NL2030008B1 - Method and system for monitoring state of high-strength bolt of rotating component - Google Patents
Method and system for monitoring state of high-strength bolt of rotating component Download PDFInfo
- Publication number
- NL2030008B1 NL2030008B1 NL2030008A NL2030008A NL2030008B1 NL 2030008 B1 NL2030008 B1 NL 2030008B1 NL 2030008 A NL2030008 A NL 2030008A NL 2030008 A NL2030008 A NL 2030008A NL 2030008 B1 NL2030008 B1 NL 2030008B1
- Authority
- NL
- Netherlands
- Prior art keywords
- bolt
- detected
- image
- sequence
- geometric center
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
A method and system for monitoring a state of a high-strength bolt of a rotating component. The method includes: arranging a special marked line on a bolt to be 5 detected; acquiring an image of the bolt to be detected with the special marked line; calculating a geometric center of the image of the bolt to be detected; determining a horizontal axis coordinate sequence according to the geometric center of the image of the bolt to be detected; calculating a central angle on the basis of the horizontal axis coordinate sequence to obtain a central angle sequence, the central angle being an 10 included angle between the bolt to be detected and a central marked line of a lens; and determining, according to the central angle sequence, whether the bolt to be detected is abnormal. Figure 1
Description
METHOD AND SYSTEM FOR MONITORING STATE OF HIGH-STRENGTH BOLT
OF ROTATING COMPONENT
[01] The present disclosure relates to the field of monitoring of states of high- strength bolts, and in particular, to a method and system for monitoring a state of a high-strength bolt of a rotating component.
[02] Breakage, for example, of a high-strength bolt of a rotating component will extend a fault point, which particularly damages peripheral bolts and equipment. Safety accidents caused by the breakage of the rotating component occur sometimes. At this stage, there are many ultrasonic detection methods for bolts. This method has a better detection effect on bolts. However, due to a large number of high-strength bolts on the rotating component, use of an ultrasonic measure and other measures not only consumes a lot of time, but also increases a lot of cost investment. At the same time, online detection cannot be effectively achieved with existing methods, and there is a lack of detection methods in a non-stop state.
[03] Based on this, the present disclosure provides a method and system for monitoring a state of a high-strength bolt of a rotating component.
[04] To achieve the above-mentioned purpose, the present disclosure provides the following solution.
[05] A method for monitoring a state of a high-strength bolt of a rotating component includes:
[06] arranging a special marked line on a bolt to be detected;
[07] acquiring an image of the bolt to be detected with the special marked line;
[08] calculating a geometric center of the image of the bolt to be detected;
[09] determining a horizontal axis coordinate sequence according to the geometric center of the image of the bolt to be detected;
[10] calculating a central angle on the basis of the horizontal axis coordinate sequence to obtain a central angle sequence, the central angle being an included angle between the bolt to be detected and a central marked line of a lens; and
[11] determining, according to the central angle sequence, whether the bolt to be detected is abnormal.
[12] Optionally, the calculating the geometric center of the image of the bolt to be detected specifically includes:
[13] training the image of the bolt to be detected by means of a cascade classifier to acquire a graphic feature file;
[14] identifying, on the basis of the graphic feature file, a boundary of the image of the bolt to be detected by using an identification algorithm; and
[15] calculating the geometric center of the image of the bolt to be detected according to the boundary of the image of the bolt to be detected.
[16] Optionally, the determining a horizontal axis coordinate sequence according to the geometric center of the image of the bolt to be detected specifically includes:
[17] restoring the image of the bolt to be detected to the geometric center by means of image transformation;
[18] calculating a horizontal coordinate center point of each restored image; and
[19] projecting the horizontal coordinate center point to a horizontal axis to obtain the horizontal axis coordinate sequence.
[20] Optionally, the determining, according to the central angle sequence, whether the bolt to be detected is abnormal specifically includes: [BI] differentiating adjacent data in the central angle sequence to obtain a new sequence;
[22] calculating a difference value between each item in the new sequence and the numerical value 1;
[23] determining whether the difference value is greater than a set error; and
[4] if yes, determining whether the current bolt to be detected to abnormal.
[25] Optionally, the method further includes:
[26] when it is determined that the bolt to be detected is abnormal, determining an abnormality type according to the graphic feature file.
[27] The present disclosure further provides a system for monitoring a state of a high-strength bolt of a rotating component, including:
[28] an arrangement module used for arranging a special marked line on a bolt to be detected;
[29] an acquisition module used for acquiring an image of the bolt to be detected with the special marked line;
[30] a geometric center calculation module used for calculating a geometric center of the image of the bolt to be detected;
[31] a horizontal coordinate sequence determination module used for determining a horizontal axis coordinate sequence according to the geometric center of the image of the bolt to be detected;
[32] a central angle sequence calculation module used for calculating a central angle on the basis of the horizontal axis coordinate sequence to obtain a central angle sequence, the central angle being an included angle between the bolt to be detected and a central marked line of a lens; and
[33] a determining module used for determining, according to the central angle sequence, whether the bolt to be detected is abnormal.
[34] Optionally, the geometric center calculation module specifically includes:
[35] a training unit used for training the image of the bolt to be detected by means of a cascade classifier to acquire a graphic feature file;
[36] an identification unit used for identifying, on the basis of the graphic feature file, a boundary of the image of the bolt to be detected by using an identification algorithm; and
[37] a geometric center calculation unit used for calculating the geometric center of the image of the bolt to be detected according to the boundary of the image of the bolt to be detected.
[38] Optionally, the horizontal coordinate sequence determination module specifically includes:
[39] a transformation unit used for restoring the image of the bolt to be detected to the geometric center by means of image transformation;
[40] a horizontal coordinate center point calculation unit used for calculating a horizontal coordinate center point of each restored image; and
[41] a projection unit used for projecting the horizontal coordinate center point to a horizontal axis to obtain the horizontal axis coordinate sequence.
[42] Optionally, the determining module specifically includes:
[43] a differentiation unit used for differentiating adjacent data in the central angle sequence to obtain a new sequence;
[44] a difference value calculation unit used for calculating a difference value between each item in the new sequence and the numerical value 1;
[45] a first determining unit used for determining whether the difference value is greater than a set error; and
[46] a second determining unit used for determining that the current bolt to be detected is abnormal when the difference value is greater than the set error.
[47] Optionally, the system further includes:
[48] an abnormality type determination module used for determining an abnormality type according to the graphic feature file when it is determined that the bolt to be detected is abnormal.
[49] According to the specific embodiments provided by the present disclosure, the present disclosure discloses the following technical effects.
[50] The present disclosure discloses a method and system for monitoring a state of a high-strength bolt of a rotating component. The method includes: arranging a special marked line on a bolt to be detected; acquiring an image of the bolt to be detected with the special marked line; calculating a geometric center of the image of the bolt to be detected; determining a horizontal axis coordinate sequence according to the geometric center of the image of the bolt to be detected; calculating a central angle on the basis of the horizontal axis coordinate sequence to obtain a central angle sequence, the central angle being an included angle between the bolt to be detected and a central marked line of a lens; and determining, according to the central angle sequence, whether the bolt to be detected is abnormal. By the adoption of the above method, the abnormality of the high-strength bolt of the rotating component can be quickly and accurately monitored.
[51] In order to describe the embodiments of the present disclosure or technical solutions in the existing art more clearly, drawings required to be used in the embodiments will be briefly introduced below. Apparently, the drawings in the descriptions below are only some embodiments of the present disclosure. Those ordinarily skilled in the art also can acquire other drawings according to the these drawings without creative work.
[52] FIG. 1 is a flowchart of a method for monitoring a state of a high-strength bolt of a rotating component according to the embodiments of the present disclosure; and
[53] FIG. 2 is a structural block diagram of a system for monitoring a state of a high- strength bolt of a rotating component according to the embodiments of the present disclosure.
[54] The following clearly and completely describes the technical solution in the embodiments of the present disclosure in combination with the accompanying 5 drawings of the embodiments of the present disclosure. Apparently, the described embodiments are only part of the embodiments of the present disclosure, not all embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present disclosure.
[55] In order to make the above-mentioned purposes, characteristics and advantages of the present disclosure more obvious and understandable, the present disclosure is further described in detail below with reference to the accompanying drawings and specific implementation modes.
[56] As shown in FIG. 1, a method for monitoring a state of a high-strength bolt of a rotating component includes the following steps.
[57] Step 101: a special marked line is arranged on a bolt to be detected.
[58] Step 102: an image of the bolt to be detected with the special marked line is acquired.
[59] Step 103: a geometric center of the image of the bolt to be detected is calculated. Specifically:
[60] Step 1031: the image of the bolt to be detected is trained by means of a cascade classifier (Traincascade) to acquire a graphic feature file.
[61] Step 1032: a boundary of the image of the bolt to be detected is identified, on the basis of the graphic feature file, by using an identification algorithm (OpenCV).
Step 1033: the geometric center of the image of the bolt to be detected is calculated according to the boundary of the image of the bolt to be detected.
[62] Step 104: a horizontal axis coordinate sequence is determined according to the geometric center of the image of the bolt to be detected. Specifically:
[63] Step 1041: the image of the bolt to be detected is restored to the geometric center by means of image transformation (tangential distortion and radial distortion correction).
[64] Step 1042: a horizontal coordinate center point of each restored image is calculated.
[65] Step 1043: the horizontal coordinate center point is projected to a horizontal axis to obtain the horizontal axis coordinate sequence.
[66] Step 105: a central angle is calculated on the basis of the horizontal axis coordinate sequence to obtain a central angle sequence, the central angle being an included angle between the bolt to be detected and a central marked line of a lens.
[67] The central angle is deduced by using the following formula (the radian of the central marked line of the lens is preset to be 0, described with the rust language):
[68] n=(({rs*™xc)/((r*b).powi(2)+(r*xc).powi(2)).sqrt()).asin())+{{r*xc)/(r*b)).atan()/dsit a
[69] wherers, r, and b are all related to a specific image probe of an existing type anda mounting method of the specific image probe; r denotes the radius of detected flange ring equipment; rs denotes a distance between a lens mounting position and a flange ring; b is a coefficient related to an equivalent focal length; dsit a denotes an included angle between adjacent bolts; and xc is a horizontal coordinate in the horizontal axis coordinate sequence.
[70] Step 106: whether the bolt to be detected is abnormal is determined according to the central angle sequence.
[71] Adjacent data in the central angle sequence (..., n-1, nO, m1, …) are differentiated to obtain a new sequence. A difference value between each item in this final sequence and 1 is a set error o under the condition that all the bolts are normal and uniform. If the difference value is greater than this error, it is indicated that the bolt here is abnormal.
[72] The method further includes: step 107: when it is determined that the bolt to be detected is abnormal, an abnormality type is determined according to the graphic feature file. It is known from the step 106 that the bolt at a specific position is abnormal, and the corresponding image is subjected to fine judgment (a corresponding defect bolt feature file can be obtained by means of acquisition and training of images under different defects; the image boundary acquired at the step 1033 is cut to obtain a new image; the new image is cut by applying the feature file), thus realizing detection of breakage, missing, and the like.
[73] As shown in FIG. 2, the present disclosure further provides a system for monitoring a state of a high-strength bolt of a rotating component. The system includes:
[74] an arrangement module 201 used for arranging a special marked line on a bolt to be detected;
[75] an acquisition module 202 used for acquiring an image of the bolt to be detected with the special marked line; and
[76] a geometric center calculation module 203 used for calculating a geometric center of the image of the bolt to be detected,
[77] the geometric center calculation module 203 specifically including:
[78] a training unit used for training the image of the bolt to be detected by means of a cascade classifier to acquire a graphic feature file;
[79] an identification unit used for identifying, on the basis of the graphic feature file, a boundary of the image of the bolt to be detected by using an identification algorithm; and
[80] a geometric center calculation unit used for calculating the geometric center of the image of the bolt to be detected according to the boundary of the image of the bolt to be detected.
[81] a horizontal coordinate sequence determination module 204 used for determining a horizontal axis coordinate sequence according to the geometric center of the image of the bolt to be detected,
[82] the horizontal coordinate sequence determination module 204 specifically including:
[83] a transformation unit used for restoring the image of the bolt to be detected to the geometric center by means of image transformation;
[84] a horizontal coordinate center point calculation unit used for calculating a horizontal coordinate center point of each restored image; and
[85] a projection unit used for projecting the horizontal coordinate center point to a horizontal axis to obtain the horizontal axis coordinate sequence;
[86] a central angle sequence calculation module 205 used for calculating a central angle on the basis of the horizontal axis coordinate sequence to obtain a central angle sequence, the central angle being an included angle between the bolt to be detected and a central marked line of a lens; and
[87] a determining module 206 used for determining, according to the central angle sequence, whether the bolt to be detected is abnormal.
[88] The determining module 206 specifically includes:
[89] a differentiation unit used for differentiating adjacent data in the central angle sequence to obtain a new sequence;
[90] a difference value calculation unit used for calculating a difference value between each item in the new sequence and the numerical value 1,
[91] a first determining unit used for determining whether the difference value is greater than a set error; and
[92] a second determining unit used for determining that the current bolt to be detected is abnormal when the difference value is greater than the set error.
[93] The system further includes:
[94] an abnormality type determination module 207 used for determining an abnormality type according to the graphic feature file when it is determined that the bolt to be detected is abnormal.
[95] Allthe embodiments in the specification are described in a progressive manner.
Contents mainly described in each embodiment are different from those described in other embodiments. Same or similar parts of all the embodiments refer to each other.
The system disclosed by the embodiments is relatively simply described as it corresponds to the method disclosed by the embodiments, and related parts refer to part of the descriptions of the method.
[96] The principle and implementation modes of the present disclosure are described by applying specific examples herein. The descriptions of the above embodiments are only intended to help to understand the method of the present disclosure and a core idea of the method. In addition, those ordinarily skilled in the art can make changes to the specific implementation modes and the application scope according to the idea of the present disclosure. From the above, the contents of the specification shall not be deemed as limitations to the present disclosure.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
NL2030008A NL2030008B1 (en) | 2021-12-03 | 2021-12-03 | Method and system for monitoring state of high-strength bolt of rotating component |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
NL2030008A NL2030008B1 (en) | 2021-12-03 | 2021-12-03 | Method and system for monitoring state of high-strength bolt of rotating component |
Publications (1)
Publication Number | Publication Date |
---|---|
NL2030008B1 true NL2030008B1 (en) | 2023-06-20 |
Family
ID=87001992
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
NL2030008A NL2030008B1 (en) | 2021-12-03 | 2021-12-03 | Method and system for monitoring state of high-strength bolt of rotating component |
Country Status (1)
Country | Link |
---|---|
NL (1) | NL2030008B1 (en) |
-
2021
- 2021-12-03 NL NL2030008A patent/NL2030008B1/en active
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110222436B (en) | Method and device for evaluating health state of train parts and storage medium | |
US11658346B2 (en) | Information processing method, learned model generation method, and apparatus | |
CN105222879B (en) | The long-range self-diagnosable system and its self-diagnosing method of complicated dynamic weighing sensing network | |
CN103149222A (en) | Flaw detection device in real-time imaging of ray | |
US11087450B1 (en) | Wheel matcher | |
CN112330615B (en) | Method and system for monitoring state of high-strength bolt of rotating part | |
US20200156680A1 (en) | Railway vehicle major component and system diagnosis apparatus | |
CN112469613A (en) | Method and device for diagnosing and monitoring vehicles, vehicle components and traffic lanes | |
NL2030008B1 (en) | Method and system for monitoring state of high-strength bolt of rotating component | |
CN112799372A (en) | Display method, learning completion model generation method, device, and program | |
KR100838722B1 (en) | Device for detecting the defects on the strip surface | |
Doycheva et al. | Computer vision and deep learning for real-time pavement distress detection | |
JP2018136877A (en) | Inspection management system, inspection management method and program | |
JP3293587B2 (en) | Defect marking method, work method of defect-marked coil, and method of manufacturing defect-marked coil | |
CN109017872B (en) | Preventative maintenance method and device for train wheels and storage medium | |
CN108944998B (en) | Train wheel detection and maintenance system | |
CN111998792B (en) | On-line detection method and on-line detection device for tire blank out-of-roundness of tire building machine | |
JP2003329600A (en) | Method for controlling quality of steel plate | |
CN113960071A (en) | Quality detection process and detection system for color printing products | |
Asplund et al. | Assessment of the data quality of wayside wheel profile measurements. | |
Doyle et al. | Pantograph condition monitoring system for automated maintenance inspections and prevention of overhead wiring tear downs | |
Soufhwee et al. | Visual inspection as a screening method in assembly process for quality improvement | |
CN113838033A (en) | Train wheel tread scratch image detection method and image detection system | |
Jhorar et al. | Failure Analysis and Improvement of Defective Clamping Pad During Leak Testing Process Using Kepner-Tregoe Analysis | |
CN110901688A (en) | System for linking alarm data of physically separated wireless sensors to a running train |