CN114923629A - Method for detecting vibration amplitude of spinning high-speed spindle during rotation - Google Patents
Method for detecting vibration amplitude of spinning high-speed spindle during rotation Download PDFInfo
- Publication number
- CN114923629A CN114923629A CN202210475326.4A CN202210475326A CN114923629A CN 114923629 A CN114923629 A CN 114923629A CN 202210475326 A CN202210475326 A CN 202210475326A CN 114923629 A CN114923629 A CN 114923629A
- Authority
- CN
- China
- Prior art keywords
- spindle
- smear
- pixel block
- image
- weight
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000009987 spinning Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004753 textile Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000549194 Euonymus europaeus Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M1/00—Testing static or dynamic balance of machines or structures
- G01M1/14—Determining imbalance
- G01M1/16—Determining imbalance by oscillating or rotating the body to be tested
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method for detecting vibration amplitude of a spinning high-speed spindle during rotation. The method is a method for identifying by using electronic equipment, and the vibration amplitude of the high-speed spindle is obtained by using an artificial intelligence system in the production field. The method comprises the steps of firstly identifying an image through a camera, acquiring a spindle region, detecting to obtain the edge of the spindle, carrying out data processing on the electronic region and the edge of the spindle to obtain a smear region, and further carrying out data processing on the smear region to obtain the vibration amplitude of the spindle.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method for detecting vibration amplitude of a spinning high-speed spindle during rotation.
Background
For the rotating body, if static and dynamic unbalance exists, periodic or random unbalance force can be generated to cause vibration and radiate noise, and other factors can also cause the spindle rotating at high speed to generate vibration, so that the stability of the spindle rotating at high speed, namely the vibration amplitude caused by the high-speed rotation is an important index for describing the quality of the spindle when the spindle is produced.
At present, a common spindle detection method is to acquire an image of a spindle during rotation by using a camera and simply analyze a smear in the image, and because the rotation rate of the spindle is high, the vibration amplitude of the spindle obtained by the method is influenced by superposition of the smear, so that the detection of the vibration amplitude is inaccurate.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method for detecting vibration amplitude when a spinning high-speed spindle rotates, which adopts the following technical scheme:
acquiring spindle images, and preprocessing the spindle images to obtain spindle areas;
based on the spindle area, obtaining the edge of the spindle by using an edge detection algorithm; dividing according to the edge of the spindle, obtaining pixel blocks on two sides of the edge according to the division, and judging whether the size of the pixel blocks is enlarged or not by calculating the similarity of the pixel blocks on the two sides to obtain the size of the pixel blocks; jointly analyzing the obtained pixel block size and the gray value matrix corresponding to the pixel block according to the smear characteristics and the motion direction to obtain a weight matrix; matching the right image of the image edge by using a matching template according to the size of the obtained pixel block; based on the weight matrix and the matching template, matching the subsequent pixel block by the sliding window, and judging whether the subsequent pixel block is a smear part to obtain a smear area;
adjusting the exposure time of the camera according to the trend of the weight difference of each pixel block in the smear region until the weight difference is greater than or equal to a preset difference threshold value, and updating the smear region;
and obtaining the vibration amplitude of the spindle according to the length of the smear area.
Preferably, the method for calculating the similarity between the pixel blocks at the two sides comprises:
the calculation formula of the similarity of the pixel blocks at the two sides is as follows:
wherein Q is the similarity of the pixel blocks at the two sides; n is the length and width of the pixel block, g (i,j) The gray value corresponding to the position with the length i and the width j in any pixel block is obtained; h is a total of (i,j) The gray value corresponding to the length i and the width j in another pixel block.
Preferably, the matching the subsequent pixel block by the sliding window based on the weight matrix and the matching template, and determining whether the subsequent pixel block is a smear part, includes:
and matching the subsequent pixel blocks according to the obtained weight matrix and the matching template by taking the size of the pixel blocks as the size of the sliding window and the step length as the width of the pixel blocks, and judging whether the subsequent pixel blocks are the smear parts.
Preferably, the matching the subsequent pixel block by the sliding window based on the weight matrix and the matching template, and determining whether the subsequent pixel block is a smear part, further includes:
obtaining the gray value of a pixel block at the position of the sliding window when the sliding window is static according to the position of the sliding window to obtain a first image; fitting the two first images by using the weight to obtain a second image, and judging whether the window is a smear part or not by calculating the similarity of the second image and the gray value of the window part at the moment;
the method for fitting the two first images comprises the following steps:
wherein, P (i,j) Is the gray value, O, at the pixel point (i, j) in any first image (i,j) Is the gray value, W, at the pixel point (i, j) in the other second image i The weight of the ith column of the image pixel block; and T is the fitted image.
Preferably, the determining whether the subsequent pixel block is a smear part to obtain a smear region includes:
and when template matching is carried out from the edge of the image main body, calculating a weight matrix obtained in each matching, and when any matching weight in the weight matrix is smaller than a preset weight threshold, stopping matching, wherein all obtained pixel block regions are smear regions.
Preferably, the method for calculating the weight difference comprises:
according to the obtained smear region, obtaining the weight of each matching, and calculating the average weight of each matching;
wherein, omega is the average weight of the ith pixel block, and N is the length and width of the pixel block; w i The weight of the ith column in the pixel block;
the calculation formula of the weight difference is as follows:
wherein b is the weight difference, ω i The average weight of the ith pixel block; omega i+1 And m is the average weight of the (i + 1) th pixel block, and the number of the pixel blocks in the smear region.
Preferably, the obtaining of the vibration amplitude of the spindle according to the length of the smear zone comprises:
the product of the number of pixel blocks in the smear region and the width of the pixel blocks is the length of the smear region; calculating the distance from the edge of the spindle to the center line of the spindle; the sum of the length of the smear region and the distance is the vibration amplitude of the spindle.
Preferably, the spindle image is collected, and the spindle image is preprocessed to obtain a spindle region, including:
spindle regions containing spindles in the spindle images are divided through semantic division to obtain the spindle regions.
The embodiment of the invention at least has the following beneficial effects:
the embodiment of the invention utilizes a data processing technology, and the method is a method for identifying by using electronic equipment and finishes the acquisition of the vibration amplitude of a high-speed spindle by using an artificial intelligence system in the production field. Firstly, acquiring spindle images, and preprocessing the spindle images to obtain spindle areas; based on the spindle area, obtaining the edge of the spindle by using an edge detection algorithm; dividing according to the edge of the spindle, obtaining pixel blocks on two sides of the edge according to the division, and determining whether the size of the pixel blocks is enlarged or not by calculating the similarity of the pixel blocks on the two sides; jointly analyzing the obtained pixel block size and the gray value matrix corresponding to the pixel block according to the smear characteristics and the motion direction to obtain a weight matrix; matching the right image of the image edge by using a matching template according to the size of the obtained pixel block; based on the weight matrix and the matching template, matching the subsequent pixel block by the sliding window, and judging whether the subsequent pixel block is a smear part or not to obtain a smear area; adjusting the exposure time of the camera according to the trend of the weight difference of each pixel block in the smear region until the weight difference is greater than or equal to a preset difference threshold value, and updating the smear region; and obtaining the vibration amplitude of the spindle according to the length of the smear area. According to the embodiment of the invention, the smear of the image is acquired and adjusted, and the exposure time of the camera is adjusted, so that the smear of the spindle image acquired by the camera is not overlapped as much as possible, the influence of the smear overlapping on the vibration amplitude detection is eliminated, the amplitude acquisition of the high-speed spindle is finally realized, and the accuracy of spindle amplitude detection is improved when the spindle rotates at a high speed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for detecting vibration amplitude of a spinning high-speed spindle during rotation according to an embodiment of the invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description, with reference to the accompanying drawings and preferred embodiments, describes a method for detecting vibration amplitude of a spinning high-speed spindle during rotation, and its specific implementation, structure, features and effects thereof. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment of the invention provides a specific implementation method of a vibration amplitude detection method during rotation of a spinning high-speed spindle, and the method is suitable for a high-speed spindle vibration amplitude detection scene. A camera is arranged in front of the spindle under the scene and used for collecting spindle images. In order to solve the problem that simple analysis of the smear in an image can be influenced by smear superposition, and further vibration amplitude detection is inaccurate, the embodiment of the invention provides a method for identifying by using electronic equipment.
The specific scheme of the vibration amplitude detection method during the rotation of the textile high-speed spindle provided by the invention is specifically described below by combining the attached drawings.
Referring to fig. 1, a flow chart of steps of a method for detecting vibration amplitude when a textile high-speed spindle rotates according to an embodiment of the invention is shown, the method includes the following steps:
and S100, acquiring spindle images, and preprocessing the spindle images to obtain spindle areas.
When the spindle is detected, a camera is placed in front of the spindle, and the camera shoots spindle images of the whole process of high-speed and stable rotation of the spindle.
Spindle regions containing spindles in the spindle images are segmented through semantic segmentation of the neural network, and the spindle regions are obtained.
Step S200, based on the spindle area, obtaining the edge of the spindle by using an edge detection algorithm; dividing according to the edge of the spindle, obtaining pixel blocks on two sides of the edge according to the division, and judging whether the size of the pixel blocks is enlarged or not by calculating the similarity of the pixel blocks on the two sides to obtain the size of the pixel blocks; jointly analyzing the obtained pixel block size and the gray value matrix corresponding to the pixel block according to the smear characteristics and the motion direction to obtain a weight matrix; matching the right image of the image edge by using a matching template according to the size of the obtained pixel block; and matching the subsequent pixel blocks by the sliding window based on the weight matrix and the matching template, and judging whether the subsequent pixel blocks are smear parts to obtain a smear area.
Image smear is a phenomenon in the normal camera shooting process. The smear is formed by the relative motion between the shooting target and the camera system during exposure, because the relative motion causes the image formed on the chip to be changed all the time, the image elements of each part are influenced by the imaging from different positions of the object in the exposure process, and the finally formed picture is the superposition of the pictures in a continuously changed image space.
And acquiring the exposure time after the camera shoots, and acquiring the motion speed v according to the length of the smear, namely the motion distance between the leftmost side and the leftmost side of the spindle, and the exposure time t. And a camera parameter q, where q is related to the optical magnification of the camera. The relationship among the three is as follows:
e＝tvq
wherein e is the smear length generated by the smear in the image; t is the exposure time; v is the rate of movement; q is a camera parameter.
That is, when the image is collected, it is impossible for each frame of image to be collected as the image when the image moves to the maximum amplitude, so that the length of the smear obtained under a certain condition can be the movement distance of the image, and the vibration amplitude can be obtained according to the smear.
However, the image generates smear in several situations, which in turn results in the fact that the generated smear information does not accurately reflect the motion amplitude.
If the smear part generated in the image is marked as a virtual image, the spindle body image is a real image.
Then the image captured by the camera may have the following three situations:
the first condition is as follows: the virtual image is just stuck together with the real image, which is the most ideal case.
Case two: no smear is produced, i.e. the exposure time is too short.
And a third situation: the virtual image overlaps the real image, i.e. the virtual image is on both sides of the real image.
Therefore, after other parameters of the camera are known, the speed of the vibration is known to fluctuate within a certain range according to experience, and the fluctuation range is not large, so that the speed can be regarded as a fixed value, and the exposure time of the camera is adjusted, so that the length of the smear in the image is adjusted, and the smear generated in the image is generated only by one-time vibration.
Based on the obtained spindle area, the spindle area comprises a virtual image and a real image.
The main difference between the virtual image and the real image is that the virtual image and the real image are both extensions of the edge of the original image, and the main difference lies in that the number of pixel points of the description image of the virtual image and the real image is inconsistent, that is, the virtual image not only contains pixel points describing the image to be solved, but also contains pixel points describing the background of the image.
By regulating the exposure time of the camera, the obtained image smear is only the first condition, namely, the spindle vibrates only once in the exposure time of the camera shooting. Then the smear length is the desired vibration amplitude.
As can be seen from the analysis of the smear region, the smear region is a composite body including the image background and the edge portion of the image close to the image background, i.e., the image background and the edge portion of the image close to the image background can be reflected by the smear region. And the smearing effect creates a gradual transition between the background and the subject image.
The method comprises the steps of dividing main body information into blocks, calculating the similarity between the close edge part of the main body area and the smear area, and determining the main part dragged by the smear area. I.e. by chunking, which parts of a particular repeated body are found.
According to the invention, the vibration amplitude of the scene, namely the spindle, is different, so that the image is partitioned, and the vibration amplitude of each part is calculated respectively, wherein the size of the partition is N x N.
If the edge is not a straight line, the edge is scanned by the block size to obtain a boundary line between two pixel blocks by using the average abscissa in the pixel blocks.
Firstly, based on a spindle region, obtaining the edge of the spindle by using an edge detection algorithm, dividing according to the edge of the spindle, obtaining pixel blocks on two sides of the edge according to the division, and judging whether the size of the pixel blocks is enlarged or not by calculating the similarity of the pixel blocks on the two sides to obtain the size of the pixel blocks.
The similarity calculation method of the two pixel blocks comprises the step of calculating the gray difference value of the corresponding pixel block.
The similarity Q of the pixel blocks at two sides is calculated by the following formula:
wherein N is the length and width of the pixel block, g (i,j) The gray value corresponding to the position with the length i and the width j in any pixel block is obtained; h is (i,j) The gray value corresponding to the length i and the width j in another pixel block.
The similarity threshold is preset, that is, if the similarity of two pixel blocks is greater than the preset similarity threshold, the two pixel blocks are considered to be dissimilar. In the embodiment of the present invention, the predetermined similarity threshold is 20.
That is, setting N0 to 1, so that the pixel block size N changes from 1, and increases by 1 for each change until the above condition is not met, that is, when the two images are dissimilar, the size of the pixel block stops changing, and the pixel block size and the gray value matrix of the corresponding shadow image at this time are obtained.
And jointly analyzing the obtained pixel block size and the gray value matrix corresponding to the pixel block according to the smear characteristics and the motion direction to obtain a weight matrix.
The smear is characterized in that the smear is generated due to the motion of an object, and the object vibration of the scene in the invention is left-right motion in the image, namely, the change of the smear part of the image is left-right changed.
And obtaining a group of weight matrixes W with the length of N, and matching the right images of the edges of the images by using a matching template according to the size of the obtained pixel blocks. It should be noted that the matching template is a pixel block of a real image at the edge of the spindle. In the embodiment of the invention, the left side of the edge of the spindle is used as a pixel block of a real image, namely a matching template, the right side of the edge of the spindle is used as a pixel block of a virtual image, and the pixel block on the right side of the edge of the spindle is matched with the matching template.
According to the obtained weight matrix and the matching template, taking the size of the pixel block as the size of the sliding window, taking the step length as the width of the pixel block, matching the subsequent pixel block, and judging whether the subsequent pixel block is a smear part or not; that is, according to the obtained weight matrix and the matching template P, the size N × N of the pixel block is used as a sliding window, the step length is N, and the subsequent pixel block is matched to determine whether the subsequent pixel block is a smear part.
And obtaining the gray value of the pixel block at the position of the scanning frame when the scanning frame is static according to the position of the scanning frame to obtain an image O. As can be seen from the above, the smear image includes both the body information and the background information. Therefore, the two images are fitted by using the weight to obtain an image K, and whether the window is a smear part or not is judged by calculating the similarity between the K and the gray value of the window part at the time. Obtaining the gray value of the pixel block at the position of the sliding window when the sliding window is static according to the position of the sliding window to obtain a first image; and fitting the two first images by using the weight to obtain a second image, and judging whether the window is a smear part or not by calculating the similarity of the gray value of the second image and the window part at the moment.
The method for fitting the two first images comprises the following steps:
wherein, P (i,j) Is the gray value, O, at the pixel point (i, j) in any first image (i,j) Is the gray value, W, at the pixel point (i, j) in the other second image i The weight of the ith column of the image pixel block; and T is the fitted image.
The template image is subjected to fitting transformation of the two first images to obtain a second image T, and whether the area is a smear area or not is judged by comparing the similarity degree of the transformed second image T and the pixel block where the sliding window is located.
The similarity measurement method is the gray scale difference Q of the pixels corresponding to the two image blocks.
And the difference between the transformed template and the subsequent pixel block is minimized by adjusting the transformation weight matrix W. I.e. the two pixel block similarity condition is fulfilled.
And when template matching is carried out from the edge of the image main body, calculating a weight matrix obtained in each matching, and when any matching weight in the weight matrix is smaller than a preset weight threshold, stopping matching, wherein all obtained pixel block regions are smear regions. In the embodiment of the present invention, the preset weight threshold is 0.2, and in other embodiments, an implementer may adjust the value according to the actual situation.
Step S300, adjusting the exposure time of the camera according to the trend of the weight difference of each pixel block in the smear region until the weight difference is greater than or equal to a preset difference threshold value, and updating the smear region.
If the smear region is not acquired according to step S200, the case is the second case, and at this time, the exposure time of the camera needs to be increased, so that the image has a smear phenomenon.
Analyzing according to the obtained smear image, wherein after the smear is generated, the distance between the smear image and the edge of the main body image changes, and the farther away from the edge of the main body, the larger the difference between the gray value of the smear part and the gray value of the edge of the main body is,
therefore, according to this feature, the change of the gray gradient of the smear image is changed along with the change of the moving direction of the subject, and the gradient change is uniform.
According to the method for obtaining the smear region, the smear length corresponding to a certain edge is obtained as m × N. That is, in smear detection, m +1 times of scanning is performed, and the matching weight obtained in the m +1 th time is smaller than the threshold s. And acquiring the matching weight value of each time according to the obtained smear area. And obtaining the average weight omega in each matching.
According to the obtained smear region, obtaining the weight of each matching, and calculating the average weight of each matching;
wherein, ω is i The average weight of the ith pixel block is N, and the length and the width of the pixel block are N; w i The weight of the ith column in the pixel block;
and according to the above rule, omega 1 Must be greater than omega m And, when varied, uniformly varied.
The calculation formula of the weight difference b is as follows:
wherein, ω is i The average weight of the ith pixel block; omega i+1 And m is the average weight of the (i + 1) th pixel block, and the number of the pixel blocks in the smear region.
That is, if the weight difference is smaller than the preset difference threshold, the smear is considered as the third condition, and at this time, the exposure time of the camera needs to be reduced, so that the smear is shortened. Until the weight difference obtained by calculation is greater than or equal to a preset difference threshold value. In the embodiment of the present invention, the preset difference threshold is 0, and in other embodiments, the implementer may adjust the value according to the actual situation.
By adjusting the exposure time of the camera, the smear image is updated accordingly.
And step S400, obtaining the vibration amplitude of the spindle according to the length of the smear area.
The product of the number of pixel blocks in the smear region and the width of the pixel blocks is the length of the smear region; the distance from the edge of the spindle to the center line of the spindle at the moment is calculated, and the sum of the length of the smear zone and the distance is the vibration amplitude of the spindle. And (4) drawing a spindle vibration amplitude time chart by shooting in real time to obtain the maximum vibration amplitude and the average vibration amplitude of the spindle.
In summary, the embodiment of the invention utilizes a data processing technology, which is a method for identifying by using electronic equipment, and utilizes an artificial intelligence system in the production field to complete the acquisition of the vibration amplitude of the high-speed spindle. Firstly, acquiring spindle images, and preprocessing the spindle images to obtain spindle areas; based on the spindle area, obtaining the edge of the spindle by using an edge detection algorithm; dividing according to the edge of the spindle, obtaining pixel blocks on two sides of the edge according to the division, and determining whether the size of the pixel blocks is enlarged or not by calculating the similarity of the pixel blocks on the two sides; jointly analyzing the obtained pixel block size and the gray value matrix corresponding to the pixel block according to the smear characteristics and the motion direction to obtain a weight matrix; matching the right image of the image edge by using a matching template according to the size of the obtained pixel block; based on the weight matrix and the matching template, matching the subsequent pixel block by the sliding window, and judging whether the subsequent pixel block is a smear part or not to obtain a smear area; adjusting the exposure time of the camera according to the trend of the weight difference of each pixel block in the smear region until the weight difference is greater than or equal to a preset difference threshold value, and updating the smear region; and obtaining the vibration amplitude of the spindle according to the length of the smear area. According to the embodiment of the invention, the amplitude of the high-speed spindle is finally obtained by obtaining and adjusting the image smear, so that the accuracy of spindle amplitude detection is improved when the spindle rotates at a high speed.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A method for detecting vibration amplitude of a spinning high-speed spindle during rotation is characterized by comprising the following steps:
acquiring spindle images, and preprocessing the spindle images to obtain spindle areas;
based on the spindle area, obtaining the edge of the spindle by using an edge detection algorithm; dividing according to the edge of the spindle, obtaining pixel blocks on two sides of the edge according to the division, and judging whether the size of the pixel blocks is enlarged or not by calculating the similarity of the pixel blocks on the two sides to obtain the size of the pixel blocks; jointly analyzing the obtained pixel block size and the gray value matrix corresponding to the pixel block according to the smear characteristics and the motion direction to obtain a weight matrix; matching the right image of the image edge by using a matching template according to the size of the obtained pixel block; based on the weight matrix and the matching template, matching the subsequent pixel block by the sliding window, and judging whether the subsequent pixel block is a smear part or not to obtain a smear area;
adjusting the exposure time of the camera according to the trend of the weight difference of each pixel block in the smear region until the weight difference is greater than or equal to a preset difference threshold value, and updating the smear region;
and obtaining the vibration amplitude of the spindle according to the length of the smear area.
2. The method for detecting the vibration amplitude of the spinning high-speed spindle during rotation according to claim 1, wherein the method for calculating the similarity of the pixel blocks at the two sides comprises the following steps:
the calculation formula of the similarity of the pixel blocks at the two sides is as follows:
wherein Q is the similarity of the pixel blocks at the two sides; n is the length and width of the pixel block, g (i,j) The gray value of the position with the length i and the width j in any pixel block is set; h is (i,j) The gray value corresponding to the position with the length i and the width j in another pixel block.
3. The method for detecting the vibration amplitude value of the spinning high-speed spindle during rotation according to claim 1, wherein the step of matching a subsequent pixel block by a sliding window based on the weight matrix and the matching template to judge whether the subsequent pixel block is a smear part comprises the following steps:
and matching the subsequent pixel blocks according to the obtained weight matrix and the matching template by taking the size of the pixel block as the size of the sliding window and the step length as the width of the pixel block, and judging whether the subsequent pixel blocks are the smear parts.
4. The method for detecting the vibration amplitude value of the spinning high-speed spindle during rotation according to claim 1, wherein a sliding window matches a subsequent pixel block based on the weight matrix and the matching template to determine whether the subsequent pixel block is a smear part, further comprising:
obtaining the gray value of a pixel block at the position of the sliding window when the sliding window is static according to the position of the sliding window to obtain a first image; fitting the two first images by using the weight to obtain a second image, and judging whether the window is a smear part or not by calculating the similarity of the gray value of the second image and the window part at the moment;
the method for fitting the two first images comprises the following steps:
wherein, P (i,j) Is the gray value, O, at the pixel point (i, j) in any first image (i,j) Is the gray value, W, at the pixel point (i, j) in the other second image i The weight of the ith column of the image pixel block; and T is the fitted image.
5. The method for detecting the vibration amplitude value of the spinning high-speed spindle during rotation according to claim 1, wherein the step of judging whether the subsequent pixel block is a smear part or not to obtain a smear region comprises the following steps:
and when template matching is carried out from the edge of the image main body, calculating a weight matrix obtained in each matching, and when any matching weight in the weight matrix is smaller than a preset weight threshold, stopping matching, wherein all obtained pixel block regions are smear regions.
6. The method for detecting the vibration amplitude of the spinning high-speed spindle during rotation as claimed in claim 1, wherein the weight difference is calculated by:
according to the obtained smear region, obtaining the weight value matched each time, and calculating the average weight value matched each time;
wherein, omega is the average weight of the ith pixel block, and N is the length and width of the pixel block; w i The weight of the ith column in the pixel block;
the calculation formula of the weight difference is as follows:
wherein b is the weight difference, ω i The average weight of the ith pixel block; omega i+1 And m is the average weight of the (i + 1) th pixel block, and the number of the pixel blocks in the smear region.
7. The method for detecting the vibration amplitude of the spinning high-speed spindle during rotation according to claim 1, wherein the obtaining the vibration amplitude of the spindle according to the length of the smear zone comprises:
the product of the number of pixel blocks in the smear region and the width of the pixel blocks is the length of the smear region; calculating the distance from the edge of the spindle to the central line of the spindle; the sum of the length of the smear region and the distance is the vibration amplitude of the spindle.
8. The method for detecting the vibration amplitude of the spinning high-speed spindle during rotation according to claim 1, wherein the spindle image acquisition and spindle image preprocessing are performed to obtain a spindle area, and the method comprises the following steps:
spindle regions containing spindles in the spindle images are divided through semantic division to obtain the spindle regions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210475326.4A CN114923629A (en) | 2022-04-29 | 2022-04-29 | Method for detecting vibration amplitude of spinning high-speed spindle during rotation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210475326.4A CN114923629A (en) | 2022-04-29 | 2022-04-29 | Method for detecting vibration amplitude of spinning high-speed spindle during rotation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114923629A true CN114923629A (en) | 2022-08-19 |
Family
ID=82807380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210475326.4A Pending CN114923629A (en) | 2022-04-29 | 2022-04-29 | Method for detecting vibration amplitude of spinning high-speed spindle during rotation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114923629A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117268759A (en) * | 2023-11-23 | 2023-12-22 | 南通进宝机械制造有限公司 | Bearing balance test system, method and medium for textile mechanical equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080271530A1 (en) * | 2007-05-01 | 2008-11-06 | Matsuura Machinery Corporation | Vibration State Detecting Method at Machining Stage of Work and/or Tool |
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN104180983A (en) * | 2014-09-02 | 2014-12-03 | 苏州市计量测试研究所 | Mechanical vibrator fastener monitoring system and monitoring method of mechanical vibrator fastener monitoring system |
| CN106629395A (en) * | 2016-12-16 | 2017-05-10 | 天津金岸重工有限公司 | Detection method for amplitude of weak vibration signal of portal type crane |
| CN107271162A (en) * | 2017-06-14 | 2017-10-20 | 东华大学 | A kind of time-division combined positioning method for spindle ingot end oscillation trajectory measuring system |
| CN107290140A (en) * | 2017-06-14 | 2017-10-24 | 东华大学 | A kind of method for measuring Yarn-spinning spindle ingot end oscillation trajectory |
| CN107490964A (en) * | 2017-08-17 | 2017-12-19 | 杭州电子科技大学 | A kind of rotating machinery fault feature reduction method of feature based evidence discretization |
| CN109636731A (en) * | 2018-10-23 | 2019-04-16 | 惠州Tcl移动通信有限公司 | A kind of removing method of image streaking, electronic equipment and storage medium |
| CN110873633A (en) * | 2018-09-03 | 2020-03-10 | 上海铼钠克数控科技股份有限公司 | Spindle vibration detection method and system |
| CN112330544A (en) * | 2019-08-05 | 2021-02-05 | 浙江宇视科技有限公司 | Image smear processing method, device, equipment and medium |
| US20210337101A1 (en) * | 2020-04-22 | 2021-10-28 | Axis Ab | Method, device, camera and software for performing electronic image stabilization of a high dynamic range image |
| CN113802227A (en) * | 2021-07-27 | 2021-12-17 | 东华大学 | Method for calibrating vision system for ring spun yarn online detection |
| JP2022035321A (en) * | 2020-08-20 | 2022-03-04 | オークマ株式会社 | Rotor imbalance calculation method and calculation device |
| CN114215357A (en) * | 2021-11-11 | 2022-03-22 | 浙江大学 | Pump truck arm support tail end vibration suppression method based on combination of input shaping and time-lag compensation |
-
2022
- 2022-04-29 CN CN202210475326.4A patent/CN114923629A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080271530A1 (en) * | 2007-05-01 | 2008-11-06 | Matsuura Machinery Corporation | Vibration State Detecting Method at Machining Stage of Work and/or Tool |
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN104180983A (en) * | 2014-09-02 | 2014-12-03 | 苏州市计量测试研究所 | Mechanical vibrator fastener monitoring system and monitoring method of mechanical vibrator fastener monitoring system |
| CN106629395A (en) * | 2016-12-16 | 2017-05-10 | 天津金岸重工有限公司 | Detection method for amplitude of weak vibration signal of portal type crane |
| CN107271162A (en) * | 2017-06-14 | 2017-10-20 | 东华大学 | A kind of time-division combined positioning method for spindle ingot end oscillation trajectory measuring system |
| CN107290140A (en) * | 2017-06-14 | 2017-10-24 | 东华大学 | A kind of method for measuring Yarn-spinning spindle ingot end oscillation trajectory |
| CN107490964A (en) * | 2017-08-17 | 2017-12-19 | 杭州电子科技大学 | A kind of rotating machinery fault feature reduction method of feature based evidence discretization |
| CN110873633A (en) * | 2018-09-03 | 2020-03-10 | 上海铼钠克数控科技股份有限公司 | Spindle vibration detection method and system |
| CN109636731A (en) * | 2018-10-23 | 2019-04-16 | 惠州Tcl移动通信有限公司 | A kind of removing method of image streaking, electronic equipment and storage medium |
| CN112330544A (en) * | 2019-08-05 | 2021-02-05 | 浙江宇视科技有限公司 | Image smear processing method, device, equipment and medium |
| US20210337101A1 (en) * | 2020-04-22 | 2021-10-28 | Axis Ab | Method, device, camera and software for performing electronic image stabilization of a high dynamic range image |
| JP2022035321A (en) * | 2020-08-20 | 2022-03-04 | オークマ株式会社 | Rotor imbalance calculation method and calculation device |
| CN113802227A (en) * | 2021-07-27 | 2021-12-17 | 东华大学 | Method for calibrating vision system for ring spun yarn online detection |
| CN114215357A (en) * | 2021-11-11 | 2022-03-22 | 浙江大学 | Pump truck arm support tail end vibration suppression method based on combination of input shaping and time-lag compensation |
Non-Patent Citations (5)
| Title |
|---|
| S. VAFAEI等: "Vibration monitoring of high speed spindles using spectral analysis techniques", INTERNATIONAL JOURNAL OF MACHINE TOOLS AND MANUFACTURE, vol. 42, no. 11, pages 1223 - 1234 * |
| 朱丽鹏等: "一种基于图像处理的提升机弦绳振动算法改进", 煤炭工程, no. 06, pages 159 - 163 * |
| 李京等: "细纱机锭子有限元分析及减振方法研究", 现代纺织技术, no. 06, pages 9 - 12 * |
| 杨硕;: "基于机器视觉的振动筛运动特性快速诊断方法", 选煤技术, no. 04, pages 31 - 35 * |
| 陈家新等: "电锭细纱机电锭锭端轨迹测量关键技术研究", 纺织导报, no. 6, pages 32 - 37 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117268759A (en) * | 2023-11-23 | 2023-12-22 | 南通进宝机械制造有限公司 | Bearing balance test system, method and medium for textile mechanical equipment |
| CN117268759B (en) * | 2023-11-23 | 2024-04-19 | 南通进宝机械制造有限公司 | Bearing balance test system, method and medium for textile mechanical equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115633259B (en) | Automatic regulation and control method and system for intelligent camera based on artificial intelligence | |
| EP2671113B1 (en) | Fast auto-focus in microscopic imaging | |
| DE102017223559B4 (en) | DEVICE FOR FOCUSING A CAMERA AND CONTROL PROCEDURES FOR THIS | |
| CN110852997B (en) | Dynamic image definition detection method and device, electronic equipment and storage medium | |
| CN114923629A (en) | Method for detecting vibration amplitude of spinning high-speed spindle during rotation | |
| CN115690105A (en) | Milling cutter scratch detection method based on computer vision | |
| CN115760893A (en) | Single droplet particle size and speed measuring method based on nuclear correlation filtering algorithm | |
| US6915022B2 (en) | Image preprocessing method capable of increasing the accuracy of face detection | |
| CN112819710B (en) | Unmanned aerial vehicle jelly effect self-adaptive compensation method and system based on artificial intelligence | |
| CN113221739B (en) | Monocular vision-based vehicle distance measuring method | |
| CN116128769B (en) | Track vision recording system of swinging motion mechanism | |
| CN111429479A (en) | Space target identification method based on image integral mean value | |
| CN113052794A (en) | Image definition recognition method based on edge features | |
| CN109064497B (en) | Video tracking method based on color clustering supplementary learning | |
| CN113344905B (en) | Strip deviation amount detection method and system | |
| CN112966699B (en) | Target detection system of communication engineering project | |
| CN114972084A (en) | Image focusing accuracy evaluation method and system | |
| CN117671014B (en) | Mechanical arm positioning grabbing method and system based on image processing | |
| US5764788A (en) | Strand orientation sensing | |
| JP2002373340A (en) | Method for extracting motion characteristic, and device and program for recognizing motion | |
| CN116612390B (en) | Information management system for constructional engineering | |
| CN116894841B (en) | Visual detection method for quality of alloy shell of gearbox | |
| CN114638790B (en) | 3D waist support detection method with high-elasticity material | |
| CN117474916B (en) | Image detection method, electronic equipment and storage medium | |
| CN117952979B (en) | Construction engineering quality detection supervision method and system |
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 |