CN-121981963-A - Method and device for detecting loosening of bolt, electronic equipment and storage medium

CN121981963ACN 121981963 ACN121981963 ACN 121981963ACN-121981963-A

Abstract

The embodiment of the application provides a method, a device, electronic equipment and a storage medium for detecting bolt looseness, wherein the method, the device, the electronic equipment and the storage medium can firstly calculate the ordinate fitting value of the central points of N bolts, and then judge whether each bolt looseness occurs according to the ordinate fitting value of the central points of N bolts and the ordinate value of the central points of N bolts. Compared with the mode that a gap sensor is needed to detect bolt loosening in the prior art, the embodiment of the application can reduce the operation difficulty of detecting bolt loosening.

Inventors

ZHONG QIANQIAN
FENG CHAO
ZHAO ZILIN
LIU YANG

Assignees

远景能源有限公司

Dates

Publication Date: 20260505
Application Date: 20251229

Claims (10)

1. A method of detecting bolt loosening, comprising: acquiring an image to be detected comprising N bolts; Performing image recognition processing on the image to be detected to determine the abscissa values and the ordinate values of the central points of the N bolts, wherein the abscissa values are the abscissa values in the image to be detected, and the ordinate values are the ordinate values in the image to be detected; performing fitting operation on the horizontal coordinate values and the vertical coordinate values of the central points of the N bolts by adopting a polynomial fitting algorithm to obtain fitting parameters of corresponding polynomial curves; generating a polynomial according to fitting parameters of the polynomial curve; Calculating ordinate fitting values of the central points of the N bolts according to the polynomial and the abscissa values of the central points of the N bolts; And judging whether each bolt loosens or not according to the ordinate values of the central points of the N bolts and the ordinate fitting values of the central points of the N bolts.
2. The method for detecting loosening of bolts according to claim 1, wherein performing image recognition processing on the image to be detected to determine the abscissa and ordinate values of the center points of the N bolts comprises: and carrying out image recognition processing on the image to be detected by adopting a target detection model so as to determine the horizontal coordinate values and the vertical coordinate values of the central points of the N bolts.
3. The method for detecting loosening of bolts according to claim 1, wherein said determining whether loosening of each bolt occurs based on the ordinate values of the center points of the N bolts and the ordinate fitting values of the center points of the N bolts comprises: calculating N difference values of the ordinate values of the central points of the N bolts and N ordinate fitting values; And comparing the N differences with a preset threshold value respectively, and judging that the corresponding bolt loosens if any difference is larger than the preset threshold value.
4. The method for detecting loosening of bolts according to claim 1, wherein the N bolts are part of bolts in a tower of a wind turbine generator, and the image to be detected is a video frame in a video shot by an image shooting device.
5. The method of detecting loosening of a bolt as claimed in claim 1, wherein the abscissa values of the central points of the N bolts are all not equal.
6. The method of detecting bolt looseness according to claim 2, wherein the target detection model is a YOLO detection model.
7. A device for detecting loosening of a bolt, comprising: the first acquisition module is used for acquiring images to be detected, including N bolts; The determining module is used for carrying out image recognition processing on the image to be detected so as to determine the abscissa values and the ordinate values of the central points of the N bolts, wherein the abscissa values are the abscissa values in the image to be detected, and the ordinate values are the ordinate values in the image to be detected; The second acquisition module is used for carrying out fitting operation on the horizontal coordinate values and the vertical coordinate values of the central points of the N bolts by adopting a polynomial fitting algorithm so as to obtain fitting parameters of corresponding polynomial curves; the generating module is used for generating a polynomial according to fitting parameters of the polynomial curve; the calculation module is used for calculating the ordinate fitting values of the central points of the N bolts according to the polynomial and the abscissa values of the central points of the N bolts; And the judging module is used for judging whether each bolt loosens or not according to the ordinate values of the central points of the N bolts and the ordinate fitting values of the central points of the N bolts.
8. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, wherein execution of the computer program by the processor causes the electronic device to implement the method of any one of claims 1 to 6.
9. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any one of claims 1 to 7.
10. A wind power generator set comprising the electronic device of claim 8.

Description

Method and device for detecting loosening of bolt, electronic equipment and storage medium Technical Field The present application relates to the field of computer technologies, and in particular, to a method and apparatus for detecting bolt loosening, an electronic device, and a storage medium. Background In the wind power field, a fan tower (simply referred to as a tower) can be manufactured and transported in sections. For example, the tower may comprise 3-5 sections. The segments of the tower are assembled into a whole in a reliable connection mode on site. The fixation between the sections is a key link for ensuring the structural safety, the rigidity continuity and the fatigue life of the tower. In the related art at present, the respective segments of the fan tower may be fixed in the following manner. The upper end and the lower end of each section of tower barrel are welded with thick steel plate flange rings, and the flange rings of two adjacent sections are uniformly connected along the circumference through a plurality of bolts (for example, high-strength pre-tightening bolts). The number of bolts on the connection face of the individual flange rings is generally dependent on the tower diameter and the load. Specifically, the number of bolts on the connection surface of a single flange ring is generally 60 to 120 bolts. Currently, a gap sensor is generally used to detect whether loosening of a bolt occurs. The method is characterized in that whether the bolt loosens or not is judged by measuring the change of a tiny axial gap between the bolt head or the nut and the connected piece in real time. However, in this method, a plurality of gap sensors are required to be installed near the bolt to be detected, and there is a problem in that the operation is difficult. The same technical problem exists when detecting whether the bolt is loosened in other scenes. For example, other scenarios may be to detect whether a bolt on a bridge or train is loose. Therefore, how to reduce the operation difficulty of detecting bolt loosening becomes the technical problem to be solved in the present. Disclosure of Invention The embodiment of the application provides a method, a device, electronic equipment and a storage medium for detecting bolt loosening, which can reduce the operation difficulty of detecting bolt loosening. According to a first aspect, an embodiment of the application provides a method for detecting bolt looseness, which comprises the steps of obtaining an image to be detected comprising N bolts, carrying out image recognition processing on the image to be detected to determine the abscissa value and the ordinate value of the central points of the N bolts, wherein the abscissa value is the abscissa value in the image to be detected, the ordinate value is the ordinate value in the image to be detected, carrying out fitting operation on the abscissa value and the ordinate value of the central points of the N bolts by adopting a polynomial fitting algorithm to obtain fitting parameters of a corresponding polynomial curve, generating a polynomial according to the fitting parameters of the polynomial curve, calculating the ordinate fitting values of the central points of the N bolts according to the polynomial and the abscissa values of the central points of the N bolts, and judging whether each bolt looseness occurs according to the ordinate values of the central points of the N bolts and the ordinate fitting values of the central points of the N bolts. Optionally, performing image recognition processing on the image to be detected to determine the abscissa and ordinate values of the center points of the N bolts includes performing image recognition processing on the image to be detected by using a target detection model to determine the abscissa and ordinate values of the center points of the N bolts. Optionally, the judging of whether each bolt loosens according to the ordinate values of the central points of the N bolts and the ordinate fitting values of the central points of the N bolts includes calculating N difference values of the ordinate values of the central points of the N bolts and the N ordinate fitting values, comparing the N difference values with a preset threshold value respectively, and judging that the corresponding bolt loosens if any difference value is larger than the preset threshold value. Optionally, the N bolts are part of bolts in a tower of the wind generating set, and the image to be detected is a video frame in a video shot by the image shooting device. Optionally, the abscissa values of the central points of the N bolts are not equal. Optionally, the target detection model is a YOLO detection model. In a second aspect, an embodiment of the present application provides a device for detecting bolt looseness, a first obtaining module configured to obtain an image to be detected including N bolts, a determining module configured to perform image recognition processing on the