CN115239711B - Online operation abnormity identification system of sewing equipment - Google Patents
Online operation abnormity identification system of sewing equipment Download PDFInfo
- Publication number
- CN115239711B CN115239711B CN202211150174.7A CN202211150174A CN115239711B CN 115239711 B CN115239711 B CN 115239711B CN 202211150174 A CN202211150174 A CN 202211150174A CN 115239711 B CN115239711 B CN 115239711B
- Authority
- CN
- China
- Prior art keywords
- frame
- waveform
- value
- sewing machine
- difference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009958 sewing Methods 0.000 title claims abstract description 91
- 230000033001 locomotion Effects 0.000 claims abstract description 36
- 230000005856 abnormality Effects 0.000 claims abstract description 29
- 230000002159 abnormal effect Effects 0.000 claims abstract description 24
- 230000008859 change Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims description 19
- 230000009467 reduction Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Sewing Machines And Sewing (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an online operation abnormity identification system of sewing equipment. The system comprises: the data acquisition module is used for acquiring motion image data of a needle of the sewing machine and a real-time vibration signal of the sewing machine; the vibration period acquisition module is used for acquiring a motion change curve, and the mean value of the distance between the abscissas of every two adjacent minimum value points in the motion change curve is a vibration period; the work abnormality recognition module is used for obtaining a template waveform of a vibration period and a plurality of waveforms to be tested, the lengths of which are the vibration period; obtaining an interception initial point; obtaining an identification waveform every other vibration period from the interception starting point; calculating the difference degree of each recognition waveform and the template waveform to form an abnormal recognition sequence; and identifying whether the sewing machine operates abnormally or not based on the elements in the abnormality identification sequence. The invention can accurately identify the running state of the sewing machine and judge whether the running state of the sewing machine is abnormal.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an online operation abnormity identification system of sewing equipment.
Background
Sewing machines are indispensable to the textile industry, and among the sewing machines, sewing machines are used the most, which are machines that sew pieces of cloth to be sewn together with sewing threads. In a large-scale clothing factory, one sewing machine is required to sew a plurality of batches of products, and when the sewing machine is abnormal, the quality of the sewn products is reduced, even some products are unqualified, and the economic benefit of the factory is reduced.
The traditional detection of the abnormality of the sewing machine mainly depends on the experience of an operator for judgment, but the judgment method has high requirement on the accuracy of the experience of the operator, has stronger subjectivity and is easy to cause misjudgment; with the continuous development of machine learning technology, a vibration signal of a sewing machine is collected, then a neural network is trained based on the vibration signal of the sewing machine, the trained neural network is used for identifying the abnormity of the sewing machine, but a large amount of data is needed during the training of the neural network, so that a large amount of data needs to be accumulated, and the time cost and the economic cost are high.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide an online operation abnormality recognition system for a sewing machine, which adopts the following technical scheme:
one embodiment of the present invention provides an online operation abnormality recognition system for a sewing apparatus, the system including: the data acquisition module is used for sequentially acquiring multi-frame grayed moving images of a needle of the sewing machine in a preset time period; collecting real-time vibration signals of the sewing machine in a preset time period, and carrying out noise reduction processing on the real-time vibration signals;
the vibration period acquisition module is used for respectively carrying out difference on the first frame of moving image and each frame of moving image to obtain a plurality of frames of difference images; obtaining a segmentation threshold of each frame of difference image by using the maximum value and the minimum value of the gray value of the pixel point in each frame of difference image; binarizing each frame difference image based on the segmentation threshold value of each frame difference image to obtain a multi-frame binary image; fitting based on the number of pixel points with the gray values of a first preset value in each frame of binary image to obtain a motion change curve; the average value of the distances between the abscissas of every two adjacent minimum value points in the motion change curve is a vibration period;
the work abnormality identification module is used for intercepting a template waveform of a vibration period from the acquired vibration signal of the sewing machine without abnormality by utilizing the vibration period; obtaining a plurality of waveforms to be tested with the length of one vibration period from the starting point of the real-time vibration signal; calculating the difference degree between each waveform to be detected and the template waveform, and selecting the starting point of the waveform to be detected with the minimum difference degree as an interception starting point; obtaining an identification waveform every other vibration period from the intercepted initial point; calculating the difference degree of each recognition waveform and the template waveform to form an abnormal recognition sequence; and identifying whether the sewing machine operates abnormally or not based on the elements in the abnormality identification sequence.
Preferably, the obtaining the segmentation threshold of each frame of difference image by using the maximum value and the minimum value of the gray value of the pixel point in each frame of difference image includes: obtaining the maximum value and the minimum value of the gray value of a pixel point in each frame of difference image; and adding the maximum value and the minimum value of the gray value and solving the average value to obtain the segmentation threshold of each frame of difference image.
Preferably, each frame of difference image is binarized to obtain a multi-frame binary image based on the segmentation threshold of each frame of difference image, including; and marking the gray value of the pixel point with the gray value larger than the segmentation threshold value in each frame of difference image as a first preset value, and marking the gray value of the pixel point with the gray value larger than the preset value as a second preset value to obtain a binary image after each frame of difference image is binarized.
Preferably, the motion profile is obtained by: acquiring the number of pixel points with a gray value of a first preset value in each frame of difference image and the number of frames corresponding to each frame of difference image; the abscissa of the motion change curve in the rectangular coordinate system is the number of frames corresponding to each frame of difference image, and the ordinate is the number of pixel points with a gray value of a first preset value in each frame of difference image.
Preferably, obtaining a plurality of waveforms to be measured with a length of one vibration cycle from a start point of the real-time vibration signal includes: setting a preset interval, and obtaining a starting point every other preset interval from the starting point of the real-time vibration signal; and obtaining the waveform to be measured corresponding to each starting point from each starting point, wherein the abscissa length of the waveform to be measured is a vibration period.
Preferably, the difference degree between each waveform to be measured and the template waveform is:
wherein,
representing the difference degree between a waveform to be detected and the template waveform; />
Represents the period of vibration; />
Representing the waveform to be measuredAnd the template waveform>
The Euclidean distance between the corresponding points; />
Representing the maximum value in Euclidean distances of all corresponding points of the waveform to be detected and the template waveform; />
Representing the minimum value in Euclidean distances of all corresponding points of the waveform to be detected and the template waveform; />
A logarithmic function with base 10 is shown.
Preferably, identifying whether the sewing machine is abnormally operated based on the elements in the abnormality identification sequence includes: and setting an abnormal recognition threshold, and if one element in the abnormal recognition sequence is larger than the abnormal recognition threshold, the operation of the sewing machine corresponding to the abnormal recognition sequence is abnormal.
The embodiment of the invention at least has the following beneficial effects: the method collects the needle point moving image and the real-time vibration signal when the sewing machine works, performs subtraction on a multi-frame moving image to obtain a difference image, obtains a proper segmentation threshold value based on the maximum value and the minimum value of the gray value of the pixel points in the difference image, binarizes the difference image to obtain a multi-frame binary image, can accurately represent the vibration period of the vibration signal through the change of the number of the pixel points with the gray value of a first preset value in each frame binary image, and provides convenience for the subsequent real-time vibration signal analysis; in addition, different waveforms to be detected are intercepted from the starting point of a real-time vibration signal and analyzed, so that the starting point of a vibration period of the real-time vibration signal can be accurately obtained, namely the intercepting starting point, the recognition waveforms obtained after the intercepting starting point are all a complete vibration period, the accuracy of calculating the difference degree of the recognition waveforms and the template waveforms is improved, and the accuracy of recognizing the running state of the sewing machine based on the difference degree of the recognition waveforms and the template waveforms is further improved.
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 embodiments or the description of 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 system block diagram of an online operation abnormality recognition system of a sewing apparatus according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to the system for identifying online operation abnormality of sewing equipment according to the present invention, and its specific implementation, structure, features and effects thereof, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily 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 specific scheme of the online operation abnormity identification system of the sewing equipment provided by the invention is concretely described below by combining the attached drawings.
Example (b):
the main application scenarios of the invention are as follows: in the operation of the sewing machine, if an abnormality occurs in the operation state of the sewing machine, the quality of a product to be sewn through the sewing machine may be degraded, resulting in a loss, and thus it is necessary to recognize the operation state of the sewing machine based on a vibration signal of the sewing machine.
Referring to fig. 1, a system block diagram of an online operation abnormality recognition system for a sewing machine according to an embodiment of the present invention is shown, the method includes the following modules:
the data acquisition module is used for sequentially acquiring multi-frame grayed moving images of a needle of the sewing machine in a preset time period; the real-time vibration signal of the sewing machine is collected in a preset time period, and noise reduction processing is carried out on the real-time vibration signal.
Firstly, the embodiment of the invention is used for testing and diagnosing when a sewing machine runs, a sensor is used for measuring a vibration signal of the sewing machine, the real-time vibration signal of the sewing machine is amplified by an amplifier and then transmitted to a data acquisition card, the real-time vibration signal is converted into a digital signal through the data acquisition card and transmitted to a computer, signal acquisition is carried out every half hour, the acquisition time is a preset time period, preferably, the duration of the preset time period in the embodiment is 10 seconds, and an implementer can adjust the duration of the preset time period based on actual conditions. Due to the influence of noise and abnormal data, it is difficult to determine the period of the real-time vibration signal directly according to the real-time vibration signal of the sewing machine, so that the period of the real-time vibration signal needs to be indirectly obtained by other methods for subsequent analysis.
Further, since the sewing machine is a periodic process in which a needle of the sewing machine is moved from the uppermost position to the lowermost position to the uppermost position in a period, the vibration of the sewing machine is also moved in a period along with the upward and downward movement of the needle of the sewing machine, and the two periods are the same. In the operation process of the sewing machine, only the motion of the needle of the sewing machine exists, the real-time vibration signal of the sewing machine is only related to the motion of the needle of the sewing machine, the real-time vibration signal of the sewing machine is a periodic signal, the sewing needle of the sewing machine keeps the same motion track to do periodic motion, the same motion track refers to the up-and-down reciprocating motion of the needle, and the real-time vibration signal also has periodicity, so that the motion cycle of the needle of the sewing machine can be regarded as the vibration cycle of the sewing machine. Thereby also requiring the acquisition of a motion image of the needle tip of the sewing machine.
A COD industrial camera is used for collecting the motion image of a needle of the sewing machine, and the camera is placed on the side face of the sewing machine when the sewing machine moves. The acquisition is performed simultaneously with the vibration sensor. Here, 1s is set as 60 frames, the collection interval is set as 1 frame, and the collection time is also set as a preset time period, namely 10 seconds, so that a plurality of moving images related to the movement of the needle of the sewing machine are obtained.
Finally, graying the moving image and denoising the real-time vibration signal, preferably, in this embodiment, a wavelet denoising method is used to remove noise in the real-time vibration signal.
The vibration period acquisition module is used for respectively carrying out difference on the first frame of moving image and each frame of moving image to obtain a plurality of frames of difference images; obtaining a segmentation threshold of each frame of difference image by using the maximum value and the minimum value of the gray value of the pixel point in each frame of difference image; binarizing each frame difference image based on the segmentation threshold value of each frame difference image to obtain a multi-frame binary image; fitting based on the number of pixel points with the gray values of a first preset value in each frame of binary image to obtain a motion change curve; the average value of the distances between the abscissas of every two adjacent minimum points in the motion change curve is the vibration period.
First, it is difficult to determine the vibration period directly from the real-time vibration signal of the sewing machine, and thus the vibration period of the real-time vibration signal can be expressed by using the movement period of the needle of the sewing machine. The difference between a first frame of moving image in the collected multiple frames of moving images and all the moving images is used to obtain a difference image, and it should be noted that when the difference image is obtained by performing the difference, the obtained difference image includes the difference image between the first frame of moving image and the first frame of moving image. The gray values of most pixel points in the difference images of the two moving images are equal, only the changed pixel points through which the needle of the sewing machine moves are changed, the gray values of the pixel points of the part are greatly changed, and the change rate of the difference image is calculated based on the change rate. In the difference image, only the gray value of the pixel points on the needle movement route of the sewing machine is changed, the pixel points of the rest part are almost unchanged, and the gray value is close to 0 after subtraction. Pixels in multi-frame difference image obtained through statisticsMaximum gray value of a dot
And the minimum gray value->
If the two moving images are not exactly the same, the maximum gray value->
Will be much larger than the minimum gray value->
Therefore, the segmentation threshold of the frame of difference image can be obtained according to the maximum gray value and the minimum gray value of the pixel points in the frame of difference image:
wherein,
a segmentation threshold representing a frame of the difference image; />
And &>
Respectively representing the maximum gray value and the minimum gray value of the pixel points in one frame of difference image.
Further, each frame of difference image is segmented based on the segmentation threshold of each frame of difference image, and is segmented into two parts, the gray value of the pixel point in each frame of difference image, which is larger than the segmentation threshold w, is marked as a first preset value, and the gray value of the pixel point in the difference image, which is smaller than the segmentation threshold w, is marked as a second preset value, that is, the difference image is subjected to binarization processing, so as to obtain a binary image corresponding to each frame of difference image, it should be noted that, preferably, the values of the first preset value and the second preset value are respectively 0 and 1, and an implementer can adjust the values of the first preset value and the second preset value according to specific conditions.
Finally, counting the number of pixel points with the gray values of a first preset value in each frame of binary image to form a difference sequence; the elements in the difference sequence are the number of pixel points with the gray value of the first preset value in each frame of binary image, so that the smaller the value of one element is, the closer the position of the needle of the sewing machine in the motion image corresponding to the element is to the position of the needle of the sewing machine in the motion image of the first frame, and ideally, the positions of the needles are the same. Since there are repeated motions of the needles of the plurality of sewing machines within the preset period of time for which the moving images are collected, that is, a plurality of motion cycles, there may be a case where the positions of the needles of the sewing machines in the plurality of moving images are the same as the positions of the needles of the sewing machines in the moving image of the first frame. The difference value sequence has a plurality of elements with very small values, and the values of the elements are very close to 0; it should be noted that the order of the elements in the difference sequence is arranged according to the time sequence.
And obtaining the number of pixel points with the gray value of a first preset value in each frame of difference image and the number of frames corresponding to each frame of difference image, and performing curve fitting, namely performing curve fitting based on elements in the difference sequence to obtain a motion change curve, wherein the abscissa of the motion change curve in a rectangular coordinate system is the number of the frame corresponding to each frame of difference image, and the ordinate is the number of the pixel points with the gray value of the first preset value in each frame of difference image. Processing the motion change curve by using a derivation mode to obtain a minimum value point in the motion change curve; obtaining the distance between the abscissa of the starting point and the abscissa of the first minimum point in the motion curve
The distance between the abscissa of the first minimum point and the abscissa of the second minimum point->
The second minimum point and the third minimum pointDistance between the abscissa points between the value points->
And so on to obtain the distance between the abscissa of each two adjacent minimum value points->
Ideally, the distance on the abscissa between two adjacent minimum points represents the movement period of the needle of the sewing machine, but in order to reduce the error, it is expressed by its average value:
wherein,
the real-time vibration signal is a real-time vibration signal, and the real-time vibration signal is a real-time vibration signal.
The work abnormality identification module is used for intercepting a template waveform of a vibration period from the acquired vibration signal of the sewing machine without abnormality by utilizing the vibration period; obtaining a plurality of waveforms to be detected with the length of one vibration period from the starting point of the real-time vibration signal; calculating the difference degree between each waveform to be detected and the template waveform, and selecting the starting point of the waveform to be detected with the minimum difference degree as an interception starting point; obtaining an identification waveform every other vibration period from the intercepted initial point; calculating the difference degree of each recognition waveform and the template waveform to form an abnormal recognition sequence; and identifying whether the sewing machine operates abnormally or not based on the elements in the abnormality identification sequence.
Firstly, in order to identify whether the real-time vibration signal of the sewing machine is abnormal or not, firstly, a group of vibration signals are collected for the sewing machine without the abnormality, and a signal of a vibration period T is extracted from the group of vibration signalsThe signal data, i.e. the complete waveform of a vibration cycle, is recorded as a template waveform
. The starting point of the real-time vibration signal acquired in real time is not necessarily the starting point of a complete vibration period, so the starting point of a vibration period needs to be found from the real-time vibration signal; therefore, starting from the starting point of the real-time vibration signal, namely starting from the abscissa 0, setting preset intervals, obtaining starting points at every other preset interval, and starting to extend backwards along the abscissa from the obtained starting points to obtain the waveform to be measured corresponding to each starting point, wherein the length of the waveform to be measured corresponding to each starting point is a vibration period T; wherein the value of the predetermined interval is->
The implementer can adjust the value of the preset interval based on the actual situation. For example, starting from the start of the real-time vibration signal, i.e. the position with the abscissa of 0, the range of the abscissa of the waveform to be measured corresponding to the abscissa 0 is from 0 to T, and based on the start point->
At the beginning, the abscissa>
The corresponding abscissa range of the waveform to be measured is ^ er>
To/>
。
After obtaining a plurality of waveforms to be detected, calculating the difference degree between the template waveform and each waveform to be detected, and when the difference degree between the first waveform to be detected and the template waveform is lower, at least one waveform to be detected and the template waveform are obtained
The difference degree is low, and the similarity is high; if all the waveforms to be detected and the template waveform->
The difference degrees of the real-time vibration signals are higher, the real-time vibration signals are considered to be abnormal at the moment, namely the running state of the sewing machine is abnormal, and subsequent calculation is not carried out at the moment. It should be noted that all the above waveforms to be tested and the template waveform->
The higher degree of difference refers to that all the waveforms to be measured and the template waveform->
The difference degree of (2) is greater than a preset threshold, wherein the value of the preset threshold is 0.6, and an implementer can adjust the value according to specific conditions.
Further, the calculation process of the difference degree between the waveform to be detected and the template waveform specifically comprises the following steps: because the waveform to be detected and the template waveform
The length of the abscissa of the waveform to be detected is the same, therefore, the euclidean distance between corresponding points of the waveform to be detected and the template waveform is obtained, the smaller the euclidean distance is, the smaller the difference between the corresponding points is, and then the average value of the euclidean distances of all the corresponding points is calculated to represent the overall difference of the two waveforms, but the local difference of the two waveforms cannot be reflected, so that the local difference of the two waveforms also needs to be analyzed through the maximum value and the minimum value of the euclidean distances of the corresponding points.
Obtaining a waveform to be measured and a template waveform
All the corresponding points of (2) form a sequence
Wherein->
Represents the first and second parts of the waveform to be detected and the waveform of the template>
The euclidean distance between the corresponding points. The difference between a waveform to be measured and the template waveform is:
wherein,
representing the difference degree between a waveform to be detected and the template waveform; />
Represents the period of vibration; />
Represents the fifth or fifth judgment of the waveform to be detected and the template waveform>
The Euclidean distance between the corresponding points; />
Representing the maximum value in Euclidean distances of all corresponding points of the waveform to be detected and the template waveform; />
Representing the minimum value in Euclidean distances of all corresponding points of the waveform to be detected and the template waveform; />
Represents a base 10 logarithmic function that may be &>
The value of (d) maps into a range of 0 to 1.
After obtaining the difference degree between all the waveforms to be detected and the template waveform, obtaining the detection waveform with the minimum difference degree, wherein the starting point of the detection waveform is the interception starting point, and an identification waveform is obtained every other vibration period from the interception starting point, and the obtained identification waveform is the waveform of the complete vibration period. It should be noted that it is possible to intercept the real-time vibration signal and eventually obtain a waveform that is not a complete vibration cycle, and the last waveform needs to be discarded.
Finally, based on multiple identification waveforms, analyzing, and calculating a waveform to be measured and a template waveform
Method for calculating the degree of difference between each recognized waveform and the template waveform->
A real-time vibration signal, all the degrees of difference corresponding to a real-time vibration signal forming a sequence which identifies the sequence->
Wherein->
Represents the degree of difference between the tth identification waveform of a real-time vibration signal and the template waveform, and/or->
Representing a real-time vibration signal with a total of Z identifying waveforms.
Further, an abnormality recognition threshold is set, preferably, in this embodiment, a value of the abnormality recognition threshold is 0.5, and an implementer may adjust the value of the abnormality recognition threshold according to a specific actual situation. If the value of an element in the abnormal recognition sequence corresponding to a real-time vibration signal of a sewing machine is larger than the abnormal recognition threshold value, the abnormal operation state of the sewing machine is indicated. For the sewing machine with abnormal operation state, the working personnel needs to take corresponding measures to overhaul in time.
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. 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 (7)
1. An online operation abnormality recognition system of a sewing apparatus, characterized by comprising:
the data acquisition module is used for sequentially acquiring multi-frame grayed moving images of a needle of the sewing machine in a preset time period; collecting real-time vibration signals of the sewing machine in a preset time period, and carrying out noise reduction processing on the real-time vibration signals;
the vibration period acquisition module is used for respectively carrying out difference on the first frame of moving image and each frame of moving image to obtain a plurality of frames of difference images; obtaining a segmentation threshold of each frame of difference image by using the maximum value and the minimum value of the gray value of the pixel point in each frame of difference image; binarizing each frame difference image based on the segmentation threshold value of each frame difference image to obtain a multi-frame binary image; fitting based on the number of pixel points with the gray values of a first preset value in each frame of binary image to obtain a motion change curve; the mean value of the difference value between the abscissa of every two adjacent minimum value points in the motion change curve is a vibration period;
the work abnormality recognition module is used for intercepting a template waveform of a vibration period from the acquired vibration signal of the sewing machine without abnormality by utilizing the vibration period; obtaining a plurality of waveforms to be tested with the length of one vibration period from the starting point of the real-time vibration signal; calculating the difference degree between each waveform to be detected and the template waveform, and selecting the starting point of the waveform to be detected with the minimum difference degree as an interception starting point; obtaining an identification waveform every other vibration period from the intercepted initial point; calculating the difference degree of each recognition waveform and the template waveform to form an abnormal recognition sequence; and identifying whether the sewing machine operates abnormally or not based on the elements in the abnormality identification sequence.
2. The system for recognizing abnormality in on-line operation of sewing machine according to claim 1, wherein said obtaining the division threshold value of each frame of difference image by using the maximum value and the minimum value of the gray scale value of the pixel point in each frame of difference image comprises: obtaining the maximum value and the minimum value of the gray value of a pixel point in each frame of difference image; and adding the maximum value and the minimum value of the gray value and solving the average value to obtain the segmentation threshold of each frame of difference image.
3. The system for identifying the online operation abnormality of the sewing equipment as claimed in claim 1, wherein the binarization of each frame of the difference image based on the segmentation threshold value of each frame of the difference image to obtain a multi-frame binary image comprises; and marking the gray value of the pixel point with the gray value larger than the segmentation threshold value in each frame of difference image as a first preset value, and marking the gray value of the pixel point with the gray value larger than the preset value as a second preset value to obtain a binary image after each frame of difference image is binarized.
4. The system for recognizing abnormality in online operation of a sewing machine according to claim 1, wherein the obtaining of the motion profile includes: acquiring the number of pixel points with a gray value of a first preset value in each frame of difference image and the number of frames corresponding to each frame of difference image; the abscissa of the motion change curve in the rectangular coordinate system is the number of frames corresponding to each frame of difference image, and the ordinate is the number of pixel points with a gray value of a first preset value in each frame of difference image.
5. The system for recognizing abnormality in online operation of sewing machine according to claim 1, wherein said obtaining a plurality of waveforms to be measured having a length of one vibration cycle from a start point of a real-time vibration signal comprises: setting a preset interval, and obtaining a starting point every other preset interval from the starting point of the real-time vibration signal; and obtaining the waveform to be measured corresponding to each starting point from each starting point, wherein the abscissa length of the waveform to be measured is a vibration period.
6. The system of claim 1, wherein the difference between each waveform to be measured and the template waveform is:
wherein,
representing a waveform to be measured and a templateThe degree of difference in the waveforms; />
Represents the period of vibration; />
Represents the fifth or fifth judgment of the waveform to be detected and the template waveform>
The Euclidean distance between the corresponding points; />
Representing the maximum value in Euclidean distances of all corresponding points of the waveform to be detected and the template waveform; />
Representing the minimum value in Euclidean distances of all corresponding points of the waveform to be detected and the template waveform; />
A logarithmic function with base 10 is shown.
7. The system of claim 1, wherein the identifying whether the sewing machine is operated abnormally based on the elements in the abnormality identification sequence comprises: and setting an abnormal recognition threshold, and if one element in the abnormal recognition sequence is larger than the abnormal recognition threshold, the operation of the sewing machine corresponding to the abnormal recognition sequence is abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211150174.7A CN115239711B (en) | 2022-09-21 | 2022-09-21 | Online operation abnormity identification system of sewing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211150174.7A CN115239711B (en) | 2022-09-21 | 2022-09-21 | Online operation abnormity identification system of sewing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115239711A CN115239711A (en) | 2022-10-25 |
| CN115239711B true CN115239711B (en) | 2023-04-07 |
Family
ID=83681641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211150174.7A Active CN115239711B (en) | 2022-09-21 | 2022-09-21 | Online operation abnormity identification system of sewing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115239711B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115496169B (en) * | 2022-11-17 | 2023-04-07 | 西安科技大学 | Unsafe behavior recognition system based on 5G and artificial intelligence |
| CN115792606B (en) * | 2022-11-18 | 2024-04-02 | 苏州东剑智能科技有限公司 | Water pump motor fault detection method, device, equipment and storage medium |
| CN116342870B (en) * | 2023-05-12 | 2023-07-28 | 天津市再登软件有限公司 | Method for determining working state of sewing machine in clothing factory |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926436A (en) * | 2022-05-20 | 2022-08-19 | 南通沐沐兴晨纺织品有限公司 | Defect detection method for periodic pattern fabric |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102441579B (en) * | 2010-10-13 | 2016-01-13 | 上海宝钢工业技术服务有限公司 | The on-line monitoring method of hot tandem rolling mill running status |
| EP2989979B8 (en) * | 2014-08-27 | 2022-02-16 | Wellell Inc. | Respiratory waveform recognition method and system |
-
2022
- 2022-09-21 CN CN202211150174.7A patent/CN115239711B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926436A (en) * | 2022-05-20 | 2022-08-19 | 南通沐沐兴晨纺织品有限公司 | Defect detection method for periodic pattern fabric |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115239711A (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115239711B (en) | Online operation abnormity identification system of sewing equipment | |
| CN101576956B (en) | On-line character detection method based on machine vision and system thereof | |
| CN109879005A (en) | Device for detecting belt tearing and method | |
| CN104268505A (en) | Automatic cloth defect point detection and recognition device and method based on machine vision | |
| CN111507261B (en) | Visual target positioning-based process operation quality monitoring method | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
| CN110261116A (en) | A kind of Bearing Fault Detection Method and device | |
| CN115311629B (en) | Abnormal bending precision monitoring system of bending machine | |
| CN114662594B (en) | Target feature recognition analysis system | |
| CN110738630A (en) | Training method and detection system of recursive deep learning system | |
| CN115131348A (en) | Method and system for detecting textile surface defects | |
| CN117147699B (en) | Medical non-woven fabric detection method and system | |
| CN117686516A (en) | Automatic chip appearance defect detection system based on machine vision | |
| CN117314829A (en) | Industrial part quality inspection method and system based on computer vision | |
| CN114324382A (en) | Panel terminal cleanliness detection method and panel terminal cleanliness detection device | |
| CN109903267B (en) | Method for testing network wire network degree based on image processing technology | |
| JP6915763B1 (en) | Abnormality diagnosis system and abnormality diagnosis method | |
| KR101830331B1 (en) | Apparatus for detecting abnormal operation of machinery and method using the same | |
| KR20210014452A (en) | Abnormal Data Detection System in Manufacturing Process | |
| CN117808801B (en) | Visual detection method and system for steel needle row implantation | |
| CN116342966B (en) | Rail inspection method, device, equipment and medium based on deep learning | |
| Charles et al. | Survey Paper on Visual Inspection of a Mechanical Part using Machine Learning | |
| CN118411502A (en) | Plate blank number identification system and method based on YOLOv and CRNN algorithm | |
| CN116482026A (en) | Online monitoring system and online monitoring method for surface quality of metal part |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |