online detection method | |
| CN109035224B (en) | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud | |
| CN111738985B (en) | Visual detection method and system for weld joint contour | |
| CN113706537B (en) | Irregular workpiece detection method based on machine vision | |
| CN114240944B (en) | Welding defect detection method based on point cloud information | |
| CN105184792B (en) | A kind of saw blade wear extent On-line Measuring Method | |
| CN112198170B (en) | Detection method for identifying water drops in three-dimensional detection of outer surface of seamless steel tube | |
| CN116228652A (en) | Pipeline weld joint surface defect detection method based on three-dimensional point cloud curvature | |
| CN108876771B (en) | Undercut welding defect detection method | |
| CN111524154B (en) | Image-based tunnel segment automatic segmentation method | |
| CN113947583A (en) | Weld joint nondestructive testing method based on deep learning two-dimensional time sequence image | |
| CN113848209B (en) | Dam crack detection method based on unmanned aerial vehicle and laser ranging | |
| CN108844469B (en) | Method and system for testing workpiece step height based on laser | |
| CN114581368A (en) | Bar welding method and device based on binocular vision | |
| CN117434083A (en) | Non-contact type steel pipe surface defect detection method | |
| Li et al. | Narrow weld joint recognition method based on laser profile sensor | |
| CN116740036A (en) | Method and system for detecting cutting point position of steel pipe end arc striking and extinguishing plate | |
| CN112525923A (en) | Shared juice platform pipeline inner wall detection method and system and readable storage medium | |
| CN114463258B (en) | Rolling stock brake pad abrasion detection method based on deep learning technology | |
| CN107705312B (en) | Method for extracting welded seam edge points based on line scanning data | |
| CN110021027B (en) | Edge cutting point calculation method based on binocular vision | |
| CN113469988A (en) | Defect identification method | |
| CN114549403A (en) | Multi-monomer intelligent precise geometric circle center detection method for side section of mechanical part |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |