Method and device for detecting bolt looseness, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a method and device for detecting bolt looseness, electronic equipment and a storage medium, and the method comprises the steps: firstly, calculating the vertical coordinate fitting values of the central points of N bolts, and then judging whether each bolt is loosened or not according to the vertical coordinate fitting values of the central points of the N bolts and the vertical coordinate values of the central points of the N bolts. Compared with the mode that a gap sensor needs to be adopted to detect bolt looseness in the prior art, the operation difficulty of bolt looseness detection can be lowered.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, electronic device, and storage medium for detecting loose bolts. Background Technology

[0002] In the wind power industry, wind turbine towers (referred to as tower sections) can be manufactured and transported in sections. For example, a tower section may consist of 3 to 5 sections. On-site, the various sections of the tower are assembled into a whole using reliable connection methods. The secure fixing between the sections is a crucial step in ensuring the structural safety, rigidity continuity, and fatigue life of the tower.

[0003] In current related technologies, the following method can be used to fix the various sections of the wind turbine tower. Thick steel plate flange rings are welded to the upper and lower ends of each tower section, and the flange rings of adjacent sections are evenly connected circumferentially by multiple bolts (e.g., high-strength preloaded bolts). The number of bolts on the connection surface of a single flange ring typically depends on the tower diameter and the load. Specifically, the number of bolts on the connection surface of a single flange ring is typically 60 to 120.

[0004] Currently, gap sensors are commonly used to detect whether bolts are loose. The core principle is to determine whether the bolt is loose by measuring the minute changes in axial clearance between the bolt head or nut and the connected parts in real time. However, this method requires installing multiple gap sensors near the bolt being detected, presenting a technical challenge in terms of operational complexity.

[0005] The same technical challenges exist when detecting loose bolts in other scenarios. For example, other scenarios might involve detecting loose bolts on bridges or trains.

[0006] Therefore, how to reduce the operational difficulty of detecting loose bolts has become an urgent technical problem to be solved. Summary of the Invention

[0007] This application provides a method, apparatus, electronic device, and storage medium for detecting loose bolts, which can reduce the operational difficulty of detecting loose bolts.

[0008] In a first aspect, embodiments of this application provide a method for detecting bolt loosening, comprising: acquiring an image to be detected including N bolts; 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; 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; employing a polynomial fitting algorithm to perform a fitting operation on the abscissa and ordinate values ​​of the center points of the N bolts to obtain fitting parameters of a corresponding polynomial curve; generating a polynomial based on the fitting parameters of the polynomial curve; calculating the ordinate fitting values ​​of the center points of the N bolts based on the polynomial and the abscissa values ​​of the center points of the N bolts; and determining whether each bolt is loose 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.

[0009] Optionally, image recognition processing is performed on the image to be detected to determine the abscissa and ordinate values ​​of the center points of the N bolts, including: using a target detection model to perform image recognition processing on the image to be detected to determine the abscissa and ordinate values ​​of the center points of the N bolts.

[0010] Optionally, determining whether each bolt is loose based on the ordinate values ​​of the center points of the N bolts and the fitted values ​​of the ordinate values ​​of the center points of the N bolts includes: calculating N differences between the ordinate values ​​of the center points of the N bolts and the fitted values ​​of the N ordinate values; comparing the N differences with a preset threshold respectively; if any difference is greater than the preset threshold, then determining that the corresponding bolt is loose.

[0011] Optionally, the N bolts are some of the bolts in the tower of the wind turbine generator, and the image to be detected is a video frame in a video captured by an image capturing device.

[0012] Optionally, the x-coordinate values ​​of the center points of the N bolts are all different.

[0013] Optionally, the target detection model is the YOLO detection model.

[0014] Secondly, embodiments of this application provide an apparatus for detecting bolt loosening. A first acquisition module is used to acquire an image to be detected, including N bolts; a determination module is used to perform image recognition processing on the image to be detected to determine the abscissa and ordinate values ​​of the center points of the N bolts; 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; a second acquisition module is used to perform a polynomial fitting algorithm to fit the abscissa and ordinate values ​​of the center points of the N bolts to obtain fitting parameters for a corresponding polynomial curve; a generation module is used to generate a polynomial based on the fitting parameters of the polynomial curve; a calculation module is used to calculate the fitted ordinate values ​​of the center points of the N bolts based on the polynomial and the abscissa values ​​of the center points of the N bolts; and a determination module is used to determine whether each bolt is loose based on the ordinate values ​​of the center points of the N bolts and the fitted ordinate values ​​of the center points of the N bolts.

[0015] Optionally, the determining module is specifically used to perform image recognition processing on the image to be detected using a target detection model, so as to determine the abscissa and ordinate values ​​of the center points of the N bolts.

[0016] Optionally, the determination module is specifically used to calculate the ordinate values ​​of the center points of the N bolts and the N differences between the fitted values ​​of the N ordinate values; compare the N differences with a preset threshold respectively, and if any difference is greater than the preset threshold, determine that the corresponding bolt is loose.

[0017] Optionally, the N bolts are some of the bolts in the tower of the wind turbine generator, and the image to be detected is a video frame in a video captured by an image capturing device.

[0018] Optionally, the x-coordinate values ​​of the center points of the N bolts are all different.

[0019] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements any of the methods described in the first aspect.

[0020] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the methods described in the first aspect.

[0021] Fifthly, embodiments of this application provide a wind turbine generator set, including any of the electronic devices described in the first aspect.

[0022] This application provides a method, apparatus, electronic device, and storage medium for detecting bolt loosening. First, the fitted values ​​of the ordinates of the center points of N bolts are calculated. Then, based on the fitted values ​​and the ordinate values ​​of the center points of the N bolts, it is determined whether each bolt is loose. Compared to current related technologies that require gap sensors to detect bolt loosening, this method reduces the operational difficulty of bolt loosening detection. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A schematic flowchart of a method for detecting bolt loosening provided in an embodiment of this application; Figure 2 A schematic diagram of an implementation environment for detecting bolt loosening in a tower, provided as an embodiment of this application; Figure 3 A schematic diagram illustrating an example of a fitting curve for detecting bolt loosening, provided as an embodiment of this application; Figure 4 A schematic diagram of a device for detecting loose bolts provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0026] The terms "first" and "second," etc., used in the specification and claims herein are used to distinguish different objects, not to describe a specific order of objects. For example, "first response message" and "second response message," etc., are used to distinguish different response messages, not to describe a specific order of response messages.

[0027] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0028] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, for example, multiple processors means two or more processors, multiple elements means two or more elements, etc.

[0029] This application provides a method, apparatus, electronic device, and storage medium for detecting loose bolts, which can reduce the operational difficulty of detecting loose bolts.

[0030] like Figure 1 As shown in the illustration, this application provides a method for detecting bolt loosening. This method can be executed by an electronic device, such as a smart interactive flat panel, laptop computer, desktop computer, mobile phone, tablet computer, or server, etc. This application is not limited to this type of device. The method for detecting bolt loosening specifically includes the following steps: S11, acquire the image to be detected, which includes N bolts.

[0031] In this step, the camera (i.e., the image capturing device) captures images of the locations of N bolts to obtain an image to be detected, including the N bolts, and sends this image to the electronic device. In this way, the electronic device can acquire an image to be detected containing the N bolts. The value of N needs to meet the sample size requirements of polynomial fitting to ensure that the fitted curve accurately reflects the positional pattern of the N bolts. For example, N equals 16. The relevant content of polynomial fitting will be introduced later.

[0032] S12, perform image recognition processing on the image to be detected to determine the horizontal and vertical coordinates of the center points of the N bolts.

[0033] In this step, an object detection model can be deployed on the electronic device, such as a convolutional neural network model or a YOLO (You Only Look Once) detection model. Then, the electronic device can use the object detection model to perform image recognition processing on the image to be detected, thereby determining the x-coordinate and y-coordinate values ​​of the center points of N bolts.

[0034] It should be noted that the x-coordinate value here refers to the x-coordinate value in the image to be detected, and the y-coordinate value refers to the y-coordinate value in the image to be detected. That is, the x-coordinate and y-coordinate values ​​here are used to represent the position of the center point of the bolt in the image to be detected, and not the position of the bolt itself in actual space.

[0035] For example, the electronic device can establish a coordinate system with the top-left vertex of the image to be detected as the origin, the left side of the image as the Y-axis, and the top side of the image as the X-axis. The x-coordinate and y-coordinate values ​​of the center points of the N bolts in the image to be detected are the x-coordinate and y-coordinate values ​​in this coordinate system. The unit of the x-coordinate and y-coordinate values ​​can be pixels. It should be noted that the Y-axis direction should be consistent with or approximately consistent with the axial direction of the bolts.

[0036] With N=16, the x-coordinates and y-coordinates of the center points of the 16 bolts are {(x1,y1),(x2,y2),…,(x...y1)}, respectively. 16 ,y 16 The units for the x-coordinate and y-coordinate values ​​can be pixels. That is, the x-coordinate of the center point of the first bolt is the x1th pixel, and the y-coordinate is the y1th pixel. In other words, the center point of the first bolt is aligned with the x1th pixel on the x-axis and the y1th pixel on the y-axis. The meanings of the x-coordinate and y-coordinate values ​​of the center points of the other bolts are similar and will not be detailed here.

[0037] S13, a polynomial fitting algorithm is used to fit the horizontal and vertical coordinates of the center points of the N bolts in the image to be detected, so as to obtain the fitting parameters of the corresponding polynomial curve.

[0038] In this step, the electronic device can choose an nth-order polynomial for fitting, i.e., y=a n x n +a n-1 x n-1 +…+a1x+a0. Where a0, a1 up to a n These are the fitting parameters for the polynomial curve. The variable y represents the ordinate of the bolt's center point in the image to be detected, and the variable x represents the abscissa of the bolt's center point in the image to be detected.

[0039] The electronic device can determine the value of n based on the distribution of the x-coordinate and y-coordinate values ​​of the center points of the aforementioned N bolts in the image to be inspected. The value of n here can be less than or equal to the aforementioned value of N, depending on the distribution pattern of the center points of the N bolts in the image to be inspected.

[0040] Specifically, when the electronic device determines that the center points of N bolts are roughly arranged along a straight line (i.e., a linear curve) in the image to be inspected, it can determine that n=1. Similarly, when the electronic device determines that the center points of N bolts are roughly arranged along a quadratic curve (e.g., a parabola), it can determine that n=2. And when the electronic device determines that the center points of N bolts are roughly arranged along a cubic curve (e.g., a spiral or S-curve), it can determine that n=3. The situation is similar when n is greater than 3, and will not be elaborated further here.

[0041] Next, the electronic device can calculate a0, a1, and so on, based on the x-coordinate and y-coordinate values ​​of the center points of the aforementioned N bolts, and by fitting the data using the least squares method. n The value.

[0042] The `numpy.polyfit` function in Python is used to perform polynomial least squares fitting, and its core function is to return the coefficients (i.e., fitting parameters) of the fitted polynomial. Therefore, in practical implementations, electronic devices can use the `numpy.polyfit` function to calculate and return the aforementioned fitting parameters.

[0043] S14, Generate a polynomial based on the fitting parameters of the polynomial curve.

[0044] In this step, the electronic device can generate a corresponding polynomial based on the previously calculated fitting parameters. The expression for this polynomial is y = a n x n +a n-1 x n-1 +…+a1x+a0, where a0, a1 up to a n The value is a known quantity, that is, the value calculated in step S13. When n=1, the expression of the polynomial is y=a1x+a0. When n=2, the expression of the polynomial is y=a2x. 2 +a1x+a0. When n=3, the expression for this polynomial is y= a3x. 3 +a2x 2 +a1x+a0.

[0045] In practice, electronic devices can use numpy.poly1d (a class) in Python to generate this polynomial.

[0046] S15, based on the polynomial and the abscissa values ​​of the center points of the N bolts, calculate the ordinate fitting values ​​of the center points of the N bolts.

[0047] In this step, the electronic device can substitute the abscissa values ​​of the center points of the N bolts obtained in step S13 into the polynomial generated in step S14, thereby calculating the ordinate fitting values ​​of the center points of the N bolts. The ordinate fitting values ​​of the center points of the bolts represent the ordinate values ​​of the center points when the bolts are in a tightened state.

[0048] S16. Based on the ordinate values ​​of the center points of the N bolts and the fitted ordinate values ​​of the center points of the N bolts, determine whether each bolt has become loose.

[0049] In this step, the electronic device calculates the difference between the ordinate value of the center point of each bolt and the fitted ordinate value of that bolt's center point, thus obtaining N difference values. Then, the electronic device compares the difference value corresponding to any bolt with a preset threshold. If the difference is greater than the preset threshold, the bolt is automatically determined to be loose. If the difference is less than or equal to the preset threshold, the bolt is determined not to be loose. The electronic device can perform the above operation on each bolt in this way, thereby determining whether all bolts are loose.

[0050] The principle behind using polynomial fitting to determine bolt loosening is essentially "identifying individual anomalies based on group consistency." It doesn't directly measure loosening, but rather infers it indirectly through statistical deviations in the bolt's center point position. This offers advantages such as non-contact operation, automation, and low cost, making it suitable for monitoring large batches of regularly arranged bolts. Specifically, typically only one or two bolts become loose; it's almost impossible for most bolts to become loose simultaneously. Therefore, the polynomial curve in the aforementioned steps is determined based on the abscissa and ordinate values ​​of the center points of most bolts in a tightened state. If the difference for a particular bolt (i.e., the difference between its ordinate value and the fitted ordinate value) exceeds a preset threshold, it indicates a significant displacement of the bolt's center point, meaning the bolt has become loose.

[0051] The aforementioned preset threshold is a key parameter. Physically, it represents the maximum allowable longitudinal deviation of the bolt center point under normal tightening conditions. Setting a reasonable preset threshold is crucial for ensuring high accuracy and low false alarm rate in the bolt loosening detection process.

[0052] When setting the specific values ​​for the aforementioned preset thresholds, the following influencing factors can be considered: Imaging system accuracy: including measurement noise introduced by camera resolution, lens distortion, and focus stability. Manufacturing and assembly tolerances: the allowable bolt position tolerances of the mechanical structure itself. Image processing error: calculation errors in determining the ordinate and abscissa values ​​of the bolt's center point. Environmental interference: the influence of changes in illumination, vibration, and obstruction on the detection results. To avoid false alarms (judging normal bolts as loose) or false negatives (failing to detect actual looseness), a certain safety margin is usually added to the measured noise level.

[0053] This application embodiment uses an experimental calibration method to determine the preset threshold. Specifically, under the standard working condition where all N bolts are tightened, multiple sets of data are collected, and the difference between the ordinate values ​​of the center points of the N bolts and the fitted ordinate values ​​is calculated. The sum of the maximum difference and the preset allowance is used as the preset threshold. This application embodiment may also use other methods to determine the preset threshold, and there are no limitations on this.

[0054] In one example, 16 bolts are located on the same plane and arranged in a straight line. Currently, the third bolt is loose, meaning its center point has moved axially, while the other 14 bolts are tightened (i.e., not loose). Therefore, the center points of these 15 bolts are in a straight line. Next, the electronic device can calculate the corresponding fitting parameters and generate the polynomial y = a1x + a0. Then, based on this polynomial, it calculates the fitted ordinate values ​​of the center points of the 16 bolts. Next, the electronic device can calculate the difference between the fitted ordinate values ​​of the center points of the 16 bolts and the fitted ordinate values. By sequentially checking whether the difference for each bolt is greater than a preset threshold, it can be determined that the third bolt has become loose.

[0055] Compared to current related technologies that require the deployment of a large number of gap sensors to detect bolt loosening, the embodiments of this application only require the deployment of cameras and electronic devices, which can significantly reduce the operational difficulty of detecting bolt loosening.

[0056] It should be noted that the distribution of the N bolts in this embodiment needs to conform to a certain pattern; that is, the ordinate values ​​of the center points of the N bolts should be expressible as a function of the abscissa values. For example, the ordinate values ​​of the N center points should have a linear or quadratic relationship with the abscissa values. This is a prerequisite for the normal implementation of this embodiment.

[0057] Otherwise, if the distribution of the center points of the N bolts is chaotic (such as random distribution or multi-branch distribution), the fitted curve will have no physical meaning, and it will be impossible to distinguish whether the bolts were designed this way or have already become loose based on the aforementioned N differences.

[0058] The polynomial fitting algorithm in this application embodiment can only fit single-valued functions. A single-valued function is defined as follows: for each independent variable x in the domain, the function has one and only one dependent variable y corresponding to it.

[0059] When fitting the coordinates of the center points of N bolts, if there are two or more bolts whose center points have the same x-coordinate value but different y-coordinate values, the definition of a single-valued function will be violated, making it impossible to fit effectively using conventional polynomial fitting algorithms.

[0060] Conversely, if the x-coordinates of the center points of the N bolts are not equal, it ensures that the definition of a single-valued function is met. This allows a polynomial fitting algorithm to fit the y-coordinates and x-coordinates of the center points of the N bolts to obtain the corresponding polynomial.

[0061] In practical implementation, the camera's shooting angle can be adjusted to avoid situations where the center points of two or more bolts have the same horizontal coordinate value. For example, when N bolts are arranged along a straight line, the camera's shooting direction should be at a certain angle to the direction of the line (e.g., 90 degrees, 60 degrees, or 120 degrees), and should avoid being the same as the direction of the line.

[0062] In some embodiments of this application, the aforementioned N bolts may be some of the bolts in the tower of a wind turbine generator. In one example, multiple bolts distributed circumferentially may be provided on the connection surface of the flange ring, such as... Figure 2 As shown. It should be noted that, Figure 2 The number of bolts shown is for illustrative purposes only and does not impose any limit on the number of bolts.

[0063] A camera can be installed inside the tower. This camera can rotate 360 ​​degrees along the central axis of the tower while capturing images of the aforementioned bolts to obtain corresponding video. Since the camera's field of view is less than 360 degrees (e.g., 90 degrees), each video frame will only include a portion of the bolts. By inspecting the bolts in the video frames in the manner described above, it can be detected whether any bolts among the aforementioned portion have become loose.

[0064] This camera can rotate to capture images of all bolts. For example, with a 90-degree field of view, the camera takes an image every 90 degrees of rotation. By sequentially detecting bolts in four adjacent video frames, it can determine which bolts are loose. The camera can rotate continuously, allowing electronic equipment to continuously monitor the looseness of each bolt based on the video generated, thus achieving real-time monitoring of all bolts for loosening.

[0065] If a loose bolt is detected, the electronic equipment can promptly issue an alarm signal, reminding staff to tighten the bolt in time to prevent dangerous accidents to the tower. For example, the alarm signal can be either an audible alarm or a visual alarm.

[0066] In a specific example, 64 bolts are evenly distributed along the circumference of the flange ring's connection surface. A camera (specifically an industrial camera) captures images of the bolts from a top-down perspective, with a field of view of 90 degrees. The camera takes one image every 90 degrees of rotation, and each image frame includes 16 bolts. In one video frame, the electronic equipment can determine the horizontal coordinates of the 16 bolts as 54, 100, 146, 194, 247, 295, 345, 379, 427, 480, 521, 586, 636, 687, 746, and 790 pixels. The electronic device can also determine the ordinate values ​​of the center points of the 16 bolts as 36, 81, 181, 212, 243, 420, 467, 644, 744, 937, 1639, 1446, 1616, 1979, 2241, and 2580, in pixels. Since the distribution pattern of the center points of the 16 bolts on the image frame roughly conforms to a quadratic curve, the electronic device can generate the corresponding polynomial y = 0.004x after fitting with a quadratic polynomial. 2 +0.04x+16. By substituting the above abscissa values ​​into this polynomial, the electronic device can calculate the fitted ordinate values ​​of the center points of the 16 bolts as follows: 29, 56, 89, 147, 271, 399, 542, 657, 817, 942, 1113, 1403, 1649, 1915, 2250, 2542, in pixels. Figure 3 As shown. Then, the electronic device can calculate the differences between the ordinate values ​​and the fitted ordinate values ​​of the center points of the 16 bolts: 7, 25, 92, 65, -28, 21, -75, -13, -73, -5, 526, 43, -33, 64, -9, 38, in pixels. A preset threshold of 100 is allowed. The electronic device can determine that the difference corresponding to the 11th bolt is greater than 100, thus indicating that the 11th bolt is loose, while the other bolts are not. The point determined by the x-coordinate and ordinate values ​​of the center point of the 11th bolt is... Figure 3 The anomaly is shown in the diagram. In the above scenario, the electronic device can specifically be a cloud platform, which can communicate with the camera sequentially through a stack server, data switch, video ring network, and wireless access point.

[0067] It should be noted that the number of bolts in the above example is only for illustrative purposes, and the number of bolts can also be other numbers, which is not limited in this application embodiment.

[0068] In a similar scenario, within a wind turbine generator, the blades are connected to the hub via their blade roots, typically using high-strength bolts. Specifically, the blade root can be cylindrical, with bolt holes arranged in a ring inside. The bolts within these holes are also arranged in a ring. By placing a camera inside the blade to photograph the bolts, it's possible to detect loosening in real-time, following the aforementioned method. The underlying principle is the same as described above and will not be elaborated further here.

[0069] like Figure 4 As shown in the illustration, this application provides an apparatus for detecting bolt loosening, comprising: a first acquisition module for acquiring an image to be detected including N bolts; a determination module for 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; wherein the abscissa value is the abscissa value in the image to be detected, and the ordinate value is the ordinate value in the image to be detected; a second acquisition module for performing a polynomial fitting algorithm to fit the abscissa and ordinate values ​​of the center points of the N bolts to obtain fitting parameters of a corresponding polynomial curve; a generation module for generating a polynomial based on the fitting parameters of the polynomial curve; a calculation module for calculating the ordinate fitting value of the center points of the N bolts based on the polynomial and the abscissa values ​​of the center points of the N bolts; and a determination module for determining whether each bolt is loose based on the ordinate values ​​of the center points of the N bolts and the ordinate fitting value of the center points of the N bolts.

[0070] Optionally, the determining module is specifically used to perform image recognition processing on the image to be detected using a target detection model, so as to determine the abscissa and ordinate values ​​of the center points of the N bolts.

[0071] Optionally, the determination module is specifically used to calculate the ordinate values ​​of the center points of the N bolts and the N differences between the fitted values ​​of the N ordinate values; compare the N differences with a preset threshold respectively, and if any difference is greater than the preset threshold, determine that the corresponding bolt is loose.

[0072] Optionally, the N bolts are some of the bolts in the tower of the wind turbine generator, and the image to be detected is a video frame in a video captured by an image capturing device.

[0073] Optionally, the x-coordinate values ​​of the center points of the N bolts are all different.

[0074] The device for detecting loose bolts provided in this application embodiment can perform the method executed by the electronic device in the above embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0075] like Figure 5 As shown in the figure, this application embodiment also provides an electronic device, which includes a memory and a processor. The memory is used to store a computer program. When the computer program is executed by the processor, it can implement the method for detecting loose bolts as described above. For details, please refer to the description of the foregoing embodiments.

[0076] Specifically, at the hardware level, the electronic device may include a processor, an internal bus, and memory. The memory may include main memory and non-volatile memory. The processor reads the corresponding computer program from the non-volatile memory into main memory and then executes it. Those skilled in the art will understand that... Figure 5 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device may also include components that are larger than... Figure 5 The components shown may include more or fewer components, such as other processing hardware like a GPU (Graphics Processing Unit) or external communication ports. Of course, this application does not exclude other implementation methods besides software implementations, such as logic devices or a combination of hardware and software.

[0077] In this embodiment, the processor may include a central processing unit (CPU) or a graphics processing unit (GPU), and may also include other microcontrollers, logic gates, integrated circuits, or appropriate combinations thereof with logic processing capabilities. The memory described in this embodiment can be a storage device for storing information. In digital systems, a device capable of storing binary data can be a memory; in integrated circuits, a circuit without physical form but with storage function can also be a memory, such as RAM or FIFO; in a system, a storage device with physical form can also be called a memory. In implementation, this memory can also be implemented using a cloud storage method; the specific implementation method is not limited in this specification.

[0078] This application also provides a wind turbine generator set, which may include any of the aforementioned electronic devices.

[0079] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the method for detecting bolt loosening as described above.

[0080] This application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the method for detecting bolt loosening as described above.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0082] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for detecting bolt loosening, characterized in that, include: Obtain an image of the bolts to be inspected, including N bolts; Image recognition processing is performed on the image to be detected to determine the abscissa and ordinate values ​​of the center points of N bolts; the abscissa value is the abscissa value in the image to be detected, and the ordinate value is the ordinate value in the image to be detected. A polynomial fitting algorithm is used to fit the abscissa and ordinate values ​​of the center points of the N bolts to obtain the fitting parameters of the corresponding polynomial curve. Generate a polynomial based on the fitting parameters of the polynomial curve; Based on the polynomial and the x-coordinate values ​​of the center points of the N bolts, calculate the fitted y-coordinate values ​​of the center points of the N bolts; Based on the ordinate values ​​of the center points of the N bolts and the fitted ordinate values ​​of the center points of the N bolts, it is determined whether each bolt has become loose.

2. The method for detecting bolt loosening according to claim 1, characterized in that, The image to be detected is subjected to image recognition processing to determine the abscissa and ordinate values ​​of the center points of the N bolts, including: A target detection model is used to perform image recognition processing on the image to be detected in order to determine the abscissa and ordinate values ​​of the center points of the N bolts.

3. The method for detecting bolt loosening according to claim 1, characterized in that, The step of determining whether each bolt is loose based on the ordinate values ​​of the center points of N bolts and the fitted ordinate values ​​of the center points of N bolts includes: Calculate the ordinate values ​​of the center points of the N bolts and the N differences between the fitted values ​​of the N ordinate values; The N differences are compared with a preset threshold. If any difference is greater than the preset threshold, the corresponding bolt is determined to be loose.

4. The method for detecting bolt loosening according to claim 1, characterized in that, The N bolts are some of the bolts in the tower of the wind turbine generator set, and the image to be detected is a video frame in a video captured by an image capturing device.

5. The method for detecting bolt loosening according to claim 1, characterized in that, The x-coordinates of the center points of the N bolts are all different.

6. The method for detecting bolt loosening according to claim 2, characterized in that, The target detection model is the YOLO detection model.

7. A device for detecting loose bolts, characterized in that, include: The first acquisition module is used to acquire an image of N bolts to be detected; The determination module is used to perform image recognition processing on the image to be detected in order to determine the abscissa and ordinate values ​​of the center points of N bolts; the abscissa value is the abscissa value in the image to be detected, and the ordinate value is the ordinate value in the image to be detected. The second acquisition module is used to perform a polynomial fitting algorithm to fit the abscissa and ordinate values ​​of the center points of the N bolts to obtain the fitting parameters of the corresponding polynomial curve. A generation module is used to generate a polynomial based on the fitting parameters of the polynomial curve. The calculation module is used to calculate the fitted values ​​of the ordinates of the center points of the N bolts based on the polynomial and the abscissa values ​​of the center points of the N bolts. The determination module is used to determine whether each bolt is loose based on the ordinate values ​​of the center points of the N bolts and the fitted ordinate values ​​of the center points of the N bolts.

8. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the electronic device to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

10. A wind turbine generator set, characterized in that, Includes the electronic device as described in claim 8.

Images