CN115684271B - Formed steel bar qualification detection method based on image recognition - Google Patents
Formed steel bar qualification detection method based on image recognition Download PDFInfo
- Publication number
- CN115684271B CN115684271B CN202211720641.5A CN202211720641A CN115684271B CN 115684271 B CN115684271 B CN 115684271B CN 202211720641 A CN202211720641 A CN 202211720641A CN 115684271 B CN115684271 B CN 115684271B
- Authority
- CN
- China
- Prior art keywords
- bending
- steel bar
- abnormal
- bending point
- function curve
- 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.)
- Active
Links
Images
Classifications
-
- 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
Abstract
The invention relates to the field of material detection, in particular to a formed steel bar qualification detection method based on image recognition.
Description
Technical Field
The invention relates to the field of material detection, in particular to a formed steel bar qualification detection method based on image recognition.
Background
The reinforcing steel bar is steel for reinforced concrete or prestressed reinforced concrete, and is widely applied in the field of buildings, so that the production and detection of the reinforcing steel bar are vital, and various types of reinforcing steel bar automatic production detection equipment are applied along with the progress of the technological level;
chinese patent publication No.: CN109632481A discloses a detection system for steel bar tensile deformation and an operation method thereof, the invention provides a detection system for steel bar tensile deformation, a light source system, a tension sensing system, a CCD imaging system, an acquisition system and a software processing system, wherein the light source system provides a light intensity signal; the tension sensing system provides tension for the tensile deformation of the steel bar and transmits the generated tension data to the software processing system; the CCD imaging system comprises a lens group and a CCD chip, wherein the lens group acquires image information of deformation of the steel bar, and then the CCD chip converts the image information from light to electricity; the software processing system receives the obtained tension data and image information, integrates the tension data and the image information and converts the tension data and the image information into a tension deformation two-dimensional image; the acquisition system filters, amplifies and A/D converts the tension data and the image information, converts the analog signals into digital signals and transmits the digital signals to the software processing system for processing. The invention also provides an operation method of the detection system for the tensile deformation of the steel bar. The invention can detect the tensile deformation of the reinforcing steel bar with high precision and reliability.
However, the prior art has the following problems,
1. in the prior art, a detection technology for steel bar quality parameters in the steel bar production process, particularly the detection for the steel bar quality parameters in the steel bar bending production process, is lacked;
2. in the prior art, the characterization of the quality parameters of the reinforcing steel bar by the heat generated in the reinforcing steel bar bending process is not considered, and especially in the bending process, the strength of each part of the reinforcing steel bar may be different, so that the conversion conditions of the mechanical energy in the reinforcing steel bar bending process are different due to the different strengths during the bending process, and the heating value of the bending part is different.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method for detecting the qualification of a formed steel bar based on image recognition, which is characterized by comprising:
s1, detecting temperature change data of each bending point in the bending process of the steel bar through an infrared imaging temperature tester, detecting the bent steel bar, and judging abnormal steel bars;
s2, constructing a sample database based on temperature change data of each bending point of the abnormal reinforcing steel bar in the bending process, wherein the construction process comprises the steps of screening the abnormal reinforcing steel bar according to the abnormal type, and storing the material attribute of the screened abnormal reinforcing steel bar, the bending angle of each bending point in the bending process and the temperature change data into the sample database;
s3, acquiring an incidence relation between a characterization function curve and a bending angle based on temperature change data, wherein the characterization function curve is formed by fitting a plurality of temperature and time change function curves constructed according to the temperature change data, and the temperature change data is data of bending points with the same bending angle under the same condition in the sample database;
s4, comparing a function curve of the temperature and the time of the bending point in the production process of the steel bar with a characterization function curve to judge whether the steel bar is abnormal or not according to a comparison result, wherein the selected characterization function curve needs to have an incidence relation with the bending angle of the bending point during comparison;
and S5, screening the reinforcing steel bars with abnormal bending points.
Further, in the step S1, an infrared imaging temperature tester is arranged on one side of the steel bar bending device to obtain temperature change data of each bending point of the steel bar during the bending process, and a camera is arranged on the bending device to obtain an image of the steel bar during the bending process, so as to determine the bending angle of each bending point according to the image.
Further, in the step S1, when the bent reinforcing steel bar is detected, the method includes performing size detection and bending point strength detection, wherein,
when the dimension detection is carried out, comparing the outline pattern of the steel bar with the outline pattern of the standard part to obtain the pattern contact ratio, comparing the pattern contact ratio with a preset contact ratio standard, and judging that the steel bar is abnormal and the abnormal type is unqualified in dimension when the comparison result meets a first comparison condition;
when the strength of the bending points is detected, the strength of each bending point of the steel bar is compared with a preset strength standard, and when the comparison result meets a second comparison condition, the steel bar is judged to be abnormal, and the abnormal type is that the strength of the bending points is unqualified;
the first comparison condition is that the coincidence degree of the pattern is lower than the preset coincidence degree standard, the second comparison condition is that the strength of the bending point is lower than the preset strength standard, the contour pattern is obtained by shooting through the camera, and the strength of each bending point is obtained by testing through a strength detector.
Furthermore, in the step S2, when abnormal steel bars are screened,
if the abnormal reason of the abnormal reinforcing steel bar is that the strength of the bending point is unqualified, screening the abnormal reinforcing steel bar, and determining the material property of the abnormal reinforcing steel bar, wherein the material property comprises the bending strength and the section radius of the abnormal reinforcing steel bar.
Further, in the step S3, when the characterization function curve is fitted, the bending angle and the temperature change data of each bending point of the abnormal steel bar with the same material attribute in the sample database during the bending process are extracted, a plurality of function curves of temperature with respect to time change are constructed according to the temperature change data of the bending points with the same bending angle, the plurality of function curves are fitted into the characterization function curve, and the incidence relation between the characterization function curve and the bending angle is established.
Further, in the step S4, the same condition includes that material attributes are the same, the characteristic function curve obtained by fitting needs to be distinguished based on the material attribute of the abnormal steel bar corresponding to the selected temperature change data when the fitting is performed, the characteristic function curve obtained by fitting is stored in different fitting databases based on the difference of the distinguishing result, and when the function curve of the temperature and the time of the bending point in the steel bar production process is compared with the characteristic function curve, the characteristic function curve in the corresponding fitting database needs to be called according to the material attribute of the steel bar to be compared with the function curve.
Further, in the step S4, when the function curve is compared with the characterization function curve, the similarity C between the function curve and the characterization function curve is calculated and compared with a preset similarity contrast parameter C0, wherein,
if the comparison result meets a third comparison condition, judging that the bending point is abnormal in bending;
the third comparison condition is that C is more than or equal to C0.
Further, the step S4 further includes shooting an image of the steel bar during bending by a camera, determining a profile of the steel bar according to the image, establishing a rectangular coordinate system with a center of the profile of the steel bar, and determining whether there is a bending point symmetrical based on coordinate axes;
if the bending points are symmetrical based on the coordinate axes and the bending angles of the bending points are the same, the bending points are marked as symmetrical bending points.
Further, in the step S4, when it is determined whether there is an abnormality in the symmetric bending point, the temperature change data in the bending process of the symmetric bending point is called, a change curve of the temperature at the symmetric bending point with respect to time is constructed according to the temperature change data, and the curve fitting difference E is calculated according to the formula (1),
in the formula (1), t represents time, t0 represents bending completion time, F1 (t) represents a transformation function of temperature at a first bending point in the symmetrical bending points with respect to time, F2 (t) represents a transformation function of temperature at a second bending point in the symmetrical bending points with respect to time, and F0 represents a preset difference quantity comparison parameter;
and determining the difference delta T between the maximum temperature of the first bending point and the maximum temperature of the second bending point in the symmetrical bending points.
Further, when it is determined whether or not there is an abnormality in the symmetric bending point based on the temperature change data in the step S4,
comparing the curve fitting difference quantity E with a preset fitting difference comparison parameter E0, and comparing the difference value DeltaT with a preset difference comparison parameter DeltaT 0,
if the comparison result meets the fourth comparison condition, judging that the symmetrical bending point is abnormal,
the fourth comparison condition is that Δ T >. DELTA.T 0 is still present when E.gtoreq.E 0.
Compared with the prior art, the temperature change data of each bending point in the bending process of the steel bar is acquired, the bent steel bar is detected, the temperature change data and the material attribute corresponding to the abnormal bending steel bar are stored in the sample database, the temperature change data of the steel bar at each bending point in the bending process are detected when the sample database is enough in capacity, the material attribute and the temperature change data of each bending point are compared with the data in the sample database, whether each bending point of the steel bar is abnormal or not is judged according to the comparison result, whether the bending point is abnormal or not can be judged according to the temperature change data of each bending point in the production process through the process, the detection efficiency is improved, the detection mode is convenient, and the detection result is reliable and accurate.
Particularly, the infrared imaging temperature tester arranged in the step S1 can continuously monitor the bending process of the reinforcing steel bar, so that temperature change data of each bending point of the reinforcing steel bar can be obtained, the obtained data are continuous, a function curve of the temperature of each bending point with respect to time change can be conveniently constructed subsequently, and data analysis is facilitated.
Particularly, in step S2 of the present invention, a sample database is constructed based on temperature change data of each bending point of the abnormal steel bar during the bending process, and a correlation between a characterization function curve based on the temperature change data and a bending angle is obtained, in an actual situation, because defects may exist inside the steel bar or fine defects may exist on the surface, such a situation is not easy to be detected in batch, and quality parameters of each part of the steel bar may have differences, which further causes different strengths of each part of the steel bar, and further may cause a situation of breaking, cracking or obviously insufficient strength of the bending part after bending, and because bending needs to do work on the steel bar, the strength determines the magnitude of the work, so that the temperature emitted from the abnormal part of the bending is different from the temperature of the normal part, therefore, the sample database is established to store the temperature change data of each bending position of the abnormal steel bar during the bending process,
and a plurality of characteristic function curves are established, and then whether the bending point of the reinforcing steel bar is abnormal or not can be judged by acquiring the temperature change condition construction function area of each bending position of the reinforcing steel bar and comparing the temperature change condition construction function area with the characteristic function curves in the production process, the detection mode is convenient and fast, the detection result is reliable and accurate, and the detection can be carried out in the production process.
Particularly, the step S4 of the invention further includes acquiring an image shot by the camera, and screening bending points according to the image, wherein the screened bending points are points with similar bending data in the same steel bar, in an actual situation, for the points with similar bending data, the heat emitted in the bending process is also similar, so that a large difference does not occur, and for a situation with a large difference, the bending points may have abnormal bending.
Drawings
FIG. 1 is a schematic diagram illustrating steps of a method for detecting the eligibility of a formed steel bar based on image recognition according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a profile of a rebar according to an embodiment of the invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Referring to fig. 1, which is a schematic diagram illustrating steps of a method for detecting the eligibility of a formed steel bar based on image recognition according to an embodiment of the present invention, the method for detecting the eligibility of a formed steel bar based on image recognition according to the present invention includes:
s1, detecting temperature change data of each bending point in the bending process of the steel bar through an infrared imaging temperature tester, detecting the bent steel bar, and judging an abnormal steel bar;
s2, constructing a sample database based on temperature change data of each bending point of the abnormal reinforcing steel bar in the bending process, wherein the construction process comprises the steps of screening the abnormal reinforcing steel bar according to the abnormal type, and storing the material attribute of the screened abnormal reinforcing steel bar, the bending angle of each bending point in the bending process and the temperature change data into the sample database;
s3, acquiring an incidence relation between a characterization function curve and a bending angle based on temperature change data, wherein the characterization function curve is formed by fitting a plurality of temperature and time change function curves constructed according to the temperature change data, and the temperature change data is data of bending points with the same bending angle under the same condition in the sample database;
s4, comparing a function curve of the temperature and the time of the bending point in the production process of the steel bar with a characterization function curve to judge whether the steel bar is abnormal or not according to a comparison result, wherein the selected characterization function curve needs to have an incidence relation with the bending angle of the bending point during comparison;
and S5, screening the reinforcing steel bars with abnormal bending points.
Specifically, in the step S1, an infrared imaging temperature tester is arranged on one side of the steel bar bending device to obtain temperature change data of each bending point of the steel bar during the bending process, and a camera is arranged on the bending device to obtain an image of the steel bar during the bending process, so as to determine the bending angle of each bending point according to the image.
Specifically, the infrared imaging temperature tester arranged in the step S1 can continuously monitor the bending process of the reinforcing steel bar, so that temperature change data of each bending point of the reinforcing steel bar can be obtained, the obtained data are continuous, a function curve of the temperature of each bending point with respect to time change can be conveniently constructed subsequently, and data analysis is facilitated.
Specifically, for the way of determining the bending angle of the steel bar according to the image, the external computer can set a preset algorithm to determine the bending angle of the steel bar outline in the image, which is not described herein in detail for the prior art.
Specifically, the temperature change data may be recorded in the present embodiment in the form of a data matrix, and for the ith bending point temperature data matrix Ai (Ai 1, ai 2.. Ain), where Ai1 represents the temperature at the 1 st moment of the ith bending point, ai2 represents the temperature at the 2 nd moment of the ith bending point, and.
Specifically, in the step S1, when the bent reinforcing steel bar is detected, the method includes performing size detection and bending point strength detection, wherein,
when the dimension is detected, comparing the outline pattern of the steel bar with the outline pattern of the standard part to obtain the pattern contact ratio, comparing the pattern contact ratio with a preset contact ratio standard, and judging that the steel bar is abnormal and the abnormal type is unqualified in dimension when the comparison result meets a first comparison condition;
when the strength of the bending points is detected, the strength of each bending point of the steel bar is compared with a preset strength standard, and when the comparison result meets a second comparison condition, the steel bar is judged to be abnormal, and the abnormal type is that the strength of the bending points is unqualified;
the first comparison condition is that the coincidence degree of the pattern is lower than the preset coincidence degree standard, the second comparison condition is that the strength of the bending point is lower than the preset strength standard, the contour pattern is obtained by shooting through the camera, the strength of each bending point is obtained by testing through a strength detector, and for the preset coincidence degree standard and the preset strength standard, a person skilled in the art can specifically set the conditions according to the application place of the reinforcing steel bar, and details are not repeated here.
Specifically, in the step S2, when the abnormal reinforcing steel bars are screened,
if the abnormal reason of the abnormal reinforcing steel bar is that the strength of the bending point is unqualified, screening the abnormal reinforcing steel bar, and determining the material property of the abnormal reinforcing steel bar, wherein the material property comprises the bending strength and the section radius of the abnormal reinforcing steel bar.
Specifically, in the step S3, when the characterization function curve is fitted, the bending angle and the temperature change data of each bending point of the abnormal steel bar with the same material attribute in the sample database during the bending process are extracted, a plurality of function curves of which the temperature changes with respect to time are constructed according to the temperature change data of the bending points with the same bending angle, the plurality of function curves are fitted to the characterization function curve, and the incidence relation between the characterization function curve and the bending angle is established.
Specifically, in this embodiment, a process of establishing an association relationship between a characterization function curve and a bending angle is provided, where a temperature change data matrix of each bending point of a steel bar with a bending strength of 400Mpa and a cross-sectional radius of 8mm in a bending process is determined from a sample database, a temperature change data matrix of the bending point with a bending angle of 45 ° is selected from the temperature change data matrix, a plurality of function curves with temperature based on time change are established according to the selected plurality of temperature change data matrices, each function curve is fitted through MATLAB to obtain a characterization function curve fn (x), and an association relationship between the characterization function curve fn (x) and 45 ° is established.
Specifically, in the step S4, the same condition includes that material attributes are the same, the characteristic function curve obtained by fitting needs to be distinguished based on the material attribute of the abnormal steel bar corresponding to the temperature change data selected when the fitting is performed, the characteristic function curve obtained by fitting is stored in different fitting databases based on the difference of the distinguishing result, and when a function curve of the temperature and time of the bending point in the steel bar production process is compared with the characteristic function curve, the characteristic function curve in the corresponding fitting database needs to be called according to the material attribute of the steel bar to be compared with the function curve.
Specifically, in this embodiment, there may be a plurality of characterization function curves obtained by fitting a function curve determined by temperature change data of steel bars with different material properties to a fitting database, in this embodiment, the first fitting database is used to store a characterization function curve obtained by fitting a function curve of temperature change data of steel bars with bending strength of 400Mpa and a cross-sectional radius of 8mm, and if the material property of the abnormal steel bar corresponding to the selected temperature change data is bending strength of 400Mpa and a cross-sectional radius of 8mm during the characterization function curve fitting, the characterization function curve is stored in the first fitting database;
the second fitting database is used for storing a characteristic function curve which is formed by fitting a function curve of temperature change data of a steel bar with the bending strength of 450MPa and the section radius of 10mm, and if the material attribute of an abnormal steel bar corresponding to the temperature change data is bending strength of 450MPa and the section radius of 10mm during fitting of the characteristic function curve, the characteristic function curve is stored in the second fitting database;
the rest fitting databases are not described herein again, and those skilled in the art can set a corresponding number of fitting databases according to specific situations.
Specifically, in step S4, when the function curve is compared with the characterization function curve, the similarity C between the function curve and the characterization function curve is calculated and compared with a preset similarity contrast parameter C0, wherein,
if the comparison result meets a third comparison condition, judging that the bending point is abnormal in bending;
the third comparison condition is that C is more than or equal to C0.
Specifically, in step S2 of the present invention, a sample database is constructed based on temperature change data of each bending point of an abnormal steel bar during a bending process, and an association relationship between a characterization function curve based on the temperature change data and a bending angle is obtained, in an actual situation, because defects may exist inside the steel bar or fine defects may exist on the surface, such a situation is not easy to perform batch detection, and quality parameters of each part of the steel bar may have differences, which further causes different strengths of each part of the steel bar, and further a situation of fracture, crack or obvious insufficient strength of the bent part after bending may occur during bending, and since bending needs to do work on the steel bar, the strength determines the magnitude of the work, so that the temperature emitted from the abnormal part of the bending is different from the temperature of the normal part, therefore, the temperature change data of each bending position of the abnormal steel bar during the bending process is stored by establishing the sample database, and a plurality of characterization function curves are established, and further, whether the abnormal steel bar bending point is characterized by comparing the temperature change condition construction function region with the normal function curve can be determined by obtaining the sample database during the production process, so that whether the abnormal steel bar is abnormal bending position is abnormal bar, the abnormal bending point is abnormal bending point can be characterized, the detection mode, the detection result is accurate, and the detection can be performed conveniently and conveniently in the production process.
Specifically, as shown in fig. 2, the step S4 further includes capturing an image of the steel bar during bending by a camera, determining a profile of the steel bar according to the image, establishing a rectangular coordinate system with a center of the profile of the steel bar, and determining whether there is a bending point symmetrical based on coordinate axes;
if the bending points are symmetrical based on the coordinate axis and the bending angles of the bending points are the same, marking the bending points as symmetrical bending points.
Specifically, in step S4, when it is determined whether there is an abnormality in the symmetric bending point, the temperature change data in the bending process of the symmetric bending point is called, a change curve of the temperature at the symmetric bending point with respect to time is constructed according to the temperature change data, and the curve fitting difference E is calculated according to the formula (1),
in the formula (1), t represents time, t0 represents bending completion time, F1 (t) represents a transformation function of temperature at a first bending point in the symmetrical bending points with respect to time, F2 (t) represents a transformation function of temperature at a second bending point in the symmetrical bending points with respect to time, and F0 represents a preset difference contrast parameter;
and determining the difference delta T between the maximum temperature of the first bending point and the maximum temperature of the second bending point in the symmetrical bending points.
Further, when it is determined whether or not there is an abnormality in the symmetrical bending point based on the temperature change data in step S4,
comparing the curve fitting difference quantity E with a preset fitting difference comparison parameter E0, and comparing the difference value DeltaT with a preset difference comparison parameter DeltaT 0,
if the comparison result meets the fourth comparison condition, judging that the symmetrical bending point is abnormal,
the fourth comparison condition is that Δ T >. DELTA.T 0 is still present when E.gtoreq.E 0.
Specifically, the method further comprises the steps of obtaining an image shot by the camera, and screening bending points according to the image, wherein the screened bending points are points with similar bending data in the same steel bar, in an actual situation, the heat emitted in the bending process is similar for the points with similar bending data, so that a large difference cannot occur, and the bending points may have abnormal bending for the situation with the large difference.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (5)
1. A formed steel bar qualification detection method based on image recognition is characterized by comprising the following steps:
s1, detecting temperature change data of each bending point in the bending process of the steel bar through an infrared imaging temperature tester, detecting the bent steel bar, and judging an abnormal steel bar;
s2, constructing a sample database based on temperature change data of each bending point of the abnormal reinforcing steel bar in the bending process, wherein the construction process comprises the steps of screening the abnormal reinforcing steel bar according to the abnormal type, and storing the material attribute of the screened abnormal reinforcing steel bar, the bending angle of each bending point in the bending process and the temperature change data into the sample database;
s3, acquiring an incidence relation between a characterization function curve and a bending angle based on temperature change data, wherein the characterization function curve is formed by fitting a plurality of temperature and time change function curves constructed according to the temperature change data, and the temperature change data is data of bending points with the same bending angle under the same condition in the sample database;
s4, comparing a function curve of the temperature and the time of the bending point in the production process of the steel bar with a characteristic function curve to judge whether the steel bar is abnormal or not according to a comparison result, wherein the characteristic function curve selected during the comparison needs to have an incidence relation with the bending angle of the bending point;
s5, screening out the steel bars with abnormal bending points;
in the step S1, arranging an infrared imaging temperature tester at one side of the steel bar bending equipment to acquire temperature change data of each bending point of the steel bar in the bending process, arranging a camera on the bending equipment to acquire an image of the steel bar in the bending process, and determining the bending angle of each bending point according to the image;
in the step S1, when the bent reinforcing steel bar is detected, the size detection and the bending point strength detection are performed, wherein,
when the dimension is detected, comparing the outline pattern of the steel bar with the outline pattern of the standard part to obtain the pattern contact ratio, comparing the pattern contact ratio with a preset contact ratio standard, and judging that the steel bar is abnormal and the abnormal type is unqualified in dimension when the comparison result meets a first comparison condition;
when the strength of the bending points is detected, the strength of each bending point of the steel bar is compared with a preset strength standard, and when the comparison result meets a second comparison condition, the steel bar is judged to be abnormal, and the abnormal type is that the strength of the bending points is unqualified;
the first comparison condition is that the coincidence degree of the pattern is lower than the preset coincidence degree standard, the second comparison condition is that the strength of the bending point is lower than the preset strength standard, the contour pattern is obtained by shooting through the camera, and the strength of each bending point is obtained by testing through a strength detector;
the step S4 also comprises the steps of shooting an image of the steel bar in the bending process through a camera, determining the outline of the steel bar according to the image, establishing a rectangular coordinate system by using the center of the outline of the steel bar, and determining whether a bending point based on coordinate axis symmetry exists or not;
if the bending points are symmetrical based on the coordinate axes and the bending angles of the bending points are the same, marking the bending points as symmetrical bending points;
in the step S4, when judging whether the symmetrical bending point is abnormal or not, calling temperature change data in the bending process of the symmetrical bending point, constructing a change curve of the temperature at the symmetrical bending point with respect to time according to the temperature change data, and calculating a curve fitting difference quantity E according to a formula (1),
determining the difference value delta T between the maximum temperature of a first bending point and the maximum temperature of a second bending point in the symmetrical bending points;
in the step S4, when judging whether the symmetrical bending point is abnormal or not according to the temperature change data,
comparing the curve fitting difference quantity E with a preset fitting difference comparison parameter E0, and comparing the difference value DeltaT with a preset difference comparison parameter DeltaT 0,
if the comparison result meets the fourth comparison condition, judging that the symmetrical bending point is abnormal,
the fourth comparison condition is that Δ T >. DELTA.T 0 is still present when E.gtoreq.E 0.
2. The method for testing the qualification of the formed steel bars based on the image recognition as claimed in claim 1, wherein in the step S2, when the abnormal steel bars are screened,
if the abnormal reason of the abnormal reinforcing steel bar is that the strength of the bending point is unqualified, screening the abnormal reinforcing steel bar, and determining the material property of the abnormal reinforcing steel bar, wherein the material property comprises the bending strength and the section radius of the abnormal reinforcing steel bar.
3. The method for detecting the eligibility of the formed steel bar based on the image recognition as claimed in claim 1, wherein in the step S3, when the characterization function curve is fitted, the bending angle and the temperature change data of each bending point of the abnormal steel bar with the same material attribute in the sample database during the bending process are extracted, a plurality of function curves of temperature change with respect to time are constructed according to the temperature change data of the bending point with the same bending angle, the plurality of function curves are fitted to the characterization function curve, and the incidence relation between the characterization function curve and the bending angle is established.
4. The method for detecting the eligibility of the formed steel bar based on the image recognition as claimed in claim 3, wherein in the step S4, the same condition includes that material attributes are the same, the characterization function curve obtained by fitting needs to be distinguished based on the material attributes of the abnormal steel bar corresponding to the temperature change data selected during the fitting, the characterization function curve obtained by fitting is stored in different fitting databases based on the difference of the distinguishing results, and when a function curve of the temperature and the time of the bending point during the production of the steel bar is compared with the characterization function curve, the characterization function curve in the corresponding fitting database needs to be called according to the material attributes of the steel bar to be compared with the function curve.
5. The method for detecting the qualification of the formed steel bars based on the image recognition as claimed in claim 4, wherein in the step S4, when the function curve is compared with the characterization function curve, the similarity C between the function curve and the characterization function curve is calculated and compared with a preset similarity contrast parameter C0, wherein,
if the comparison result meets a third comparison condition, judging that the bending point is abnormal in bending;
the third comparison condition is that C is more than or equal to C0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211720641.5A CN115684271B (en) | 2022-12-30 | 2022-12-30 | Formed steel bar qualification detection method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211720641.5A CN115684271B (en) | 2022-12-30 | 2022-12-30 | Formed steel bar qualification detection method based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115684271A CN115684271A (en) | 2023-02-03 |
| CN115684271B true CN115684271B (en) | 2023-04-07 |
Family
ID=85057335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211720641.5A Active CN115684271B (en) | 2022-12-30 | 2022-12-30 | Formed steel bar qualification detection method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115684271B (en) |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4232554A (en) * | 1978-11-30 | 1980-11-11 | Grumman Aerospace Corporation | Thermal emission flaw detection method |
| FR2692988A1 (en) * | 1992-06-30 | 1993-12-31 | Armines | Method and device for determining the fatigue limit of a material. |
| CN100565175C (en) * | 2006-05-17 | 2009-12-02 | 中国科学院力学研究所 | Carry out the method for analysis of fatigue and detection with infrared thermal imagery |
| US8209133B2 (en) * | 2007-08-16 | 2012-06-26 | Board Of Supervisors Of Louisiana State University And Agricultural And Mechanical College | Rapid determination of fatigue failure based on temperature evolution |
| CN103076243A (en) * | 2012-12-07 | 2013-05-01 | 太原理工大学 | System for predicting fatigue limit of magnesium alloy member based on infrared thermal imaging, and method thereof |
| CN104007007B (en) * | 2014-06-13 | 2016-06-08 | 太原理工大学 | A kind of fatigue analysis method based on magnesium alloy surface of test piece temperature profile |
| CN108829878B (en) * | 2018-06-26 | 2021-10-01 | 北京理工大学 | Method and device for detecting abnormal points of industrial experimental data |
| JP7099215B2 (en) * | 2018-09-18 | 2022-07-12 | 横浜ゴム株式会社 | Hose fatigue resistance evaluation system |
| CN109632481A (en) * | 2018-12-19 | 2019-04-16 | 安徽省骏腾工程试验检测有限公司 | A kind of detection system and its operating method of steel bar stretching deformation |
| CN212301098U (en) * | 2020-04-17 | 2021-01-05 | 南昌创达新型建材有限公司 | Bending degree test structure of reinforcing bar bender for building |
| CN112630046A (en) * | 2020-12-15 | 2021-04-09 | 中国科学院长春光学精密机械与物理研究所 | Method and system for measuring performance of high-temperature material |
| CN112903427A (en) * | 2021-01-22 | 2021-06-04 | 武汉红视热像科技有限公司 | Mechanical test system and method for dynamically controlling temperature rise of surface of material |
| CN113295546A (en) * | 2021-05-10 | 2021-08-24 | 武汉精测电子集团股份有限公司 | FPC microcircuit bending damage degree verification method and device and electronic equipment |
| CN113466026A (en) * | 2021-05-19 | 2021-10-01 | 福建省建研工程检测有限公司 | Reinforcing steel bar reverse bending test fixture and test method of support roller type bending test machine |
-
2022
- 2022-12-30 CN CN202211720641.5A patent/CN115684271B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115684271A (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100580435C (en) | System and method for process variation monitor | |
| US5146779A (en) | Indentation hardness tester | |
| CN102006402A (en) | Image pick-up device and identity identification method thereof | |
| KR101628955B1 (en) | Position information detection device for roll and method thereof | |
| EP2546798A1 (en) | Biometric authentication device and biometric authentication method | |
| CN112233994B (en) | Chip gold wire detection method | |
| US20200071131A1 (en) | Elevator rope elongation measuring device | |
| CN115684271B (en) | Formed steel bar qualification detection method based on image recognition | |
| KR101643713B1 (en) | Method for inspecting of product using learning type smart camera | |
| CN116136393A (en) | Bearing ring inner ring detection system and method | |
| US20090303469A1 (en) | Crack measuring method and apparatus | |
| JP4876599B2 (en) | Quality detection method and apparatus for butt welds | |
| CN116097111A (en) | Battery pack judging method | |
| CN116307939B (en) | Cement pole quality intelligent pre-screening analysis system | |
| JP3327134B2 (en) | Testing method and apparatus for metal materials and thermometer | |
| KR102507561B1 (en) | Tensile testing device | |
| CN115020286A (en) | Method and system for sorting and picking crystal grains | |
| JP4793161B2 (en) | Quality inspection method and apparatus for butt welds | |
| CN113310996A (en) | Defect detection device and detection method thereof | |
| CN107607539B (en) | Connecting rod expansion section quality visual detection device and detection method | |
| CN113677953A (en) | Line shape measuring device, line three-dimensional image generating method, and line shape measuring method | |
| ES2350665A1 (en) | Method and device for detecting drawing defects | |
| KR100459590B1 (en) | Position detecting apparatus and method thereof | |
| JP3292063B2 (en) | Testing method and apparatus for metal materials | |
| JPH09178427A (en) | Image position measuring method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |